JP4992820B2 - Data processing apparatus, computer program thereof, and data processing method - Google Patents

Description

  The present invention relates to a data processing apparatus that processes document data in correspondence with a computer program, and in particular, a data processing apparatus that detects a modification of document data such as a contract and warns a user, the computer program, and a data processing method therefor About.

  Currently, when a user executes various contracts with a specialist, the contract is made by creating a so-called contract. The contract may be created on a so-called paper medium by printing or handwriting, or may be created by electronic data using an electronic signature.

Currently, there are various proposals as data processing devices that electronically support the creation of contracts as described above (see, for example, Patent Documents 1 and 2).
JP 2002-074206 A Japanese Patent Laid-Open No. 2004-070704

  However, conventionally, only a data processing apparatus that electronically supports the creation of a contract has been proposed. On the other hand, technical terms are often listed in contracts and the like, which is difficult for general users. For this reason, even if a primary document such as a contract is changed to a malicious expert to become a secondary document, it is difficult for a general user to recognize it.

  The present invention has been made in view of the above-described problems, and a data processing apparatus capable of allowing a user to confirm at a glance the modified part of the secondary document with respect to the primary document together with the importance, the computer program thereof, and the data processing Method.

  The data processing apparatus of the present invention includes document acquisition means for acquiring original primary document data and possibly modified secondary document data, and document description of the acquired primary document data and secondary document data Description recognition means for recognizing contents, modification detection means for comparing the primary document data and the secondary document data based on the recognized document description contents, and detecting a document modification portion; and primary document data based on the recognized document description contents Classification determination means for determining at least one document type of the document data and secondary document data, rule storage means for storing the importance determination rule of the document modification part for each document type, and the degree of modification importance of the detected document modification part The importance determination means for individually determining the importance by the importance determination rule corresponding to the determined document type, and outputting the detected document modification portion together with the determined modification importance. It has a modified output means, a.

  A computer program according to the present invention includes a document acquisition process for acquiring original primary document data and possibly modified secondary document data, and document descriptions of the acquired primary document data and secondary document data A recognition process for recognizing the document, a modification detection process for comparing the primary document data and the secondary document data based on the recognized document description, and detecting a document modification part; and the primary document data based on the recognized document description A type determination process for determining at least one document type of the secondary document data, a rule storage process for storing the importance determination rule of the document modification part for each document type, and a modification importance level of the detected document modification part. The importance determination process for individually determining by the importance determination rule corresponding to the determined document type, and the modification importance degree for which the detected document modification part is determined Executing the modified output process of outputting, to the data processing device.

  The data processing method according to the present invention includes a document acquisition operation for acquiring original primary document data and possibly modified secondary document data, and document description of the acquired primary document data and secondary document data Description recognition operation for recognizing contents, modification detection operation for detecting a document modification portion by comparing primary document data and secondary document data based on recognized document description contents, and primary document data based on recognized document description contents Type determination operation for determining at least one of the document type and secondary document data, rule storage operation for storing the document modification portion importance determination rule for each document type, and the modification importance level of the detected document modification portion Outputs the importance judgment operation for individually judging by the importance judgment rule corresponding to the document type judged and the detected document modification part together with the judged modification importance degree. A modified output operation and, the.

  It should be noted that the various components of the present invention need only be formed so as to realize their functions. For example, dedicated hardware that exhibits a predetermined function, data processing in which a predetermined function is provided by a computer program It can be realized as an apparatus, a predetermined function realized in the data processing apparatus by a computer program, an arbitrary combination thereof, or the like.

  In addition, the various components of the present invention do not have to be individually independent, a plurality of components are formed as a single member, and a single component is formed of a plurality of members. That a certain component is a part of another component, a part of a certain component overlaps a part of another component, and the like.

  Moreover, although the data processing method of this invention has described several operation | movement in order, the order of description does not limit the order which performs several operation | movement. For this reason, when implementing the data processing method of this invention, the order of the several operation | movement can be changed in the range which does not interfere in content.

  Furthermore, the data processing method of the present invention is not limited to the case where a plurality of operations are executed at different timings. For this reason, another operation may occur during execution of a certain operation, or a part or all of the execution timing of a certain operation and the execution timing of another operation may overlap.

