Analysis case report evaluation device, evaluation method, and evaluation program

Abstract

An evaluation device (3) for evaluating an analysis case report disclosed on a website, the evaluation device (3) comprising: an extraction unit (34) that extracts, from the report, a first item which relates to the content of the analysis case reported in the report, a second item which relates to the volume of the report, and a third item which relates to the type of a relevant sample of the analysis case reported in the report; an evaluation information storage unit (322) that stores evaluation scores for evaluating the report for each of the first item, the second item, and the third item; and a calculation unit (35) that aggregates the evaluation scores of each of the first item, the second item, and the third item extracted by the extraction unit, and evaluates the report on the basis of an aggregation result.

Description

Apparatus, method and program for evaluating analysis case reports

[0001] The present invention relates to an evaluation device, an evaluation method, and an evaluation program for evaluating an analysis case report.

[0002] A device has been proposed that collects documents describing various products, services, etc. posted on websites publicly available on the Internet, analyzes the documents, and evaluates products and services (Patent Document 1). This device extracts words that express emotions from the documents, tallying up the scores assigned to the words, and converts the evaluations into numerical values. From the numerical evaluations of the products or services, it is possible to understand third-party evaluations and rankings of various products and services.

[0003] The device described in Patent Document 1 assigns scores to products and services based on subjective evaluations by people who post evaluation documents for the products and services on a website.

[0004] In response to this trend, in recent years, companies that manufacture and sell products and companies that provide services have begun publishing articles about their products and services on the Internet as application notes and application news. Application notes and application news (hereinafter collectively referred to as application notes) contain, for example, explanations of the product's specifications, functions, and operation methods, precautions for using the product, and explanations of experiments conducted to confirm the product's operation. Furthermore, in the case of analytical equipment such as liquid chromatographs and mass spectrometers, application notes contain documents, graphs, tables, and the like that show the results of analyzing a specified sample using the analytical equipment.

[0005] Japanese Patent Application Laid-Open No. 2015-36923

[0006] Application notes can serve as reference information for people considering purchasing a product or receiving a service, so the contents of application notes published by a company are important documents that can affect the company's reputation.

[0007] However, many of the documents included in application notes do not contain words or phrases that express emotions, or even if they do, they contain very few. In particular, in the case of application notes related to analytical devices, the documents included are technical documents, and in addition to the documents, they also contain many graphs and tables that show the analysis results, so there was a problem that the device in Patent Document 1 could not correctly evaluate the application notes.

[0008] The problem to be solved by the present invention is to enable correct evaluation of reports that report analysis cases, such as application notes and application news published on websites.

[0009] The present invention, which has been made to solve the above-mentioned problems, is an evaluation device for evaluating reports of analytical cases published on a website, the device having an extraction unit that extracts from the report a first item which is an evaluation item related to the content of the analytical case reported in the report, a second item which is an evaluation item related to the volume of the report, and a third item which is an evaluation item related to the type of target sample of the analytical case reported in the report; an evaluation information storage unit that stores evaluation scores for evaluating the report for each of the first item, the second item, and the third item; and a calculation unit that tallies the evaluation scores for each of the first item, the second item, and the third item extracted by the extraction unit, and evaluates the report based on the tallied results.

[0010] Furthermore, the present invention, which has been made to solve the above-mentioned problems, is an evaluation method for evaluating reports of analytical cases published on a website, comprising: collecting reports of analytical cases from the website; extracting from the reports a first item which is an evaluation item related to the content of the analytical case reported in the report, a second item which is an evaluation item related to the volume of the report, and a third item which is an evaluation item related to the type of target sample of the analytical case reported in the report; aggregating evaluation scores for the first item, the second item, and the third item extracted by the extraction unit based on the contents stored in an evaluation information storage unit which stores evaluation scores for evaluating the report for each of the first item, the second item, and the third item; and evaluating the report based on the aggregation results of the evaluation scores.

