JP2016206841A - Task management device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a task management device capable of instantaneously grasping a task related to an object person when facing the object person without performing any operation such as complicate data processing.SOLUTION: A task management device includes: task storage means (45) capable of storing an object person and a task related to the object person in association; task acquisition means (10-14) for extracting the task and the object person from an input voice on the basis of a keyword for extracting the task and a keyboard for extracting the object person related to the task, and for causing the task storage means to store the task and object person; specifying data storage means (23) for storing data related to a specifying image for specifying the object person; determination means (22) for determining whether or not the specifying image is included in a photographic image corresponding to image data output from a camera; and task reading means (24) for, when the specifying image is included, reading the task stored in association with the object person corresponding to the specifying image in the task storage means.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a task management apparatus capable of reading a task stored in association with a target person.

  Conventionally, each participant's utterance input to each voice input device provided for each participant in the conference is converted into document data, and each document data is converted to each speaker along the time series (that is, the channel of the voice input device). (For example, see Patent Document 1).

JP2013-73323A

  If a keyword search is performed on data created by the apparatus described in Patent Document 1 using a personal computer (hereinafter referred to as a personal computer), a task related to each participant can be grasped. However, it is desirable that the tasks related to the colleagues of the company can be immediately grasped at the time of meeting without performing a search or the like using a personal computer. In addition, if the data created by the apparatus described in Patent Document 1 is processed largely in advance by hand, it may be possible to immediately read out the task related to the subject. Complicated work is required for processing.

  Therefore, the present invention provides a task management device that can immediately grasp a task related to a target person when facing the target person without performing complicated operations such as data processing. It was made as a purpose.

  The present invention includes a task storage unit, a task acquisition unit, a specifying data storage, a determination unit, and a task reading unit. The task storage means can store the subject and the task related to the subject in association with each other. The task acquisition means extracts the task and the target person related to the task from the input speech based on the keyword for extracting the task and the keyword for extracting the target person related to the task, and supports both In addition, it is stored in the task storage means. Therefore, the target person and the task related to the target person are automatically associated and stored in the task storage unit.

  The specifying data storage means stores data relating to the specifying image for specifying the subject. The determining means determines whether or not the specified image is included in the captured image corresponding to the image data output from the camera based on the data stored in the specifying data storage means. When the determination unit determines that the specifying image is included, the task reading unit reads the task stored in the task storage unit in association with the target person corresponding to the specifying image. For this reason, if the camera is pointed at the target person when facing the target person, the task related to the target person can be immediately grasped. In addition, since the task is stored in the task storage means automatically, it is not necessary to perform complicated data work in order to make such a grasp possible.

It is a block diagram showing the structure of the task management apparatus with which this invention was applied. It is a flowchart showing the process by the 1st control part of the task management apparatus. It is a flowchart showing the process by the 2nd control part of the said task management apparatus. It is a flowchart showing the registration process by the information display part of the said task management apparatus. It is a flowchart showing the task display process by the information display part. It is a flowchart showing in detail the function development task display process in the task display process. It is a flowchart showing in detail the bug corresponding task display process in the task display process. It is a flowchart showing in detail the support task display process in the task display process. It is explanatory drawing showing the example of a display by the said task display process. It is explanatory drawing showing a part of the example of a display in detail. It is a flowchart showing the action execution process in the said task display process in detail.

Embodiments to which the present invention is applied will be described below with reference to the drawings.
[1. First Embodiment]
[1-1. Constitution]
The task management apparatus shown in FIG. 1 is configured as a task management system including an information terminal device 1 and a task information management server 40 configured to be able to communicate with each other. A plurality of information terminal devices 1 may be provided for one task information management server 40. Moreover, the information terminal device 1 can also be configured by downloading appropriate software (so-called application) to the smartphone as described below.

  The information terminal device 1 includes a voice recording unit 10, a voice data storage unit 11, a first control unit 12, a document data storage unit 13, and a second control unit 14 as a processing system related to voice. The voice recording unit 10 records voice input from the outside of the information terminal device 1 and stores it as voice data in a voice data storage unit 11 as a voice memory. The voice recording unit 10 receives and records the voices of a plurality of speakers as illustrated as voice input A, voice input B, and voice input C in FIG. The first control unit 12 reads the audio data stored in the audio data storage unit 11, documents the audio data, creates document data 18, and stores it in the document data storage unit 13 as a document memory. The second control unit 14 reads out the document data 18 stored in the document data storage unit 13 and extracts task information 19 by performing keyword extraction on the document data 18.

