JP2013131048A - Information processing apparatus, information processing method and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a method for registering mail data to a learning DB such as Bayesian inference spam mail filter, which determines a spam mail from a behavior for an electronic mail received by the user, and automatically registers it to the learning DB.SOLUTION: An unread electronic mail is extracted from received electronic mails, determination is made as to whether the extracted unread mail has not been read for more than a predetermined period of time, and if determination is made that it has not been read for more than the predetermined period of time, data on the electronic mail is registered as data to be decision material for filtering.

Description

  The present invention relates to a technique for determining whether or not a junk mail.

  In recent years, electronic mail has been widely used as a means for transmitting information. E-mails are also used for sending information unilaterally from senders, such as for use in advertising and advertising of products.

  Such advertisements are not necessarily necessary information for the receiver. For this reason, many e-mails are received that have been received but are left unread.

  E-mails that are left unread are deleted as spam mails each time, or are managed separately from necessary e-mails.

  Conventionally, junk mail filtering using Bayesian inference has been performed to determine whether or not it is such junk mail.

  Japanese Patent Application Laid-Open No. 2004-228561 describes a technique of rejecting mail reception from the mail transmission source when the number of unread mails exceeds a predetermined value.

Japanese Patent Laid-Open No. 2003-85101

  However, Patent Document 1 makes a determination based on “the number of unread messages”. Even if an e-mail message is necessary for the recipient, if a predetermined number or more remains unread, the sender of the e-mail message Will not be able to receive e-mails from and will cause inconvenience.

  In addition, the Bayesian inference type spam filter registers the email that the user has manually judged as annoying to generate the learning DB in the learning DB, or a word that is said to be included in many spam emails. In many cases, mail is determined based on dictionary information such as a transmission source and stored in a learning DB.

  When judging based on dictionary information, it can be registered as a general spam mail learning pattern, but unlike a user's judgment of spam mail, a learning pattern depending on the user cannot be registered. Therefore, in order to register the learning pattern depending on the individual user, the user has to register it manually.

  However, manual determination and registration in the learning DB by a user is a very complicated task when the number of spam mails increases.

  In addition, since the Bayesian inference type junk mail filter analyzes the mail data itself registered at the time of learning, the judgment based on the usage method of the user and the passage of time is not reflected in the learning pattern.

  Therefore, in the present invention, as a method of registering mail data in the learning DB in a Bayesian inference type spam filter or the like, it is determined that the user is a spam mail from the behavior with respect to the received email, and is automatically registered in the learning DB. The purpose is to provide a mechanism to do this.

  The present invention is an information processing apparatus that performs filtering processing on a received e-mail, a mail receiving unit that receives an e-mail, and an unread e-mail that extracts an unread e-mail from among e-mails received by the mail receiving unit An unread mail extracted by the extracting means, an unread mail extracted by the unread mail extracting means, an unread determining means for determining whether or not the unread mail exceeds a predetermined time, and an unread mail exceeding the predetermined time by the unread determining means. Learning DB generation means for registering the data of the e-mail as data used as a determination material for filtering if it is determined to be present.

  The present invention is also an information processing method in an information processing apparatus that performs filtering processing on received electronic mail, wherein a mail reception unit of the information processing apparatus receives an electronic mail, and the information processing apparatus The unread mail extracting means extracts the unread e-mail from the e-mail received in the mail receiving process, and the unread determining means of the information processing apparatus is extracted by the unread mail extracting process. An unread determination step for determining whether or not an unread mail has been unread beyond a predetermined time, and the learning DB generation means of the information processing apparatus is unread for a predetermined time by the unread determination step. If it is determined, the learning DB generator for registering the data of the e-mail as data to be used as a determination material for filtering Characterized in that it comprises a and.

  Further, the present invention is a program executable in an information processing apparatus that performs filtering processing on a received electronic mail, wherein the information processing apparatus is received by a mail receiving unit that receives the electronic mail and the mail receiving unit. Unread mail extracting means for extracting unread e-mail from e-mail, and unread determining means for determining whether or not unread mail extracted by the unread mail extracting means is unread over a predetermined time; When it is determined by the unread determination means that it has not been read for a predetermined time, it functions as a learning DB generation means for registering the data of the e-mail as data as a determination material for filtering. .

