JP3625054B2 - Technical document retrieval device - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to a technical document search apparatus that searches technical documents such as patent documents and technical papers, and in particular, implements an apparatus that can perform an accurate search and display search results in an easy-to-understand manner. is there.
[0002]
[Prior art]
The number of patent documents and technical papers has reached an enormous amount even with existing publications alone, and it is certain that it will continue to increase in the future. In order to use these technical documents effectively, it is indispensable to have a search means that can accurately select a document in a target field.
[0003]
Conventionally known methods for searching for documents include keyword search and a method for searching for a document similar to a search query using a vector space method.
[0004]
FIG. 20 shows the configuration of a conventional document search apparatus. The apparatus includes an input / output unit 11 that inputs search conditions and outputs a search result, a document entity storage unit 14 that stores technical documents, an index storage unit 13 that stores technical document search indexes, Search means 12 for searching for technical documents using the search index is provided.
[0005]
The index storage unit 13 stores keywords, vector data, dictionaries, and the like extracted from each technical document as an index of each technical document stored in the document entity storage unit 14.
[0006]
When a search condition expression or a search question is input from the input / output means 11, the search means 12 uses the index stored in the index storage means 13, a document that matches the search condition expression, or a document similar to the search question. The search result is displayed through the input / output means 11. The document entity of the search result is read from the document entity storage unit 14 and displayed according to the selection operation from the input / output unit 11.
[0007]
Moreover, in order to show the searched patent document in an easy-to-understand manner, display using a patent map has been conventionally performed.
[0008]
FIG. 19 shows an example of a patent map. This example is a patent map for an inkjet printer for a personal computer, and describes the relationship of the components of this printer, the number and keyword of the related patent document for each component, the age of extraction of the patent document, the patent classification, etc. For patent documents, the applicant and a symbol indicating technical evaluation are displayed.
[0009]
An apparatus for supporting the creation of such a patent map is described in Japanese Patent Laid-Open No. 7-182356. In this apparatus, patent documents are automatically classified according to a predetermined keyword, patent classification, age, and the like.
[0010]
Japanese Patent Application Laid-Open No. 8-221435 describes a system for automatically updating patent documents displayed on a patent map. In this system, when the patent database is updated by sending a search key from the client terminal to the patent database server in advance, the patent data in the update range is searched with the search key, and the search result is sent to the client terminal. It is added to the patent map database of the terminal.
[0011]
Thus, the patent map on which the searched patent documents are displayed is widely used as a material for grasping technical trends and rights.
[0012]
In addition, it is also widely performed to display the document collection of searched patent documents in a graph by the number of cases by filing age and to show the application trends in the corresponding technical field. Japanese Patent Application Laid-Open No. Hei 7-182356 stores patent documents and technical information in a database together with data such as fields of use, elemental technologies, and issuance dates. A method of displaying in a technical information space with an axis and a time axis as coordinate axes is disclosed.
[0013]
[Problems to be solved by the invention]
However, when searching for technical documents using keywords, even if the documents are related, technical documents with completely new concepts or technical documents written using words other than those specified as keywords may be omitted from the search. May not be classified correctly.
[0014]
In addition, in technical terms, for example, “filter” has the meaning of a circuit component that limits the frequency range of a signal in the electrical field, and the meaning of a porous material that separates suspended particulate matter from a liquid in the mechanical field. In the optical field, the same term is often used in different meanings in the technical field to represent an optical component that limits the amount of light. Therefore, in the keyword search of technical documents, a search result may include a large amount of noise unless keywords are selected appropriately.
[0015]
An apparatus for organizing and displaying searched technical documents from various viewpoints is described in the above-mentioned Japanese Patent Application Laid-Open No. 7-182356, etc., but paying attention to the relationship between searched technical documents. No device for displaying the relationship between technical documents has been made so far.
[0016]
The present invention solves these conventional problems, and can search and classify technical documents efficiently and accurately, and clearly shows the relationship between retrieved technical documents. It is an object of the present invention to provide a technical document search apparatus capable of performing the above.
