Information processing device and method, storage medium and computer program product

Abstract

An information processing device, a storage medium and an information processing method, wherein the information processing device comprises: an acquisition unit, which acquires information of the contents recorded in a plurality of first information browsed by a user, namely content information; an extraction unit, which extracts a part edited by the user from a second information, namely an object on which the user performs operations; and a determination unit, which determines, from the content information, the first information browsed by the user when editing the part or before and after editing, among the plurality of first information.

Description

Technical Field

[0001] The present invention relates to an information processing device, a storage medium and an information processing method. Background Art

[0002] For example, Patent Document 1 describes a server device capable of improving the accuracy of user attention to web pages and the like. The server device comprises: an information acquisition unit that acquires, from a terminal device, information regarding scrolling operations on a display area and content identification information used to identify the content displayed in the display area; and an attention calculation unit that calculates, based on the acquired scrolling information, the user's attention to the content identified by the acquired content identification information. Furthermore, when calculating the attention based on the scrolling information, the attention calculation unit adjusts the attention based on a weighting corresponding to a parameter that influences the time it takes for a user to grasp the content of a directory.

[0003] Patent Document 1: Japanese Patent No. 5185240

[0004] However, when editing information by referring to the descriptions of a plurality of web pages, there may be web pages that are useful for editing and web pages that are not useful. Summary of the Invention

[0005] The object of the present invention is to provide an information processing device, a storage medium and an information processing method, in which, when editing second information using the record of first information, the first information used when editing a certain part of the second information can be determined.

[0006] In order to achieve the above-mentioned purpose, the information processing device involved in the first method comprises: an acquisition unit, which acquires information about the content recorded in a plurality of first information browsed by a user, namely content information; an extraction unit, which extracts a part edited by the user from the object of the operation performed by the user, namely second information; and a determination unit, which determines, from the content information, the first information browsed by the user when editing the part or before and after editing, among the plurality of first information.

[0007] Furthermore, in the information processing device involved in the second embodiment, in the information processing device involved in the first embodiment, the acquisition unit further acquires information related to the operation performed by the user on the first information, namely, interaction information, and the determination unit further uses the interaction information to further determine the determined first information as first information with availability.

[0008] Furthermore, in the information processing device according to the third aspect, in the information processing device according to the second aspect, the interaction information is information related to an operation performed by the user on the first information browsed before or after the editing.

[0009] Furthermore, in the information processing device according to a fourth aspect, in the information processing device according to the third aspect, the interaction information includes information obtained from content of an operation performed by the user on the first information through an input device used.

[0010] Furthermore, in the information processing device according to the fifth aspect, in the information processing device according to the fourth aspect, the interaction information further includes browsing time, which is a time when the user browsed the first information.

[0011] Furthermore, in the information processing device involved in the 6th mode, in the information processing device involved in any one of the 1st mode to the 5th mode, when the part extracted by the extraction unit is edited twice by the user, the determination unit determines that the first information determined during the second editing is higher in usability than the first information determined during the first editing.

[0012] Furthermore, in the information processing device involved in the 7th embodiment, in the information processing device involved in the 6th embodiment, the value indicating the availability of the first information is derived based on the feature amount obtained from the content information, and the determination unit outputs the value indicating the availability of the first information that records the newly recorded content in the part as larger than the value indicating the availability of the initially determined first information, and outputs the value indicating the availability of the initially determined first information as smaller than the value indicating the availability of the undetermined first information in the first information browsed by the user.

[0013] Furthermore, in the information processing device involved in the 8th mode, in the information processing device involved in any one of the 1st mode to the 5th mode, the acquisition unit further acquires operation information related to the operation performed by the user on the second information at at least one time before, during and after browsing the first information, and the determination unit further uses the operation information to further determine the determined first information as first information with availability.

[0014] Furthermore, in the information processing device involved in the 9th embodiment, in the information processing device involved in the 1st embodiment, the acquisition unit further acquires information related to the operation performed by the user on the first information, namely, interaction information and operation information related to the operation performed by the user on the second information at at least one time before, during and after browsing the first information, and the determination unit derives a value representing the availability of the first information based on a feature quantity obtained from at least one of the content information, the interaction information and the operation information, and further determines the first information with availability based on the derived value representing availability.

[0015] Furthermore, in the information processing device involved in the tenth embodiment, in the information processing device involved in the ninth embodiment, when the user is judged to be evaluated as having the availability to obtain the first information based on the value representing the availability, the acquisition unit further acquires the evaluation of the availability related to the first information from the user.