[0011] Furthermore, the present invention, which has been made to solve the above-mentioned problems, is an evaluation program that causes a computer having an evaluation information storage unit to execute a process of evaluating reports of analytical cases published on a website, the program comprising: collecting reports of analytical cases from the website; extracting from the reports a first item that is an evaluation item related to the content of the analytical case reported in the report, a second item that is an evaluation item related to the volume of the report, and a third item that is an evaluation item related to the type of target sample of the analytical case reported in the report; tallying up the evaluation scores for the first item, the second item, and the third item extracted by the extraction unit based on the contents stored in the evaluation information storage unit, which stores evaluation scores for evaluating the report for each of the first item, the second item, and the third item; and evaluating the report based on the results of the evaluation score aggregation.

[0012] In the present invention, "reports of analytical cases published on a website" refer to documents describing analytical cases performed using a specified analytical device, such as the analytical device's operating procedures, the types of samples to be analyzed and their preparation methods, the analytical results, and precautions for using the analytical device. These documents generally refer to documents called application notes or application reports published on the websites of the manufacturers or distributors of the specified analytical devices. In the case of application notes or application reports as reports of analytical cases, the report contains information such as the type of analytical device and the types of samples to be analyzed used in the analytical case, tables and graphs showing the analytical results, and reference technical literature. Therefore, the report can be an important technical document for users of the analytical device. Furthermore, the report is useful for those considering purchasing an analytical device to evaluate the analytical device.

[0013] According to the present invention, it is possible to correctly evaluate reports that report analysis cases, such as application notes and application news published on websites.

[0014] FIG. 1 is a schematic configuration diagram of an evaluation system according to an embodiment of the present invention. FIG. 2 is a diagram showing an example of an analysis case report. FIG. 3 is a diagram explaining the contents of first to third items stored in an evaluation information storage unit and the evaluation scores for each item. FIG. 4 is a flowchart of evaluation processing. FIG. 5 is a diagram showing a table that is an example of an output of evaluation results. FIG. 6 is a diagram showing a radar chart that is an example of an output of evaluation results.

[0015] An embodiment of the present invention will now be described with reference to the drawings. Fig. 1 is a diagram showing a schematic configuration of an evaluation system according to this embodiment. The evaluation system 1 shown in Fig. 1 has a configuration in which a plurality of server devices 2 and an evaluation device 3 installed by a plurality of analytical device makers (manufacturing makers, sales makers) are connected via a network 4 so that they can send and receive information to and from each other.

[0016] The server device 2 executes processing for analytical device manufacturers to publish websites on the network 4, and stores company information to be posted on the websites. It also executes processing for publishing company information including analysis case reports.

[0017] Here, an analytical case report is a report on an analytical case performed using an analytical device manufactured or sold by an analytical device manufacturer, and is also called application news or application notes. An analytical case report includes an analytical report, the name of the author and the date and time of creation of the analytical report, and the names of academic papers and patent documents related to the analytical case. The analytical report includes a description explaining the content of the analytical case, graphs, tables, images, etc. showing the analysis results, and the description includes the analytical device and the name and type of sample analyzed. Figure 2 shows an example of an analytical case report. This analytical case report consists of two pages, with the first page listing the title of the analytical report, the name of the author, and the date and time of creation. The first and second pages contain an analytical report consisting of a description explaining the content of the analytical case, graphs and tables showing the analysis results, and the second page listing the names of academic papers and patent documents related to the analytical case, as well as the name of the analytical device manufacturer providing the analytical case report.

[0018] The evaluation device 3 is a general-purpose computer, a workstation, a desktop personal computer (PC), a notebook PC, or the like, and includes a control unit 30, a communication unit 31, a memory unit 32, a report collection unit 33, an extraction unit 34, a calculation unit 35, a display unit 36, and an input unit 37. The display unit 36 ​​is, for example, a liquid crystal display, and outputs the evaluation results. The input unit 37 is made up of input devices such as a keyboard and a mouse.

[0019] The communication unit 31 controls connection and communication with the network 4. The extraction unit 34 extracts, from the case report to be evaluated, an evaluation item (first item) related to the content of the analytical case reported in the report, an evaluation item (second item) related to the volume of the report, and an evaluation item (third item) related to the type of target sample of the analytical case reported in the report.

[0020] The storage unit 32 includes a report storage unit 321 and an evaluation information storage unit 322. The report storage unit 321 stores analysis case reports to be searched. The evaluation information storage unit 322 stores information on the evaluation items (first to third items) and evaluation scores used to evaluate analysis case reports for each of the first item, the second item, and the third item. The report collection unit 33 collects analysis case reports from various analysis manufacturers that are published on websites via the network 4.

