Evaluation System and Evaluation Program

Abstract

To provide an evaluation system and evaluation program capable of accurately evaluating a business plan with a small burden by using a plurality of evaluation criteria. [Solution] An evaluation system that evaluates a business plan using multiple evaluation criteria comprises a plan input unit 11 for inputting the business plan, a criteria input unit 12 for inputting the evaluation criteria, an evaluation level calculation unit 20 that uses the input business plan and evaluation criteria to calculate an evaluation level for each evaluation criterion for the business plan, and an evaluation unit 30 that makes a final evaluation of the business plan based on the evaluation level.

Description

[Technical field]

[0001] The present invention relates to an evaluation system that evaluates a business plan using a plurality of evaluation criteria, and an evaluation program that causes a computer to execute such an evaluation. [Background technology]

[0002] The business plan creation support system according to Patent Document 1 stores regional information and multiple case information of businesses created for each region, acquires indicators for the problems to be solved by the business plan, extracts case information with common indicators from the case information as recommended case information, and generates and outputs information based on business evaluation items that indicate business results from the recommended case information. Furthermore, the business plan creation support system generates an evaluation model trained from learning data in which one of the business evaluation items is a response variable and the other business evaluation items are explanatory variables based on the recommended case information, and outputs the value of the response variable obtained by inputting the value of the business evaluation item of the business plan as an explanatory variable into the evaluation model.

[0003] The language production ability evaluation system according to Patent Document 2 includes an evaluation object acquisition unit that accepts user input including a question and an evaluation object, an evaluation criterion acquisition unit that acquires evaluation criteria for a language ability evaluation test, a prompt provision unit that provides a prompt including the user input and instructions and explanations for the generation AI to the generation AI, an answer acquisition unit that acquires an answer to the prompt from the generation AI, and an evaluation display unit that displays an evaluation of the evaluation object included in the answer. The instructions that make up the prompt include a role assignment instruction that assigns the generation AI a role as an evaluator for the language ability evaluation test, an evaluation creation instruction that causes the generation AI to evaluate the evaluation object based on the evaluation criteria, and a confirmation instruction that causes the evaluation in the evaluation creation instruction to be confirmed to be based on the evaluation criteria. Furthermore, the explanation that makes up the prompt includes an explanation of the evaluation criteria and an explanation of an evaluation method based on the evaluation criteria. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2024-011875 A [Patent Document 2] Patent No. 7521860 Summary of the Invention [Problem to be solved by the invention]

[0005] In the business planning support system described in Patent Document 1, it is necessary to construct a learning model that is trained using learning data in which one of the business evaluation items is used as the objective variable and the other business evaluation items are used as explanatory variables. However, if there are many business evaluation items, creating the learning data imposes a large burden.

[0006] In the language production ability evaluation system of Patent Document 2, evaluation information for the evaluation target is obtained from the generation AI by giving a prompt, so the preparation work burden for the evaluation is small. In particular, in language production ability evaluation such as the English Proficiency Test, the evaluation criteria are limited to language production ability and are relatively simple because they are well-known criteria. However, if the evaluation target is a business plan, the items that make up the business plan and the items of the evaluation criteria are complex, and it is difficult to apply the evaluation technology shown in Patent Document 2 to the evaluation of a business plan as it is.

[0007] In view of the above-mentioned circumstances, an object of the present invention is to provide an evaluation system that can accurately evaluate a business plan using multiple evaluation criteria with little burden. [Means for solving the problem]

[0008] The evaluation system according to the present invention is a system for evaluating a business plan using a plurality of evaluation criteria, and includes a plan input unit for inputting the business plan, a criterion input unit for inputting the evaluation criteria, an evaluation level calculation unit for calculating an evaluation level for the business plan for each of the evaluation criteria using the input business plan and the evaluation criteria, and an evaluation unit for making a final evaluation of the business plan based on the evaluation levels. 、 The evaluation level calculation unit generates plan vector data by vector-representing sentences constituting the business plan, and generates criterion vector data by vector-representing sentences constituting the evaluation criteria; A classification area corresponding to the evaluation level is set in a vector space in which a data group consisting of the plan vector data and the reference vector data is scattered, and a similarity between the business plan and each of the evaluation criteria is calculated based on the distance between the data group contained in each classification area and each classification area, and the evaluation level is calculated based on the similarity.

