JP7339148B2 - Search support device - Google Patents

Description

One aspect of the present invention relates to a search support device.

2. Description of the Related Art Conventionally, there has been known a search system that performs a search based on a search keyword input by a user and presents documents hit by the search to the user. In such a search system, in order for a document desired by the user to be hit by search, the user needs to enter an appropriate search keyword. However, the user does not necessarily know appropriate search keywords (eg, technical terms, etc.).

Patent Literature 1 discloses a mechanism for presenting related keywords related to a search keyword input by the user to the user. According to the method described in Patent Document 1, documents obtained as search results of a document database using a search keyword input by a user are assigned to the first group, and documents not obtained as search results are assigned to the second group. Then, an arbitrary keyword is extracted from the documents in the first group. given a higher rating. Then, highly rated keywords are presented to the user as related keywords.

Japanese Patent Application Laid-Open No. 2009-217406

As one form of the above-described retrieval system, there is a system for retrieving documents divided into a plurality of parts. For example, there is an FAQ search system that searches for a document desired by a user from documents in which question sentences and answer sentences are paired. It is possible to apply the mechanism disclosed in Patent Document 1 to such an FAQ search system. However, the mechanism disclosed in Patent Literature 1 does not focus on the fact that the document data to be searched is divided into a plurality of parts like the FAQ search system, and improves the user's search efficiency. There is room for improvement in terms of

SUMMARY OF THE INVENTION Accordingly, it is an object of one aspect of the present invention to provide a search support apparatus capable of improving search efficiency for a document divided into a plurality of parts.

A search support device according to one aspect of the present invention is a search support device that supports a search for a plurality of document data each including first character string information and second character string information that are associated with each other, wherein a user inputs a document related to the search keyword by searching a plurality of document data using the search keyword with both the first character string information and the second character string information as search targets; a retrieval unit that acquires one or more related documents as data; an extraction unit that extracts characteristic words that characterize the one or more related documents from the first character string information of the one or more related documents; a presenting unit for presenting the feature word to the user.

In the search support device according to one aspect of the present invention, by setting the entire document data (the first character string information and the second character string information) as the search range, compared with the case where part of the document data is set as the search range By doing so, many related documents can be obtained by searching. On the other hand, when extracting characteristic words, it is possible to extract limited characteristic words by setting part of the document data (first character string information) as an extraction range. That is, when retrieving related documents, emphasis is placed on coverage and more related documents are acquired, while when extracting feature words, the search range is limited to obtain feature words with higher accuracy. can be presented to the user. By performing a search using such feature words as new search keywords (or additional search keywords), the user can efficiently search for document data desired by the user. . Therefore, according to the search support device, it is possible to improve the efficiency of searching a document divided into a plurality of parts.

According to one aspect of the present invention, it is possible to provide a search support device capable of improving search efficiency for a document divided into a plurality of parts.

It is a figure which shows the functional structure of the search assistance apparatus which concerns on embodiment. It is a figure which shows an example of the suggestion function by a search assistance apparatus. FIG. 3 is a diagram showing an example of document data stored in a document DB and keywords extracted by a preprocessing unit; It is a flowchart which shows an example of operation|movement of a search assistance apparatus. It is a figure which shows an example of the hardware constitutions of a search assistance apparatus.

An embodiment of the present invention will be described in detail below with reference to the accompanying drawings. In the description of the drawings, the same or corresponding elements are denoted by the same reference numerals, and overlapping descriptions are omitted.

FIG. 1 is a diagram showing the functional configuration of a search support device 10 according to one embodiment. The search support device 10 is a device that supports searching for a plurality of document data each including first character string information and second character string information that are associated with each other. As an example in this embodiment, the first character string information is information indicating a question sentence. Also, the second character string information is information indicating an answer to the question. That is, the search support device 10 is a device that supports a user's search processing in an FAQ search system that searches for document data consisting of pairs of question sentences and answer sentences. More specifically, as an example in the present embodiment, the search support device 10 acquires a search keyword being input by the user, and has a suggestion function that presents the user with a feature word corresponding to the search keyword as an additional search keyword. I will provide a.

