JP7664611B2 - Information processing device, information processing method, and information processing program - Google Patents

Description

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

Documents such as legal documents and contracts have a significant impact on business transactions. For this reason, it is common for documents to be reviewed when they are created, but there is a problem that many of the expressions used are difficult for people other than those with specialized knowledge, such as professionals and corporate legal personnel, to understand, making reviewing them a heavy burden. In the past, there were systems that supported document reviews during the contract creation stage, such as by recognizing risks associated with modified contract terms, making decisions about whether modified contract terms are appropriate, and presenting countermeasures to risks (see, for example, Patent Document 1).

JP 2010-92227 A

However, conventional review support technologies generally judge contract terms and risks for each document type, such as transaction form. This requires labeling the advantages and disadvantages of each type and performing pattern matching, which requires large amounts of data and work to build a system, resulting in heavy financial burdens. Also, there is a risk that the review will be so detailed that it will include many comments that are inappropriate from the user's perspective.

The present invention has been made in consideration of the above problems, and aims to provide an information processing device, an information processing method, and an information processing program that enable more effective reviews.

In order to solve the above problem, the information processing device of the present invention includes a receiving unit that receives input of document data, an extraction unit that analyzes the document data and extracts a character string that is characteristic of a predetermined expression contained in the document data, and an output unit that outputs information that displays the character string extracted by the extraction unit in a manner different from other character strings contained in the document data.

The present invention provides an information processing device, an information processing method, and an information processing program that enable more effective reviews.

1 is a diagram illustrating an example of a schematic configuration of an information processing system according to an embodiment. FIG. 2 is a diagram illustrating an example of a hardware configuration of a server according to an embodiment. FIG. 2 is a diagram illustrating an example of a functional configuration of a server according to an embodiment. FIG. 2 is a diagram illustrating an example of a hardware configuration and a functional configuration of a user terminal according to the embodiment. FIG. 11 is a diagram illustrating an example of a screen displayed on a display device of a user terminal according to the embodiment. FIG. 11 is a diagram illustrating an example of a screen displayed on a display device of a user terminal according to the embodiment. 10 is a flowchart illustrating an example of information processing by a server according to the embodiment.

Hereinafter, an embodiment of the present invention will be described with reference to the drawings.
In the following embodiment, a contract is used as an example of the document, but the document is not limited to a contract. For example, the document may be a regulation document, an ordinance or treaty, a securities report, a financial statement summary, a patent specification, an application form, or various other formats.

[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. 1. The information processing system 1 includes a server 2 (information processing device) and a user terminal 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. The 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 a 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, etc. The server 2 may also include an input device (e.g., a keyboard, a touch panel, etc.) and a display device (e.g., a liquid crystal monitor, an organic EL monitor, etc.).

Communication IF200A is an interface for communicating with an external terminal (in this embodiment, user terminal 3).

The storage device 200B is, for example, a HDD or a semiconductor storage device. The storage device 200B stores information processing programs and various data used by the server 2. In the embodiment, the information processing programs and various data are stored in the storage device 200B of the server 2, but they may also be stored in an external storage device such as a USB memory or an external server connected via a network, and configured to be referenced or downloaded as needed.

For example, the various data includes morpheme analysis data used by the analysis unit 205 (described below) to perform morpheme analysis and labeling data (classification data) for labeling (classification). Data for morpheme analysis includes, for example, an idiom table, a table for splitting hiragana parts into words, a dependent word table, a hiragana independent word table, a conjugated ending table, a hiragana stem table, a special verb table, an adverb table, an information table (dictionary information corresponding to each item in the table), a connection table (a table that describes the interconnection relationships between morphemes, and data that lists, for each connection category (part of speech), the category and conjugation form of the morpheme that can appear before it), and data such as rules. Note that a known algorithm can be used for the morpheme analysis by the analysis unit 205.

