JP7747826B2 - Contract processing device, contract processing method, and program - Google Patents

Description

Article 30, Paragraph 2 of the Patent Act applies. Disclosure on May 11, 2020 at https://jp.corp-sansan.com/news/2020/contract-one_launch.htm, https://twitter.com/SansanJapan/status/1259756624006152192, and https://corporate.bengo4.com/press/release/3055/

Application of Article 30, Paragraph 2 of the Patent Act Disclosure in a distribution by Bengo4.com Co., Ltd. on May 11, 2020

Article 30, paragraph 2 of the Patent Act applies. Publication by Japan Records Management Co., Ltd. and Bunshodo Co., Ltd. on May 11, 2020.

Article 30, paragraph 2 of the Patent Act applies. Publication by GMO Cloud Co., Ltd. on May 12, 2020

Article 30, paragraph 2 of the Patent Act applies. Disclosure on May 20, 2020 by BizReach Inc., Toko Metals Co., Ltd., LayerX Inc., OLTA Corporation, SoldOut Inc., Dining Innovation Investment Inc., SCRAP Inc., Legase Inc., iREP Inc., BASE Corporation, NTT PC Communications Inc., UUUM Corporation, Nestle Japan Co., Ltd., and Gurunavi Inc.

Article 30, paragraph 2 of the Patent Act applies. Disclosure by Mitsubishi Corporation Urban Development Co., Ltd. on May 28, 2020.

Article 30, paragraph 2 of the Patent Act applies. Disclosure by NTT PC Communications Corporation, JEC Corporation, and Legal Vision Corporation on July 2, 2020.

Article 30, paragraph 2 of the Patent Act applies. Disclosure by Mitsubishi UFJ Alternative Investments Co., Ltd. on July 3, 2020.

Article 30, paragraph 2 of the Patent Act applies. Disclosure by DeNA Co., Ltd. on July 9, 2020

The present invention relates to a contract processing device that processes contract information.

Conventionally, there have been contract management systems that assist in the creation of contracts (see Patent Document 1).

Japanese Patent Application Laid-Open No. 2019-185096

However, with conventional technology, it was not easy to properly manage or use contracts.

The contract processing device of this first invention is a contract processing device that includes a clue phrase storage unit that stores one or more clue phrases that serve as clues for obtaining contract attribute values, which are attribute values of a contract; a contract reception unit that receives contract information; an attribute value acquisition unit that acquires contract text from the contract information and uses one or more clue phrases to acquire from the contract text two or more contract attribute values from the contract text: contract type information, contract counterparty information, contract conclusion date information, contract effectiveness start date information, contract effectiveness end date information, contract automatic renewal information, contract termination notice deadline information, and contract amount information; and a storage support unit that performs storage support processing to store two or more contract attribute values.

This configuration makes it easier to properly manage contracts.

Furthermore, in the contract processing device of the second invention, compared to the first invention, the storage support unit stores two or more contract attribute values in association with contract information.

This configuration makes it easier to properly manage contracts.

In addition, the contract processing device of the third invention is a contract processing device that, compared to the second invention, further comprises a contract information storage unit that stores one or more pieces of contract information each having contract information associated with two or more contract attribute values obtained from the contract information; a search information receiving unit that receives search information using one or more contract attribute values; a search unit that determines contract information that matches the search information; and a contract information output unit that outputs the contract information contained in the contract information determined by the search unit.

This configuration makes it easier to properly manage contracts.

In addition, the contract processing device of the fourth invention is a contract processing device that further includes a post-processing unit that performs post-processing using one or more contract attribute values out of two or more contract attribute values for any one of the first to third inventions.

This configuration makes it easier to use contracts appropriately.

Furthermore, the contract processing device of the fifth invention is a contract processing device according to the fourth invention, in which the post-processing unit is equipped with a notification means for issuing a notification regarding contract renewal or contract termination when it is determined that the date indicated by the end date information or the date indicated by the cancellation notice deadline information is approaching so quickly that it satisfies predetermined conditions.

This configuration allows you to notify contract renewals.

The contract processing device of the sixth invention is a contract processing device according to any one of the first to fifth inventions, further comprising a classification unit that analyzes one or more inspection units of the contract text and obtains a class indicating whether the contract is unfavorable or not, a related information acquisition unit that uses the class obtained by the classification unit to obtain related information related to the class, and a related information output unit that outputs the related information.

This configuration makes it possible to classify contract contents.

Furthermore, the contract processing device of the seventh invention is a contract processing device that, compared to the sixth invention, has a classification unit that acquires a class for each of one or more inspection units of the contract text of a single piece of contract information, a related information acquisition unit that uses one or more classes acquired by the classification unit to acquire a single score, which is the score of the single piece of contract information, and a related information output unit that outputs the single score.

This configuration makes it possible to score contract contents.

Furthermore, in the contract processing device of the eighth invention, compared to the seventh invention, the related information acquisition unit includes a recommendation acquisition means that acquires recommendation information based on the inspection unit corresponding to the class when the class satisfies predetermined conditions, and the related information output unit is a contract processing device that outputs the recommendation information.

This configuration allows information to be presented that will result in an appropriate contract.

The contract processing device of the ninth invention differs from the sixth invention in that the classification unit acquires a class for each of one or more inspection units of the contract text of each of two or more pieces of contract information, the related information acquisition unit includes a comprehensive score acquisition means that acquires a comprehensive score, which is a score for two or more pieces of contract information, using the two or more classes acquired by the classification unit, and the related information output unit outputs the comprehensive score.

This configuration makes it possible to score contract contents.

Furthermore, the contract processing device of the tenth invention, compared to the eighth or ninth invention, further comprises a score storage unit in which individual scores or overall scores for contract information at a first point in time are stored, the related information acquisition unit further comprises contribution information acquisition means for acquiring contribution information relating to the difference between the individual scores or overall scores acquired from contract information at a second point in time after the first point in time and the individual scores or overall scores in the score storage unit, and the related information output unit is a contract processing device that outputs the contribution information.

With this configuration, the degree of contribution can be indicated using changes in the score for a contract.

The contract processing device of the present invention facilitates the proper management and use of contracts.

FIG. 1 is a conceptual diagram of an information system A according to a first embodiment. Block diagram of the information system A Block diagram of the contract processing device 1 A flowchart illustrating an example of the operation of the contract processing device 1 Flowchart illustrating an example of attribute value acquisition processing Flowchart illustrating an example of same-type acquisition processing Flowchart illustrating an example of the partner acquisition process A flowchart illustrating an example of the execution date acquisition process A flowchart illustrating an example of the start date and end date acquisition process A flowchart illustrating an example of the automatic update acquisition process. A flowchart illustrating an example of the cancellation notice deadline acquisition process. A flowchart illustrating an example of the transaction amount acquisition process A flowchart illustrating an example of the related information acquisition process Flowchart illustrating an example of class acquisition processing A flowchart illustrating an example of the examination unit class determination process A flowchart illustrating an example of the notification process A flowchart illustrating an example of the update process A flowchart illustrating an example of the overall score acquisition process A flowchart illustrating an example of the contribution information acquisition process A diagram showing the contract information management table Figure showing the overall score management table Overview of the computer system Block diagram of the computer system

Embodiments of a contract processing device and the like will be described below with reference to the drawings. Note that components with the same reference numerals in the embodiments perform similar operations, and therefore may not be described again.

(Embodiment 1)
In this embodiment, an information system will be described that includes a contract processing device that receives contract information, acquires two or more predetermined contract attribute values from the contract information, and outputs the values.

In this embodiment, we also describe an information system equipped with a contract processing device that stores two or more contract attribute values in association with contract information.

In this embodiment, we also describe an information system equipped with a contract processing device that can search for contract information using contract attribute values.

In this embodiment, we will also describe an information system equipped with a contract processing device that performs post-processing using one or more contract attribute values. The post-processing is, for example, the processing of contract renewal notifications using expiration information.

In this embodiment, we will also describe an information system equipped with a contract processing device that inspects the inspection units of a contract, determines a class such as whether it is unfavorable or not, and outputs that class.

In this embodiment, we also describe an information system equipped with a contract processing device that uses the class determination results to obtain a contract score.

In this embodiment, we also describe an information system equipped with a contract processing device that uses class classification results to make recommendations for the next contract.

Furthermore, in this embodiment, we will describe an information system equipped with a contract processing device that uses time-series scores to obtain and output the degree of contribution to legal work and business contribution.

Figure 1 is a conceptual diagram of information system A in this embodiment. Information system A includes a contract processing device 1 and one or more terminal devices 2. The contract processing device 1 is what is called a server device here. The contract processing device 1 is, for example, a cloud server or ASP server, but its type and installation location are not important. The terminal device 2 is a mobile device such as a smartphone, tablet device, or mobile phone, or a so-called personal computer, and its type is not important.

Figure 2 is a block diagram of information system A in this embodiment. Figure 3 is a block diagram of contract processing device 1.

The contract processing device 1 includes a storage unit 11, a receiving unit 12, a processing unit 13, and a transmitting unit 14.

The storage unit 11 includes a cue phrase storage unit 111, a learning information storage unit 112, a contract information storage unit 113, and a score storage unit 114.

The receiving unit 12 includes a contract receiving unit 121 and a search information receiving unit 122.

The processing unit 13 includes an attribute value acquisition unit 131, a storage support unit 132, a search unit 133, a post-processing unit 134, a classification unit 135, and a related information acquisition unit 136.

The post-processing unit 134 includes a notification means 1341, an update means 1342, and an indication means 1343.

The related information acquisition unit 136 includes a single score acquisition means 1361, a total score acquisition means 1362, a contribution information acquisition means 1363, and a recommendation acquisition means 1364.

The transmission unit 14 includes a related information output unit 141 and a contract information output unit 142.

The terminal device 2 includes a terminal storage unit 21, a terminal reception unit 22, a terminal processing unit 23, a terminal transmission unit 24, a terminal reception unit 25, and a terminal output unit 26.

The storage unit 11 that constitutes the contract processing device 1 stores various types of information. This information includes, for example, cue phrases (described below), learning information (described below), contract information (described below), and scores (described below).

The cue phrase storage unit 111 stores one or more cue phrases. A cue phrase is one or more terms that serve as a clue for obtaining a contract attribute value from the contract text, as described below. A cue phrase may be one term, two or more terms, a sentence pattern, or the like. A cue phrase may also be referred to as clue information.

