JP2018169753A - Document sorting apparatus, document sorting method and document sorting program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a document sorting apparatus for sorting documents with a small processing load.SOLUTION: The document sorting apparatus includes: a storage unit for storing first document information indicating a plurality of document data retrieved according to a retrieval formula, first feature information indicating one or more technical features of document data given to the document data, and relevant information indicating whether or not the document data is a document desired by the user in association with each other; an acquisition unit for acquiring second document information that is newly retrieved in accordance with the retrieval formula and that indicates other document data to which second feature information indicating one or more technical features is given; an extraction unit for extracting a predetermined number of document data from the plurality of document data on the basis of a consistency degree between the second feature information and the first feature information; a determination unit for determining whether or not the other document data is a document desired by the user on the basis of the relevant information associated with each of the predetermined number of document data extracted by the extraction unit; and an output unit for outputting a determination result of the determination unit.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a document classification apparatus, a document classification method, and a document classification program for classifying documents.

  In recent years, engineers often read various patent documents according to their own purposes every year in order to keep up with the latest technological trends. In reading the patent document, the engineer narrows down the search formula, but the number of documents obtained as a result remains enormous, and it is not realistic to read all the documents. Therefore, the user may perform screening, that is, screening, of documents that should be read from a huge amount of documents, and documents that should not be read.

  There are various techniques for assisting such screening. For example, a seed document representing the content to be searched is added to the document set obtained as a search result of the search by patent classification, and clustering based on the similarity of the document content is performed, and the patent documents displayed in a cluster are sequentially screened. The technique to do is disclosed (for example, refer patent document 1). For calculating the similarity, clustering is performed by performing morphological analysis on the document, decomposing it into terms, and calculating the similarity between the terms.

  Moreover, in order to perform screening after literature search efficiently, a method of automatically turning the content indicating each document in document units is disclosed (for example, see Patent Document 2).

  Further, the degree of similarity between the document to be classified and the document set to which the classification is assigned is calculated based on the keyword in the document, and a specified number of documents most similar to the input document are extracted, and the degree of similarity is calculated. Calculate the classification score of the specified number of documents extracted based on the number of classifications taken into account, extract the classification whose calculated score is greater than the specified value, and assign it to the target document for classification automatically There is also a technique to perform (see, for example, Patent Document 3).

JP 2003-157270 A JP 2004-234430 A JP 2007-323454 A

  By the way, in the case of the above-mentioned Patent Document 2, although the document is automatically turned, the number of documents to be read by the user is not reduced, and the fact that the person performs the screening itself does not change. There is a problem that is large.

  In the case of Patent Document 1 and Patent Document 3 described above, a method is used in which similarity is calculated for each extracted term after performing morphological analysis on each document. There is a problem that a huge processing load is applied to the processor, such as calculating the similarity of the terms.

  Accordingly, the present invention has been made in view of the above problems, and an object thereof is to provide a document classification device, a document classification method, and a document classification program that require less processing load on humans and processors than in Patent Documents 1 to 3. And

  In order to solve the above problems, a document classification device according to an aspect of the present invention includes first document information indicating a plurality of document data searched according to a search formula, and the document data assigned to the document data. A storage unit that stores first feature information indicating one or more technical features and corresponding information indicating whether or not the document data is a document desired by the user, and a new one according to the search formula The second feature information and the first feature information coincide with each other, an acquisition unit for acquiring second document information indicating other document data to which the second feature information indicating one or more technical features is added. Based on the degree, the extraction unit that extracts a predetermined number of document data from the plurality of document data, and other document data based on the corresponding information associated with each of the predetermined number of document data extracted by the extraction unit, Whether the document is desired by the user Comprising a determining section for determining, and an output unit for outputting a determination result of the determination unit.

  Further, the document classification method according to one aspect of the present invention includes one or more technical information of first document information indicating a plurality of document data searched according to a search formula and the document data attached to the document data. A storage step for storing first feature information indicating a feature and corresponding information indicating whether or not the document data is a document desired for the user, and a new search according to the search formula. Based on the acquisition step of acquiring second document information indicating other document data to which the second feature information indicating the above technical features is given, and the degree of coincidence between the second feature information and the first feature information, An extraction step for extracting a predetermined number of document data from the document data, and other document data based on the corresponding information associated with each of the predetermined number of document data extracted in the extraction step. Comprising a determining step of determining whether, and an output step of outputting the result of determination at decision step.

  Further, the document classification program according to one aspect of the present invention provides a computer with one or more of first document information indicating a plurality of document data searched according to a search expression and the document data attached to the document data. Is stored in association with the first feature information indicating the technical features of the document and the corresponding information indicating whether or not the document data is a document desired by the user, and is newly searched according to the search formula. Based on an acquisition function for acquiring second document information indicating other document data to which second feature information indicating one or more technical features is given, and a degree of coincidence between the second feature information and the first feature information Based on the extraction function for extracting a predetermined number of document data from a plurality of document data and the corresponding information associated with each of the predetermined number of document data extracted by the extraction function, other document data is desired by the user. Literature A determining function of determining whether, to achieve an output function of outputting a determination result of the determination function.

  In the document classification device, the extraction unit extracts a predetermined number from a plurality of pieces of document data having a high degree of coincidence between the second feature information and the first feature information, and the determination unit is extracted by the extraction unit. If the corresponding information associated with the document is more than the threshold value indicating that the document is the document desired for the user, it is determined that the other document data is the document desired for the user, If there are more items indicating that the document is not a document than the threshold value, it may be determined that the other document data is not a document desired by the user.

  In the document classification apparatus, the determination unit weights the corresponding information associated with the document extracted by the extraction unit according to the degree of coincidence, and based on the corresponding information after the weighting is performed. Further, it may be determined whether the other document data is a document desired for the user.