The data for assigning labels includes a dictionary for assigning labels. This dictionary is data in which characteristic character strings are associated with each of predetermined expressions, such as rights and obligations, parties, conditions attached to rights/obligations, principles and exceptions, cautions, subjects of rights/obligations, laws and regulations, and cited relationships. Below, we will explain examples of characteristic character strings for each of predetermined expressions, such as rights and obligations, parties, conditions attached to rights/obligations, principles and exceptions, cautions, subjects of rights/obligations, laws and regulations, and cited relationships. Note that the following is merely an example, and it is up to the user to decide what character strings are characteristic of each of the predetermined expressions.

(1) Rights/Obligations Rights/obligations are expressions that indicate the presence or absence and the strength of rights/obligations. For example, in the following sentence, the character string in "" is a characteristic expression that indicates an obligation, and can be labeled as <Obligation: shall pay>. Note that obligations may be labeled by their type and strength (strength of obligation), such as <Obligation type: pay> and <Obligation strength: shall>. In this case, expressions of type and strength are registered in a dictionary in advance. Furthermore, periods may also be extracted. In this case, labels can be labeled as <Obligation deadline: from the day after the payment due date until repayment>. Note that labels other than rights/obligations may also be similarly subdivided and labeled by type and strength.
(Late payment charges)
Article 1 If the buyer fails to pay the purchase price, he/she shall pay to the seller late payment charges at the rate of ○% per annum from the day after the due date until payment is made.

(2) Parties The term parties is used to refer to the parties to a contract. For example, in the following sentence, the characters in "" are characteristic of expressions expressing obligations, and can be labeled as <Party A: Myself>, <Party B: Other Party>, etc.
(Late payment charges)
Article 7 If Party A fails to pay the price specified in Article 3, it must pay to Party B a late payment charge at the rate of 5 sen per day from the day after the due date until the day of full payment.

(3) Conditions attached to rights/obligations Conditions attached to rights/obligations are expressions that express the conditions for exercising the right/obligation. For example, in the following sentence, the characters in "" are characteristic expressions that express the subject of the right/obligation to be exercised, and can be labeled as <Right: Sale Retention, Condition: Payment Security, Full payment not obtained>.
(Detention of Cargo)
Article 14 Party B may retain the goods for the freight and other claims against Party A, and auction the goods "in order to receive payment therefor." However, this does not prevent Party B from claiming the remaining amount against Party A "if Party B is still unable to obtain payment in full even after auctioning the goods."

(4) Principle/Exception Principle/Exception expressions serve as guidelines for how to interpret the multiple meanings of rights/obligations. For example, in the following sentence, the characters in "" are exception expressions. Principle/Exception relationships, known as proviso, are unique to legal documents, with the principle stated in the main text and exceptions stated in the proviso. Note that the "however" in the conditions attached to the above rights/obligations does not express exceptions, so it is necessary to correctly recognize characteristic expressions such as "However, not limited to...".
(Confidentiality)
Article 21 The issuing company and the management shareholders shall not provide, disclose or leak the contents of this Agreement to any third party without the prior written consent of all investors, except for the public announcement pursuant to the previous article. "However, this shall not apply when disclosure is required by law, or under the order of a court or administrative agency."

(5) Caution Caution is an appropriate expression to have a unique meaning on its own because it does not fall under the various expressions above regarding rights/obligations, or even if it does, it is distinctive. For example, the term "prior consent" in the above principle/exception is a commonly used condition expression, but since there is a legal evaluation that it is a limited condition in general evaluation, it can be considered to be normalized and made the target of an alert.

(6) Subject of Right/Obligation The subject of a right/obligation refers to an expression that represents the subject of the right/obligation. For example, in the following sentence, the expression in "" is characteristic as an expression that represents the subject of the right/obligation, and can be labeled as <Right: Sale Retention, Subject: Cargo>. In addition, since a quantitative expression such as the amount of the object of the right/obligation often gives meaning to the strength of the right/obligation, it is preferable to make it an extraction subject of the extraction unit 206 described later so that the quantitative expression such as the amount can also be evaluated. In this case, it can be labeled as <Subject quantity: XXX>. Labels other than the subject of the right/obligation may also be labeled as extraction subjects of the extraction unit 206 described later so that the quantitative expression can be evaluated in the same manner.
(Detention of Cargo)
Article 14 Party B may retain "the goods for the freight and other claims" against Party A and auction "the goods to receive payment thereof." However, if Party B is still unable to obtain full payment even after auctioning the goods, this shall not prevent Party B from making a claim for the remaining amount against Party A.

