JP2007122146A - Electronic mail evaluation device and electronic mail evaluation method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To improve the convenience of a user by efficiently filtering electronic mail. <P>SOLUTION: An electronic mail evaluation device 100 determines whether or not electronic mail has a suitable content based on words included in the electronic mail. In this case, the suitability of each word is registered in a database called suitability information, and the propriety of the electronic mail is determined as the overall evaluation of the suitability of each word. The determination result of the electronic mail is reflected on the suitability information. In the evaluating the electronic mail, when the sender of the electronic mail is a normal user, it is determined that the electronic mail is suitable electronic mail. Also, when the sender is an unauthorized user, it is determined that the electronic mail is unsuitable electronic mail. <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  The present invention relates to a technique for evaluating the contents of a document file, and more particularly to a technique for determining the suitability of the contents of an electronic mail.

  In recent years, with the spread of computers and the advancement of network technology, the exchange of electronic information via the network has become popular. E-mail is one of them, but most of e-mail is said to be spam mail called spam mail.

In response to such a situation, a technique has been developed for determining the suitability of the contents of an electronic mail by natural language processing and automatically eliminating junk mail.
As an example, there is a method of comprehensively evaluating whether or not an e-mail corresponds to a junk e-mail by determining appropriateness of each word included in the e-mail. For example, out of 100 e-mails, 70 are junk mails and the remaining 30 are normal e-mails (hereinafter referred to as “regular mails”). Here, it is assumed that a word A is detected from 60 of 70 spam mails and 3 of 30 regular mails. In this case, since the word A is a word that easily appears in junk mail, it can be said that there is a high possibility that an e-mail containing the word A is a junk mail. From this point of view, the appropriateness or inappropriateness of each word is indexed into a database, and the possibility that the e-mail is spam from all the words included in the newly received e-mail is comprehensive. evaluate. The evaluation result is fed back to the database.
JP 2003-18324 A

  In order to accurately evaluate the suitability of e-mail content by such a method, it is important to enhance the database. The more emails you receive, the more word-by-word ratings will be. In addition, the number of words to be evaluated increases. On the other hand, in the initial stage where the number of words to be evaluated is small, the database is not enriched, so the accuracy of detecting junk mail is low. Therefore, in the initial stage, it is necessary to enhance the database by allowing the system to learn whether the received e-mail is a regular mail or a junk mail for each received e-mail.

  In order to deal with such a problem, a method of preparing a database in which evaluations about a plurality of words are prepared from the beginning can be considered. While executing the e-mail evaluation process based on the initially set database, the database is further enriched according to the evaluation result. However, whether or not it is a spam mail or a regular mail has a different judgment criterion depending on the user in the first place. Therefore, the method of preparing a database in which the appropriateness or inappropriateness of each word is indexed in advance is not always an effective solution.

  The present invention has been made in view of such circumstances, and a main object of the present invention is to provide a technique for improving user convenience in a system that evaluates the contents of an e-mail with reference to a database.

One embodiment of the present invention is an electronic mail evaluation apparatus.
In order to determine whether or not the e-mail transmitted from the external device has appropriate contents for the user of the recipient, the degree-of-fit information holds the degree of relevance obtained by indexing the appropriateness of each word as the degree-of-fit information. A holding unit, a mail acquisition unit that acquires an e-mail to be evaluated, a word extraction unit that extracts a word included in the e-mail, and a fitness of each word included in the e-mail with reference to the fitness information And a suitability determination unit that determines whether or not the e-mail has appropriate content based on the degree of suitability thereof, and determination of the suitability for each word included in the e-mail to be judged with respect to the e-mail A fitness level update unit that updates the fitness level information by performing recalculation according to the result.
The conformity determination unit refers to the regular address table in which the email address of the authorized user is registered in advance, and if the transmission source address of the obtained email is registered as the email address of the authorized user, the email is Determine that the content is appropriate.

  Alternatively, the conformity determination unit refers to an unauthorized address table in which the email address of the unauthorized user is registered in advance, and if the source address of the acquired email is registered as the email address of the unauthorized user, The e-mail may be determined to be inappropriate content.