  The data processing apparatus according to the present invention can read a computer program and execute a corresponding processing operation, so that a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), a HDD (Hard). Disc drive), hardware constructed with general-purpose devices such as I / F (Interface) units, etc., dedicated logic circuits constructed to execute predetermined processing operations, combinations thereof, etc. it can.

  In the present invention, causing the data processing apparatus to execute various operations corresponding to the computer program also means causing the data processing apparatus to control operations of the various devices.

  For example, storing various data in the data processing apparatus means that the CPU stores various data in an information storage medium such as an HDD fixed to the data processing apparatus, or a CD that is exchangeably loaded in the data processing apparatus. The CPU allows various data to be stored in a CD drive in an information storage medium such as -R (Compact Disc-Recordable).

  Furthermore, “store data” in the present invention means that the apparatus of the present invention has at least a function of storing data. For this reason, in addition to storing data newly registered by the consumer, the device of the present invention also stores data registered at the time of manufacture by the supplier, and allows new data not to be registered by the consumer after shipment. .

  In the data processing apparatus of the present invention, the document acquisition unit acquires the primary document data that is the original and the secondary document data that may be altered. Then, the description recognition unit recognizes the document description contents of the acquired primary document data and secondary document data. Based on the recognized document description, the alteration detection means compares the primary document data and the secondary document data to detect the document alteration portion. Further, the type determination unit determines at least one document type of the primary document data and the secondary document data based on the recognized document description. Since the rule storage unit stores the importance determination rule of the document modification part for each document type, the importance determination unit is based on the importance determination rule corresponding to the document type for which the modification importance of the detected document modification part is determined. Judge individually. Since the modification output unit outputs the detected document modification part together with the determined modification importance level, the user can confirm the modification part of the secondary document with respect to the primary document at a glance together with the importance level.

  An embodiment of the present invention will be described below with reference to the drawings. As shown in FIGS. 1 and 2, the data processing system 1000 according to the present embodiment has at least one data processing device 100 of a service provider and a plurality of user operation terminals 200 for each user, and these are the current ones. And a communication network IN such as the next generation NGN (Next Generation Network).

  The data processing apparatus 100 according to the present embodiment includes a document acquisition unit 110 that acquires primary document data FDD that is an original and secondary document data SDD that may be altered, and acquired primary document data FDD. Recognizing part 120 for recognizing document description contents of secondary document data SDD and modification for detecting document modification portion DCP by comparing primary document data FDD and secondary document data SDD according to the recognized document description contents The detection unit 130, the type determination unit 140 that classifies at least one of the primary document data FDD and the secondary document data SDD according to the recognized document description, and the importance determination rule IJR of the document modification portion DCP for each document type Corresponding to the document type for which the rule storage unit 150 stored in the file and the modification importance degree CIR of the detected document modification part DCP are determined. Has a significance determination unit 160 to determine individually significance determination rule IJR, and the modified output unit 170 for outputting with detected is determined document modifying moiety DCP was altered importance degree CIR, the.

  More specifically, the data processing device 100 includes a server device of a service provider, and is used, for example, for opening a website (not shown) used in the user operation terminal 200 in the communication network IN. The

  The user operation terminal 200 includes a personal computer or a mobile phone terminal used by a user, and is used, for example, for using a website established in the communication network IN by the data processing apparatus 100.

  Therefore, the data processing apparatus 100 according to the present embodiment opens a website on the communication network IN for a fee or free of charge to detect document modification and determine the importance. Therefore, the document acquisition unit 110 of the data processing apparatus 100 receives the primary document data FDD and the secondary document data SDD from the user operation terminal 200 of the user via the communication network IN. The modification output unit 170 returns the document modification part DCP to the user operation terminal 200 via the communication network IN together with the determined modification importance degree CIR.

  As will be described in detail later, the rule storage unit 150 of the data processing apparatus 100 stores an importance determination rule IJR that associates a plurality of specific important notations IIM, at least one of which is a document modification part DCP. Therefore, the importance determination unit 160 determines the modification importance degree CIR by associating the detected plurality of document modification portions DCP with the importance determination rule IJR.

  Further, the modification detection unit 130 extracts at least one sentence part sentence including the detected document modification part DCP from the primary document data FDD and the secondary document data SDD. Therefore, the modification output unit 170 generates a modified summary sentence that summarizes the first sentence partial text of the extracted primary document data FDD and secondary document data SDD, and outputs the modified summary sentence together with the document modification part DCP.