(7) Laws and Regulations Contracts are primarily written to describe rights and obligations, but there may be characteristic expressions that are difficult to describe as either obligations or rights. However, since the number of such characteristic expressions that are difficult to describe as either obligations or rights is limited, they can be labeled by categorizing them and registering them as a dictionary (stored in the storage device 200B).
(Dispute Resolution)
Article 10 If any doubt arises regarding any matter not specified in this Agreement or the interpretation of any provision specified in this Agreement, Party A and Party B shall attempt to resolve the matter through good faith negotiations.
2. If a dispute cannot be resolved through the discussions set forth in the preceding paragraph, Party A and Party B agree that the exclusive court of first instance for all disputes relating to this Agreement shall be the XX District Court.

(8) Cited Relationships Cited relationships are expressions (cited expressions) that are quoted from other places (e.g., other specified units, etc.). For example, expressions that cite other clauses, such as "In the event of a violation of the provisions of Article X, ..." or "In accordance with Article X, ..."

The labeling dictionary also includes normalization data for normalizing the expression of character strings included in the document data. The normalization data is, for example, data that associates character strings characteristic of a specific expression with different expressions that have the same meaning as the specific expression.
Table 1 below is an example of normalization data.

As shown in Table 1, normalization data is data that associates character strings that are characteristic of a specific expression with different expressions that have the same meaning as the specific expression. By preparing such normalization data, it is possible to assign labels to character strings that are different expressions but have the same meaning as the specific expression.

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

Fig. 3 is a diagram showing an example of the functional configuration of the server 2 according to the embodiment. As shown in Fig. 3, the server 2 has functions such as a receiving unit 201 (acceptance unit), a transmitting unit 202 (output unit), a storage device control unit 203, a dividing unit 204, an analyzing unit 205, an extracting unit 206, and an evaluating unit 207. Note that the functions shown in Fig. 3 are realized by the CPU 200C executing an information processing program stored in the ROM (not shown) of the server 2.

The receiving unit 201 receives data transmitted from the user terminal 3 via the network 4. For example, the receiving unit 201 receives (accepts) document data to be reviewed.

The transmission unit 202 transmits (outputs) data to the user terminal 3 via the network 4. For example, the transmission unit 202 transmits the evaluation results by the evaluation unit 207, etc.

The storage device control unit 203 controls the storage device 200B. For example, the storage device control unit 203 writes and reads data to the storage device 200B.

The division unit 204 divides the base contract into predetermined units for the user. In an embodiment, the division unit 204 divides the contract by clause. Specifically, the division unit 204 identifies a line in the contract where the number rule "Article n" or "Article n" (n is any number (mainly an integer)) appears at the beginning of the line, which indicates the hierarchy of "articles", and divides the contract by clause, regarding that line or the line immediately preceding it as the boundary, which indicates the "article heading". Note that the predetermined unit can be any unit. For example, the target contract may be divided by clause or item. In this case, the division unit 204 identifies a line in the target contract where the number rule "n." or "(n)" or "nth" (n is any number (mainly an integer)) appears at the beginning of the line, which indicates the hierarchy of "clause" or "issue", and divides the contract by clause or issue, regarding that line or the line immediately preceding it as the boundary, and dividing the contract by clause or issue. Alternatively, the words "article", "clause", or "issue" may simply be extracted, and the contract may be divided by clause, regarding these "article", "clause", or "issue" as the boundary. Furthermore, rather than extracting and dividing the words "article", "clause", or "issue", it may be divided by judging from the text data in the consecutive lines whether they are article paragraphs, clause paragraphs, or issue paragraphs.

