Information provision device, information provision method, and program

Abstract

An information provision device (100) is provided with: an extraction unit (101) that extracts, from at least one piece of document information, identification information for identifying each of a plurality of materials and a characteristic value of each of the plurality of materials; a derivation unit (105) that derives reliability of the characteristic value of a material on the basis of similarity of the characteristic value between the material and at least one other material; and an image processing unit (106) that generates a first image that shows the characteristic value of each of the plurality of materials (i) in a display mode corresponding to the reliability derived for the characteristic value of the material and (ii) in association with the identification information of the material, and outputs the first image to a display unit (13).

Description

Information providing device, information providing method, and program

[0001] The present disclosure relates to an information providing device that provides information about materials.

[0002] Conventionally, information providing devices have been proposed that provide information on materials or experiments described in documents such as academic papers (see, for example, Patent Documents 1 to 3). Patent Document 1 proposes a numerical search device as an information providing device that extracts numerical data on materials described in each of multiple documents and calculates the similarity between the numerical data. Patent Document 2 proposes a support device as an information providing device that extracts information on synthesis processes described in papers and provides information indicating the synthesis process from starting materials to the target material. Patent Document 3 proposes a reliability evaluation system as an information providing device that evaluates the reliability of experimental documents. In other words, the reliability evaluation system searches for documents in response to input keywords such as experimental methods, and calculates the reliability of the document based on a magazine usefulness list that stores the usefulness of the journals to which the searched documents are submitted and the frequency of appearance of the input keywords.

[0003] JP 2020-80087 A International Publication No. 2021 / 039175 JP 2008-152701 A

[0004] However, the information providing devices disclosed in the above patent documents require further improvement in order to provide information about materials appropriately.

[0005] Therefore, the present disclosure provides an information providing device and the like that can be further improved to appropriately provide information about materials.

[0006] An information providing device according to one aspect of the present disclosure includes an extraction unit that extracts identification information for identifying each of a plurality of materials and characteristic values ​​of each of the plurality of materials from at least one piece of literature information; a derivation unit that derives the reliability of the characteristic value of the material based on the similarity of the characteristic value between the material and one or more other materials; and an image processing unit that (i) displays the characteristic value of each of the plurality of materials in a display mode corresponding to the reliability derived for the characteristic value of the material, and (ii) generates a first image that shows the characteristic value of the material in association with the identification information of the material, and outputs the first image to a display unit.

[0007] This comprehensive or specific aspect may be realized as a system, a method, an integrated circuit, a computer program, or a computer-readable recording medium, or may be realized as any combination of an apparatus, a system, a method, an integrated circuit, a computer program, and a computer-readable recording medium. The recording medium may be a non-volatile recording medium such as a CD-ROM (Compact Disc-Read Only Memory).

[0008] The information providing device of the present disclosure can be further improved to appropriately provide information about materials.

[0009] FIG. 1 is a block diagram showing an example of a configuration of an information providing system according to the first embodiment. FIG. 2A is a diagram showing an example of a display screen displayed on a display unit by an image processing unit according to the first embodiment. FIG. 2B is a diagram showing another example of a display screen displayed on a display unit by an image processing unit according to the first embodiment. FIG. 3 is a diagram showing an example of metadata according to the first embodiment. FIG. 4 is a diagram showing an example of main text data according to the first embodiment. FIG. 5 is a diagram showing an example of material names and characteristic values ​​extracted from sentences in main text data according to the first embodiment. FIG. 6A is a diagram showing an example of a figure to be extracted in the main text data according to the first embodiment. FIG. 6B is a diagram showing an example of characteristic values ​​extracted from a figure to be extracted in the first embodiment. FIG. 7A is a diagram showing an example of a figure to be extracted by the extraction unit according to the first embodiment. FIG. 7B is a diagram showing an example of a figure to be excluded from the extraction target by the extraction unit according to the first embodiment. FIG. 8A is a diagram showing an example of a table to be extracted in the main text data according to the first embodiment. FIG. 8B is a diagram showing an example of characteristic values ​​extracted from a table to be extracted in the first embodiment. FIG. 9 is a diagram showing an example of a normalization process for material names according to the first embodiment. FIG. 10 is a diagram showing an example of a conversion process of a material characteristic value in the first embodiment. FIG. 11 is a diagram showing an example of an extracted information table after updating in the first embodiment. FIG. 12 is a diagram showing an example of a display screen including the extracted information table after updating in the first embodiment. FIG. 13 is a diagram showing an example of a graph display screen including a characteristic value graph in the first embodiment. FIG. 14 is a diagram showing an example of a graph display screen showing reliability in the first embodiment. FIG. 15A is a diagram showing another example of a graph display screen showing reliability in the first embodiment. FIG. 15B is a diagram showing an example of a graph display screen after the bias has been changed in the first embodiment. FIG. 15C is a diagram showing another example of a graph display screen after the bias has been changed in the first embodiment. FIG. 16 is a flowchart showing an example of the overall processing operation of the information providing device in the first embodiment. FIG. 17 is a flowchart showing an example of processing by the extraction unit in the first embodiment. FIG. 18A is a block diagram showing an example of a configuration of an information providing system in a modified example of the first embodiment.Fig. 18B is a block diagram showing another example of the configuration of an information provision system in a modified example of Embodiment 1. Fig. 19 is a diagram showing an example of a material display screen in Embodiment 2. Fig. 20 is a diagram showing another example of a material display screen in Embodiment 2. Fig. 21 is a diagram showing an example of a material display screen on which edited material is displayed in Embodiment 2. Fig. 22 is a diagram showing another example of a material display screen on which edited material is displayed in Embodiment 2. Fig. 23 is a diagram showing another example of a material display screen on which edited material is displayed in Embodiment 2. Fig. 24 is a flowchart showing an example of the overall processing operation of the information provision device in Embodiment 2.

