JP2020173849A - Information processing device, method, and program - Google Patents

Abstract

To provide information processing device, method, and program capable of achieving proper evaluation of quality of a patent publication such as a specification.SOLUTION: In a publication evaluation device 1, a claim word frequency distribution generation part 41 separates content of a range of a patent claim of a patent published publication into respective words, and generates claim word frequency distribution indicating frequency distribution of each word, after the content is separated into words. A specification word frequency distribution generation part 42 separates content of a specification of the patent published publication into respective words, and generates specification word frequency distribution indicating frequency distribution of each word after the content is separated into words. A specification synonym frequency distribution generation part 43 classifies the respective words extracted from the specification into a plurality of groups corresponding to each of the plurality of words in the range of the patent claim, and then, generates specification synonym frequency distribution indicating frequency distribution in which each of the plurality of groups after classification is a unit. An evaluation information generation part 44 generates evaluation information on the basis of the claim word similarity distribution and the specification synonym frequency distribution.SELECTED DRAWING: Figure 2

Description

The present invention relates to information processing devices and methods, and programs.

Traditionally, patent rights have been acquired by many companies for the purpose of protecting projects scheduled to be implemented or projects underway. In addition, the patent right is a property right and can be effectively utilized by transferring it to a third party, setting an exclusive license, or granting a non-exclusive license.

In order to obtain a patent right, it is necessary to submit the application and the attached documents of the application. Attachments to the application include claims, specification, drawings, and abstract.
A lot of research and development has been done on the technology to support the preparation of the attached documents of the application (see, for example, Patent Document 1) and the technology to analyze the sentence structure of the attached documents of the application (see, for example, Patent Document 2). ing.

JP 2013-080278 Japanese Unexamined Patent Publication No. 2014-010728

However, although there has been a demand for the realization of an appropriate evaluation method for the quality of publications such as specifications, there has been a situation in which conventional techniques including Patent Documents 1 and 2 cannot sufficiently meet the demand.

The present invention has been made in view of such a situation, and an object of the present invention is to realize an appropriate evaluation method for the quality of publications such as specifications.

The information processing device of one aspect of the present invention is
The content of the first document that can be included in the publication on intellectual property rights is separated into predetermined unit information consisting of characters, figures, symbols, or a combination thereof, and the frequency distribution of the unit information after separation is shown. 1 The first information generation means for generating information and
A second information generating means that separates the contents of the second document that can be included in the publication into the unit information and generates the second information indicating the frequency distribution of the unit information after the separation.
An evaluation information generating means for generating evaluation information for evaluating the contents of the publication based on the first information and the second information.
To be equipped.

Here, each unit information in the second information is classified into a plurality of groups corresponding to each of the plurality of unit information in the first information, and the frequency distribution in each of the plurality of groups after classification is calculated. Further provided with a third information generating means for generating the third information shown,
The evaluation information generating means generates the evaluation information based on the first information and the third information.
be able to.

The evaluation information generating means calculates a score based on the ranking difference from the corresponding group in the third information for each unit information in the first information.
The evaluation information is generated based on the total value of the scores of the unit information in the first information.
be able to.

The evaluation information generating means weights the score based on the order of each unit information in the first information.
be able to.

The evaluation information generating means weights the score for each unit information of the first information based on the degree of association with each unit information belonging to the corresponding group in the third information.
be able to.

The evaluation information generating means removes noise information from the unit information of the first information, and the evaluation information is based on the total value of the score for each unit information after the noise information is removed. To generate,
be able to.

The information processing method and program of one aspect of the present invention are the methods and programs corresponding to the above-mentioned information processing device of one aspect of the present invention.

According to the present invention, it is possible to realize an appropriate evaluation method for the quality of publications such as specifications.

It is a block diagram which shows the hardware structure of the publication evaluation apparatus as one Embodiment of the information processing apparatus to which this invention is applied. It is a functional block diagram which shows the functional structure of the publication evaluation apparatus of FIG. It is a schematic diagram explaining the outline of the evaluation information generation processing executed by the publication evaluation apparatus having the functional structure of FIG. It is a flowchart explaining the flow of the evaluation information generation processing executed by the publication evaluation apparatus having the functional structure of FIG.