  Furthermore, the modification output unit 170 generates and outputs modification emphasis data in which the document modification part DCP is emphasized and expressed by the secondary document data SDD corresponding to the determined modification importance degree CIR. Further, the modification output unit 170 sorts and outputs a plurality of one-sentence partial sentences in which the document modification parts DCP are respectively detected by the determined modification importance degree CIR.

  The data processing apparatus 100 according to the present embodiment includes a CPU that is the main component of a computer apparatus as hardware, and various devices such as ROM, RAM, HDD, and communication I / F are connected to the CPU as hardware. (Not shown).

  In the data processing apparatus 100 of the present embodiment, hardware such as ROM, RAM, HDD, and the like corresponds to an information storage medium, and at least one of them stores a computer program and resources for the CPU as software.

  Such software is installed in the data processing apparatus 100 in advance, and is read by the CPU when the data processing apparatus 100 is activated. As described above, when the CPU reads an appropriate computer program and executes various processes, in the data processing apparatus 100 of the present embodiment, the above-described units 110 to 170 are logically realized as various functions. .

  The document acquisition unit 110 and the modified output unit 170 correspond to a function in which the CPU controls the data communication of the communication I / F corresponding to the computer program. The rule storage unit 150 corresponds to a storage area of an HDD recognized by the CPU corresponding to a computer program. Each of the other units 120 to corresponds to a function of the CPU executing predetermined data processing corresponding to the computer program.

  Such a computer program includes, for example, document acquisition processing for acquiring primary document data FDD that is an original and secondary document data SDD that may have been altered, acquired primary document data FDD, and secondary document data A description recognition process for recognizing the document description content with the SDD, and a modification detection process for detecting the document modification portion DCP by comparing the primary document data FDD and the secondary document data SDD according to the recognized document description content. A type determination process for classifying at least one of the primary document data FDD and the secondary document data SDD according to the document description, a rule storage process for storing the importance determination rule IJR of the document modification part DCP for each document type, Importance determination rule IJ corresponding to the document type for which the modification importance degree CIR of the detected document modification portion DCP is determined And severity determination process of determining an individual in, is described so as to perform a modified output process of outputting with the determined modified importance degree CIR detected document modifying moiety DCP, to the data processing apparatus 100.

  In the configuration as described above, the data processing apparatus 100 according to the present embodiment opens a website on the communication network IN for a fee or free of charge, as described above, for detecting document modification and determining the importance.

  In this website, for example, “The modified part of the primary document and the secondary document such as a contract document will be judged and taught along with its importance. The text data of the primary document will be in the first input space below. , Enter the text data of the secondary document in the second input space respectively ", and guidance data such as" is not shown ".

  Therefore, a user who has primary document data FDD that is the original and secondary document data SDD that may have been altered uses the above-described website on the user operation terminal 200 as desired.

  In this case, for example, as shown in FIG. 3, if the primary document data FDD and the secondary document data SDD are held as electronic data in the user operation terminal 200 composed of a personal computer, the data from the user operation terminal 200 is stored. Primary document data FDD and secondary document data SDD are input to an input space (not shown) of the website of the processing apparatus 100.

  Then, as shown in FIG. 6, the data processing apparatus 100 that has acquired the primary document data FDD and the secondary document data SDD (step S1-Y), the primary document acquired by the existing sentence analysis algorithm or the like. The document description contents of the data FDD and the secondary document data SDD are recognized (step S2).

  Next, the data processing apparatus 100 compares the primary document data FDD and the secondary document data SDD according to the recognized document description, and detects the document modification portion DCP (step S3).

  If the document modification part DCP is not detected (step S4-N), the above-mentioned website says "These two documents have the same contents. Modifications were not detected. A guidance message such as “It is not assumed” is displayed and output as an analysis result (step S8).

  On the other hand, as shown in FIG. 4, when the document modification portion DCP is detected (step S4-Y), the document type of the primary document data FDD is determined from the recognition result of the character string at the beginning of the sentence (step S5). Then, the importance determination rule IJR corresponding to this document type is read (step S6).

  Therefore, the modification importance degree CIR of the detected document modification part DCP is individually determined by the importance degree determination rule IJR (step S7). In the importance determination rule IJR, for example, a modified importance degree CIR is set for each specific importance notation IIM.