The analysis unit 205 performs morphological analysis for each predetermined unit based on the dictionary (morphological analysis data and labeling data) stored in the storage device 200B, and assigns labels to character strings included in each predetermined unit. Specifically, the analysis unit 205 assigns labels to character strings of predetermined expressions such as part-of-speech analysis by morphological analysis, rights and obligations by named entity extraction, parties (e.g., organization names, personal names, etc.), conditions attached to rights/obligations (e.g., date expressions, time expressions, etc.), principles and exceptions, cautions, targets of rights/obligations (e.g., monetary expressions, percentage expressions, etc.), laws and regulations, and cited relationships.

When assigning a label to a character string, the analysis unit 205 refers to normalization data in which character strings characteristic of a specific expression are associated with different expressions that have the same meaning as the specific expression, and also assigns a label to character strings that have different expressions but have the same meaning as the specific expression.

In the embodiment, the analysis unit 205 divides character strings contained in the document data into morphemes (the smallest units that have meaning in a language) using morphological analysis, but it may also divide character strings contained in the document data into any units using other methods, such as sentencepiece or n-gram.
In addition, various methods can be used for the labeling by the analysis unit 205. For example, correct answer data to which labels are assigned to character strings of parties, rights, obligations, conditions, laws and regulations, principles/exceptions, and cautions may be prepared, an AI model for automatic labeling using machine learning or deep learning may be created, and the AI model may assign labels to the character strings. Of course, the assignment of the labels by the AI model is just one example, and labels may be assigned to the character strings by other methods.

The extraction unit 206 extracts character strings relating to a predetermined expression from character strings included in the document data. Specifically, the extraction unit 206 extracts the following character strings (a1) to (a8) from character strings included in the document data based on the labels assigned by the analysis unit 205.
(a1) Character strings related to at least one of rights and obligations (rights/obligations) (a2) Character strings related to the parties involved (a3) Character strings related to conditions attached to rights/obligations (a4) Character strings related to at least one of principles and exceptions (principles/exceptions) (a5) Character strings related to cautions (a6) Character strings related to the subject of rights/obligations (a7) Character strings related to laws and regulations (a8) Character strings related to cited relationships

In the embodiment, the analysis unit 205 assigns a label to each divided unit, and extracts the above character strings (a1) to (a8) from the character string included in the document data based on the assigned label. However, for example, it is also possible to extract character strings based on character string position information (offset information) without assigning a label, or to extract the character string itself (without assigning a label) and use the extracted character string as visualization information.

The evaluation unit 207 evaluates the contract in predetermined units based on the extracted character strings and evaluation rules.
For example, the evaluation unit 207 scores the contract in a predetermined unit based on the following rules (b1) to (b4): Note that the following rules (b1) to (b4) are merely examples, and the contract may be scored based on other rules.
(b1) A score is assigned to the right/obligation. When the rights/obligations are labeled according to their type and strength (strength of the obligation), a score is assigned according to the expression of the type and strength. For example, the stronger the strength of one's own right, the higher the score may be, and the stronger the strength of the obligation, the lower the score may be. In addition, when the deadline for the right/obligation is labeled, the longer the payment date of the right, the higher the score may be, and the longer the deadline for the obligation, the lower the score may be.
(b2) Scope of rights/obligations (the weighting of the score changes depending on how many objects the rights/obligations apply to and the quantitative expression of the objects. For example, if the party to the rights is the principal, the greater the number or quantity of objects, the higher the score will be, since it is considered that the degree of advantage will be higher. Also, if the party to the rights is the other party, the greater the number or quantity of objects, the lower the score will be, since it is considered that the greater the number or quantity of objects, the lower the score will be.)
(b3) If the right/obligation is conditional, the weighting of the score will change depending on the size of the conditions (how many conditions there are). (If the party to the right is the principal, a conditional right is considered to be less advantageous than a right without conditions, so the more conditions there are, the lower the score. On the other hand, if the party to the right is the other party, a conditional right is considered to be more advantageous than a right without conditions, so the more conditions there are, the higher the score.)
(b4) For passages quoted from other passages (quoted passages), the weighting of the score is adjusted because of the large influence. A quoted passage is, for example, a clause quoted from another clause. If a passage is quoted from another clause, it can be determined to be more important because it is related to the contents of the quoted clause. For this reason, the evaluation unit 207 increases the weighting of the cited passage (increases the evaluation) when a quoted passage exists.
For example, in the case of the following document data, since Article 10 cites Article 14 (see ""), the evaluation unit 207 weights Article 14 more heavily (evaluates it more highly) in Article 10. Note that the weighting may be increased the more frequently a document is cited from other places (the number of times it has been cited).
Article 10 (Liability for infringement, etc.)
In the event that a claim, objection, or lawsuit is filed on the grounds that the Deliverables or technical results infringe the rights of a third party, Party A shall immediately notify Party B, and Party B shall either settle the matter at its own responsibility and expense, or compensate Party A for any damages incurred thereby in accordance with "Article 14." However, this shall not apply if the use of the right in question is based on instructions from Party A.
Furthermore, the evaluation unit 207 judges the contract in a predetermined unit based on the score (see FIG. 6 for examples of the score and evaluation).