  The information terminal device 1 includes an information display unit 20 and a communication unit 30 in addition to the processing system related to the voice. The information display unit 20 includes a camera 21, a face recognition function unit 22, a data storage unit 23, a task display unit 24, a touch panel 25, a shape recognition function unit 27, and a task information interference function unit 28. The face recognition function unit 22, the task display unit 24, the shape recognition function unit 27, and the task information interference function unit 28 may be divided on software in one microcomputer, or may be configured by different microcomputers. Good. The camera 21 outputs image data corresponding to the captured video. The data storage unit 23 is a memory capable of storing various data such as data transmitted / received via the communication unit 30. The touch panel 25 is a known one provided with a display using a color liquid crystal or the like.

The face recognition function unit 22 extracts a face image from the image data output from the camera 21, determines a person corresponding to the face image, and sends it to the data storage unit 23. The task display unit 24 displays an image captured by the camera 21 on the touch panel 25. Further, the task display unit 24 acquires the task information 19 from the task information management server 40 when the task information 19 corresponding to the person determined by the face recognition function unit 22 exists, and the camera 21 captures the task information 19. The image is superimposed on the person image 90 (details of the display method will be described later).

  The shape recognition function unit 27 determines the shape of the object photographed by the camera 21 from the image data output from the camera 21, and sends the determination result to the task information interference function unit 28. The task information interference function unit 28 is displayed on the touch panel 25 when the object shape determined by the shape recognition function unit 27 is a predetermined finger shape (an example of an instruction image) registered (ie, stored) in advance. Interference such as erasure is performed on the task information 19.

  The communication unit 30 communicates with the task information management server 40. For example, the communication unit 30 transmits the task information 19 extracted by the second control unit 14 to the task information management server 40. For example, the communication unit 30 transmits the task information 19 read from the task information management server 40 to the data storage unit 23. In addition, the communication unit 30 transmits the person discrimination result by the face recognition function unit 22 to the task information management server 40.

  The task information management server 40 includes a communication unit 41, a task management processing device 43, and a task storage unit 45. The communication unit 41 transmits and receives the above-described task information 19 and the like with the communication unit 30. The task storage unit 45 is a memory that stores (that is, stores) the task information 19. The task management processing device 43 is configured by a microcomputer or the like, and controls communication by the communication unit 41 and task registration (hereinafter also referred to as storage: storing) and reading with respect to the task storage unit 45.

[1-2. processing]
[1-2-1. Processing related to voice]
Next, processing executed in the information terminal device 1 will be described. When a predetermined panel operation is performed on the information terminal device 1, the first control unit 12 executes a process (hereinafter, also referred to as a document process) shown in the flowchart of FIG.

  In this process, first, the voice of the conference participant (an example of the target person) is recorded in S1 (S represents a step; the same applies hereinafter), and in the subsequent S2, the voiceprint of the participant is recorded from the recorded voice. Is registered. Various forms of processing of S1 can be considered. For example, in S1, the sound from when the start of recording is instructed by the panel operation in the information terminal device 1 until the stop of recording is instructed, It may be recorded as the voice of one participant. Further, in S2, the participant's voiceprint may be registered in association with the name, affiliation, etc. of the participant who has entered the text by panel operation. Moreover, in S1, the audio | voice recorded by opening the silence period more than fixed time (for example, 2 second) may be processed as an audio | voice of a different participant. In that case, in S2, a name or the like inputted by text for each participant may be registered in association with each voiceprint.

  In S3 following S2, voice (that is, speech) at a meeting or the like is recorded. This recording may also be performed until a recording stop is instructed after a recording start is instructed by a panel operation in the information terminal device 1. Further, as will be described later, since the process of S3 is repeatedly executed during the execution of the documenting process, if there is a silent period of a certain time (for example, 2 seconds) or more even if a recording stop instruction is not given, The process may move to S4.

In S4 following S3, the voice recorded in S3 is collated with the voiceprint registered in S2. In subsequent S5, based on the collation in S4, it is determined whether or not there is a person who has registered a voiceprint that matches the voiceprint recorded in S3. If such a person exists (S5: Y), after the speaker of the voice is specified as the person in S6, the process proceeds to S7. On the other hand, when such a person does not exist (S5: N), after the voice speaker is set unspecified in S8, the process proceeds to S7.

  In S7, the voice recorded in S3 is documented (that is, converted into document data 18). In subsequent S9, the documented data is stored in the document data storage unit 13 in association with the speaker information, and the process proceeds to S3 described above. In S9, the documented data may be stored in the document data storage unit 13 in association with date / time information representing the recording date / time. If the information terminal device 1 is provided with position detecting means such as GPS, the documented data may be stored in the document data storage unit 13 in association with the location information indicating the recording location in S9. Good. Through the above processing by the first control unit 12, audio in a meeting or the like is stored in the document data storage unit 13 as document data 18.

