JP2010277204A - Information classification processing apparatus, method, and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To achieve general versatility and practicality in a processing speed in information classification. <P>SOLUTION: A data acquiring part 15A acquires object data included in a processing-objective time section out of a plurality of history data including time information, and a data classification part 15D classifies the object data with a time difference within a threshold value with respect to the temporally adjacent object data, out of the object data, based on the time information of the object data, as a same group. <P>COPYRIGHT: (C)2011,JPO&INPIT

Description

  The present invention relates to an information processing technique, and more particularly, to an information classification technique for grouping data including time information.

  Along with the increase in capacity of hard disks, a large amount of information has been stored continuously and in large quantities as history. For example, surveillance cameras installed at various locations store images of the installed locations on a hard disk for a long time. The Web browser keeps holding the URL and title history of the Web page displayed by the browser for a certain period. A mobile phone keeps a history of incoming and outgoing calls for a certain number of times. In addition, many people regularly back up the document being edited in the PC. It can be said that such a backup file is also an update history of the document.

  The history data accumulated in this way can be used in various ways such as confirming and remembering later, restoring the old state, and making new discoveries by looking again. However, these history data automatically accumulated easily expands enormously. In other words, there is always a problem of information flooding where useful information is buried in it and cannot be searched well. Therefore, research on techniques for acquiring necessary information when necessary from a large amount of historically accumulated data has been actively conducted.

  For example, Google Desktop Search (registered trademark) of Google Inc. can search for necessary information from a file in a desktop PC or a web browsing history by inputting a keyword. The HCB tool refers to a page similar to the currently browsed web page or the same URL stored in the web browsing history database, or traces the web page stored in the web browsing history database in chronological order. Or search with reference to a search keyword input in the past (see, for example, Non-Patent Document 1).

  In the process of searching for information, people look at the information to materialize their vague interests or find interest in other things. That is, information needs gradually change according to the information that is seen. For this reason, it is said that a system for searching for information should realize an overview display and a detailed display of an information source, and smoothly go back and forth between the displays.

  The system realizes an overview display and detailed display of information, so that users who use the system first have an overview of the information source, and then look at the details of the information that they are likely to find, and obtain the necessary information. Information can be acquired interactively according to changing interests, such as searching for new necessary information found in the process and returning to the overview display and continuing the search. Even in a system that searches history data recorded in time series, it is possible to support efficient search of history data by similarly realizing such an overview display and detailed display.

  As a method for realizing an overview display and a detailed display of history data, there is an overview / detail display of history data based on a grouping of accumulated history data. In the present invention, the history data refers to the minimum unit of history for recording the behavior of an arbitrary target. For example, in the Web browsing history, a set of URL, title, and time stamp recorded when a specific Web page is opened corresponds to the history data. Similarly, in the case of a history of a monitoring camera that records an image at a specific sampling period, a set of one image and a time stamp is used as history data. Hereinafter, a set of the plurality of history data may be expressed as history data.

In the overview display, information about the group is presented for each grouped history data, and in the detailed display, the contents of the data are displayed for each individual history data, realizing the overview display and detailed display. it can.
If the user can interactively change the grouping granularity, the user can search the history data while switching between the overview display and the detailed display. If the granularity of the grouping can be changed, it is possible to broadly classify a large number of historical data into a small number of groups and overview the grouping of historical data, and to browse the obtained small classification groups in detail. This is because

Yoshinari Shirai, Yasuhiro Yamamoto, Kumiyo Nakakoji: A history-centric approach for enhancing web browsing experiences, CHI '06: CHI '06 extended abstracts on Human factors in computing systems, pp. 1319-1324, 2006.

However, such a conventional information classification technique has a problem that its practicality is poor in terms of versatility and processing speed.
When grouping historical data, it is necessary to determine a grouping method. As a grouping method, for example, a video indexing technique in which videos are classified into scenes in order to make it easy to search for necessary videos from videos over a long period of time can be used. The basic algorithm is that if a change in the pixel value exceeds a certain level between the images before and after the video, it is interpreted that the scene has changed, and the video is segmented (segmented). is there. Such a technique can be used for grouping of a history of videos in which a specific place is recorded for a long period of time, such as videos of surveillance cameras.