[0010] (Findings that led to the present disclosure) To synthesize new materials, it is necessary to find materials with appropriate properties from a vast amount of material data. However, finding optimal materials from a vast amount of material data requires a lot of time and money, and even experienced researchers find it difficult to discover new materials. For this reason, materials search is being carried out using computers. That is, large amounts of information on material synthesis are extracted from literature such as papers and patents, the extracted information is stored in a database, and knowledge on material development is gained from the stored information. For example, as in Patent Documents 1 to 3 mentioned above, calculations of similarity, provision of information showing the synthesis process, evaluation of the reliability of the literature, etc. are carried out.

[0011] However, although the information providing devices in the above Patent Documents 1 to 3 provide various information, there is a problem in that it is difficult to know whether the property values ​​of the materials described in the documents are reliable. For example, even if champion data indicates the highest property value of a material, its reliability (i.e., reproducibility) is often low.

[0012] Therefore, the inventors discovered that it is possible to extract characteristic values ​​of each of a plurality of materials from literature, derive the reliability of those characteristic values ​​based on the similarity of those extracted characteristic values, and display the plurality of characteristic values ​​in a display mode according to their reliability, thereby arriving at the present disclosure.

[0013] That is, an information providing device according to one aspect of the present disclosure includes an extraction unit that extracts identification information for identifying each of a plurality of materials and characteristic values ​​of the plurality of materials from at least one piece of literature information; a derivation unit that derives a reliability of a characteristic value of the material based on a similarity of the characteristic value between the material and one or more other materials; and an image processing unit that (i) displays the characteristic value of each of the plurality of materials in a display mode corresponding to the reliability derived for the characteristic value of the material, and (ii) generates a first image that shows the characteristic value of the material in association with the identification information of the material and outputs the first image to a display unit. For example, the identification information may be the name of the material, i.e., the material name, and the material name may be a composition formula. The plurality of materials may be the same material, different materials, or materials having a common purpose or element type. In a specific example, the plurality of materials are materials used for the positive or negative electrodes of a battery. For example, a lower degree of similarity leads to a lower reliability, and a higher degree of similarity leads to a higher reliability.

[0014] As a result, in the displayed first image, the property values ​​of each of the multiple materials are displayed in a manner corresponding to the reliability of the property value, and the property values ​​are associated with the material's identification information. Therefore, by viewing the first image, a user such as a materials researcher can easily understand the reliability of the property values ​​of the materials described in, for example, a vast amount of literature stored in a database. For example, if the property values ​​of a material are similar to those of many other materials, the user can easily understand that the property values ​​of that material are reliable.

[0015] The extraction unit may extract a plurality of type-specific characteristic values ​​as the characteristic values, for example, the type-specific characteristic values ​​being electrical conductivity and activation energy values ​​of the material.

[0016] This makes it possible to easily grasp the reliability of the multiple type characteristic values ​​possessed by the material.

[0017] The plurality of type characteristic values ​​may include a first type characteristic value and a second type characteristic value, and the image processing unit may set a characteristic map on the first image, the characteristic map being configured with a first coordinate axis for indicating the first type characteristic value and a second coordinate axis for indicating the second type characteristic value, and may superimpose marks corresponding to each of the plurality of materials on the characteristic map at positions corresponding to the first type characteristic value and the second type characteristic value of the material, in a display manner corresponding to the reliability derived for the material's characteristic value. For example, the characteristic map may be a characteristic value graph showing electrical conductivity and activation energy values ​​on a first coordinate axis and a second coordinate axis, respectively. Then, a mark corresponding to each material is arranged on the characteristic value graph at a position corresponding to the material's electrical conductivity and activation energy value, in a display manner corresponding to the reliability of the type characteristic value.