Hereinafter, embodiments of the present invention will be described with reference to the drawings.

FIG. 1 is a block diagram showing a hardware configuration of a publication evaluation device 1 as an embodiment of the information processing device of the present invention.

The publication evaluation device 1 includes a CPU (Central Processing Unit) 11, a ROM (Read Only Memory) 12, a RAM (Random Access Memory) 13, a bus 14, an input / output interface 15, an input unit 16, and an output unit. A 17, a storage unit 18, a communication unit 19, and a drive 20 are provided.

The CPU 11 executes various processes according to the program recorded in the ROM 12 or the program loaded from the storage unit 18 into the RAM 13.
Data and the like necessary for the CPU 11 to execute various processes are also appropriately stored in the RAM 13.

The CPU 11, ROM 12 and RAM 13 are connected to each other via the bus 14. An input / output interface 15 is also connected to the bus 14. An input unit 16, an output unit 17, a storage unit 18, a communication unit 19, and a drive 20 are connected to the input / output interface 15.

The input unit 16 is composed of a keyboard, a mouse, or the like, and inputs various information in response to an operator's instruction operation.
The output unit 17 is composed of a display, a speaker, or the like, and outputs an image or sound.
The storage unit 18 is composed of a hard disk, a DRAM (Dynamic Random Access Memory), or the like, and stores various data.
The communication unit 19 controls communication with another device (not shown) via the network 4 including the Internet.

A removable medium 31 made of a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is appropriately mounted on the drive 20. The program read from the removable media 31 by the drive 20 is installed in the storage unit 18 as needed. In addition, the removable media 31 can also store various data stored in the storage unit 18 in the same manner as the storage unit 18.

In the present embodiment, the publication evaluation device 1 having such a configuration is a device that evaluates the quality of a specification that can be included in a patent publication, an application publication publication, or a utility model registration publication.
In the following description, the patent right will be described for convenience, but the same is basically true for the utility model right.

In order to obtain a patent right, in addition to the application, it is necessary to submit the claims, specification, necessary drawings, and abstract as attachments to the application.

The scope of claims should fulfill its mission as a title of patent right. That is, the technical scope of the patented invention is determined based on the description of the claims.
The specification should fulfill its mission as a technical document that discloses the contents of the invention to a third party.
Here, regarding the description of the scope of claims, the requirement that "the invention for which a patent is sought is described in the detailed description of the invention" (hereinafter referred to as "support requirement") is required. There is. Specifically, in Japan, the support requirements are stipulated in Article 36, Paragraph 6, Item 1 of the Patent Act.
This support requirement is a reason for refusal (Patent Law Article 49, No. 4) in Japan. In other words, a patent right cannot be obtained in Japan unless the specification meets the support requirements.
Therefore, meeting the support requirements is one of the important factors for the quality of the specification.
Therefore, the publication evaluation device 1 of the present embodiment provides evaluation information for evaluating the contents of the specification based on the frequency distribution of words included in the claims and the frequency distribution of words included in the specification. Generates an evaluation value (hereinafter referred to as "support information fulfillment index") indicating the degree of fulfillment of support requirements.
Hereinafter, a series of processes until the evaluation information (support information enrichment index) of the patent gazette or the application publication gazette to be evaluated is generated is referred to as "evaluation information generation process".

FIG. 2 is a functional block diagram showing a functional configuration for executing the evaluation information generation process among the functional configurations of the publication evaluation device 1.
When the evaluation information generation process is executed in the CPU 11 of the publication evaluation device 1, the claim word frequency distribution generation unit 41, the specification word frequency distribution generation unit 42, the specification document synonym frequency distribution generation unit 43, and the evaluation information The generation unit 44 functions. The evaluation information generation unit 44 includes a weighting unit 51.
The publication information DB 61 is provided in one area of the storage unit 18 of the publication evaluation device 1.

The claim word frequency distribution generation unit 41 separates the content of the claims (contents of the claim) included in the patent gazette or the publication of the application to be evaluated into each word, and information indicating the frequency distribution of the separated words. (Hereinafter referred to as "claim word frequency distribution") is generated.

The specification word frequency distribution generation unit 42 separates the contents of the specification included in the patent gazette or the application publication gazette to be evaluated into each word, and provides information indicating the frequency distribution of the separated words (hereinafter, “specification”. (Called word frequency distribution) is generated.