  In conjunction with the processing by the first control unit 12, the second control unit 14 executes the processing shown in the flowchart of FIG. In this process, first, keywords are extracted from the document data 18 that has been documented and stored in the document data storage unit 13 in S11. As this keyword, for example, a well-known keyword described in JP 2014-135543 A can be used. In the present embodiment, keywords such as “development” and “project” are extracted as keywords indicating that the type of task is function development. In the present embodiment, keywords such as “bug” and “complaint” are extracted as keywords indicating that the type of task is bug handling. In the present embodiment, keywords such as “support” and “support” are extracted as keywords indicating that the task type is support.

  In S13 subsequent to S11, in response to the keyword extraction result in S11, with respect to the document data 18 of each utterance stored in the document data storage unit 13, the utterer of the utterance, the contents of the task, the time limit of the task, the task The contents of the task person or the like who treats are extracted. This information is stored as task information 19 in the temporary memory of the communication unit 30, for example.

  For example, if the document data 18 of a certain statement has the content “Please △△ by Mr. XX”, the following task content information, deadline information, task handler information, Are extracted and stored as task information 19 in association with each other. That is, “XX” is a task handler based on the keyword “san”, “XX” is a due date based on the keyword “by”, and “△△” is a task based on the keyword “Please” Are extracted and stored as task information 19. If the above-described keyword “development” is further included in the document data 18 extracted as the contents of the task, the type of the task is set as function development. Similar processing is performed on other keywords and task types.

  In subsequent S <b> 15, communication is performed via the communication unit 41 and the communication unit 30 of the task information management server 40. In subsequent S17, the task information 19 stored in S13 is registered in the task management processing device 43 of the task information management server 40, and the process proceeds to S11 described above. Note that when the task information 19 is registered in the task management processing device 43 by the processing of S13, the task information 19 is divided for each task person and further for each type of task, and is stored in the task storage unit 45. Saved (ie, stored).

In the present embodiment, the task types are classified into three types: function development, bug handling, and support. Function development includes tasks such as development of new functions and improvement of existing functions. The bug handling includes tasks such as software bug correction. Support includes tasks such as work that is not directly linked to deliverables, such as the creation of documents and procedures for project management.

[1-2-2. Processing related to video]
Further, in the information display unit 20 related to the video, a registration process shown in the flowchart of FIG. 4 is executed as advance preparation. This process is started when the information terminal device 1 is set to the registration mode by a panel operation.

  As shown in FIG. 4, in this process, first, a process of photographing a face with the camera 21 is executed in S21. Specifically, in this process, for example, a face image is extracted from image data output from the camera 21 when a shutter operation is performed in the information terminal device 1 by a well-known image analysis, and the face image is stored in the data storage unit. 23 is stored.

  In subsequent S23, processing for registering the face image photographed in S21 is executed. In this process, similar to the process of S2 described above, the document data such as the name and affiliation of the person and the image data of the face image (an example of the identification image) input by the panel operation in the information terminal device 1 are included. The data is stored in the data storage unit 23 in association with each other.

  In subsequent S <b> 25, processing is performed in which the camera 21 captures the shape of the finger associated with the action. In this process, specifically, for example, a finger shape is extracted from image data output from the camera 21 when a shutter operation is performed in the information terminal device 1 by a known image analysis, and an image of the finger shape is obtained. Is stored in the data storage unit 23. Note that the finger shape stored in this process may be a moving image showing a series of finger movements.

  In subsequent S27, a process of registering the image photographed in S25 in association with the action is executed, and the process is temporarily ended. In this process, the action selected from the menu by the panel operation in the information terminal device 1 and the finger-shaped image are registered in the data storage unit 23 in association with each other.

  In this registration process, if either the face image or the finger shape has already been registered and only registration of the other one is desired, a part of the process is passed by instructing cancellation by panel operation. be able to. For example, if cancellation is instructed at the time when the process of S21 is started, the process passes through S21 and S23 without doing anything so that only a finger-shaped image is registered without registering a face image. Registration is possible (S25, S27). If cancellation is instructed at the time when the processing of S25 is started, only the face image is registered by passing through the processing of S25 and S27 substantially without doing anything (S21, S23). The process can be completed without registering the shape image.