[0018] This makes it easier to grasp the overall reliability of the multiple type characteristic values ​​possessed by each material.

[0019] The derivation unit may determine the similarity of the characteristic value of the material based on the distance between the mark corresponding to the material and the mark corresponding to each of the one or more other materials. For example, the shorter the average value of the distances, the higher the similarity value determined. In other words, the closer the density of multiple marks, the higher the similarity is determined to be for the characteristic value indicated by the marks, and conversely, the less the density of multiple marks, the lower the similarity is determined to be for the characteristic value indicated by the marks.

[0020] This makes it possible to appropriately identify one similarity for a plurality of material type characteristic values, and as a result, to appropriately derive a reliability based on the similarity.

[0021] The image processing unit may determine the display mode of the characteristic value such that the higher the reliability derived for the characteristic value of the material, the darker the color depth, and generate the first image showing the characteristic value with the determined color depth.

[0022] This allows the user to easily visually grasp the reliability of the characteristic value. In the first image showing the characteristic value in the determined color intensity, the numerical value of the characteristic value itself may be displayed in the determined color intensity, or a mark showing the characteristic value may be displayed in the determined color intensity.

[0023] The extraction unit may further extract attribute information indicating attributes of each of the plurality of materials from the at least one document information, and the derivation unit may derive a reliability of the characteristic value of the material based on the similarity of the characteristic value of the material and the attribute information extracted for the material. For example, the derivation unit may derive the reliability of the characteristic value of the material by performing a weighted addition of the similarity of the characteristic value of the material and an attribute value based on the attribute information extracted for the material.

[0024] This allows the reliability of a characteristic value to be derived based on the similarity of the characteristic value and the attributes of the material, making it possible to derive the reliability from multiple angles and improve the accuracy of the reliability.By adjusting the weights of the similarity and attributes as biases, it is possible to derive the reliability according to the user's purpose.

[0025] The attribute information may indicate, as an attribute, the publication date of the at least one piece of literature information containing identification information and characteristic values ​​of the material corresponding to the attribute information, and the deriving unit may derive the reliability of the characteristic value using the attribute value indicating the recency of the publication date. For example, the attribute value may indicate a larger value the more recently the publication date, and the deriving unit may derive a larger value as the reliability of the characteristic value of the material increases as the similarity of the characteristic values ​​of the material increases and the attribute value corresponding to the material increases. For example, the publication date may be the publication date.

[0026] This allows a relatively high reliability to be derived for characteristic values ​​described in new document information, making it possible to derive a reliability appropriate for users who place importance on publication time.

[0027] The attribute information may indicate, as an attribute, the number of citations of literature information among the at least one piece of literature information in which identification information and characteristic values ​​of the material corresponding to the attribute information are written, and the derivation unit may derive the reliability of the characteristic value using the attribute value corresponding to the number of citations. For example, the attribute value may indicate a larger value the more the number of citations, and the derivation unit may derive a larger value as the reliability of the characteristic value of the material increases as the similarity of the characteristic values ​​of the material increases and as the attribute value corresponding to the material increases.

[0028] This allows for a relatively high reliability to be derived for characteristic values ​​described in document information with a high number of citations, making it possible to derive an appropriate reliability for users who place importance on the number of citations.

[0029] The attribute information may indicate, as the attribute, an author of the at least one piece of literature information in which identification information and characteristic values ​​of the material corresponding to the attribute information are written, and the deriving unit may derive the reliability of the characteristic value using the attribute value depending on whether the author of the literature information is the same as each of the authors of one or more other pieces of literature information. For example, the attribute value may be larger the more authors of the one or more other pieces of literature information that are different from the author of the literature information, and the deriving unit may derive a larger value as the reliability of the characteristic value of the material increases the higher the similarity of the characteristic values ​​of the material and the larger the attribute value corresponding to the material.

[0030] This allows a relatively high reliability to be derived for characteristic values ​​described in document information written by authors different from many other document information. In other words, if characteristic values ​​described in many document information written by different authors are similar, a high reliability is derived for those characteristic values. On the other hand, even if similar characteristic values ​​are described in many document information, if those document information are written by the same author, a low reliability is derived for those characteristic values. Therefore, an appropriate reliability can be derived for users who place importance on the identity of the author of the document information.

[0031] The attribute information may indicate, as the attribute, a synthesis method of the material corresponding to the attribute information, and the derivation unit may derive the reliability of the characteristic value using the attribute value corresponding to the degree of similarity between the synthesis method of the material and each of the synthesis methods of the one or more other materials. For example, the attribute value may be greater the greater the degree of similarity between the synthesis method of the material and each of the synthesis methods of the one or more other materials, and the derivation unit may derive a greater value as the reliability of the characteristic value of the material increases the greater the similarity of the characteristic values ​​of the material and the greater the attribute value corresponding to the material. For example, the synthesis method of the material may include at least one of temperature conditions, time conditions, and type of equipment used to synthesize the material.