  In addition, for example, a method of performing grouping by performing clustering using closeness between words included in a document may be considered. For example, a search result by Google Desktop Search (registered trademark) of Google Inc. can be regarded as being classified into a document group including the search keyword and a document group not including the search keyword. In HCB-tempo, Web browsing history recorded in time series is grouped by a method in which the person enters a search keyword into a search system such as Google (registered trademark) (for example, (See Non-Patent Document 1, etc.).

  However, these conventional grouping methods are less versatile because they depend on the recording format of history data. For example, grouping by clustering using closeness between words included in a document requires that history data be recorded in text, and grouping using patterns and brightness values included in an image is history The data must include an image. The grouping method used in HCB-tempo is also specialized for Web browsing history. At present, when building a history data search system, it is necessary to implement a grouping method suitable for the history data format each time.

  In order to go back and forth between the overview and details, it is necessary to change the grouping granularity based on the user's interactive operation, but the grouping granularity cannot be changed or even if it can be changed There are many grouping techniques that are difficult to perform in real time.

  For example, in HCB-tempo, grouping is performed by cutting off the timing input by a search keyword, but this method cannot change the grouping granularity. In the case of grouping using the similarity between words contained in a document or the change in luminance value in the video, the grouping granularity can be changed by changing the similarity or the threshold value of the luminance value. When calculating the similarity or the like based on the contents (contents) of an image, generally pre-processing is necessary, and it is not suitable for grouping history data recorded in real time.

  The present invention has been made to solve such problems, and it is an object of the present invention to provide an information classification technique that is practical in terms of versatility and processing speed.

  In order to achieve such an object, the information classification processing device according to the present invention acquires, from among a plurality of data including time information, data for acquiring the target data included in the processing target time interval in which the time information is specified. Based on the time information of the target data, an acquisition unit, and a data classification unit that classifies target data whose time difference between the target data and the target data that are temporally adjacent to each other within a threshold value are classified as the same group. Yes.

  At this time, the data classification unit further includes a threshold value acquisition unit that acquires a new threshold value input by the operation, and the data classification unit is a target whose time difference from the target data temporally adjacent to the target data is within the new threshold value. Data may be classified as the same group.

  In addition, the information classification processing method according to the present invention acquires target data included in a display target time interval specified by the time information from a plurality of data including time information, and classifies the target data into groups. An information classification processing method used in an information classification processing device, wherein a data acquisition unit acquires target data included in a specified processing target time interval from a plurality of data including time information. Data in which the data acquisition step and the data classification unit classify target data whose time difference from the target data temporally adjacent to the target data is within the threshold among the target data as the same group based on the time information of the target data And a classification step.

  In addition, the program according to the present invention acquires, from among a plurality of data including time information, target data included in the display target time interval in which the time information is specified, and classifies these target data into groups. In the computer of the processing device, the data acquisition unit acquires the target data included in the specified processing target time interval from the plurality of data including the time information, and the data classification unit includes: Based on the time information of the target data, a data classification step of classifying the target data whose time difference from the target data temporally adjacent to the target data is within a threshold is performed as the same group.

  According to the present invention, it is possible to classify based on general time information included in common in any classification processing target data, not information specific to the classification processing target data, and extremely high versatility is obtained. In addition, since the classification is based on the time difference of each target data, the target data can be classified without requiring complicated information processing, and the time required for the classification process can be greatly reduced. . Thereby, it is possible to realize an information classification technique that is practical in terms of versatility and processing speed.

It is a block diagram which shows the structure of the information classification system concerning 1st Embodiment. It is a flowchart which shows the data classification process of the information classification processing apparatus concerning 1st Embodiment. It is a structural example of text edit history data. It is an example of text edit history data before data classification processing (unclassified). It is an example of text edit history data after data classification processing (threshold value: 1 second). It is an example of text edit history data after a data classification process (threshold value: 5 seconds). It is a structural example of sketch input history data. It is an example of sketch input history data after data classification processing (threshold value: 1 second). It is a thumbnail image output example.

Next, embodiments of the present invention will be described with reference to the drawings.
[First Embodiment]
First, an information classification system according to a first embodiment of the present invention will be described with reference to FIG. FIG. 1 is a block diagram showing the configuration of the information classification system according to the first exemplary embodiment of the present invention.
The information classification system 1 includes an information classification processing device 10 and a database (DB) 20.

The database 20 includes a storage device such as a hard disk as a whole, and has a function of storing a plurality of data including time information such as history data indicating the history of various processes. The history data includes various history data such as web pages viewed with a web browser, emails sent and received with email software, document files edited with word processing software, video files taken with a surveillance camera, and incoming and outgoing calls on mobile phones. . These history data are attached with time information indicating the date and time when the process is executed.
Hereinafter, a case where data stored in the database 20 is history data will be described as an example.

