JP2019008395A - Comprehension support method, comprehension support device, and program - Google Patents

Abstract

To support efficient comprehension of things.SOLUTION: A comprehension support method causes a computer to execute: an acquisition procedure which acquires expression information by a plurality of types of expression methods, about each of a first thing and one or more second things having relation to the first thing; a first calculation procedure which calculates an expression level of the expression information by each of the expression methods, about each of the first thing and the second things, the level quantitatively showing adequacy for corresponding explanation of the things; a second calculation procedure which calculates, for each of the expression methods, a common index for the expression level of the first thing, the index reducing influence of a trend of the expression methods on the expression level on the basis of distribution of the expression level; and a selection procedure which selects expression information used for explanation of the first thing on the basis of the common index.SELECTED DRAWING: Figure 4

Description

The present invention relates to an understanding support method, an understanding support device, and a program.

  With the spread of terminals owned by individuals such as smartphones and tablets, information retrieval on terminals with small screens is routinely performed. In addition, there are many opportunities to check on the terminal of the object that thought "What is this?" When the rapidly increasing number of foreigners who visit Japan or when the Japanese travel abroad. In order to present information in an easy-to-understand manner on a terminal at hand, it is desirable that the expression is an easily understandable explanation with an amount of information that can be displayed on a small screen.

  Conventionally, as a method of generating an appropriate explanation for a question, a method of generating an optimal answer sentence by machine learning of a question sentence and its correct example from a newspaper article or the like has been proposed (for example, Non-Patent Document 1). .

  Moreover, a method for promoting understanding by presenting expressions other than text has been proposed (for example, Non-Patent Document 2).

Hiroshi Sasaki, Hideki Amagasaki, Jun Suzuki, Koji Kuniyo, Tsutomu Hirao, Hideto Kazawa, Eisaku Maeda, "Learning Question Answering System SAIQA-II Using SVM", Transactions of Information Processing Society of Japan, Vol.45, No.2 pp.635-646, 2004. Akihiro Matsumoto, Yuichi Ito, Rei Murakami, Yoshifumi Kitamura, Fumiro Kishino, "Examination of Dynamic Multimedia Content Generation to Support Text Understanding Promotion", IPSJ SIG Entertainment Entertainment Computing 2006 (24 (2006EC003)), pp.121-128.

  However, in the method of Non-Patent Document 1, since the optimal expression is extracted from the contents included in the existing explanatory text, comparison in a common expression method called text can be performed, but in texts other than diagrams and questions and answers It is difficult to compare the representation method and which is easy to understand.

  In the method of Non-Patent Document 2, understanding is promoted by adding image or audio information to text-only content. However, when the amount of information that can be presented on a small screen is limited, a plurality of text, images, etc. It is difficult to determine which method should be prioritized using the same index.

  The present invention has been made in view of the above points, and an object thereof is to support efficient understanding of things.

  Therefore, in order to solve the above problem, the understanding support method obtains expression information by a plurality of types of expression methods for each of the first thing and one or more second things related to the first thing. A first calculation for calculating the degree of expression that quantitatively indicates the appropriateness of the explanation of the corresponding thing with respect to the expression information obtained by each expression method of each of the first thing and the second thing A second step of calculating, for each of the expression methods, a common indicator for the expression level of the first thing that reduces the influence of the tendency of the expression method on the expression level based on the distribution of the expression level; And a selection procedure for selecting expression information used to describe the first thing based on the common index.

  Can support efficient understanding of things.

It is a figure which shows the structural example of the system in embodiment of this invention. It is a figure which shows the hardware structural example of the understanding assistance apparatus 10 in embodiment of this invention. It is a figure which shows the function structural example of the understanding assistance apparatus 10 in embodiment of this invention. It is a flowchart for demonstrating an example of the process sequence which the understanding assistance apparatus 10 performs. It is a figure which shows the structural example of comparison object definition DB120. It is a figure which shows the structural example of presentation rule definition DB130. It is a figure for demonstrating the expression method in this Embodiment. It is a figure which shows an example of distribution of the expression degree of each expression method. It is a figure which shows the example of the input / output in this Embodiment.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. FIG. 1 is a diagram illustrating a configuration example of a system according to an embodiment of the present invention. In FIG. 1, an understanding support apparatus 10 is connected to one or more user terminals 20 via a network N1 such as the Internet. The user terminal 20 may be connected to the network N1 via a wireless line or the like.