In the embodiment, the evaluation unit 207 evaluates the contract based on the evaluation rules exemplified above, but for example, a standard contract (standard contract) may be evaluated in advance, and the contract to be evaluated may be evaluated relatively based on the evaluation of this standard contract. For example, the contract to be evaluated may be rated higher or lower than the standard contract depending on the difference in the expression of the extracted character string from the standard contract.

(User terminal 3)
Fig. 4 is a diagram showing an example of a hardware configuration and a functional configuration of a user terminal 3 according to an embodiment. Fig. 4(a) is a diagram showing an example of a hardware configuration of the user terminal 3, and Fig. 4(b) is a diagram showing an example of a functional configuration of the user terminal 3. The user terminal 3 is a PC (Personal Computer) or a mobile terminal (e.g., a tablet terminal), etc. As shown in Fig. 4(a), the user terminal 3 includes a communication IF 300A, a storage device 300B, an input device 300C, a display device 300D, a CPU 300E, etc.

Communication IF300A is an interface for communicating with other devices (in this embodiment, server 2).

The storage device 300B is, for example, a hard disk drive (HDD) or a semiconductor storage device (solid state drive (SSD)). 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 an IP (Internet Protocol) address, a MAC (Media Access Control) address, or the like may be used.

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

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

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

As shown in FIG. 4(b), the user terminal 3 has functions such as a receiving unit 301, a transmitting unit 302, a storage device control unit 303, an operation receiving unit 304, and a display device control unit 305. The functions shown in FIG. 4(b) are realized by the CPU 300E executing an information processing program stored in the storage device 300B.

The receiving unit 301 receives data sent from the server 2.

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

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 data.

The operation reception unit 304 receives input operations 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.

The user terminal 3 may display the data transmitted from the server 2 using, for example, a web browser, or application software may be installed on the user terminal 3 and the data transmitted from the server 2 may be displayed on this application.

(Display screen example)
5 and 6 are diagrams showing an example of a screen displayed on the display device 300D of the user terminal 3 according to the embodiment. Hereinafter, an example of a screen displayed on the display device 300D of the user terminal 3 according to the embodiment will be described with reference to Fig. 5 and 6. Note that the screens shown in Fig. 5 and 6 are merely examples, and other display modes may be used.