[0017]
[Means for Solving the Problems]
Therefore, in the present invention,Includes bibliographic itemsIn a technical document search device for searching for technical documents such as patent documents and technical papers,A search expression synthesis means for generating a search expression from bibliographic items of technical documents;Document similarity determination means for determining the similarity between technical documents is provided,The search formula synthesis means generates a search formula from bibliographic items of the original technical document, the search means executes a search using the search formula generated by the search formula synthesis means, and the document similarity The determining means determines the similarity of a part excluding bibliographic items between the technical document searched by the searching means and the original technical document, and the relationship between the searched technical document and the original technical document is determined by the similarity. It is displayed so that the degree can be visually recognized.
[0021]
Therefore, in this apparatus, it is possible to appropriately classify search results using the information of the technical map.
[0022]
Also listed on the technology mapTechniqueSearch results can be narrowed down based on the similarity to the technical document.
[0023]
It is also possible to display the relationship of technical documents that share the inventor and applicant included in the bibliographic items, or display the relationship of technical documents that are in a reference relationship.
[0024]
DETAILED DESCRIPTION OF THE INVENTION
(First embodiment)
In the first embodiment, a technical document search apparatus that uses information of a patent map, which has been conventionally used to display a search result of technical documents, to classify searched patent documents will be described.
[0025]
As shown in FIG. 1, this apparatus stores input / output means 11 for inputting search conditions and outputting search results, document entity storage means 14 for storing patent documents, and a search index for patent documents. The index storage means 13, the search means 12 for searching for patent documents using the search index, the analysis means 15 for analyzing the document vector of the patent documents, and a plurality of patent maps created so far are accumulated. A technical map group accumulating unit 17, a technical map storing unit 18 for storing a patent map read out from the technical map group accumulating unit 17, and a document similarity for determining a similarity between patent documents using a document vector Determination means 16.
[0026]
As shown in FIG. 2, each patent map stored in the technical map group accumulating means 17 has a tree-like data structure. In this example, a control unit, a computer interface, a printing unit, etc. of a personal computer inkjet printer. The search keyword and important patent list data are described for each of the components. When this patent map is displayed on the screen, it is displayed as shown in FIG. 19, for example.
[0027]
The user designates a patent map to be used by the input / output unit 11 when using the technical document retrieval apparatus. The designated patent map is read from the technical map group storage means 17 and stored in the map storage means 18.
[0028]
Next, a user inputs a favorite keyword and searches patent documents. The search means 12 searches for a document that matches the keyword using the index stored in the index storage means 13, and the search result is displayed through the input / output means 11. FIG. 3 shows a search result display screen when a patent document is searched using “color * high speed” as a keyword. Here, 2000 search results are obtained.
[0029]
Even if a large number of search results are obtained in this way, the search results are classified and displayed for each configuration diagram of the patent map as shown in FIG. 4 by pressing the “category display” button on the display screen. .
[0030]
When "classification display" is input from the input / output means 11, the degree of similarity between each patent document as a search result and the patent document described for each component of the patent map is calculated and searched. The resulting patent document is classified into the most similar component parts. The similarity is determined using a known technique such as a vector space method.
[0031]
This process is performed in the following procedure.
(1) The analysis means 15 calculates the document vector of each patent document described for each component of the patent map (this may be calculated in advance).
(2) The analyzing means 15 takes out one patent document as a search result and calculates a document vector of this patent document.
(3) The document similarity determination means 16 compares the document vector of the patent document of each component in the patent map with the document vector of the patent document of the search result, and finds the closest similarity at the closest place. Classify. (If it doesn't look like anything else, classify it as "Other". If it's too different from the whole document space, classify it as "Not relevant" and discard the search results.)
(4) The patent document of the next search result is taken out and the processing from (2) is repeated. If there is no patent document of the next search result, the process ends.
As described above, in this technical document search apparatus, searched patent documents can be classified and displayed using the information of the patent map.