[0032] This allows a relatively high reliability to be derived for a characteristic value if the literature information describes that the material with that characteristic value is synthesized using the same synthesis method as other literature information, making it possible to derive an appropriate reliability for users who place importance on synthesis methods.

[0033] The extraction unit may further acquire material conditions, and for each of one or more materials that meet the material conditions, extract information about the material as display information candidates from the at least one literature information, and the image processing unit may further acquire weights for each of multiple attributes of the material, and from the multiple display information candidates extracted by the extraction unit, select one or more display information candidates corresponding to materials having characteristic values ​​from which the reliability equal to or greater than a threshold is derived as display information, generate a second image showing display information corresponding to each of the multiple attributes from the one or more display information in an amount corresponding to the weight of each of the multiple attributes, and output the second image to the display unit.

[0034] This allows the amount of display information corresponding to each of the multiple attributes shown in the second image to be changed by adjusting the bias, which is the weight of each of the multiple attributes. Therefore, the user can arbitrarily adjust the amount of display information for each attribute so that more display information related to attributes in which the user is interested is displayed and less display information related to attributes in which the user is not interested is displayed. Furthermore, since the displayed display information is information about materials with a reliability above a threshold, the user can use the displayed display information with confidence for work such as material research. Display information for materials that meet material conditions is displayed, and the material conditions are, for example, conditions related to the element species contained in the material or the composition of the material. This allows the one or more pieces of displayed display information to be limited to materials in which the user is interested.

[0035] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. Each of the embodiments described below represents a specific example of the present disclosure. Therefore, the numerical values, shapes, materials, components, arrangement positions and connection forms of the components shown in the following embodiments are merely examples and are not intended to limit the present disclosure. Therefore, among the components in the following embodiments, components that are not described in the independent claims that represent the highest concept will be described as optional components.

[0036] It should be noted that the drawings are schematic diagrams and are not necessarily strict illustrations. In the drawings, the same reference numerals are used to designate substantially the same components, and redundant explanations will be omitted or simplified.

[0037] (Embodiment 1) [Device Configuration] Fig. 1 is a block diagram showing an example configuration of an information provision system in embodiment 1. The information provision system 1000 in this embodiment is a system that provides information on materials, and includes an information provision device 100, an input unit 11, a literature database (DB) 12, and a display unit 13, as shown in Fig. 1 .

[0038] The input unit 11 accepts an input operation from a user and outputs an input signal corresponding to the input operation to the information providing device 100. The input unit 11 is configured as, for example, a keyboard, a touch sensor, a touch pad, or a mouse. Use of the input unit 11 allows for more intuitive input operations.

[0039] The display unit 13 receives an image signal from the information providing device 100 and displays an image corresponding to the image signal. The display unit 13 is, for example, a liquid crystal display, a plasma display, an organic EL (Electro-Luminescence) display, or the like, but is not limited to these.

[0040] The literature database 12 is a recording medium such as a hard disk, and stores multiple pieces of literature information D. Each piece of literature information D is electronic data of a literature. The literature may be, for example, a paper on materials, material synthesis, or experiments on material synthesis. The literature information D includes text data D1 and metadata D2. The text data D1 is, for example, a digitized paper in PDF or XML format published as an online journal (also called an electronic journal). The metadata D2 is data related to figures, tables, images, authors, research institutions, publication dates, titles, and the like shown in the text data D1. Such metadata D2 is attached to the text data D1. Note that, although the metadata D2 is attached to the text data D1 in this embodiment, it does not necessarily have to be attached to the text data D1. If the metadata D2 is not attached to the main data D1, the information providing device 100 may download the metadata D2 provided by the publisher of the document corresponding to the main data D1 from a server or the like and attach it to the main data D1.

[0041] Such a literature database 12 may be connected to the information providing device 100 via a communication network such as the Internet, or may be directly connected to the information providing device 100 without going through a communication network. The literature database 12 may be a recording medium other than a hard disk, such as a RAM (Random Access Memory), a ROM (Read Only Memory), or a semiconductor memory. The literature database 12 may be volatile or non-volatile.

[0042] The information providing device 100 provides information about materials based on a plurality of pieces of literature information D stored in the literature database 12, in response to an input signal output from the input unit 11. That is, the information providing device 100 displays the information about materials on the display unit 13. Specifically, the information providing device 100 receives an input signal from the input unit 11 and searches the literature database 12 for at least one piece of literature information D corresponding to the input signal. The information providing device 100 then extracts a plurality of pieces of information from the retrieved at least one piece of literature information D, generates an image based on the plurality of pieces of information, and outputs an image signal representing the image to the display unit 13. Note that the information providing device 100 may be composed of a processor, such as a central processing unit (CPU), and a memory. In this case, the processor functions as the information providing device 100 by, for example, executing a computer program stored in the memory.