  Further, in the document classification device, the determination unit is the document data associated with the first feature information, and the first feature of the document data indicating that the corresponding information is a document not desired by the user. Non-correspondence ratio indicating the ratio to the entire document data with which the information is associated is a document that the user does not desire other document data having the second feature information that matches the first feature information that exceeds the first threshold. It may be determined that there is.

  Further, in the document classification device, the determination unit is document data associated with the first feature information, and the first feature of the document data indicating that the corresponding information is a document desired by the user. This is a document in which the user desires other document data having second feature information that matches the first feature information whose ratio indicating the ratio to the entire document data with which the information is associated exceeds the second threshold. It is good also as judging.

  In the document classification apparatus, the first threshold value may be larger than the second threshold value.

  In the document classification device, when the feature information is used in the search formula, the determination unit makes a determination based on the first feature information excluding the feature information and the second feature information. It is good as well.

  In the document classification device according to an aspect of the present invention, whether or not the newly searched other document data is a document desired by the user is given to a document previously searched by the same search formula. Determination can be made based on the degree of coincidence of feature information indicating technical information and corresponding information indicating whether the document is a document desired by the user. Therefore, since the document classification device can perform screening of documents that the user does not need to read, the number of documents that the user should read can be reduced. Therefore, the processing load on the user can be reduced. In addition, since the document classification apparatus can perform screening of documents without examining the documents, the processing load on the document classification apparatus can be reduced.

It is a block diagram which shows the structural example of a document classification device. It is a block diagram which shows the detailed structural example of a document classification device. (A) is a data conceptual diagram which shows an example of the past list | wrist which shows the classified list | wrist. (B) is a data conceptual diagram which shows an example of the new literature list | wrist which shows the list | wrist of a new literature. It is a data conceptual diagram which shows an example of the coincidence degree table which sorted the past literature by the coincidence with a new literature. It is a data conceptual diagram which shows an example of the IPC applicable information which shows whether it is noise for every classification. It is an operation of the document classification device, and is a flowchart showing processing related to advance preparation. It is a flowchart which shows the process following FIG. It is operation | movement of a document classification | category apparatus, Comprising: It is a flowchart which shows the process at the time of classifying a new document. It is a flowchart which shows the process following FIG. 10 is a flowchart illustrating processing subsequent to FIG. 9. It is a block diagram which shows the structural example of a document classification device.

  Hereinafter, a document classification apparatus according to an embodiment of the present invention will be described in detail with reference to the drawings.

<Embodiment>
<Configuration>
FIG. 1 is a block diagram illustrating a configuration example of a document classification apparatus. As illustrated in FIG. 1, a storage unit 130, an acquisition unit 110, an extraction unit 121, a determination unit 122, and an output unit 140 are provided.

  The storage unit 130 includes first document information indicating a plurality of document data searched according to a search formula, first feature information indicating one or more technical features of the document data attached to the document data, Corresponding information indicating whether or not the document data is a document desired by the user is stored in association with each other. The storage unit 130 can be realized by, for example, an HDD (Hard Disc Drive), an SSD (Solid State Drive), a flash memory, or the like, but is not limited thereto. Here, the first document information may be data indicating the document itself of the first document information or identification information indicating the first document information. Here, the first feature information indicates technical features of each document data, and examples thereof include, but are not limited to, IPC, CPC, ECLA, ICO, USC, FI, and F terms. It is not a thing. In addition, the relevant information may be information indicating whether each of the documents obtained as a result of the search by viewing the documents obtained by the search by the user who performed the search is a document desired for the user. For example, information such as “applicable” or “noise”, or information indicating contents such as “neither” or “unknown” may be used. Note that the corresponding information may be provided by the document classification device. As described above, each first document information is associated with at least one technical feature as the first feature information indicating the technical feature.

  The obtaining unit 110 obtains second document information indicating another document data that is newly searched according to the search formula and is given second feature information indicating one or more technical features. For example, the acquisition unit 121 may acquire the second document information by wired or wireless communication, or may acquire other document data stored in the storage unit 130 in advance. Then, another storage medium that stores other document data may be connected to the document classification device to acquire other document data from the other storage medium. The other storage medium is a portable storage medium such as a flash memory. The second document information may be data indicating the document itself of the second document information or identification information indicating the second document information. The second feature information indicates technical features of other document data, and examples thereof include, but are not limited to, IPC, CPC, ECLA, ICO, USC, FI, and F terms. It is not a thing. Here, the other document data acquired by the acquisition unit 110 may be one or plural.

  The extraction unit 121 extracts a predetermined number of document data from a plurality of document data based on the degree of coincidence between the second feature information and the first feature information. The extraction unit 121 can be realized by a processor that executes an extraction program stored in the storage unit 130, for example. For example, the extraction unit 121 may extract document data having a high degree of coincidence between the second feature information and the first feature information from a plurality of document data, or extract document data having a certain degree of coincidence. It is good to do.

  The determination unit 122 determines whether the other document data is a document desired for the user based on the corresponding information associated with each of the predetermined number of document data extracted by the extraction unit 121. The determination unit 122 can be realized by, for example, a processor that executes a determination program stored in the storage unit 130. For example, the determination unit 122 may determine that other document data also corresponds to the document desired by the user when there are many pieces of corresponding information associated with the document data extracted by the extraction unit 121. it can. The condition “whether the document is desired for the user” is a condition such as “whether it is a document that matches a predetermined viewpoint” or “a document that meets a predetermined condition”. Also good.

  The output unit 140 outputs the determination result of the determination unit 122. The output unit 140 only needs to be able to output the determination result of the determination unit 122 to the outside. For example, the document classification device 100 includes a monitor and a speaker as an output device, and outputs the determination result as image information to those monitors. The determination result may be output as audio information. Further, the output unit 140 may be configured to output by transmitting information indicating a determination result to an external apparatus by wireless or wired connection with an external apparatus connected to the document classification apparatus 100, for example.