[0009] According to this configuration, a plurality of evaluation criteria are prepared for use in evaluating a business plan, and the business plan to be evaluated is evaluated for each evaluation criterion, and each evaluation level is calculated. Even if a business plan contains many contents, the evaluation workload is small if it is evaluated using one evaluation criterion. Furthermore, the final evaluation of the business plan is determined based on all the evaluation levels calculated for each evaluation criterion, so that the business plan is checked from every perspective, and the final evaluation is accurate.

[0010] In order to check whether the business plan meets the evaluation criteria, it is preferable to check the similarity between the sentences included in the business plan and the sentences included in the evaluation criteria. If the sentences are expressed as vectors, the similarity between sentences can be calculated by vector operations such as an inner product operation. If a technique such as "Word Embedding" is used to express the sentences as vectors, it is also convenient for the subsequent evaluation process (natural language processing). For this reason, in the present invention, it is proposed that the evaluation level calculation unit generates plan vector data by vector-expressing the sentences constituting the business plan, generates reference vector data by vector-expressing the sentences constituting the evaluation criteria, and calculates the evaluation level based on the similarity between the business plan and each of the evaluation criteria calculated using the plan vector data and the reference vector data.

[0011] In order to calculate the similarity (degree of satisfaction of the evaluation criteria) between the business plan and each evaluation criterion using the plan vector data and the reference vector data, a classification method such as the K-means method is advantageous because it enables quantitative consideration (such as Euclidean distance from the representative point of the cluster) of the calculated cluster (corresponding to the evaluation level). For this reason, in the present invention, it is proposed that the evaluation level is represented by a plurality of clusters divided in a vector space including the plan vector data and the reference vector data, and the evaluation level is calculated through the calculation of the distribution state of the cluster. The evaluation level of the business plan is calculated from the distribution state of each of the clusters. For example, the K-means method can be used to classify vector data into a plurality of clusters (evaluation levels), and the vector data can be classified into each cluster (each evaluation level).

[0012] As described above, the calculation of the evaluation level for the business plan using the plan vector data and the reference vector data can be performed relatively easily and with high accuracy by using various generating AIs if an appropriate prompt is created. For this reason, in the present invention, it is proposed that the evaluation level calculation unit is configured using a generating AI, and the business plan and the evaluation criteria are given to the generating AI as prompts.

[0013] Recently, one of the business plans that has been the subject of debate due to the difficulty of its evaluation is a business plan that generates carbon credits. Carbon credits are a mechanism that allows companies to trade the amount of greenhouse gas emission reductions between each other, and companies can quantify the amount of greenhouse gas reduction or absorption generated by environmental activities, and trade the emission rights certified as carbon credits with other companies. For this reason, business plans related to carbon credits need to be evaluated from multiple angles, and the number of items in the evaluation criteria increases, so the evaluation is important. In addition, the evaluation criteria include those formulated by each country and the unique criteria and know-how of each company. For this reason, in the present invention, the business plan is a business plan for acquiring carbon credits, and the evaluation criteria include general evaluation criteria created in accordance with the carbon credit certification criteria and unique evaluation criteria created independently. This allows business plans that generate carbon credits to be accurately evaluated with little burden.

[0014] Since carbon credits are traded between companies or brokers, the trading value of the carbon credits to be generated is important in a business plan for generating carbon credits. Therefore, the high trading value of the carbon credits to be generated may be added as an evaluation criterion. For this reason, the present invention also proposes that the final evaluation of a business plan for acquiring carbon credits be influenced by the trading value of the carbon credits.

[0015] The scope of the present invention also includes an evaluation program that causes a computer to execute a process for evaluating a business plan using a plurality of evaluation criteria. Such an evaluation program causes a computer to execute a plan input process for inputting the business plan, a criterion input process for inputting the evaluation criteria, an evaluation level calculation process for calculating an evaluation level for the business plan for each of the evaluation criteria using the input business plan and the evaluation criteria, and an evaluation process for making a final evaluation of the business plan based on the evaluation levels. 、 The evaluation level calculation process generates plan vector data by vector-representing sentences constituting the business plan, and generates criterion vector data by vector-representing sentences constituting the evaluation criteria, A classification area corresponding to the evaluation level is set in a vector space in which a data group consisting of the plan vector data and the reference vector data is scattered, a similarity between the business plan and each of the evaluation criteria is calculated based on a distance between the data group included in each of the classification areas and each of the classification areas, and the evaluation level is calculated based on the similarity. do. Each process carried out during execution provides the various effects described in the evaluation system above.