(Display screen G11)
5 is an example of a screen G1 presenting the analysis result of the contract. As shown in FIG. 5, the screen G1 presenting the analysis result of the contract displays the character strings extracted by the extraction unit 206 in different modes according to the labels attached to the character strings. Specifically, the character strings related to the following (a1) to (a8) are displayed in different display modes (e.g., different character colors, background colors, character sizes, fonts, etc.). In addition, the character strings extracted by the extraction unit 206 may be marked in the text, represented in a table, or represented in a tree structure or graph representation of the text, so that the character strings extracted by the extraction unit 206 and other character strings can be displayed in a distinguishable manner.
(a1) Character strings related to at least one of rights and obligations (rights/obligations) (a2) Character strings related to the parties involved (a3) Character strings related to conditions attached to rights/obligations (a4) Character strings related to at least one of principles and exceptions (principles/exceptions) (a5) Character strings related to cautions (a6) Character strings related to the subject of rights/obligations (a7) Character strings related to laws and regulations (a8) Character strings related to cited relationships

(Display screen G2)
Fig. 6 is an example of a screen G2 presenting the evaluation results of a contract. As shown in Fig. 6, the screen G1 presenting the evaluation results of a contract displays information associated with each clause, which is a predetermined unit, such as clauses, character strings related to at least one of rights and obligations (rights/obligations), character strings related to the parties, character strings related to conditions attached to the rights/obligations, character strings related to at least one of principles and exceptions (principles/exceptions), character strings related to cautions, character strings related to targets of rights/obligations, character strings related to laws and regulations, character strings related to citation relationships, and scores and judgments which are evaluations of clauses, which are predetermined units, in a form that allows a list of information associated with each clause, which is a predetermined unit.
This provides excellent visibility by allowing users to grasp at a glance the rights and obligations of each clause in the contract, the parties, the conditions attached to the rights/obligations, principles and exceptions, cautions, the subjects of the rights/obligations, laws and regulations, citation relationships, scores and judgments.

(Processing Executed in Information Processing System 1)
Fig. 7 is a flowchart showing an example of processing executed in the information processing system 1. Below, the processing executed in the information processing system 1 will be described with reference to Fig. 7, but the same components as those described with reference to Figs. 1 to 6 are given the same reference numerals and duplicated descriptions will be omitted.

(Step S101)
The user operates the input device 300C to drag and drop the contract to be reviewed. Alternatively, the user may select the contract file.

(Step S102)
The transmission unit 202 of the user terminal 3 transmits the contract data that has been dragged and dropped or selected to the server 2 .

(Step S103)
When the receiving unit 201 of the server 2 receives the contract data transmitted from the user terminal 3, the dividing unit 204 divides the base contract for the user into predetermined units.

(Step S104)
The analysis unit 205 of the server 2 performs morphological analysis for each predetermined unit and assigns a label to the character string included in each predetermined unit. As described above, the analysis unit 205 refers to the normalization data and assigns a label to the character string of an expression that is a different expression but has the same meaning as the predetermined expression.

(Step S105)
The extraction unit 206 of the server 2 extracts character strings relating to a predetermined expression from character strings included in the document data based on the analysis result (label) by the analysis unit 205 .

(Step S106)
The evaluation unit 207 of the server 2 evaluates (scores and judges) the contract in a predetermined unit based on the extracted character string and the evaluation rules.

(Step S107)
The transmission unit 202 of the server 2 transmits data for displaying screens G1 and G2 shown in Figures 5 and 6, respectively, to the user terminal 3 based on the data of the character string extracted by the extraction unit 206 and the evaluation results by the evaluation unit 207.
The receiving unit 301 of the user terminal 3 receives the data transmitted from the server 2. The display device control unit 305 of the user terminal 3 causes the display device 300D to display screens G1 and G2 shown in Fig. 5 and Fig. 6, respectively, based on the data received by the receiving unit 201.

As described above, server 2 (information processing device) according to the embodiment includes a receiving unit 201 (receiving unit) that receives input of document data, an extraction unit 206 that analyzes the document data and extracts a character string that is characteristic of a predetermined expression contained in the document data, and a transmitting unit 202 (output unit) that transmits (outputs) information for displaying the character string extracted by extraction unit 206 in a manner different from other character strings contained in the document data.
In this way, rather than labeling advantages and disadvantages for each type or performing pattern matching, the system has a simple configuration in which character strings contained in a document are extracted and the extracted character strings are displayed in a manner different from other character strings, making it possible to use the system on a variety of documents and highly versatile.