  Therefore, it is searched whether the document modification part DCP is registered as the specific important notation IIM in the importance determination rule IJR. In this case, all the words constituting one sentence including the document modification part DCP are extracted, and it is searched whether or not the words are registered as the specific important notation IIM in the importance determination rule IJR.

  Next, as described above, it is determined whether the combination of the specific important notation IIM retrieved from one sentence including the document modification part DCP is registered in the importance determination rule IJR. In this importance determination rule IJR, a modified importance degree CIR is also set for a combination of a plurality of specific important notations IIM.

Therefore, when the combination of the specific important notation IIM retrieved from one sentence including the document modification part DCP is registered in the importance determination rule IJR, for example,
(Document modification part DCP modification importance degree CIR × A (A is a constant of 1 or more) + Specific importance notation IIM modification importance degree CIR × B (B is a constant of 1 or less) + ... + Document modification part DCP modification importance Degree CIR × A + modified importance degree CIR × B) of specific importance notation IIM × modified importance degree CIR of combination =
For example, the modification importance degree CIR of the corresponding sentence is calculated.

  When the modification importance degree CIR is calculated for each sentence including the document modification part DCP in this way, for example, as shown in FIG. 5, the sentences are sorted by the modification importance degree CIR, and “document data XX (The document type was determined. There was a difference between the primary document data FDD and the secondary document data SDD ....) and the modification importance level calculated for the sentence where the document modification part DCP was detected. Sorted by CIR and displayed as a list. At this time, the document modification portion DCP of each sentence exemplified is emphasized by underlining.

  In the data processing apparatus 100 according to the present embodiment, when the primary document data FDD that is the original and the secondary document data SDD that may be altered are acquired as described above, the acquired primary document data FDD and the secondary document data FDD are acquired. Recognizes document description content with document data SDD.

  Next, the primary document data FDD and the secondary document data SDD are compared with the recognized document description to detect the document modification portion DCP, and the primary document data FDD and the secondary document are detected based on the recognized document description. The document type is at least one of data SDD.

  Then, the modification importance degree CIR of the detected document modification part DCP is individually determined by the importance determination rule IJR corresponding to the determined document type, and the detected document modification part DCP is determined together with the determined modification importance degree CIR. The modified output unit 170 outputs. For this reason, the user can confirm at a glance the modification part of the secondary document data SDD with respect to the primary document data FDD together with the importance.

  In particular, in the data processing apparatus 100 according to the present embodiment, a plurality of detected document modification portions DCP are important by the importance determination rule IJR that associates a plurality of specific important notations IIM, at least one of which is a document modification portion DCP. The modification importance degree CIR is determined in association with the degree determination rule IJR.

  For this reason, since the modification importance degree CIR corresponding to the combination of a plurality of specific important notations IIM existing in the sentence in which the document modification part DCP is detected is calculated, the more appropriate modification importance degree CIR can be easily determined and used. Can be provided.

  Moreover, the data processing apparatus 100 according to the present embodiment determines at least one document type of the primary document data FDD and the secondary document data SDD, and determines the modified importance degree CIR by the importance degree determination rule IJR corresponding to the document type. To do. For this reason, it is possible to accurately determine the modification importance degree CIR of the document modification portion DCP that differs depending on the document type.

  Nevertheless, the data processing apparatus 100 according to the present embodiment does not determine the document type unless the document modification portion DCP is detected. For this reason, useless data processing is not executed, and the processing load can be reduced.

  Furthermore, the data processing apparatus 100 according to the present embodiment emphasizes and outputs the document modification portion DCP with an underline. For this reason, the user can confirm at a glance the document modification portion DCP included in the long sentence.

  In addition, when there are a plurality of sentences in which the document modification portion DCP is detected, the data processing apparatus 100 according to the present embodiment sorts the plurality of sentences by the modification importance degree CIR and outputs them. For this reason, the user can check the modified sentences in an important order.

  Further, the data processing apparatus 100 according to the present embodiment is configured to input primary document data FDD and second text data from the user operation terminal 200 of the user via the communication network IN by an input operation to a website established in the communication network IN. Next document data SDD is received.