  The understanding support device 10 is, for example, an arbitrary thing unfamiliar to the user (or an interest of the user) (a proper noun such as a product name such as “Karukan”, a general noun such as “Udon”, Information to be presented to the user (hereinafter referred to as “presentation information”) in order to support the understanding of menu names such as “Teriyaki”, landmark names, place names, etc. (hereinafter referred to as “objects”). ) To generate and output a computer.

  The user terminal 20 includes information (hereinafter referred to as “target information”) indicating a target matter, such as a smartphone, tablet, PC, terminal installed in a public place such as a storefront or a station, and the target matter. Is an arbitrary device used for inputting a genre (category) to which the user belongs. As an example of the target information, there are a name of the target thing, a term representing the target thing, and the like. The input method of the target information may be any method such as voice input, selection using a touch panel, character input, or keyboard input.

  FIG. 2 is a diagram illustrating a hardware configuration example of the understanding support apparatus 10 according to the embodiment of the present invention. 2 includes a drive device 100, an auxiliary storage device 102, a memory device 103, a CPU 104, an interface device 105, and the like that are mutually connected by a bus B.

  A program for realizing processing in the understanding support apparatus 10 is provided by a recording medium 101 such as a CD-ROM. When the recording medium 101 storing the program is set in the drive device 100, the program is installed from the recording medium 101 to the auxiliary storage device 102 via the drive device 100. However, the program need not be installed from the recording medium 101 and may be downloaded from another computer via a network. The auxiliary storage device 102 stores the installed program and also stores necessary files and data.

  The memory device 103 reads the program from the auxiliary storage device 102 and stores it when there is an instruction to start the program. The CPU 104 executes functions related to the understanding support device 10 in accordance with a program stored in the memory device 103. The interface device 105 is used as an interface for connecting to a network.

  FIG. 3 is a diagram illustrating a functional configuration example of the understanding support device 10 according to the embodiment of the present invention. In FIG. 3, the understanding support apparatus 10 includes a reception unit 11, a condition extraction unit 12, an expression level calculation unit 13, a common index calculation unit 14, a presentation rule acquisition unit 15, a display shaping unit 16, a transmission unit 17, and the like. Each of these units is realized by processing that one or more programs installed in the understanding support apparatus 10 cause the CPU 104 to execute. The understanding support apparatus 10 also uses databases (storage units) such as the comparison target definition DB 120 and the presentation rule definition DB 130. Each of these databases can be realized by using, for example, a storage device that can be connected to the auxiliary storage device 102 or the understanding support device 10 via a network.

  Hereinafter, a processing procedure executed by the understanding support device 10 will be described. FIG. 4 is a flowchart for explaining an example of a processing procedure executed by the understanding support device 10.

  In step S <b> 1, the receiving unit 11 receives from the user terminal 20 an acquisition request for presentation information related to the target thing input to the user terminal 20. The acquisition request includes target information and information (hereinafter referred to as “genre name”) indicating a genre to which the target thing belongs (classification of a thing related to the target thing).

  The genre name is selected from genre names stored in the comparison target definition DB 120. FIG. 5 is a diagram illustrating a configuration example of the comparison target definition DB 120. In FIG. 5, the comparison target definition DB 120 stores a genre name and thing information for each genre defined in advance.

  The genre name is a name for distinguishing the genre (category) of things. The granularity or type of the genre may be arbitrarily set. For example, a product category on an Internet mail order site such as Amazon (registered trademark) may be cited. The granularity of the genre may be a rough one such as food / drink / other, and for example, for food, rice dishes / fish dishes / meat dishes / hot pot dishes / Japanese sweets / Western sweets ... A detailed genre may be set.

  The matter information is information (for example, name) indicating (identifying) the matter for each matter belonging to each genre. In FIG. 5, two examples (1) and (2) are shown as examples of registration of the thing information. (1) is an example in which the URL (Uniform Resource Locator) of the website from which the object information related to each genre is acquired is set. In (2), the thing information acquired by accessing the website of the acquisition destination of the thing information related to each genre is registered in advance, or the thing information obtained from another information source is manually input. It is an example. The matter information is used by the common index calculation unit 14 in the subsequent steps.