FIG. 2 is a diagram showing an example of the suggestion function of the search support device 10. As shown in FIG. FIG. 2 shows a search window W1 and a suggestion window W2 displayed on, for example, a web page. The search window W1 is an area where the user inputs a search keyword. In this example, the search keyword "line contract" is entered in the search window W1. The suggestion window W2 is an area in which one or more feature words presented to the user by the search support device 10 (presentation unit 15 described later) are displayed. As an example, the suggestion window W2 is displayed directly below the search window W1 in response to the user's input of a search keyword.

In the example of FIG. 2, two characteristic words "family discount" and "family" are displayed in the suggestion window W2 to the user as additional search keywords (that is, search keywords used together with the original search keyword "line contract"). Presented. If a search is performed using only the search keyword input by the user, many document data including document data other than the document data desired by the user are hit, and the document data desired by the user is found among them. It can take a lot of work to do. Therefore, the search support device 10 improves the user's search efficiency by proposing to the user a search using an additional keyword (that is, a feature word) for appropriately narrowing down.

The search support device 10 is composed of one or more computer devices. The form of the search support device 10 is not limited to a specific form. For example, the search support device 10 may be a terminal such as a smartphone, a tablet terminal, or a personal computer owned by the user, or may be configured to be capable of communicating with the terminal (client terminal) as described above. It may also be a server device configured to process the request.

As shown in FIG. 1 , the document DB 10 a and the search support device 10 are provided with a preprocessing section 11 , an acquisition section 12 , a search section 13 , an extraction section 14 and a presentation section 15 .

The document DB 10a is a database that stores a plurality of document data to be searched. As described above, each document data is character string information including a question sentence and an answer sentence that are associated with each other. The upper part of FIG. 3 shows an example of document data. The document data exemplified in FIG. 3 consists of a question sentence "What is the range of family members who can apply for a family discount?" and

The preprocessing unit 11 extracts one or more keywords included in the question sentence of the document data for each of the plurality of document data, and executes preprocessing for associating the extracted one or more keywords with the document data. Here, a keyword is a character string consisting of one or more words. A keyword is a character string that is a candidate for a feature word extracted by the extraction unit 14, which will be described later. The preprocessing unit 11 extracts keywords included in the question sentence of the document data by using a known text analysis technique such as morphological analysis.

In this embodiment, as an example, the preprocessing unit 11 extracts nouns or noun strings as the keywords. In the example of FIG. 3, the preprocessing unit 11 extracts the nouns "family", "range", and "where" from the question sentence of the document data, and the two consecutive nouns "family" and "discount". "Family Discount", which is a combined noun string, is extracted as a keyword. A technical term such as a specific service name may be a name that combines a plurality of (here, two as an example) nouns, such as "family discount". Therefore, by extracting a noun string as a keyword as described above, a group of meaningful words can be extracted as one keyword.

The preprocessing unit 11 associates one or more keywords extracted from certain document data by the above process with the document data. For example, the preprocessing unit 11 performs the above processing on a record of document data stored in the document DB 10a (data structure having a question text field for storing a question text and an answer text field for storing an answer text). Add a keyword field to store one or more extracted keywords. That is, the preprocessing unit 11 generates a data structure in which the question sentences, answer sentences, and keywords shown in FIG. 3 are associated with each other for each piece of document data.

Acquisition unit 12 acquires a search keyword input by a user. In this embodiment, the acquisition unit 12 is configured to acquire in real time a search keyword (here, "line contract") input (in the middle of input) in the search window W1 shown in FIG. Here, the term "search keyword in the middle of input" refers to the period from when the user starts inputting a search keyword into the search window W or the like until the user determines the search keyword (that is, an operation for instructing execution of a search using the search keyword). ) is the search keyword that has been entered.

The search unit 13 searches for a plurality of document data stored in the document DB 10a using the search keyword acquired by the acquisition unit 12, thereby acquiring one or more related documents that are document data related to the search keyword. do. The search unit 13 performs the above-described search with both the question sentence and the answer sentence of each document data as search targets. Through such search processing, for example, document data in which a search keyword is included in a question sentence or an answer sentence is acquired as a related document. Any known search algorithm can be used as the search algorithm executed by the search unit 13 . The search unit 13 is configured to obtain as many related documents as possible by conducting a search with all character strings included in document data as a search target, with emphasis on coverage.

The extraction unit 14 extracts characteristic words from the question sentences of the one or more related documents acquired by the search unit 13 . In this embodiment, the extraction unit 14 extracts one or more characteristic words from among one or more keywords associated with one or more related documents (that is, the keywords extracted by the preprocessing unit 11 (see FIG. 2)). Extract.