  According to the present invention, as a method of registering mail data in the learning DB in a Bayesian inference type spam filter or the like, it is determined that the mail is spam from the behavior of the received email and is automatically registered in the learning DB. It becomes possible to do.

It is a figure which shows an example of a structure of the information processing system of this invention. It is a figure which shows an example of the hardware constitutions of the information processing apparatus 101 of FIG. It is a flowchart which shows the spam mail filtering process in embodiment of this invention. It is a flowchart which shows 1st Embodiment of learning DB registration processing in this invention. It is a flowchart which shows 2nd Embodiment of learning DB registration processing in this invention. It is a data table used to determine the unread period It is a data table used to determine the unread period

  Hereinafter, an example of an embodiment of the present invention will be described with reference to the drawings.

  FIG. 1 is a diagram showing an example of a system configuration diagram of an information processing system according to the present invention. As shown in FIG. 1, the information system of the present invention includes a client terminal (information processing apparatus) 101, a mail server 102, and a proxy server 103. In addition, the above devices are connected to each other via a LAN (Local Area Network) 104 so that they can communicate with each other.

  Further, the mail server 102 and the information processing apparatus 101 are connected to the external mail servers 106-1 and 106-2 connected to the wide area network 105 through the proxy server 103 so as to be able to communicate with each other.

  The proxy server 103 is a server device that performs relay control processing on e-mail data transmitted from the mail server 102 or the information processing apparatus 101.

  The mail server 102 is a server device that is used to send and receive e-mails, and has server functions such as e-mail address management and storing e-mails sent to the e-mail addresses. It is.

  The information processing apparatus 101 receives an e-mail transmitted from an e-mail transmission source terminal (not shown).

  Hereinafter, an example of the hardware configuration of the information processing apparatus applicable to the information processing apparatus 101 illustrated in FIG. 1 will be described with reference to FIG.

  In FIG. 2, reference numeral 201 denotes a CPU that comprehensively controls each device and controller connected to the system bus 204. Further, the ROM 203 or the external memory 211 is necessary to realize a BIOS (Basic Input / Output System) or an operating system program (hereinafter referred to as an OS), which is a control program of the CPU 201, or a function executed by each server or each PC. Various programs are stored.

  A RAM 202 functions as a main memory, work area, and the like for the CPU 201. The CPU 201 implements various operations by loading a program necessary for execution of processing from the ROM 203 or the external memory 211 into the RAM 202 and executing the loaded program.

  An input controller 205 controls input from the input device 209 or the like. A video controller 206 controls display on a display device 210 such as a liquid crystal display. The display device is not limited to a liquid crystal display, and may be a CRT display or the like. These are used by clients as needed.

  A memory controller 207 is connected to the hard disk (HD), flexible disk (FD), or PCMCIA card slot for storing a boot program, various applications, font data, user files, editing files, various data, etc. via an adapter. The access to the external memory 211 such as a compact flash (registered trademark) memory is controlled.

  A communication I / F controller 208 connects and communicates with an external device via a network (for example, the LAN 400 shown in FIG. 1), and executes communication control processing in the network. For example, communication using TCP / IP is possible.

  Note that the CPU 201 enables display on the display device 210 by executing outline font rasterization processing on a display information area in the RAM 202, for example. Further, the CPU 201 enables a user instruction with a mouse cursor (not shown) on the display device 210.

  Various programs that operate on the hardware are recorded in the external memory 211 and are executed by the CPU 201 by being loaded into the RAM 202 as necessary.

  It should be noted that not all devices have these configurations, and it is only necessary to provide necessary devices.

  Next, the registration processing to the learning DB performed by the information processing apparatus 101 in the embodiment of the present invention will be described using FIG.

  Note that the process shown in the flowchart of FIG. 3 is a process in which the CPU 201 of the information processing apparatus 101 reads and executes a predetermined control program.

  In step S301, the CPU 201 of the information processing apparatus 101 receives an e-mail transmitted from an external sender terminal (not shown).

