JP2023106724A - Support apparatus, support method, and support program - Google Patents

Abstract

To provide a support apparatus for search that can clarify a problem, a support method, and a support program.SOLUTION: A support apparatus, which is a support apparatus for search, includes a receiving unit which receives a search condition, a search unit which searches for a document including a sentence on at least a problem, based on the search condition received by the receiving unit, and a transmission unit which transmits a result searched by the search unit.SELECTED DRAWING: Figure 1

Description

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

Advance technical research is becoming more and more important in new technology development and product development (hereinafter simply referred to as new development). In such technical research, it is common to set a problem and search for a technology to solve the problem. However, after repeated searches, there is a risk that the search will only find hits for technologies that are different from what was expected, and the investigation will end in vain.

Especially when conducting new development, there is a high possibility that the setting of the problem will be ambiguous or the focus will be off due to lack of knowledge in the technical field to be investigated, and there is a high possibility that the investigation will end in vain. However, a conventional search support device (see, for example, Patent Document 1) generates a display screen on which screen processing is added to enable determination of matching points based on information about matching points between a target sentence and a reference sentence. It presents the degree of matching between the search conditions and the search results, such as making it possible to display the search results, and does not provide any support for the setting of tasks, which is the premise of the search.

JP 2020-181529 A

SUMMARY OF THE INVENTION It is an object of the present invention to provide a search support device, a support method, and a support program that can clarify the problem.

In order to solve the above problems, a support device according to the present invention is a search support device comprising: a receiving unit for receiving search conditions; a retrieval unit for retrieving a document to be retrieved; and a transmission unit for transmitting the retrieval result of the retrieval unit.

According to the present invention, it is possible to provide a search support device, a support method, and a support program that can clarify a problem.

It is a figure which shows an example of arrangement|positioning of the search system which concerns on embodiment. It is a figure which shows an example of a structure of the support apparatus which concerns on embodiment. It is a figure which shows an example of a structure of the support apparatus which concerns on embodiment. It is a figure which shows an example of a structure of the user terminal which concerns on embodiment. It is a figure which shows an example of a structure of the user terminal which concerns on embodiment. It is a figure which shows an example of the search result shown to the user terminal which concerns on embodiment. It is a figure which shows an example of the search result shown to the user terminal which concerns on embodiment. 6 is a flow chart showing an example of processing by the search system according to the embodiment;

[Embodiment]
Embodiments of the present invention will be described below with reference to the drawings.
First, the search system 1 according to the embodiment will be described. FIG. 1 is a diagram showing an example of the configuration of a search system according to an embodiment. A search system 1 includes a server 2 and one or more user terminals 3 connected to the server 2 via a network 4 . The server 2 is also configured to access an external database via the network 4 to refer to and acquire data. In the example shown in FIG. 1, the search system 1 includes one server 2 and one user terminal 3, but the number of servers 2 and user terminals 3 included in the search system 1 is arbitrary. The user terminal 3 may be a desktop PC (Personal Computer), a tablet PC, a smart phone, or the like.

(Server 2)
2 and 3 are configuration diagrams of the server 2. FIG. FIG. 2 shows the main hardware configuration of the server 2. The server 2 has a configuration in which a communication IF 200A, a storage device 200B, and a CPU 200C are connected via a bus. Although not shown in FIG. 2, the server 2 includes input devices (for example, mouse, keyboard, touch panel, etc.) and display devices (CRT (Cathode Ray Tube), liquid crystal display, organic EL display, etc.). may

The communication IF 200A is an interface for communicating with another device (the user terminal 3 in this embodiment).

The storage device 200B is, for example, an HDD (Hard Disk Drive) or a semiconductor storage device (SSD (Solid State Drive)). Various data and information processing programs are stored in the storage device 200B. Some or all of the various data stored in the storage device 200B may be stored in an external storage device such as a USB (Universal Serial Bus) memory, an external HDD, or another information processing device connected via the network 4. may be stored on the device. In this case, the server 2 refers to or acquires various data stored in an external storage device or a storage device of another information processing device.

The CPU 200C controls the server 2 according to this embodiment, and includes a ROM and a RAM (not shown).