  Hereinafter, the document classification device 100 will be described in more detail.

  FIG. 2 is a block diagram illustrating a detailed configuration example of the document classification device 100. As illustrated in FIG. 2, the document classification device 100 includes an acquisition unit 110, a control unit 120, a storage unit 130, and an output unit 140. The document classification apparatus 100 is a computer system having a function of determining whether new document data is noise corresponding to a document desired by a user when new document data is input.

  The acquisition unit 110 has a function of acquiring information indicating a patent document as other new document data to be classified by the document classification device 100. The information indicating the patent document may be information indicating the patent document, and may be identification information indicating the patent document or the document itself. The information indicating the patent document is given information indicating the patent classification as the second feature information indicating the technical information of the patent document. For example, the acquisition unit 110 is a communication interface that acquires other unclassified document data from an external device (not shown).

  The control unit 120 is a processor having a function of controlling each unit of the document classification device 100 by executing various programs stored in the storage unit 130. The control unit 120 functions as an extraction unit 121 and a determination unit 122. The control unit 120 determines whether the IPC assigned to each document is “noise” in order to determine whether or not the document retrieved according to the retrieval formula is a document desired for the user. It has a function of generating IPC pertinent information for determining whether to do as prior information. Further, the control unit 120 determines whether or not the patent document to which the noise or the corresponding classification newly retrieved by the retrieval formula is not assigned by the functions of the extraction unit 121 and the determination unit 122 is the document desired by the user. It also has a function to determine whether or not.

  The extraction unit 121 extracts a document used to determine whether or not a new document is noise from a past document list that is a past classified document list. The extraction unit 121 extracts a predetermined number of documents from the top of the past document list sorted in descending order of the degree of coincidence of IPC with new documents.

  The determination unit 122 determines whether or not the new document is a document desired by the user based on the classification (“noise” or “corresponding”) as the corresponding information given to the document extracted by the extraction unit 121. That is, whether it is “noise” or “corresponding”. The determination unit 122 sets a classification that occupies a majority of the documents extracted by the extraction unit 121 as a new document classification.

  Details of the process for determining whether the new document by the control unit 120 is a document desired by the user and the process for generating the IPC pertinent information will be described later.

  The storage unit 130 is a recording medium having a function of storing various data and programs necessary for the operation of the document classification device 100. The storage unit 130 is realized by, for example, an HDD, an SSD, a flash memory, or the like, but is not limited thereto. The storage unit 130 corresponds to, for example, a program for the control unit 120 to generate prior information as to whether each IPC is noise, or whether the new document is noise when a new document is input. A program for the control unit 120 to determine whether or not is stored. The storage unit 130 is a list of past patent documents, and the acquisition unit 110 includes a past document list 300 in which corresponding information indicating whether each document corresponds to a user's desired document is associated with the past document list 300. A new document list 350 that is a list of new documents to be acquired and an IPC corresponding information 500 that is prior information generated by the control unit 120 are stored. In addition, a coincidence degree table 400 generated when determining whether the new document is noise or not is also stored.

  The output unit 140 is a communication interface having a function of outputting information related to the determination result of the new document from the control unit 120 to an external device. Here, for example, a new document list to which a classification is assigned is output in a mode as illustrated in FIG. 3A (a mode in which at least a publication number and a classification of a new document are associated with each other).

  The above is the description of the configuration of the document classification device 100.

<Data>
From here, various data used in the document classification device 100 will be described.

  FIG. 3A is a data conceptual diagram illustrating a configuration example of the past document list 300 regarding classified document data stored in the storage unit 130. The past document list 300 includes information regarding documents that have been searched with a predetermined search formula in the past, and includes information indicating whether each document is a document desired for the user. As shown in FIG. 3A, the past document list 300 is searched for the publication number 301 as the first document information indicating a plurality of document data searched according to the search formula and the patent document as the corresponding document data. As a result, a classification 302 that is information corresponding to the corresponding information indicating whether or not the content desired by the user is described, and a first that indicates one or more technical features assigned to each document data This is information associated with the IPC classification 303 corresponding to the feature information.

  The publication number 301 is document data searched according to the search formula, and is information for uniquely identifying a patent document that is classified document data. Here, the publication number of the patent document to be classified is used. However, this is not limited to the publication number, and any other identification number can be used as long as the identification information can uniquely identify the document. Also good.

  The classification 302 is information that should be called relevant information indicating whether or not the corresponding patent document is a document desired for the user. Here, when the corresponding patent document is a document desired for the user, If it is not “relevant” and is not a desired document, it is indicated by a binary value of “noise”.

  The IPC classification 303 is information indicating the IPC assigned to the corresponding patent document. The IPC classification 303 is information indicating one or more technical features of the corresponding patent document, and is information indicating a classification based on the technical content of the patent document that is used internationally.

  FIG. 3B is a data conceptual diagram showing a configuration example of a new document list 350 showing an example of new document data acquired by the acquisition unit 110 of the document classification device 100. Each patent document described in the new document list 350 is a list of new document data to be classified. The new document list 350 corresponds to a publication number 351 corresponding to information indicating other document data newly searched by a search and an IPC classification 352 corresponding to second feature information indicating one or more technical features. It is the attached information.

  The publication number 351 is information for uniquely identifying document data. Here, the publication number of the patent document to be classified is used. However, this is not limited to the publication number, and any other identification number can be used as long as the identification information can uniquely identify the document. Also good.

  The IPC classification 352 is information indicating the IPC assigned to the corresponding patent document. The IPC classification 352 is information indicating one or more technical features of the corresponding patent document, and is information indicating a classification based on the technical content of the patent document that is used internationally.