  The information classification processing device 10 is composed of an information processing device such as a personal computer or a server as a whole, and has a function of acquiring history data stored in the database 20 and classifying it by group.

  In the present embodiment, the data acquisition unit 15A acquires target data included in the processing target time period from among a plurality of history data including time information, and the data classification unit 15D acquires the target data based on the time information of these target data. Among these target data, the target data whose time difference with the target data temporally adjacent is within the threshold is classified as the same group.

[Information classification processor]
Next, the configuration of the information classification processing device according to the first exemplary embodiment of the present invention will be described in detail with reference to FIG.
The information classification processing device 10 includes an input / output I / F unit 11, an operation input unit 12, a screen display unit 13, a storage unit 14, and an arithmetic processing unit 15 as main functional units.

The input / output I / F unit 11 includes a dedicated data input / output circuit, and has a function of receiving arbitrary history data from the database 20 by performing data communication with the database 20 under the control of the arithmetic processing unit 15. is doing.
The operation input unit 12 includes an operation input device such as a keyboard and a mouse, and has a function of detecting a user operation and outputting the operation to the arithmetic processing unit 15.

The screen display unit 13 includes a screen display device such as an LCD or a PDP, and has a function of performing screen display of history data acquired from the operation menu or the database 20 under the control of the arithmetic processing unit 15.
The storage unit 14 includes a storage device such as a hard disk or a semiconductor memory, and has a function of storing processing information and programs used in various display processes in the arithmetic processing unit 15.

The arithmetic processing unit 15 has a microprocessor such as a CPU and its peripheral circuits, reads and executes a program in the storage unit 14, and realizes various processing units by causing the hardware and the program to cooperate with each other. It has a function.
As main processing units realized by the arithmetic processing unit 15, there are a data acquisition unit 15A, a time order sorting unit 15B, a threshold value acquisition unit 15C, and a data classification unit 15D.

The data acquisition unit 15 </ b> A has a function of acquiring time information of a designated display target time interval according to a user operation detected by the operation input unit 12, and among the history data stored in the database 20, the history It has a function of searching history data whose time information of data is included in the display target time section, and acquiring these as target data.
The time order sorting unit 15B has a function of sorting the target data in time order based on the time information of the target data acquired by the data acquisition unit 15A.

The threshold value acquisition unit 15C has a function of acquiring an initial threshold value set in advance in the storage unit 14, and a new threshold value that is input according to a user operation detected by the operation input unit 12. It has a function to acquire.
The data classifying unit 15D classifies the target data sorted by the time order sorting unit 15B into the same group with the target data whose time difference from the adjacent target data is within the threshold acquired by the threshold acquiring unit 15C. And a function for displaying the obtained classification result on the screen display unit 13.

[Operation of First Embodiment]
Next, the operation of the information classification processing apparatus according to the first embodiment will be described with reference to FIG. FIG. 2 is a flowchart showing data classification processing of the information classification processing apparatus according to the first embodiment.
The arithmetic processing unit 15 of the information classification processing device 10 executes the data classification processing of FIG. 2 in response to the processing start instruction by the user operation detected by the operation input unit 12.

When a person creates a document with a text editor, he or she usually enters a word or phrase one after another, and then stops once to key in the next word or phrase. Also, the stop interval tends to be short when a word or a short sentence is typed and long when a long sentence or paragraph is written. This is because it takes time to think about the sentence according to the length of the sentence.
Based on this hypothesis, when grouping is actually performed using the interval for each text editing operation, the history data is grouped into words or phrases if the threshold for grouping is small, and the threshold is increased. It was found that it was grouped into sentences and paragraphs to some extent. In the following, description will be given by taking an editing history of text to be actually recorded as an example.

  FIG. 3 is a configuration example of text editing history data. Here, a text editor that records history data for each key operation is assumed. The history data recorded by this text editor is, for example, as shown in FIG. The input character (text) is recorded with the input time and the input position information together with the start position and the end position. The start position and the end position indicate how many characters from the beginning of the sentence are replaced by the input characters.