  In step S302, the CPU 201 of the information processing apparatus 101 performs a junk mail filtering process on the email received in step S301. The junk mail filter used in step S302 makes a determination based on the data registered in the learning DB in step S406. If it is determined by this process that the received electronic mail is a junk mail, the electronic mail is subjected to processing such as deletion.

  The spam mail filtering process in step S302 may be executed in the proxy server 103. In this case, the proxy server 103 receives the e-mail in step S301, the proxy server 103 performs a junk mail filtering process on the received e-mail, and the e-mail determined to be not junk mail is processed by the information processing apparatus. Delivered to 101.

  Next, a first embodiment of the registration process to the learning DB performed by the information processing apparatus 101 in the embodiment of the present invention will be described with reference to FIG.

  The learning DB may be stored in the information processing apparatus 101 or may be stored in the proxy server 103.

  Note that the process shown in the flowchart of FIG. 4 is a process in which the CPU 201 of the information processing apparatus 101 reads and executes a predetermined control program.

  In step S401, the CPU 201 of the information processing apparatus 101 extracts an unread e-mail from e-mails that are not determined to be junk mail in step S302.

  Then, the processing shown in steps S403 to S406 is executed for each unread mail extracted in step S401 (step S402).

  In step S402, the CPU 201 of the information processing apparatus 101 determines whether the e-mail extracted in step S401 has been in an unread state for a predetermined period. Here, the predetermined period serving as the determination criterion is determined using information set in the table shown in FIG. 6 or FIG. Note that the tables shown in FIGS. 6 and 7 are created by accepting settings from the user via a setting screen (not shown).

The specific determination method is based on a method of comparing the reception time of the e-mail and the current time, but is not limited to this method, and any method may be used.
Here, FIG. 6 will be described.

  FIG. 6 is used when there is a difference in the unread time that is determined to be junk mail (determined as YES in step S403) for each time period when the e-mail is received.

  For example, in the example of FIG. 6, if an e-mail received between 0:00 and 05:00 has an unread period of 24 hours or more, it is determined to be a junk mail (YES in step S403). Determined). Further, it is determined that an e-mail received between 05:00 and 24:00 is determined to be a spam mail when there is an unread period of 48 hours or more (YES is determined in step S403).

  As described above, by making a difference in the unread period depending on the time zone when the electronic mail is received, a more appropriate determination can be made. That is, for example, it can be said that a business mail is rarely sent at 3 o'clock in the middle of the night. Therefore, an e-mail received at 3 o'clock in the middle of the night is highly likely to be unrelated to business. By determining that such mail is a junk mail at an early stage, more appropriate statistics can be obtained.

  On the other hand, it can be said that e-mails received during the day are often related to business. Therefore, even if there is a certain unread period for such an e-mail, there is a possibility that it is an e-mail necessary for the recipient, so it is necessary not to judge that it is a junk mail.

From the above, it is necessary to make a difference in the unread period until it is determined to be spam mail depending on the time zone when the electronic mail is received as shown in FIG.
Next, FIG. 7 will be described.

  FIG. 7 is used when there is a difference in unread time that is determined to be junk mail (determined as YES in step S403) for each day of the week when an e-mail is received.

  For example, in the example of FIG. 7, the e-mail received from Monday to Thursday is unread for 24 hours or more, and the e-mail is determined to be spam (determined as YES in step S403).

  Further, it is determined that the e-mail received on Friday is 96 hours, the e-mail received on Saturday is 72 hours, and the e-mail received on Sunday is unread for 48 hours or more. (Determined as YES in step S403).

  As described above, by making a difference in the time until it is determined to be spam mail depending on the day of the week, an appropriate determination can be made as in the case shown in FIG.

  That is, for example, if an e-mail received on Friday is not opened on Friday, it is likely to be opened on Monday of the next week (since Saturday and Sunday are closed). In such a case, if an e-mail received on Friday is uniformly determined as an unread period that is determined to be spam, it will be determined as spam even though it is a necessary mail. Become.

Assuming such a case, as shown in FIG. 7, it is necessary to have a difference in the unread time until it is determined to be junk mail according to the day of the week when the electronic mail is received.
Returning to the description of FIG.

  If it has not been read for a predetermined period (step S402: YES), the process proceeds to step S403.