[0021] The input unit 37 is operated to input a search string (search keyword) into the report collection unit 33, which is the content of the analytical case report to be evaluated, such as the analytical device used in the analytical case, the analytical sample, the name of the report creator, etc., expressed in natural language such as characters and sentences. The report collection unit 33 searches for analytical case reports published on websites via the network 4 based on a pre-defined search dictionary for the input search keyword, and collects the analytical case report to be evaluated. The collected analytical case reports are stored in the report storage unit 321. Note that in this embodiment, the search for analytical case reports not only involves a simple keyword match search, but also uses semantic search technology that interprets the content of the analytical case to be investigated from the search keyword.

[0022] The evaluation scores stored in the evaluation information storage unit 322 will now be described. In the evaluation system 1 of this embodiment, the analytical case report to be evaluated is evaluated based on predetermined evaluation items. The evaluation items include three main items: the first item is an evaluation item related to the content of the analytical case reported in the analytical case report, the second item is an evaluation item related to the volume of the analytical case report, and the third item is an evaluation item related to the type of target sample of the analytical case reported in the analytical case report.

[0023] Examples of the first item include the technical field of the analytical case reported in the analytical case report, whether or not a third party is involved in the analytical case, the target market for the analytical equipment used in the analytical case, and the purpose of the analytical case (e.g., regulatory compliance). Examples of the second item include the number of authors of the analytical case report, the number of pages of the analytical case report, and the number of academic and patent literature cited in the analytical case report. Examples of the third item include the attention level of the samples used in the analytical case reported in the analytical case report (e.g., samples containing environmental pollutants or substances that are considered rare and useful resources are considered to be of high attention), and corporate social responsibility (CSR). CSR refers to corporate behavior that takes responsibility for the impact a company has on society and the environment.

[0024] Therefore, the evaluation information storage unit 322 stores the contents of the first to third items and the evaluation scores for each item in association with each other. Figure 3 is a diagram explaining the contents of the first to third items stored in the evaluation information storage unit 322 and the evaluation scores for each item. In Figure 3, "strong indicator," "slightly strong indicator," and "weak indicator" roughly correspond to the first item, the second item, and the third item, respectively. As an exception, the number of pages of the analysis case report corresponds to the second item, but is included in "strong indicator."

[0025] Each indicator is weighted according to its importance and assigned an evaluation score. For the second item, a conversion rate (0.1, 0.2, 0.5, etc.) is set according to its content. For example, in the case of the number of pages of case study reports, the actual number is multiplied by 0.1 to obtain the evaluation score.

[0026] In FIG. 3, the "hot words" included in the "slightly strong indicators" refer to words that express the technical quality of the analysis case, such as "new, novel," "unique," and "first." In addition to these words, hot words also include "singular, singularity," "inventive, patentable," and the like. Hot words are search keywords used to evaluate analysis case reports, separate from the first to third items. Evaluation scores are also associated with the hot words and stored in the evaluation information storage unit 322.

[0027] Next, the evaluation process in the evaluation system of this embodiment will be described using the flowchart in Figure 4. First, when a user operates the input unit 37 to input a search keyword, the report collection unit 33 searches for analytical case reports published on websites via the network 4 and collects analytical case reports of the evaluation target (step 1). The number of analytical case reports collected may be one or more. The collected analytical case reports are stored in the report storage unit 321.

[0028] Next, the extraction unit 34 reads the analysis case report from the report storage unit 321 and extracts the first to third items and hot words from the analysis case report (step 2). The above-mentioned semantic search technology is used to extract the first to third items, and so-called keyword search technology is used to extract the hot words. The first to third items and hot words extracted by the extraction unit 34 are input to the calculation unit 35.

[0029] The calculation unit 35 reads from the evaluation information storage unit 322 the evaluation scores stored in association with the input first to third items and hot words, and totals them (step 3). For example, in FIG. 3, if, among the items included in "strong indicators," the type is B-B-B, the market is environmental (market), the number of sheets is two, and regulatory compliance is "yes," the evaluation scores are 4 points, 0.6 points, 0.2 points, and 2 points, for a total of 6.8 points. Similarly, for "slightly strong indicators" and "weak indicators," the evaluation scores associated with the extracted items and hot words are read from the evaluation information storage unit 322 and totaled, and the total value of the evaluation scores for all indicator items becomes the evaluation score for the analysis case report.