The history data in FIG. 3 is obtained when “Tomorrow is a business trip. The place is Tokyo.” However, when “Tokyo” is entered, “Kyo” is entered incorrectly. “Kyo” is deleted and “Tokyo” is re-entered.
FIG. 4 is an example of text editing history data before data classification processing (unclassified). Here, a group ID, a time interval of history data included in the group, and a presentation text to be presented as the contents of the group are registered as a set for each group. In this case, each history data can be regarded as forming an individual group.

  In the data classification process of FIG. 2, the arithmetic processing unit 15 first acquires the time information of the processing target time interval designated from the operation input unit 12 by the data acquisition unit 15 </ b> A, and the history data accumulated in the database 20. Among them, the history data in which the time information of the history data is included in the display target time section is searched, and these are acquired as the target data (step 100).

Next, the arithmetic processing unit 15 sorts the target data in time order based on the time information of each target data acquired by the data acquisition unit 15A by the time order sorting unit 15B (step 101).
In addition, the arithmetic processing unit 15 acquires a new threshold value input by an operation in accordance with an initial threshold value preset in the storage unit 14 or a user operation detected by the operation input unit 12 (step). 102).

  Thereafter, the arithmetic processing unit 15 classifies the target data that is sorted by the time order sorting unit 15B and whose time difference from the adjacent target data is within the threshold value into the same group (step 103). The classification result thus obtained is displayed on the screen display unit 13 (step 104), and a series of data classification processing is completed.

FIG. 5 is an example of text editing history data after data classification processing (threshold value: 1 second). In step 102, when “1 second” is acquired as the threshold value by the threshold value acquisition unit 15C, the data classification unit 15D determines that the time difference between previous and next history data is within one second, Classify as
At this time, the classification result presented to the user, here, the text string of each history data belonging to the group, presents the editing result within the group.

For example, the history data of ID41 and ID42 are classified as the same group because the time difference is “0 seconds” and is equal to or less than the threshold value. Similarly, the history data of ID42 and ID43 and the history data of ID43 and ID44 are classified into the same group because the K time difference is less than or equal to the threshold value. Thereby, the history data of ID41-ID44 become the same group.
On the other hand, since the time difference between the history data of ID44 and ID45 is “2 seconds” and is larger than the threshold value, the history data of ID45 belongs to a different group from the history data of ID41 to ID44, and a new group is created. And belong to that group.

  Thus, when a group is created, the group becomes as shown in FIG. If the editing result of the text performed in the group is presented to the user in units of groups, the presented text in the group composed of the history data of ID52 to ID56 is “Tokyo,” and within the group. The error input made in will disappear from the presentation text.

FIG. 6 is an example of text editing history data after data classification processing (threshold value: 5 seconds), and shows the classification result when “5 seconds” is set as the threshold value. Thus, if the presentation text grouped with a relatively long threshold value is presented, the user can overview the text editing history.
On the other hand, as shown in FIG. 4 described above, if the presentation text that is not grouped is presented, the user browses the text editing history in detail including the editing process that does not appear explicitly in the resulting text. can do.

  In this way, the classification granularity can be easily changed by changing the threshold value. Therefore, for example, if the threshold acquisition unit 15C allows the user to change the threshold for grouping with a slider or the like, the user can overview the text editing history and find his interest. In response, the user can browse the overview display and the detailed display, such as viewing in detail.

[Effect of the first embodiment]
As described above, in the present embodiment, the data acquisition unit 15A acquires target data included in the processing target time interval from among a plurality of history data including time information, and the data classification unit 15D acquires these target data. Based on the time information, among the target data, the target data whose time difference with the target data that is temporally adjacent is within a threshold is classified as the same group.

  Therefore, it is possible to classify according to general time information that is included in common in any classification processing target data, not information unique to the classification processing target data, and extremely high versatility is obtained. In addition, since the classification is based on the time difference of each target data, the target data can be classified without requiring complicated information processing, and the time required for the classification process can be greatly reduced. . Thereby, it is possible to realize an information classification technique that is practical in terms of versatility and processing speed.

  Further, in the present embodiment, the threshold value acquisition unit 15C acquires a new threshold value input by the operation, and the data classification unit 15D newly adds a time difference from the target data that is temporally adjacent to the target data. Since the target data within a certain threshold is classified as the same group, the user can classify the target data with an arbitrary granularity by changing the threshold. As a result, the user can easily go back and forth between the overview display and the detailed display as the display of the classification processing target data, and can search for the desired data extremely efficiently.