[0032]
In this apparatus, when comparing the similarity between the patent document of the search result and the patent document described in the patent map, the document vector for the entire document is calculated and compared. It can also be configured to take out and compare.
[0033]
As shown in FIG. 5, the apparatus in this case is provided with a partial document extracting means 19 for extracting a part of the description part of the patent document. Other configurations are the same as the apparatus of FIG.
[0034]
When calculating the similarity, the partial document extracting unit 19 extracts a description portion of “conventional technology” from each of the patent documents of the search result and the patent documents of the patent map. The analysis unit 15 calculates the document vector of the “conventional technology”, and the document similarity determination unit 16 converts the document vector of the “conventional technology” in the patent document as the search result into the “patent document” in the patent map. Compared with the document vector of “Prior art”, classify it to the closest place.
[0035]
The patent document is very long, and the “embodiment” occupying the maximum amount of data may include various contents such as various examples and comparative examples. For this reason, when comparing the degree of similarity for the entire patent document, not only the processing load is large, but also the classification accuracy may decrease.
[0036]
In that regard, since the "conventional technology" emphasizes what has been the problem and what has been improved, it is necessary to create a document vector for this "conventional technology" and compare it with each other. Classification becomes possible.
[0037]
Similarly, the “document to be solved by the invention” of the patent document may be extracted by the partial document extracting means 19 and the document vectors of this portion may be compared and classified.
[0038]
In the case of a technical paper, a part referring to a past document is extracted as a center, a document vector is created only from this part, and comparison classification is performed. In the case of technical papers, unlike patent literature, it is difficult to extract a specific part because the format is free, but the area around the part that refers to past literature is the description part of the conventional technology. Therefore, it is possible to extract and classify the description part of the prior art by using the description part of the past document as a guide.
[0039]
As described above, in this technical document retrieval apparatus, it is possible to improve the classification accuracy with a small processing load.
[0040]
Further, as shown in FIG. 6, this technical document search apparatus is provided with display composition means 20 for synthesizing display data entangled with similarities, so that the patent documents of the search results can be displayed in a large size representing the similarity in the technical space. It can be displayed in terms of size.
[0041]
When the “multi-dimensional classification” button on the display screen shown in FIG. 3 showing the search result is pressed, this apparatus displays bibliographic items (such as applicants), time (such as the application date), and components as shown in FIG. A point representing the position of the patent document as a search result is displayed in a multidimensional space as an axis. At this time, the display synthesizing unit 20 displays the size of the point representing the patent document as the search result in correspondence with the size of the similarity calculated by the document similarity determining unit 16.
[0042]
When the user clicks the classified and displayed point with the mouse, the corresponding patent document is read from the document entity storage means 14 and the contents thereof are displayed. Further, when the “Add to patent map” button is clicked while the contents are displayed, the patent document is added to the patent map. Therefore, the user can select a patent document to be added to the patent map using the size of a point in the multidimensional space as a guide.
[0043]
As described above, this technology search apparatus has a function of supporting the creation of a patent map, and can easily update patent documents registered in the patent map.
[0044]
Here, although the case where the size of the display point of the patent document is differentiated according to the similarity is described, the color or shape of the point may be differentiated according to the similarity.
[0045]
(Second Embodiment)
In the second embodiment, a technical document search apparatus that uses information on a patent map, which has been conventionally used to display search results of technical documents, to narrow down the number of searches for patent documents will be described.
[0046]
As shown in FIG. 8, this apparatus includes search formula combining means 21 that combines a search formula obtained by adding a keyword of a patent map to a search formula set by a user. Other configurations are the same as those in FIG. 6 of the first embodiment.
[0047]
The technology map group storage means 17 of this apparatus stores a patent map created in advance. The user designates a patent map to be used from now on when using this technical document retrieval apparatus. The designated patent map is read from the technical map group storage unit 17 and stored in the technical map storage unit 18.