[0043] Specifically, as shown in FIG. 1, the information providing device 100 includes an extraction unit 101, a first information processing unit 102, a second information processing unit 103, a third information processing unit 104, a derivation unit 105, and an image processing unit 106.

[0044] The extraction unit 101 acquires an input signal output from the input unit 11 and searches the literature database 12 for at least one piece of literature information D corresponding to the input signal. Furthermore, the extraction unit 101 extracts, from the literature information D, first information indicating the name of a material, second information indicating a characteristic value of the material, and third information indicating an attribute of the material. The material name is hereinafter also referred to as the material name and is identification information for identifying the material. If the literature information D describes material synthesis, the materials corresponding to the first information, second information, and third information are the materials ultimately produced by the material synthesis and are also referred to as final materials or target materials. The extraction unit 101 then outputs the first information to the first information processing unit 102, the second information to the second information processing unit 103, and the third information to the third information processing unit 104.

[0045] The first information processing unit 102 performs a process of correcting the material name indicated by the first information using a predetermined method, and outputs the processed first information to the derivation unit 105 .

[0046] The second information processing unit 103 performs processing to correct the property values ​​of the material indicated by the second information using a predetermined method, and outputs the processed second information to the derivation unit 105.

[0047] The third information processing unit 104 performs processing to correct the property value of the material indicated by the third information using a predetermined method, and outputs the processed third information to the derivation unit 105.

[0048] The derivation unit 105 acquires the processed first information, second information, and third information from the first information processing unit 102, the second information processing unit 103, and the third information processing unit 104. The derivation unit 105 then integrates the processed first information, second information, and third information, and further derives the reliability of the extracted characteristic value of each material based on that information. The derivation unit 105 outputs an output signal including the derived reliability to the image processing unit 106.

[0049] The image processing unit 106 acquires the output signal from the derivation unit 105, and generates a first image by performing image processing according to the output signal. Then, the image processing unit 106 outputs an image signal representing the first image to the display unit 13.

[0050] In this embodiment, the first information processing unit 102, the second information processing unit 103, and the third information processing unit 104 do not have to modify all of the first information, all of the second information, and all of the third information extracted from the literature database 12. In other words, the first information processing unit 102, the second information processing unit 103, and the third information processing unit 104 may modify part of the information as necessary. In this embodiment, the information providing device 100 includes the first information processing unit 102, the second information processing unit 103, and the third information processing unit 104, but may not include at least one of them.

[0051] Each of the components shown in FIG. 1 will now be described in detail.

[0052] [Information Extraction from Metadata] FIGS. 2A and 2B are diagrams showing an example of a display screen displayed on the display unit 13 by the image processing unit 106. FIG.

[0053] 2A, the image processing unit 106 displays a display screen 20 on the display unit 13. The display screen 20 includes a document list window 21, an extracted information table 22, and an extraction start button 23a.

[0054] The document list window 21 displays a list of document information D stored in the document database 12. That is, the icon and document ID of each document information D stored in the document database 12 are displayed. The document ID is identification information for identifying the document information D.

[0055] The extracted information table 22 is a table for showing information extracted from the literature information D. This information includes, for example, the literature ID, publication date, journal name, title, number of citations, final material name, electrical conductivity, and activation energy value. The publication date is the publication date of the paper corresponding to the literature information D, and the journal name is the name of the journal in which the paper was published. The title is the title of the paper, and the number of citations is the number of times the paper has been cited in other papers. The final material name is the name of the final material produced by the material synthesis described in the paper. The electrical conductivity is the electrical conductivity or electrical conductivity rate that indicates the ease of electrical conduction in the final material, and will hereinafter be referred to simply as "conductivity." The activation energy value is a value indicating the magnitude of the activation energy of the final material.

[0056] Here, the initial extracted information table 22 does not show information extracted from the document information D, but shows the names of the types of the information. In the examples of Figures 2A and 2B, "Magazine," "Final Material," and "Activation" are shown as the names of the types of the information, where "Magazine" means the name of the magazine, "Final Material" means the name of the final material, and "Activation" means the activation energy value.

[0057] The extraction start button 23 a is a button for starting extraction of the above-mentioned information from the plurality of document information D stored in the document database 12 .

[0058] The user performs an input operation on the input unit 11 to select the icons of one or more pieces of desired document information D from all of the document information D displayed in the document list window 21, and selects the extraction start button 23a. The input unit 11 outputs an input signal corresponding to this input operation to the extraction unit 101. In other words, the user selects one or more pieces of desired document information D, and instructs the information providing device 100 to extract various pieces of information from the selected pieces of document information D.