  In the present embodiment, before the target data is classified by the data classification unit 15D, the time order sorting unit 15B sorts each target data in time order based on the time information of the target data. Two target data that are temporally adjacent can be easily extracted, and a time difference can be calculated from a difference in time information of these target data. As a result, the time required for the classification process can be significantly reduced.

[Second Embodiment]
Next, an information classification processing system according to the second exemplary embodiment of the present invention will be described.
In the first embodiment, the case where the present invention is applied as a system for searching a text editing history has been described as an example. In this embodiment, a case where the present invention is applied as a system for searching a sketch input history will be described.
Note that the information classification processing system according to the present embodiment merely replaces the text editing history used in the first embodiment with the sketch input history as classification processing target data. Is the same as in the first embodiment. Therefore, detailed description here is omitted.

[Operation of Second Embodiment]
When drawing a sketch, a person first thinks about what kind of sketch to draw, then inputs it as a stroke on the sketch screen, sees the drawn sketch, and what is newly drawn, that is, The sketch is completed while repeating input and thought, such as thinking about whether to add or erase.
Therefore, by grouping using “interval” of thoughts appearing between sketches, the state of the sketch can be presented for each meaningful sketch block (a set of strokes).

FIG. 7 is a configuration example of sketch input history data. Here, for each input stroke, an ID, a stroke start time, an end time, and a coordinate array are registered as a set.
FIG. 8 is an example of sketch input history data after the data classification process (threshold value: 1 second), and shows the classification result when “5 seconds” is set as the threshold value. Here, the group ID, the time when the input of each stroke included in the group is completed, and the ID of each stroke included in the group are registered as a set.

The sketch input history records the stroke input start time and end time and the coordinate group constituting the input stroke when each stroke constituting the sketch is input. The state transition history of the sketch screen records which ID of the stroke input in this way is currently displayed on the screen every time the configuration of the displayed stroke changes. .
Thus, for example, when a stroke is added by inputting a stroke or when a part of the stroke is erased from the screen, the state of the stroke displayed on the screen is recorded at that timing.

In the data classification unit 15D, the history data is grouped by comparing the time difference between the history data, in this case, the time difference between the stroke end and start times, by comparing the threshold values with respect to the state transition history. Create a thumbnail image of the sketch screen and present it. At this time, the thumbnail image of each group presents, for example, the state having the largest number of strokes among the history data belonging to the group.
FIG. 9 is an example of thumbnail image output. In this example, the image sequence 30 is not grouped and a thumbnail image is created in units of history data. Therefore, a thumbnail image is created for each stroke input.

  When the threshold value is changed and grouped, the image row 31 and the image row 32 are displayed. A plurality of history data are grouped, and thumbnail images are created based on the history data having the largest number of strokes in the group. As the threshold value is increased as in the image sequence 32, the created sketch group can be overviewed. On the other hand, as the threshold value is decreased as in the image sequence 30, the sketch process becomes more detailed. You can browse through.

In the input history of the sketch, each history data holds not the time information indicating the moment but the time interval from the start to the end of the stroke. Therefore, in the present embodiment, it is only necessary to determine whether or not to group the time difference from the end time of the previous history data to the start time of the next history data by comparing the threshold values.
In this way, the history data is grouped, and for example, all the strokes included in the group are displayed as thumbnail images corresponding to each group. Such a presentation makes it possible to look up the history of the sketch and search for the necessary past state while following the details.

[Third Embodiment]
Next, an information classification processing system according to a third embodiment of the present invention will be described.
In the present embodiment, not only text editing and sketch creation, but also a case where personal history data is classified will be described. The information classification processing system according to the present embodiment uses a history of human behavior as classification processing target data, but the other configuration is the same as that of the first embodiment, and detailed description here Is omitted.

  When a person takes some action, he / she performs steps of thinking → behavior → thinking → behavior → ... at various levels. For this reason, the history data recorded from the viewpoint of the individual appears between the actions. By using this, history data can be grouped and browsed for each unit of cognitive behavior performed by a person.

For example, in the web browsing history, history data (time stamp, URL, title, etc.) is generally recorded at the timing when a new web page is opened. Thinking about everyday web browsing, search for information for some purpose (for example, search for paper references), and if information is found, use it to do some thought or work (for example, write a paper) ) Searching for information that has become necessary as a result of consideration and work is performed again from the WWW, such as searching for information and searching for other information. Is often present.
If web browsing histories are grouped according to the time “between” the browsing of a web page and the browsing of the next web page, the history data included in the group is semantically similar to some extent. Become.