Contract attribute values are attribute values of the contract. Contract attribute values include, for example, type information, name information, date information, automatic renewal information, and amount information. Type information is information indicating the type of contract. Examples of type information include "content certification," "debt waiver," "payment agreement," "payment of indemnity," "assignment agreement," "confidentiality obligation," "basic transaction agreement," "personal information protection agreement," and "service outsourcing agreement." Name information is information about the names of the parties to the contract. Name information includes, for example, counterparty information and self information. Counterparty information is the name of the other party to the contract, such as an organization name or organization name, or a person's name. Self information is the name of the party to the contract (the person using the contract processing device 1), such as an organization name or a person's name. Date information is information that identifies a specific date, such as conclusion date information that identifies the conclusion date of the contract, start date information that identifies the start date of the contract, end date information that identifies the end date of the contract, and cancellation notice deadline information that identifies the contract cancellation notice deadline. The cancellation notice deadline information is preferably date information, but may also be information specifying the period before the date indicated by the end date information (for example, N months or N days in advance). Automatic renewal information is information specifying whether automatic renewal will occur. Amount information is information specifying the amount related to the contract. Amount information is usually information specifying the transaction amount.

Furthermore, clue phrases include, for example, type information, party terms which are terms used to identify the parties to a contract, period patterns which are used to obtain period information, period terms which are used to obtain period information, effect terms which indicate when the contract comes into effect, termination terms which indicate when the contract ends, automatic renewal patterns which are character string patterns used to determine whether the contract is automatically renewed, deadline prediction terms which are used to detect when the contract expires, deadline terms which are used to obtain the deadline, transaction amount terms which are used to obtain the transaction amount, and class determination patterns which are used to determine the class of the inspection unit described below.

Party terms are, for example, "Party A," "Party B," and "Party C." Period patterns are, for example, "Y year M month D day to y year M month D day," "Y year M month D day to y year M month D day," (note that Y, M, D, y, m, and d are numbers). Period terms are, for example, "period." Effect terms are, for example, "effective," "become effective," or "effect." Termination terms are, for example, "end upon" or "end." Automatic renewal patterns are, for example, "the same shall apply thereafter," "follow this example," "automatically ~ renewed," or "automatically ~ extended" (note that ~ is an arbitrary character string). Deadline expectation terms are, for example, "the same shall apply thereafter," or "the same thereafter." Date terms are, for example, "X months in advance," "X months in advance," or "X days in advance" (note that X is a number). Transaction amount terms are, for example, "price" or "consideration."

Class determination patterns include, for example, "If Party A or Party B violates the terms of this Agreement by disclosing the other party's confidential information," corresponding to the "neutral" class, "If Party A violates the terms of this Agreement by disclosing the other party's confidential information," corresponding to the "adverse" class against Party A, "If Party B violates the terms of this Agreement by disclosing the other party's confidential information," corresponding to the "favorable" class against Party A, "If Party B violates the terms of this Agreement by disclosing the other party's confidential information," and corresponding to the "adverse" class against Party A, "If Party A violates the terms of this Agreement by disclosing the other party's confidential information, Party A will compensate Party A, but this does not apply to Party B."

The learning information storage unit 112 stores one or more pieces of learning information. The learning information is, for example, information used to obtain the class of the contract content. Classes will be described later. The learning information may also be a learner, which will be described later. A learner is, for example, information used when obtaining a class using a machine learning algorithm. A learner for obtaining a class is called a class learner. A learner may also be called a learning model, classifier, or classification model.

The learning information may be information used to determine whether a term is an organization name. The learning information may also be information used to determine whether a term is a person's name. The learning information may also be information used to determine whether a term is an organization name or a person's name. In such cases, the learning information is a learner that determines whether a received term is an organization name or a person's name, and is referred to as a name learner. The name learner is, for example, data constructed by the processing unit 13, described below, through machine learning learning processing.

The contract information storage unit 113 stores one or more pieces of contract information. The contract information has two or more contract attribute values. It is preferable that the two or more contract attribute values correspond to the contract information. The contract information has, for example, two or more contract attribute values associated with the contract information. It is preferable that the contract information corresponds to an organization identifier that identifies the organization to which the user who sent the contract information belongs. The organization identifier is usually information that identifies the subject of the contract. The organization identifier is, for example, a company name, company ID, department name, department ID, workplace name, workplace ID, or person's name. It is also preferable that the two or more contract attribute values are information acquired by the attribute value acquisition unit 131, which will be described later.

The score storage unit 114 stores one or more scores. The score is information that indicates the degree of disadvantage or advantage of a contract. The score may be, for example, a single score or a total score. The single score is the score of one piece of contract information. The total score is usually the total score of two or more pieces of contract information. The total score is, for example, the total score of one or more pieces of contract information for an organization. The total score is, for example, the total score of one or more pieces of contract information for an organization over a specific period of time. It is preferable that the score is information acquired by the related information acquisition unit 136, which will be described later.

The score storage unit 114 stores one or more scores in association with time information that specifies a time. The time information may be information that specifies a single point in time (June 30, 2020), or information that specifies a certain period of time (for example, fiscal year 2020, first half of 2019, etc.). A certain period of time may also be referred to as a point in time.

The receiving unit 12 receives various information and instructions. The receiving unit 12 typically receives various information and instructions from the terminal device 2. Examples of the various information and instructions include contract information and search information.

The contract reception unit 121 receives contract information. Contract information is information about a contract. For example, contract information is a PDF, text file, or image (JPEG, GIF, etc.). Contract information is typically a file. However, the data structure and data type of the contract information are not important.

It is preferable that the contract reception unit 121 accepts contract information associated with an organization identifier. Here, the organization identifier is the identifier of the organization to which the user who entered the contract information belongs.

Note that, while "acceptance" here typically refers to reception from the terminal device 2, it may also include the concept of accepting information entered from an input device such as a keyboard, mouse, or touch panel, or information read from a recording medium such as an optical disk, magnetic disk, or semiconductor memory.

The search information receiving unit 122 receives search information using one or more contract attribute values from the terminal device 2. The search information may be called a query. The structure of the search information is not important. The search information may be, for example, a query to search for contract information or a query to search for a character string within the contract information.

The processing unit 13 performs various types of processing. These types of processing include, for example, processing performed by the attribute value acquisition unit 131, storage support unit 132, search unit 133, post-processing unit 134, classification unit 135, and related information acquisition unit 136.

The processing unit 13 acquires, for example, two or more sets of training data, each of which is a pair of a sentence constituting a contract and the class of that sentence, from the storage unit 11, and performs a learning process on the two or more sets of training data using a machine learning algorithm to construct a class learner that performs multi-value classification. In this machine learning, algorithms such as deep learning, decision trees, and random forests can be used. Furthermore, multiple regression analysis and neural networks can also be used in machine learning. In other words, the machine learning algorithm is not important. Furthermore, the machine learning module can be, for example, fasttext, TensorFlow functions, MicrosoftML functions, etc.

The processing unit 13 acquires, for example, two or more pieces of training data for each class from the storage unit 11, each of which has one or more positive examples that are sentences belonging to that class and one or more negative examples that are sentences that do not belong to that class. The processing unit 13 then performs a learning process on the two or more pieces of training data using a machine learning algorithm to construct a class learner that performs binary classification. In this machine learning, algorithms such as deep learning, decision trees, random forests, and SVMs can be used. Furthermore, multiple regression analysis and neural networks can also be used in the machine learning. In other words, any machine learning algorithm can be used. Furthermore, any machine learning module can be used, such as fasttext, Tiny_svm, TensorFlow functions, MicrosoftML functions, etc.

The processing unit 13 uses a machine learning algorithm to perform a learning process on training data that includes one or more positive examples, such as one or more organization names or one or more personal names, and one or more negative examples that are neither organization names nor personal names, to construct a name learner. Note that machine learning can use algorithms such as deep learning, decision trees, random forests, SVR, and SVM. Machine learning can also use multiple regression analysis, neural networks, and the like. In other words, any machine learning algorithm can be used. The machine learning module can be, for example, Tiny_SVM, TensorFlow functions, MicrosoftML functions, and the like.

The attribute value acquisition unit 131 acquires two or more contract attribute values from the accepted contract information. Specifically, the attribute value acquisition unit 131 acquires a contract sentence, which is a sentence consisting of a set of character strings, from the contract information. Next, the attribute value acquisition unit 131 acquires one or more contract attribute values from the acquired contract sentence using one or more cue phrases in the cue phrase storage unit 111. Below, an example of how to acquire each contract attribute value will be described.
(1) How to obtain contract type information

The attribute value acquisition unit 131 acquires from the contract text a character string that matches a character string indicated by one or more pieces of type information stored in the cue phrase storage unit 111, or a character string that is close enough to satisfy a predetermined condition. The predetermined conditions are, for example, "match," "type information with the highest similarity above a threshold," or "type information with a similarity above a threshold."

The attribute value acquisition unit 131 acquires, for example, from a predetermined first range of character strings in the contract text, character strings that match character strings indicated by one or more type information stored in the cue phrase storage unit 111, or character strings that are so similar as to satisfy predetermined conditions. The first range is, for example, the first line containing the character string in the contract text, or within a predetermined amount from the beginning of the contract text (for example, within a predetermined number of lines, within a predetermined amount of data, or within a predetermined percentage from the beginning of the contract text). A character string that is so similar as to satisfy predetermined conditions has the highest similarity.

The similarity between two character strings is, for example, the Levenshtein distance, and the process of obtaining this is a well-known technique.
(2) How to obtain information about the contracting party

The attribute value acquisition unit 131, for example, searches the contract text for characters that match any of the characters in the party terms "A," "B," or "C" stored in the clue phrase storage unit 111, and acquires counterparty information that is a noun phrase within a predetermined distance from the searched characters.

The attribute value acquisition unit 131 searches for, for example, the characters "A," "B," and "C" that appear at the beginning of the contract text, and acquires from the characters "A," "B," and "C" organization names or personal names that are close enough to satisfy predetermined conditions. The attribute value acquisition unit 131 determines, for example, a noun phrase consisting of a character string and a "joint stock company" or a "limited company" to be an organization name. The attribute value acquisition unit 131 excludes the name of the principal associated with the contract information from the two or more acquired organization names or personal names, and acquires the remaining one or more organization names or personal names as the other party information. The principal's name will be referred to as principal identification information, where appropriate.

