JP6707484B2 - Understanding support method, understanding support device and program - Google Patents

Description

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

In recent years, with the increase in the number of foreigners visiting Japan, there are many opportunities to provide easy-to-understand information to tourists. Also, when we Japanese go abroad, there are many occasions where we need to explain things that we are not familiar with, such as food that we see for the first time. As a method for understanding unfamiliar things, it is often the case to look up the explanation in a guidebook or to enter a keyword in a Web search and browse the explanation such as a dictionary from the search results.

These methods are complicated because the user needs to look down and understand the search results by himself.

Further, as a method for supporting understanding of unfamiliar things, a method of promoting understanding by devising a presentation order of search results of Web pages has been proposed so far.

Yoko Nishihara, Wataru Sunayama, Masahiko Yachida, "Information Understanding Support System based on Web Page Difficulty and Learning Order", IEICE Transactions D, Vol.J89-D, No.9, pp.1963-1975, 2006.

The method of Non-Patent Document 1 proposes a system that promotes understanding of unfamiliar words in order from simple content by presenting Web search results in order based on difficulty level. If the entered keyword is a difficult word such as a technical term, the search results can be compared based on the degree of difficulty, but if the name of food is entered, the keyword included in the search result will be the raw material, the place of origin, the taste, etc. Since there is no difference in difficulty in explanation, the order of explanation cannot be determined by difficulty. In addition, if you want to immediately know about food in front of you when traveling, it is complicated to read the search results carefully.

Also, as a related service, there is a service "GourNavi foreign language version" that presents supplementary explanations of menus posted on restaurant sites to foreigners. In this service, the supplementary explanation to be presented needs to be selected and input by the restaurant (service provider) side in advance, and the explanation cannot be automatically generated, which is troublesome. Further, when a plurality of ingredients are included, it is not possible to deal with the explanation of each ingredient.

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-mentioned problems, an acquisition procedure for acquiring document information about a certain thing, an extraction procedure for extracting the constituent elements of the document information, and a plurality of terms used for explaining the thing are described in terms of roles in the description. From the storage unit that classifies and stores the plurality of groups, the determination procedure for determining the group to which each of the constituent elements belongs , and the maximum presentation number in each group in order from the group with the highest priority. And a selection procedure for selecting, as an output target, a component number equal to or less than the maximum number determined in total .

It can support efficient understanding of things.

It is a figure showing an example of composition of a system in an embodiment of the invention. It is a figure showing an example of hardware constitutions of understanding support device 10 in an embodiment of the invention. It is a figure showing an example of functional composition of understanding support device 10 in an embodiment of the invention. 6 is a flowchart for explaining an example of a processing procedure executed by the understanding support device 10. It is a figure which shows an example of the extraction result of a component and element importance. It is a figure which shows the structural example of structured rule definition DB120. It is a figure which shows the example in which the structure tag was attached to each component. It is a figure which shows the structural example of presentation rule definition DB130. It is a figure which shows an example of presentation information.

Hereinafter, embodiments of the present invention will be described with reference to the drawings. FIG. 1 is a diagram showing a configuration example of a system according to an embodiment of the present invention. In FIG. 1, the understanding support device 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 an arbitrary thing that the user is not familiar with (proprietary nouns such as product names, general nouns such as "udon", menu names such as "teriyaki teriyaki", landmark names and place names). One or more computers that generate and output information (hereinafter referred to as “presentation information”) to be presented to the user in order to assist understanding of (hereinafter referred to as “target object”).

The user terminal 20 is capable of inputting information (hereinafter, referred to as “target information”) indicating a target object such as a smartphone, a tablet, a PC owned by a user, a terminal installed in a public place such as a store or a station. Equipment. As an example of the target information, there are a name of the target object, a term representing the target object, and the like. The input method of the target information may be any method such as voice input, touch panel selection, character input, or keyboard input.

FIG. 2 is a diagram showing a hardware configuration example of the understanding support device 10 in the embodiment of the present invention. The understanding support device 10 of FIG. 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, which are connected to each other by a bus B.

