KR20200028561A - System for personalized pimple management service - Google Patents

Abstract

The present invention relates to an automatic document classification service providing system. According to an embodiment of the present invention, the automatic document classification service providing server is interlocked with a user terminal, receives a first keyword input from a user through the user terminal, and provides a classification model related to the first keyword to the user terminal. The automatic document classification service providing server comprises: a data collection unit collecting a plurality of drawings and document information from an external server; a classification keyword extraction unit extracting classification keywords from a document included in the data collection unit and collecting user classification keywords based on user information; a classification model generation unit generating a plurality of classification models by learning the classification keywords extracted from the document and the user classification keywords and generating a customized classification model by extracting a classification model related to the first keyword among the plurality of classification models; and a classification service providing unit providing the customized classification model to the user terminal.

Description

System for providing automatic document classification service {SYSTEM FOR PERSONALIZED PIMPLE MANAGEMENT SERVICE}

The present invention relates to a system for providing a document automatic classification service.

In general, for public institutions, banks or companies, etc., as well as individuals, the automatic classification of documents is increasing in need in terms of work efficiency. The automatic document classification device for satisfying these functions provides speed and efficiency in sorting, archiving, and retrieving and checking documents after archiving.

In addition, with the introduction of electronic documents, the amount of document storage has decreased, but payments, review documents, official documents, confirmations, certificates, identification cards, etc. are still used in document form, and it is difficult to classify and store them electronically.

Therefore, in order to solve this, an automatic document classification device has been developed and used.

In this regard, Korean Patent Publication No. 10-2012-0017235 automatically scans, sorts, and archives documents, and automatically documents that have the ability to search, view, and print electronic documents after storage. A classification storage device is disclosed.

Korean Patent Publication No. 10-2012-0017235

The present invention is to solve the problems of the prior art described above, an embodiment of the present invention, to provide a document automatic classification service providing system.

Specifically, it is intended to automatically classify drawings and documents scattered on an external server such as a company or an institution, and to provide a customized classification model suitable for a user's needs.

In addition, by providing a classification model suitable for each user's purpose and providing it to a user, an automatic document classification service providing system is provided to facilitate a large amount of drawing or document management or document search.

On the other hand, the technical problems to be achieved in the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned are clearly understood by those skilled in the art from the following description. Will be understandable.

As a technical means for achieving the above technical problem, the document automatic classification service providing server according to an embodiment of the present invention is linked to a user terminal, receives a first keyword input from the user through the user terminal, and the A classification model related to the first keyword is provided to the user terminal. At this time, the document automatic classification service providing server includes a data collection unit for collecting a plurality of drawings and document information from an external server; A classification keyword extraction unit that extracts classification keywords from documents included in the data collection unit and collects user classification keywords based on user information; A classification model that generates a plurality of classification models by learning the classification keywords extracted from the document and the user classification keywords, and extracts a classification model related to the first keyword from among the plurality of classification models to generate a customized classification model. Generation unit; And a classification service providing unit that provides the customized classification model to a user terminal.

According to any one of the above-described problem solving means, an embodiment of the present invention can provide a system and method for providing an automatic document classification service.

Specifically, drawings and documents scattered on an external server such as a company or an institution may be automatically classified, and a customized classification model suitable for a user's needs may be provided.

In addition, by generating and providing a classification model suitable for each user's purpose, a large amount of drawings or document management or document search can be easily performed.

On the other hand, the effects obtainable in the present invention are not limited to the above-mentioned effects, and other effects not mentioned will be clearly understood by those skilled in the art from the following description. Will be able to.

1 is a view schematically showing the configuration of a document automatic classification service providing system according to an embodiment of the present invention.
2 is a schematic configuration diagram of an automatic document classification server 100 according to an embodiment of the present invention.
3 is a diagram illustrating an example of extracting a classification keyword from drawings and documents according to an embodiment of the present invention.
4 illustrates an example in which the classification model generation unit generates a plurality of classification models according to an embodiment of the present invention.
5 is a view for explaining an automatic classification and search service platform according to an embodiment of the present invention.
6 is a flowchart illustrating in detail a method for providing a document automatic classification service in a system for automatically providing a document classification service according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art to which the present invention pertains can easily practice. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. In addition, in order to clearly describe the present invention, parts not related to the description are omitted.