The attribute value acquisition unit 131, for example, performs morphological analysis on a predetermined second range of character strings in the contract text to acquire one or more noun phrases. Next, the attribute value acquisition unit 131 uses the name learner in the storage unit 11 to perform a prediction process using a machine learning algorithm to acquire whether each of the acquired one or more noun phrases is an organization name or a person's name. Next, the attribute value acquisition unit 131 acquires a noun phrase that has been determined to be an organization name or a person's name and whose distance to a character that matches any character in the party term stored in the clue phrase storage unit 111 is close enough to satisfy a predetermined condition, and acquires one or more names from the noun phrase excluding the person identification information as other party information.

As with the learning process, the algorithms for machine learning learning and prediction processes can be deep learning, random forest, decision tree, SVM, etc. The machine learning learning process module can be, for example, Tiny_SVM, TensorFlow functions, MicrosoftML functions, etc.

The second range is, for example, within a predetermined amount from the beginning of the contract text (for example, within a predetermined number of lines, within a predetermined amount of data, or within a predetermined percentage from the beginning of the contract text). The second range is, for example, within a predetermined amount at the end of the contract text (for example, within a predetermined number of lines from the last line, within a predetermined amount of data from the end, or within a predetermined percentage from the end of the contract text).
(3) How to obtain information on the contract conclusion date

The attribute value acquisition unit 131 detects, for example, one or more character strings in the format of date information from within the contract document (e.g., "Year, Month, Day," "Year, Month, Day," "Reiwa Year, Month, Day," etc.). Next, the attribute value acquisition unit 131 determines, for example, whether one or more characters (e.g., "desu") exist before and after the date information, and if not, acquires the date information as conclusion date information. Note that the technology for acquiring character strings in the format of date information from within a document is publicly known technology.

The attribute value acquisition unit 131 detects, for example, one or more character strings in the format of date information from within the contract text. Next, the attribute value acquisition unit 131 determines, for example, whether or not one or more characters exist before the first date information detected (the first position in the contract text), and if not, acquires the date information as the conclusion date information. Furthermore, the attribute value acquisition unit 131 determines, for example, whether or not one or more characters exist after the last date information detected (the last position in the contract text), and if not, acquires the date information as the conclusion date information.
(4) How to obtain information on the start date and end date of a contract

The attribute value acquisition unit 131 identifies, for example, from the contract text, two pieces of date information that match the period pattern "from <date information> to <date information>" or "<date information> to <date information>". Such period patterns are stored in the cue phrase storage unit 111. <date information> indicates that it can be replaced with date information. Next, the attribute value acquisition unit 131 acquires the first <date information> in the identified pattern as start date information. Furthermore, the attribute value acquisition unit 131 acquires the last <date information> in the identified pattern as end date information.

Furthermore, when the attribute value acquisition unit 131 detects, for example, two pieces of date information from the contract text that match a period pattern, and a period term (e.g., "period") that is a cue phrase exists immediately before the pattern, it acquires the first <date information> of the detected pattern as the start date information, and the latter <date information> as the end date information.

The attribute value acquisition unit 131 detects date information, for example, from within the contract text. Then, the attribute value acquisition unit 131 determines whether or not an effect term is included in the sentence containing the detected date information. Next, the attribute value acquisition unit 131 acquires the date information from the sentence determined to contain an effect term as start date information.

The attribute value acquisition unit 131 detects date information, for example, from within the contract document. Then, the attribute value acquisition unit 131 determines whether or not a sentence containing the detected date information includes a closing term (e.g., "ends with"). Next, the attribute value acquisition unit 131 acquires, as end date information, the date information from the sentence determined to include a closing term.
(5) How to obtain automatic contract renewal information

The attribute value acquisition unit 131, for example, determines whether any of the automatic renewal patterns indicating that the contract is an automatic renewal contract exists in the contract text, and if so, acquires automatic renewal information indicating automatic renewal.
(6) How to obtain contract cancellation notification deadline information

For example, when the attribute value acquisition unit 131 acquires end date information, it acquires cancellation notice deadline information as shown below. That is, the attribute value acquisition unit 131 determines whether or not a deadline expectation term (e.g., "the same applies thereafter") and a date term (e.g., "X months in advance" or "X months in advance") are present in the contract text, and if so, it acquires cancellation notice deadline information, which is the year, month, and date indicating the cancellation notice deadline, using the end date information and the date term. Note that the cancellation notice deadline information may also be a date term containing a numerical value (e.g., "1 month in advance").
(7) How to obtain contract amount information

The attribute value acquisition unit 131 acquires monetary amount expressions (e.g., "~ yen" or "~$") from the contract text as monetary amount information.

The attribute value acquisition unit 131, for example, detects monetary expressions from within the contract text. Next, the attribute value acquisition unit 131 determines whether a monetary information cue phrase (e.g., "price" or "compensation") exists close enough to the monetary expression to satisfy predetermined conditions. If a monetary information cue phrase exists, the monetary expression for that cue phrase is acquired as monetary information.

The storage support unit 132 performs storage support processing to store two or more contract attribute values. Storage support processing includes, for example, storage processing and transmission to an external device (not shown) for storage in that external device. Note that the storage destination for the two or more contract attribute values may be the contract processing device 1 or another device.

It is preferable that the storage support unit 132 stores two or more contract attribute values in association with the contract information from which the contract attribute values were obtained. Furthermore, the two or more contract attribute values may also include personal identification information.

The search unit 133 determines contract information that matches the received search information. The search unit 133 searches, for example, for contract information in the contract information storage unit 113 that matches the search information. Note that the contract information determined by the search unit 133 may be contract information stored in an external device (not shown). Furthermore, searching for contract information may also involve obtaining partial information of the contract information.

The post-processing unit 134 performs post-processing using one or more of the two or more contract attribute values corresponding to the contract information. Here, post-processing refers to, for example, processing performed by the notification unit 1341 (described below), processing performed by the update unit 1342 (described below), or processing performed by the explicit indication unit 1343 (described below).

For example, the notification means 1341 obtains expiration date information corresponding to the contract information, and if it determines that the date indicated by the expiration date information is approaching so quickly that it satisfies predetermined conditions, it issues a notification regarding the contract renewal in the contract information. The predetermined conditions are, for example, "1 month" or "60 days," and are stored in the storage unit 11.

For example, if the notification means 1341 determines that the date indicated by the cancellation notice deadline information corresponding to the contract information is approaching so quickly that it satisfies predetermined conditions, it will send a notification regarding the termination of the contract in that contract information. The predetermined conditions are, for example, "one month" or "60 days," and are stored in the storage unit 11.

Furthermore, the timing at which the notification means 1341 operates is not important. The notification means 1341 operates periodically, for example, for one or more pieces of contract information.

The update means 1342 acquires automatic renewal information corresponding to the contract information, and if the automatic renewal information indicates that automatic renewal is enabled, acquires the automatic renewal date corresponding to the automatic renewal information, acquires the next end date information corresponding to the automatic renewal date, and updates the next end date information as the end date information. It is preferable that the update means 1342 updates the next end date information as the end date information when the date indicated by the current end date information has passed, or when the date indicated by the current end date information has arrived, or when the date indicated by the cancellation notice deadline information has passed, or when the date indicated by the cancellation notice deadline information has arrived.

The indicating means 1343 performs processing to indicate information using one or more contract attribute values. For example, the indicating means 1343 acquires start date information and end date information corresponding to the contract information, acquires information on the validity period determined by the start date information and end date information, and performs processing to indicate the validity period information. Note that this indicating processing is, for example, processing to send the information to the terminal device 2. Also, this indicating processing is, for example, processing to indicate the validity period in calendar information.

The indicating means 1343 performs processing to indicate the class (described below) for each inspection unit in the contract information, for example. The indicating means 1343 performs processing to output the portion of the inspection unit corresponding to the class "unfavorable" in a highlighted manner compared to other portions. Such processing may involve, for example, changing the font of the portion of the inspection unit corresponding to the class "unfavorable" to bold, writing it in red, or underlining it.

The classification unit 135 analyzes one or more inspection units of the contract text and obtains a class for each inspection unit. An inspection unit is, for example, the entire contract information, a chapter in the contract information, an article in the contract information (for example, information categorized by a heading that matches Article X), a clause in the contract information (for example, information categorized by a numerical heading), a number in the contract information (for example, information categorized by a "(numerical)" heading), or a sentence in the contract information. A class can also be called a classification. A class is information about whether a contract is disadvantageous or not. For example, a class is one of three categories: "disadvantageous," "advantageous," or "neutral." Also, a class is one of two categories: "disadvantageous" and "not disadvantageous."

The classification unit 135, for example, obtains a class for each of one or more inspection units of the contract text of a single contract information item.

The classification unit 135, for example, obtains a class for each of one or more inspection units of the contract text of each of two or more pieces of contract information. Each of two or more pieces of contract information may be, for example, contract information for one organization or contract information for one person in charge.

The classification unit 135 may use, for example, (1) a machine learning method, or (2) a pattern matching method, etc. Examples of the two methods will be described below.
(1) Machine learning method

The classification unit 135 accepts an inspection unit or a vector obtained from the inspection unit, and uses the class learner in the learning information storage unit 112 and the inspection unit or vector to perform prediction processing using a machine learning algorithm and obtain a class.

The classification unit 135, for example, accepts an inspection unit, provides the inspection unit and a class learner capable of multi-value classification to a module that performs machine learning prediction processing, executes the module, and obtains a class.

The classification unit 135, for example, accepts a test unit, constructs a vector (e.g., a vector having the number of occurrences of each word as an element) from the test unit, provides the vector and a class learner capable of multi-value classification to a module that performs machine learning prediction processing, executes the module, and obtains a class.

The classification unit 135, for example, accepts an inspection unit, and for each class, provides the inspection unit or vector and a class learner capable of performing binary classification of the class to a module that performs machine learning prediction processing, executes the module, and determines whether or not the test unit belongs to the class. The classification unit 135 then obtains the class that it determines the test unit belongs to.

As described above, the class learner may be a learner capable of multi-value classification to acquire a class, or may be a learner for binary classification to determine whether or not a data belongs to a specific class.
(2) Pattern matching method

For each inspection unit, the classification unit 135 determines whether it contains a sentence that matches a class determination pattern used to determine a class in the storage unit 11 or has a similarity equal to or greater than a threshold. If it contains such a sentence, the classification unit 135 obtains the party identifier and class corresponding to the class determination pattern.