Moreover, the server 2 (information processing device) according to the embodiment includes an analysis unit 205 that analyzes character strings included in document data and assigns a classification to the analyzed character strings. An extraction unit 206 of the server 2 extracts character strings to which a classification has been assigned from character strings included in the document, and a transmission unit 202 (output unit) of the server 2 outputs information to be displayed in different modes according to the classification.
In this way, since the character string is displayed in a different manner depending on the classification assigned to the character string, it becomes possible to identify the classification of the character string.

Moreover, the server 2 (information processing device) according to the embodiment includes a dictionary in which character strings characteristic of a predetermined expression are associated with classifications of the character strings. The analysis unit 205 of the server 2 refers to the dictionary and assigns the classification to the character string.
Therefore, it is possible to label strings of expressions that are different but have the same meaning as a given expression.

In addition, the dictionary according to the embodiment includes at least
Character strings that are characteristic of any of the following relationships are stored in association with the classification of the character string: (1) rights and obligations; (2) parties; (3) conditions attached to the rights/obligations; (4) principles and exceptions; (5) cautions; (6) subjects of the rights/obligations; (7) laws and regulations; and (8) cited relationships.
In this way, a label can be assigned by matching with a dictionary.

In addition, in the dictionary according to the embodiment, character strings characteristic of a predetermined expression are stored in association with expressions that are different from the predetermined expression but have the same meaning as the predetermined expression.
Therefore, it is possible to label strings of expressions that are different but have the same meaning as a given expression.

Moreover, the server 2 (information processing device) according to the embodiment includes an evaluation unit that gives an evaluation to the extracted character string according to the assigned classification.
In this way, the system has a simple structure that assigns evaluations according to the assigned classification, so it can be used for a variety of documents and is highly versatile. In addition, since it does not require a large amount of data and work to build the system, there is little risk of the cost burden becoming heavy. In addition, it is possible to reduce the risk of the review being too detailed and including many inappropriate comments from the user's perspective.

Moreover, the evaluation unit 207 of the server 2 (information processing device) according to the embodiment changes the evaluation to be given depending on at least one of the subject and the amount of the right/obligation.
In this way, the rights/obligations can be flexibly evaluated according to at least one of the subject matter and amount of the rights/obligations, improving convenience.

Moreover, the evaluation unit 207 of the server 2 (information processing device) according to the embodiment changes the evaluation to be given depending on at least one of the number of targets of the right/obligation and the conditions attached to the right/obligation.
In this way, the rights/obligations can be flexibly evaluated depending on at least one of the number of objects of the rights/obligations and the conditions attached to the rights/obligations, thereby improving convenience.

The server 2 (information processing device) according to the embodiment includes a division unit 204 that divides a document into predetermined units. The analysis unit 205 of the server 2 assigns a classification to character strings included in the document data for each predetermined unit.
In this way, since a classification is assigned to character strings contained in document data in predetermined units, it is possible to evaluate the contract contents, etc. in predetermined units rather than the entire document, thereby improving convenience.

Moreover, the transmission unit 202 (output unit) of the server 2 (information processing device) according to the embodiment outputs information that displays the combination of character strings extracted for each predetermined unit in association with the evaluation.
In this way, information is output that correlates and displays the extracted character string combinations and evaluations for each specified unit, improving listability and identifiability (the relationship between the character string combinations and the evaluations can be understood at a glance).

[Modification of the embodiment]
Furthermore, the server 2 (information processing device) according to the embodiment may include a calculation unit that calculates a fixed amount or a billing amount according to the contract volume (document volume) evaluated by the evaluation unit 207 for the user. This allows flexible billing for the user, improving convenience.

The above-mentioned embodiments and modifications are merely examples of the implementation of the present invention, and the technical scope of the present invention should not be interpreted in a limiting manner. In other words, the present invention can be implemented in various forms without departing from its gist or main characteristics.