  When the information terminal device 1 is set to the task display mode by a panel operation in such a registration process, the information display unit 20 executes the task display process shown in the flowchart of FIG.

As shown in FIG. 5, in this process, first, in S31, shooting by the camera 21 is started, and image analysis for image data corresponding to video shot by the camera 21 is started. In subsequent S32, it is determined whether or not the camera 21 has photographed a face, that is, whether or not a face image has been extracted from image data corresponding to a video photographed by the camera 21. If the camera 21 has not photographed a face (S32: N), the process repeats S32 as it is and waits. If the camera 21 photographs a face (S32: Y), the process proceeds to S33. In S33, the face photographed by the camera 21 is collated with the face image registered in the data storage unit 23 as image data by the registration process. In subsequent S34, based on the collation result in S33, it is determined whether or not the face photographed by the camera 21 matches any of the registered face images.
If the face photographed by the camera 21 does not match any of the registered face images (S34: N), the process proceeds to S32 described above, and if it matches any of the face images (S34: Y), the process proceeds to S35.

  In S35, the name of the person photographed by the camera 21 is specified based on the registration contents by the registration process. Note that the processing of S32 to S35 is processing by the face recognition function unit 22.

  In subsequent S37, communication is performed via the communication unit 41 and the communication unit 30 of the task information management server 40, and the task information 19 in which the person is a task person is transferred to the task management processing device 43 of the task information management server 40. Via the task storage unit 45. The acquired task information 19 is stored in the data storage unit 23. In subsequent S38, the type of task in which the photographed person is registered as a task handler is acquired from the task information 19 stored in the data storage unit 23. In the subsequent S39, the time limit of the task in which the photographed person is registered as the task handler is acquired from the task information 19 stored in the data storage unit 23.

  In subsequent S40, a function development task display process as shown in detail in the flowchart of FIG. 6 is executed. As shown in FIG. 6, in this process, first, it is determined in S41 whether or not there is a task whose function type is the function development acquired in S38 among the tasks for which the person is a task handler. Is judged. If there is a task whose type is function development (S41: Y), it is determined in S42 whether there is a task whose deadline (hereinafter also referred to as deadline) has passed. To be judged. If there is one whose deadline has passed (S42: Y), the process proceeds to S43. In S43, the task is displayed on the red rectangular pop-up screen 91A, and the process proceeds to S44.

  As illustrated in FIG. 9, when the camera 21 is photographing a face (Y in S <b> 32), a photographed person image 90 is displayed on the touch panel 25. Therefore, in S44, a pop-up screen 91A composed of a thin red rectangle is displayed over the person image 90, and the task contents and the like are displayed in black on the pop-up screen 91A. Although details of the pop-up screen 91A are omitted in FIG. 9, in detail, as shown in FIG. 10, various information is displayed as character strings on the pop-up screen 91A. That is, the type of task (in this case, function development), the name of the task registrant (for example, the speaker), the name of the task handler, the deadline of the task, and the specific content of the task are character strings. It is displayed. The same applies to other pop-up screens 91B to 93 described later shown in FIG.

  Returning to FIG. 6, on the other hand, when there is no file whose deadline has passed (S42: N), the process directly proceeds from S42 to S44. In S44, it is determined whether or not there is a task whose deadline is close (for example, less than three days until the deadline) among the tasks whose type of task is function development. In addition, the time as a threshold for determining that the deadline is close (that is, the remaining time until the deadline) is set to an appropriate value for each information terminal device 1, and a different value can be set for each type of task. It is. If it is determined in S44 that there is a close deadline (S44: Y), the process proceeds to S45. In S45, the task is displayed on a yellow rectangular pop-up screen 91B (see FIG. 9), and the process proceeds to S47. On the other hand, when there is no close deadline (S44: N), the process directly proceeds from S44 to S47.

In S47, it is determined whether or not there is a task whose type is function development. That is, it is determined whether or not there is a task whose function type is function development that has not passed the deadline and whose deadline is not near. If it is determined that there are more task types of function development (S47: Y), the process is S48.
Migrate to In S48, the task is displayed on the blue rectangular pop-up screen 91C (see FIG. 9), and the process proceeds to S50 in FIG. On the other hand, if there is no other task type of function development (S47: N), the process directly moves from S47 to S50 in FIG. If it is determined in S41 described above that there is no task whose function is developed in S38 among the tasks in which the person is a task handler (S41: N) The process directly moves from S41 to S50 in FIG.

  In S50, a bug handling task display process as shown in detail in the flowchart of FIG. 7 is executed. As shown in FIG. 7, this process is the same as the function development task display process described above except that the type of task to be processed is different and the shape of the pop-up screen is different.