The related information acquisition unit 136 acquires related information using the classes acquired by the classification unit 135. Related information is information related to classes. Related information is information related to disadvantageous or advantageous contract content. Related information is the result of statistical processing of one or more classes acquired by the classification unit 135. Related information may be the class itself. The result of statistical processing is, for example, a score. The score is, for example, an individual score or an overall score. An individual score is a score that indicates the degree of dearth of disadvantageous items contained in a piece of contract information. An overall score is a score that indicates the degree of dearth of disadvantageous items in one or more pieces of contract information that meet predetermined conditions. An overall score is, for example, the overall score of two or more pieces of contract information from one organization. An overall score is, for example, the overall score of two or more pieces of contract information from one organization for one period (e.g., one fiscal year).

The related information acquisition unit 136, for example, performs statistical processing on one or more classes acquired by the classification unit 135 for each inspection unit and calculates a score. The related information acquisition unit 136, for example, performs statistical processing on one or more classes acquired by the classification unit 135 for each one or more pieces of contract information and calculates a score.

The individual score acquisition means 1361 acquires an individual score, which is the score of a piece of contract information, using one or more classes acquired by the classification unit 135 for each inspection unit in the piece of contract information.

The individual score acquisition means 1361, for example, acquires two or more inspection unit classes for a single contract information, and acquires an individual score that becomes lower the more the number of "unfavorable" classes there are. The individual score acquisition means 1361, for example, acquires two or more inspection unit classes for a single contract information, and acquires an individual score that becomes higher the more the number of "favorable" classes there are.

The individual score acquisition means 1361, for example, acquires the classes of two or more inspection units of a single contract information, calculates the proportion of "unfavorable" classes from the classes (number of "unfavorable" classes / number of inspections), and acquires a score using a decreasing function with this proportion as a parameter. The individual score acquisition means 1361, for example, acquires the classes of two or more inspection units of a single contract information, calculates the "number of "unfavorable" classes - number of "favorable" classes" from the classes, and acquires a score using a decreasing function with this difference as a parameter.

The individual score acquisition means 1361, for example, acquires two or more inspection unit classes for one contract information, and from those classes, acquires the number of "unfavorable" classes and the number of "favorable" classes. It is preferable that the fewer the "unfavorable" numbers and the more the "favorable" numbers, the higher the score acquired.

The overall score acquisition means 1362 uses two or more classes acquired by the classification unit 135 to acquire an overall score, which is the score of two or more pieces of contract information.

The individual score acquisition means 1361, for example, acquires the individual scores of two or more pieces of contract information belonging to a single group. Next, the overall score acquisition means 1362, for example, acquires a representative value (e.g., average, median, total, etc.) of the two or more individual scores as the overall score. Note that the two or more pieces of contract information belonging to a single group are, for example, contract information associated with a single organization identifier, and contract information associated with a single organization identifier and date information for a predetermined period.

The contribution information acquisition means 1363 acquires contribution information relating to the difference between the individual score acquired from the contract information at a second point in time, which is later than the first point in time, and the individual score at the first point in time stored in the score storage unit 114. The contribution information is information indicating the contribution to legal work or the contribution to business. For example, the contribution information acquisition means 1363 acquires the difference between the second individual score acquired from the contract information at the second point in time corresponding to a contract and the first individual score acquired from the contract information at the first point in time corresponding to that contract, and the greater the difference, the higher the score of the contribution information acquired.

The contribution information acquisition means 1363 acquires contribution information relating to the difference between the overall score acquired from contract information at a second time point after the first time point and the overall score at the first time point stored in the score storage unit 114. The contribution information acquisition means 1363 acquires, for example, the difference between a second overall score acquired from one or more pieces of contract information at a second time point corresponding to a single organization identifier and a first overall score acquired from one or more pieces of contract information at a first time point corresponding to that single organization identifier, and acquires contribution information with a higher score the greater the difference.

When a class satisfies predetermined conditions, the recommendation acquisition means 1364 acquires recommendation information based on the test unit corresponding to the class. Predetermined conditions include, for example, the class being "unfavorable" and the score being equal to or less than a threshold. Recommendation information is information presented to the user to improve an unfavorable contract situation, such as information that the test unit is unfavorable and information on the contract contents to overturn the test unit. For example, the unfavorable contract text and the favorable contract text are associated and stored in the storage unit 11.

The transmitter 14 transmits various types of information. The various types of information include, for example, related information.

The related information output unit 141 outputs related information. For example, the related information output unit 141 outputs one or more of the following information: individual score, overall score, recommendation information, and contribution information.

Here, output typically means transmission to terminal device 2. However, output may also be a concept that includes display on a display, projection using a projector, printing on a printer, sound output, storage on a recording medium, and delivery of processing results to other processing devices or other programs.

The contract information output unit 142 outputs all or part of the information contained in the contract information determined by the search unit 133. The contract information output unit 142 outputs, for example, the contract document information contained in the contract information determined by the search unit 133. The contract information output unit 142 may also output, for example, two or more attribute values contained in the contract information determined by the search unit 133.

Here, output typically means transmission to terminal device 2. However, output may also be a concept that includes display on a display, projection using a projector, printing on a printer, sound output, storage on a recording medium, and delivery of processing results to other processing devices or other programs.

The terminal storage unit 21 that constitutes the terminal device 2 stores various types of information. Examples of such information include a user identifier, a terminal identifier, and the organization identifier of the organization to which the user belongs. The terminal identifier may also be considered a user identifier.

The terminal reception unit 22 receives various instructions and information. Examples of such instructions and information include contract information and search information. The means for inputting such instructions and information may be a touch panel, keyboard, mouse, menu screen, or any other input method.

The device processing unit 23 performs various types of processing. For example, various types of processing include processing to configure information received by the device receiving unit 25 into data to be displayed. For example, various types of processing include processing to configure instructions received by the device accepting unit 22 into instructions to be transmitted.

The terminal transmission unit 24 transmits various instructions, information, etc. to the contract processing device 1. Examples of various instructions, information, etc. include instructions generated by the device processing unit 23 and instructions and information received by the terminal reception unit 22.

The terminal receiving unit 25 receives various information from the contract processing device 1. Examples of such information include related information, contract information, and contract attribute values.

The terminal output unit 26 outputs various types of information. Examples of such information include information accepted by the terminal acceptance unit 22, information received by the terminal reception unit 25, and information constructed by the device processing unit 23. Examples of such information include related information, contract information, and contract attribute values.

The storage unit 11, cue phrase storage unit 111, learning information storage unit 112, contract information storage unit 113, score storage unit 114, and terminal storage unit 21 are preferably non-volatile recording media, but can also be realized as volatile recording media.

The process by which information is stored in the storage unit 11, etc. is not important. For example, information may be stored in the storage unit 11, etc. via a recording medium, information transmitted via a communication line, etc. may be stored in the storage unit 11, etc., or information input via an input device may be stored in the storage unit 11, etc.

The receiving unit 12, contract acceptance unit 121, search information receiving unit 122, and terminal receiving unit 25 are typically implemented using wireless or wired communication means, but may also be implemented using means for receiving broadcasts.

The processing unit 13, attribute value acquisition unit 131, accumulation support unit 132, search unit 133, post-processing unit 134, classification unit 135, related information acquisition unit 136, notification means 1341, update means 1342, explicit indication means 1343, individual score acquisition means 1361, total score acquisition means 1362, contribution information acquisition means 1363, recommendation acquisition means 1364, and device processing unit 23 can typically be realized by a processor, memory, etc. The processing procedures of the processing unit 13, etc. are typically realized by software, and the software is recorded on a recording medium such as ROM. However, they may also be realized by hardware (dedicated circuitry). The processor may be a CPU, MPU, GPU, etc., and the type does not matter.

The transmission unit 14, related information output unit 141, contract information output unit 142, and terminal transmission unit 24 are typically implemented using wireless or wired communication means, but may also be implemented using broadcasting means.

The terminal reception unit 22 can be realized by a device driver for an input means such as a touch panel or keyboard, or control software for a menu screen.

The terminal output unit 26 may or may not include output devices such as a display or speaker. The terminal output unit 26 may be realized by driver software for an output device, or by a combination of driver software for an output device and an output device, etc.

Next, we will explain an example of the operation of information system A. First, we will explain an example of the operation of contract processing device 1 using the flowchart in Figure 4.

(Step S401) The contract reception unit 121 determines whether or not contract information associated with the organization identifier has been received from the terminal device 2. If contract information has been received, the process proceeds to step S402; if contract information has not been received, the process proceeds to step S409.

(Step S402) The attribute value acquisition unit 131 acquires the contract text from the contract information received in step S401.

(Step S403) The attribute value acquisition unit 131 acquires two or more contract attribute values using the contract text acquired in step S402. An example of the attribute value acquisition process for acquiring contract attribute values is described using the flowchart in Figure 5.

(Step S404) The storage support unit 132 stores the two or more contract attribute values acquired in step S403 in association with the received contract information and organization identifier. The storage destination is, for example, the contract information storage unit 113, but it may also be an external device. The organization identifier may also be considered to be one of the two or more contract attribute values.

(Step S405) The related information acquisition unit 136 performs related information acquisition processing. An example of the related information acquisition processing will be described using the flowchart in Figure 13.

(Step S406) The storage support unit 132 stores one or more pieces of related information acquired in step S405 in association with the contract information received in step S401.

(Step S407) The processing unit 13 determines whether to make a recommendation. If a recommendation is to be made, the process proceeds to step S408; if a recommendation is not to be made, the process returns to step S401. Note that there are no restrictions on the conditions for making a recommendation. The processing unit 13 may decide to make a recommendation if there is a test target corresponding to the class "unfavorable."

(Step S408) The related information output unit 141 transmits the recommendations obtained in step S405 to the terminal device 2 that transmitted the contract information. Return to step S401.

(Step S409) The search information receiving unit 122 determines whether search information has been received. If search information has been received, the process proceeds to step S410; if search information has not been received, the process proceeds to step S412.

(Step S410) The search unit 133 obtains information about the contract that matches the search information received in step S409.

(Step S411) The contract information output unit 142 transmits the information acquired in step S410 to the terminal device 2 that transmitted the search information. Return to step S401.

(Step S412) The post-processing unit 134 determines whether or not to perform post-processing. If post-processing is to be performed, the process proceeds to step S413; if post-processing is not to be performed, the process proceeds to step S418. Note that, for example, if an instruction to perform post-processing is received, the post-processing unit 134 determines that post-processing will be performed at a predetermined timing.

(Step S413) The post-processing unit 134 assigns 1 to counter i.