[0016] Furthermore, the information processing device involved in the 11th mode, in the information processing device involved in the 10th mode, takes the feature quantity as input and uses a machine learning model that outputs a value representing the availability to determine the first information with availability, and also has an updating unit that inputs a pair of the evaluation obtained by the acquisition unit and the feature quantity corresponding to the evaluation as learning data into the machine learning model, and updates the machine learning model.

[0017] Furthermore, in order to achieve the above-mentioned object, a storage medium according to a twelfth aspect stores a program for causing a computer to function as each unit included in the information processing apparatus according to any one of the first to eleventh aspects.

[0018] Moreover, in order to achieve the above-mentioned purpose, the information processing method involved in the 13th method includes the following steps: an acquisition step, obtaining information on the content recorded in the first information, i.e., content information, from multiple first information browsed by the user; an extraction step, extracting the part edited by the user from the object on which the user performs the operation, i.e., second information; and a determination step, determining, from the content information, the first information browsed by the user when editing the part or before and after editing, among the multiple first information.

[0019] Effects of the Invention

[0020] According to the first aspect, the twelfth aspect, and the thirteenth aspect, when the second information is edited using the description of the first information, it is possible to identify the first information used when editing a certain part of the second information.

[0021] According to the second aspect, there is an effect that the first information having availability can be specified with higher accuracy compared to the case where the interactive information is not used.

[0022] According to the third aspect, there is an effect that it is possible to more efficiently identify first information having usefulness as interactive information, compared to a case where the operation time is not taken into consideration.

[0023] According to the fourth aspect, there is an effect that it is possible to more appropriately identify first information having usability as interactive information, compared to a case where the input device is not taken into consideration.

[0024] According to the fifth aspect, there is an effect that it is possible to more appropriately identify first information having usefulness as interactive information, compared to a case where browsing time is not taken into consideration.

[0025] According to the sixth aspect, there is an effect that the first information having usability can be specified with higher accuracy compared to a case where the number of times the user edits is not taken into consideration.

[0026] According to the seventh aspect, there is an effect that the first information having availability can be specified with higher accuracy compared to a case where the value indicating the availability of the first information is not taken into consideration.

[0027] According to the eighth aspect, there is an effect that the first information having usability can be specified with higher accuracy compared to a case where the operation information is not used.

[0028] According to the ninth aspect, there is an effect that the first information having usability can be specified with higher accuracy compared to a case where a feature amount obtainable from at least one of content information, interactive information, and operation information is not considered.

[0029] According to the tenth aspect, there is an effect that the first information having usability can be specified with higher accuracy compared to a case where the user's evaluation is not taken into consideration.

[0030] According to the eleventh aspect, there is an effect of being able to identify first information having usefulness with higher accuracy, compared to a case where a pair of a user's evaluation and a feature value is not considered as learning data. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Embodiments of the present invention will be described in detail with reference to the following drawings.

[0032] Figure 1 A diagram showing an example of a configuration of a network system according to an embodiment;

[0033] Figure 2 A block diagram showing an example of an electrical configuration of a server device according to an embodiment;

[0034] Figure 3 A block diagram showing an example of a functional configuration of a server device according to an embodiment;

[0035] Figure 4 FIG. 1 is a diagram showing an example of a browsing history record according to an embodiment of the present invention;

[0036] Figure 5 A diagram showing an example of content information according to an embodiment;

[0037] Figure 6A diagram showing an example of interactive information according to an embodiment;

[0038] Figure 7 A diagram showing an example of operation information according to an embodiment;

[0039] Figure 8 FIG. 1 is a diagram showing an example of characteristic quantities according to an embodiment of the present invention;

[0040] Figure 9 This is a flowchart showing an example of the flow of feature quantity creation processing performed by a learning processing program according to an embodiment;

[0041] Figure 10 A flowchart showing an example of a flow of a learning process performed by a learning process program according to an embodiment;

[0042] Figure 11 This is a flowchart showing an example of the flow of processing performed by the determination processing program according to the embodiment.

[0043] Explanation of symbols

[0044] 10-Server device, 12-Control unit, 12A-CPU, 12B-ROM, 12C-RAM, 12D-I / O, 14-Storage unit, 14A-Learning processing program, 14B-Determination processing program, 16-Display unit, 18-Operation unit, 20-Communication unit, 30-First acquisition unit, 32-Export unit, 34-Generation unit, 40-Second acquisition unit, 42-Extraction unit, 44-Determination unit, 46-Update unit, 50-Terminal device, 50A-Web browser, 90-Network system. DETAILED DESCRIPTION

[0045] Hereinafter, an example for implementing one embodiment of the present invention will be described in detail with reference to the drawings.