  That is, in this process, first, it is determined in S51 whether there is a task whose bug type is the task type acquired in S38 among the tasks for which the person is the task handler. . If there is a task type corresponding to a bug (S51: Y), it is determined whether there is a task whose deadline has passed (S52), and the deadline has passed. If something exists (S52: Y), the process proceeds to S53. In S53, the task is displayed on the red triangle pop-up screen 92A (see FIG. 9), and the process proceeds to S54.

  In S54, it is determined whether or not there is a task whose deadline is close among the tasks whose task type is bug handling. If there is a task whose deadline is close (S54: Y), the process is as follows. The process proceeds to S55. In S55, the task is displayed on the yellow triangular pop-up screen 92B (see FIG. 9), and the process proceeds to S57. In S57, it is determined whether or not there is another task type corresponding to a bug. If there is a task type (S57: Y), the task is displayed in a blue triangular pop-up screen (not shown) in S58. ) And the process proceeds to S60 of FIG.

  On the other hand, when a negative determination is made in any of S52, S54, and S57 described above (S52: N, S54: N, or S57: N), the subsequent processing of S53, S54, or S58 is skipped. If it is determined in S51 that none of the tasks for which the person is a task handler is a bug-compatible task type acquired in S38 (S51: N), Shifts directly from S51 to S60 in FIG.

  In S60, a support task display process as shown in detail in the flowchart of FIG. 8 is executed. As shown in FIG. 8, this process is the same as the function development task display process described above except that the type of task to be processed is different and the shape of the pop-up screen is different.

  That is, in this process, first, it is determined in S61 whether or not there is a task whose support type is the task type acquired in S38 among the tasks for which the person is a task handler. If there is a task whose type is support (S61: Y), it is determined whether there is a task whose deadline has passed (S62) and the deadline has passed. Is present (S62: Y), the process proceeds to S63. In S63, the task is displayed on a red round pop-up screen 93 (see FIG. 9), and the process proceeds to S64.

In S64, it is determined whether there is a task with a close deadline among the tasks whose task type is support. If there is a task with a close deadline (S64: Y), the process is S65. Migrate to In S65, the task is displayed on a yellow round pop-up screen (not shown), and the process proceeds to S67. In S67, it is determined whether or not there is a task whose type is support, and if it exists (S67: Y),
In S68, the task is displayed on a blue round pop-up screen (not shown), and the process proceeds to S71 in FIG.

  On the other hand, when a negative determination is made in any of S62, S64, and S67 described above (S62: N, S64: N, or S67: N), the subsequent processing of S63, S64, or S68 is skipped. If it is determined in S61 that there is no support for the task type acquired in S38 among the tasks for which the person is a task handler (S61: N), the process is as follows. The process directly moves from S61 to S71 in FIG. Note that the processing of S37 to S60 is processing by the task display unit 24.

  As shown in FIG. 5, in S71, whether or not the camera 21 has taken a finger shape within a predetermined time (for example, several seconds) after the display processing in S40 to S60 is completed, that is, an image taken by the camera 21. It is determined whether or not a finger-shaped image has been extracted from the image data corresponding to. If the camera 21 has not taken a finger-shaped image (S71: N), the process proceeds directly to S32 described above. On the other hand, if the camera 21 captures a finger-shaped image within the predetermined time (S71: Y), the process proceeds to S72.

  In S72, the finger-shaped image captured by the camera 21 is collated with the finger-shaped image registered in the data storage unit 23 by the registration process. In subsequent S73, based on the collation result in S72, it is determined whether or not the finger-shaped image captured by the camera 21 matches the registered finger-shaped image. If the finger-shaped image captured by the camera 21 does not match the registered image (S73: N), the process proceeds to S32 as it is, and if the finger-shaped image matches the registered image. (S73: Y), the process proceeds to S75.

  In S75, the action linked to the shape of the finger is specified based on the registration contents by the registration process. In S76, the action is executed, and the process proceeds to S32 described above. The processing of S71 to S73 is processing by the shape recognition function unit 27, and the processing of S75 and S76 is processing by the task information interference function unit 28.

  Here, although various forms can be considered as an action, an interference process for deleting a human task displayed as an image 90 on the touch panel 25 will be described as an example. As the shape of the finger for instructing the interference, for example, a pop-up screen (any one of 91A to 93) corresponding to the task to be erased with the thumb and forefinger is displayed on the screen displayed on the touch panel 25 (i.e., virtual). -The shape of the finger to be picked in the reality space). However, other finger shapes can be freely registered by the registration process as finger shapes for instructing erasure.