Another aspect of the present invention is also an electronic mail evaluation apparatus.
In order to determine whether or not the e-mail transmitted from the external device has appropriate contents for the user of the recipient, the degree-of-fit information holds the degree of relevance obtained by indexing the appropriateness of each word as the degree-of-fit information. A holding unit, a mail acquisition unit that acquires an e-mail to be evaluated, a word extraction unit that extracts a word included in the e-mail, and a fitness of each word included in the e-mail with reference to the fitness information And a suitability determination unit that determines whether or not the e-mail has appropriate content based on the degree of suitability thereof, and determination of the suitability for each word included in the e-mail to be judged with respect to the e-mail A fitness level update unit that updates the fitness level information by performing recalculation according to the result.
The mail acquisition unit also acquires an e-mail that the user transmits to the external device, and the fitness update unit determines that the e-mail transmitted from the user has an appropriate content for each word included in the e-mail. The fitness information is updated by recalculating the fitness of.

  It should be noted that any combination of the above-described constituent elements and a conversion of the expression of the present invention between a method, an apparatus, a system, a recording medium, a computer program, etc. are also effective as an aspect of the present invention.

  ADVANTAGE OF THE INVENTION According to this invention, a user's convenience can be improved in the system which evaluates the content of an email with reference to a database.

FIG. 1 is a schematic diagram showing the relationship between an electronic mail evaluation apparatus and a mail browser.
The client terminal 80 is an information device such as a personal computer or a portable terminal used by the user. The client terminal 80 is installed with a mail browser 90 for mail transmission / reception and browsing. In this embodiment, the email received by the client terminal 80 is first evaluated by the email evaluation device 100. The e-mail evaluation apparatus 100 transfers the e-mail to the mail browser 90 if the e-mail is not junk mail, and does not transfer it to the mail browser 90 if the e-mail is junk mail. In other words, the e-mail evaluation apparatus 100 functions as an e-mail filter.

The e-mail evaluation apparatus 100 according to the present embodiment evaluates the content of the e-mail based on the Bayesian filter method, and determines whether the e-mail is a junk mail.
The determination principle will be described.
Suppose that a total of 200 spam mails and 100 regular mails have been acquired. Here, it is assumed that the word “sweep award” appears 98 times in this spam mail group and twice in the regular mail group. In this case, it is highly probable that an e-mail containing the word “price” will be a spam mail. For each word, the e-mail evaluation apparatus 100 indexes “the probability that an e-mail containing the word is a junk mail” as a “spam word probability”.

In the case of the well-known Paul Graham method, the spam word probability P (w) of a word w is
P (w) = (m / M) / (2 × n / N + m / M)
Is defined by the expression
here,
m: Number of times the word w appeared in the spam mail group M: Total number of spam mails n: Number of times the word w appeared in the regular mail group N: Total number of regular mails
When calculating the spam probability of the word “price” just before using the Paul Graham method, m = 98, M = 100, n = 2, N = 100.
P (“Stakes Prize”) = (98/100) / (2 × 2/100 + 98/100)
Is calculated as about 96%.
The e-mail evaluation apparatus 100 creates a database of spam word probabilities for each word included in these 200 e-mails. In this embodiment, such a database is referred to as “fitness information”.

It is assumed that spam word probabilities of “prayer: 96%”, “frozen: 30%”, and “udon: 5%” are set in the fitness information.
It is assumed that after the above initial settings are made, the e-mail evaluation apparatus 100 newly receives an e-mail with the content “I often apply for sweepstakes.
The probability that this e-mail is spam (hereinafter referred to as “spam mail probability”) is (0.96 × 0.3 × 0.05) / {(0.96 × 0.3 × 0.05). It is calculated as + (1−0.96) × (1−0.3) × (1−0.05)} = 35%.
The e-mail evaluation apparatus 100 determines an e-mail having a spam e-mail probability of 90% or more as a junk e-mail. At this time, since the total number of spam mails is 101, the spam word probability of each word in the electronic mail is recalculated accordingly. That is, P (w) is recalculated after m and M are changed.
On the other hand, if it is less than 90%, the e-mail evaluation apparatus 100 transfers the e-mail to the mail browser 90 as not being a spam mail. The user of the mail browser 90 determines whether the transferred electronic mail is indeed a regular mail or is also a junk mail. The determination result is fed back to the electronic mail evaluation apparatus 100. Reflecting this determination result, the e-mail evaluation apparatus 100 updates the fitness information. If it is a regular mail, P (w) is recalculated after changing n and N respectively. The e-mail evaluation apparatus 100 updates and enhances the fitness information every time an e-mail is received. In this way, the evaluation of words appearing in regular mail and spam mail is determined.
Note that the user can also change various determination conditions in the e-mail evaluation apparatus 100.