(Step S414) The post-processing unit 134 determines whether the ith contract information to be post-processed exists. If the ith contract information exists, the process proceeds to step S415; if the ith contract information does not exist, the process returns to step S401. The contract information to be post-processed may be identified by information included in the received post-processing instruction, or it may be all of the contract information stored in the storage unit 11. The post-processing unit 134 may also perform post-processing on the received contract information. The information included in the received post-processing instruction may be, for example, information that identifies the contract information, an organization identifier.

(Step S415) The notification means 1341 performs notification processing for the i-th contract information. An example of the notification processing is explained using the flowchart in Figure 16.

(Step S416) The update means 1342 performs update processing on the i-th contract information. An example of the update processing is explained using the flowchart in Figure 17.

(Step S417) The post-processing unit 134 increments counter i by 1. Return to step S414.

(Step S418) The related information acquisition unit 136 determines whether or not to perform statistical processing on the score. If statistical processing is to be performed, proceed to step S419; if statistical processing is not to be performed, return to step S401. Note that the related information acquisition unit 136 determines to perform statistical processing, for example, when an instruction to perform statistical processing is received or when a predetermined time has arrived.

(Step S419) The related information acquisition unit 136 determines whether or not to acquire a total score. If a total score is to be acquired, the process proceeds to step S420; if a total score is not to be acquired, the process proceeds to step S422. Note that the conditions for acquiring a total score are not specified.

(Step S420) The related information acquisition unit 136 acquires the overall score. An example of this overall score acquisition process is described using the flowchart in Figure 18.

(Step S421) The related information output unit 141 transmits the total score obtained in step S420 to the terminal device 2.

(Step S422) The related information acquisition unit 136 determines whether or not to acquire contribution information. If contribution information is to be acquired, proceed to step S423; if contribution information is not to be acquired, return to step S401. Note that any conditions may be met for acquiring contribution information.

(Step S423) The related information acquisition unit 136 acquires contribution information. An example of the contribution information acquisition process is described using the flowchart in Figure 19.

(Step S424) The related information output unit 141 transmits the contribution information acquired in step S423 to the terminal device 2. Return to step S401.

In the flowchart in Figure 4, processing ends when the power is turned off or an interrupt occurs to end processing.

Next, the attribute value acquisition process in step S403 will be explained using the flowchart in Figure 5.

(Step S501) The attribute value acquisition unit 131 acquires type information from the contract document to be processed. An example of this type acquisition process is described using the flowchart in Figure 6.

(Step S502) The attribute value acquisition unit 131 acquires counterparty information from the contract document being processed. An example of this counterparty acquisition process is described using the flowchart in Figure 7.

(Step S503) The attribute value acquisition unit 131 acquires the conclusion date information from the contract document being processed. An example of this conclusion date acquisition process is described using the flowchart in Figure 8.

(Step S504) The attribute value acquisition unit 131 acquires start date information and end date information from the contract document to be processed. An example of this start date/end date acquisition process is described using the flowchart in Figure 9.

(Step S505) The attribute value acquisition unit 131 acquires automatic update information from the contract document being processed. An example of this automatic update acquisition process is described using the flowchart in Figure 10.

(Step S506) The attribute value acquisition unit 131 acquires cancellation notice deadline information from the contract document being processed. An example of this cancellation notice deadline acquisition process is described using the flowchart in Figure 11.

(Step S507) The attribute value acquisition unit 131 acquires transaction amount information from the contract document being processed. An example of this transaction amount acquisition process is described using the flowchart in Figure 12.

Next, an example of the type acquisition process in step S501 will be explained using the flowchart in Figure 6.

(Step S601) The attribute value acquisition unit 131 acquires the string of characters in the header line of the target contract document.

(Step S602) The attribute value acquisition unit 131 assigns 1 to counter i.

(Step S603) The attribute value acquisition unit 131 determines whether the i-th type information exists in the cue phrase storage unit 111. If the i-th type information exists, the process proceeds to step S604; if the i-th type information does not exist, the process proceeds to step S609.

(Step S604) The attribute value acquisition unit 131 acquires the similarity between the character string acquired in step S601 and the i-th type information.

(Step S605) The attribute value acquisition unit 131 determines whether the two character strings match based on the similarity acquired in step S604. If they match, the process proceeds to step S606; if they do not match, the process proceeds to step S607.

(Step S606) The attribute value acquisition unit 131 stores the i-th type information as the type information, which is the contract attribute value of the target contract information. It then returns to the upper-level processing.

(Step S607) The attribute value acquisition unit 131 temporarily stores the similarity in a buffer (not shown) in association with the i-th type information.

(Step S608) The attribute value acquisition unit 131 increments the counter i by 1. Return to step S603.

(Step S609) The attribute value acquisition unit 131 accumulates the type information whose similarity satisfies the condition as type information, which is the contract attribute value of the target contract information. It then returns to higher-level processing. Note that the condition may be, for example, "the similarity is maximum" or "the similarity is maximum and is equal to or greater than the threshold value."

Next, an example of the partner acquisition process in step S502 will be explained using the flowchart in Figure 7.

(Step S701) The attribute value acquisition unit 131 acquires a predetermined second range of character strings from the contract document to be processed.

(Step S702) The attribute value acquisition unit 131, for example, performs morphological analysis on the character string acquired in step S701 to acquire one or more noun phrases.

(Step S703) The attribute value acquisition unit 131 assigns 1 to counter i.

(Step S704) The attribute value acquisition unit 131 determines whether the i-th noun phrase is present among the noun phrases acquired in step S702. If the i-th noun phrase is present, the process proceeds to step S705; if the i-th noun phrase is not present, the process returns to the upper level processing.

(Step S705) The attribute value acquisition unit 131 uses the name learner in the storage unit 11 to determine, through machine learning prediction processing, whether the i-th noun phrase is an organization name or a person's name.

(Step S706) If the result of the determination in step S705 is an organization name or a person's name, the attribute value acquisition unit 131 proceeds to step S707; if not, it proceeds to step S712.

(Step S707) The attribute value acquisition unit 131 acquires a string (a sentence, or two or more terms) that includes the i-th noun phrase and is within a predetermined distance from the i-th noun phrase.

(Step S708) The attribute value acquisition unit 131 determines whether the character string acquired in step S707 contains a party term (e.g., "A" or "B"). If it does, the process proceeds to step S709; if it does not, the process proceeds to step S712.

(Step S709) The attribute value acquisition unit 131 acquires, for example, personal identification information associated with the contract information to be processed. Next, the attribute value acquisition unit 131 determines whether the i-th noun phrase matches the personal identification information. If they match, the process proceeds to step S712; if they do not match, the process proceeds to step S710.

(Step S710) The attribute value acquisition unit 131 determines whether the i-th noun phrase has already been registered. If it has already been registered, proceed to step S712; if it has not already been registered, proceed to step S711.

(Step S711) The attribute value acquisition unit 131 registers the i-th noun phrase as party information. Note that registration means storing the noun phrase in association with the contract information as one of the contract attribute values. Here, it is preferable for the attribute value acquisition unit 131 to store the party information in pairs with the party term.

(Step S712) The attribute value acquisition unit 131 increments the counter i by 1. Return to step S704.

Next, an example of the conclusion date acquisition process in step S503 will be explained using the flowchart in Figure 8.

(Step S801) The attribute value acquisition unit 131 acquires all date information from the target contract document, paired with location information that identifies that location. Location information may be, for example, an offset or line number, but any information that can identify a location within the contract document will do. Furthermore, the technology for acquiring date information and location information having a date structure (such as "year/month/day" or "xx/xx/xx") from a document is publicly known.

(Step S802) The attribute value acquisition unit 131 assigns 1 to counter i.

(Step S803) The attribute value acquisition unit 131 determines whether the i-th date information exists among the date information acquired in step S801. If the i-th date information exists, the process proceeds to step S804; if the i-th date information does not exist, the process returns to the upper level processing.

(Step S804) The attribute value acquisition unit 131 temporarily stores the i-th date information and location information pair.

(Step S805) The attribute value acquisition unit 131 determines whether the i-th date information is the first date information among the date information acquired in step S801. If it is the first date information, proceed to step S807; if it is not the first date information, proceed to step S806.

(Step S806) The attribute value acquisition unit 131 determines whether the i-th date information is the last date information among the date information acquired in step S801. If it is the last date information, proceed to step S807; if it is not the last date information, proceed to step S809.

(Step S807) The attribute value acquisition unit 131 determines whether any wording (e.g., "is") exists before or after the i-th date information. If such wording exists, the process proceeds to step S808; if such wording does not exist, the process proceeds to step S809.

(Step S808) The attribute value acquisition unit 131 stores the i-th date information as contract conclusion date information, in association with the contract information.

(Step S809) The attribute value acquisition unit 131 increments the counter i by 1. Return to step S803.

Next, an example of the start and end date acquisition process in step S504 will be explained using the flowchart in Figure 9.

(Step S901) The attribute value acquisition unit 131 assigns 1 to counter i.

(Step S902) The attribute value acquisition unit 131 determines whether the i-th date information exists among the date information acquired in step S801. If the i-th date information exists, the process proceeds to step S903; if the i-th date information does not exist, the process returns to the upper level processing.

(Step S903) The attribute value acquisition unit 131 acquires a specified range of character strings following the i-th date information. Note that the specified range refers to, for example, the same line as the i-th date information, a sentence containing the i-th date information, or a clause containing the i-th date information.

(Step S904) The attribute value acquisition unit 131 assigns 1 to counter j.

(Step S905) The attribute value acquisition unit 131 determines whether the jth period pattern exists in the cue phrase storage unit 111. If the jth period pattern exists, the process proceeds to step S906; if not, the process proceeds to step S912.

(Step S906) The attribute value acquisition unit 131 determines whether the character string acquired in step S903 is an expression of the jth period pattern. If it is an expression of the jth period pattern, the process proceeds to step S907; if it is not an expression of the jth period pattern, the process proceeds to step S911.

(Step S907) The attribute value acquisition unit 131 acquires a specified range of character strings before the i-th date information. Note that the specified range may be, for example, a noun phrase, a sentence, a line, etc.

(Step S908) The attribute value acquisition unit 131 determines whether a time period term (e.g., "period") is present in the character string acquired in step S907. If a time period term is present, the process proceeds to step S909; if a time period term is not present, the process proceeds to step S911.

(Step S909) The attribute value acquisition unit 131 acquires the first date information in the string that matches the expression of the jth period pattern as start date information and stores it in association with the contract information.

(Step S910) The attribute value acquisition unit 131 acquires the later date information in the character string that matches the expression of the jth period pattern as end information, associates it with the contract information, and stores it. Then it returns to the upper-level processing.