[0016] Other features, operations, and advantages of the present invention will become apparent from the following description of the invention using the accompanying drawings. [Brief description of the drawings]

[0017] [Figure 1] FIG. 1 is a schematic diagram showing a schematic configuration of an evaluation system. [Diagram 2] 1 is a flowchart showing a process flow when a business plan is quantitatively evaluated. [Diagram 3] FIG. 1 is a document diagram illustrating an example of a prompt. [Figure 4] FIG. 1 is an explanatory diagram for explaining classification of evaluations using the K-means method. [Diagram 5] 1 is a table listing the evaluation levels for each evaluation criterion for multiple business plans. [Figure 6] This is a list of evaluation levels for multiple business plans. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0018] First, the schematic configuration of the evaluation system according to the present invention will be described with reference to Fig. 1. This evaluation system evaluates a business plan using multiple evaluation criteria. This system includes a plan input unit 11, a criterion input unit 12, an evaluation level calculation unit 20, and an evaluation unit 30.

[0019] The plan input unit 11 converts the input business plan into data that can be processed by the evaluation level calculation unit 20, and provides the data to the evaluation level calculation unit 20. The criteria input unit 12 converts evaluation criteria used when evaluating the business plan into data that can be processed by the evaluation level calculation unit 20, and provides the data to the evaluation level calculation unit 20. The evaluation criteria may have from several items to more than several hundred items, and these items may be summarized by one or more documents.

[0020] The evaluation level calculation unit 20 is a core component of the evaluation system, and is substantially constructed using a computer unit, and calculates an evaluation level for each evaluation criterion for the business plan using a given business plan and evaluation criteria. For this reason, the evaluation level calculation unit 20 includes, as functional units, an instruction generation unit 21, a vector representation module 22, and a calculation unit 23. Note that at least some of the processes in each component constituting the evaluation system are substantially realized by a computer by executing a computer program.

[0021] The command generation unit 21 (prompt generation unit 21) functions as an interface that receives instructions from a user and generates a command script for the calculation unit 23 of this evaluation system. The command script for the calculation unit 23 generated by the command generation unit 21 includes the user's instructions, the contents of the business plan, and the contents of the evaluation criteria. Examples of the user's instructions include "The document to be input is a report on a carbon credit project," "For each criterion, find a statement that serves as evidence for the question of whether this project complies with the criterion," and "Output the obtained evidence in strict compliance with the output format."

[0022] The vector representation module 22 generates plan vector data by vector-representing sentences (including words and phrases) constituting the business plan included in the instruction script, and similarly generates reference vector data by vector-representing sentences constituting the evaluation criteria included in the instruction. For vector representation of sentences, for example, a Word Embedding technique used in BERT (Bidirectional Encoder Representations from Transformers) is used. The generated plan vector data and reference vector data are provided to the calculation unit 23 together with the user's instructions.

[0023] The calculation unit 23 calculates an evaluation level of the input business plan by using the plan vector data and the reference vector data and calculating a similarity indicating the degree of fulfillment of each evaluation criterion in the business plan with reference to a user instruction. The similarity can be calculated by a technique of determining the similarity between each sentence of the plan vector data and each sentence of the reference vector data by vector calculation (e.g., inner product calculation). The evaluation level is calculated for each of multiple criterion items included in the evaluation criteria. Here, the evaluation level can be regarded as a collection of evaluation levels for each criterion item.

[0024] The evaluation unit 30 performs a final evaluation of the business plan to be evaluated based on the evaluation level, which is the calculation result of the calculation section 23, i.e., the output of the evaluation level calculation unit 20, and outputs the business plan final evaluation. The evaluation unit 30 may be incorporated into the evaluation level calculation unit 20 as one of the functional parts of the evaluation level calculation unit 20.

[0025] The vector representation module 22 and the evaluation level calculation unit 20 may be integrated as a generation AI 25. In that case, the instruction generation unit 21 functions as a prompt generation unit 21. Furthermore, the generation AI 25 may also incorporate the function of an evaluation unit 30. Moreover, the evaluation unit 30 may be configured as an independent machine learning model independent of the generation AI 25.