  FIG. 4 shows a state in which one document included in the new document list 300 is associated with the matching degree of the technical classification between each document included in the past document list 350 and sorted in descending order from the highest matching degree. 5 is a data conceptual diagram showing a configuration example of a coincidence degree table 400. FIG. The coincidence degree table 400 is information generated in the process in which the document classification apparatus 100 determines whether the new document data is “noise” or “corresponding”.

  The publication number 401 is information for uniquely identifying a patent document that is classified document data. Here, the publication number of the patent document to be classified is used. However, this is not limited to the publication number, and if it is identification information that can uniquely identify the document, other than the publication number is used. Also good.

  The classification 402 is information that should be called relevant information indicating whether or not the corresponding patent document is a document desired for the user. Here, when the corresponding patent document is a document desired for the user, If it is not “relevant” and is not a desired document, it is indicated by a binary value of “noise”.

  The IPC classification 403 is information indicating the IPC assigned to the corresponding patent document. The IPC classification 403 is information indicating one or more technical features of the corresponding patent document, and is information indicating a classification based on the technical content of the patent document that is used internationally.

  The degree of coincidence 404 indicates that, for one new document included in the new document list 350, the IPC class 352 assigned to the new document, and the IPC class 303 associated with each document included in the past document list 300, This is information indicating the degree of coincidence.

  The degree of coincidence table 400 is generated for each document included in the new document list 350. Then, the determination unit 122 determines whether each document is a document desired by the user or not by using the corresponding matching degree table 400.

  FIG. 5 is a data conceptual diagram showing a configuration example of IPC corresponding information 500 indicating the probability of becoming noise or corresponding for each IPC classification. As shown in FIG. 5, the IPC applicable information 500 is information in which an IPC classification 501, a publication number 502, a noise number 503, a noise rate 504, and a noise determination 505 are associated with each other.

  The IPC classification 501 is information indicating technical characteristics of patent documents, and is information indicating classification according to technical contents of patent documents that are used internationally. The IPC classification 501 is obtained by extracting IPCs assigned to past documents included in the past document list 300.

  The number of publications 502 is information indicating the total number of documents to which the corresponding IPC classification 501 is assigned in the past document list 300.

  The number of noises 503 is information indicating the total number of documents that the user has determined to be “noise” among the past documents to which the corresponding IPC classification 501 is assigned.

  The noise rate 504 is information that suggests a probability that the document is not a desired document when the corresponding IPC classification 501 is given to the document data. The noise number 503 is the corresponding number of publications 502. The divided value is shown.

  The noise determination 505 is a value for determining whether or not noise occurs when the corresponding IPC classification 501 is assigned. If the noise determination is “100”, the document classification apparatus 100 can determine that the document is “noise”, that is, a document that is not desired by the user. Further, the document classification device 100 can determine that the document is “corresponding”, that is, a document desired for the user if the noise determination is “0”. In the present embodiment, the IPC classification in which the noise ratio 504 is 95 or more has a noise determination 505 of 100, and the IPC classification in which the noise ratio 504 is 10 or less has a noise determination 505 of 0. Here, the threshold values 95 and 10 are values determined by the document classification apparatus 100, and the settings may be changed as appropriate. When changing the setting, the setting can be changed by using an input device connected to the document classification device 100.

  The IPC corresponding information 500 can be used by the document classification apparatus 100 to identify a document that can be a noise or a corresponding with high probability for a specific IPC classification. That is, for example, the document classification apparatus 100 can specify a document to which an IPC classification having a noise determination of 100 is given as a document that is not desired by the user. Conversely, a document to which an IPC classification with a noise determination of 0 can be specified as a document desired for the user. Each value shown in FIG. 5 is an example.

<Operation>
From here, the operation | movement which concerns on calculation of the distortion amount by the document classification device 100 is demonstrated. The flowcharts shown in FIGS. 6 to 7 are flowcharts showing processing for preparation before the document classification device 100 classifies a new document. This process is a process executed by the control unit 120 of the document classification device 100. This process is a process for generating the corresponding probability information 500 shown in FIG. Details will be described below.

(Step S601)
In step S601, the control unit 120 of the document classification device 100 sets the variable i used for processing to 1. The variable i is a variable for determining a document to be processed for each document included in the past document list 300. After setting the variable i to 1, the process proceeds to step S602.

(Step S602)
In step S602, the control unit 120 determines whether or not processing has been performed for all documents included in the past document list 300. This determination can be made based on whether or not the number of variables i matches the total number of past document lists 300. In the determination, if all documents are not processed (NO), the process proceeds to step S603. If all documents are processed (YES), the process proceeds to step S609. Transition.

(Step S603)
In step S <b> 603, the control unit 120 determines whether the classification of the publication in the i-th row of the past document list 300 is “noise” with reference to the corresponding classification 302 of the past document list 300. When the classification of the i-th publication is “noise” (YES), the process proceeds to step S604, and when it is not “noise”, that is, “applicable” (NO), step The process proceeds to S605.

(Step S604)
In step S604, the control unit 120 sets the count setting value C to 1, and proceeds to the process of step S606.

(Step S605)
In step S605, the control unit 120 sets the count setting value C to 0, and proceeds to step S607.

(Step S606)
In step S606, the count setting value C calculated in step S604 or step S605 is added to the noise count of each IPC indicated in the IPC classification 303 corresponding to the i-th document in the past document list 300. Here, the noise count is a value serving as an index for determining whether or not each IPC is noise. Thereafter, the process proceeds to step S607.

(Step S607)
In step S <b> 607, the control unit 120 adds 1 to the total count value indicating the total number for each IPC indicated in the IPC classification corresponding to the i-th document in the past document list 300. Thereafter, the process proceeds to step S608.

(Step S608)
In step S608, the control unit 120 sets the value obtained by adding 1 to the variable i as the next value of i, and returns to the process of step S602.

