JP2010191864A - Automatic task generation system, and method and program for the same - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To facilitate task management. <P>SOLUTION: An automatic task generation system includes: a feature word extracting means 400 for extracting feature words being words related to a time and a place from received mail; a tag selecting means 450 for selecting tags associated with a task from among the feature words; and a task generating means 500 for generating a task on the basis of the feature words. When there exist a plurality of tasks attached with the same tags, the tag selecting means 450 detects an appearance frequency of the same tags so as to weight the same tags according to the appearance frequency. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

  The present invention relates to an automatic task generation system, a method thereof, and a program thereof that analyze an email content when receiving an email, extract items that are likely to become user tasks, and automatically generate a task.

  Users often request and contract tasks by e-mail, but if they want to register a task that occurs at that time, the following steps are required.

  The trouble is that you read the contents of the email carefully, know the time and place of the task, what you need to do, then start the task management system and manually register the task in the task management system It is.

  In business, tasks often occur during mail transmission / reception, but task recognition errors may occur as mail transmission / reception is repeated. In addition, missed tasks may be caused by skipping mail.

  Similarly, task management is an important issue. When confirming existing tasks, there are cases where it is desired to confirm the tasks in time series, and there are cases where it is desirable to grasp the tasks in a categorized state.

  Therefore, an invention that analyzes text data of received e-mail, obtains a feature set such as metadata, content, context, keyword, time, day of the week, etc., and determines and classifies the intention of the text data based on these features is disclosed in Patent Literature 1 is disclosed.

JP-A-2005-316953

  However, the invention disclosed in Patent Document 1 does not have sufficient consideration for disclosing the analysis result to the user, makes it difficult to grasp the status of the acquired feature set, and as a result, the task management by the user is difficult There was a problem of becoming.

  The present invention has been made in view of the above. The present invention automatically extracts a task from an email and notifies the user of the task, thereby preventing a task recognition error or oversight, and facilitating task management performed by the user himself / herself. An object of the present invention is to provide an automatic task generation system, a method thereof, and a program thereof.

  In order to solve the above-described problem, an automatic task generation system, a method thereof, and a program thereof according to the present invention are provided in an automatic task generation system that analyzes the contents of a received mail, extracts items, and automatically generates a task. A feature word extracting unit that extracts a feature word that is a word related to time and place from the received mail; a tag selecting unit that selects a tag to be associated with the task from the feature word; and Task generation means for generating a task, wherein the tag selection means detects the frequency of appearance of the same tag when there are a plurality of the tasks with the same tag, and according to the frequency of appearance Thus, the same tag is weighted.

  In order to solve the above-described problem, the method for automatically generating a task according to the present invention is a method for automatically generating a task by analyzing the contents of the received mail, extracting items, and automatically generating a task. A feature word extraction procedure for extracting a feature word, which is a word related to time and place, a tag selection procedure for selecting a tag to be associated with the task from the feature word, and generating the task based on the feature word A task generation procedure, wherein the tag selection procedure detects an appearance frequency of the same tag when there are a plurality of the tasks with the same tag, and determines the same frequency according to the appearance frequency. The tag is weighted.

  In order to solve the above-described problem, the automatic task generation program according to the present invention analyzes the contents of the received mail, extracts the items, and automatically generates a task. A feature word extraction process for extracting a feature word that is a word related to time and place from the tag, a tag selection process for selecting a tag to be associated with the task from the feature word, and generating the task based on the feature word A task generation process executed by a computer, and the tag selection process detects an appearance frequency of the same tag when there are a plurality of the tasks with the same tag, and determines the appearance frequency according to the appearance frequency. The same tag is weighted.

  According to the present invention, a task automatic generation system that automatically extracts a task from an e-mail and notifies the user of the task, prevents a task recognition error and oversight, and facilitates task management performed by the user himself, and a method thereof The program can be provided.