(Step S911) The attribute value acquisition unit 131 increments counter j by 1. Return to step S905.

(Step S912) The attribute value acquisition unit 131 determines whether the character string acquired in step S903 contains an effect term (e.g., "effect"). If an effect term is included, the process proceeds to step S913; if an effect term is not included, the process proceeds to step S914.

(Step S913) The attribute value acquisition unit 131 acquires the i-th date information as start date information and stores it in association with the contract information.

(Step S914) The attribute value acquisition unit 131 determines whether the character string acquired in step S903 contains an ending term (e.g., "ends with"). If an ending term is included, the process proceeds to step S915; if an ending term is not included, the process proceeds to step S916.

(Step S915) The attribute value acquisition unit 131 acquires the i-th date information as end information and stores it in association with the contract information.

(Step S916) The attribute value acquisition unit 131 increments the counter i by 1. Return to step S902.

Next, an example of the automatic update acquisition process in step S505 will be explained using the flowchart in Figure 10.

(Step S1001) The attribute value acquisition unit 131 assigns 1 to counter i.

(Step S1002) The attribute value acquisition unit 131 determines whether the i-th automatic update pattern exists in the cue phrase storage unit 111. If the i-th automatic update pattern exists, the process proceeds to step S1003; if the i-th automatic update pattern does not exist, the process returns to the upper-level process.

(Step S1003) The attribute value acquisition unit 131 acquires the i-th automatic update pattern from the cue phrase storage unit 111.

(Step S1004) The attribute value acquisition unit 131 assigns 1 to counter j.

(Step S1005) The attribute value acquisition unit 131 determines whether the jth inspection unit exists in the contract document. If the jth inspection unit exists, the process proceeds to step S1006; if not, the process proceeds to step S1009. Note that the inspection unit may be a sentence, a clause, etc.

(Step S1006) The attribute value acquisition unit 131 determines whether a character string matching the i-th automatic update pattern exists in the j-th inspection unit. If it exists, the process proceeds to step S1007; if it does not exist, the process proceeds to step S1008.

(Step S1007) The attribute value acquisition unit 131 assigns "Yes" to the contract attribute value "Automatic Update Information." The contract attribute value "Automatic Update Information" is stored in association with the contract information.

(Step S1008) The attribute value acquisition unit 131 increments counter j by 1. Return to step S1005.

(Step S1009) The attribute value acquisition unit 131 increments the counter i by 1. Return to step S1002.

In the flowchart of FIG. 10, if the determination result in step S1002 is "No," the attribute value acquisition unit 131 may assign "None" to the contract attribute value "Automatic Update Information" and store the contract attribute value in association with the contract information.

Next, an example of the cancellation notification deadline acquisition process in step S506 will be explained using the flowchart in Figure 11.

(Step S1101) The attribute value acquisition unit 131 determines whether end date information for the target contract information has been acquired. If end date information has been acquired, the process proceeds to step S1102; if end date information has not been acquired, the process returns to the upper-level process.

(Step S1102) The attribute value acquisition unit 131 assigns 1 to counter i.

(Step S1103) The attribute value acquisition unit 131 determines whether the i-th deadline-anticipating term exists in the clue phrase storage unit 111. If the i-th deadline-anticipating term exists, the process proceeds to step S1104; if not, the process returns to the upper-level process.

(Step S1104) The attribute value acquisition unit 131 acquires the i-th deadline prediction term from the clue phrase storage unit 111.

(Step S1105) The attribute value acquisition unit 131 assigns 1 to counter j.

(Step S1106) The attribute value acquisition unit 131 determines whether the jth inspection target exists in the target contract document. If the jth inspection target exists, the process proceeds to step S1107; if the jth inspection target does not exist, the process proceeds to step S1115.

(Step S1107) The attribute value acquisition unit 131 determines whether the i-th deadline-anticipating term is present in the j-th test target. If the i-th deadline-anticipating term is present, the process proceeds to step S1108; if the i-th deadline-anticipating term is not present, the process proceeds to step S1114.

(Step S1108) The attribute value acquisition unit 131 acquires character strings surrounding the ith deadline-predicting term in the jth test target, and that are at a distance from the ith deadline-predicting term that satisfies a predetermined condition.

(Step S1109) The attribute value acquisition unit 131 assigns 1 to counter k.

(Step S1110) The attribute value acquisition unit 131 determines whether the kth date term exists in the clue phrase storage unit 111. If the kth date term exists, proceed to step S1111; if not, proceed to step S1114.

(Step S1111) The attribute value acquisition unit 131 determines whether the kth deadline term is present in the character string acquired in step S1108. If the kth deadline term is present, the process proceeds to step S1112; if the kth deadline term is not present, the process proceeds to step S1113.

(Step S1112) The attribute value acquisition unit 131 acquires the date information for the location corresponding to the kth date term. The attribute value acquisition unit 131 also acquires the cancellation notice deadline information using the end date information and the deadline information. The process returns to the upper level processing. For example, if the end date information is "July 31, 2020" and the deadline information is "two months ago," the attribute value acquisition unit 131 acquires the cancellation notice deadline information "May 31, 2020."

(Step S1113) The attribute value acquisition unit 131 increments the counter k by 1. Return to step S1110.

(Step S1114) The attribute value acquisition unit 131 increments counter j by 1. Return to step S1106.

(Step S1115) The attribute value acquisition unit 131 increments the counter i by 1. Return to step S1103.

Next, an example of the transaction amount acquisition process in step S507 will be explained using the flowchart in Figure 12.

(Step S1201) The attribute value acquisition unit 131 assigns 1 to counter i.

(Step S1202) The attribute value acquisition unit 131 determines whether the i-th inspection unit exists in the contract document. If the i-th inspection unit exists, the process proceeds to step S1203; if not, the process returns to the upper level processing. Note that the inspection unit may be, for example, a sentence, a clause, etc.

(Step S1203) The attribute value acquisition unit 131 determines whether the i-th inspection unit contains a monetary expression (such as "numeric string 'yen'" or "numeric string '$'"). If it contains a monetary expression, proceed to step S1204; if it does not, proceed to step S1210.

(Step S1204) The attribute value acquisition unit 131 acquires surrounding character strings that are close enough to the monetary amount expression to satisfy predetermined conditions.

(Step S1205) The attribute value acquisition unit 131 assigns 1 to counter j.

(Step S1206) The attribute value acquisition unit 131 determines whether the jth transaction amount term exists in the cue phrase storage unit 111. If the ith transaction amount term exists, the process proceeds to step S1207; if the ith transaction amount term does not exist, the process proceeds to step S1210.

(Step S1207) The attribute value acquisition unit 131 determines whether the jth transaction amount term is included in the string acquired in step S1204. If the jth transaction amount term is included, the process proceeds to step S1208; if the jth transaction amount term is not included, the process proceeds to step S1209.

(Step S1208) The attribute value acquisition unit 131 acquires the acquired amount expression as transaction amount information and stores it in association with the contract information. It then returns to the upper-level processing.

(Step S1209) The attribute value acquisition unit 131 increments counter j by 1. Return to step S1206.

(Step S1210) Increment counter i by 1. Return to step S1202.

Next, an example of the related information acquisition process in step S405 will be explained using the flowchart in Figure 13.

(Step S1301) The single score acquisition means 1361 assigns 1 to counter i. The single score acquisition means 1361 also assigns 0 to the number of each class. Each class is, for example, "unfavorable," "favorable," or "neutral."

(Step S1302) The unit score acquisition means 1361 determines whether the i-th inspection unit exists in the contract document to be inspected. If the i-th inspection unit exists, proceed to step S1303; if the i-th inspection unit does not exist, proceed to step S1309.

(Step S1303) The unit score acquisition means 1361 acquires the i-th inspection unit from the contract document.

(Step S1304) The unit score acquisition means 1361 acquires the class of the i-th test unit. An example of this class acquisition process is described using the flowchart in Figure 14.

(Step S1305) The single score acquisition means 1361 increments the number corresponding to the class acquired in step S1304 by 1.

(Step S1306) The single score acquisition means 1361 determines whether the class acquired in step S1304 has a value of "unfavorable." If the class has a value of "unfavorable," proceed to step S1307; if the class does not have a value of "unfavorable," proceed to step S1308.

(Step S1307) The individual score acquisition means 1361 acquires the i-th inspection unit. The individual score acquisition means 1361 also acquires recommendation information corresponding to the i-th inspection unit. The individual score acquisition means 1361 then associates the i-th inspection unit with the recommendation information and temporarily stores it in a buffer (not shown).

The unit score acquisition means 1361 acquires from the storage unit 11 recommendation information that is paired with a string of adverse clauses whose similarity to the i-th inspection unit is large enough to satisfy predetermined conditions. In such a case,

(Step S1308) The single score acquisition means 1361 increments the counter i by 1. Return to step S1302.

(Step S1309) The individual score acquisition means 1361 calculates the individual score using the number of each class.

(Step S1310) The individual score acquisition means 1361 stores the individual score acquired in step S1309 in association with the contract information.

(Step S1311) The single score acquisition means 1361 uses the recommendation information acquired in step S1307 to construct the recommendation information to be accumulated.

(Step S1312) The individual score acquisition means 1361 stores the recommendation information constructed in step S1311 in association with the contract information. The process returns to the upper-level processing.

Next, an example of the class acquisition process in step S1304 will be explained using the flowchart in Figure 14.

(Step S1401) The classification unit 135 acquires the person's party term (e.g., "A").

(Step S1402) The classification unit 135 obtains the party word of the subject from the target test unit.

(Step S1403) The classification unit 135 determines the class of the subject in the inspection unit. An example of the inspection unit class determination process is described using the flowchart in Figure 15.

(Step S1404) The classification unit 135 determines whether the subject's party term in the test unit matches the person's party term. If they match, the process returns to the upper level process; if they do not match, the process proceeds to step S1405.

(Step S1405) The classification unit 135 determines whether the class determined in step S1403 is "disadvantageous." If it is "disadvantageous," proceed to step S1406; if it is not "disadvantageous," proceed to step S1407.

(Step S1406) The classification unit 135 assigns "Advantageous" to the class. The process returns to the upper level processing.

(Step S1407) The classification unit 135 determines whether the class determined in step S1403 is "advantageous." If it is "advantageous," the process proceeds to step S1408; if it is not "advantageous," the process returns to the upper level processing.

(Step S1408) The classification unit 135 assigns "disadvantage" to the class. The process returns to the upper level processing.