(Step S609)
In step S609, the control unit 120 sets the threshold value T to 2.5% of the total number of documents described in the past document list 300, and proceeds to the process of step S610. Here, the threshold value T is set for each IPC.

(Step S610)
In step S610, the control unit 120 determines whether or not the threshold T calculated in step S609 exceeds 50. If the threshold value T exceeds 50 (YES), the process proceeds to step S611. If not (NO), the threshold value remains unchanged and the process proceeds to step S701 in FIG. To do.

(Step S611)
In step S611, the control unit 120 resets the threshold T to 50, and proceeds to the process of step S701 in FIG.

(Step S701)
In step S701 illustrated in FIG. 7, the control unit 120 sets the variable j to 1 and proceeds to the process of step S702. The variable j is a variable for specifying the IPC to be processed for each IPC.

(Step S702)
In step S702, the control unit 120 determines whether or not the variable j is equal to the number obtained by adding 1 to the total number of IPCs to be processed. When the variable j is the same as the number of IPCs to be processed plus 1 (YES), the process is terminated, and when the number is not the same, the process proceeds to the process of (Step S703).

(Step S703)
In step S703, the control unit 120 determines whether the total number of cases is less than the threshold T for each IPC. If the total number is less than the threshold T (YES), the process proceeds to step S709. If not (NO), the process proceeds to step S704.

(Step S704)
In step S704, the control unit 120 calculates the noise rate of each IPC as a value obtained by dividing the noise count value of each IPC by the total count value of the IPC. The noise count value is a value calculated by the process of step S606 by repeating the processes of steps S602 to S608 in FIG. The IPC total count value is a value calculated by the process of step S607 by repeating the processes of steps S602 to S608. After calculating the noise rate, the process proceeds to step S705.

(Step S705)
In step S705, the control unit 120 determines whether each noise rate is less than 10% for each IPC. If it is less than 10% (YES), the process proceeds to step S706. If it is not less than 10%, that is, if it is 10% or more (NO), the process proceeds to step S708.

(Step S706)
In step S706, the control unit 120 sets the IPC noise determination that the IPC noise rate is less than 10% to 0%. Thereafter, the process proceeds to step S709.

(Step S707)
In step S707, the control unit 120 determines whether or not the noise rate is 95% or more for each IPC whose IPC noise rate is not less than 10%. When the noise rate is 95% or more (YES), the process proceeds to step S709. When the noise rate is not 95% or more (NO), the noise rate is calculated as the value calculated in step S704. The process proceeds to step S709.

(Step S708)
In step S708, the control unit 120 sets the IPC noise determination that the IPC noise rate is 95% or more to 100%. Thereafter, the process proceeds to step S709.

(Step S709)
In step S709, the control unit 120 sets a value obtained by adding 1 to j as a new j, and returns to the process of step S702.

  By executing the above processing, the control unit 120 calculates the noise rate for each IPC, generates the IPC corresponding information 500 shown in FIG. 5, and stores it in the storage unit 130.

  Next, an operation when the document classification apparatus 100 determines whether the publication is “noise” or “applicable” when new document data (publication) is actually input will be described. The flowchart shown in FIGS. 8 to 10 corresponds to this process. This process is a process executed by the extraction unit 121 and the determination unit 122 after the acquisition unit 110 obtains a new document list 350 that is a set of new documents. Details will be described below.

(Step S801)
In step S801, the determination unit 122 sets a variable 1 for distinguishing unidentified documents to 1. Thereafter, the process proceeds to step S802.

(Step S802)
In step S802, the determination unit 122 determines whether or not unidentified documents remain. This determination is made based on whether or not the number of documents included in the new document list 350 matches the variable l. If unidentified documents remain (YES), the process proceeds to step S803. If no documents remain (NO), the process ends.

(Step S803)
In step S803, the determination unit 122 extracts the IPC of the l-th publication. Here, it is extracted from the IPC classification 352 of the new document list 350. The extracted IPC is managed individually. After extracting the IPC, the process proceeds to step S804.

(Step S804)
In step S804, the determination unit 122 sets a variable m used to identify an IPC that is not performing processing to 1. Here, the maximum value of the variable m corresponds to the total number of IPCs extracted in step S803. Thereafter, the process proceeds to step S805.

(Step S805)
In step S805, the determination unit 122 determines whether the determination is for the last IPC, that is, whether m is a number obtained by adding 1 to the total number of m. When m is the number obtained by adding 1 to the total number of IPCs (YES), the process proceeds to step S806. When m is not (NO), the process proceeds to step S812.

(Step S806)
In step S806, the determination unit 122 determines whether or not the number of IPCs that match the search expression IPC is m. If yes (YES), the process proceeds to step S807. If not (NO), the process proceeds to step S901 in FIG.

(Step S807)
In step S807, the determination unit 122 sets the target IPC noise determination to 0%, and proceeds to the process of step S811.

(Step S808)
In step S808, the determination unit 122 determines whether or not the noise determination is zero. If the noise determination is 0 (YES), the process proceeds to step S809. If not (NO), the process proceeds to step S810. Note that. Here, the determination is based on whether or not the noise determination is 0, but this may be determined based on whether or not the noise determination is 100. The process proceeds to step S810, and if not 100, the process proceeds to step S809.

(Step S809)
In step S809, the determination unit 122 determines that Pl, that is, the l-th document is “corresponding”, that is, the document desired by the user, and stores it in association with the l-th document. Thereafter, the process proceeds to step S811.

(Step S810)
In step S810, the determination unit 122 determines that Pl, that is, the l-th document is “noise”, that is, is not a document desired by the user, and stores it in association with the l-th document. Thereafter, the process proceeds to step S811.

(Step S811)
In step S811, the determination unit 122 sets the value obtained by adding 1 to the variable l as a new variable l, and returns to the process of step S802.