FIG. 3 is a functional block diagram of the server 2. As shown in FIG. As shown in FIG. 3, the server 2 has functions such as a receiving unit 201, a transmitting unit 202, a storage device control unit 203, a searching unit 204, an extracting unit 205, and the like. Note that the functions shown in FIG. 3 are implemented by the CPU 200C executing an information processing program stored in the storage device 200B.

The receiving unit 201 receives information from the user terminal 3 or an external database via the network 4 . The receiving unit 201 receives, for example, search conditions (for example, one or more words (search words), etc.) transmitted from the user terminal 3 . The receiving unit 201 also receives, for example, the user's evaluation of the search results transmitted by the transmitting unit 202 . Here, the receiving unit 201 receives the user's evaluation as an index of multiple stages. These multiple stages include relevance or non-relevance, e.g., Excellent, Good, Not Sure, Poor, Irrelevant. Receive a five-level evaluation (see Figure 7). In addition, in the embodiment, although the five-level evaluation is used, this is only an example, and the number is not limited to five.

The transmission unit 202 transmits information to the user terminal 3 via the network 4 . The transmission unit 202 transmits, for example, the search result of the search unit 204 to the user terminal 3 . The transmitting unit 202 also transmits, for example, the words extracted by the extracting unit 205 and the degree of association of the words to the user terminal 3 . As will be described later, when the extraction unit 205 extracts a sentence included in a document, the transmission unit 202 transmits the sentence extracted by the extraction unit 205 and the degree of relevance of the sentence to the user terminal 3 .

The storage device control unit 203 controls the storage device 200B. The storage device control unit 203, for example, writes and reads information to and from the storage device 200B.

The search unit 204 , for example, accesses an external database, and based on the search conditions received by the reception unit 201 , determines documents containing at least sentences related to issues (especially technical issues). Here, the search unit 204 determines the type of the document, and determines whether or not the document includes at least sentences related to the assignment depending on whether the determined document is of a predetermined type.
The search unit 204 analyzes the document by morphological analysis or the like, acquires information on items included in the document, and compares the acquired items with document type determination data to determine the type of the document. In this document type determination data, items of documents containing technical problems are stored for each type of document. For example, patent documents include items such as "patent application", "description", "claims", and "abstract". For technical documents, items such as "summary" and "text" are included. In this way, the document type determination data stores items of documents including technical problems for each type of document.

If the document type cannot be determined by collation with the document type determination data, the retrieval unit 204 searches for items included in the document obtained by analyzing the document, which of the documents included in the document type determination data. If the document does not match the type item, the search unit 204 determines that the document does not include a technical problem. On the other hand, if the retrieval unit 204 can match the document type determination data, that is, the item included in the document obtained by analyzing the document, the search unit 204 retrieves any of the document type items included in the document type determination data. , the search unit 204 determines that the document contains a technical problem. The method described above is merely an example, and other methods may be used as long as the search unit 204 can determine whether or not the document contains a technical problem. For example, the server 2 may be provided with a learning unit to learn a document containing a description of the assignment. Note that a known method can be used for learning by the learning unit.

The search unit 204 calculates the degree of relevance between the document determined to include at least a sentence related to the assignment and the search condition received by the reception unit 201 . The search unit 204, for example, evaluates documents according to the calculated degree of association, and extracts documents with an evaluation value equal to or higher than a certain value as search results.

Further, the search unit 204 searches for documents again based on the user's evaluation received by the reception unit 201, for example. The search unit 204 searches for documents again based on the received user evaluation each time the receiving unit 201 receives the user evaluation.
For example, if the evaluation is excellent (highly relevant), the retrieval unit 204 determines that the retrieved document describes information close to the information the user is looking for, and determines that the information related to it is described. Priority is given to extracting documents that are likely to be In this case, documents that are highly relevant to the retrieved documents are preferentially extracted.
For example, if the evaluation is Irrelevant (no relevance), the retrieval unit 204 determines that the retrieved document describes information far from the information desired by the user, and determines that the information related to it is described. Subordinately extract documents that are likely to be In this case, documents that are more likely to contain related information are not displayed higher in the search results, and documents that are less likely to contain related information are displayed to be higher in the search results.