[0048]
Next, the user inputs a favorite keyword from the input / output means 11 and searches for patent documents. When a keyword is input from the input / output unit 11, the search formula combining unit 21 adds a basic keyword or bibliographic item (IPC classification or the like) specified in the patent map to the search formula in addition to the keyword specified by the user. Are automatically assembled, and the search means 12 performs a search using this search formula. The document similarity determination means 16 determines the similarity between the patent document of the search result and the patent document described in the patent map, except for those having very low similarity (this determination does not narrow the similarity so much) Display search results).
[0049]
For example, it is assumed that a user wants to search for a patent related to “FAX server device”. With conventional search devices
"(FAX + facsimile + fax) * control * image * communication * compression"
And so on, patents for NC control devices (machine tool numerical control devices) will be searched in addition to the target FAX server related patents. In addition to narrowing down by IPC classification, the user has to specify words such as NC with the NOT operator and narrow down little by little, which requires know-how for each patent field.
[0050]
In this technical document search apparatus, if a user has a patent map related to the FAX server apparatus in advance, the patent of the FAX server apparatus can be searched simply by specifying the patent map.
[0051]
In addition, when only the keyword “color” is specified, a normal search device searches for everything from color television to color film, and the number reaches a huge amount. In the case of this technical document search device, Can search only patent documents of FAX server devices related to color FAX.
[0052]
As described above, this technical document search apparatus can efficiently and accurately search technical documents by synthesizing search conditions using a patent map.
[0053]
(Third embodiment)
In the third embodiment, a technical document search apparatus that searches patent documents having commonality in bibliographic items and displays the relationship between them will be described.
[0054]
As shown in FIG. 9, this apparatus includes a bibliographic item extracting unit 22 for extracting bibliographic items of patent documents, a search formula synthesizing unit 21 for synthesizing a search formula from bibliographic items, and a relationship between searched patent documents. And a document relation storage means 23 for storing. Other configurations are the same as those in FIG. 1 of the first embodiment.
[0055]
The user inputs some keyword from the input / output means 11 and searches for patent documents. As a result, it is assumed that a certain number of patent documents are retrieved as shown in the screen example of FIG. Assume that one of them corresponds to the patent document you were looking for. Therefore, the user tries to see a patent document similar to this patent document (referred to as the original patent document). The subsequent procedure is shown in the flowchart of FIG.
[0056]
Step 1: As shown in FIG. 12, the user selects a document on the screen and presses a “similar bibliography search” button. Then, the bibliographic item extraction means 22 of this technical document search apparatus extracts the inventor and the applicant from the selected original patent document. It is assumed that the name of “applicant A” is extracted as the applicant, and three names of “inventor 1”, “inventor 2”, and “inventor 3” are extracted as inventors.
[0057]
Step 2: The retrieval formula combining means 21
Applicant A * Inventor 1 + Applicant A * Inventor 2 + Applicant A * Inventor 3
Assemble the search expression.
Step 3: The search means 12 performs a search using this search formula. As a result, 50 search results are obtained.
Step 4: The document similarity determination means 16 calculates the similarity with the original patent document for all 50 obtained cases. If the degree of similarity is greater than or equal to a predetermined threshold value, that is, if it is similar to a certain extent, it is left as a result, but other (not similar) search results are discarded.
Step 5: The remaining search results are stored in the document relation storage unit 23, and output and displayed by sorting in time order (application order), similarity order, or time order.
[0058]
In this way, as shown in FIG. 13, the similarity between the patent documents shared by the applicant and the inventor can be displayed on the time axis.
[0059]
In this way, this device extracts only a part of bibliographic items from the original document, synthesizes a search formula from the extracted bibliographic items, performs a search using this search formula, and obtains similar results from the obtained search results. By searching for and displaying only similar items in alignment, it is possible to display the relationship between patent documents having common bibliographic items.
[0060]
(Fourth embodiment)
In the fourth embodiment, a technical document search device that searches patent documents in a reference relationship and displays the relationship between them will be described.
[0061]
As shown in FIG. 14, this apparatus includes a related document extracting unit 24 that extracts a document referred to in a patent document, a document relationship storage unit 23 that stores a relationship between searched patent documents, and a reference. Display synthesizing means 20 for displaying related patent documents in association with each other. Other configurations are the same as those in FIG. 1 of the first embodiment.