[0046] Figure 1 It is a diagram showing an example of the configuration of a network system 90 according to the present embodiment.

[0047] like Figure 1 As shown, the network system 90 according to this embodiment includes a server device 10 and a terminal device 50. The server device 10 is an example of an information processing device. As an example, a general-purpose computer device such as a server computer or a personal computer (PC) is applicable to the server device 10.

[0048] The server device 10 according to this embodiment is connected to a terminal device 50 via a network N. Examples of applicable network N include the Internet, a LAN (Local Area Network), and a WAN (Wide Area Network). Examples of applicable terminal devices 50 according to this embodiment include general-purpose computers such as personal computers (PCs), and mobile computers such as smartphones and tablet computers.

[0049] The terminal device 50 according to the present embodiment has a web browser 50A installed therein. The web browser 50A is software for accessing a website via the network N and browsing a web page provided by the accessed website.

[0050] Figure 2 This is a block diagram showing an example of the electrical configuration of the server device 10 according to the present embodiment.

[0051] like Figure 2 As shown, the server device 10 according to the present embodiment includes a control unit 12 , a storage unit 14 , a display unit 16 , an operation unit 18 , and a communication unit 20 .

[0052] The control unit 12 includes a CPU (Central Processing Unit) 12A, a ROM (Read Only Memory) 12B, a RAM (Random Access Memory) 12C, and an input / output interface (I / O) 12D, and these components are connected via a bus.

[0053] The I / O 12D is connected to functional units including the storage unit 14, the display unit 16, the operation unit 18, and the communication unit 20. These functional units can communicate with the CPU 12A via the I / O 12D.

[0054] The control unit 12 can be configured as a sub-control unit that controls a part of the operation of the server device 10, or can be configured as a part of the main control unit that controls the operation of the server device 10 as a whole. For example, integrated circuits such as LSI (Large Scale Integration) or IC (Integrated Circuit) chipsets are used in part or all of the blocks of the control unit 12. Independent circuits can be used in each of the above blocks, or circuits formed by integrating part or all of them can be used. The above blocks can be set as a whole, or a part of the blocks can be set separately. In addition, a part of each of the above blocks can be set separately. In the integration of the control unit 12, there is no limitation to LSI, and a dedicated circuit or a general-purpose processor can be used.

[0055] The storage unit 14 may be, for example, an HDD (Hard Disk Drive), an SSD (Solid State Drive), or a flash memory. The storage unit 14 stores a learning program 14A for implementing the learning process according to this embodiment and a determination program 14B for implementing the first information determination process according to this embodiment. Alternatively, the learning program 14A and the determination program 14B may be stored in the ROM 12B.

[0056] The learning processing program 14A and the determination processing program 14B can be pre-installed in the server device 10, for example. The learning processing program 14A and the determination processing program 14B can be implemented by storing them in a non-volatile storage medium or distributing them via the network N and then installing them appropriately in the server device 10. Examples of non-volatile storage media include CD-ROMs (Compact Disc Read Only Memory), magneto-optical disks, HDDs, DVD-ROMs (Digital Versatile Disc Read Only Memory), flash memories, memory cards, and the like.

[0057] The display unit 16 uses, for example, a liquid crystal display (LCD) or an organic EL (electroluminescence) display. The display unit 16 may also include an integrated touch panel. The operation unit 18 includes, for example, a keyboard, a mouse, or other input device. The display unit 16 and the operation unit 18 receive various instructions from the user of the server device 10. The display unit 16 displays various information, such as the results of processing executed in accordance with the instructions received from the user and notifications of the processing.

[0058] The communication unit 20 is connected to a network N such as the Internet, a LAN, or a WAN, and can communicate with the terminal device 50 via the network N.

[0059] However, as described above, when a user edits second information (e.g., a document or source code) using multiple records of first information (e.g., web pages), there may be some first information that is useful for editing and some that is not. In such cases, if it can be determined that the first information is used for editing the second information, it can serve as a criterion for determining whether the editing is useful. However, there is no method for determining that the first information is used for editing the second information.

[0060] Therefore, the CPU 12A of the server device 10 according to the present embodiment writes the learning processing program 14A and the determination processing program 14B stored in the storage unit 14 into the RAM 12C and executes them. Figure 3 The parts shown in the figure perform their functions.