  When the action associated with the finger shape is erasure, the details of the processing in S76 are as shown in the flowchart of FIG. As shown in FIG. 11, in this process, first, the position of the finger with respect to the camera 21 is specified in S761. In other words, the display position of the finger captured by the camera 21 and displayed on the touch panel 25 with respect to the person image 90 captured by the camera 21 and displayed on the touch panel 25 is specified. In subsequent S763, a task (that is, a pop-up screen) designated by the finger is specified. In subsequent S765, data of the task information 19 corresponding to the pop-up screen specified in S763 is deleted from the task storage unit 45 by communication with the task information management server 40, and the process proceeds to S32 in FIG. Then, when the task information 19 is subsequently subjected to the various display processes of S40 to S60 described above, the pop-up screen corresponding to the task information 19 is not displayed.

Of course, it goes without saying that an image in which the pop-up screen corresponding to the task information 19 disappears may be more aggressive. For example, an image in which the pop-up screen moves to the side or explodes may be displayed.

  If the action is not erasure, but other action such as changing the time limit, in S765, the data of the corresponding task information 19 may be altered instead of erasing the data. The task information 19 may include information such as priority, importance, and necessity of alert. In this case, the action is an operation for changing the priority, importance, necessity of alert, and the like. May be. Even in that case, in S765, the data of the corresponding task information 19 may be altered instead of being erased.

[1-3. effect]
According to the first embodiment described in detail above, the following effects can be obtained.
[1A] In the present embodiment, when a face image of a person registered in advance is included in the image corresponding to the image data output from the camera 21 (S34: Y), the task storage unit 45 associates with the person. The stored task is automatically read and displayed (S35 to S60). For this reason, when facing a target person (person), if the camera is pointed at the target person, the task related to the target person can be immediately grasped.

  [1B] In addition, the tasks related to each target person (that is, the task person) are automatically stored as task information 19 in the task storage unit 45 by the processing of the first control unit 12 and the second control unit 14. For this reason, since the task information 19 is automatically registered for each target person, it is not necessary to perform complicated operations such as data processing in order to enable the grasp as shown in [1A]. Further, the user of the information terminal device 1 can manage and share tasks without being aware of the task management processing device including the information terminal device 1 and the task information management server 40.

  [1C] The task information 19 is also generated by documenting the input voice (S7) and then extracting keywords from the document (S11). For this reason, the processing can be simplified and the processing accuracy can be improved as compared with the case where the keyword is extracted directly from the voice.

  [1D] Furthermore, in the processing of the first control unit 12 and the second control unit 14, the input voice is collated with a pre-registered voiceprint (S4), and the information of the speaker of the voice also constitutes the task information 19 Is stored as information to be performed (S13). For this reason, the task information 19 representing the task relating to each subject can be extracted more accurately. For example, it is possible to accurately estimate who is the task handler as “I” from a statement such as “I will Δ △”.

  [1E] In the present embodiment, pop-up screens 91 </ b> A to 93 representing tasks are displayed on the person image 90 (specifically, the body image) displayed according to the image data output from the camera 21. (S40 to S60). The pop-up screens 91A to 93 display task contents and the like as documents. For this reason, the task related to the subject can be grasped visually.

  [1F] Moreover, in the present embodiment, the shapes and colors of the pop-up screens 91A to 93 are different depending on the type of task and the time limit. For this reason, the kind and time limit of each task concerning a subject can be grasped visually better.

[1G] In the present embodiment, when the pop-up screens 91A to 93 are displayed and the camera 21 captures a finger-shaped image registered in advance (S71: Y, S73: Y), the finger shape is tied. The attached action can be executed (S76). That is, the owner of the information terminal device 1 can reach a task corresponding to a desired pop-up screen by reaching out in front of the camera 21 and making the finger shape. For example, when the action is erasure, the person who is photographing the task relating to the person photographed by the camera 21 can be erased. For this reason, for example, when a task requested by a subordinate to a subordinate is requested in the middle, an operation for deleting a task related to the subordinate first requested can be easily performed.

  [1H] Although FIG. 1 shows one information terminal device 1 and one task information management server 40, one task information management server 40 may be shared by a plurality of information terminal devices 1. . In this case, in this embodiment, the task information 19 extracted via the voice recording unit 10 of each information terminal device 1 is shared by each information terminal device 1 via one task information management server 40, and It can be used for task display processing. Therefore, the task related to the subject to whom the camera 21 is directed can be grasped more accurately.