[0062]
The user inputs some keyword from the input / output means 11 and searches for patent documents. As a result, as shown in the screen example of FIG. 11, it is assumed that a certain number of patent documents are searched, and one of them corresponds to the searched patent document. Therefore, the user tries to see a patent document similar to this patent document (referred to as a seed patent document). The subsequent procedure is shown in the flowchart of FIG.
[0063]
Step 11: The user selects a seed patent document on the screen and presses a “reference document search” button.
Step 13: The related document extraction unit 24 of the technical document search apparatus extracts (a plurality of) reference document names cited in the seed patent document from the seed patent document. This is called a parent patent document.
Step 14: The document relationship storage means 23 stores the relationship between the seed patent document and the parent patent document.
Step 15: The parent patent document is acquired from the document entity storage means 14,
Step 16: The parent patent document is used as a seed, and Steps 13 to 16 are repeated until N generations (N can be specified) are traced back from the first seed patent document.
[0064]
Step 17: Set the first seed patent document as the seed patent document again,
Step 19: Search for a patent document referring to this kind of patent document by searching the full text of the patent document stored in the document entity storage unit 14.
Step 20: The document relationship storage means 23 stores the relationship between the retrieved result (child patent document) and the seed patent document.
Step 21: Use this as a seed for all the child patent documents, and repeat Steps 19 to 21 until after M generations (M can be specified).
Step 22: The display composition unit 20 displays the relationship between the documents stored in the document relationship storage unit 23 in Step 14 and Step 20.
16 and 17 show an example of the screen displayed in this way.
[0065]
Note that the extraction of the document name referred to in the literature is formally described as “Japanese Patent Publication No. 11-12345” in the case of patent literature, so that the computer can easily recognize it. Also, in the case of papers, references are at the end of the sentence,
[8] Yaizuki Iizuka, Word segmentation by connection establishment minimum method, 200-NL-139, pp11, 2000
For example, the computer can be easily recognized from this description part.
[0066]
In addition, when searching for a child patent document (child), if a full-text search is performed on the database based on the patent publication number of the seed patent document (own), the child patent document (child) that refers to the seed patent document (self) ) Is possible.
[0067]
Also, if you want to search for documents that correspond to the sibling's child (甥), how far to go back to the parent (N generation or X years ago), how far to go to the child (M generation or all up to now), etc. To be able to choose.
[0068]
In addition, a document referred to by more documents (a document with many children) may be highlighted with a particular color when displayed. This shows that the fact that there are many children is more important, so that it can be clearly shown.
[0069]
In FIG. 16 and FIG. 17, only the patent publication number is displayed for the sake of explanation. However, in addition to the publication number, the display of the name, the applicant, etc. can be selected, or as shown in FIG. The bibliographic items and summary contents may be displayed in a pop-up only when the mouse pointer is placed at the position of the public number in the figure.
[0070]
It is also possible to browse the patent document immediately by double-clicking the patent publication number box in FIGS. Also, if there is a part in which the reference patent (parent patent) number is written in the patent document being browsed, only that part is highlighted (or colored), and when it is clicked, the reference patent (parent patent) is displayed. You may comprise as follows.
The similarity between related patent documents may be determined by the document similarity determination means, and the similarity may be displayed so as to be visually understood.
[0071]
As described above, this technical document retrieval apparatus can retrieve a reference relationship between documents and display the relationship between the documents on the screen. By browsing this screen, it is possible to easily grasp the technical system and the technical trend.
[0072]
In the embodiment, the description has been made centering on the search of patent documents, but the technical document search apparatus of the present invention can also target a technical paper or the like.
[0073]
【The invention's effect】
As is clear from the above description, the technical document search apparatus of the present invention uses the technical map such as a patent map for the search, so that the user can easily obtain the desired search result without making a difficult specification. be able to.