(Step S812)
In step S812, the determination unit 122 determines whether the noise rate of the IPC to be processed is set to 0% or 100% in the IPC applicable information 500. When the noise rate is set to 0% or 100% (YES), the process proceeds to step S813, and when not set (NO), the process proceeds to step S814.

(Step S813)
In step S813, the determination unit 122 sets the noise determination of the new document to the noise determination value of the target IPC (that is, either 0% or 100%), and proceeds to the process of step S808. In the processing, when the new document has the IPC classification that is 100% noise or the IPC classification that is 100% corresponding to the IPC corresponding information 500, the classification indicated by the IPC corresponding information 500 is applied to the new document as it is. To do.

(Step S814)
In step S814, the determination unit 122 determines whether the processing target IPC matches the IPC used as the search expression. If they match (YES), the process proceeds to step S815. If they do not match (NO), the process proceeds to step S816.

(Step S815)
In step S815, the determination unit 122 adds 1 to the IPC count that matches the search expression IPC. Thereafter, the process proceeds to step S816.

(Step S816)
In step S816, the determination unit 122 sets a value obtained by adding 1 to the variable m as a new m, and returns to the process of step S805.

(Step S901)
In step S901, the determination unit 122 sets the variable k to 1. The variable k is a variable used for identifying a past document in the past document list 300 to be processed. After the variable k is set to 1, the process proceeds to step S902.

(Step S902)
In step S <b> 902, the determination unit 122 determines whether or not the document to be processed is the total number of past document lists in the past document list 300, and adds a variable k to the total number of past documents included in the past document list 300. Judgment is made based on whether or not the value matches. If the document to be processed is the last document of the past documents included in the past document list 300 (YES), the process proceeds to step S1001 in FIG. 10, and if not (NO), the step The process proceeds to S903.

(Step S903)
In step S903, the determination unit 122 extracts the IPC of the kth publication in the past document list 300. That is, each IPC is extracted from the IPC classification 303 in the k-th row of the past document list 300. Thereafter, the process proceeds to step S904.

(Step S904)
In step S904, each IPC (h) of the h-th publication in the new document list 350 is extracted from the IPC classification 352 in the new document list 350. Thereafter, the process proceeds to step S905.

(Step S905)
In step S905, the determination unit 122 sets the variable n to 1. The variable n is a variable for distinguishing the IPC that is the processing target among the IPCs assigned to the new document to be processed. After setting the variable n to 1, the process proceeds to step S906.

(Step S906)
In step S906, the determination unit 122 determines whether n is last, that is, whether all IPCs assigned to the new document have been processed. If yes (YES), the process proceeds to step S906. If not (NO), the process proceeds to step S907.

(Step S907)
In step S907, the determination unit 122 determines whether IPC (h) n matches the IPC of the search expression. If they match (YES), the process proceeds to step S908. If they do not match (NO), the process proceeds to step S909.

(Step S908)
In step S908, the determination unit 122 decrements the target IPC count by 1, and proceeds to the process of step S911.

(Step S909)
In step S909, the determination unit 122 determines whether IPC (h) n matches IPC (k). That is, of the IPCs assigned to the h-th new document in the new document list 350, the n-th IPC matches any of the IPCs assigned to the k-th past document in the past document list 300. Determine whether. If they match, the process proceeds to step S910 (YES), and if they do not match (NO), the process proceeds to step S911.

(Step S910)
In step S910, the determination unit 122 adds 1 to the IPC match count, and then proceeds to the process of step S911.

(Step S911)
In step S911, the determination unit 122 sets a value obtained by adding 1 to k as a new k, and returns to the process of step S902.

(Step S912)
In step S912, the determination unit 122 has counted the coincidence rate between the IPC of the h-th new document in the new document list 350 and the IPC assigned to the k-th past document in the past document list 300 so far. The IPC match rate count is calculated by dividing by the target IPC count number. Thereafter, the process proceeds to step S913.

(Step S913)
In step S913, the determination unit 122 sets a value obtained by adding 1 to the variable k as a new k, and returns to the process of step S902.

(Step S1001)
In step S <b> 1001, the determination unit 122 arranges the matching rates for each document between the IPC assigned to the new document in the new document list 300 and the IPC assigned to each past document in the past document list 350 in descending order. Change. Thereafter, the process proceeds to step S1002.

(Step S1002)
In step S1002, the extraction unit 121 sets the variable q to 1. The variable q is a variable for specifying the number in order to extract past documents from those having a high degree of coincidence of IPC. After the variable q is set to 1, the process proceeds to step S1003.

(Step S1003)
In step S1003, the extraction unit 121 determines whether or not q is 8. If q is 8 (YES), the process proceeds to step S1004, and if not (NO), the process proceeds to step S1009.

(Step S1004)
In step S <b> 1004, the determination unit 122 divides the noise count by the comparative publication number count for an index t for determining whether the target newly searched patent document is a document desired for the user. Calculate with The noise count is the number calculated in step S1011 and indicates the number of documents that are noise among the past documents extracted from the top of the documents having a high degree of coincidence in patent classification. The comparative publication number count is a number counted in step S1012 and coincides with the maximum number of q. That is, the comparative publication number count means the number of publications to be extracted. When t is calculated, the process proceeds to step S1005.

(Step S1005)
In step S1005, the determination unit 122 determines whether t calculated in step S1004 exceeds a predetermined threshold value α. When t exceeds the threshold value α (YES), the process proceeds to step S1006. When t does not exceed (NO), the process proceeds to step S1007.

(Step S1006)
In step S1006, the determination unit 122 gives information indicating that the corresponding new publication corresponds to the user's desired document (classifies as corresponding). Thereafter, the process proceeds to step S1008.

(Step S1007)
In step S <b> 1007, the determination unit 122 assigns information indicating that the corresponding new gazette is not a user's desired document as noise (classifies as noise). Thereafter, the process proceeds to step S1008.

