KR101822629B1 - Method and system for performing classification and archiving of emails based on ontology - Google Patents

Abstract

The present invention provides a method for classifying and archiving an email based on ontology. The method for classifying and archiving an email based on ontology includes the steps of: determining whether an email is generated; extracting a feature word of the email; expanding the feature word by using the ontology related to the email; classifying the email by using the feature words; generating indexing information of the email according to a classification result; and storing the email according to the indexing information. Accordingly, the present invention can improve work efficiency.

Description

≪ Desc / Clms Page number 1 > METHOD AND SYSTEM FOR FOR PERFORMING CLASSIFICATION AND ARCHIVING OF EMAILS BASED ON ONTOLOGY < RTI ID =

The present invention relates to providing an ontology-based email classification and archiving method and system.

In general, business emails from companies or companies have been managed by employees who have exchanged emails with clients or clients.

Techniques for managing such individual emails are conventionally known. For example, there is a patent publication 10-2009-0118908 entitled " Email Management System, Method, and Program " issued November 18, 2009. This patent discloses a technique for managing the e-mail of an individual account. There is also a patent publication 10-2014-0084316 entitled " E-MAIL TAG " published July 4, In this patent it is proposed to provide a proposal for at least one proposed tag based on the content of the email, receive a selection of the selected tag, store the email in the computer database and thus generate the stored email, To associate it with the stored e-mail of the database '. As such, techniques are known for each person to manage their account email.

However, when an employee who is a member of a corporation or a company leaves the company, the emails the employee has received related to a certain job are often not delivered to the recipient. Therefore, there is a demand for a technique for managing emails in a corporation or an organization.

KR 10-2009-0118908 B (2009.11.18.) KR 10-2014-0084316 B (2014.07.04.)

An object of the present invention is to provide an ontology-based e-mail classification and archiving method and system, which is created by focusing on the above-described points, and which is constructed by establishing an ontology for a business of an enterprise, .

It is another object of the present invention to provide an ontology-based e-mail classification and archiving method and system capable of performing selective e-mail archiving for each business field and searching archived e-mails according to business fields.

According to one embodiment of the present invention, an ontology-based email classification and archiving method comprises: determining whether an email is generated; Extracting feature words of the email; Expanding a feature word using an ontology associated with the email; Performing classification of the e-mail using the feature words; Generating indexing information of the e-mail according to the classification result; And storing the email according to the indexing information.

The ontology-based email classification and archiving method may further include building the ontology.

The step of constructing the ontology may be performed using at least one of words describing a task, a project, and a specific event of a department or department of an enterprise.

The ontology-based email classification and archiving method may further include performing tagging on the email.

The step of classifying the e-mail may be performed using a support vector machine (SVM).

According to another embodiment of the present invention, an ontology-based e-mail classification and archiving system includes a feature word extracting unit for extracting a feature word of the e-mail when an e-mail is generated; A feature word expander for expanding a feature word using an ontology related to the e-mail; An email classifier for classifying emails using the feature words; And an archiving unit for generating indexing information of the e-mail according to the classification result and storing the e-mail according to the indexing information.

The step of constructing the ontology can be constructed based on at least one of words describing a task, a project, and a specific event of an enterprise department, department, or the like.

The ontology-based email classification and archiving system may further include an email tagging unit for performing tagging on the email.

The email classifier may classify the email using a support vector machine (SVM).

According to the embodiments of the present invention, work efficiency can be improved by constructing an ontology for the business of an enterprise and classifying the e-mail using the constructed ontology. In addition, the present invention can perform selective e-mail archiving for each business field and enable archived e-mail search according to a business field, thereby improving work efficiency.

1 is a block diagram of an ontology-based e-mail classification and archiving system according to an embodiment of the present invention.
2 is a diagram schematically showing an example of an ontology of a research department of a company according to the present invention.
FIG. 3 is a diagram illustrating an example of a company ontology according to the present invention.
4 is a flowchart of an ontology-based email classification and archiving method according to an embodiment of the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS The present invention is capable of various modifications and various embodiments, and specific embodiments are illustrated in the drawings and described in detail in the detailed description. The effects and features of the present invention and methods of achieving them will be apparent with reference to the embodiments described in detail below with reference to the drawings. The present invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings, wherein like reference numerals refer to like or corresponding components throughout the drawings, and a duplicate description thereof will be omitted .

1 is a block diagram of an ontology-based e-mail classification and archiving system according to an embodiment of the present invention.

Referring to FIG. 1, an ontology-based e-mail classification and archiving system 100 according to an embodiment of the present invention is connected to a mail server 40 through a communication network 30. The mail server 40 may be, for example, a mail server of an enterprise. Employees who work in the company can send and receive e-mails necessary for the business related business to the customer or client through the mail server 40. Employees can send and receive e-mails through their user terminals.