[0026] Next, one embodiment of the evaluation system of the present invention will be described. In this embodiment, the evaluation system evaluates a business plan for acquiring carbon credits based on carbon credit evaluation criteria. The evaluation level calculation unit 20 of this evaluation system includes a generation AI 25 that outputs an evaluation level when given a prompt generated by a prompt generation unit 21. The carbon credit evaluation criteria include general evaluation criteria created according to carbon credit certification criteria and unique evaluation criteria created independently.

[0027] Carbon credits are emission rights that companies and individuals can acquire by funding projects that reduce greenhouse gas emissions, and the value of the emission rights corresponds to the amount of greenhouse gas reduction. Since such greenhouse gas emission projects (hereinafter simply referred to as projects) require large investments, it is important to carefully examine the project proposal in advance to see whether the carbon credits generated by the project have appropriate value. Project proposals include project proposals related to reducing greenhouse gas emissions from paddy fields, project proposals related to afforestation and deforestation control, project proposals related to biochar, etc., and such project proposals are the business plans of the present invention. In the examples shown in Figures 3 and 6, a project proposal related to biochar is handled as the business plan, but of course the business plan of the present invention is not limited to a project proposal related to biochar.

[0028] Figure 2 shows the process flow when a business plan and a forest business plan, which are project proposals related to biochar, are quantitatively evaluated by the evaluation system. This evaluation system also makes it possible to sequentially evaluate various business plans using the same evaluation criteria. In the following explanation, a business plan, which is a project proposal related to biochar, is dealt with.

[0029] A business plan for a biochar project to be evaluated is created by the user. At the same time, the user creates carbon credit evaluation criteria (hereinafter simply referred to as evaluation criteria) for evaluating this business plan. The created business plan and evaluation criteria are converted into text data and provided to the evaluation system.

[0030] The evaluation criteria consist of over 100 items, some examples of which are as follows: (1) The raw material must be purely biological waste biomass and not cultivated for any particular purpose. (2) The raw materials are left to rot or be burned for purposes other than energy production. (3) Biochar is expressed in dry tons. Care must be taken to avoid adding moisture, which will overestimate carbon sequestration. (4) The biomass used must be free of paint residues, solvents, and other potentially toxic impurities. (5) The raw materials must not be imported from other countries.

[0031] The evaluation system can generate a prompt using a given business plan and evaluation criteria, but the prompt may be created by a user using a user interface of the prompt generation unit 21 and given to the evaluation system. In this embodiment, the generation AI 25 is constructed using an LLM (large-scale language model), so a prompt suitable for the specifications of this LLM is generated. An example of such a prompt is shown in FIG. 3. In the example of FIG. 3, the prompt generation unit 21 generates a prompt based on an instruction (user's instruction content), a business plan, and evaluation criteria given by a user via the Internet or the like. Here, the prompt is written in English to improve the output accuracy of the generation AI 25. Of course, the prompt may be written in Japanese.

[0032] When the amount of data of the business plan to be input is large, the document file name designated to be read from an appropriate memory is entered in the prompt. When the number of items of the input evaluation criteria is large, prompts including a predetermined number of items of the evaluation criteria are sequentially given to the generation AI 25, and the multiple output results output from the generation AI 25 are integrated.

[0033] The extent to which a business plan meets the evaluation criteria is judged based on the similarity between the business plan and each evaluation criterion item (the degree to which the business plan satisfies the evaluation criteria). As a result of this judgment, the evaluation level, which is the degree to which the business plan meets each evaluation criterion, is set to the following six evaluation levels: "Yes", "Likely Yes", "Likely No", "No", "Irrelevant", and "Not Mentioned".

[0034] In this evaluation system, to make a judgment based on similarity, the closeness (similarity: distance) of each piece of data in the vector space of the vector data of the sentences that make up the business plan (plan vector data) and the vector data of the sentences that make up the evaluation criteria (evaluation criteria vector data) is used. In other words, each piece of data is classified into clusters based on the evaluation levels of "Yes", "Likely Yes", "Likely No", "No", "Irrelevant", and "Not Mentioned". In other words, the classification of each vector data into a specific cluster (specific evaluation level) is calculated based on the distribution state of the vector data group for each cluster in the vector space. The K-means method is used for this classification.