The e-mail evaluation apparatus 100 in the present embodiment holds a list (hereinafter referred to as “user list”) in which e-mail addresses of authorized users and unauthorized users are registered. The user of the e-mail evaluation apparatus 100 can freely update this user list.
The e-mail transmitted from the legitimate user is uniformly determined to be the legitimate mail without being based on the calculation of the spam mail probability. For example, since an e-mail transmitted from a close friend is not considered a junk mail, the friend may be registered in the user list as a regular user. For each word included in the e-mail sent from the authorized user, the spam word probability is recalculated after changing n and N.
The regular user may be a user registered in the address book of the mail browser 90. In this case, since the user does not even need to explicitly register the regular user in the user list, the user interface can be further simplified.

On the other hand, an electronic mail transmitted from an unauthorized user is uniformly determined to be a spam mail without being based on the calculation of the spam mail probability. For example, a trader with a history of sending spam mails in the past may be registered as an unauthorized user. For each word included in the e-mail sent from the unauthorized user, the spam word probability is recalculated after m and M are changed.
According to such a processing method, the fitness level information can be automatically enriched based on the user list.

  In addition, since the spam mail probability is not calculated for an email from a typified user such as a regular user or an unauthorized user, the processing load of the email evaluation apparatus 100 can be reduced.

FIG. 2 is a functional block diagram of the electronic mail evaluation apparatus.
Each block shown here can be realized in hardware by an element such as a CPU of a computer or a mechanical device, and in software it is realized by a computer program or the like. Draw functional blocks. Therefore, those skilled in the art will understand that these functional blocks can be realized in various forms by a combination of hardware and software. In the present embodiment, the e-mail evaluation apparatus 100 will be described assuming that the function is exhibited by application software installed in the client terminal 80.
In addition, here, the functions that should be exhibited by each block will be described with reference to FIG.

The e-mail evaluation apparatus 100 includes a user interface processing unit 110, a mail acquisition unit 112, a mail transfer unit 114, a data processing unit 116, and a data storage unit 118.
The user interface processing unit 110 is in charge of processing related to the entire user interface such as input processing from the user and information display for the user. The mail acquisition unit 112 acquires an e-mail from an external mail server (not shown). The mail transfer unit 114 transfers, to the mail browser 90, an e-mail that is determined not to be a junk mail by the data processing unit 116 among e-mails acquired from the external device.

  The mail acquisition unit 112 also acquires an e-mail transmitted from the mail browser 90 to the outside, and the data processing unit 116 sets such an e-mail as a processing target. Hereinafter, an e-mail transmitted from the external device to the client terminal 80 is referred to as “received mail”, and an e-mail transmitted from the client terminal 80 to the external device is referred to as “transmitted mail”. The outgoing mail acquired by the mail acquisition unit 112 is processed by the data processing unit 116 and then sent to the mail server by the mail transfer unit 114.

The data processing unit 116 executes various types of data processing based on data acquired from the user interface processing unit 110 and the mail acquisition unit 112. The data processing unit 116 also serves as an interface among the user interface processing unit 110, the mail acquisition unit 112, the mail transfer unit 114, and the data storage unit 118.
The data storage unit 118 stores various setting data prepared in advance and data received from the data processing unit 116.

  The data storage unit 118 includes a fitness information holding unit 136 and a user list holding unit 138. The goodness-of-fit information holding unit 136 holds goodness-of-fit information in which a word is associated with its spam word probability. The user list holding unit 138 holds a user list. The user list is a list of e-mail addresses of authorized users and e-mail addresses of unauthorized users. The user can arbitrarily change the contents of the user list via the user interface processing unit 110.

The data processing unit 116 includes a fitness information processing unit 120, a user list update unit 122, and a mail evaluation unit 124.
When the mail acquisition unit 112 acquires an email, the mail evaluation unit 124 determines whether the email is appropriate by calculating the spam mail probability of the email. The fitness information processing unit 120 updates the fitness information in the fitness information holding unit 136 according to the determination result. The user list update unit 122 updates the user list according to the user's operation on the e-mail. The update of the user list will be described later.