[0061] Figure 3 This is a block diagram showing an example of the functional configuration of the server device 10 according to the present embodiment.

[0062] like Figure 3 As shown, the CPU 12A of the server device 10 according to the present embodiment functions as the first acquisition unit 30, the derivation unit 32, and the generation unit 34 by executing the learning processing program 14A, and functions as the second acquisition unit 40, the extraction unit 42, the determination unit 44, and the update unit 46 by executing the determination processing program 14B. Furthermore, in the present embodiment, the first acquisition unit 30 and the second acquisition unit 40 are shown separately, but these first acquisition unit 30 and second acquisition unit 40 may be implemented integrally as a single acquisition unit.

[0063] First, refer to Figures 4 to 8 The learning process according to this embodiment will be described.

[0064] Figure 4 This is a diagram showing an example of browsing history records according to this embodiment.

[0065] Figure 5 This is a diagram showing an example of content information according to this embodiment.

[0066] Figure 6 A diagram showing an example of interactive information according to this embodiment.

[0067] Figure 7 This is a diagram showing an example of operation information according to this embodiment.

[0068] Figure 8 This is a diagram showing an example of feature quantities according to this embodiment.

[0069] The first acquisition unit 30 according to this embodiment acquires the browsing history of web pages browsed by the user of the terminal device 50 using the web browser 50A, and stores the acquired browsing history in the storage unit 14. For example, the browsing history is as follows: Figure 4 As shown, it includes information such as URL (Uniform Resource Locator), title, browsing start time, etc. In addition, a web page is an example of the first information. Among them, the first information can be any information that can obtain a log, and is not limited to a web page.

[0070] Furthermore, the first acquisition unit 30 acquires information about the content recorded in the web page from the web page acquired as the browsing history. Figure 5 As shown, it can include information such as browsing start time, URL, title, URL of the previous browsing page, page text, etc. In addition, the content information can also include information such as DOCTYPE (html version), window size, document size, etc.

[0071] Furthermore, the first acquisition unit 30 acquires information related to the user's operations on the web page, i.e., interaction information, from the web page acquired as the browsing history. The interaction information includes information obtained from the content of the user's operations on the web page through the input device used. The input device mentioned here is, for example, a keyboard or a mouse. In the interaction information, for example, Figure 6 As shown, the interaction information includes the URL, title, browsing start time, browsing end time, browsing time, and mouse position and scrolling information, as an example of an input device. More specifically, the interaction information includes the webpage browsing start time, browsing end time, whether the mouse is on the window, the browsing position at each regular time interval, the mouse movement position, the scrolling distance, the tab transitions, the number of copy operations, the number of drag operations, and the number of link clicks. Furthermore, the means for acquiring the interaction information can be implemented as an extension function of the web browser 50A, or using JavaScript (registered trademark) embedded in the webpage.

[0072] Furthermore, the first acquisition unit 30 acquires operation information related to the operation performed by the operation target data, which is the object of the user's operation. In this embodiment, the user performs the operation on the operation target data through the terminal device 50. The operation target data includes, for example, a document or source code. For example, when the user performs programming, the operation information includes, for example, Figure 7 As shown, the job information includes, as an example, the source code's edit history, timestamps, and error information. On the other hand, when a user is creating a document, for example, the job information includes the document's edit history, timestamps, and other information. Document editing, for example, includes creating and editing documents using document creation software, creating and editing presentation slides using presentation software, and creating and editing emails using email software. Furthermore, the job information is an example of the second information.

[0073] The browsing history, content information, interaction information, and operation information obtained in the above manner are stored in the storage unit 14 .

[0074] The derivation unit 32 of this embodiment uses the aforementioned content information, interaction information, and task information as input to derive feature quantities for input into the machine learning model described below. For example, the derivation unit 32 compares the time at which the content information and interaction information were viewed, i.e., the timestamp of the task information, obtained from the webpage, were viewed. The derivation unit 32 then associates task information close to the time the webpage was viewed with the webpage. This association is then established between the webpage and the content information, interaction information, and task information.