[0059] When the extraction unit 101 receives the input signal from the input unit 11, it extracts, for example, four pieces of bibliographic information indicating the publication date, magazine name, title, and number of citations from the metadata D2 of one or more selected pieces of document information D. Then, for each selected piece of document information D, the extraction unit 101 outputs the document ID of that piece of document information D and the four pieces of bibliographic information extracted from the metadata D2 of that piece of document information D to the image processing unit 106. Note that the publication date, magazine name, title, and number of citations can also be considered to be attributes of the material. In other words, each of the four pieces of bibliographic information can also be considered to be third information.

[0060] When the image processing unit 106 acquires the document ID and the four pieces of bibliographic information from the extraction unit 101, it updates the display screen 20 displayed on the display unit 13 as shown in Fig. 2B. That is, the image processing unit 106 writes the document ID and the publication date, magazine name, title, and number of citations indicated by the four pieces of bibliographic information in the extracted information table 22 in association with each other.

[0061] The extracted information table 22 included in the updated display screen 20 shows the publication date, magazine name, title, etc. of each piece of document information D. Therefore, the user can narrow down the material field for analysis or perform analysis of materials by era.

[0062] 2B , the image processing unit 106 includes a replenishment start button 23b in the updated display screen 20. The replenishment start button 23b is a button for starting extraction of three pieces of information indicating the name of the final material, the conductivity, and the activation energy value from the text data D1 of the plurality of pieces of literature information D stored in the literature database 12.

[0063] FIG. 3 is a diagram illustrating an example of metadata.

[0064] The metadata D2 is structured data, for example, a bib format file. That is, the metadata D2 is a file with the extension "bib" and is also called a BIB file. For example, as shown in FIG. 3, such metadata D2 describes the title of the paper, the name of the author of the paper, the name of the organization to which the author belongs (Affiliation), the publication date of the paper, and the like. The metadata D2 may also indicate the number of citations. The extraction unit 101 extracts the above-mentioned four pieces of bibliographic information from such metadata D2. The name of the author is also called the author name, and the organization to which the author belongs is also called the research institution.

[0065] [Information extraction from text data] When the user selects the replenishment start button 23b by inputting data into the input unit 11, the extraction unit 101 acquires an input signal corresponding to the input operation from the input unit 11 and starts extracting information from the text data D1 of one or more pieces of literature information D that have already been selected.

[0066] FIG. 4 is a diagram showing an example of the main data D1.

[0067] As shown in FIG. 4 , the main text data D1 includes sentences written in natural language, tables, and diagrams such as graphs. The extraction unit 101 treats these sentences, tables, and diagrams as extraction targets and extracts the first, second, and third information from the extraction targets. In other words, the extraction unit 101 acquires the first, second, and third information extracted from the extraction targets. Note that, if the main text data D1 includes text data, the extraction unit 101 extracts the first, second, and third information from the text data. In other words, the extraction unit 101 acquires the first, second, and third information extracted from the text data. If the main text data D1 does not include text data, the extraction unit 101 may convert the sentences represented as images in the main text data D1 into text data and extract the first, second, and third information from the text data. In other words, the extraction unit 101 may obtain the first information, the second information, and the third information extracted from the converted text data.

[0068] When extracting the first information, the second information, and the third information from text data, the extraction unit 101 may use a natural language processing tool or a deep learning tool. Examples of natural language processing tools include CoreNLP and MeCab. Examples of deep learning tools include word2vec, BERT, Tensorflow, and PyTorch. This makes it possible to extract each piece of information with high accuracy. Note that multiple types of tools may be used in combination to extract one piece of information. This makes it possible to extract each piece of information with even higher accuracy.

[0069] Words indicating material names are often written as combinations of element symbols and numbers. Therefore, the extraction unit 101 may use a dictionary in which patterns of combinations of element symbols and numbers are registered, and compare the text data with the patterns to extract words that match the patterns as material names. The extraction unit 101 may express the combinations of element symbols and numbers included in the text data as regular expressions and compare the regular expressions with the patterns. Then, the extraction unit 101 may extract, as material names, combinations of element symbols and numbers that correspond to the regular expressions that match the patterns. Regular expressions are expressions that follow predetermined rules. For example, if the text data indicates "The conductivity and activation energy for LiAlLaZrO with an ion dose of 2.7 x 10 cm are 4.6 x 10 S cm and 0.11 eV, respectively," the extraction unit 101 extracts the material name "LiAlLaZrO" by describing the combination of element symbols and numbers using regular expressions and matching the regular expressions with patterns. This allows the user to appropriately extract the information they desire. Note that in this disclosure, the number to the right of an element symbol indicates the composition ratio or number of atoms of the element, even if the character is not a subscript.