For example, the extracting unit 205 calculates the degree of relevance between the words included in the document searched by the searching unit 204 and the search condition received by the receiving unit 201, and based on the calculated degree of relevance, the search unit 204 searches for Extract words contained in documents. An existing technique can be used for calculating the degree of association by the extraction unit 205 . Existing technologies, for example, evaluate "features obtained from documents", "features obtained from search keywords", "features given from pairs of documents and search keywords", etc. is calculated. Note that the extracting unit 205 calculates the degree of relevance between not only the words but also the sentences included in the document searched by the searching unit 204 and the search condition received by the receiving unit 201, and performs a search according to the calculated degree of relevance. The sentence included in the retrieved document may be extracted by the unit 204 .

(User terminal 3)
The user terminal 3 is a terminal used by the user of the search system 1 when searching for technical information. 4 and 5 are configuration diagrams of the user terminal 3. FIG. 4 shows the main hardware configuration of the user terminal 3. The user terminal 3 has a configuration in which a communication IF 300A, a storage device 300B, an input device 300C, a display device 300D, and a CPU 300E are connected via a bus. have.

The communication IF 300A is an interface for communicating with another device (the server 2 in this embodiment).

The storage device 300B is, for example, a HDD (Hard Disk Drive) or a semiconductor storage device (SSD (Solid State Drive)). The storage device 300B stores terminal identifiers, information processing programs, and the like. The terminal identifier is an identifier for identifying the user terminal 3 . By adding a terminal identifier to the information transmitted from the user terminal 3, the server 2 can determine from which user terminal 3 the received information is transmitted. The terminal identifier may be an IP (Internet Protocol) address, a MAC (Media Access Control) address, or the like, or may be assigned to the user terminal 3 by the server 2 .

The input device 300C is, for example, an input device such as a keyboard, mouse, or touch panel, but may be other devices or equipment as long as input is possible. Also, it may be a voice input device.

The display device 300D is, for example, a liquid crystal display, a plasma display, an organic EL display, or the like, but may be another device or device (eg, CRT: Cathode Ray Tube) as long as it can display.

The CPU 300E controls the user terminal 3 according to this embodiment, and includes ROM and RAM (not shown).

FIG. 5 is a functional block diagram of the user terminal 3. As shown in FIG. As shown in FIG. 5, the user terminal 3 has functions such as a receiving section 301, a transmitting section 302, a storage device control section 303, an input reception section 304, a display device control section 305, and the like. The functions shown in FIG. 5 are implemented by CPU 300E executing an information processing program stored in storage device 300B.

The receiving unit 301 receives information transmitted from the server 2, for example.

The transmission unit 302 transmits information corresponding to the input operation received by the input reception unit 304 to the server 2, for example.

The storage device control unit 303 controls the storage device 300B. For example, the storage device control unit 303 controls the storage device 300B to write and read information.

The input reception unit 304 receives an input operation from the input device 300C.

The display device control unit 305 controls the display device 300D, and displays the information received by the reception unit 301 on the display device 300D.

(Display screen)
6 and 7 are diagrams showing examples of search results displayed on the display device 300D of the user terminal 3. FIG. An example of search results displayed on the display device 300D of the user terminal 3 will be described below with reference to FIGS. 6 and 7. FIG. The same reference numerals are assigned to the same configurations as those described with reference to FIGS. 1 to 5, and overlapping descriptions are omitted. Further, as already described, the server 2 has a display device (CRT (Cathode Ray Tube), liquid crystal display, organic EL display, etc.), and the screens shown in FIGS. 6 and 7 can be displayed on the display device of the server 2. can be configured to

FIG. 6 is a diagram showing an example of a display screen G1 of documents found out of the search results. As shown in FIG. 6, the number of retrieved documents of 11 is presented on the display screen G1. Also, the user can display a desired document from the searched documents by operating the input device 300C of the user terminal 3 and selecting the tab 12 . Also, the box 13 presents the contents of the document selected by the tab 12 . Also, the user can evaluate the retrieved document by operating the input device 300C of the user terminal 3 and selecting the evaluation button 14 .