[0075] Furthermore, as a feature quantity obtained from the operation information, for example, Figure 8 As shown in , it includes the presence or absence of editing of the document being browsed, the number of edits, the number of errors, the number of functions contained, the number of edited lines, the edit distance between the previous and the next browsing, etc. And, as a feature quantity obtained from the interactive information, as an example, Figure 8 As shown, it includes browsing time, number of mouse cursor movements, mouse cursor movement distance (also including x-axis and y-axis directions), mouse cursor movement speed obtained by dividing the mouse cursor movement distance by browsing time, ..., scrolling maximum value, etc. Furthermore, content information and operation information can be combined. For example, when programming a user's operation, the number of functions included in the source code edited at any time before, during, or after browsing a web page can be used as a feature quantity. Furthermore, using content information and browsing history records, whether the web page being evaluated was browsed via a link from the previously browsed page can be used as a feature quantity, and the similarity between the text of the previously browsed page and the text of the web page being evaluated can also be used as a feature quantity.

[0076] The feature quantities obtained from the content information, interaction information, and operation information are stored in the storage unit 14. The feature quantities may be derived from a combination of a plurality of information or from each piece of information.

[0077] The generating unit 34 involved in this embodiment uses the feature quantity derived by the deriving unit 32 as input to generate a machine learning model for determining whether a web page is useful to the user. As an example, a pair of the above-mentioned feature quantity and the correct label explicitly given by the user is used as learning data for machine learning. In addition, as an example of a machine learning algorithm, support vector machine, random forest, gradient boosting, XGboost, neural network (including deep neural network), etc. can be cited. Moreover, regarding the output value of the machine learning model, the presence or absence of availability can be represented by two values, 0 (no availability) and 1 (availability), or by a probability greater than 0 and less than 1. The machine learning model generated by the above is stored in the storage unit 14.

[0078] Next, the first information identification process according to this embodiment will be described. Note that the first information according to this embodiment is a web page.

[0079] The second acquisition unit 40 involved in this embodiment acquires content information recorded on multiple web pages browsed by a user of a terminal device 50 using a web browser 50A. Furthermore, the second acquisition unit 40 acquires interaction information related to user operations performed on the web pages. An example of this interaction information is information related to user operations performed on the browsed web page before or after editing. "Before editing" includes the period immediately before editing or within a specified time period before editing (e.g., within 30 minutes), while "after editing" includes the period immediately after editing or within a specified time period after editing (e.g., within 30 minutes). Furthermore, the second acquisition unit 40 acquires operation information related to operations performed by the user on the operation target data at at least one of the following times: before, during, or after browsing the web page. This content information, interaction information, and operation information are used to identify usable web pages, but a configuration may also include only content information and operation information without the interaction information.

[0080] The extraction unit 42 according to the present embodiment extracts a portion edited by the user from work target data on which the user performs work.

[0081] The identification unit 44 of this embodiment identifies, from the content information of multiple web pages, the web page that the user browsed while editing the portion in question, or before or after editing. Specifically, as an example, the identification unit 44 compares the browsing start time of the content information obtained from the web page with the browsing start time of the interaction information, i.e., the timestamp of the task information, and associates the task information close to the browsing time of the web page with the web page. In this way, the web page is associated with the content information, interaction information, and task information.

[0082] The web page is identified based on whether at least a portion of the content information is present in the information recorded in the portion of the work target data that the user has edited. Specifically, if at least a portion of the content information is present in the information recorded in the edited portion, the web page is identified as a web page used for editing the work target data. In other words, the web page is used to improve the product (e.g., a document or source code) resulting from the work performed by the user and is therefore considered useful to the user.

[0083] Furthermore, the determination unit 44 can derive the value indicating the availability of the web page determined above based on the feature quantity obtained from at least one of the content information, interaction information, and operation information, and determine the web page with availability based on the derived value indicating availability. In this case, the feature quantity is used as input, and the determination of the web page with availability is performed using a machine learning model that outputs a value indicating availability. As described above, the machine learning model is a model that has been machine-learned in advance using learning data. In addition, as the value indicating availability, that is, the output value of the machine learning model, as described above, the presence or absence of availability can be represented by two values, 0 (no availability) and 1 (availability), or can be represented by a probability greater than 0 and less than 1.

[0084] Furthermore, when the user determines that a usability evaluation of the webpage is to be obtained based on the usability value derived by the determination unit 44, the second acquisition unit 40 can acquire the usability evaluation of the webpage from the user. Specifically, for example, when the usability value is less than a threshold and is not sufficiently high, a request for an evaluation is sent to the terminal device 50. When the evaluation request is sent, for example, the user can display the evaluation of the webpage on a UI (User Interface) screen (not shown) where input is possible on the webpage being browsed, and be prompted to enter the evaluation. For example, the evaluation can be a selection of "good, bad, or neither," or a multi-level evaluation (e.g., a five-level rating of 1 to 5).