The mail evaluation unit 124 includes a word extraction unit 132 and a match determination unit 134.
The word extraction unit 132 extracts words included in the e-mail. The word here may be a word group or a byte stream, and is not necessarily limited to a “word” as a minimum unit of sentence structure. The suitability determination unit 134 reads the spam word probability of the extracted word from the suitability information holding unit 136 and calculates the spam mail probability. As already described, the conformity determination unit 134 transfers the e-mail from the mail transfer unit 114 to the mail browser 90 if the spam mail probability is less than 90%, and does not transfer it if it is 90% or more. Prior to calculating the spam mail probability, the suitability determining unit 134 refers to the user list, and if the address of the source of the received mail is registered, the suitability determining section 134 determines the suitability of the email according to the registered content. .

What is regular email?
(1) A received mail from a legitimate user or a received mail with a spam mail probability of less than 90%, and
(2) An e-mail that is determined to be appropriate by the user at the client terminal 80. Also,
(3) The outgoing mail is treated as regular mail uniformly.

On the other hand, spam is
(1) Incoming mail from unauthorized users or received mail with a spam mail probability of 90% or more, or
(2) The spam mail probability is an e-mail judged to be unsuitable by the user although it is a received mail of less than 90%.

As described above, whether or not the e-mail is appropriate is determined by both or one of the mail evaluation unit 124 of the e-mail evaluation apparatus 100 and the user of the mail browser 90.
Note that the user can arbitrarily change the numerical value of 90%, which is an e-mail determination criterion, via the user interface processing unit 110.

The fitness information processing unit 120 includes an update unit 126 and a word registration unit 128.
The update unit 126 updates the fitness information. That is, the spam word probability of each word included in the fitness information is recalculated according to Paul Graham's formula according to the determination result for the new e-mail. If there is an unregistered word in the fitness information among the words included in the email, the word registration unit 128 newly registers this in the fitness information. Thereafter, the calculation of the spam word probability for the newly registered word is started.
Next, a process when the e-mail evaluation apparatus 100 newly receives an e-mail will be described.

FIG. 3 is a flowchart showing the basic processing steps of the e-mail evaluation apparatus at the time of e-mail acquisition.
First, the mail acquisition unit 112 acquires an e-mail (S10). If this electronic mail is a transmission mail (Y in S12), a transmission mail determination process for updating the fitness information is executed (S14). Thereafter, the outgoing mail is sent to an external mail server by the mail transfer unit 114 (S18). On the other hand, if the acquired e-mail is a received mail (N in S12), a received mail process for determining the suitability of the e-mail and updating the fitness information is executed (S16).
The processing contents of S14 and S16 will be described in detail later.

FIG. 4 is a flowchart showing in detail the outgoing mail determination process in S14 of FIG.
The word extraction unit 132 extracts words included in the transmitted mail (S20). Among these, if there is a word that is not registered in the fitness information (Y in S22), the word registration unit 128 newly registers this unregistered word in the fitness information (S24). If there is no unregistered word (N in S22), the process in S24 is skipped.

  The update unit 126 recalculates the spam word probability of each word included in the transmitted mail, assuming that the transmitted mail is a regular mail (S26). Thereby, the fitness information is updated. The user list update unit 122 executes a user list update process for updating the user list (S28).

FIG. 5 is a flowchart showing in detail the user list update process in S28 of FIG.
If the outgoing mail is an email sent as a reply to the received mail (Y in S30), the user list updating unit 122 registers the addressee of the outgoing mail, that is, the sender of the original received mail as a regular user. (S36). When the user of the client terminal 80 receives an e-mail and replies to the e-mail, it is considered that the reply destination is not an unauthorized user, so such a user is automatically registered as a regular user. ing. When the reply destination user is already registered in the user list as an unauthorized user, the user may be removed from the unauthorized user by a reply from the user.

  The user list update unit 122 manages the number of email transmissions for each addressee. In S30, if the transmitted mail is not a reply mail (N in S30), the user list updating unit 122 counts up the number of transmissions of the transmitted mail to the addressee (S32). When the number of transmissions exceeds a predetermined threshold S, for example, 5 (Y in S34), the addressee is registered as a regular user (S36). Since a user who is frequently regarded as a destination is considered not to be an unauthorized user, such a user is automatically registered as a regular user. On the other hand, if it is equal to or less than the threshold value S (N of S34), the process of S28 is terminated.

  As a modification, for example, in S30, the addressee may be registered as a regular user on the condition that the addressee has replied a predetermined number of times or more. In S34, the destination person may be registered as a regular user on condition that the number of transmissions in a predetermined period of the past month exceeds the threshold S.