FIG. 7 is a diagram showing an example of the display screen G2 of the words extracted by the extraction unit 205 from the documents searched out of the search results and the degree of association of the words. As shown in FIG. 7, the extracted word 21 is presented together with the degree of association 22 on the display screen G2. Here, the degree of relevance 22 is presented in the form of a bar graph (black indicates degree of relevance (%)), but the presentation method is not limited to this. A numerical value (%) of the degree of association may simply be presented, or a pie chart or the like may be presented.

(information processing)
FIG. 8 is a flowchart showing an example of information processing of the search system 1. As shown in FIG. Information processing of the search system 1 will be described below with reference to FIG. The same components as those described with reference to FIGS. 1 to 7 are denoted by the same reference numerals, and overlapping descriptions are omitted. Further, as already described, the server 2 includes an input device (for example, a mouse, keyboard, touch panel, etc.) and a display device (CRT (Cathode Ray Tube), liquid crystal display, organic EL display, etc.). Information may be input from the device.

(Search process)
FIG. 8 is a flowchart showing an example of search processing of the search system 1. As shown in FIG. An example of search processing of the search system 1 will be described below with reference to FIG.

(Step S101)
The user operates the input device 300C of the user terminal 3 to input search conditions. A search condition input by operating the input device 300</b>C is received by the input reception unit 304 and transmitted from the transmission unit 302 to the server 2 via the network 4 . The search condition transmitted from the user terminal 3 is received by the receiving section 201 of the server 2 .

(Step S102)
The search unit 204 of the server 2 accesses an external database and searches for documents containing at least sentences related to the assignment based on the search conditions received by the reception unit 201 . Note that since the search by the search unit 204 has already been described, redundant description will be omitted.

(Step S103)
The extraction unit 205 extracts words included in the document searched by the search unit 204 according to the degree of relevance to the search condition received by the reception unit 201 . Since the method of calculating the degree of association by the extraction unit 205 has already been described, redundant description will be omitted. Further, as described above, the extracting unit 205 calculates the degree of relevance between not only words but also sentences included in the document searched by the searching unit 204 and the search condition received by the receiving unit 201, and calculates the calculated degree of relevance. , the sentence included in the document retrieved by the retrieval unit 204 may be extracted.

(Step S104)
The transmission unit 202 transmits search results to the user terminal 3 via the network 4 . The search results (including extracted words and word relevance information) transmitted by the transmission unit 202 are received by the reception unit 301 of the user terminal 3 and displayed on the display device 300D by the display device control unit 305. (See FIGS. 6 and 7).

(Step S105)
The user operates the input device 300C of the user terminal 3 to input an evaluation of the search result (as described above, the evaluation is represented by a multi-level index and includes the presence or absence of relevance). An evaluation input by operating the input device 300</b>C is received by the input reception unit 304 and transmitted from the transmission unit 302 to the server 2 via the network 4 . The evaluation transmitted from the user terminal 3 is received by the receiving section 201 of the server 2 .

(Step S106)
The search unit 204 of the server 2 searches for the document again based on the user's evaluation received by the reception unit 201 . After that, the server 2 shifts to the process of step S104. The re-searching of the document based on the user's evaluation by the searching unit 204 has already been described, so redundant description will be omitted. By repeating the processing of steps S104 to S106, the user can turn the search→evaluation loop and clarify the problem.

As described above, the server 2 according to the embodiment is a search support device. The server 2 includes a receiving unit 201 that receives search conditions, a searching unit 204 that searches for documents containing at least sentences related to assignments based on the search conditions received by the receiving unit 201, and a search result from the searching unit 204. and a transmitting unit 202 for transmitting.
Therefore, it is possible to assist the user in setting the assignment more clearly by referring to the assignment included in the document.

The search unit 204 of the server 2 according to the embodiment calculates the degree of relevance between the document and the search condition received by the receiving unit 201, and searches for documents that include at least sentences related to the assignment according to the degree of relevance.
For this reason, it is possible to exclude documents that contain sentences related to the task but are irrelevant.