Throughout the specification, when a part “includes” a certain component, it means that the component may further include other components, not to exclude other components, unless otherwise stated.

Hereinafter, a system for automatically providing a document classification service according to an embodiment of the present invention will be described in detail with reference to the drawings.

1 is a view schematically showing the configuration of a document automatic classification service providing system according to an embodiment of the present invention.

An automatic document classification service providing system according to an embodiment of the present invention includes an automatic document classification server 100 and a database 200. At this time, the document automatic classification server 100 is linked to the database 200 and the user terminal 300 through a network.

At this time, the network means a connection structure capable of exchanging information between each node, such as a terminal and a server. Examples of such a network include a 3GPP (3rd generation partnership project) network, a long term evolution (LTE) network, and a WIMAX ( world interoperability for microwave access (internet), internet (local area network), wireless local area network (LAN), wide area network (WAN), personal area network (PAN), Bluetooth network, satellite Broadcast networks, analog broadcast networks, digital multimedia broadcasting (DMB) networks, and the like.

The document automatic classification server 100 collects drawing and document information from an enterprise or an external server in which a plurality of data are stored, and stores the collected drawing and document information in the database 200.

At this time, the database 200 may include memory. Here, the memory refers to a nonvolatile or volatile storage device that keeps stored information even when power is not supplied. For example, the memory is a read only memory (ROM), programmable ROM (PROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), random access memory (RAM), compact flash (CF) card , NAND flash memory, hard disk drives such as secure digital (SD) cards, memory sticks, solid-state drives (SSDs), and micro SD cards drive (HDD), and the like, and may include magnetic computer storage devices and optical disc drives, such as CD-ROMs and DVD-ROMs.

In addition, the document automatic classification server 100 automatically classifies each drawing and document according to the collected drawings and document information to generate a plurality of classification models, and then extracts a classification model related to a user from among the generated classification models Provided to the user terminal 300.

Specifically, the document automatic classification server 100 receives the first keyword input by the user from the user terminal 300, extracts a classification model associated with the first keyword, and transmits it to the user terminal 300.

Meanwhile, the user terminal 300 may include a camera module, a display, a memory, a processor, and a network communication module, and may be a smart terminal capable of moving and using a network. For example, the smart terminal is a wireless communication device that guarantees portability and mobility, that is, Personal Communication System (PCS), Global System for Mobile communications (GSM), Personal Digital Cellular (PDC), Personal Handyphone System (PHS), PDA All kinds of handhelds such as Personal Digital Assistant (IMT), International Mobile Telecommunication (IMT) -2000, Code Division Multiple Access (CDMA) -2000, W-Code Division Multiple Access (W-CDMA), and Wireless Broadband Internet (WiBro) terminals (Handheld) -based wireless communication device. In addition, the smart terminal is a notebook computer (notebook computer), a tablet (tablet) PC, etc., mobility is guaranteed, and may include a personal computer capable of wireless communication and a smart device such as a smart phone.

Hereinafter, each component of the document automatic classification service providing system according to an embodiment of the present invention will be described in detail.

2 is a schematic configuration diagram of an automatic document classification server 100 according to an embodiment of the present invention.

Referring to FIG. 2, the document automatic classification server 100 includes a data collection unit 110, a classification keyword extraction unit 120, a classification model generation unit 130, and a classification service providing unit 140. However, the present invention is not limited to the above-described configuration examples, and may be separated into detailed components or further include other components as necessary.

First, the data collection unit 100 is interlocked with a company or an external server, and collects information on drawings and documents stored in the corresponding server and stores it in the database 200. At this time, the information about the drawing and the document is, for example, the file name of the drawing or document, the content of the document, the author and the creation date, but may be at least one, but is not limited thereto.

In this case, the drawing may be an image file, that is, an image file having extensions such as jpg, tif, tiff, dwg, and bmp, and the document may be an electronic document having extensions such as doc, xls, xlsx, ppt, txt, and pdf. You can.

The classification keyword extraction unit 120 extracts classification keywords from a plurality of drawings and documents stored in the database 200.