FIG. 6 is a flowchart showing in detail the received mail determination process in S16 of FIG.
The conformity determination unit 134 manages two types of flags, an affirmative flag and a negative flag. The affirmative flag indicates that the e-mail to be evaluated is a regular mail, and the negative flag indicates that it is a spam mail. The conformity determination unit 134 first resets each flag before determining the suitability of the received mail (S40). If the sender of the received mail is a regular user (Y in S42), the conformity determination unit 134 turns on the positive flag (S44). On the other hand, if the sender of the received mail is an unauthorized user (N in S42, Y in S46), the conformity determination unit 134 turns on a negative flag (S48). If the sender is neither an authorized user nor an unauthorized user (N in S42, N in S46), neither flag is turned on.
Thereafter, conformity evaluation processing for conformity evaluation of the received mail is executed (S50).

FIG. 7 is a flowchart showing in detail the conformity evaluation process in S50 of FIG.
The word extraction unit 132 extracts words included in the received mail (S60). If there is a word that is not registered in the fitness information (Y in S62), the word registration unit 128 newly registers the unregistered word in the fitness information (S64). If there is no unregistered word (N of S62), the process of S64 is skipped.

  If the affirmative flag is turned on (Y in S66), the process skips to S74. If the negative flag is on (N in S66, Y in S68), the process skips to S80. If neither the positive flag nor the negative flag is turned on (N in S66, N in S68), the matching determination unit 134 calculates the spam mail probability from the spam word probability for the word extracted from the received mail (S70).

If the spam mail probability is equal to or higher than a predetermined threshold (N in S72), the conformity determination unit 134 determines that the electronic mail is a spam mail (S80). In this embodiment, the threshold is set as 90%, but can be changed by a setting input from the user. On the other hand, if the spam mail probability is less than this threshold (Y in S72), the conformity determination unit 134 temporarily determines that the mail is a regular mail. The mail transfer unit 114 transfers the received mail to the mail browser 90 (S74). When it is determined by the user that the forwarded received mail is a regular mail (Y in S76), this mail is treated as a regular mail (S78). When it is determined by the user that the transferred received mail is spam mail (N in S76), the electronic mail is treated as spam mail (S80).
The updating unit 126 recalculates the spam word probability of each word in the fitness information according to the determination result on the received mail (S82).

The present invention has been described above based on the embodiments.
According to the electronic mail evaluation apparatus 100 shown in the present embodiment, when the spam mail probability is obtained by the Bayesian filter method, the fitness information that is the basis of the determination can be efficiently enhanced.

  By classifying the e-mail according to the sender by the user list, the e-mail evaluation apparatus 100 can exhibit the filtering function even when the fitness information is not substantial. Moreover, since the spam mail probability is not calculated for the electronic mail from the legitimate user or the unauthorized user, there is an effect of suppressing the processing load of the electronic mail evaluation apparatus 100. For this reason, the method shown in this embodiment functions effectively even after the fitness information is enriched. Moreover, since the user list can be enriched by automatically updating the user list in accordance with the user's transmission operation, the convenience is further enhanced. In particular, if the regular user is a user registered in the address book, the user does not need to be aware of the existence of the user list.

Furthermore, since the outgoing mail transmitted to the outside by the user is a regular mail reflecting the user's intention, the suitability information can be enriched even earlier by using such outgoing mail. Thus, according to the e-mail evaluation apparatus 100 shown in the present embodiment, the convenience of the user in e-mail filtering can be further enhanced.
In this embodiment, the description has been made on the premise of the Bayesian filter, particularly the Paul Graham method. However, the present invention is not limited to this, and the present invention can be widely applied to document content evaluation based on appropriateness for each word.

  It should also be understood by those skilled in the art that the functions to be fulfilled by the constituent elements described in the claims are realized by the individual functional blocks shown in the present embodiment or their linkage.

  The present invention has been described based on the embodiments. This embodiment is an exemplification, and it will be understood by those skilled in the art that various modifications can be made to combinations of the respective constituent elements and processing processes, and such modifications are also within the scope of the present invention. is there.