  In step S1, for example, a list of genre names stored in the comparison target definition DB 120 is transmitted from the receiving unit 11 to the user terminal 20 and displayed on the user terminal 20 based on the list. Any one of the genre names may be selected via.

  Subsequently, the condition extraction unit 12 acquires the presentation environment information and transmits the presentation environment information to the reception unit 11 (S2). The presentation environment information is information indicating the environment type of the output destination of the presentation information (for example, the user terminal 20) according to the granularity defined in the presentation rule definition DB 130.

  FIG. 6 is a diagram illustrating a configuration example of the presentation rule definition DB 130. As shown in FIG. 6, the presentation rule (rule information regarding presentation of presentation information) is registered in the presentation rule definition DB 130 for each presentation environment that is a candidate for the output destination of presentation information.

  FIG. 6 illustrates an example in which the presentation environment is classified into “smart phone”, “PC”, “tablet”, and “other than that”. When more detailed settings are made for the presentation rule definition DB 130, for example, information such as a model of a smartphone, a PC, a tablet, or a display model connected to the user terminal 20 can be acquired and presented. The presentation environment can be further classified according to the number of characters and the font size, and a presentation rule can be set.

  In this embodiment, an example in which the input source of the target information and the output destination of the presentation information are the same user terminal 20 will be described. However, when the input source and the output destination are different, the presentation environment of the output destination Information only needs to be acquired. Note that the presentation environment information may be automatically determined by the condition extraction unit 12 based on information included in the presentation information acquisition request transmitted from the user terminal 20, or for the user terminal 20. It may be explicitly input by the user. When the presentation environment information is automatically determined and the presentation environment information cannot be determined, a preset default value (for example, “smart phone” or the like) may be adopted as the presentation environment information. Details of the presentation rule will be described later.

  Subsequently, the reception unit 11 transmits the received target information and genre name to the expression degree calculation unit 13 (S3), and transmits the presentation environment information to the presentation rule acquisition unit 15 (S4).

  Subsequently, the expression level calculation unit 13 acquires a list of thing information corresponding to the genre name from the comparison target definition DB 120 (S5). Each acquired item information is hereinafter referred to as “comparison information”, and an item related to each comparison information is referred to as “comparison item”. Note that the thing information that matches the target information in the list of obtained thing information is excluded from the comparison information. If the comparison target definition DB 120 is configured as shown in (1) of FIG. 5, the expression level calculation unit 13 compares at this timing from the website related to the URL corresponding to the genre. A list of information may be acquired.

  Subsequently, the expression degree calculation unit 13 expresses (explains) information (hereinafter referred to as “expression information”) for each of the target thing and each comparative thing for each of a plurality of types of expression methods defined in advance for explanation of the target thing. Is obtained from the information source D1 (S6). The expression information of the target thing is a content candidate included in the presentation information.

  Here, the expression method refers to a method or format for explaining or expressing an object. In the present embodiment, three types of expression methods 1 to 3 are defined as an example.

  FIG. 7 is a diagram for explaining a representation method in the present embodiment. As shown in FIG. 7, the expression method 1 is a method for explaining a target object using an image. In the expression method 1, for example, an image that expresses a target thing and a word that is highly related to the image (hereinafter referred to as “tag information”) are used as expression information.

  The expression method 2 is a method for explaining a target thing by an analogy with a thing similar to the target thing (by an example of a thing similar to the target thing). In the expression method 2, for example, the thing information (comparison information) of the comparison thing that is most similar to the target thing among the comparison things is used as the expression information.

  The expression method 3 is a method for explaining a target thing by summarizing word-of-mouth information or review information (hereinafter referred to as “evaluation information”). In the expression method 3, for example, a summary sentence of the top 50 evaluation information related to the target thing is used as the expression information.

  Note that FIG. 7 shows an explanation using expression information corresponding to each expression method when the target object is “KARUKAN”.

  In this way, the expression information required for the description differs for each expression method. Therefore, the acquisition method of the expression information of the target thing and each comparison thing differs for each expression method. For example, the acquisition method may be defined as an algorithm of the expression degree calculation unit 13 or may be defined in an external file or the like.