[0030] The evaluation score aggregation process is performed on all analytical case reports read by the extraction unit 34. Once the aggregated evaluation scores for all analytical case reports have been calculated (Yes in step 4), the calculation unit 35 ranks each analytical case report (step 5). This ranking can be performed by sorting the analytical case reports in descending order of evaluation score. In addition to ranking, the calculation unit 35 may also calculate the highest aggregated evaluation score value for multiple analytical case reports, divide the highest value by each aggregated evaluation score value, and multiply the result by 100 to calculate the relative value of the aggregated evaluation score value. By using the highest aggregated evaluation score value for analytical case reports collected over a period such as a quarter, half year, or year, the relative value of the aggregated evaluation score value for analytical case reports published on the website during each period can be calculated.

[0031] When the calculation unit 35 calculates the total value of the evaluation scores for each analytical case report, the control unit 30 displays the results on the display unit 36 ​​as a table, for example, as shown in Fig. 5. By looking at this table, the user can know the evaluation score for each item of each analytical case report, the total value of the evaluation scores, and the rank (score).

[0032] Furthermore, as a result of the evaluation process by the calculation unit 35, it is also possible to display the evaluation results of the analytical case report of each analytical device manufacturer, for example, in a radar chart such as that shown in Fig. 6. From such a radar chart, each analytical device manufacturer can determine at a glance which evaluation items their analytical device report is strong in and which evaluation items it is weak in, which can be useful in formulating their own marketing strategies.

[0033] Aspects It will be apparent to those skilled in the art that the exemplary embodiments described above are examples of the following aspects.

[0034] (Item 1) One aspect of the present invention is an evaluation device that evaluates reports of analytical cases published on a website, and includes an extraction unit that extracts from the report a first item that is an evaluation item related to the content of the analytical case reported in the report, a second item that is an evaluation item related to the volume of the report, and a third item that is an evaluation item related to the type of target sample of the analytical case reported in the report; an evaluation information storage unit that stores evaluation scores for evaluating the report for each of the first item, the second item, and the third item; and a calculation unit that tallies the evaluation scores for each of the first item, the second item, and the third item extracted by the extraction unit, and evaluates the report based on the tallied results.

[0035] The evaluation device according to the first aspect can correctly evaluate reports that report analysis cases, such as application notes and application news published on websites.

[0036] (Clause 2) The evaluation device according to paragraph 2 is the evaluation device according to paragraph 1, further comprising a report collection unit that collects a plurality of reports that are published on a website during a predetermined period, wherein the extraction unit extracts the first item, the second item, and the third item for each of the plurality of reports collected by the report collection unit, and the calculation unit tally up evaluation scores for each of the first item, the second item, and the third item extracted by the extraction unit for each of the plurality of reports, and relatively evaluates each report based on the total value of the evaluation scores for each of the plurality of reports.

[0037] (Clause 3) The evaluation device according to clause 3 is the evaluation device according to clause 1 or 2, wherein the first item includes evaluation items related to the technical field of the analysis case, the market size of the analytical device used in the analysis case, and the purpose of the analysis case, where an example of the purpose of the analysis case is whether or not the analysis case is for compliance with regulations.

[0038] (4) The evaluation device according to paragraph 4 is the evaluation device according to any one of paragraphs 1 to 3, wherein the second item includes evaluation items relating to the number of pages of the report, the number of authors of the report, and the number of documents cited in the report.

[0039] (5) The evaluation device according to 5 is the evaluation device according to any one of 1 to 4, wherein the extraction unit is configured to extract words and phrases expressing technical qualities of the analysis case from the report, and the calculation unit evaluates the report based on the counting result and the number of the words and phrases extracted from the report. Examples of words and phrases expressing technical qualities include singular, singularity, new, novel, unique, inventive, patentable, etc.