A program that realizes the processing in the understanding support device 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, it is not always necessary to install the program from the recording medium 101, and the program may be downloaded from another computer via the 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 the program when an instruction to activate the program is given. The CPU 104 executes a function related to the understanding support device 10 according to 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 showing a functional configuration example of the understanding support device 10 in the embodiment of the present invention. 3, the understanding support device 10 includes a receiving unit 11, a condition extracting unit 12, an element extracting unit 13, a configuration information acquiring unit 14, a presentation rule acquiring unit 15, a display shaping unit 16, a transmitting unit 17, and the like. Each of these units is realized by a process that causes the CPU 104 to execute one or more programs installed in the understanding support device 10. The understanding support device 10 also uses databases (storage units) such as the structured rule definition DB 120 and the presentation rule definition DB 130. Each of these databases can be realized using, for example, the auxiliary storage device 102 or a storage device that can be connected to the understanding support device 10 via a network.

The processing procedure executed by the understanding support device 10 will be described below. 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, the acquisition request for the presentation information of the target object related to the target information input to the user terminal 20. The acquisition request includes the target information.

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 indicates the type of environment (user terminal 20) to which the presentation information is output, such as “smartphone”, “PC”, “tablet”, “smart TV”, or the like. In the present embodiment, an example will be described in which the input source of the target information and the output destination of the presentation information are the same user terminal 20, but when the input source and the output destination are different, the user of the output destination The presentation environment information of the terminal 20 may be acquired. The presentation environment information may be automatically discriminated by the condition extraction unit 12 based on the information included in the presentation information acquisition request transmitted from the user terminal 20. It may be explicitly input by the user. When the presentation environment information is automatically discriminated, if the presentation environment information cannot be discriminated, a preset default value (for example, “smartphone” or the like) may be adopted as the presentation environment information.

Subsequently, the reception unit 11 transmits the received target information to the element extraction unit 13 (S3) and the presentation environment information to the presentation rule acquisition unit 15 (S4).

Subsequently, the element extraction unit 13 collects the information source D1 of the presentation information for the target information (S5). The information source D1 may be, for example, the top 100 snippets obtained by searching the target information as a search word on the Web (Internet). That is, the information source D1 is a document information group in which some kind of information related to the target object (information describing the target object or information indicating the characteristics of the target object) is described.

Subsequently, the element extracting unit 13 extracts the constituent element of the information source D1 and the element importance degree of each constituent element from the information source D1 (S6). The component is, for example, a word, and the element importance is the word importance. The components may be obtained by morphologically analyzing the information source D1. For the morphological analysis, for example, a tool disclosed in “http://tools.metro-bb.com/api/keitaiso” may be used. When a plurality of pieces of document information, such as 100 snippets, is the information source D1, the element extraction unit 13 performs a morpheme analysis on the document information in which all the collected pieces of document information are combined into one. Get the component group (word group). The element importance degree (word importance degree) of the constituent element may be any numerical value capable of indicating the degree of importance in the expression of the feature of the target object such as the appearance frequency obtained by the morpheme analysis.

FIG. 5 is a diagram showing an example of the extraction result of the constituent elements and the element importance degree. In FIG. 5, the information source D1 in the case where the target information is “namero”, and the constituent elements and element importance levels extracted from the information source D1 are shown.

Subsequently, the element extraction unit 13 transmits each component and the element importance of each component to the configuration information acquisition unit 14 (S7).

Subsequently, the configuration information acquisition unit 14 refers to the structured rule definition DB 120, and determines the priority order for selecting the configuration element to be included in the presentation information for each configuration element (S8).

FIG. 6 is a diagram showing a configuration example of the structured rule definition DB 120. As shown in FIG. 6, in the structured rule definition DB 120, a plurality of registered keywords are registered in advance by being classified into one or more structure definitions. The structural definition is a concept that classifies a plurality of terms used to describe various things into a plurality of groups in terms of their roles in the description. The registered keyword is a term used to describe things.