(Step S1008)
In step S1008, the determination unit 122 sets the value obtained by adding 1 to the variable l as a new l, and proceeds to the process of step S802 in FIG.

(Step S1009)
In step S <b> 1009, the determination unit 122 determines whether or not the number of documents to be processed has reached a value obtained by adding one to the total number of past document lists 300. This determination is a measure for a case where q documents are not included in the past document list 300. If the number of documents to be processed has reached the value added to the total number of the past document list 300 (YES), the process proceeds to step S1004. If not reached (NO), the process of step S1010 is performed. Migrate to

(Step S1010)
In step S1010, the determination unit 122 determines whether the classification 302 of the qth publication in the past document list is “noise”. If it is determined to be noise (YES), the process proceeds to step S1011. If it is determined not to be noise (NO), the process proceeds to step S1012.

(Step S1011)
In step S1011, the determination unit 122 adds 1 to the noise count, and the process proceeds to step S1012.

(Step S1012)
In step S1012, the determination unit 122 increments the comparative publication number count by 1, and proceeds to the process of step S1013.

(Step S1013)
In step S1013, the determination unit 122 sets a value obtained by adding 1 to the variable q as a new q, and proceeds to the process of step S1003.

  By executing the processing shown in FIGS. 8 to 10, the document classification apparatus 100 can determine whether each new document is noise or not for all new documents included in the new document list 350. it can.

  The operation of the document classification apparatus 100 has been described above.

<Summary>
The document classification device according to the above embodiment determines whether or not a document obtained by a search formula in advance is a desired one based on the patent classification originally given to the patent gazette. "Is given. When a new patent publication is input, a predetermined number of documents are extracted based on the degree of coincidence between the patent classification assigned to the new patent publication and the patent classification of the classified patent publication. The contents of the patent gazette indicate whether the new patent gazette is “noise” or “corresponding” depending on whether the classification given to the extracted document is “Noise” or “Applicable”. Can be classified without scrutiny. And even if the document is searched according to the search formula set by the user, it is not necessary to check the content of the document determined to be noise, so the time required for document screening is reduced. can do. In addition, as a document classification device, it is not necessary to scrutinize the inside of the official gazette (it is not necessary to perform morphological analysis or see the matching rate of a huge number of words extracted by morphological analysis). The processing load of the processor can be reduced as compared with the classification devices shown in 1 to 3.

<Supplement>
It goes without saying that the document classification device according to the above embodiment is not limited to the above embodiment, and may be realized by other methods. Hereinafter, various modifications will be described.

  (1) Although not specifically described in the above embodiment, the number of documents q extracted by the extraction unit 121 is desirably an odd number. This is because “noise” or “corresponding” can always be specified by setting an odd number. The variable q may be calculated using a so-called k-nearest neighbor method.

  When q is set to an even number, the number of “noise” and “corresponding” may be the same. Therefore, the document classification device may classify the document using the following method. That is, the basic value of the “noise” document is “−1”, and the basic value of “applicable” is “+1”. Then, a value obtained by multiplying the basic value by the matching degree as a weight value is set as a classification value indicating whether the reference is noise or appropriate. And the judgment part 122 adds together the classification | category value of the literature which the extraction part 121 extracted, and if the value is positive, it may classify | categorize as "applicable", and if it is negative, it may classify as "noise". Good. In the case of this method, the processing load related to the determination process of “noise” or “appropriate” is larger than the processing load due to the process shown in the above embodiment, but more accurately “noise” or “applicable”. Judgment can be made. That is, the document classification apparatus 100 may perform classification after performing correction by weighting. Here, the degree of coincidence itself is used as the weight value, but this is not limited to this, and an arbitrary value may be used as the weight value.

  (2) In the above-described embodiment, the classification of the majority occupying the determination of whether it is noise or not is the classification of a new document, but this is not limited thereto. For example, if the classification of a predetermined number or more of the q documents extracted by the extraction unit 121 is “noise”, the new document may be determined to be “noise”. For example, if the number of extracted documents is 10, and 8 or more of them are classified as “noise”, the new document may be classified as “noise”.

  (3) In the above embodiment, in determining whether the patent classification, which is a technical feature, is noise or appropriate, the classification with a noise rate of less than 10% is set as noise determination 0%, and the IPC noise A classification with a rate of 95% or more was determined as a noise determination of 100%. Here, it can be said that the threshold value of 10% is a second threshold value for determining whether or not a document corresponds to a document desired by the user when a corresponding classification is given. That is, it can be said that the determination in step S705 is a determination as to whether the corresponding rate is 90% or more. The same applies to the first threshold value used for the determination in step S707.

  That is, the document classification device 100 determines based on whether or not the corresponding rate indicating whether or not the patent classification assigned to the document is applicable is 90% or more which is the first threshold, and the non-applicable rate is the first. It can be understood that the determination is made based on whether or not the threshold value is 95% or more. Here, by providing a difference between the first threshold value and the second threshold value, the classification can be surely classified as either noise or appropriate. Further, the first threshold value and the second threshold value may be varied depending on whether priority is given to determining that the classification is noise or priority is determined to be applicable. For this purpose, the document classification apparatus 100 may include a setting unit for setting the first threshold value and the second threshold value. The input to the setting unit may be set to an appropriate value by the document classification device 100 by learning, or may be set by the user of the document classification device 100. Note that the threshold percentages used for these determinations are not limited to the numerical values shown in the above embodiment, and the operator of the document classification apparatus 100 can change the set values as appropriate.