Here, in generating the support information enrichment index, the claim word frequency distribution and the specification word frequency distribution may be compared, but the comparison may not be a valid comparison. The reason for this will be described below.

However, in addition to the support requirements described above, the specification provides a detailed description of the invention, "clear and sufficient to the extent that a person having ordinary knowledge in the technical field to which the invention belongs can carry out the invention. The requirement that "it must be as described in" (hereinafter referred to as "enablement requirement") is also required. Specifically, in Japan, the enablement requirement is stipulated in Article 36, Paragraph 4, Item 1 of the Patent Act.
This enablement requirement is a reason for refusal (Patent Law Article 49, No. 4) in Japan. In other words, a patent right cannot be obtained in Japan unless the specification meets the enablement requirements.
Here, since the scope of claims has the character of a title as described above, it is often described in the highest possible concept so as to have a broad scope of rights in general. In other words, each word that appears in the claim word frequency distribution is often a vague word of a superordinate concept.
On the other hand, the specification should be a word indicating a specific technical content, that is, a subordinate concept exemplifying the superordinate concept (word described in the claims) in order to satisfy the enablement requirement. There are many. That is, in the specification, a word indicating a specific technical content often appears as a word for explaining a superordinate concept.
In other words, the words of the superordinate concept described in the claims are used as they are, and the embodiments in the specification are rarely described, and the words of a plurality of subordinate concepts (exemplifications) are described. There are many.
Therefore, even if the claim word frequency distribution and the specification word frequency distribution are compared as they are, it may not be a valid comparison.

Therefore, in the present embodiment, the specification document synonym frequency distribution generation unit 43 classifies each word extracted from the specification into a plurality of groups corresponding to each of the plurality of words (superordinate concept) in the claims. ..
Here, the method of classifying into a plurality of groups is not particularly limited, but in the present embodiment, the synonyms are classified into the same group assuming that the superordinate concept of the plurality of synonyms corresponds to a predetermined one word in the claims. The classification method of doing is adopted.
The specification document synonym frequency distribution generation unit 43 generates information indicating a frequency distribution in units of each of a plurality of classified groups (groups corresponding to a plurality of words in the claims). Such information is hereinafter referred to as "detailed document synonym frequency distribution".

The evaluation information generation unit 44 generates a support information enrichment index (evaluation information) based on the claim word synonym frequency distribution and the detailed document synonym frequency distribution.
For example, in the present embodiment, the evaluation information generation unit 44 has a frequency ranking of words included in the claim word frequency distribution and a frequency of a group included in the detailed document synonym frequency distribution (a group corresponding to a predetermined word in the claim word frequency distribution). The degree of similarity is calculated by comparing with the ranking. The evaluation information generation unit 44 generates the similarity or its processed value as a support information enrichment index (evaluation information).
Specifically, for example, the evaluation information generation unit 44 calculates a score based on the ranking difference from the corresponding group in the detailed document synonym frequency distribution for each word in the claim word frequency distribution, and each in the claim word frequency distribution. A support information enrichment index (evaluation information) is generated based on the total value of the word scores.

FIG. 3 is a schematic diagram illustrating an outline of an evaluation information generation process executed by the publication evaluation device 1 having such a functional configuration of FIG. 2.

In the example of FIG. 3, regarding the frequency ranking of the claim word frequency 71, the first place is “elastic body” and the second place is “stress”.
Here, regarding the frequency ranking of the specification word frequency 72, the first place is "stress", the second place is "spring", and the third place is "rubber". Therefore, when the claim word frequency 71 and the specification word frequency 72 are compared in terms of frequency ranking, the scope of claims and the first place of the specification are different, and the first place of the claims "elastic body". Is not ranked in the specification. As a result, if the support information enrichment index (evaluation information) is simply generated based on this ranking, the similarity may be low (the degree of agreement is low) and the value may be low.
Specifically, for example, if the rankings match, a score "1" is given, if the ranking difference is 1, a score "0.9" is given, and if the ranking difference is 2, a score "0" is given. 0.8 ”is given, and the score decreases by 0.1 each time the ranking difference increases thereafter, and after the score becomes“ 0 ”, the score becomes uniformly“ 0 ”. In this case, for the claim word frequency 71, the score of the first-ranked "elastic body" is "0.9", and the score of the second-ranked "stress" is "0". If the total value of these scores is the support information enrichment index (evaluation information), the value will be "0.9".
The reason why the support information enrichment index (evaluation information), which should be originally high, is low is that the superordinate concept of "elastic body" is associated with the subordinate concepts of "spring" and "rubber". Because it is not.