Next, an example of the inspection unit class determination process in step S1403 will be explained using the flowchart in Figure 15.

(Step S1501) The classification unit 135 assigns 1 to counter i.

(Step S1502) The classification unit 135 determines whether the i-th class determination pattern exists in the cue phrase storage unit 111. If it exists, the process proceeds to step S1503; if it does not exist, the process proceeds to step S1508.

(Step S1503) The classification unit 135 retrieves the i-th class determination pattern from the cue phrase storage unit 111.

(Step S1504) The classification unit 135 compares the test object with the i-th class determination pattern.

(Step S1505) The classification unit 135 determines whether the test object and the i-th class determination pattern are similar enough to satisfy predetermined conditions. If the predetermined conditions are satisfied, the process proceeds to step S1506; if the predetermined conditions are not satisfied, the process proceeds to step S1507.

(Step S1506) The classification unit 135 obtains the class that pairs with the i-th class determination pattern. The process returns to the upper-level process.

(Step S1507) The classification unit 135 increments the counter i by 1. Return to step S1502.

(Step S1508) The classification unit 135 assigns the value "Neutral" to the class.

In the flowchart of Figure 15, the classification unit 135 may obtain the class for each test unit using the machine learning method described above.

Next, an example of the notification process in step S415 will be explained using the flowchart in Figure 16.

(Step S1601) The notification means 1341 obtains date information indicating today's date from a clock (not shown).

(Step S1602) The notification means 1341 obtains the end date information paired with the contract information to be processed.

(Step S1603) The notification means 1341 determines whether the end date information satisfies the predetermined notification conditions for the date information indicating today's date. If the conditions are met, the process proceeds to step S1604; if the conditions are not met, the process proceeds to step S1606.

(Step S1604) The notification means 1341 acquires notification information corresponding to the end date information. Note that the notification information or a template for the notification information is stored, for example, in the storage unit 11. The notification information or a template for the notification information is stored, for example, in the storage unit 11 in a pair with information specifying the end date information.

(Step S1605) The notification means 1341 sends the notification information acquired in step S1604. Note that information specifying the destination (e.g., email address, telephone number, etc.) is stored, for example, in association with the target contract information.

(Step S1606) The notification means 1341 obtains the contract cancellation deadline information that is paired with the contract information to be processed.

(Step S1607) The notification means 1341 determines whether the contract termination deadline information satisfies the predetermined notification conditions for the date information indicating today's date. If the conditions are met, the process proceeds to step S1608; if the conditions are not met, the process returns to the upper level processing.

(Step S1608) The notification means 1341 acquires notification information corresponding to the contract cancellation deadline information. Note that the notification information or a template for the notification information is stored, for example, in the storage unit 11. The notification information or a template for the notification information is stored, for example, in the storage unit 11 in a pair with information specifying the contract cancellation deadline information.

(Step S1609) The notification means 1341 sends the notification information acquired in step S1608. Note that information specifying the destination (e.g., email address, telephone number, etc.) is stored, for example, in association with the target contract information.

Next, an example of the update process in step S416 will be explained using the flowchart in Figure 17.

(Step S1701) The update means 1342 obtains automatic update information that pairs with the contract information to be processed.

(Step S1702) The update means 1342 determines whether the information acquired in step S1701 indicates an automatic update. If the information indicates an automatic update, the process proceeds to step S1703; if the information does not indicate an automatic update, the process returns to the upper-level process.

(Step S1703) The update means 1342 obtains date information indicating today's date from a clock (not shown).

(Step S1704) The update means 1342 obtains the end date information that pairs with the contract information to be processed.

(Step S1705) The update means 1342 determines whether the end date information acquired in step S1704 satisfies predetermined conditions with respect to the date information indicating today's date. If the conditions are met, the process proceeds to step S1706; if the conditions are not met, the process returns to the upper-level process.

(Step S1706) The update means 1342 acquires end date information that specifies the next end date. Note that the end date information that specifies the next end date is, for example, one year after the stored end date information. Also, the end date information that specifies the next end date is, for example, N years after the stored end date information. "N years later" is information that is written in the contract information and is information that specifies the time to review the contract.

(Step S1707) The update means 1342 overwrites the old end date information with the end date information obtained in step S1706. The process returns to the upper level process.

In the flowchart of FIG. 17, it is determined whether the end date information satisfies predetermined conditions with respect to date information indicating today's date. However, the update means 1342 may also determine whether the cancellation notice deadline information satisfies predetermined conditions with respect to date information indicating today's date.

Next, an example of the total score acquisition process in step S420 will be explained using the flowchart in Figure 18.

(Step S1801) The total score acquisition means 1362 reads out the individual scores paired with all target contract information.

(Step S1802) The total score acquisition means 1362 acquires a representative value of one or more individual scores acquired in step S1801. The process returns to the higher-level process. This representative value is the total score in this case.

Next, an example of the contribution information acquisition process in step S423 will be explained using the flowchart in Figure 19.

(Step S1901) The contribution information acquisition means 1363 acquires past scores for comparison.

(Step S1902) The contribution information acquisition means 1363 acquires the score of interest. The score of interest is a score corresponding to contract information that is newer than the past score to be compared.

(Step S1903) The contribution information acquisition means 1363 calculates the difference between the score of interest and the past score of the comparison target. Next, the contribution information acquisition means 1363 uses this difference to acquire contribution information. Then, the process returns to the upper level process.

In the flowchart of Figure 19, the contribution information acquisition means 1363 typically uses the overall score, but it may also use a single score corresponding to one piece of contract information.

Next, an example of the operation of the terminal device 2 will be described. The terminal reception unit 22 receives various instructions and information from the user (for example, instructions to obtain contract information, search information, individual scores, total scores, or contribution information). Next, the terminal processing unit 23 composes the instructions received by the terminal reception unit 22 into instructions to be transmitted. Next, the terminal transmission unit 24 transmits the various instructions and information to the contract processing device 1.

The terminal receiving unit 25 also receives various information (e.g., related information, contract information, contract attribute values, individual scores, overall scores, and contribution information) from the contract processing device 1. Next, the terminal processing unit 23 composes the various information into information to be displayed. Next, the terminal output unit 26 outputs the information.

The specific operation of information system A in this embodiment will be described below. A conceptual diagram of information system A is shown in Figure 1.

The cue phrase storage unit 111 of the contract processing device 1 stores a large amount of the above-mentioned clue information. The clue information is information that serves as a clue for obtaining contract attribute values from the contract text.

Furthermore, it is assumed that the learning information storage unit 112 stores the above-mentioned name learner and class learner. The name learner is a learner for determining whether a received term is an organization name or a person's name. The class learner is a learner for determining the class of the received test unit (here, one of "unfavorable," "favorable," or "neutral").

It is also assumed that the contract information storage unit 113 stores a contract information management table with the structure shown in Figure 20. The contract information management table is a table that manages information related to the contracts of each organization or individual. The contract information management table is a table that manages records that have an "ID," "user identifier," "organization identifier," "contract information," and "individual score." "ID" is information that identifies a record. "Contract information" here includes "type information," "counterparty information," "conclusion date information," "start date information," "end date information," "cancellation notice deadline information," "automatic renewal information," "amount information," and "file name." "File name" is the name of the file containing the contract information. It is assumed that the file identified by "file name" is stored in the contract information storage unit 113.

The score storage unit 114 is also assumed to store a total score management table with the structure shown in Figure 21. The total score management table is a table that manages total scores related to contracts for each organization or individual and for each period. The total score management table is a table that manages records that have an "ID," "organization identifier," "period identifier," and "total score." The "ID" is information that identifies the record. The "period identifier" is information that specifies the period of the contract information used to calculate the total score. In this case, the "period identifier" is information that specifies the fiscal year. In this case, the "total score" is, for example, contract information that pairs with the "organization identifier," and is the total score obtained using the contract information for the contract conclusion date for the period indicated by the "period identifier."

Furthermore, the storage unit 11 stores a user information management table that stores two or more pieces of user information each having a user identifier and an organization identifier.

Now, let's assume that user "U001" uses terminal device 2 to send the contract in "fileA.pdf" to contract processing device 1.

Next, the contract processing device 1 receives "fileA.pdf" and the user identifier "U001". Next, the contract processing device 1 obtains the organization identifier "Corporation A", which pairs with the user identifier "U001", from the user information management table. Furthermore, it is assumed that the contract processing device 1 has obtained various contract attribute values (type information, counterparty information, ... automatic update information) of the record with ID=1 in the table of Figure 20 from "fileA.pdf" using the clue information in the clue phrase storage unit 111 and the name learner in the learning information storage unit 112 through the processing described above (for example, the processing described in Figure 4, etc.). On the other hand, it is assumed that the contract processing device 1 was unable to obtain amount information from "fileA.pdf".

Furthermore, through the above-described processing, the contract processing device 1 uses a class learner to determine a class (here, "unfavorable," "favorable," or "neutral") for each inspection unit contained in "fileA.pdf" using a machine learning algorithm, and obtains the number of each "unfavorable," "favorable," and "neutral." Next, the contract processing device 1 substitutes the number of each class into the arithmetic formula "single score = f (number of unfavorable, number of favorable, number of neutral)" or the arithmetic formula "single score = f (number of unfavorable, number of favorable)," executes the arithmetic formula, and obtains the single score of "fileA.pdf." Note that the arithmetic formula is a function that results in a higher score the more unfavorable numbers there are, and a higher score the fewer favorable numbers there are. Also, here, the arithmetic formula is a function that outputs the single score as an integer between 0 and 100. Then, the contract processing device 1 uses the arithmetic formula to calculate a single score of "75" for "fileA.pdf."

Next, the contract processing device 1 uses the various acquired information to create the record with "ID=1" in Figure 20, and stores it in the contract information storage unit 113 along with the entity of "fileA.pdf."

The contract processing device 1 also sends recommendation information constructed using the single score "75" and the inspection unit corresponding to "unfavorable" (for example, "The contract content of "<inspection unit>" is unfavorable. You may want to consider amending the contract to improve it from next time onwards.") to the terminal device 2 of user "U001". Note that here, the explicit indication means 1343 of the contract processing device 1 may construct contract information that highlights the inspection unit corresponding to "unfavorable" in the contract information (for example, by writing it in red), and the contract processing device 1 may send the amended contract information to the terminal device 2. Note that <inspection unit> is a variable that contains the character string of the inspection unit.

Next, terminal device 2 receives and outputs the single score "75" and the recommendation information.

The contract processing device 1 performs the above contract information storage process each time contract information is received.