In each structure definition, a presentation importance, which is a priority when presenting registered keywords as presentation information, is set. In the present embodiment, the larger the value of the presentation importance, the higher the priority. The same presentation importance level may be set for a plurality of structure definitions. The presentation importance may be any value as long as the relative priorities between the structure definitions can be compared, and may be defined by a fine numerical value such as a small number.

Although FIG. 6 shows an example in which six structural definitions of “category”, “composition (material)”, “composition (making method)”, “evaluation”, “positioning” and “special element” are registered. The classification form of structure definitions and the number of structure definitions are not limited to predetermined ones.

The “category” is a category (group) to which a term expressing a category of a thing, that is, what the thing is other than a term used as target information belongs. In the case of food, dishes, foods, luxury items, etc. are considered as part of the "category", and in the case of buildings, temples, buildings, etc. are considered as part of the "category".

“Structure” is a classification (group) to which the terms used for objectively explaining the thing itself belong. In the case of food, ingredients such as ingredients and seasonings, and recipes such as cooking methods and cutting methods are considered as part of the composition, and in the case of buildings, appearance such as size and color, period and related people are considered. History can be considered as a part of "composition".

“Evaluation” is a classification (group) to which a term used when expressing a person's impression of a thing belongs. "Positioning" is a classification (group) to which terms expressing how things are perceived in society (social positioning of things) belong. The “special element” will be described later.

Registration of registered keywords is performed by referring to the classification definitions of words such as Japanese Vocabulary (http://www.kecl.ntt.co.jp/icl/lirg/resources/GoiTaikei/). Good. In the Japanese vocabulary system, an arbitrary word classification is defined. A term corresponding to this classification may be registered as a registered keyword. Which structural definition each term belongs to may be determined by the registrant. Moreover, a term that does not exist in the Japanese vocabulary system may be added to the registered keywords.

It should be noted that what kind of grouping is to be performed as the structure definition, the degree of presentation importance, etc. may be determined based on a user survey or evaluation. The example of FIG. 6 is the presentation importance level and the structure definition that are actually determined based on the knowledge of the user survey. Further, a plurality of structured rule definition DBs 120 may be prepared according to the types of things such as food, buildings, and others.

In step S8, the configuration information acquisition unit 14 specifies the structure definition and the presentation importance degree with reference to the structured rule definition DB 120 for each component obtained from the information source D1. That is, the configuration information acquisition unit 14 classifies each of the constituent elements into any of the structure definitions, and specifies the presentation importance degree corresponding to the structure definition of the classification destination for each of the constituent elements.

Specifically, the configuration information acquisition unit 14 acquires the structure definition and the presentation importance degree corresponding to the registered keyword for the component that completely matches any of the registered keywords. The configuration information acquisition unit 14 acquires the structure definition and the presentation importance degree corresponding to the registered keyword that matches the classification of the component, for the component that does not completely match any of the registered keywords. A Japanese vocabulary system may be used to specify the classification of the component. For example, when the classification of “cooking” is specified in the Japanese vocabulary for the constituent element “local cuisine”, the configuration information acquisition unit 14 determines the structure definition and the presentation importance degree corresponding to the registered keyword “cooking”. get. The configuration information acquisition unit 14 adds the structure definition specified for each component to the component as a structure tag. In addition, for a component whose classification obtained in the Japanese vocabulary system does not match any of the registered keywords, the configuration information acquisition unit 14 uses the name of the classification (classification name) as a structure tag as the structural element. Give. FIG. 7 shows an example in which a structural tag is added to each component.

If a certain component is a word such as a proper noun that is not included in the Japanese vocabulary, and the component importance of the component is higher than the threshold, the configuration information acquisition unit 14 The constituent element may be registered in the registration keyword of the “special element” in the structured rule definition DB 120. In this case, the structure tag given to the component is a "special element". Further, the threshold may be, for example, an average value of the element importance degrees of the respective constituent elements. When the structure definition “special element” does not exist in the structured rule definition DB 120, the structure definition “special element” is added to the structured rule definition DB 120 and then the registered keyword of the structure definition is added. It suffices if components are added. At this time, the presentation importance of the structure definition may be set to a value lower than any presentation importance of the existing structure definitions.