In this embodiment, as described above, the preprocessing unit 11 preliminarily extracts one or more keywords, which are feature word candidates, from the question text of each document data. In this case, the extraction unit 14 can extract characteristic words from the one or more keywords. In other words, the extraction unit 14 does not need to extract keywords (characteristic word candidates) included in the question sentences of the related documents as a preparatory process when executing the process of extracting characteristic words. That is, since the preprocessing unit 11 executes the preprocessing in advance, the preparatory processing can be omitted. As a result, the extraction processing of characteristic words by the extraction unit 14 is sped up.

A feature word is a keyword (character string consisting of one or more words) that characterizes one or more related documents acquired by the search unit 13 . For example, a feature word is a keyword that is particularly likely to appear in the one or more related documents. The extraction unit 14 can extract such feature words by executing any known algorithm. In this embodiment, as an example, the extraction unit 14 extracts the appearance ratio (first appearance ratio) of the keyword in the related document and the appearance ratio (second appearance ratio) of the keyword in the entire plurality of document data stored in the document DB 10a. , to calculate the evaluation value based on. Then, the extraction unit 14 extracts characteristic words from the one or more keywords based on the evaluation value for each keyword.

The first appearance ratio of a keyword is the value "Nr" obtained by dividing the number "N1" of related documents containing the keyword among the one or more related documents by the total number "Nr" of the one or more related documents acquired by the search unit 13. N1/Nr”. The second appearance ratio of a keyword is obtained by dividing the number "N2" of document data containing the keyword among the plurality of document data by the total number "Na" of the plurality of document data stored in the document DB 10a. N2/Na”. In the calculation of the first appearance ratio or the second appearance ratio, whether or not the keyword is included in the document data may be determined based on only the question sentence of the document data, or the question sentence and the answer sentence of the document data. Both may be considered. In the former case, only document data containing a keyword in the question sentence is counted as document data containing the keyword. On the other hand, in the latter case, document data containing a keyword in at least one of the question sentence and answer sentence is counted as document data containing the keyword.

The method of calculating the evaluation value based on the first appearance ratio and the second appearance ratio described above is not limited to a specific method, but as an example, the extraction unit 14 calculates the JLH score as the evaluation value for each keyword. The JLH score is a score determined by the following formulas (1) to (3).
Formula (1): JLH score = absolute percentage change × relative percentage change formula (2): absolute percentage change = first occurrence rate - second occurrence rate formula (3): relative percentage change = first occurrence rate / second occurrence ratio

As a concrete example, consider the following situation.
・Total number of related documents (Nr) acquired by the search unit 13 = 84
・Total number of document data stored in the document DB 10a (Na)=2403
・Number of documents including “Family Discount” out of 84 related documents (N1) = 10
・Number of documents including “Family Discount” out of 2403 document data (N2) = 23

In this case, the first appearance ratio "N1/Nr" is "0.1190 (=10/84)", and the second appearance ratio "N2/Na" is "0.009571 (=23/2403)". . Therefore, the absolute rate change is calculated as "0.1095 (=0.1190-0.009571)" by the above formula (2). Also, the relative ratio change is calculated as "12.43 (=0.1190/0.009571)" by the above formula (3). Therefore, the evaluation value (JLH score) of the keyword “family discount” is calculated as “1.361 (=0.1095×12.43)” by the above formula (1).

The presentation unit 15 presents the feature words extracted by the extraction unit 14 to the user. As shown in FIG. 2, in this embodiment, as an example, the presentation unit 15 adds an additional search keyword (a keyword for efficiently narrowing down the search) to be used together with the search keyword input by the user via the suggestion window W2. ), the feature words are presented to the user.

An example of the processing of the search support device 10 will be described with reference to the flowchart shown in FIG.

In step S1, the preprocessing unit 11 extracts one or more keywords included in the question sentence of the document data for each of a plurality of document data, and performs preprocessing for associating the extracted one or more keywords with the document data. Execute.

In step S2, the acquisition unit 12 acquires the search keyword input by the user. In this embodiment, the acquisition unit 12 acquires in real time a search keyword (here, "line contract") input (in the middle of input) in the search window W1 shown in FIG.