In addition, a photograph taken by an individual with a digital camera or the like can be regarded as a photographing history of the person. Of course, photos taken consecutively at a certain time have moved from nearby places. For example, a photo taken on the same date may be roughly related to a trip or event.
Considering that a person sleeps for 5 or 6 hours a day (does not shoot during that time), setting the threshold to 5 or 6 hours will allow the person's photos to be grouped by trip or event. Also, when viewed from a microscopic viewpoint in time, a person often shoots the same subject continuously. By using the present invention, it is possible to browse these continuously taken photographs of the same subject as one group.

[Fourth Embodiment]
Next, an information classification processing system according to the fourth exemplary embodiment of the present invention will be described.
In the present embodiment, a case where history data indicating the occurrence history of an arbitrary event is classified will be described. Note that the information classification processing system according to the present embodiment uses the event occurrence history as the classification processing target data, but the other configurations are the same as those in the first embodiment, and the detailed description here is as follows. Omitted.

  In this case, since the time information of the history data indicating the occurred event indicates instantaneous time information as in the first embodiment, the data classification process has the same contents as in the first embodiment. It becomes. This makes it possible to classify not only individual histories but also histories of various events that have occurred.

  On the other hand, the technique according to the first embodiment cannot be applied as it is to history data sampled at a fixed interval, such as a video of a surveillance camera or a history of a moving locus by GPS. However, the present technique can be applied if these history data can be handled as a history recorded in units of events by performing some preprocessing.

  For example, when still images are recorded with a constant sampling period by a monitoring camera, the history data becomes a group of still images with time stamps recorded at a constant interval. The difference between each still image recorded in this way and a specific background image, for example, the sum of the absolute value of the color value difference for each pixel is equal to or less than a certain threshold value. Things are not treated as historical data. Such processing may be executed by a registration source external device that registers history data in the database 20, or may be executed by the data acquisition unit 15A.

  As a result, only the data that has changed more than a certain amount with respect to the background image remains in the history data as history data, which is the history data recorded when an event of some change occurs in the background image. . The present technique can be applied to history data subjected to such preprocessing.

[Extended embodiment]
The present invention has been described above with reference to the embodiments, but the present invention is not limited to the above embodiments. Various changes that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention.

  Moreover, although each embodiment demonstrated as an example the case where the database 20 was implement | achieved by the apparatus independent from the information classification processing apparatus 10, it is not limited to this, The memory | storage part of the information classification processing apparatus 10 14 may implement the database 20.

  As for the threshold setting method by the user, a numerical value may be directly input, or may be input intuitively using a slider interface or a mouse gesture.

  DESCRIPTION OF SYMBOLS 1 ... Information classification system, 10 ... Information classification processing apparatus, 11 ... Input / output I / F part, 12 ... Operation input part, 13 ... Screen display part, 14 ... Memory | storage part, 15 ... Operation processing part, 15A ... Data acquisition part , 15B ... time order sorting unit, 15C ... threshold value acquisition unit, 15D ... data classification unit, 20 ... database.

Claims (4)

A data acquisition unit that acquires target data included in a specified processing target time interval from a plurality of data including time information;
A data classifying unit that classifies target data having a time difference within a threshold value within a threshold value among the target data based on time information of the target data as a same group. Information classification processing device. In the information classification processing device according to claim 1,
A threshold acquisition unit for acquiring a new threshold input by the operation;
The information classification processing device, wherein the data classifying unit classifies target data having a time difference with respect to target data that is temporally adjacent to the target data within the new threshold as the same group. An information classification processing method used in an information classification processing apparatus for acquiring target data included in a specified display target time interval from a plurality of data including time information and classifying the target data into groups Because
A data acquisition step in which the data acquisition unit acquires target data included in a specified processing target time interval from among a plurality of data including time information;
A data classification step in which a data classification unit classifies the target data whose time difference from the target data temporally adjacent to the target data is within a threshold based on the time information of the target data as the same group. An information classification processing method characterized by comprising: From among a plurality of data including time information, the target information included in the display target time section in which the time information is designated is acquired, and the computer of the information classification processing device that classifies these target data into groups,
A data acquisition step in which the data acquisition unit acquires target data included in a specified processing target time interval from among a plurality of data including time information;
A data classification step in which a data classification unit classifies the target data whose time difference from the target data temporally adjacent to the target data is within a threshold based on the time information of the target data as the same group. The program to be executed.

Images