It is a figure which shows the structure of the automatic task generation system of 1st Embodiment which concerns on this invention. It is a figure which shows the case where a tag is highlighted. It is a flowchart which shows operation | movement of the automatic task creation system of 1st Embodiment which concerns on this invention. It is a figure which shows the structure of the automatic task generation system of 2nd Embodiment which concerns on this invention. It is a figure which shows the structure of the task automatic generation system of 3rd Embodiment concerning this invention.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

[First Embodiment]
FIG. 1 is a diagram showing a configuration of an automatic task generation system according to the first embodiment of the present invention. Arrows indicate the flow of data.

  According to FIG. 1, in the automatic task generation system according to the first embodiment of the present invention, first, the mail server 100 receives a mail from a sender describing a task to be requested of a recipient.

  The mail is received by the mailer 200 in which the task automatic generation system according to the first embodiment of the present invention is incorporated, and the received mail is passed to the natural language processing means 300.

  The natural language processing means 300 analyzes the content of the email and confirms the style of the email. At this time, in the case of a sentence style such as a request sentence or a command sentence, there is a high possibility that contents to be a task are described in the mail.

  Next, the feature word extraction unit 400 performs feature word extraction that extracts feature words that are words related to time and place from the mail.

  Tag selection means 450 collects elements for generating a task from feature words extracted from the contents of the received mail, and selects a tag associated with the task. At this time, when there are a plurality of tasks with the same tag, the appearance frequency of the same tag is detected, and the same tag is weighted according to the appearance frequency.

  The selected tag is used as a tag cloud for search in task management, and a tag with higher appearance frequency is highlighted and displayed as in the example of FIG. Here, FIG. 2 is a diagram illustrating a case where the tag is highlighted.

  The task generation unit 500 generates a task to be actually performed by the receiver based on the feature word.

  The receiver confirms the task generated by the task generation unit 500, corrects the task if necessary, and registers the task in the task storage device 600 as it is.

  The processing of analyzing the content of the received mail by the natural language processing means 300 and confirming the style of the mail, and the processing by the task generation means 500 are based on known techniques such as morphological analysis and syntax analysis, and therefore will be described. Omitted.

[Operation of First Embodiment]
The operation of the automatic task creation system according to the first embodiment of the present invention will be described in detail with reference to the drawings. FIG. 3 is a flowchart showing the operation of the automatic task creation system according to the first embodiment of this invention.

  First, an e-mail describing the contents of the requested task is transmitted (step S1).

  The mailer 200 of the automatic task creation system according to the first embodiment of the present invention receives an email related to a task request (step S2).

  The natural language processing means 300 performs natural language processing of the mail and analyzes the style (step S3).

  If the natural language processing means 300 can extract a task from the received mail (step S4: Yes), the process proceeds to the next step. Otherwise, the process ends (step S4: No).

  Next, the feature word extraction unit 400 extracts feature words from the mail, and extracts feature words for generating tasks such as time and place (step S5).

  Tag selection means 450 selects a tag to be attached to the task from the extracted feature words (step S6).

  The task generation unit 500 generates a task as accurate as possible from the output result (step S7). As an example, it is possible to convey more accurate information to the user if the details are known, such as “meeting at □□ at □□” rather than “meeting at XX”.

  The automatic task creation system according to the first embodiment of the present invention asks the recipient whether or not to register the task extracted from the mail (step S8). If Yes, register, and if No, end without registering.

  The receiver confirms the preview of the task to be registered and selects whether or not to correct the contents (step S9). If correction is selected (step S9: Yes), the error part is corrected in step S10.

  The automatic task creation system according to the first embodiment of this invention registers the generated task in the task storage device 600.

[Second Embodiment]
Next, the configuration of the second exemplary embodiment of the present invention will be described in detail with reference to FIG. Here, FIG. 4 is a diagram illustrating a configuration of the automatic task generation system according to the second embodiment of this invention.

  Referring to FIG. 4, in this embodiment, the mailer 200 having the configuration in the embodiment shown in FIG. 1 is changed to the mobile phone terminal 201, and the task storage device 600 is changed to the scheduler 601 in the mobile phone terminal. It is different in point.