In step S3, the search unit 13 searches for a plurality of document data stored in the document DB 10a using the search keyword acquired by the acquisition unit 12 in step S2, and finds document data related to the search keyword. Get one or more related documents. The search unit 13 performs the above-described search with both the question sentence and the answer sentence of each document data as search targets.

In step S4, the extraction unit 14 extracts characteristic words from the question sentences of the one or more related documents acquired by the search unit 13 in step S3. Specifically, the extraction unit 14 extracts one or more feature words from one or more keywords associated with one or more related documents (that is, the keywords extracted by the preprocessing unit 11 in step S1). .

In step S5, the presentation unit 15 presents the feature words extracted by the extraction unit 14 to the user.

After the feature word is presented to the user by the presentation unit 15, the search support device 10 may operate as follows. That is, when the user selects a presentation keyword (for example, "line contract family discount") presented in the suggestion window W2 by the presentation unit 15, the acquisition unit 12 acquires the presentation keyword. Then, the search unit 13 searches for a plurality of document data stored in the document DB 10a using both the question sentence and the answer sentence as search targets and using the presented keywords. Subsequently, the search unit 13 sorts the document data hit by the search in the order of search scores (scores given according to the search algorithm used by the search unit 13), and ranks the top N (N is a predetermined number). document data is presented to the user as a search result. As described above, even if the user does not know the appropriate search keyword (technical term, etc.) for obtaining desired document data, the user can use the additional search keyword (feature word) provided by the search support device 10. It is possible to efficiently find the desired document data by executing the search using the relevant information.

In the search support device 10 described above, the search unit 13 sets the entire document data (question sentences and answer sentences) as the search range. related documents can be obtained by searching. On the other hand, when the extraction unit 14 extracts feature words, it is possible to extract limited feature words by setting part of the document data (first character string information) as an extraction range. That is, when retrieving related documents, emphasis is placed on coverage and more related documents are acquired, while when extracting feature words, the search range is limited to obtain feature words with higher accuracy. can be presented to the user. By performing a search using such feature words as new search keywords (or additional search keywords), the user can efficiently search for document data desired by the user. . Therefore, according to the search support device 10, it is possible to improve the efficiency of searching a document divided into a plurality of parts.

In general, in a document in which a question sentence and an answer sentence are paired, the question sentence is shorter than the answer sentence and is often compactly organized. Furthermore, in many cases, a keyword (characteristic word) related to the content that the user wants to search (content that the user wants to know) is included in the question rather than in the answer. By limiting the extraction range of feature words to question sentences using such properties, feature words related to the content that the user wants to search can be extracted with high accuracy. In other words, by excluding answer sentences from the extraction range of feature words, it is possible to reduce the possibility of extracting feature words unrelated to the content that the user wants to search.

The search support device 10 also includes a preprocessing unit 11 . Then, the extraction unit 14 extracts feature words from one or more keywords associated with one or more related documents (that is, keywords extracted in advance by the preprocessing unit 11). By executing the preprocessing in advance by the preprocessing unit 11, the feature word extraction processing by the extraction unit 14 can be simplified, and the extraction processing can be speeded up. As a result, feature words can be presented to the user at high speed. More specifically, it is possible to present additional keywords (characteristic words) to the user in a timely manner while the user is entering a search keyword, such as the suggestion function illustrated in FIG. It becomes possible.

The acquisition unit 12 acquires a search keyword that is being input by the user, and the presentation unit 15 presents the user with a feature word as an additional search keyword used for searching together with the search keyword. In this embodiment, the acquisition unit 12 acquires the search keyword input to the search window W1 before an operation is performed to instruct execution of a search using the search keyword. And the presentation part 15 presents a characteristic word as an additional search keyword used with the said search keyword to the suggestion window W2. According to the above configuration, it is possible to provide a suggestion function of timely presenting additional search keywords to the user for improving search accuracy.

Note that the preprocessing unit 11 may be omitted in the above embodiment. That is, step S1 in the flowchart shown in FIG. 4 may be omitted. In this case, in step S4, the extracting unit 14 performs preprocessing by the preprocessing unit 11 on the one or more related documents as preparatory processing for extracting characteristic words from the question sentences of the one or more related documents. A process corresponding to the process may be executed. However, as described above, the preparatory processing of the extraction unit 14 can be omitted by extracting keywords, which are candidates for feature words, in advance by the preprocessing unit 11 . As a result, the time until the feature word is presented in the suggestion window W2 can be shortened, and the user's convenience can be improved.