[0085] The updating unit 46 of this embodiment inputs the pair of the evaluation acquired by the second acquiring unit 40 and the feature value corresponding to the evaluation as learning data into the machine learning model, and updates the machine learning model. The machine learning model can be updated each time new learning data is added, or after a predetermined amount of new learning data is collected based on the amount of data, or periodically.

[0086] Furthermore, if the portion extracted by extraction unit 42 is edited twice by the user, determination unit 44 may determine that the web page determined during the second edit has a higher usability than the web page determined during the first edit. In this case, determination unit 44 outputs a value indicating the usability of the web page containing the newly recorded content as greater than the value indicating the usability of the initially determined web page, and outputs a value indicating the usability of the initially determined web page as less than the value indicating the usability of the undetermined web pages among the web pages browsed by the user. The value indicating usability described herein refers to the output value of the aforementioned machine learning model.

[0087] Next, refer to Figures 9 to 11 , the role of the server device 10 involved in this embodiment is described. In addition, Figures 9 to 11 In the flowchart shown, the description targets a task in which a user edits source code while referring to a web page.

[0088] Figure 9 This is a flowchart showing an example of the flow of feature amount creation processing performed by the learning processing program 14A according to this embodiment.

[0089] First, when an instruction to start execution of feature amount creation processing is given to the server device 10, the following steps are executed.

[0090] exist Figure 9 In step 100 , the first acquisition unit 30 sets i, which indicates the number of web page browsing history records, to 0.

[0091] In step 102, the first acquisition unit 30 acquires the above-mentioned Figure 4 Specifically, the browsing history of web pages browsed by the user of the terminal device 50 using the web browser 50A is acquired.

[0092] In step 104, the first acquisition unit 30 acquires the above-mentioned Figure 5 Specifically, the content information is acquired from the web page acquired as the browsing history in step 102 .

[0093] In step 106, the first acquisition unit 30 acquires the above-mentioned Figure 6 Specifically, for the web page acquired as the browsing history, information related to the operation performed by the user, that is, interaction information, is acquired.

[0094] In step 108, the first acquisition unit 30 acquires the above-mentioned Figure 7 Specifically, in browsing a web page acquired as a browsing history, job information related to a job performed by the user on job target data is acquired at any time before and after browsing.

[0095] In step 110, the deriving unit 32 derives the above-mentioned information as an example from each of the content information, interaction information, and operation information acquired in steps 104 to 108. Figure 8Specifically, when the task target data is source code, for example, the task information and content information can be used to derive information such as whether the source code has been edited after the webpage has been viewed, the number of source code edits during the webpage, whether there are errors in the source code after the webpage has been viewed, and the number of functions included in the source code of the webpage. Furthermore, for example, interaction information can be used to derive information such as the webpage browsing time, the number of mouse cursor movements, the mouse cursor movement distance, the mouse cursor movement speed, the maximum and minimum positions of the mouse cursor in the x-axis direction, the maximum and minimum positions of the mouse cursor in the y-axis direction, the number of scrolls, the scroll frequency, and the scroll distance.

[0096] In step 112 , the derivation unit 32 stores the feature value derived in step 110 in the storage unit 14 .

[0097] In step 114, the derivation unit 32 determines whether the remaining number of browsing history records is 0. If it is determined that the remaining number of browsing history records is not 0 (a negative judgment time), the process proceeds to step 116. If it is determined that the remaining number of browsing history records is 0 (a positive judgment time), the feature value creation process performed by the learning processing program 14A ends.

[0098] On the other hand, in step 116 , the deriving unit 32 repeatedly increments i, which indicates the number of browsing history records, by one, and returns to step 102 .

[0099] Figure 10 This is a flowchart showing an example of the flow of the learning process performed by the learning process program 14A according to the present embodiment.

[0100] First, when an instruction to start execution of a learning process is given to the server device 10, the following steps are executed.

[0101] exist Figure 10 In step 120 , the generating unit 34 acquires the feature quantity stored in the storage unit 14 .

[0102] In step 122, the generator 34 acquires a correct label. Specifically, for each web page acquired as a browsing history, the evaluation (for example, binary values ​​such as 0 and 1) assigned by the user is acquired as a correct label.

[0103] In step 124 , the generator 34 uses the correctly labeled feature quantities acquired in step 122 as input and generates a machine learning model that outputs a value representing availability using a machine learning algorithm.

[0104] In step 126 , the generation unit 34 stores the machine learning model generated in step 124 in the storage unit 14 , and ends the learning process performed by the learning processing program 14A.