  In the case of the expression method 1, when the image is searched on the Internet using the target information (for example, “Karukan”) as a search word (keyword), the image output at the top of the search result and the URL of the source site of the image are displayed. The top N words of the words obtained by inputting to the keyword extraction tool “http://gensen.dl.itc.u-tokyo.ac.jp/gensenweb.html” are acquired as expression information. Also good. Each of the top N words in this case corresponds to the tag information described above. Here, the value of N is arbitrary. Note that the tag information may be extracted by other methods. For example, it may be extracted by an arbitrary method from sentences included in the source site of the image output at the highest level. The image and tag information relating to each comparative object may be acquired in the same manner. Therefore, the information source D1 for the expression method 1 is, for example, a search site on the Internet.

  In the case of expression method 2, "Rika Mochizuki, Shinichiro Nagatoku, Manabu Mogi, Takashi Yagi, Nobuhiro Muto, Toru Kobayashi," Proposal of Kansei Communication Realization Utilizing Life Log-Verification of Information Transmission Effect with Reality ", Information The method described in “Journal of Processing Society of Japan, Vol. 53, No. 1, pp. 30-38, 2012” (hereinafter referred to as “reference document 1”) may be used. In this case, since multi-dimensional numerical values (for example, sweetness 5, popularity 10, etc.) representing the features of the target thing and the comparative thing are necessary as input, for example, the co-occurrence word of the target information and the co-occurrence of each comparison information The words are extracted by the co-occurrence word search tool “http://neoinspire.net/cooccur/”, etc., the top 20 co-occurrence words and their co-occurrence frequencies are obtained, and the acquired co-occurrence words and the co-occurrence frequencies are obtained. Is applied to the equation (1) of P33 of Reference Document 1, and the thing information (comparison information) of the comparative thing with the highest equivalence (similarity) is acquired. In this case, a co-occurrence word may be applied to each parameter in FIG. 4 of Reference 1 and a co-occurrence frequency may be applied to a vector of each parameter. The thing information of the thing similar to each comparison thing should just be acquired from object information and other comparison information similarly. Therefore, the information source D1 for the expression method 2 is, for example, a co-occurrence word extraction tool.

  In the case of the expression method 3, evaluation information to be summarized is acquired by a method such as quoting a customer review regarding a target thing from a shopping site. For the evaluation information obtained, for example, “Naoto Takubo, Ryoya Suzuki,“ Review summary from the user's viewpoint extracted automatically ”, Proc. Of the 18th Annual Conference of the Language Processing Society, pp.295-298, 2012.” A summary may be generated using the method described in (hereinafter referred to as “Reference Document 2”). In Reference 2, the user needs to select a keyword. Among the selection candidate keywords, for example, the expression calculation unit 13 automatically selects and summarizes the candidate having the highest appearance count. May be generated. A summary for each comparison item may be generated as well. Therefore, the information source D1 for the expression method 3 is, for example, a shopping site.

  Subsequently, the expression degree calculation unit 13 uses the expression information acquired for each of the target thing and the comparative thing, and makes it easy to understand each expression method for each of the target thing and the comparative thing. An index (hereinafter referred to as “expression”) that quantitatively indicates appropriateness as an explanation is calculated (S7). In other words, the degree of expression of each expression method related to a certain thing is a numerical value indicating how easily the expression information acquired regarding the object is easy to understand as an explanation of the object or how appropriate the calculation method is. It may be different for each expression method.

  For example, in the case of the expression method 1, the degree of matching may be a degree of matching between a word acquired as tag information and a word included in an explanatory text of a dictionary related to target information (for example, “Karukan”). The explanatory text of the dictionary related to the target information refers to an explanatory text obtained when the target information is examined using a dictionary provided on the Internet or the like. The degree of coincidence between the word acquired as tag information and the word included in the explanatory text is the ratio of the number of tag information included in the explanatory text to the total number of tag information. For example, if there are 10 pieces of tag information and a word that matches 5 pieces of tag information is included in the explanatory text, the degree of expression is 0.5. It should be noted that the degree of expression may be similarly calculated for the expression information of each comparative thing.

  In the case of the expression method 2, the equivalence (similarity with the comparative thing that is most similar to the target thing) calculated by the method of Reference 1 may be used as the degree of expression as it is. The degree of expression may be similarly calculated for the expression information of each comparative thing.