In the above-described embodiment, the document data to be searched includes a question sentence and an answer sentence, but the search support device 10 uses pairs other than the question sentence and the answer sentence (the first character string information and the second This may be applied when document data including character string information) is to be searched.

It should be noted that the block diagrams used in the description of the above embodiments show blocks in units of functions. These functional blocks (components) are implemented by any combination of at least one of hardware and software. Also, the method of realizing each functional block is not particularly limited. That is, each functional block may be implemented using one device physically or logically coupled, or directly or indirectly using two or more physically or logically separated devices (e.g. , wired, wireless, etc.) and may be implemented using these multiple devices. A functional block may be implemented by combining software in the one device or the plurality of devices.

Functions include judging, determining, determining, calculating, calculating, processing, deriving, examining, searching, checking, receiving, transmitting, outputting, accessing, resolving, selecting, choosing, establishing, comparing, assuming, expecting, assuming, Broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, assigning, etc. can't

For example, the search support device 10 according to one embodiment of the present disclosure may function as a computer that performs the communication control method of the present disclosure. FIG. 5 is a diagram showing an example of the hardware configuration of the search support device 10 according to one embodiment of the present disclosure. The search support device 10 described above may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, and the like.

Note that in the following description, the term "apparatus" can be read as a circuit, device, unit, or the like. The hardware configuration of the search support device 10 may be configured to include one or more of the devices shown in FIG. 1, or may be configured without some of the devices.

Each function in the search support device 10 is performed by causing the processor 1001 to perform calculations, controlling communication by the communication device 1004, and controlling the It is realized by controlling at least one of data reading and writing in 1002 and storage 1003 .

The processor 1001, for example, operates an operating system to control the entire computer. The processor 1001 may be configured by a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic device, registers, and the like.

The processor 1001 also reads programs (program codes), software modules, data, etc. from at least one of the storage 1003 and the communication device 1004 to the memory 1002, and executes various processes according to these. As the program, a program that causes a computer to execute at least part of the operations described in the above embodiments is used. For example, the extraction unit 14 may be implemented by a control program stored in the memory 1002 and running on the processor 1001, and other functional blocks may be implemented in the same way. Although it has been explained that the above-described various processes are executed by one processor 1001, they may be executed simultaneously or sequentially by two or more processors 1001. FIG. Processor 1001 may be implemented by one or more chips. Note that the program may be transmitted from a network via an electric communication line.

The memory 1002 is a computer-readable recording medium, and is composed of at least one of, for example, ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), and RAM (Random Access Memory). may be The memory 1002 may also be called a register, cache, main memory (main storage device), or the like. The memory 1002 can store executable programs (program codes), software modules, etc. for implementing a communication control method according to an embodiment of the present disclosure.

The storage 1003 is a computer-readable recording medium, for example, an optical disc such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disc, a magneto-optical disc (for example, a compact disc, a digital versatile disc, a Blu-ray disk), smart card, flash memory (eg, card, stick, key drive), floppy disk, magnetic strip, and/or the like. Storage 1003 may also be called an auxiliary storage device. The storage medium described above may be, for example, a database, server, or other suitable medium including at least one of memory 1002 and storage 1003 .

The communication device 1004 is hardware (transmitting/receiving device) for communicating between computers via at least one of a wired network and a wireless network, and is also called a network device, a network controller, a network card, a communication module, or the like.

The input device 1005 is an input device (for example, keyboard, mouse, microphone, switch, button, sensor, etc.) that receives input from the outside. The output device 1006 is an output device (eg, display, speaker, LED lamp, etc.) that outputs to the outside. Note that the input device 1005 and the output device 1006 may be integrated (for example, a touch panel).

Devices such as the processor 1001 and the memory 1002 are connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or may be configured using different buses between devices.

Further, the search support device 10 includes hardware such as a microprocessor, a digital signal processor (DSP), an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), and an FPGA (Field Programmable Gate Array). , and part or all of each functional block may be implemented by the hardware. For example, processor 1001 may be implemented using at least one of these pieces of hardware.