  In the embodiment, the task storage unit 45 is the task storage unit, the data storage unit 23 is the identification data storage unit, the touch panel 25 is the task display unit, the task information interference function unit 28 is the task operation unit, the information The terminal device 1 corresponds to a mobile terminal, the task information management server 40 corresponds to a server, and the face recognition function unit 22 corresponds to a determination unit. A configuration from the voice recording unit 10 to the second control unit 14 corresponds to a task acquisition unit. Among them, the configuration related to the process of S6 in the first control unit 12 is related to the speaker specifying means, the configuration related to the process of S7 in the first control unit 12 is related to the documenting means, and the process related to S11 in the second control unit 14 is related. The configuration corresponds to the keyword extraction unit, and the configuration related to the process of S13 in the second control unit 14 corresponds to the task extraction unit. In addition, the configuration relating to the processing of S37 to S39 in the task display unit 24 corresponds to task reading means.

[2. Other Embodiments]
As mentioned above, although embodiment of this invention was described, this invention can take a various form, without being limited to the said embodiment.

  [2A] In the above embodiment, a smartphone is used as the information terminal device 1, but the present invention is not limited to this. For example, pop-up screens 91A to 93 corresponding to the task information 19 are superimposed on an image of a subject actually seen through the glasses via a glasses-type display device as described in JP-A-2006-338163. May be displayed.

  [2B] In the embodiment described above, the pop-up screens 91A to 93 have different display forms depending on the type of task (that is, task attributes), and the pop-up screens 91A to 93 have different colors as the display form. However, the present invention is not limited to this. For example, the colors and shapes used as the pop-up screens 91A to 93 can be arbitrarily set. Further, only the outlines of the pop-up screens 91 </ b> A to 93 may be colors according to the deadline. As the display mode of the pop-up screen, in addition to the shape and color, the display position of the pop-up screen, the vertical relationship between the pop-up screens (that is, the relationship between overlapping and overlapping), the size of the pop-up screen, the character color, and the character size There are various display modes such as a font of characters. These display modes may be associated with task attributes or deadlines in any way. For example, the color of the pop-up screen may be varied depending on the type of task (that is, the task attribute), and the shape of the pop-up screen may be varied depending on the task deadline. Furthermore, all pop-up screen display modes may be the same regardless of task attributes and time limits.

  [2C] In the above embodiment, task types such as function development, bug handling, and support are set as task attributes. However, the present invention is not limited to this. For example, as task attributes, attributes such as “schedule for action”, “schedule for treatment”, and “miscellaneous memo” are set depending on the presence / absence of date / time information and the presence / absence of location information, as described in Japanese Patent Application Laid-Open No. 2014-135543, for example. May be.

  [2D] In the above-described embodiment, the task information 19 is displayed as the pop-up screens 91 </ b> A to 93 on the person image 90. However, the present invention is not limited to this. For example, the character string corresponding to the task information 19 may be directly displayed as a caption on the person image 90. Further, when a shutter operation is performed with the camera 21 facing the target person, only the character string corresponding to the task information 19 is displayed on the touch panel 25, and the person image 90 may not be displayed. Further, the task information 19 may be output by voice via an earphone or the like connected to the information terminal device 1.

  [2E] In the above embodiment, the voice for extracting the task information 19 is input to the voice recording unit 10 provided in the information terminal device 1, but the present invention is not limited to this. For example, a microphone may be provided for each speaker in a conference room or the like, and the task information 19 may be extracted based on sound input via each microphone. That is, the task acquisition unit, the camera, and the task reading unit may be provided in separate devices. For example, voice may be input to the voice recording unit 10 of the information terminal device 1 including a smartphone, and the pop-up screens 91A to 93 may be displayed on the glasses-type display device as shown in [2A].

  Conversely, a task storage unit 45 may be provided for each information terminal device 1, and all processing may be completed inside the information terminal device 1. The information terminal device 1 may transmit the image data corresponding to the video captured by the camera 21 and the audio data recorded by the audio recording unit 10 to the task information management server 40 as they are. In that case, almost all the above-described processes may be executed by the task information management server 40, and image data to be displayed on the touch panel 25 as it is may be transmitted from the task information management server 40 to the information terminal device 1.

  [2F] In the above embodiment, the target person is specified based on the face image photographed via the camera 21 (that is, the face image is used as the specifying image), but the present invention is not limited to this. It is not a thing. For example, when the name tag, employee ID, etc. of the subject can be read via the camera 21, the subject may be specified based on a character string such as the name tag. In addition, in the case where a barcode for specifying the target person (may be a two-dimensional bar code) is described on the name tag or the like, the target person may be specified based on the barcode. .