  In the case of the expression method 3, among the keywords extracted from the evaluation information of the target thing, the total value of the number of appearances of the keywords included in the created summary may be used as the expression level. The degree of expression may be similarly calculated for the expression information of each comparative thing.

  In any case, it is assumed that the higher the degree of expression (the larger the value), the higher the understandability.

  The degree of expression calculated for each expression method for the target thing and each comparative thing is transmitted to the common index calculation unit 14.

  Subsequently, the common index calculation unit 14 converts the expression level for each expression method into a common index for enabling comparison with the same standard (S8). That is, when it is desired to compare the superiority or inferiority of the expression methods 1 to 3 related to the object, it is not appropriate to use the expression level which is an individual scale for each expression method. Therefore, in order to align the scale with an image that normalizes the expression level of each expression method, a common index is calculated for the expression level of each expression method. The common index is calculated for each expression method. That is, the common index of the expression method N is calculated based on the expression degree of the expression method N (N = 1, 2, 3) for each of the target thing and each comparative thing. Therefore, three common indices are obtained in the present embodiment.

  Specifically, the common index of each expression method is a value indicating the degree of weight of the expression of the target object based on the distribution of expression calculated for the expression method for each of the target object and the comparative object. Calculated. In other words, the expression distribution of each expression method can be said to represent each expression method tendency, and hence the influence on the expression of the tendency is reduced based on the distribution (a part or all of the influence is removed). By converting (converting), the degree of expression calculated based on different standards for each expression method is converted (converted) into a common index “relative ease of understanding for the entire genre (specified by the user)” Can do. As a result, the expression methods 1 to 3 can be compared on the same basis.

As a specific conversion method, for example, the distribution of the population is estimated based on the obtained numerical data, and the density of the input value (degree of frequent occurrence) is estimated. A distribution f ⁱ (x) of each expression degree of the target thing and the comparative thing of the expression method i is calculated using the expression.

図８に、各表現方法の表現度の分布の一例を示す。

FIG. 8 shows an example of the expression level distribution of each expression method.

Then, when the frequency of appearance (appearance frequency) is relatively low and the expression level is relatively high, the target in the distribution f ⁱ (x) of the expression level of the expression method i is set as a calculation policy that the common index is increased. A common index of the degree of expression a of things can be calculated by the following formula.

Common index = a / f ⁱ (a)
For example, even if the degree of expression is the same 0.9, when most of the other degrees of expression in the same expression method are 0.9, the frequency of occurrence is high and the value of the common index is low. On the other hand, when the other degree of expression is only 0.1, the frequency of occurrence is low and the value of the common index is high.

  For example, when the expression level 1 of the expression “Karukan” is 0.5, the expression level 2 is 0.9, and the expression level 3 is 0.75, the common index for each expression method Is calculated as follows.

Common index for expression method 1 = 0.5 / f ¹ (0.5)
Common index for expression method 2 = 0.9 / f ² (0.9)
Common index for expression method 3 = 0.75 / f ³ (0.75)
Each calculated common index is transmitted to the display shaping unit 16.

  Subsequently, the presentation rule acquisition unit 15 acquires a presentation rule (hereinafter referred to as “target presentation rule”) corresponding to the presentation environment information transmitted from the reception unit 11 in step S4 from the presentation rule definition DB 130, and presents the presentation rule. The rule is transmitted to the display shaping unit 16 (S9). For example, when the presentation environment information is “smartphone”, “within 1 content corresponding to“ smartphone ”in FIG. 6, within 2 content if one of them is an image content, and 300 for text content with a character size of 18 px or more. The presentation rule “within characters” is acquired.

  Thus, the presentation rule is information in which the number of expression methods and conditions to be output are defined according to the presentation environment. As a setting method of the presentation rule definition DB 130, for example, a method of reducing the number of presentation methods to be presented on a small screen such as a smartphone or designating a limit on the character size or the number of characters can be considered. At that time, it is conceivable to add a condition such that one image content is always displayed when the value of the common index of the expression method 1 is equal to or greater than a threshold value.

  Subsequently, the display shaping unit 16 generates presentation information based on the common index for each expression method, the expression information of the target thing, and the target presentation rule (S10). The selection order of the expression information to be included as content in the presentation information (used for presentation information) follows the order in which the value of the common index calculated for the expression method related to each expression information is large. Therefore, in the presentation rule, when the number of contents is 2 or less, the presentation information related to the presentation method having the lowest common index is not included in the presentation information.