Although the present embodiments have been described in detail above, it will be apparent to those skilled in the art that the present embodiments are not limited to the embodiments described herein. This embodiment can be implemented as modifications and changes without departing from the spirit and scope of the present invention defined by the description of the claims. Therefore, the description in this specification is for the purpose of illustration and explanation, and does not have any restrictive meaning with respect to the present embodiment.

The processing procedures, sequences, flowcharts, etc. of each aspect/embodiment described in this disclosure may be rearranged as long as there is no contradiction. For example, the methods described in this disclosure present elements of the various steps using a sample order, and are not limited to the specific order presented.

Input/output information and the like may be stored in a specific location (for example, memory), or may be managed using a management table. Input/output information and the like can be overwritten, updated, or appended. The output information and the like may be deleted. The entered information and the like may be transmitted to another device.

The determination may be made by a value represented by one bit (0 or 1), by a true/false value (Boolean: true or false), or by numerical comparison (for example, a predetermined value).

Each aspect/embodiment described in the present disclosure may be used alone, may be used in combination, or may be used by switching according to execution. In addition, the notification of predetermined information (for example, notification of “being X”) is not limited to being performed explicitly, but may be performed implicitly (for example, not notifying the predetermined information). good too.

Software, whether referred to as software, firmware, middleware, microcode, hardware description language or otherwise, includes instructions, instruction sets, code, code segments, program code, programs, subprograms, and software modules. , applications, software applications, software packages, routines, subroutines, objects, executables, threads of execution, procedures, functions, and the like.

Software, instructions, information, etc. may also be sent and received over a transmission medium. For example, the software uses wired technology (coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL), etc.) and/or wireless technology (infrared, microwave, etc.) to create websites, Wired and/or wireless technologies are included within the definition of transmission medium when sent from a server or other remote source.

Information, signals, etc. described in this disclosure may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may refer to voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, light fields or photons, or any of these. may be represented by a combination of

In addition, the information, parameters, etc. described in the present disclosure may be expressed using absolute values, may be expressed using relative values from a predetermined value, or may be expressed using other corresponding information. may be represented.

The names used for the parameters described above are not limiting names in any way. Further, the formulas, etc., using these parameters may differ from those expressly disclosed in this disclosure. The various names assigned to these various information elements are not limiting names in any way, as the various information elements can be identified by any suitable name.

As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly specified otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

Any reference to elements using the "first," "second," etc. designations used in this disclosure does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient method of distinguishing between two or more elements. Thus, reference to a first and second element does not imply that only two elements can be employed or that the first element must precede the second element in any way.

Where "include," "including," and variations thereof are used in this disclosure, these terms are inclusive, as is the term "comprising." is intended. Furthermore, the term "or" as used in this disclosure is not intended to be an exclusive OR.

In this disclosure, where articles have been added by translation, such as a, an, and the in English, the disclosure may include the plural nouns following these articles.

In the present disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean that "A and B are different from C". Terms such as "separate," "coupled," etc. may also be interpreted in the same manner as "different."

DESCRIPTION OF SYMBOLS 10... Search assistance apparatus, 10a... Document DB, 11... Pre-processing part, 12... Acquisition part, 13... Search part, 14... Extraction part, 15... Presentation part.

Claims (3)

A search support device for supporting search of a plurality of document data each including first character string information and second character string information associated with each other,
an acquisition unit that acquires a search keyword input by a user;
One or more of the document data related to the search keyword by searching the plurality of document data using the search keyword with both the first character string information and the second character string information as search targets a search unit for acquiring documents related to
an extraction unit that extracts characteristic words that characterize the one or more related documents from the first character string information of the one or more related documents;
a presentation unit that presents the feature word extracted by the extraction unit to the user;
with
The first character string information is information indicating a question sentence,
The search support device , wherein the second character string information is information indicating an answer sentence to the question sentence . for each of the plurality of document data, extracting one or more keywords consisting of one or more words included in the first character string information of the document data, and applying the extracted one or more keywords to the document data; further comprising a preprocessing unit that executes preprocessing to associate,
2. The search support device according to claim 1 , wherein said extraction unit extracts said characteristic word from said one or more keywords associated with said one or more related documents. The acquisition unit acquires the search keyword being input by the user,
3. The search support device according to claim 1 , wherein said presenting unit presents said characteristic word to said user as an additional search keyword used for searching together with said search keyword.

Images