  For example, in the present embodiment, a mode has been described in which a regular user is automatically registered in the user list in response to a user's transmission operation. As a modification, an unauthorized user may be updated according to the received mail. For example, when the number of received mails by the same sender per unit time exceeds a predetermined number, the sender may be registered in the user list as an unauthorized user. Thus, by linking the user list based on the suitability of the user and the fitness information based on the suitability of the word, it is possible to realize more convenient and precise e-mail filtering.

It is a schematic diagram which shows the relationship between an electronic mail evaluation apparatus and a mail browser. It is a functional block diagram of an electronic mail evaluation apparatus. It is a flowchart which shows the basic process of the email evaluation apparatus at the time of email acquisition. It is a flowchart which shows the transmission mail determination process in S14 of FIG. 3 in detail. It is a flowchart which shows the user list update process in S28 of FIG. 4 in detail. It is a flowchart which shows the received mail determination process in S16 of FIG. 3 in detail. It is a flowchart which shows the conformity evaluation process in S50 of FIG. 6 in detail.

Explanation of symbols

  80 client terminal, 90 mail browser, 100 e-mail evaluation device, 110 user interface processing unit, 112 mail acquisition unit, 114 mail transfer unit, 116 data processing unit, 118 data storage unit, 120 fitness information processing unit, 122 user list An update unit, a 124 mail evaluation unit, a 126 update unit, a 128 word registration unit, a 132 word extraction unit, a 134 suitability determination unit, a 136 suitability information holding unit, and a 138 user list holding unit.

Claims (13)