  For example, as shown in FIG. 9, when the target information “Karukan” and the genre name “Japanese confectionery” are input, if the presentation environment is “smartphone”, if one of the contents is an image content, the content is within two contents. Therefore, the expression information of expression method 1 (explained in image) and the expression information of expression method 2 (explained in illustration), which are the top two common indices calculated for each expression method, are selected as contents to be included in the presentation information. It is. The display method of each content at the time of presentation may be an arbitrary position on the screen. If an image is included, the positional relationship such as an image at the top and characters at the bottom may be set.

  Subsequently, the display shaping unit 16 transmits the presentation information to the transmission unit 17 (S11). The transmission unit 17 transmits the presentation information to the user terminal 20 (S12). As a result, the presentation information is displayed on the user terminal 20.

  With the above processing, it is possible to compare different expression methods based on a common standard for arbitrary target information input by the user, and to present a description in a relatively easy-to-understand expression method.

  As described above, according to the present embodiment, it is possible to automatically select a relatively easy-to-understand expression method for an arbitrary thing, thereby supporting efficient understanding of the thing. Easily understand different expression methods that cannot be compared with the same standard, and compare with a common standard, so even if there is a limit to the amount of information that can be presented, such as a small screen, select an appropriate expression method with priority based on a common indicator be able to.

  In the present embodiment, the target thing is an example of the first thing. The comparative thing is an example of the second thing. The expression level calculation unit 13 is an example of an acquisition unit and a first calculation unit. The common index calculation unit 14 is an example of a second calculation unit. The display shaping unit 16 is an example of a selection unit.

  Although the embodiments of the present invention have been described in detail above, the present invention is not limited to such specific embodiments, and various modifications can be made within the scope of the gist of the present invention described in the claims. Deformation / change is possible.

DESCRIPTION OF SYMBOLS 10 Comprehension support apparatus 11 Receiving part 12 Condition extraction part 13 Expression degree calculation part 14 Common index calculation part 15 Presentation rule acquisition part 16 Display shaping part 17 Transmission part 20 User terminal 100 Drive apparatus 101 Recording medium 102 Auxiliary storage apparatus 103 Memory apparatus 104 CPU
105 Interface device 120 Comparison target definition DB
130 Presentation rule definition DB
B bus

Claims (6)

An acquisition procedure for acquiring expression information by a plurality of types of expression methods for each of the first thing and one or more second things related to the first thing;
A first calculation procedure for calculating a degree of expression that quantitatively indicates the appropriateness of the explanation of the corresponding thing with respect to the expression information by each expression method of each of the first thing and the second thing;
A second calculation procedure for calculating, for each expression method, a common index for the expression degree of the first thing, in which the influence of the tendency of the expression method on the expression degree is reduced based on the distribution of the expression degree. When,
A selection procedure for selecting expression information to be used for explanation of the first thing based on the common indicator;
An understanding support method characterized in that a computer executes. In the second calculation procedure, the common index is increased so that the frequency of appearance of the first thing in the distribution is relatively low and the common index is large when the expression is relatively large. To calculate,
The understanding support method according to claim 1, wherein: The plurality of types of expression methods include one or more of an expression by an image, an expression by an analogy, and an expression by a summary of evaluation information of things.
The understanding support method according to claim 1 or 2, characterized in that: The selection procedure further selects expression information to be used for explanation of the first thing based on rule information defined according to a type of output destination of the expression information.
The understanding support method according to any one of claims 1 to 3. An acquisition unit that acquires expression information by a plurality of types of expression methods for each of the first thing and one or more second things related to the first thing;
A first calculation unit that calculates an expression that quantitatively indicates the appropriateness of the explanation of the corresponding thing for the expression information by each expression method of each of the first thing and the second thing;
A second calculation unit that calculates, for each expression method, a common index for which the influence of the tendency of the expression method on the expression level is reduced based on the distribution of the expression level for the expression level of the first thing. When,
A selection unit that selects expression information used to describe the first thing based on the common index;
An understanding support apparatus characterized by comprising:   A program for causing a computer to execute the understanding support method according to any one of claims 1 to 4.

Images