1 Information processing system 2 Server (information processing device)
200A Communication IF
200B Storage device 200C CPU
201 Receiving unit (receiving unit)
202 Transmission unit (output unit)
203 Storage device control unit 204 Division unit 205 Analysis unit 206 Extraction unit 207 Evaluation unit 3 User terminal 300A Communication IF
300B: storage device 300C: input device 300D: display device 300E: CPU
301 Receiving unit 302 Transmitting unit 303 Storage device control unit 304 Operation receiving unit 305 Display device control unit 4 Network

Claims (9)

a reception unit for receiving input of document data;
an analysis unit that refers to a dictionary in which character strings characteristic of a predetermined expression are associated with classifications of the character strings, analyzes character strings included in the document data, and assigns a classification to the character strings;
an extraction unit that extracts a character string to which the classification has been assigned from a character string included in the document data ;
an output unit that outputs information for displaying the character string extracted by the extraction unit in a form different from other character strings included in the document data ,
The dictionary includes at least:
(1) Rights and Obligations
(2) The parties
(3) Conditions attached to rights/obligations
(4) Principles and exceptions
(5) Caution
(6) Subject of rights/obligations
(7) Laws and regulations
(8) Citation relationships
A character string that is characteristic of any one of the above is stored in association with a classification of the character string,
The output unit is
outputting information to be displayed in different manners according to the classification;
23. An information processing apparatus comprising: The dictionary states:
A character string characteristic of a predetermined expression is stored in association with an expression that is different from the predetermined expression but has the same meaning as the predetermined expression;
2. The information processing apparatus according to claim 1 , an evaluation unit that evaluates the extracted character string according to the classification;
3. The information processing device according to claim 1, further comprising: The evaluation unit is
4. The information processing apparatus according to claim 3 , wherein the evaluation to be given is changed depending on at least one of the subject and the amount of the right/obligation. The evaluation unit is
5. The information processing apparatus according to claim 3 , wherein the evaluation to be given is changed depending on at least one of the number of objects of the right/obligation and a condition attached to the right/obligation. A division unit for dividing a document into predetermined units,
The analysis unit is
assigning the classification to character strings included in the document data for each of the predetermined units;
3. The information processing apparatus according to claim 1, wherein the information processing apparatus is a computer . The output unit is
outputting information for displaying the combination of character strings extracted for each predetermined unit in association with an evaluation;
7. The information processing apparatus according to claim 6 , a step of a receiving unit receiving input of document data;
an analysis unit referring to a dictionary in which character strings characteristic of a predetermined expression are associated with classifications of the character strings, analyzing character strings included in the document data, and assigning a classification to the character strings;
an extraction unit extracting character strings to which the classification has been assigned from character strings included in the document data ;
and outputting information for displaying the character string extracted by the extraction unit in a form different from other character strings included in the document data ,
The dictionary includes at least:
(1) Rights and Obligations
(2) The parties
(3) Conditions attached to rights/obligations
(4) Principles and exceptions
(5) Caution
(6) Subject of rights/obligations
(7) Laws and regulations
(8) Citation relationships
A character string that is characteristic of any one of the above is stored in association with a classification of the character string,
The output unit is
outputting information to be displayed in different manners according to the classification;
23. An information processing method comprising: Computer,
a reception unit for receiving input of document data;
an analysis unit that refers to a dictionary in which character strings characteristic of a predetermined expression are associated with classifications of the character strings, analyzes character strings included in the document data, and assigns classifications to the character strings;
an extraction unit that extracts character strings to which the classification has been assigned from character strings included in the document data ;
an output unit that outputs information for displaying the character string extracted by the extraction unit in a form different from other character strings included in the document data ;
The dictionary includes at least:
(1) Rights and Obligations
(2) The parties
(3) Conditions attached to rights/obligations
(4) Principles and exceptions
(5) Caution
(6) Subject of rights/obligations
(7) Laws and regulations
(8) Citation relationships
A character string that is characteristic of any one of the above is stored in association with a classification of the character string,
The output unit is
outputting information to be displayed in different manners according to the classification;
2. An information processing program comprising:

Images