[0040] (Section 6) Another aspect of the present invention is an evaluation method for evaluating reports of analytical cases published on a website, comprising: collecting reports of analytical cases from the website; extracting from the reports a first item that is an evaluation item related to the content of the analytical case reported in the report, a second item that is an evaluation item related to the volume of the report, and a third item that is an evaluation item related to the type of target sample of the analytical case reported in the report; aggregating evaluation scores for the first item, the second item, and the third item extracted by the extraction unit based on the contents stored in an evaluation information storage unit that stores evaluation scores for evaluating the report for each of the first item, the second item, and the third item; and evaluating the report based on the aggregation of the evaluation scores.

[0041] (Section 7) Another aspect of the present invention is an evaluation program that causes a computer having an evaluation information storage unit to execute a process of evaluating reports of analytical cases published on a website, the evaluation program comprising: collecting analytical case reports from the website; extracting from the reports a first item that is an evaluation item related to the content of the analytical case reported in the report, a second item that is an evaluation item related to the volume of the report, and a third item that is an evaluation item related to the type of target sample of the analytical case reported in the report; tallying up evaluation scores for the first item, the second item, and the third item extracted by the extraction unit based on the contents stored in the evaluation information storage unit, which stores evaluation scores for evaluating the report for each of the first item, the second item, and the third item; and causing the computer to execute a process of evaluating the report based on the tallying results of the evaluation scores.

[0042] REFERENCE SIGNS LIST 1 evaluation system 2 server device 3 evaluation device 30 control unit 31 communication unit 32 storage unit 321 report storage unit 322 evaluation information storage unit 33 report collection unit 34 extraction unit 35 calculation unit 36 ​​display unit 37 input unit 4 network

Claims

1. An evaluation device for evaluating reports of analytical cases published on a website, comprising: an extraction unit that extracts from the report a first item that is an evaluation item related to the content of the analytical case reported in the report, a second item that is an evaluation item related to the volume of the report, and a third item that is an evaluation item related to the type of target sample of the analytical case reported in the report; an evaluation information storage unit that stores evaluation scores for evaluating the report for each of the first item, the second item, and the third item; and a calculation unit that tallies the evaluation scores for each of the first item, the second item, and the third item extracted by the extraction unit, and evaluates the report based on the tallied results.

2. An evaluation device according to claim 1, further comprising a report collection unit that collects a plurality of reports published on a website during a predetermined period, wherein the extraction unit extracts the first item, the second item, and the third item for each of the plurality of reports collected by the report collection unit, and the calculation unit tally up the evaluation scores for each of the first item, the second item, and the third item extracted by the extraction unit for each of the plurality of reports, and relatively evaluates each report based on the total value of the evaluation scores for each of the plurality of reports.

3. The evaluation device according to claim 1, wherein the first item includes evaluation items relating to the technical field of the analysis case, the market size of the analytical device used in the analysis case, and the purpose of the analysis case.

4. An evaluation device according to claim 1, wherein the second item includes evaluation items relating to the number of pages of the report, the number of authors of the report, and the number of documents cited in the report.

5. An evaluation device according to claim 1, wherein the extraction unit is configured to extract words and phrases expressing the technical quality of the analysis case from the report, and the calculation unit evaluates the report based on the aggregation result and the number of words and phrases extracted from the report.

6. A method for evaluating reports of analytical cases published on a website, comprising: collecting reports of analytical cases from the website; extracting from the reports a first item that is an evaluation item related to the content of the analytical case reported in the report, a second item that is an evaluation item related to the volume of the report, and a third item that is an evaluation item related to the type of target sample of the analytical case reported in the report; aggregating the evaluation scores for the first, second, and third items extracted by the extraction unit based on the contents stored in an evaluation information storage unit that stores evaluation scores for evaluating the report for each of the first, second, and third items; and evaluating the report based on the aggregation of the evaluation scores.

7. An evaluation program that causes a computer having an evaluation information storage unit to execute a process for evaluating reports of analytical cases published on a website, the evaluation program comprising: collecting analytical case reports from the website; extracting from the reports a first item that is an evaluation item related to the content of the analytical case reported in the report, a second item that is an evaluation item related to the volume of the report, and a third item that is an evaluation item related to the type of target sample of the analytical case reported in the report; tallying up the evaluation scores for the first item, second item, and third item extracted by the extraction unit based on the contents stored in the evaluation information storage unit, which stores evaluation scores for evaluating the report for each of the first, second, and third items; and evaluating the report based on the results of the tallying of the evaluation scores.

Images