  Then, the document modification portion DCP is returned to the user operation terminal 200 via the communication network IN together with the determined modification importance degree CIR as a display output of the website. Therefore, the user can easily confirm whether there is a difference between the primary document data FDD and the secondary document data SDD without installing a special application program or the like in the user operation terminal 200.

  The present invention is not limited to the present embodiment, and various modifications are allowed without departing from the scope of the present invention. For example, in the above embodiment, the data processing apparatus 100 has exemplified the primary document data FDD and the secondary document data SDD acquired from the user operation terminal 200 in real time.

  However, the data processing apparatus 100 receives a primary document data FDD and secondary document data SDD from the outside and stores them in a document holding unit, and a document holding unit that holds primary document data FDD and secondary document data SDD. The document acquisition unit 110 may read the primary document data FDD and the secondary document data SDD from the document holding unit (not shown).

  In the above embodiment, the primary document data FDD and the secondary document data SDD are acquired from the user operation terminal 200 of the user by the website established by the data processing apparatus 100 of the service provider in the communication network IN, and the analysis result is obtained. An example of replying.

  However, a document acquisition unit 110 that acquires primary document data FDD that is the original and secondary document data SDD that may have been altered by installing a dedicated application program on a personal computer owned by the user, etc. The description recognition unit 120 for recognizing document description contents of the acquired primary document data FDD and secondary document data SDD, and comparing the primary document data FDD and the secondary document data SDD according to the recognized document description contents The modification detection unit 130 that detects the document modification part DCP, the type determination unit 140 that classifies at least one of the primary document data FDD and the secondary document data SDD according to the recognized document description, and the importance of the document modification part DCP A rule storage unit 150 for storing the degree determination rule IJR for each document type, and An importance determination unit 160 that individually determines the modification importance degree CIR of the document modification part DCP by the importance determination rule IJR corresponding to the document type determined, and the modification importance degree CIR that is determined for the detected document modification part DCP A data processing device (not shown) having a modified output unit 170 that outputs the data may be realized.

  Such a data processing apparatus optically reads a primary document original and a secondary document original to generate primary image data and secondary image data, and description of primary image data and secondary image data You may further have the character recognition means (not shown) which produces | generates the primary document data FDD and the secondary document data SDD by character recognition.

  In this case, the data processing apparatus can easily detect a modified portion between the primary document original and the secondary document original made of a so-called paper medium and can teach the user. In the case where such a data processing device is composed of a mobile phone terminal, a current CCD (Charge Coupled Device) camera can be used as the above-mentioned optical reading means in the current mobile phone terminal.

  Further, such a data processing apparatus 100 also has image comparison means for comparing the primary image data and the secondary image data that have been optically read to detect an image modification portion, and also refers to the detected image modification portion. Then, the document modification part DCP may be detected (not shown).

  In this case, it is possible to determine the document modification portion DCP by detecting a portion that is recognized as the same text data but is modified as an image. For this reason, for example, it is possible to detect alteration by handwriting or the like with good accuracy.

  In addition, the data processing apparatus 100 receives a primary image data and secondary image data generated by optically reading a primary document original and a secondary document original, respectively, and receives the primary image data and secondary image data from an external user operation terminal 200 and the like. A character recognition unit that generates primary document data FDD and secondary document data SDD by recognizing the written characters of the primary image data and secondary image data, and stores them in the document holding unit. 110 may read primary document data FDD and secondary document data SDD from the document holding unit.

  In this case, for example, a general user can use as the user operation terminal 200 a mobile phone terminal on which a CCD camera is mounted, a personal computer to which a web camera or a flatbed scanner is connected, and the like.

  When a general user optically reads a primary document manuscript or a secondary document manuscript at such a user operation terminal 200 and transmits it to the data processing apparatus 100, the general user receives the analysis result of the presence / absence of modification at the user operation terminal 200. Can do.

  In the above embodiment, the detected document modification portion DCP is simply emphasized by underlining. However, the modification emphasis data in which the document modification portion DCP is emphasized by the secondary document data SDD corresponding to the determined modification importance degree CIR may be generated and output.

  For example, when the modification importance degree CIR is “3”, the document modification portion DCP can be highlighted in red, “2” in yellow, and “1” in blue. Not shown). In this case, the user can confirm the document modification portion DCP together with the modification importance degree CIR at a glance.