  If the unread state has not reached the predetermined period (step S402: NO), the process returns to step S402, and the process for the other electronic mail extracted in step S401 is executed.

  In step S404, the CPU 201 of the information processing apparatus 101 determines whether an e-mail from the same transmission source as the e-mail to be processed has been received. The process in step S404 is a process for preventing an unread mail magazine or the like from being registered in the learning DB. This is a process that is executed because an e-mail magazine or the like is often unread, but cannot always be determined as a junk e-mail.

  If an e-mail from the same transmission source has been received (step S404: YES), the process returns to step S402, and the process for the other e-mail extracted in step S401 is executed.

  If an e-mail from the same sender has not been received (step S404: NO), the process proceeds to step S405.

  In step S405, the CPU 201 of the information processing apparatus 101 determines whether an e-mail having the same or similar subject as the e-mail to be processed has been received. The process in step S405 is also a process assuming a mail magazine or the like.

  If it is determined that an e-mail with the same or similar subject has been received (step S405: YES), the process returns to step S402, and the process for the other e-mail extracted in step S401 is executed.

  If it is determined that an e-mail with the same or similar subject has not been received (step S405: NO), the process proceeds to step S406.

  In step S406, the CPU 201 of the information processing apparatus 101 registers the email data to be processed in the learning DB.

  Here, when the learning DB is in the information processing apparatus 101, the e-mail data is registered in the learning DB of the information processing apparatus 101. When the learning DB is in the proxy server 103, the e-mail data is stored in the proxy server 103. And the proxy server 103 registers.

  Then, the process returns to step S402, and the process for the other electronic mail extracted in step S401 is executed.

  When the processes in steps S403 to S406 are executed for all the emails extracted in step S401, the process of this flowchart is terminated.

  Note that the CPU 201 of the information processing apparatus 101 always performs the processing shown in the flowchart of FIG.

  Next, a second embodiment of the registration process to the learning DB performed by the information processing apparatus 101 in the embodiment of the present invention will be described with reference to FIG.

  Note that the processing shown in the flowchart of FIG. 5 is processing in which the CPU 201 of the information processing apparatus 101 reads and executes a predetermined control program.

  Further, among the processes shown in the flowchart of FIG. 5, the same processes (steps S401 to S403 and S406) as those of the flowchart of FIG. 4 are not described. Here, the process of step S504, which is a process different from FIG. 4, will be described.

  In step S504, the CPU 201 of the information processing apparatus 101 determines whether other e-mails that are not processing target e-mails are unread.

  If it is determined that another e-mail has not been read (step S504: YES), the process returns to step S402, and the process for the other e-mail extracted in step S401 is executed.

  If it is determined that another electronic mail is not unread (step S504: NO), the process proceeds to step S406.

  By determining whether other e-mails are unread as in step S504, for example, whether it is an unsolicited e-mail even if the received mail has not been read because of a vacation. Can be determined. That is, when a vacation is entered, an e-mail that is not originally a junk mail is left unread for a long time. Even in such a case, it is not an appropriate decision to determine that the e-mail is spam. If e-mail received for a certain period before or after the e-mail to be processed is also unread Can be determined not to be spam mail by determining that it is unread due to vacation or the like.

  As for junk mail, a large number of e-mails may be sent in a short period of time. If such a case is dealt with by the above-described method, it may be determined that the message is not spam and is not appropriate.

  Therefore, it is determined whether or not an e-mail transmitted from a transmission source different from the transmission source of the e-mail to be processed is unread among e-mails received in a certain period before and after the e-mail to be processed. By doing so, it becomes possible to eliminate the above-mentioned inconvenience.

  In addition to the determination at the transmission source, it is also possible to determine whether or not an email with a subject that is not similar to the subject of the email to be processed is unread.

  With the above processing, as a method of registering mail data in the learning DB in the Bayesian inference type spam filter or the like, it is determined that it is a spam mail from the behavior with respect to the email received by the user, and is automatically registered in the learning DB. It becomes possible.

  It should be noted that the configuration and contents of the various data described above are not limited to this, and it goes without saying that the various data and configurations are configured according to the application and purpose.

  Moreover, the program in this invention is a program which a computer can perform the processing method of FIGS. The program in the present invention may be a program for each processing method of each apparatus in FIGS.