Subsequently, the configuration information acquisition unit 14 transmits all the components and the element importance, the structure tag, and the presentation importance of each component to the display shaping unit 16 (S9).

Subsequently, the presentation rule acquisition unit 15 acquires the 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 transmits the presentation rule to the display shaping unit 16 (S10). ).

FIG. 8 is a diagram showing a configuration example of the presentation rule definition DB 130. As shown in FIG. 8, a presentation rule is registered in the presentation rule definition DB 130 for each presentation environment that is a candidate output destination of presentation information.

The presentation rule is information that defines the amount of information (the number of components, etc.) included in the presentation information according to the presentation environment. For example, the presentation rule defines an output target (target included in the presentation information) based on the structure definition and the element importance.

As a presentation rule, a rule that preferentially selects a component having a high presentation importance can be considered. At that time, if the element importance of the selected component is equal to or more than the threshold value th1, a plurality of pieces of information are presented from the same structural definition as the component, and if the element importance is equal to or less than the threshold value th2, the component element is selected. It is also possible to add conditions such as not presenting two or more of the same structure definition. The threshold th1 may be, for example, the average value of the element importance degrees, and the threshold th2 may be 1, for example.

As a method of setting the presentation rule definition DB 130, regarding the number of pieces of information to be presented, for example, assuming that a character size of 12 pt or more is set as 4 characters per information, the number of characters that fit within 80% or less of the average smartphone screen size is set. A method such as the amount can be considered.

For example, when the presentation environment information is “smartphone”, the presentation rule acquisition unit 15 associates “smartphone” in the presentation rule definition DB 130 (FIG. 8) with “one structural element whose category is the structure definition”. The presentation rule is to present, and then present the constituent elements of each structure definition in order from the one with the highest element importance in order of the highest presentation importance with respect to the other structure definitions, and present up to seven pieces of information. To get.

In this way, the presentation environment information is used to acquire the presentation rule. Therefore, the presentation environment information may be any information that can identify the presentation environment with the granularity registered as “presentation environment” in the presentation rule definition DB 130.

Note that, for example, the presentation environment may be further finely classified based on the model of the smartphone, the PC, or the like, the model of the display connected to the user terminal 20, or the like. In this case, the presentation rule can be set more finely according to the number of characters to be presented and the font size.

Subsequently, the display shaping unit 16 includes (configures as an output target) all the constituent elements in the presentation information based on the element importance degree of each constituent element, the structure tag and the presentation importance degree, and the presentation rule. An element is selected (S11). For example, according to the presentation rule corresponding to “smartphone” in FIG. 8, first, one component having the highest element importance (“local cuisine”) is selected from the components having the structural definition of “category”. To be done. Next, in order from the structure definition with the highest presentation importance, two constituent elements applicable to each structure definition are provided in order from the element with the highest element importance, and up to one if the element importance is 1 or less. Since it is selected until it becomes an individual, "miso, horse mackerel" belonging to "composition (material)" is selected, "tataki, grated" belonging to "composition (how to make)" is selected, and "stickiness" belonging to "evaluation" is selected. Is selected, and a “knob” belonging to “positioning” is selected.

Subsequently, the display shaping unit 16 generates the presentation information based on the selected component (S12). The presentation information may be a list of selected components in the order of selection, or may be a sentence formed by connecting the components. Moreover, as shown in FIG. 9, a component may be included for each structure definition. Note that FIG. 9 shows an example in which the constituent element selected in “Category” is applied to “XXX” of “This is XXX”. In addition, “composition (material)” is replaced with “main material”, “composition (how to make)” is replaced with “cooking method”, and “evaluation” is replaced with “taste/texture”. , Each structure definition is replaced with an expression suitable for the type of target object.

Subsequently, the display shaping unit 16 transmits the presentation information to the transmission unit 17 (S13). The transmission unit 17 transmits the presentation information to the user terminal 20 (S14). As a result, the presentation information is displayed on the user terminal 20.