[0105] Figure 11 This is a flowchart showing an example of the flow of processing performed by the determination processing program 14B according to this embodiment.

[0106] First, when the server device 10 is instructed to start the first information identification process, the following steps are executed. In this embodiment, the information recorded in the portion of the work target data edited by the user includes at least a portion of the content information.

[0107] exist Figure 11 In step 130 , the second acquisition unit 40 reads the machine learning model stored in the storage unit 14 .

[0108] In step 132 , the second acquisition unit 40 acquires a plurality of feature quantities from each or a combination of content information, interaction information, and task information associated with the web page to be evaluated.

[0109] In step 134 , the determination unit 44 sets a threshold value (upper limit, lower limit) for the value Prob indicating availability output from the machine learning model read in step 130 based on information such as the number of acquired data and data characteristics.

[0110] In step 136 , the specifying unit 44 sets i, which indicates the number of browsing histories of the web page to be evaluated, to 0.

[0111] In step 138, determination unit 44 inputs the multiple feature quantities acquired in step 132 into the machine learning model read in step 130, and derives a value Prob indicating usability for the web page associated with the multiple feature quantities. Furthermore, if there are multiple feature quantities associated with the web page being evaluated, the machine learning model outputs a single value Prob indicating usability for each of the multiple feature quantities. In this embodiment, the value Prob indicating usability is set to a probability of 0 or greater and 1 or less.

[0112] In step 140, the determination unit 44 determines whether the lower threshold value ≤ Prob ≤ the upper threshold value. If the lower threshold value ≤ Prob ≤ the upper threshold value (a positive determination time), the process proceeds to step 142. If the lower threshold value ≤ Prob ≤ the upper threshold value is not determined (a negative determination time), the process proceeds to step 148.

[0113] In step 142, the second acquisition unit 40 displays a UI screen (not shown) for assigning user evaluation requests on the terminal device 50, and acquires the user's evaluation of the web page via the terminal device 50. Specifically, as described above, the user can selectively input an evaluation of "good, bad, or neither," and input any of a plurality of levels (e.g., 1 to 5) as the evaluation.

[0114] In step 144 , the updating unit 46 inputs the pair of the user evaluation acquired in step 142 and the feature value corresponding to the user evaluation as new learning data into the machine learning model, thereby updating the machine learning model.

[0115] In step 146, the determination unit 44 determines whether the number of remaining browsing history records is 0. If it is determined that the number of remaining browsing history records is not 0 (a negative determination time), the process proceeds to step 148. If it is determined that the number of remaining browsing history records is 0 (a positive determination time), the first information determination process performed by the determination processing program 14B ends.

[0116] On the other hand, in step 148 , the specifying unit 44 increments i indicating the number of browsing history records by one, and returns to step 138 to repeat the process.

[0117] As described above, according to this embodiment, when a user edits target data using descriptions on a plurality of web pages, a web page used for editing the target data, that is, a web page useful to the user, is identified from the plurality of web pages.

[0118] The above description uses a server device as an example of an information processing device according to the embodiments. The embodiments may take the form of a program for causing a computer to execute the various functions of the server device. The embodiments may also take the form of a computer-readable storage medium storing the program.

[0119] In addition, the configuration of the server device described in the above embodiment is an example and can be modified according to circumstances without departing from the scope of the invention.

[0120] Furthermore, the process flow of the program described in the above embodiment is merely an example, and unnecessary steps may be deleted, new steps may be added, or the process order may be changed without departing from the spirit of the invention.

[0121] Furthermore, in the above embodiments, the processing involved in the embodiments is implemented by executing a program and using a computer with a software structure, but the present invention is not limited thereto. The embodiments may also be implemented with a hardware structure or a combination of hardware and software structures.

[0122] The above-described embodiments of the present invention are provided for the purpose of illustration and explanation. In addition, the embodiments of the present invention do not fully and exhaustively include the present invention, and do not limit the present invention to the disclosed embodiments. It is obvious that various modifications and variations are self-evident to those skilled in the art to which the present invention belongs. The present embodiment is selected and described in order to most easily explain the principles of the present invention and its application. Thus, other technical personnel in this technical field can understand the present invention by determining the various modifications optimized for the assumed various embodiments. The scope of the present invention is defined by the above claims and their equivalents.