  Furthermore, in the said form, it illustrated illustrating simply enumerating the sentence which contains the document modification part DCP detected. However, at least one sentence part sentence including the detected document modification part DCP is extracted from the primary document data FDD and the secondary document data SDD, and the modification output unit 170 extracts the extracted primary document data FDD and secondary document data SDD. A modified summary sentence that summarizes the one sentence part sentence may be generated and output together with the document modification part DCP. In this case, general users can more easily understand sentences such as difficult contracts.

  Alternatively, the annotation text data may be set in the importance determination rule IJR for each document modification portion DCP, and the detected document modification portion DCP may be output together with the modification importance level CIR and the annotation text data. In this case, technical terms that are difficult for general users to understand can be understood more easily.

  Furthermore, in the present embodiment, it has been exemplified that each unit of the data processing apparatus is logically realized as various functions by a computer program. However, each of these units can be formed as unique hardware, or can be realized as a combination of software and hardware.

  Needless to say, the above-described embodiment and a plurality of modifications can be combined within a range in which the contents do not conflict with each other. Further, in the above-described embodiments and modifications, the structure of each part has been specifically described, but the structure and the like can be changed in various ways within a range that satisfies the present invention.

It is a schematic diagram which shows the logical structure of the data communication system of embodiment of this invention. It is a block diagram which shows the physical structure of a data communication system. It is a typical front view which shows the description content of primary document data and secondary document data. It is a typical front view which shows the state in which the document modification part was detected from secondary document data. It is a typical front view which shows the output result of a document modification part and modification importance. It is a flowchart which shows the data processing method by a data processor.

Explanation of symbols

DESCRIPTION OF SYMBOLS 100 Data processor 110 Document acquisition part 120 Description recognition part 130 Modification detection part 140 Type determination part 150 Rule storage part 160 Importance determination part 170 Modification output part 200 User operation terminal 1000 Data processing system CIR Modification importance degree DCP Document modification part FDD Primary document data IIM Specific important notation IJR Importance determination rule IN Communication network SDD Secondary document data

Claims (18)