As described above, according to the present embodiment, since information (components) that is highly effective in promoting understanding of the target object is preferentially presented, it is possible to support efficient understanding of the target object. .. Further, since the feature of the target object is derived from the Web information or the like, it is possible to generate a description (presentation information) including a term that is not in the dictionary. Furthermore, by determining the priority of the information to be presented according to the presentation environment, the amount of information can be narrowed down according to the presentation environment.

In addition, in this Embodiment, the element extraction part 13 is an example of an acquisition part and an extraction part. The configuration information acquisition unit 14 is an example of a determination unit. The display shaping unit 16 is an example of a selection unit. The structured rule DB 120 is an example of a storage 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 are possible within the scope of the gist of the present invention described in the claims. It can be modified and changed.

10 understanding support device 11 receiving unit 12 condition extracting unit 13 element extracting unit 14 configuration information acquiring unit 15 presentation rule acquiring unit 16 display shaping unit 17 transmitting unit 20 user terminal 100 drive device 101 recording medium 102 auxiliary storage device 103 memory device 104 CPU
105 Interface device 120 Structured rule definition DB
130 Presentation rule definition DB
B bus D1 information source

Claims (7)

An acquisition procedure for acquiring document information about a certain thing,
An extraction procedure for extracting the constituent elements of the document information,
A determination procedure for determining a group to which each of the constituent elements belongs by referring to a storage unit that stores a plurality of terms used to describe an object by classifying them into a plurality of groups from the viewpoint of the role in the description,
In order from the group with the highest priority , under the provision of the maximum number of presentations in each group, a selection procedure for selecting as many output components as the maximum number or less determined in total ,
An understanding support method, characterized in that a computer executes. The extraction procedure to extract the respective importance of the components of multiple,
The selection procedure for a plurality of said component which are determined to belong to the same group, to select a component to be outputted is based on the importance,
The understanding support method according to claim 1, wherein: An acquisition procedure for acquiring document information about a certain thing,
An extraction procedure for extracting the constituent elements of the document information,
A determination procedure for determining a group to which each of the constituent elements belongs by referring to a storage unit that stores a plurality of terms used to describe an object by classifying them into a plurality of groups from the viewpoint of the role in the description,
A selection procedure for preferentially selecting a component determined to belong to a group with a high priority as an output target,
The computer runs
The extraction procedure extracts the importance of each of the plurality of components,
The selection procedure refers to the information defining the output target based on the group and the degree of importance according to the output destination of the component, the plurality of the components determined to belong to the same group, the Select the component to be output based on the importance ,
Understand support how to, characterized in that. An acquisition unit that acquires document information about a certain thing,
An extraction unit for extracting the constituent elements of the document information,
A determination unit that determines a group to which each of the constituent elements belongs by referring to a storage unit that stores a plurality of terms used to describe an object by classifying them into a plurality of groups from the viewpoint of the role in the description,
In order from the group with the highest priority , under the provision of the maximum number of presentations in each group, a selection unit that preferentially selects the constituent elements less than the maximum number determined in total as an output target,
An understanding support device characterized by having. The extraction unit extracts each of importance of the components of multiple,
The selection unit includes a plurality of said component which are determined to belong to the same group, to select a component to be outputted is based on the importance,
The understanding support device according to claim 4, wherein An acquisition unit that acquires document information about a certain thing,
An extraction unit for extracting the constituent elements of the document information,
A determination unit that determines a group to which each of the constituent elements belongs by referring to a storage unit that stores a plurality of terms used to describe an object by classifying them into a plurality of groups from the viewpoint of the role in the description,
A selection unit that preferentially selects a component determined to belong to a group with a high priority as an output target,
Have
The extraction unit extracts the importance of each of the plurality of components,
The selecting unit refers to the information defining the output target based on the group and the importance according to the output destination of the constituent element, and for the plurality of constituent elements determined to belong to the same group, Select the component to be output based on the importance ,
Understanding support device characterized in that. A program that causes a computer to function as each unit according to any one of claims 4 to 6.

Images