The server 2 according to the embodiment includes an extraction unit 205 that extracts words included in the document searched by the search unit 204 according to the degree of relevance to the search condition received by the reception unit 201 . Also, the transmission unit 202 of the server 2 according to the embodiment transmits the word extracted by the extraction unit 205 .
Therefore, it is possible to assist the user in clarifying the problem by referring to the words (words serve as reference for search words).

The receiving unit 201 of the server 2 according to the embodiment receives the user's evaluation of the information transmitted by the transmitting unit 202 . Also, the search unit 204 of the server 2 according to the embodiment searches for documents based on the user's evaluation.
Therefore, the user can obtain the search result of the re-search in response to the evaluation of the search result, which enhances convenience.

The receiving unit 201 of the server 2 according to the embodiment further receives the user's evaluation of the information transmitted by the transmitting unit 202 . Further, the search unit 204 of the server 2 according to the embodiment further searches for documents based on the user's evaluation.
For this reason, the user can go through a search->evaluation loop, and can assist in clarifying the problem.

The receiving unit 201 of the server 2 according to the embodiment receives the user's evaluation using a multi-level index.
Therefore, the search unit 204 can evaluate the document in more detail according to the user's evaluation, and can be expected to reach the desired information more quickly.

Multiple stages according to embodiments include whether or not they are related. Here, if Irrelevant (irrelevant) is given as an evaluation for search results, the user can expect to reach documents that cannot be searched by NOT searches, such as technical literature related to other than specific diseases. When searching for technical literature other than a specific disease, the specific disease name is not searched as a search formula. can't get there. However, if Irrelevant (not relevant) is given as an evaluation for the search results, it is not a NOT search, so the documents related to the above-mentioned specific diseases are not excluded, and it is expected that technical documents related to other than the specific diseases will be found. can.

In addition, the above embodiments and modifications are merely examples of specific implementations of the present invention, and the technical scope of the present invention should not be construed in a limited manner. be. Thus, the invention may be embodied in various forms without departing from its spirit or essential characteristics.

1 Search system 2 Server (support device)
200A communication interface
200B storage device 200C CPU
201 Reception unit 202 Transmission unit 203 Storage device control unit 204 Retrieval unit 205 Extraction unit 3 User terminal 300A Communication IF
300B storage device 300C input device 300D display device 300E CPU
301 Reception unit 302 Transmission unit 303 Storage device control unit 304 Input reception unit 305 Display device control unit 4 Network

Claims (9)

A search support device,
a receiving unit that receives search conditions;
a search unit that searches for documents containing at least sentences related to the assignment based on the search conditions received by the reception unit;
a transmission unit that transmits search results from the search unit;
A support device comprising: The search unit is
calculating a degree of relevance between the document and the search condition received by the receiving unit, and retrieving a document containing at least sentences related to the task according to the degree of relevance;
2. The support device according to claim 1, characterized by: An extraction unit for extracting words included in the document searched by the search unit according to the degree of relevance to the search condition received by the reception unit,
The transmission unit
transmitting the word extracted by the extraction unit;
3. The support device according to claim 2, characterized by: The receiving unit
receiving a user's evaluation of the search results sent by the sending unit;
The search unit is
searching the document based on the user's ratings;
4. The support device according to any one of claims 1 to 3, characterized in that: The receiving unit
Further receiving a user's evaluation of the search results sent by the sending unit;
The search unit is
searching for more documents based on the user's ratings;
5. The support device according to claim 4, characterized by: The receiving unit
receiving the user's evaluation according to a multi-level index;
6. The support device according to claim 5, characterized by: The multiple steps include:
including whether or not they are relevant,
7. The support device according to claim 6, characterized by: A search assistance method comprising:
a receiving unit receiving a search condition;
a step in which a search unit searches for documents containing at least sentences related to the assignment based on the search conditions received by the reception unit;
a transmission unit transmitting a search result of the search unit;
A support method characterized by having A search support program,
the computer,
a receiver that receives search conditions;
a search unit that searches for documents containing at least sentences related to the assignment based on the search conditions received by the reception unit;
a transmission unit that transmits search results of the search unit;
A support program characterized by functioning as

Images