The user terminal can be any type of terminal capable of data communication and capable of executing an application. As an example of a user terminal, a laptop computer 20 and a smartphone 22 are shown in FIG. 1, but are not limited thereto. Other examples of user terminals include hand-held computers, personal digital assistants (PDAs), tablet computers, desktop computers, cellular telephones, or any combination of two or more of these data processing devices or any other suitable data processing device, But is not limited to.

Examples of the communication network 30 include a local area network ("LAN") and a wide area network ("WAN"), for example, the Internet. The communication network 30 may include a variety of wired or wireless protocols such as Ethernet, Universal Serial Bus (USB), FIREWIRE, GSM (Global System for Mobile Communications), EDGE (Enhanced Data GSM Environment) (CDMA), time division multiple access (TDMA), Bluetooth, Wi-Fi, voice over Internet Protocol (VoIP), Wi-MAX, or Any other suitable communication protocol may be implemented using any known network protocol.

The ontology-based email classification and archiving system 100 includes an interface 110, a feature word extracting unit 120, a feature word expanding unit 130, an email classification unit 140, an email tagging unit 150, (160). The ontology-based email classification and archiving system 100 may also include an ontology database (DB) 210 and an email database 220.

The interface 110 is connected to the mail server 40 and interfaces with the mail server 40. When the interface 110 detects the occurrence of an e-mail via the mail server 40, the interface 110 can request and receive the e-mail to the mail server 40.

The feature word extracting unit 120 extracts a feature word of the e-mail when the e-mail is generated. The feature word of the email can be extracted from the title and content of the email. Or e-mail may be extracted from the sender and recipient information.

The feature word expander 130 expands the feature word using the ontology associated with the e-mail. The feature word expansion unit 130 may obtain another feature word from the ontology associated with the feature word of the email.

To this end, the feature word expansion unit 130 is connected to the ontology database 210. The term "ontology" generally refers to knowledge of data elements. A given set of data elements may have one or more associated ontologies. The ontology has features that make it inappropriate to store the ontology in the database. For example, knowledge in an ontology is typically less structured than data elements.

The ontology database 210 may store the ontology information constructed by the operator. For example, a person in charge of each department of a corporation or an institution can establish an ontology of his / her department work. After that, each department manager can modify the corresponding ontology so that it is reflected in the ontology whenever department work is changed or added.

2 is a diagram schematically showing an example of an ontology of a research department of a company according to the present invention. The ontology of each department has a tree-like hierarchical structure as shown in FIG. The ontology of the research department shown in FIG. 2 includes an archiving server development and a storage development as subclasses.

Archiving server development is a subclass that includes archiving, email, and in-brain. Storage development includes NVDIMN, storage, and kernel as subclasses. The plurality of ontologies may be connected to each other according to an ontology of an upper layer. These ontology words can be determined, for example, by the department manager or the project manager as the main keywords of the business domain.

FIG. 3 is a diagram illustrating an example of a company ontology according to the present invention. As shown in FIG. 3, Company A has a subclass of a sales department, a planning department, and a research department. The subclass of the sales department has a sales department ontology tree. A subclass of a planning department has a planning department ontology tree. The subclass of the research department also has a research department ontology tree.

On the other hand, the ontology of FIG. 2 is constructed based on the department, but is not limited thereto. For example, an ontology can be built based on at least one of a business department, a business of a department, a project, and a word describing a specific event.

The feature word expansion unit 130 expands feature words using the ontology as described above. Specifically, another feature word is extracted using the ontology to which the feature word extracted from the email belongs as a subclass.

For example, if the feature word of e-mail 1 is archiving, conference, and date, if the feature word of e-mail 1 is extended using the ontology, the feature word of e-mail 1 may be archiving, server, development, project, research department, It can include dates.

The email classifier 140 classifies the email using the feature words. Specifically, the email classifier 140 classifies the email using a support vector machine (SVM).

Support Vector Machine (SVM) is one of the fields of machine learning. It is a map learning model for pattern recognition and data analysis. It is mainly used for classification and regression analysis. Given a set of data belonging to either category, the SVM algorithm builds a non-probabilistic binary linear classification model that determines, based on a given set of data, which categories the new data belongs to. The generated classification model is represented as a boundary in the space where data is mapped. The SVM algorithm is an algorithm for finding the boundary having the largest width. SVM can be used in nonlinear classification as well as linear classification.