Therefore, in the present embodiment, the specification document synonym frequency distribution generation unit 43 classifies the "spring" and "rubber" extracted from the specification so as to belong to the group corresponding to the "elastic body" in the claims. To do.
As a result of such classification, a detailed document synonym frequency 73 is generated. Regarding the frequency ranking of the specification synonym frequency 73, the first place is the group to which the "spring, group" belongs, that is, the group corresponding to the "elastic body" in the claims. The second place is the group to which "stress" belongs, that is, the group corresponding to "stress" in the claims.
In this case, the order of the claim word frequency 71 and the order of the detailed document synonym frequency 73 are the same. Therefore, when the support information enrichment index (evaluation information) is generated based on this order, the degree of similarity is high (match degree). Is high), and the price is high.
Specifically, for example, if a higher score is used, the score of the first-ranked "elastic body" is "1" and the score of the second-ranked "stress" is also "1" for the claim word frequency 71. .. Therefore, the high value of the total value "2" of these scores becomes the support information enrichment index (evaluation information).

Here, both the claim word frequency 71 and the detailed document synonym frequency 54 are distributions based on the appearance frequency of simple words. In some cases, the reliability of the support information enrichment index (evaluation information) compared between such simple appearance frequencies is not high.
Therefore, the evaluation information generation unit 44 of the present embodiment is provided with a weighting unit 51.

For example, when the score based on the frequency ranking described above is adopted, the evaluation information generation unit 44 can weight the score based on the ranking of each word in the claim word frequency 71.
For example, even if the rankings match, when comparing the cases where the first places match and the cases where the tenth places match each other, the former case contributes more to the overall similarity. It can be said that it is expensive.
Therefore, the weighting unit 51 weights so that the score when matching as the first place is high, and weights so that the score when matching as the tenth place is low. For example, the score is "2" when the first place matches, while the score when the tenth place matches is "0.2".

Further, for example, the evaluation information generation unit 44 can weight each word in the claim word frequency 71 based on the degree of association with each word belonging to the corresponding group in the detailed document synonym frequency 73.
For example, for the group corresponding to "elastic body" in the claims, "spring, rubber" is included in the corresponding group in the specification synonym frequency 73. These are subordinate concepts of "elastic body", but the word "elastic body" itself does not belong to the group.
On the other hand, for the group corresponding to "stress" in the claims, the word "stress" itself is included in the corresponding group in the specification synonym frequency 73.
Therefore, the weighting unit 51 increases the weight by assuming that the "stress" in the claims belongs to the corresponding group of the words having a high degree of relevance rather than the "elastic body" in the claims. Is weighted.

It is assumed that the support information enrichment index (evaluation information) generated after various weighting in this way has a value closer to the substance. That is, by weighting, it is possible to generate a more accurate support information enrichment index (evaluation information).

Here, in the claim word frequency 71, a word different from the word characteristic of the patented invention, for example, a general word such as “the above” shown in FIG. 3 may be ranked high in the frequency ranking. Therefore, it is advisable to remove such words as noise information.
That is, the evaluation information generation unit 44 removes noise information (for example, the word "above") from each word in the claim word frequency 71, and the total value of the score for each word after the noise information is removed. Support information enrichment index (evaluation information) is generated based on.

It is assumed that the support information enrichment index (evaluation information) generated after noise removal is a value closer to the substance. That is, by removing the noise information, it is possible to generate a more accurate support information enrichment index (evaluation information).

FIG. 4 is a flowchart illustrating a flow of evaluation information generation processing executed by the publication evaluation device 1 having the functional configuration of FIG.