Document acquisition means for acquiring the original primary document data and possibly modified secondary document data;
Description recognizing means for recognizing document description contents of the acquired primary document data and the secondary document data;
Modification detection means for detecting a document modification portion by comparing the primary document data and the secondary document data according to the document description content recognized;
Type determination means for determining at least one document type of the primary document data and the secondary document data according to the recognized document description;
Rule storage means for storing the importance determination rule of the document modification part for each document type;
Importance determination means for individually determining with the importance determination rule corresponding to the document type for which the modification importance of the detected document modification portion is determined;
Modification output means for outputting the detected document modification part together with the determined modification importance degree;
I have a,
A number of specific important titles are predefined,
The rule storage means stores the importance determination rule that is a combination of the specific important notations,
The importance determination means extracts the specific important mark from one sentence including the detected document modification part, and uses a result of comparing the extracted combination of the specific important mark and the importance determination rule, A data processing apparatus for determining the modification importance level . Document holding means for holding at least the primary document data;
The data processing apparatus according to claim 1, wherein the document acquisition unit reads the primary document data from the document holding unit.   The data processing apparatus according to claim 2, further comprising a document receiving unit that receives at least the primary document data from the outside and stores it in the document holding unit. Optical reading means for generating a primary image data by reading optical at least primary original document,
Character recognition means for generating the primary document data by recognizing written characters of the generated primary image data and storing it in the document holding means;
The data processing apparatus according to claim 2, further comprising: A document receiving means for receiving from the outside the primary image data generated by reading optical at least primary original document,
Character recognition means for generating the primary document data by notation character recognition of the received primary image data and storing it in the document holding means;
The data processing apparatus according to claim 2, further comprising: A document holding means for holding at least the secondary document data;
The data processing apparatus according to claim 1, wherein the document acquisition unit reads the secondary document data from the document holding unit.   The data processing apparatus according to claim 6, further comprising a document receiving unit that receives at least the secondary document data from outside and stores the data in the document holding unit. Optical reading means for generating a secondary image data by reading optical at least secondary original document,
Character recognition means for generating the secondary document data by recognizing written characters of the generated secondary image data and storing it in the document holding means;
The data processing apparatus according to claim 6, further comprising: A document receiving means for receiving from the outside at least the secondary document original secondary image data generated by reading optical and
Character recognition means for generating the secondary document data by recognizing the written character of the received secondary image data and storing it in the document holding means;
The data processing apparatus according to claim 6, further comprising: The document receiving means receives the primary document data and the secondary document data from a user operation terminal of a user via a communication network,
The data processing device according to claim 3 or 7, wherein the modification output unit returns the document modification part to the user operation terminal via the communication network together with the determined modification importance level. The optical reading unit optically reads the primary document original and the secondary document original to generate the primary image data and the secondary image data;
The character recognizing means generates the primary document data and the secondary document data by recognizing written characters of the generated primary image data and the secondary image data;
Image comparison means for detecting an image modification portion by comparing the optically read primary image data and the secondary image data, and
9. The data processing apparatus according to claim 4, wherein the alteration detection unit detects the document alteration portion with reference to the detected image alteration portion. The document receiving means receives the primary image data and the secondary image data generated by optically reading the primary document original and the secondary document original;
The character recognition means generates the primary document data and the secondary document data by recognizing the written characters of the received primary image data and the secondary image data,
Image comparison means for detecting an image modification portion by comparing the optically read primary image data and the secondary image data, and
The data processing apparatus according to claim 5 or 9, wherein the alteration detection unit detects the document alteration portion with reference to the detected image alteration portion. The modification detection means extracts at least one sentence part sentence including the detected document modification part from the primary document data and the secondary document data,
Said modified output means, any one of claims 1 to 12 for output together with the document-modifying moiety to the sentence portion sentences and extracted the primary document data the secondary document data to generate the modified summary sentence summarizing The data processing device according to one item. The rule storage means stores the importance determination rule in which annotation text data is set for each document modification part,
The data processing apparatus according to any one of claims 1 to 13 , wherein the modification output unit outputs the detected document modification part together with the modification importance level and the annotation text data. Said modified output means, any one of claims 1 to 14 for generating and outputting a modified enhancement data highlighted expressed in the secondary document data in response to said modified important degree it is determined the document modifying moiety The data processing apparatus described in 1. The data processing apparatus according to any one of claims 1 to 15 , wherein the modification output unit sorts and outputs a plurality of one-sentence partial sentences in which the document modification parts are respectively detected according to the determined importance of modification. . A document acquisition process for acquiring the original primary document data and possibly modified secondary document data;
A description recognition process for recognizing document descriptions of the acquired primary document data and the secondary document data;
A modification detection process for detecting a document modification portion by comparing the primary document data and the secondary document data according to the document description content recognized;
A type determination process for determining at least one document type of the primary document data and the secondary document data according to the recognized document description content;
A rule storage process for storing the importance determination rule of the document modification part for each document type;
Importance determination processing for individually determining with the importance determination rule corresponding to the document type for which the modification importance of the detected document modification portion is determined;
A modification output process for outputting the detected document modification part together with the determined modification importance degree;
To the data processing device ,
A number of specific important titles are predefined,
In the rule storage process, the importance determination rule that is a combination of the specific important notations is stored,
In the importance determination process, the specific important mark is extracted from one sentence including the detected document modification part, and the result of comparing the extracted combination of the specific important mark and the importance determination rule is used. It said modified important degree the computer program Ru is determined. A document acquisition operation for acquiring the original primary document data and possibly modified secondary document data;
A description recognition operation for recognizing document description contents of the acquired primary document data and the secondary document data;
A modification detecting operation for detecting a document modification portion by comparing the primary document data and the secondary document data according to the recognized document description content;
A type determination operation for determining at least one document type of the primary document data and the secondary document data according to the recognized document description;
A rule storage operation for storing the importance determination rule of the document modification part for each document type;
An importance determination operation for individually determining with the importance determination rule corresponding to the document type for which the modification importance level of the detected document modification portion is determined;
A modification output operation for outputting the detected document modification portion together with the determined modification importance degree;
I have a,
A number of specific important titles are predefined,
In the rule storage operation, the importance determination rule that is a combination of the specific important notations is stored,
In the importance level judgment operation, the specific important title is extracted from one sentence including the detected document modification part, and the result of comparing the extracted combination of the specific important title and the importance level judgment rule is used. data processing method for data processing apparatus for determining the modified importance degree.

Images