3 is a diagram illustrating an example of extracting a classification keyword from drawings and documents according to an embodiment of the present invention. Specifically, FIG. 3 (a) shows an example of extracting text from a drawing according to an embodiment of the present disclosure, and FIG. 3 (b) shows an example of extracting text from an electronic document.

Referring to FIG. 3, the classification keyword extracting unit 120 may extract a plurality of words included in the drawings and documents, and calculate a frequency for each word to determine a plurality of classification keywords.

In this case, in the case of a drawing, it is possible to recognize text and words inserted in the drawing using an optical character reader (OCR) // user-defined control.

Thereafter, the classification keyword extraction unit 120 may calculate the frequency of occurrence of each of the extracted words, and learn the classification keyword according to the calculated frequency of occurrence to generate a classification model.

For example, the classification keyword extracting unit 120 extracts words having a frequency of a certain ratio or more by calculating a frequency ratio value of the word relative to the frequency of occurrence of a word whose frequency is a certain number of times or more, or among words extracted from the document A And can be determined by classification keywords.

For example, in the document A, the words car, auto, unmanned, video, and control are extracted, and the frequency of each word is 30, 35 auto, 10 unmanned, 5 video, 15 control, etc. When a frequency is calculated, and a word having a frequency of 15 or more is determined as a classification keyword, the first classification keyword may be determined as automatic, the second classification keyword as automobile, and the third classification keyword as control 15.

In addition, the classification keyword extraction unit 120 collects user classification keywords. Here, the user classification keyword refers to a keyword related to the user, such as a user name using the user terminal 300, a characteristic of an organization or a company to which the user belongs, a department to which the user belongs, and project information in progress by the user.

Subsequently, the classification model generation unit 130 generates a plurality of classification models by learning classification keywords and user classification keywords extracted from drawings and documents from the classification keyword extraction unit 120 through machine learning.

4 illustrates an example in which the classification model generation unit generates a plurality of classification models according to an embodiment of the present invention.

Referring to FIG. 4, the classification model generation unit 130 may generate a plurality of classification models using a clustering technique that bundles similar keywords.

For example, the classification model generation unit 130 may generate a classification model 1 by clustering using a "project" among classification keywords, and a classification model 2 by clustering using a "product" as the classification keyword. .

In other words, the classification model 1 may be generated by clustering drawings and documents containing the keyword “project”, and the classification model 2 may be generated by clustering the drawings and documents containing the keyword “product”.

In addition, the classification model generation unit 130 may generate a classification model according to a user classification keyword. That is, a classification model related to a department or task to which a user belongs, such as a design manager or a product manager, may be generated.

In the above-described manner, the classification model generation unit 130 may generate as many classification models as the preset number. Alternatively, the classification model generation unit 130 may generate a classification model for all classification keywords extracted from the drawings and documents. The entire set of classification models generated in this way is defined as a master model in the present invention.

In addition, the classification model generation unit 130 may select at least one classification model related to a user from among a plurality of classification models included in the master model to generate a user-customized model and provide it to a user terminal.

That is, in the present invention, the user-customized model refers to a set of at least one classification model associated with a user among classification models included in the master model.

At this time, the classification model generator 130 according to an embodiment of the present invention may receive a first keyword for generating a user-customized model with a user terminal.

Accordingly, the classification model generation unit 130 extracts similar keywords related to the first keyword based on the first keyword input through the user terminal, selects a classification model, and includes at least one selected classification model. Create custom models.

Finally, the classification service providing unit 140 provides a user-customized model generated by the classification model generation unit 130 to the user. At this time, the classification service providing unit 140 may provide a user-customized classification model and a customized classification service to a user through an automatic classification and search service platform.

5 is a view for explaining an automatic classification and search service platform according to an embodiment of the present invention.

Referring to Figure 5, the document automatic classification service providing system according to an embodiment of the present invention includes an automatic classification and search service platform 10, a drawing management system 12 and a document management system 14 included in an enterprise or an external server. And a data management system 16 and a network. In addition, the automatic classification and search service platform 10 is interlocked with the data collection unit 110 of the automatic document classification server 100, the drawing management system 12, the document management system 14 and the data management system 16 Information about drawings and documents, such as document name, content, author, and creation date, can be transmitted through the collected drawings and documents.