In step S1, the claim word frequency distribution generation unit 41 generates a claim word frequency distribution.
In step S2, the specification word frequency distribution generation unit 42 generates the specification word frequency distribution.
In step S3, the detailed document synonym frequency distribution generation unit 43 generates the detailed document synonym frequency distribution.
In step S4, the evaluation information generation unit 44 generates a support information enrichment index (evaluation information) based on the claim word synonym frequency distribution and the detailed document synonym frequency distribution.
As a result, the evaluation information generation process is completed.

Although the embodiments of the present invention have been described above, the present invention is not limited to the above-described embodiments. Further, the effects described in the present embodiment merely list the most preferable effects arising from the present invention, and the effects according to the present invention are not limited to those described in the present embodiment.

For example, in the above-described embodiment, each word is extracted from the claims of the patent publication or the publication of the application to generate a frequency distribution, and each word is extracted from the specification to generate a frequency distribution.
However, it is not particularly limited to the above-described embodiment, and characters, figures, symbols, or combinations thereof (hereinafter, referred to as "characters and the like") may be extracted from, for example, a specification, a drawing, or a summary.
Furthermore, in the above-described embodiment, the publication relating to the patent is adopted, but it is not particularly necessary to limit the publication to the patent, and the intellectual property right granted on the premise of submitting two or more types of documents including characters and the like. The present invention can be adopted for general evaluation.

Further, for example, in the above-described embodiment, the unit information of the frequency distribution is a word, but the unit information is not particularly limited to this, and any unit information consisting of characters, figures, symbols, or a combination thereof may be adopted. it can.

In other words, the information processing apparatus to which the present embodiment is applied only needs to have the following configuration, and can take various various embodiments.

That is, the information processing device of the present invention
The contents of the first document (for example, claims) that can be included in the publication on intellectual property rights are separated into predetermined unit information (for example, words) consisting of characters, figures, symbols, or a combination thereof. A first information generating means (for example, the claim word frequency distribution generation unit 41 in FIG. 2) for generating the first information (for example, the claim word frequency distribution) indicating the frequency distribution of the unit information later, and
The content of the second document (for example, the specification) that can be included in the publication is separated into the unit information (for example, a word), and the second information (for example, the specification word frequency distribution) showing the frequency distribution of the unit information after the separation is shown. ) (For example, the specification word frequency distribution generation unit 42 in FIG. 2) and
An evaluation information generating means for generating evaluation information for evaluating the contents of the publication based on the first information and the second information.
To be equipped.

By adopting such an information processing device, it becomes possible to more appropriately evaluate the publication on intellectual property rights.

The contents of the first document and the second document that can be included in the gazette do not necessarily have to be a copy of the gazette, and if the gazette is issued, the first document that will be included in the gazette. And each content of the second document is also included.
In other words, the issuance of a gazette is not particularly essential, and information indicating the contents of the first and second documents may exist even at the stage of unapplication or the stage of unpublished after filing, so we intend to include these as well. , "Can be included in the gazette".
Therefore, as the contents of the first document and the second document that can be included in the gazette, for example, the copy data held by the applicant regarding the "claims" and "specification" that have not been published after the application. It also includes the contents of documents (for example, invention reports prepared by the applicant) that describe the contents of the "claims" and "specifications" before filing the application.
Further, the second user does not have to be a candidate business operator, and the person in charge of intellectual property on the applicant side may also be applicable.
From the above, for example, the person in charge of intellectual property on the patent applicant (company) side can evaluate the draft specification at the stage before filing the application, so that the draft specification with a low evaluation is highly evaluated. You can also apply after rewriting in.

Furthermore, such evaluation information can be applied to other fields such as patent analysis. For example, it can be used to modify (weight) the patent evaluation index based on the number of citations.
Further, for example, when searching for a license candidate or the like based on patent analysis, a patent consisting of a specification having high evaluation information (support information enrichment index) is given priority as a patent with a "high matching possibility" as a license candidate. It can also be presented to others.

The series of processes described above can be executed by hardware or software.
In other words, the functional configuration of FIG. 3 is merely an example and is not particularly limited. That is, it suffices if the publication evaluation device 1 is provided with a function capable of executing the above-mentioned series of processes as a whole, and what kind of functional block is used to realize this function is not particularly limited to the example of FIG. ..
Further, one functional block may be configured by a single piece of hardware, a single piece of software, or a combination thereof.