  [2G] In the above-described embodiment, when a plurality of pop-up screens 91A to 93 are displayed, an operation such as erasure (that is, an operation such as erasure) according to the positional relationship between the shape of the finger as the instruction image and each of the pop-up screens 91A to 93 The task in which the interference occurs is determined, but is not limited to this. For example, an operation such as deleting all the tasks related to the plurality of displayed pop-up screens 91 </ b> A to 93 may be possible.

  [2H] In the embodiment described above, after the input voice is documented (S7), the task information 19 is generated by keyword extraction for the document. However, the present invention is not limited to this. Absent. For example, a task and its treatment person may be obtained directly from voice data, and task information may be generated based on the task.

  [2I] The functions of one component in the embodiment may be distributed as a plurality of components, or the functions of a plurality of components may be integrated into one component. Further, at least a part of the configuration of the embodiment may be replaced with a known configuration having the same function. Moreover, you may abbreviate | omit a part of structure of the said embodiment. Further, at least a part of the configuration of the embodiment may be added to or replaced with the configuration of the other embodiment. In addition, all the aspects included in the technical idea specified only by the wording described in the claim are embodiment of this invention.

  [2J] In addition to the task management device described above, various forms such as a system including the task management device as a constituent element, a program for causing a computer to function as the task management device, a medium storing the program, a task management method, and the like Thus, the present invention can be realized.

DESCRIPTION OF SYMBOLS 1 ... Information terminal device 10 ... Voice recording part 11 ... Voice data storage part 12 ... 1st control part 13 ... Document data storage part 14 ... 2nd control part 18 ... Document data 19 ... Task information 20 ... Information display part 21 ... Camera DESCRIPTION OF SYMBOLS 22 ... Face recognition function part 23 ... Data storage part 24 ... Task display part 25 ... Touch panel 27 ... Shape recognition function part 28 ... Task information interference function part 40 ... Task information management server 30, 41 ... Communication part 43 ... Task management processing apparatus 45 ... Task storage unit 90 ... Images 91A, 91B, 91C, 92A, 92B, 93 ... Pop-up screen

Claims (9)

Task storage means capable of storing a subject and a task related to the subject in association with each other;
Based on the keyword for extracting the task and the keyword for extracting the target person related to the task, the task and the target person related to the task are extracted from the input voice, and the task storage is associated with both. Task acquisition means to be stored in the means;
Specifying data storage means for storing data relating to the specifying image for specifying the target person;
Determining means for determining whether the specified image is included in the captured image corresponding to the image data output from the camera, based on the data stored in the specifying data storage means;
Task reading means for reading out a task stored in the task storage means in association with a target person corresponding to the specifying image when the determining means determines that the specifying image is included;
A task management device comprising: The task acquisition means includes
Documenting means for converting the input voice into document data;
Keyword extracting means for extracting each of the keywords from the document data converted by the documenting means;
Task extraction means for extracting a task and a target person related to the task from the document data based on the keyword extraction result by the keyword extraction means;
The task management apparatus according to claim 1, further comprising: The task acquisition means includes
A speaker specifying means for comparing the input voice and a voice print stored in advance for each target person and specifying a speaker of the voice,
In addition,
The task management device according to claim 2, wherein the task extracting unit extracts the task and a target person related to the task with reference to a speaker specified by the speaker specifying unit. When the captured image is displayed and the specified image is included in the captured image, the task read by the task reading unit corresponding to the target corresponding to the specified image represents the target Task display means for displaying the photographed image as a document in an overlapping manner,
The task management device according to claim 1, further comprising:   The task management device according to claim 4, wherein the task display unit displays the task as a pop-up screen so as to overlap the photographed image representing the target person. In the task storage means, the task is stored in association with the attribute of the task,
The task management apparatus according to claim 5, wherein a display mode of the pop-up screen differs according to an attribute of the task displayed as the pop-up screen. In the task storage means, the task is stored in association with the deadline of the task,
The task management apparatus according to claim 5 or 6, wherein a display mode of the pop-up screen differs according to a time limit of the task displayed as the pop-up screen. When an instruction image stored in advance as an image of a body part instructing an operation for a task displayed as the pop-up screen is included in the captured image, task operation means for executing the operation according to the instruction image,
The task management apparatus according to claim 5, further comprising: A mobile terminal and a server configured to communicate with each other;
The portable terminal includes the camera, the task acquisition unit, and the task reading unit,
The task management apparatus according to claim 1, wherein the server includes the task storage unit.

Images