For example, the email classifier 140 may use a support vector machine (SVM) to determine which class of the ontology the email is to be classified using the extended feature words. E-mail 1 as described above has the characteristics of archiving, servers, development, projects, research departments, meetings, and dates. With these feature words, e-mail 1 can be classified as research department and archiving server development.

The email tagging unit 150 performs tagging according to the classification result in the e-mail. For example, tagging data or tagging information of e-mail 1 may be (research department, archiving server development). Thereafter, e-mail 1 is used to search for later archived and archived e-mails.

The archiving unit 160 generates indexing information of the e-mail according to the classification result, and stores the e-mail according to the indexing information. Archiving terms are used primarily as a means of data correction along with backups, meaning moving data from one location to another.

More specifically, the archiving unit 160 stores the e-mail data in the e-mail database 200. [ The archiving unit 160 is connected to the e-mail database 200. The e-mail database 200 stores e-mails according to the index information generated by the archiving unit 160. The index information may be determined according to the ontology or classification result. The index information may be determined by the user. For example, if the specific time is determined as the index information, the archiving unit 160 may store the email in association with a specific time. Similarly, if a specific project is determined as the index information, the archiving unit 160 may store the email in association with a specific project. That is, the classification result of the e-mail can be sorted according to the specific index information.

4 is a flowchart of an ontology-based email classification and archiving method according to an embodiment of the present invention.

Referring to FIG. 4, the ontology-based email classification and archiving system 100 determines in step 310 whether an email is generated. The ontology-based e-mail classification and archiving system 100 can determine whether e-mail has been generated through the connected mail server 40.

The ontology-based email classification and archiving system 100 extracts the feature word of the email in step 320 when the email is generated. The feature word of the email can be extracted from the title and content of the email. Or e-mail may be extracted from the sender and recipient information.

The ontology-based email classification and archiving system 100 expands the feature word using the ontology associated with the email in step 330. That is, the ontology-based email classification and archiving system 100 may obtain other feature words from the ontology associated with the feature words of the email.

The ontology-based email classification and archiving system 100 classifies emails using the feature words in step 340. For example, the ontology-based email classification and archiving system 100 may use a support vector machine (SVM) to determine which class of the ontology the email is to be classified.

Subsequently, the ontology-based email classification and archiving system 100 performs tagging on the email according to the classification result in step 350. Tagging refers to attaching related words to emails. That is, tagging is an operation that links at least one word representing information about e-mail. This tacking information is used to search for archived and archived emails in the future.

The ontology-based e-mail classification and archiving system 100 generates indexing information of the e-mail according to the classification result in step 360, and stores the e-mail according to the indexing information.

Specifically, the ontology-based email classification and archiving system 100 stores the email data in the email database 200. The index information may be determined according to the ontology or classification result. The index information may be determined by the user. For example, if the specific time is determined as the index information, the ontology-based e-mail classification and archiving system 100 may store the e-mail in association with a specific time.

Although the preferred embodiments of the present invention have been disclosed for illustrative purposes, those skilled in the art will appreciate that various modifications, additions and substitutions are possible, without departing from the scope and spirit of the invention as disclosed in the accompanying claims. Therefore, the scope of the present invention should not be limited by the described embodiments, but should be determined by the scope of the appended claims and equivalents thereof.

Claims (9)

An ontology-based email classification and archiving method,
Determining whether an email sent to or received from the mail server occurs;
Extracting feature words of the email;
Expanding a feature word using an ontology associated with the email;
Performing classification of the e-mail using the feature words;
Generating indexing information of the e-mail according to the classification result; And
And storing the email according to the indexing information. ≪ RTI ID = 0.0 > 11. < / RTI >
The ontology-based email classification and archiving method of claim 1, further comprising: constructing the ontology.
The ontology-based e-mail classification and archiving method according to claim 2, wherein the ontology is performed based on at least one of words describing a task, a project, and a specific event of a department or department of an enterprise.
The ontology-based email classification and archiving method of claim 1, further comprising performing tagging on the email.
The ontology-based email classification and archiving method of claim 1, wherein the step of classifying the e-mail is performed using a support vector machine (SVM).
An ontology-based email classification and archiving system,
A feature word extracting unit for extracting a feature word of the email when an email transmitted or received to the mail server occurs;
A feature word expander for expanding a feature word using an ontology related to the e-mail;
An email classifier for classifying emails using the feature words; And
And an archiving unit for generating indexing information of the email according to the classification result and storing the email according to the indexing information.
The ontology-based email classification and archiving system according to claim 6, wherein the ontology is constructed based on at least one of words describing tasks, projects, and specific events of a department or department of an enterprise.
The system of claim 6, further comprising an email tagging unit for performing tagging on the email.
7. The system of claim 6, wherein the email classifier classifies the email using a support vector machine (SVM).

Images