When a series of processes are executed by software, the programs constituting the software are installed on a computer or the like from a network or a recording medium.
The computer may be a computer embedded in dedicated hardware. Further, the computer may be a computer capable of executing various functions by installing various programs, for example, a general-purpose personal computer.

The recording medium including such a program is not only composed of the removable media 31 of FIG. 1 distributed separately from the device main body in order to provide the program to the user, but also is preliminarily incorporated in the device main body. Consists of recording media and the like provided in. The removable media 31 is composed of, for example, a magnetic disk (including a floppy disk), an optical disk, a magneto-optical disk, or the like. The optical disk is composed of, for example, a CD-ROM (Compact Disk-Read Only Memory), a DVD (Digital Versaille Disk), or the like. The magneto-optical disk is composed of MD (Mini-Disk) or the like. Further, the recording medium provided to the user in a state of being incorporated in the apparatus main body in advance includes, for example, the ROM 12 of FIG. 1 in which the program is recorded, the hard disk included in the storage unit 18, and the like.

In the present specification, the steps for describing a program recorded on a recording medium are not necessarily processed in chronological order, but also in parallel or individually, even if they are not necessarily processed in chronological order. It also includes the processing to be executed.

1 ... Publication evaluation device, 11 ... CPU, 12 ... ROM, 13 ... RAM, 14 ... Bus, 15 ... Input / output interface, 16 ... Input unit, 17 ... -Output unit, 18 ... Storage unit, 19 ... Communication unit, 20 ... Drive, 31 ... Removable media, 41 ... Claim word frequency distribution generation unit, 42 ... Specification word frequency Distribution generation unit, 43 ... Detailed document frequency distribution generation unit, 44 ... Evaluation information generation unit, 51 ... Weighting unit, 61 ... Publication information DB

Claims (8)

The content of the first document that can be included in the publication on intellectual property rights is separated into predetermined unit information consisting of characters, figures, symbols, or a combination thereof, and the frequency distribution of the unit information after separation is shown. 1 The first information generation means for generating information and
A second information generating means that separates the contents of the second document that can be included in the publication into the unit information and generates the second information indicating the frequency distribution of the unit information after the separation.
An evaluation information generating means for generating evaluation information for evaluating the contents of the publication based on the first information and the second information.
Information processing device equipped with. A third group in which each unit information in the second information is classified into a plurality of groups corresponding to each of the plurality of unit information in the first information, and the frequency distribution in each of the plurality of groups after classification is shown. Further equipped with a third information generation means for generating information,
The evaluation information generating means generates the evaluation information based on the first information and the third information.
The information processing device according to claim 1. The evaluation information generating means calculates a score based on the ranking difference from the corresponding group in the third information for each unit information in the first information.
The evaluation information is generated based on the total value of the scores of the unit information in the first information.
The information processing device according to claim 2. The evaluation information generating means weights the score based on the order of each unit information in the first information.
The information processing device according to claim 3. The evaluation information generating means weights the score for each unit information of the first information based on the degree of association with each unit information belonging to the corresponding group in the third information.
The information processing device according to claim 3. The evaluation information generating means removes noise information from the unit information of the first information, and the evaluation information is based on the total value of the score for each unit information after the noise information is removed. To generate,
The information processing device according to claim 3. In the information processing method executed by the information processing device
The content of the first document that can be included in the publication on intellectual property rights is separated into predetermined unit information consisting of characters, figures, symbols, or a combination thereof, and the frequency distribution of the unit information after separation is shown. 1 The first information generation step to generate information and
A second information generation step of separating the contents of the second document that can be included in the publication into the unit information and generating the second information indicating the frequency distribution of the unit information after the separation.
An evaluation information generation step for generating evaluation information for evaluating the contents of the publication based on the first information and the second information.
Information processing methods including. On the computer
The content of the first document that can be included in the publication on intellectual property rights is separated into predetermined unit information consisting of characters, figures, symbols, or a combination thereof, and the frequency distribution of the unit information after separation is shown. 1 The first information generation step to generate information and
A second information generation step of separating the contents of the second document that can be included in the publication into the unit information and generating the second information indicating the frequency distribution of the unit information after the separation.
An evaluation information generation step for generating evaluation information for evaluating the contents of the publication based on the first information and the second information.
A program that executes a control process that includes.

Images