In order to determine whether or not the e-mail transmitted from the external device has appropriate contents for the user of the recipient, a fitness information holding unit that holds the fitness that indexes the appropriateness of each word as fitness information,
An email acquisition unit for acquiring emails to be evaluated;
A word extractor for extracting words contained in the email;
A fitness determination unit that detects the fitness of each word included in the e-mail with reference to the fitness information, and determines whether the e-mail has appropriate content from the fitness; and
A relevance level update unit that updates the relevance level information by recalculating the relevance level for each word included in the e-mail to be determined according to the determination result for the e-mail,
The conformity determination unit refers to a regular address table in which the email address of the authorized user is registered in advance, and if the transmission source address of the obtained email is registered as the email address of the authorized user, the email An e-mail evaluation apparatus characterized by determining that the content is appropriate.   The conformity determination unit refers to an address book attached to an e-mail software as the regular address table, and if the source address of the acquired e-mail is registered in the address book, the e-mail The e-mail evaluation apparatus according to claim 1, wherein it is determined that the content is appropriate.   And a regular address table updating unit for registering the sender of the email transmitted from the external device as a regular user in the regular address table when the recipient user replies to the email transmitted from the external device. The electronic mail evaluation apparatus according to claim 1, wherein the electronic mail evaluation apparatus is an electronic mail evaluation apparatus.   The regular address table updating unit registers the predetermined addressee as a regular user in the regular address table on the condition that the number of times of transmission of e-mail from the user to the predetermined addressee exceeds a predetermined number of times. 4. The e-mail evaluation apparatus according to claim 3, wherein In order to determine whether or not the e-mail transmitted from the external device has appropriate contents for the user of the recipient, a fitness information holding unit that holds the fitness that indexes the appropriateness of each word as fitness information,
An email acquisition unit for acquiring emails to be evaluated;
A word extractor for extracting words contained in the email;
A fitness determination unit that detects the fitness of each word included in the e-mail with reference to the fitness information, and determines whether the e-mail has appropriate content from the fitness; and
A relevance level update unit that updates the relevance level information by recalculating the relevance level for each word included in the e-mail to be determined according to the determination result for the e-mail,
The mail acquisition unit also acquires an email sent by the user to an external device,
The fitness level update unit updates the fitness level information by recalculating the fitness level for each word included in the email, assuming that the email sent from the user has appropriate content. A featured e-mail evaluation device. In order to determine whether or not the e-mail transmitted from the external device has appropriate contents for the user of the recipient, a fitness information holding unit that holds the fitness that indexes the appropriateness of each word as fitness information,
An email acquisition unit for acquiring emails to be evaluated;
A word extractor for extracting words contained in the email;
A fitness determination unit that detects the fitness of each word included in the e-mail with reference to the fitness information, and determines whether the e-mail has appropriate content from the fitness; and
A relevance level update unit that updates the relevance level information by recalculating the relevance level for each word included in the e-mail to be determined according to the determination result for the e-mail,
The conformity determination unit refers to an unauthorized address table in which an email address of an unauthorized user is registered in advance, and if the source address of the acquired email is registered as an email address of the unauthorized user, An e-mail evaluation device characterized in that e-mail is determined to be inappropriate content.   The fitness level update unit recalculates the fitness level of each word included in the acquired e-mail based on a Bayesian filtering method. The e-mail evaluation device described. Obtaining an email sent from an external device;
Extracting words contained in the email;
Refers to the fitness information indicating the fitness that is indexed by the appropriateness of each word, detects the fitness of each word contained in the acquired email, and the email obtained from those fitness is appropriate Determining whether the content is correct,
Updating the fitness level information by recalculating the fitness level for each word included in the email to be determined according to the determination result for the email, and
In the step of determining the content of the e-mail, the e-mail address of the authorized user is referred to a previously-registered authorized address table, and the source address of the obtained e-mail is registered as the e-mail address of the authorized user. For example, the e-mail evaluation method includes determining that the e-mail has appropriate contents. Obtaining an email sent from an external device;
Extracting words contained in the email;
Refers to the fitness information indicating the fitness that is indexed by the appropriateness of each word, detects the fitness of each word contained in the acquired email, and the email obtained from those fitness is appropriate Determining whether the content is correct,
Updating the fitness level information by recalculating the fitness level for each word included in the email to be determined according to the determination result for the email; and
Obtaining an e-mail sent to an external device, and
In the step of updating the fitness information, the email transmitted to the external device is assumed to be an email with an appropriate content, and the fitness for each word included in the email is recalculated, thereby recalculating the fitness. An e-mail evaluation method characterized by updating fitness information. Obtaining an email sent from an external device;
Extracting words contained in the email;
Refers to the fitness information indicating the fitness that is indexed by the appropriateness of each word, detects the fitness of each word contained in the acquired email, and the email obtained from those fitness is appropriate Determining whether the content is correct,
Updating the fitness level information by recalculating the fitness level for each word included in the email to be determined according to the determination result for the email, and
In the step of determining the contents of the e-mail, the sender address of the acquired e-mail is registered as the e-mail address of the illegitimate user with reference to the illegitimate address table in which the e-mail address of the illegitimate user is registered in advance. Then, the e-mail evaluation method is characterized in that the e-mail is determined to have inappropriate contents. A function of holding a fitness indexed by the appropriateness of each word as fitness information in order to determine whether the email sent from the external device is appropriate for the recipient user;
The ability to retrieve emails sent from external devices;
The ability to extract words contained in emails;
A function of detecting the suitability of each word included in the e-mail with reference to the suitability information and determining whether or not the e-mail has appropriate content from the suitability;
A function of updating the fitness information by recalculating the fitness for each word included in the email to be judged according to the judgment result for the email;
If the sender address of the acquired email is registered as the email address of the authorized user by referring to the authorized address table in which the email address of the authorized user is registered in advance, the email has an appropriate content. A function for determining
E-mail evaluation program characterized by causing a computer to exhibit A function of holding a fitness indexed by the appropriateness of each word as fitness information in order to determine whether the email sent from the external device is appropriate for the recipient user;
The ability to retrieve emails sent from external devices;
The ability to extract words contained in emails;
A function of detecting the suitability of each word included in the e-mail with reference to the suitability information and determining whether or not the e-mail has appropriate content from the suitability;
A function of updating the fitness information by recalculating the fitness for each word included in the email to be judged according to the judgment result for the email;
A function of obtaining an e-mail to be transmitted to the external device by the user;
A function of updating the fitness information by recalculating the fitness for each word included in the email, assuming that the email sent from the user has appropriate content;
E-mail evaluation program characterized by causing a computer to exhibit A function of holding a fitness indexed by the appropriateness of each word as fitness information in order to determine whether the email sent from the external device is appropriate for the recipient user;
The ability to retrieve emails sent from external devices;
The ability to extract words contained in emails;
A function of detecting the suitability of each word included in the e-mail with reference to the suitability information and determining whether or not the e-mail has appropriate content from the suitability;
A function of updating the fitness information by recalculating the fitness for each word included in the email to be judged according to the judgment result for the email;
If the sender address of the acquired email is registered as the email address of the unauthorized user by referring to the unauthorized address table in which the email address of the unauthorized user is registered in advance, the email is inappropriate. A function to determine that
E-mail evaluation program characterized by causing a computer to exhibit

Images