The contract processing device 1 performs notification processing on the record with ID=1 in Figure 20, as follows: In other words, the notification means 1341 of the contract processing device 1 acquires date information indicating today's date, "April 1, 2020," from a clock (not shown). The notification means 1341 also acquires the cancellation notice deadline information, "May 1, 2020," that pairs with the contract information with ID=1 in the table in Figure 20. The notification means 1341 then determines that the contract cancellation deadline information, "May 1, 2020," satisfies the predetermined notification condition (within one month) for the date information indicating today's date, "April 1, 2020." Next, the notification means 1341 acquires notification information corresponding to the contract cancellation deadline information (for example, "The contract cancellation deadline, May 1, 2020, is approaching"). The notification means 1341 sends the acquired notification information to the contact information (managed separately) paired with the user identifier "U001".

The contract processing device 1 performs update processing on the record with ID=1 in Figure 20, as follows: In other words, the update means 1342 of the contract processing device 1 acquires date information indicating today's date, "May 1, 2020," from a clock (not shown). The update means 1342 also acquires the cancellation notice deadline information, "May 1, 2020," that pairs with the contract information with ID=1 in the table in Figure 20. The update means 1342 then determines that the contract cancellation deadline information, "May 1, 2020," satisfies the predetermined notification conditions (date information <= cancellation notice deadline information) for the date information indicating today, "May 1, 2020." Next, the update means 1342 acquires end date information, "June 30, 2021" (one year later), that specifies the next end date. Next, the update means 1342 rewrites the end date information of the record with "ID=1" in Figure 20 to "June 30, 2021."

Furthermore, let us assume that the contract processing device 1, through the process of obtaining the overall score described above, uses the individual scores paired with two or more pieces of contract information for which the date indicated by the contract date information paired with the organization identifier "Corporation A" falls within fiscal year 2019, and obtains an overall score (here, for example, "72") using an increasing function (here, for example, a function for calculating the average) with each individual score as a parameter. Next, the contract processing device 1 accumulates a record having the organization identifier "Corporation A", the period identifier "FY2019", and the overall score "72" in the overall score management table of Figure 21. This record is the record with "ID=108" in Figure 21.

Next, the contract processing device 1 acquires contribution information indicating the degree of contribution made by the legal department of "Corporation A" to the business in fiscal year 2019 through the above-described processing. That is, the contribution information acquisition means 1363 of the contract processing device 1 acquires the overall score of "72" for "Corporation A" for fiscal year 2019 from the table in FIG. 21. Next, the contribution information acquisition means 1363 acquires the overall score of "65" for "Corporation A" for fiscal year 2018 from the table in FIG. 21. Next, the contribution information acquisition means 1363 calculates the difference of "7" between the score for fiscal year 2019 and the comparison score for fiscal year 2018. Next, the related information output unit 141 sends the contribution information "7", which is the difference, to the contact information paired with the user identifier "U001" paired with "Corporation A".

As described above, this embodiment makes it easier to properly manage contracts.

Furthermore, this embodiment makes it easier to use contracts appropriately.

Furthermore, this embodiment allows you to notify contract renewals.

Furthermore, this embodiment makes it possible to classify contract contents.

Furthermore, this embodiment makes it possible to score contract details.

Furthermore, according to this embodiment, information that will lead to an appropriate contract can be presented.

Furthermore, according to this embodiment, the degree of contribution can be presented using changes in the score for a contract.

In this embodiment, (1) the process of obtaining contract attribute values from contract information and storing the contract attribute values together with the contract information, and (2) the process of obtaining a score for the contract information may be performed separately and independently.

A contract processing device that performs only the process (1) is, for example, a contract processing device that includes a clue phrase storage unit that stores one or more clue phrases that serve as clues for obtaining contract attribute values, which are attribute values of the contract; a contract reception unit that receives contract information; an attribute value acquisition unit that acquires contract text from the contract information and uses the one or more clue phrases to acquire from the contract text two or more contract attribute values from the contract text: contract type information, contract counterparty information, contract conclusion date information, contract effectiveness start date information, contract effectiveness end date information, contract automatic renewal information, contract termination notice deadline information, and contract amount information; and a storage support unit that performs storage support processing to store the two or more contract attribute values.

A contract processing device that performs only (2) is, for example, a contract processing device that includes a contract reception unit that receives contract information, a classification unit that analyzes one or more inspection units of the contract text obtained from the contract information and obtains a class indicating whether the contract is unfavorable or not, a related information acquisition unit that uses the class obtained by the classification unit to obtain related information related to the class, and a related information output unit that outputs the related information.

Furthermore, the processing in this embodiment may be implemented using software. This software may be distributed by software download, etc. It may also be distributed by recording it on a recording medium such as a CD-ROM. This also applies to other embodiments in this specification. The software that implements the contract processing device 1 in this embodiment is the following program. That is, this program causes, for example, a computer that can access a cue phrase storage unit that stores one or more cue phrases that serve as clues for acquiring contract attribute values, which are attribute values of a contract, to function as: a contract reception unit that receives contract information; an attribute value acquisition unit that acquires contract text from the contract information and acquires from the contract text, using the one or more cue phrases, two or more contract attribute values selected from contract type information, contract counterparty information, contract conclusion date information, contract validity start date information, contract validity end date information, contract automatic renewal information, contract termination notice deadline information, and contract amount information; and an accumulation support unit that performs accumulation support processing to accumulate the two or more contract attribute values.

This program also functions as, for example, a contract reception unit that receives contract information, a classification unit that analyzes one or more inspection units of the contract text obtained from the contract information and obtains a class indicating whether the contract is unfavorable or not, a related information acquisition unit that uses the class obtained by the classification unit to obtain related information related to the class, and a related information output unit that outputs the related information.

Figure 22 also shows the external appearance of a computer that executes the programs described herein to realize the various embodiments of the contract processing device described above. The above-described embodiments can be realized by computer hardware and computer programs executed on the computer hardware. Figure 22 is an overview of this computer system 300, and Figure 23 is a block diagram of system 300.

In FIG. 22, computer system 300 includes computer 301, which includes a CD-ROM drive, keyboard 302, mouse 303, and monitor 304.

In FIG. 23, in addition to a CD-ROM drive 3012, the computer 301 includes an MPU 3013, a bus 3014 connected to the CD-ROM drive 3012, etc., a ROM 3015 for storing programs such as a boot-up program, a RAM 3016 connected to the MPU 3013 for temporarily storing application program instructions and providing temporary storage space, and a hard disk 3017 for storing application programs, system programs, and data. Although not shown here, the computer 301 may also include a network card that provides connection to a LAN.

A program that causes the computer system 300 to execute functions such as the contract processing device 1 of the above-described embodiment may be stored on CD-ROM 3101, inserted into the CD-ROM drive 3012, and then transferred to the hard disk 3017. Alternatively, the program may be sent to the computer 301 via a network (not shown) and stored on the hard disk 3017. The program is loaded into RAM 3016 when executed. The program may also be loaded directly from the CD-ROM 3101 or the network.

The program does not necessarily have to include an operating system (OS) or third-party programs that cause the computer 301 to execute functions such as the contract processing device 1 of the above-described embodiment. The program need only include instructions that call appropriate functions (modules) in a controlled manner and achieve the desired results. How the computer system 300 operates is well known, so a detailed explanation will be omitted.

Note that in the above program, the steps of transmitting information and receiving information do not include processing performed by hardware, such as processing performed by a modem or interface card in the transmission step (processing that can only be performed by hardware).

Furthermore, the computer that executes the above program may be a single computer or multiple computers. In other words, it may perform centralized processing or distributed processing.

It goes without saying that in each of the above embodiments, two or more communication means present in one device may be physically realized using a single medium.

Furthermore, in each of the above embodiments, each process may be realized by centralized processing on a single device, or may be realized by distributed processing on multiple devices.

The present invention is not limited to the above-described embodiments, and various modifications are possible, and it goes without saying that these modifications are also included within the scope of the present invention.

As described above, the contract processing device of the present invention has the effect of facilitating the appropriate management and use of contracts, and is useful as a contract management device, etc.

REFERENCE SIGNS LIST 1 Contract processing device 2 Terminal device 11 Storage unit 12 Receiving unit 13 Processing unit 14 Transmission unit 21 Terminal storage unit 22 Terminal reception unit 23 Terminal processing unit 24 Terminal transmission unit 25 Terminal reception unit 26 Terminal output unit 111 Search phrase storage unit 112 Learning information storage unit 113 Contract information storage unit 114 Score storage unit 121 Contract reception unit 122 Search information reception unit 131 Attribute value acquisition unit 132 Storage support unit 133 Search unit 134 Post-processing unit 135 Classification unit 136 Related information acquisition unit 141 Related information output unit 142 Contract information output unit 1341 Notification means 1342 Update means 1343 Clear indication means 1361 Single score acquisition means 1362 Total score acquisition means 1363 Contribution information acquisition means 1364 Recommendation acquisition means

Claims (5)

a contract reception unit that receives contract information;
an attribute value acquisition unit that acquires a contract sentence from the contract information, and acquires one or more contract attribute values including contract termination notice deadline information from the contract sentence using one or more clue phrases that serve as clues for acquiring contract attribute values that are attribute values of the contract;
a storage support unit that performs a storage support process for storing the one or more contract attribute values,
The attribute value acquisition unit
a contract document is acquired from the contract information, and automatic renewal information is also acquired from the contract document using the one or more cue phrases, the automatic renewal information being information specifying whether or not the contract is automatically renewed;
The accumulation support unit
performing a storage support process for storing automatic renewal information of the contract;
The one or more contract attribute values include contract expiration date information and contract automatic renewal information;
A contract processing device further comprising an update means for acquiring the automatic update information, and if the automatic update information indicates that an automatic update is "enabled," acquiring the automatic update date paired with the automatic update information, acquiring the next end date information corresponding to the automatic update date, and updating the next end date information as the end date information . The contract processing device according to claim 1 , further comprising a post-processing unit that performs post-processing using one or more of the one or more contract attribute values. The post-processing unit includes:
3. A contract processing device according to claim 2, further comprising notification means for issuing a notification regarding contract renewal or contract termination when it is determined that the date indicated by the cancellation notice deadline information is approaching so close that a predetermined condition is met. A contract processing method , comprising the steps of: causing a computer to execute all of the processes performed by the contract processing device according to any one of claims 1 to 3 ; Computer,
A program for causing the contract processing device according to any one of claims 1 to 3 to function.