On the other hand, according to an embodiment of the present invention, the document automatic classification service providing system, the automatic classification and search service platform 10 may be provided through a web page. Alternatively, it can be downloaded in the form of an application through the user terminal and stored in the user terminal. Therefore, when the user executes the automatic classification and search service platform application, it is possible to provide a customized classification service to the user.

In other words, the classification service providing unit 140 according to an embodiment of the present invention provides a user-customized classification model through the automatic classification and search service platform 10 of a web page, or a user of the automatic classification and search service platform application. It is possible to provide a user-customized classification service by transmitting to a terminal.

Hereinafter, a method for providing a document automatic classification service in a document automatic classification service providing system according to an embodiment of the present invention will be described in detail with reference to FIG. 6.

6 is a flowchart illustrating in detail a method for providing a document automatic classification service in a system for automatically providing a document classification service according to an embodiment of the present invention.

Referring to FIG. 6, in the method for providing an automatic document classification service according to an embodiment of the present invention, first, the data collection unit 110 receives the first keyword input from the user terminal through the automatic classification and search service platform ( S10).

Thereafter, the data collection unit 110 collects drawing and document information from an external server such as a company or an institution and stores it in the database 200. At this time, the data collection unit 110 may collect documents according to characteristics of a company or organization to which the user belongs, a department to which the user belongs, etc. (S20).

At this time, the information about the drawing and the document is, for example, the file name of the drawing or document, the content of the document, the author and the creation date, but may be at least one, but is not limited thereto.

Here, the drawing may be an image file, that is, an image file having extensions such as jpg, tif, tiff, dwg, and bmp, and the document may be an electronic document having extensions such as doc, xls, xlsx, ppt, txt, and pdf. You can.

Next, the classification keyword extraction unit 120 extracts classification keywords from a plurality of drawings and documents stored in the database 200 (S30).

The classification keyword extraction unit 120 may extract a plurality of words included in the drawings and documents, and calculate a frequency for each word to determine a plurality of classification keywords.

Thereafter, the classification keyword extraction unit 120 calculates the frequency of occurrence of each of the extracted words, and determines the classification keyword according to the calculated frequency of occurrence. For example, the classification keyword extracting unit 120 extracts words having a frequency of a certain ratio or more by calculating a frequency ratio value of the word relative to the frequency of occurrence of a word whose frequency is a certain number of times or more, or among words extracted from the document A And can be determined by classification keywords.

Subsequently, the classification keyword extraction unit 120 collects user classification keywords (S42), and the classification model generation unit 130 extracts classification keywords and user classification keywords extracted from the drawing keywords and documents from the classification keyword extraction unit 120. Learning through machine learning (S40).

Thereafter, the classification model generation unit 130 generates a plurality of classification models through the learned classification keywords (S50). At this time, the classification model generation unit 130 may generate a plurality of classification models using a clustering technique that bundles similar keywords.

For example, the classification model generation unit 130 may generate a classification model 1 by clustering using a "project" among classification keywords, and a classification model 2 by clustering using a "product" as the classification keyword. .

In other words, the classification model 1 may be generated by clustering drawings and documents containing the keyword “project”, and the classification model 2 may be generated by clustering the drawings and documents containing the keyword “product”.

Thereafter, the classification model generation unit 130 determines whether to use the generated classification model (S60). At this time, the classification model generation unit 130 may display whether or not the generated classification model is utilized by the user terminal, so that the user can check whether it is suitable, or if the reliability is higher than a predetermined reliability, the classification model may be determined to be suitable. .

At this time, when it is determined that the classification model is suitable, the classification model is determined as an element of the classification model for generating the master classification model, and when it is determined that it is not suitable, the classification keyword is returned to step S40. (A) learning the classification keyword (S40) and generating the classification model (S50) may be repeated again.

Accordingly, the classification model generation unit 130 generates a plurality of classification models for a predetermined number or all classification keywords extracted from drawings and documents, and generates a master model (S70).

Next, the classification model generation unit 130 selects at least one classification model related to a user from among a plurality of classification models included in the master model (S82) to generate a user-customized model (S80) and provides it to the user terminal. It can be (S90).