[0070] For example, the extraction unit 101 extracts "Li6.25Al0.25La3Zr2O12" as a material name from the sentence to be extracted, and －３ SCM －１ " is extracted as a characteristic value of the material, i.e., conductivity, and "0.11 eV" is extracted as a characteristic value of the material, i.e., activation energy value. Note that in this disclosure, the number to the right of "10" or a unit indicates a multiplier even if it is not a superscript number.

[0071] For example, the extraction unit 101 extracts "3.70 x 10 －４ SCM －１ ", "1.49 x 10 －４ SCM －１ " is extracted as a characteristic value of the material, i.e., conductivity. At this time, the extraction unit 101 extracts "conductivity" or "Scm －１ Since the table contains keywords related to conductivity, such as ", conductivity is extracted from the table.

[0072] The extraction unit 101 extracts, for example, conductivity, which is a characteristic value of a material, from the graph to be extracted. At this time, the extraction unit 101 adds "conductivity" or "Scm" to the label or caption of the axis of the graph. －１ Since the table contains keywords related to conductivity, such as ", conductivity is extracted from the graph.

[0073] FIG. 5 is a diagram showing an example of material names and characteristic values ​​extracted from sentences in the main data D1.

[0074] The extraction unit 101 extracts material names from each sentence in the text data D1. At this time, the extraction unit 101 associates a document ID, an extracted line number, and a span with the extracted material name and records them in the extraction list 31, as shown in FIG. 5, for example. The document ID is identification information for the document information D containing the text data D1 from which the extracted material name was extracted. The extracted line number is the line number in which the material name is described in the text data D1. The span indicates the start point where the description of the material name begins on the line with the extracted line number and the end point where the description ends. The start point is indicated by the number of characters from the first character of the line to the first character of the material name, and the end point is indicated by the number of characters from the first character of the line to the last character of the material name.

[0075] If the material name spans multiple lines, the numbers of those lines may be recorded as extracted line numbers. The extracted line number may be the number of the sentence in which the material name is written in the body data D1. The sentence number is, for example, a number assigned to every sentence in the body data D1 for identifying that sentence. The extraction unit 101 may record the extracted line number and the page number in the body data D1 in which the material name is written in the extraction list 31.

[0076] Here, when extracting a material name, the extraction unit 101 may extract, for example, a combination of an element symbol and a number as the material name. If there are parentheses next to the element symbol and the number, the parentheses and the character string within the parentheses may also be extracted as part of the material name. For example, the extraction unit 101 may extract "LiAlO.25LaZrO12 (LALZ)" as the material name. The extraction unit 101 may recognize the character string within the parentheses as an abbreviation for the material name. For example, the extraction unit 101 may recognize "LiAlO.25LaZrO12" in "LiAlO.25LaZrO12 (LALZ)" as the standard expression form for the material name, and recognize "LALZ" as an abbreviation for the material name "LiAlO.25LaZrO12." As a result, the extraction unit 101 also extracts "LALZ" as the material name from the main data D1.

[0077] If the extraction unit 101 determines that the character string in the parentheses contains a variable, it does not recognize the character string in the parentheses as an abbreviation for the material name. For example, if the character string in the parentheses contains a variable x, such as "x = 0.1, 0.2, 0.3," the extraction unit 101 does not recognize the character string in the parentheses as an abbreviation for the material name. The material name extracted by the extraction unit 101 may include a mixture ratio of multiple components. For example, the material name may include a mixture ratio of "60:40" between the component "Li2SO4" and the component "Li3BO3," such as the material name "60Li2SO4 * 40Li3BO3." Such variables and mixture ratios may be corrected by the first information processing unit 102 through processing described below.

[0078] The material name extracted by the extraction unit 101 is the name of the target material or the final material, as described above. For example, if the text data D1 contains multiple material names, the extraction unit 101 may extract the name of the final material from the multiple material names using a natural language processing tool or a deep learning tool. For example, if the text data D1 contains the sentence "XXX was synthesized using...", the extraction unit 101 detects "synthesized" in the sentence as a keyword. Then, the extraction unit 101 determines that "XXX", which is the target of the keyword, is the name of the final material (i.e., the final material name), and extracts the final material name "XXX".

[0079] The extraction unit 101 extracts a material name and a characteristic value from each sentence in the text data D1. For example, the characteristic value is conductivity. At this time, the extraction unit 101 associates a document ID, an extracted line number, and a span with the extracted characteristic value and records them in the extraction list 32, as shown in FIG. 5 . The document ID is identification information for the document information D containing the text data D1 from which the extracted characteristic value was extracted. The extracted line number is the line number in the text data D1 where the characteristic value is described. Note that the extracted line number may be a sentence number, as described above. The span indicates the start point where the description of the material name begins and the end point where the description ends on the line corresponding to the extracted line number. The start point is indicated by the number of characters from the first character of the line to the first character of the characteristic value, and the end point is indicated by the number of characters from the first character of the line to the last character of the characteristic value.