Claims

1. An information processing device comprising: an acquisition unit, which acquires, from a plurality of first information browsed by a user, information on the content recorded in the first information, namely content information, information on the operation performed by the user on the first information, namely interaction information, and operation information related to the operation performed by the user on the object of operation, namely second information, at least one time before, during and after browsing the first information, wherein the content information includes the recorded content of the plurality of first information browsed by the user and the browsing start time, the interaction information includes the browsing start time and the browsing position, and the operation information includes the number of edited lines of the second information and a timestamp, and the content information, the interaction information and the operation information are associated based on the browsing start time of the content information, the browsing start time of the interaction information and the timestamp; an extracting unit that extracts a portion edited by the user from the second information; and a determination unit that determines, based on the recorded content and the browsing start time of the content information, the browsing start time and the browsing position of the interactive information, and the number of edited lines and the timestamp of the operation information, first information browsed by the user within a specified time when editing the portion or before and after editing, among the plurality of first information as first information having availability, When the portion extracted by the extracting unit is edited twice by the user, the determining unit determines that the first information determined in the second editing has higher usability than the first information determined in the first editing.

2. The information processing device according to claim 1, wherein: The interaction information is information related to an operation performed by the user on the first information browsed before or after the editing.

3. The information processing device according to claim 2, wherein: The interaction information includes information obtained from the operation content performed by the user on the first information through the input device used.

4. The information processing device according to claim 3, wherein: The interaction information also includes the time when the user browsed the first information, ie, the browsing time.

5. The information processing device according to claim 1, wherein: deriving a value indicating the availability of the first information based on a feature amount obtained from the content information, The determination unit outputs a value indicating the availability of the first information recording the newly recorded content in the portion as being greater than a value indicating the availability of the first information initially determined, and outputs a value indicating the availability of the first information initially determined as being less than a value indicating the availability of the undetermined first information in the first information browsed by the user.

6. The information processing device according to claim 1, wherein: When the evaluation of the availability of the user to acquire the first information is determined based on the value indicating the availability, the acquisition unit further acquires the evaluation of the availability related to the first information from the user.

7. The information processing device according to claim 6, wherein: The first information having availability is determined by using a machine learning model that takes as input a feature quantity obtained from at least one of the content information, the interaction information, and the operation information and outputs a value representing the availability. The method also includes an updating unit that inputs a pair of an evaluation obtained by the acquisition unit and a feature quantity corresponding to the evaluation as learning data into the machine learning model and updates the machine learning model. 8 . A storage medium storing a program for causing a computer to function as each unit included in the information processing device according to claim 1 .

9. An information processing method comprising the following steps: An acquisition step of acquiring, from a plurality of first information browsed by a user, information on the content recorded in the first information, namely content information, information on the operation performed by the user on the first information, namely interaction information, and operation information related to the operation performed by the user on the object of operation, namely second information, at least one time before, during and after browsing the first information, wherein the content information includes the recorded content of the plurality of first information browsed by the user and the browsing start time, the interaction information includes the browsing start time and the browsing position, and the operation information includes the number of edited lines of the second information and a timestamp, and the content information, the interaction information and the operation information are associated based on the browsing start time of the content information, the browsing start time of the interaction information and the timestamp; an extracting step of extracting a portion edited by the user from the second information; and a determining step of determining, based on the recorded content and the browsing start time of the content information, the browsing start time and the browsing position of the interactive information, and the number of edited lines and the timestamp of the operation information, the first information browsed by the user within a specified time when editing the part or before and after editing, among the plurality of first information, as the first information having availability; When the portion extracted by the extracting step is edited twice by the user, the determining step determines that the first information determined at the second editing has higher usability than the first information determined at the first editing.

10. A computer program product, characterized in that Includes programs for causing a computer to: Acquire, from a plurality of first information browsed by a user, information on the content recorded in the first information, namely content information, information on the operation performed by the user on the first information, namely interaction information, and operation information related to the operation performed by the user on the object of operation, namely second information, at least one time before, during and after browsing the first information, wherein the content information includes the recorded content of the plurality of first information browsed by the user and the browsing start time, the interaction information includes the browsing start time and the browsing position, and the operation information includes the number of edited lines of the second information and a timestamp, and the content information, the interaction information and the operation information are associated based on the browsing start time of the content information, the browsing start time of the interaction information and the timestamp; extracting a portion edited by the user from the second information; and According to the recorded content and the browsing start time of the content information, the browsing start time and the browsing position of the interactive information, and the number of edited lines and the timestamp of the operation information, the first information browsed by the user within a specified time when editing the part or before and after editing is determined as the first information with availability among the plurality of first information, When the extracted portion is edited twice by the user, the first information determined at the second editing is determined to have higher usability than the first information determined at the first editing.

Images