Specifically, in the step (S82) of selecting at least one classification model associated with the user, the classification model generation unit 130 extracts similar keywords related to the first keyword based on the first keyword, and extracts the classification model. You can choose.

In addition, in the step (S90) of providing a user-customized model to the user terminal, the classification service providing unit 140 automatically classifies and searches the user-customized model generated by the classification model generation unit 130 of the webpage platform. Through 10), a user-defined classification model may be provided, or a user-defined classification service may be provided by transmitting an automatic classification and search service platform application to a user terminal.

On the other hand, the document automatic classification service providing system according to an embodiment of the present invention performs user authentication from the user terminal 300 connected to the document automatic classification server 100, and the number of customized classification model services provided by the user, or A payment unit (not shown) for charging a fee according to the service period may be further included.

For example, the document automatic classification server 100 may calculate a customized classification model service fee and provide a payment service through a payment unit.

As described above, according to an embodiment of the present invention, a system for providing an automatic document classification service can be provided.

Specifically, drawings and documents scattered on an external server such as a company or an institution may be automatically classified, and a customized classification model suitable for a user's needs may be provided.

Therefore, by generating and providing a classification model suitable for each user's purpose, it is possible to easily manage a large amount of drawings or documents or search documents.

One embodiment of the invention may also be implemented in the form of a recording medium comprising instructions executable by a computer, such as program modules, being executed by a computer. Computer readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. In addition, computer readable media may include both computer storage media and communication media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Communication media typically include computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave, or other transport mechanism, and includes any information delivery media.

Although the methods and systems of the present invention have been described in connection with specific embodiments, some or all of their components or operations may be implemented using a computer system having a general purpose hardware architecture.

The above description of the present invention is for illustration only, and those of ordinary skill in the art to which the present invention pertains can understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as distributed may be implemented in a combined form.

The scope of the present invention is indicated by the following claims rather than the above detailed description, and it should be interpreted that all changes or modified forms derived from the meaning and scope of the claims and equivalent concepts thereof are included in the scope of the present invention. do.

10: Automatic classification and search service platform
100: automatic document classification server
110: data collection unit
120: classification keyword extraction unit
130: classification model generation unit
140: classification service provider
200: database
300: user terminal

Claims (7)

In the document automatic classification service providing server interworking with a user terminal, receiving a first keyword input from the user through the user terminal, and providing a classification model related to the first keyword to the user terminal,
A data collection unit collecting a plurality of drawing and document information from an external server;
A classification keyword extraction unit that extracts classification keywords from documents included in the data collection unit and collects user classification keywords based on user information;
A classification model that generates a plurality of classification models by learning the classification keywords extracted from the document and the user classification keywords, and extracts a classification model related to the first keyword from among the plurality of classification models to generate a customized classification model. Generation unit; And
It includes a classification service providing unit for providing the customized classification model to the user terminal,
Server for automatic document classification service.
According to claim 1,
Further comprising a database for storing the drawings and document information collected from the data collection unit,
The drawings and document information
The document automatic classification service providing server, which includes any one of a file name, content, author, and creation date for each drawing and document.
According to claim 1,
The classification keyword extraction unit extracts at least one word included in each of the drawings and documents,
The classification keyword is determined according to the frequency of occurrence of the word,
Server for automatic document classification service.
The method of claim 3,
The classification keyword extraction unit determines the user classification keyword based on at least one of a department to which the user who input the first keyword belongs, a project in which the user is in progress, and a business pattern of the user,
Server for automatic document classification service.
The method of claim 4,
The classification model generation unit
Create a complete set of a plurality of classification models generated by learning the classification keywords and the user classification keywords as a master model,
At least one classification model related to the first keyword is extracted from the master model to generate a customized classification model.
Server for automatic document classification service.
The method of claim 5,
The classification model generation unit
Extracting similar keywords related to the first keyword, and generating the customized classification model based on the similar keywords,
Server for automatic document classification service.
According to claim 1,
Further comprising a payment service for classification services,
The classification service fee payment unit
Calculating a fee according to the number of times of the customized classification model provided to the user terminal, and transmitting the calculated fee information to the user terminal,
Server for automatic document classification service.

Images