  (4) In the above embodiment, a document to which a classification with an IPC noise rate of 100% is assigned is classified as noise, and a document to which a classification with an IPC noise rate of 0% is assigned is classified as applicable. I am going to do that. However, in some cases, there may be a document to which a classification with a noise rate of 100% and a classification with a noise rate of 0% are given. In such a case, the document classification device 100 may determine that the document is “noise” or “appropriate” in accordance with a predetermined criterion determined in advance by the user. Good. For example, when “noise” is set to be prioritized, it is determined to be “noise”, and when “setting” is set to be prioritized, it is determined to be “corresponding”.

  (5) In the above embodiment, as a method for classifying new document data by the document classification apparatus, a processor functioning as each functional unit constituting the document classification apparatus 100 executes a document classification program or the like. Document data is classified, but this is realized by a logic circuit (hardware) or a dedicated circuit formed in an integrated circuit (IC (Integrated Circuit) chip, LSI (Large Scale Integration)) in the device. Also good. These circuits may be realized by one or a plurality of integrated circuits, and the functions of the plurality of functional units described in the above embodiments may be realized by a single integrated circuit. An LSI may be called a VLSI, a super LSI, an ultra LSI, or the like depending on the degree of integration. That is, as shown in FIG. 11, each functional unit constituting the document classification device 100 may be realized by a physical circuit. As shown in FIG. 11, the document classification device 100 includes a storage circuit 130a, an acquisition circuit 110a, an extraction circuit 121a, a determination circuit 122a, and an output circuit 140a, and each circuit has the same function as described above. The same function as the unit.

  The document classification program may be recorded on a processor-readable recording medium, and the recording medium may be a “non-temporary tangible medium” such as a tape, a disk, a card, a semiconductor memory, a programmable logic A circuit or the like can be used. The document classification program may be supplied to the processor via an arbitrary transmission medium (such as a communication network or a broadcast wave) that can transmit the document classification program. The present invention can also be realized in the form of a data signal embedded in a carrier wave, in which the document classification program is embodied by electronic transmission.

  The document classification program can be implemented using, for example, a script language such as ActionScript or JavaScript (registered trademark), an object-oriented programming language such as Objective-C or Java (registered trademark), or a markup language such as HTML5. .

  (6) The configurations described in the above embodiments and supplements may be combined as appropriate.

100 Document Classification Device 110 Acquisition Unit 121 Extraction Unit 122 Determination Unit 140 Output Unit

Claims (9)

First document information indicating a plurality of document data searched according to a search formula, first feature information indicating one or more technical features of the document data assigned to the document data, and the document data A storage unit that stores corresponding information indicating whether or not the document is desired for the user;
An acquisition unit that acquires second document information indicating other document data that is newly searched according to the search formula and is given second feature information indicating one or more technical features;
An extraction unit that extracts a predetermined number of document data from the plurality of document data based on the degree of coincidence between the second feature information and the first feature information;
A determination unit that determines whether the other document data is a document desired by the user based on the corresponding information associated with each of the predetermined number of document data extracted by the extraction unit;
A document classification apparatus comprising: an output unit that outputs a determination result of the determination unit. The extraction unit extracts a predetermined number from the plurality of document data from a high degree of coincidence between the second feature information and the first feature information,
The determination unit determines that the other document data is desired by the user when the corresponding information associated with the document extracted by the extraction unit is more than a threshold value indicating that the document is desired by the user. The document according to claim 1, wherein the document is determined to be a document, and if the number of documents indicating that the document is not desired for the user is greater than a threshold value, the other document data is determined not to be a document desired for the user Document document classification device. The determination unit weights the corresponding information associated with the document extracted by the extraction unit according to the degree of matching, and based on the corresponding information after the weighting, the other document The document classification apparatus according to claim 1, wherein data is determined as to whether or not the document is a document desired for the user. The determination unit associates the first feature information of the document data that is associated with the first feature information and indicates that the corresponding information is a document that the user does not desire. The non-applicable rate indicating the ratio to the entire document data is determined as a document that the user does not desire other document data having the second feature information that matches the first feature information exceeding the first threshold. The document classification device according to claim 1, wherein The determination unit associates the first feature information of document data that is associated with the first feature information and indicates that the corresponding information is a document desired by the user. The corresponding rate indicating the ratio with respect to the entire document data is determined as a document that the user desires other document data having the second feature information that matches the first feature information exceeding the second threshold. The document classification device according to claim 4, wherein the document classification device is characterized in that: The document classification apparatus according to claim 5, wherein the first threshold is larger than the second threshold. In the case where feature information is used in the search formula, the determination unit performs the determination based on the first feature information excluding the feature information and the second feature information. The document classification device according to any one of claims 1 to 6. First document information indicating a plurality of document data searched according to a search formula, first feature information indicating one or more technical features of the document data assigned to the document data, and the document data A storage step for storing the corresponding information indicating whether or not the document is desired for the user;
An acquisition step of acquiring second document information indicating other document data newly searched according to the search formula and provided with second feature information indicating one or more technical features;
An extraction step of extracting a predetermined number of document data from the plurality of document data based on the degree of coincidence between the second feature information and the first feature information;
A determination step of determining whether the other document data is a document desired for the user based on the corresponding information associated with each of the predetermined number of document data extracted in the extraction step;
A document classification method including an output step of outputting a determination result in the determination step. On the computer,
First document information indicating a plurality of document data searched according to a search formula, first feature information indicating one or more technical features of the document data assigned to the document data, and the document data A storage function for associating and storing corresponding information indicating whether or not the document is desired for the user;
An acquisition function for acquiring second document information indicating other document data that is newly searched according to the search formula and is given second feature information indicating one or more technical features;
An extraction function for extracting a predetermined number of document data from the plurality of document data based on the degree of coincidence between the second feature information and the first feature information;
A determination function for determining whether the other document data is a document desired by the user based on the corresponding information associated with each of the predetermined number of document data extracted by the extraction function;
A document classification program for realizing an output function for outputting a determination result of the determination function.

Images