[0035] In this embodiment, as shown in Fig. 4, the classification by the K-means method is performed by setting six classification areas (corresponding to evaluation levels) corresponding to "Yes", "Likely Yes", "Likely No", "No", "Irrelevant", and "Not Mentioned" in a vector space in which data groups consisting of plan vector data and reference vector data are scattered, classifying data groups into each classification area, and calculating the distance (Euclidean distance: L2 distance) between the center of gravity of the data group contained in each classification area and the center of gravity of each classification area, which distance quantitatively supports the calculation of the evaluation level. To explain in more detail, for example, classification is performed according to the following procedure. (1) A description of each piece of evidence is converted into a vector representation to generate a set of vector data; (2) Cluster the vector data into each classification region. (3) Calculate the centroid vector of the cluster for each classification region; (4) For each evidence description, the classification area of ​​the cluster with the smallest Euclidean distance among the centroid vectors calculated in (3) is used as the classification using the K-means method.

[0036] For this reason, the prompt includes output instructions such as six rating levels, a description of the evidence on which such ratings are based, and so on.

[0037] The evaluation unit 30 evaluates the value (quality) of the business plan being evaluated based on the evaluation level calculated for each of more than 100 evaluation criteria, and generates evaluation data (evaluation report) including the carbon credit value of the business plan.

[0038] Figure 5 shows a table output as a reference example showing six levels of evaluation for multiple evaluation criteria for multiple business plans. In this reference example, the data group subject to the K-means method is vector data obtained by vectorizing the text (evidence) extracted as the basis for evaluation calculation, output by the generation AI. Examples of text extracted as the basis for evaluation calculation are as follows: (1) A certain company uses a batch method for charcoal production. The kilns are filled with firewood, the combustion chamber is sealed, and pyrolysis takes place in each kiln. During the cooling stage, heat is dissipated through the walls and top of the kiln, allowing it to cool. After cooling, the combustion chamber is opened and the charcoal is processed for transportation. (2) There is no mention of the moisture content of biochar to prevent dust generation or explosion during transportation. (3) The document does not provide details about the moisture content of biochar to prevent dust and explosion during transportation. (4) Moisture content of each large bag is measured to confirm that it is between 20% and 30%. (5) The document does not provide information on transporting biochar over 200 km and associated greenhouse gas emissions.

[0039] In the table in Figure 5, each column item indicates the document number that specifies the business plan, and each row item indicates the evaluation criterion item number that specifies the evaluation criterion item. For example, each cell in the second column displays the evaluation level of each evaluation criterion item for the business plan of document number 2, and the cell in row 2, column 2 (2,2) displays "Likely Yes" as the evaluation level of evaluation criterion item 2 for the business plan of document number 2.

[0040] The evaluation unit 30 can also estimate the trading value of carbon credits for each business plan based on the evaluation level data as shown in FIG. 5, and generate a comprehensive evaluation report showing the value ranking.

[0041] In the table output shown as a reference example in Figure 6, the vertical columns are the same as in Figure 5, with the first cell in the row (Document iD) indicating the document number that specifies the business plan, the second cell in the row (labeled class) indicating the evaluation level of the business plan, the third cell in the row (evidence) indicating the text (evidence) extracted as the basis for the evaluation calculation, the fourth cell in the row (matched) indicating the agreement (TRUE) or disagreement (FALSE) between the evaluation by the generation AI and the evaluation by the K-means method, the fifth cell in the row (K-means classification) indicating the evaluation level by the K-means method, and the sixth cell in the row (L2 distance) indicating the distance value calculated by the K-means method. The fifth cell in the row indicates the evaluation level that was ranked first in the K-means method, and the sixth cell in the row indicates the distance value as the basis for the first place. The seventh and subsequent cells in the row sequentially indicate the evaluation levels and distance values ​​from the second place onwards in the K-means method. The final evaluation of the business plan is the evaluation level that is ranked first, and in Figure 6, the final evaluation of the business plan shown in document number 1 is "Yes." At that time, the evaluation levels and distance values ​​from the second place onwards are also shown, making it possible to quantitatively consider the final evaluation.