[0074]
Further, based on the search result, the technical document to be registered in the technical map can be accurately and easily identified, and the technical map data can be accurately updated. As a result, the technical trend can be grasped more easily and accurately.
[0075]
In addition, since the technical document search apparatus of the present invention can search and display the connection between documents, the user can easily grasp the technical system and the technical trend, and can also search the related document from this connection. Therefore, it is possible to reduce retrieval omissions and perform document retrieval more easily and accurately.
[Brief description of the drawings]
FIG. 1 is a block diagram showing a configuration of a technical document search apparatus according to a first embodiment;
FIG. 2 is a diagram showing a data structure of a patent map;
FIG. 3 is a diagram showing a search result screen of the technical document search device according to the first embodiment;
FIG. 4 is a view showing a patent map classification display screen of the technical document search apparatus according to the first embodiment;
FIG. 5 is a block diagram showing another configuration of the technical document search apparatus according to the first embodiment;
FIG. 6 is a block diagram showing another configuration of the technical document search apparatus according to the first embodiment;
FIG. 7 is a diagram showing a three-dimensional classification display screen of the technical document search device according to the first embodiment;
FIG. 8 is a block diagram showing a configuration of a technical document search apparatus according to the second embodiment;
FIG. 9 is a block diagram showing a configuration of a technical document search apparatus according to a third embodiment;
FIG. 10 is a flowchart showing an operation procedure of the technical document search apparatus according to the third embodiment;
FIG. 11 is a view showing a search result screen of the technical document search apparatus according to the third embodiment;
FIG. 12 is a view showing a similar bibliographic search selection screen of the technical document search apparatus according to the third embodiment;
FIG. 13 is a diagram showing a display screen of the technical document search device according to the third embodiment;
FIG. 14 is a block diagram showing a configuration of a technical document search apparatus according to the fourth embodiment;
FIG. 15 is a flowchart showing an operation procedure of the technical document search apparatus according to the fourth embodiment;
FIG. 16 is a diagram showing a connection between documents displayed by the technical document search apparatus according to the fourth embodiment;
FIG. 17 is a diagram showing a three-dimensional classification display screen in the technical document search device of the fourth embodiment;
FIG. 18 is a diagram showing a pop-up display in the technical document search device according to the fourth embodiment;
FIG. 19 is a diagram showing a patent map;
FIG. 20 is a block diagram showing a configuration of a conventional technical document search apparatus.
[Explanation of symbols]
11 Input / output means
12 Search means
13 Index storage means
14 Document entity storage means
15 Analytical means
16 Document similarity determination means
17 Technical map group storage means
18 Technical map storage means
19 Partial document extraction means
20 Display composition means
21 Search formula synthesis means
22 Bibliographic item extraction means
23 Document relation storage means
24 Related Document Extraction Means

Claims (5)

In a technical document search device for searching technical documents such as patent documents and technical papers including bibliographic items
Search means;
A search expression synthesis means for generating a search expression from bibliographic items of technical documents;
Document similarity determination means for determining similarity between technical documents, wherein the search expression synthesis means generates a search expression from bibliographic items of the original technical document, and the search means includes the search expression synthesis means The document similarity determination unit determines a similarity of a part excluding bibliographic items between the technical document searched by the search unit and the original technical document, A technical document search apparatus for displaying a relationship between the searched technical document and the original technical document so that the similarity is visually understood. 2. The technical document search apparatus according to claim 1, wherein a technical document whose similarity determined by the document similarity determination unit is equal to or less than a predetermined value is excluded from a search result. A partial document extracting unit for extracting a part of the technical document, wherein the document similarity determination unit uses a part extracted from the searched technical document and the original technical document by the partial document extracting unit; The technical document search device according to claim 1, wherein the similarity is determined. 4. The technical document search apparatus according to claim 3, wherein the partial document extracting unit extracts a part of “conventional technology” or “problem to be solved by the invention” from patent documents. 2. The technical document search apparatus according to claim 1, wherein the search formula synthesizing unit generates the search formula using information of an applicant and an inventor included in a bibliographic item of the original technical document.

Images