  As described above, a recording medium that records a program that implements the functions of the above-described embodiments is supplied to a system or apparatus, and a computer (or CPU or MPU) of the system or apparatus stores the program stored in the recording medium. It goes without saying that the object of the present invention can also be achieved by reading and executing.

  In this case, the program itself read from the recording medium realizes the novel function of the present invention, and the recording medium recording the program constitutes the present invention.

  As a recording medium for supplying the program, for example, a flexible disk, hard disk, optical disk, magneto-optical disk, CD-ROM, CD-R, DVD-ROM, magnetic tape, nonvolatile memory card, ROM, EEPROM, silicon A disk or the like can be used.

  Further, by executing the program read by the computer, not only the functions of the above-described embodiments are realized, but also an OS (operating system) operating on the computer based on an instruction of the program is actually It goes without saying that a case where the function of the above-described embodiment is realized by performing part or all of the processing and the processing is included.

  Furthermore, after the program read from the recording medium is written to the memory provided in the function expansion board inserted into the computer or the function expansion unit connected to the computer, the function expansion board is based on the instructions of the program code. It goes without saying that the case where the CPU or the like provided in the function expansion unit performs part or all of the actual processing and the functions of the above-described embodiments are realized by the processing.

  The present invention may be applied to a system constituted by a plurality of devices or an apparatus constituted by a single device. Needless to say, the present invention can be applied to a case where the present invention is achieved by supplying a program to a system or apparatus. In this case, by reading a recording medium storing a program for achieving the present invention into the system or apparatus, the system or apparatus can enjoy the effects of the present invention.

  Furthermore, by downloading and reading a program for achieving the present invention from a server, database, etc. on a network using a communication program, the system or apparatus can enjoy the effects of the present invention. In addition, all the structures which combined each embodiment mentioned above and its modification are also included in this invention.

101 Information processing apparatus 102 Mail server 103 Proxy server 104 LAN
105 Wide area network 106 External mail server

Claims (6)

An information processing apparatus that performs filtering processing on received emails,
Mail receiving means for receiving e-mail;
Unread mail extracting means for extracting unread e-mail from e-mail received by the mail receiving means;
Unread determination means for determining whether or not unread mail extracted by the unread mail extraction means has been unread beyond a predetermined time;
A learning DB generating means for registering the data of the e-mail as data to be used as a determination material for filtering when the unread determination means determines that the data has not been read for a predetermined time;
An information processing apparatus comprising: The e-mail other than the unread e-mail that has been determined to be unread after a predetermined time by the unread determination unit further includes another mail status determination unit that determines whether or not it is in an unread state.
The learning DB generation means does not register the data of the unread mail as data used as a judgment material for filtering when the other mail status determination means determines that an electronic mail other than the unread mail is also unread. The information processing apparatus according to claim 1.   The information processing apparatus according to claim 1, wherein the predetermined time varies depending on a time when the electronic mail is received.   The information processing apparatus according to claim 1, wherein the predetermined time varies depending on a day of the week when the e-mail is received. An information processing method in an information processing apparatus that performs filtering processing on received e-mail,
A mail receiving step in which the mail receiving means of the information processing apparatus receives an e-mail;
An unread mail extracting unit of the information processing apparatus extracts an unread e-mail out of the e-mails received in the mail receiving process; and
The unread determination unit of the information processing apparatus determines whether the unread mail extracted by the unread mail extraction step is unread beyond a predetermined time; and
Learning in which the learning DB generating means of the information processing apparatus registers the data of the e-mail as data to be used as a determination material for filtering when it is determined by the unread determination step that the data has not been read for a predetermined time. DB generation process;
An information processing method comprising: A program that can be executed in an information processing apparatus that performs filtering processing on a received email,
The information processing apparatus;
Mail receiving means for receiving e-mail;
Unread mail extracting means for extracting unread e-mail from e-mail received by the mail receiving means;
Unread determination means for determining whether or not unread mail extracted by the unread mail extraction means has been unread beyond a predetermined time;
When it is determined by the unread determination means that it has not been read for a predetermined time, it functions as a learning DB generation means for registering the data of the e-mail as data as a determination material for filtering. program.

Images