[0042] [Another embodiment] (1) In the above embodiment, the evaluation system is shown to be configured as an integrated system, but these components may be distributed via a network, and the evaluation system may be configured as a distributed system. For example, the prompt generation unit 21 of the evaluation level calculation unit 20 may be constructed in a user terminal, and the generation AI 25 of the evaluation level calculation unit 20 and the evaluation unit 30 may be constructed in a remote cloud computing service, and the final evaluation result may be sent to the user terminal. Also, the generation AI 25 may be constructed in another server or user terminal.

[0043] (2) The evaluation unit 30 can be configured integrally with the generation AI 25, but it may also be constructed as a machine learning model that uses various data outputs from the generation AI 25 (e.g., list data such as those shown in Figures 5 and 6) as input data and outputs a final result indicating the value ranking of the business plan.

[0044] (3) In the above-described embodiment, a business plan related to a biochar project was mainly taken up as an embodiment of a business plan, but the present invention is not limited to this, and the evaluation system of the present invention can be applied with similar advantages to various business plans such as plans for energy conservation-related projects and plans for food self-sufficiency projects.

[0045] In addition, the configurations disclosed in the above embodiments (including other embodiments, the same applies below) can be applied in combination with configurations disclosed in other embodiments, provided no contradiction arises. Furthermore, the embodiments disclosed in this specification are illustrative, and the embodiments of the present invention are not limited thereto, and can be appropriately modified within the scope that does not deviate from the purpose of the present invention. [Industrial Applicability]

[0046] The present invention can be applied to an evaluation system and evaluation program that evaluates a business plan using a plurality of evaluation criteria. [Explanation of symbols]

[0047] 2: Evaluation criteria 11: Plan input section 12: Reference input section 20: Evaluation level calculation unit 21: Command generation unit (prompt generation unit) 22: Vector representation module 23: Arithmetic section 25: Generation AI 30: Evaluation unit

Claims

1. An evaluation system for evaluating a business plan using multiple evaluation criteria, A plan input unit for inputting the business plan; A criterion input unit for inputting the evaluation criteria; an evaluation level calculation unit that calculates an evaluation level for each of the evaluation criteria for the business plan using the input business plan and the evaluation criteria; an evaluation unit that performs a final evaluation of the business plan based on the evaluation level; The evaluation level calculation unit generates plan vector data by vector-representing sentences constituting the business plan, and generates criterion vector data by vector-representing sentences constituting the evaluation criteria; An evaluation system in which a classification area corresponding to the evaluation level is set in a vector space in which a data group consisting of the plan vector data and the reference vector data is scattered, a similarity between the business plan and each of the evaluation criteria is calculated based on the distance between the data group contained in each classification area and each classification area, and the evaluation level is calculated based on the similarity.

2. The evaluation system according to claim 1 , wherein the classification area is represented by a plurality of clusters divided in a vector space including the plan vector data and the reference vector data, and the classification area is calculated by calculating the distribution state of the clusters.

3. The evaluation system of claim 2, wherein the classification regions are six regions corresponding to "Yes", "Likely Yes", "Likely No", "No", "Irrelevant", and "Not Mentioned".

4. The evaluation system of claim 1 , wherein the evaluation level calculation unit is configured using a generative AI, and the business plan and the evaluation criteria are provided to the generative AI as prompts.

5. The evaluation system described in claim 4, wherein the business plan is a business plan for acquiring carbon credits, and the evaluation criteria include general evaluation criteria created in accordance with carbon credit certification standards and unique evaluation criteria created independently.

6. An evaluation program for causing a computer to execute a process of evaluating a business plan using a plurality of evaluation criteria, A plan input process for inputting the business plan; A criterion input process for inputting the evaluation criteria; an evaluation level calculation process for calculating an evaluation level for each of the evaluation criteria for the business plan using the input business plan and the evaluation criteria; an evaluation process for performing a final evaluation of the business plan based on the evaluation level; The evaluation level calculation process generates plan vector data by vector-representing sentences constituting the business plan, and generates criterion vector data by vector-representing sentences constituting the evaluation criteria, An evaluation program in which a classification area corresponding to the evaluation level is set in a vector space in which a data group consisting of the plan vector data and the reference vector data is scattered, a similarity between the business plan and each of the evaluation criteria is calculated based on the distance between the data group contained in each classification area and each classification area, and the evaluation level is calculated based on the similarity.

Images