  This embodiment includes a mail server 101, a mobile phone terminal 201, a natural language processing unit 301, a feature word extraction unit 401, a tag selection unit 451, a task generation unit 501, and a scheduler 601.

  In this embodiment, a task can be extracted from an email received by the mobile phone terminal 201 and automatically registered in the schedule and calendar functions of the scheduler 601 provided in the mobile phone terminal 201. .

  Accordingly, there is an advantage that the user can perform two operations “view mail” and “register schedule” at a time.

[Third Embodiment]
The configuration of the third embodiment of the present invention will be described in detail with reference to FIG. Here, FIG. 5 is a diagram illustrating a configuration of the automatic task generation system according to the second embodiment of this invention.

  Referring to FIG. 5, the present embodiment is changed to the task storage service 602 on the network in which the task storage device 600 having the configuration in the embodiment shown in FIG. 1 is connected via the network. Is different.

  This embodiment includes a mail server 102, a mailer 202, a natural language processing means 302, a feature word extraction means 402, a tag selection means 452, a task generation means 502, and a task storage service 602 on the network.

  This embodiment is an example in which a task can be extracted from received mail and automatically registered in a schedule or calendar service on the network.

  As a result, the user can link the schedule data registered on the network with other network applications.

  The present invention can be implemented not only as an apparatus but also as a method invention and a program invention.

  The present invention belongs to the field of task management, and in particular, takes out tags from feature word extraction and classifies tasks, and can be used not only for mail but also for analysis of digitized data.

100, 101, 102 Mail server 200 Mailer 201 Mobile phone terminal 202 Mailer 300, 301, 302 Natural language processing means 400, 401, 402 Feature word extraction means 450, 451, 452 Tag selection means 500, 501, 502 Task generation means 600 Task storage device 601 Scheduler 602 Task storage service

Claims (8)

In the automatic task generation system that analyzes the contents of the received mail, extracts items and automatically generates tasks,
Feature word extraction means for extracting feature words that are words related to time and place from the received mail;
Tag selection means for selecting a tag associated with the task from the feature words;
Task generation means for generating the task based on the feature word;
With
The tag selection means detects the frequency of appearance of the same tag when there are a plurality of the tasks with the same tag, and weights the same tag according to the frequency of appearance. Automatic task generation system characterized by   2. The tag selection unit uses the tag for search in managing the task, and displays the tag with a high appearance frequency in an emphasized manner according to the appearance frequency. Automatic task generation system described.   The automatic task generation system according to claim 1, wherein the automatic task generation system is incorporated in a mobile phone terminal, and includes a scheduler having functions of a schedule and a calendar instead of the task storage device.   The automatic task generation system according to claim 1, wherein the task storage device is connected to the automatic task generation system via a network. In the method of automatic task generation that analyzes the contents of the received mail, extracts items and automatically generates tasks,
A feature word extraction procedure for extracting a feature word that is a word related to time and place from the received mail;
A tag selection procedure for selecting tags to be associated with the task from the feature words;
A task generation procedure for generating the task based on the feature word;
With
In the tag selection procedure, when there are a plurality of the tasks with the same tag, the frequency of appearance of the same tag is detected, and the same tag is weighted according to the frequency of appearance. A method of automatic task generation characterized by   6. The tag selection procedure uses the tag for a search when managing the task, and displays the tag with a high appearance frequency in an emphasized manner according to the appearance frequency. The method of automatic task generation described. In the automatic task generation program that analyzes the contents of the received mail, extracts items, and automatically generates tasks,
A feature word extraction process for extracting a feature word that is a word related to time and place from the received mail;
A tag selection process for selecting tags to be associated with the task from the feature words;
Task generation processing for generating the task based on the feature word;
To the computer,
In the tag selection process, when there are a plurality of the tasks with the same tag, the appearance frequency of the same tag is detected, and the same tag is weighted according to the appearance frequency. A program for automatically generating tasks.   8. The tag selection process uses the tag for a search in managing the task, and the tag with a high appearance frequency is highlighted and displayed according to the appearance frequency. The automatic task generation program described.

Images