[0080] In a specific example, the sentence in the main data D1 is "The conductivity and activation energy for LiAlLaZrO with an ion dose of 2.7 x 10 cm are 4.6 x 10 S cm and 0.11 eV, respectively." In this case, the extraction unit 101 describes the combination of numbers and units using a regular expression and compares the regular expression with a pattern, thereby recognizing and extracting "4.6 x 10 S cm" from the sentence as a characteristic value.

[0081] Here, the text data D1 of the paper contains a large number of sentences that do not include material names or material property values. For example, these sentences include references or acknowledgments. In other words, if all sentences in the text data D1 are to be extracted, there is a possibility that a lot of noise other than material names and property values ​​will be extracted. In other words, extraction errors are more likely to occur. Therefore, the extraction unit 101 in this embodiment may treat sentences that include words related to materials as extraction targets.

[0082] For example, a sentence containing a material name or property value may contain keywords related to those. In other words, if a sentence contains a keyword, it is likely that the sentence contains a material name or property value. For example, "XXX was synthesized using ..." and "The conductivity and activation energy for XXX are YYY S cm -1 and ZZZ eV, respectively." －１ " are keywords. The extraction unit 101 may treat sentences containing such keywords as extraction targets and extract material names or characteristic values ​​from the extraction target sentences using pattern matching based on regular expressions. This makes it possible to reliably extract the material names or characteristic values ​​desired by the user.

[0083] When extracting ingredient names and characteristic values, the extraction unit 101 attempts to extract, for each processing unit, such as a sentence or a clause, if one of the ingredient name and the characteristic value is extracted from that processing unit, the other is also extracted from that processing unit. If the extraction unit 101 extracts one of the ingredient name and the characteristic value from a processing unit but is unable to extract the other, the extraction unit 101 may store that processing unit in a database. Such processing units may be used as training data for machine learning. The extraction unit 101 may prompt the user to extract ingredient names, characteristic values, or ingredient names and characteristic values ​​from that processing unit. That is, the extraction unit 101 may display an error message on the display unit 13 via the image processing unit 106 to prompt the user to extract ingredient names, characteristic values, or ingredient names and characteristic values.

[0084] FIG. 6A shows an example of a diagram to be extracted from the main text data D1, and FIG. 6B shows an example of characteristic values ​​extracted from the diagram to be extracted.

[0085] The extraction unit 101 extracts material names and characteristic values ​​from graphs such as line graphs and scatter plots in the main data D1. For example, as shown in FIG. 6A , the extraction unit 101 extracts the conductivity and temperature of a material from graphs included in the main data D1 for each of the document IDs "0001" and "0002." For example, the conductivity is a characteristic value. The temperature is one of the conditions used in a synthesis method for synthesizing a material and is an attribute of the material. The extraction unit 101 uses tools such as image processing, image recognition, and deep learning to extract these values.

[0086] Here, the vertical axis of the graph shown in Figure 6A represents conductivity, and the horizontal axis represents temperature. The horizontal axis is also called the x-axis, and the vertical axis is also called the y-axis. The graph also shows a broken line when the material is in a bulk state and a broken line when the material is in a total state. Bulk refers to, for example, a state in which the material is a single substance, and total refers to, for example, a state in which the material is incorporated into a product. The x-axis is marked with scales at 1000°C, 1200°C, 1400°C, 1600°C, 1800°C, and 2000°C.

[0087] 6A, the extraction unit 101 reads the conductivity corresponding to the temperature indicated by each scale on the x-axis of the graph from each of the Bulk line and the Total line in the graph. As a result, the conductivity corresponding to each of the temperatures of 1000° C., 1200° C., 1400° C., 1600° C., 1800° C., and 2000° C. is extracted for each of the Bulk material and the Total material.

[0088] For example, in the graph of the text data D1 of the document ID "0001," the extraction unit 101 reads "0.0070 S / cm" as the conductivity on the y-axis indicated by the broken line for Bulk when the temperature on the x-axis is 1000° C. The temperature on the x-axis is also called the x-value, and the conductivity on the y-axis is also called the y-value.

[0089] Next, as shown in Fig. 6B, the extraction unit 101 records the above-mentioned document ID, the figure number of the graph included in the text data D1 of that document ID, the x-value, which is the temperature at which the x-axis is scaled, and the y-value, which is the conductivity read out for that x-value, in the extraction list 33. Furthermore, the extraction unit 101 records the x-axis label and y-axis label of that graph, the state of the material corresponding to the read-out conductivity (i.e., Blu or Total), and the caption of that graph in the extraction list 33. Note that the caption often includes the name of the material, and therefore the caption can be used as a clue for associating the x-value and y-value with the material name.

[0090] Note that even if the graph includes multiple broken lines, as in the example of FIG. 6A , the extraction unit 101 extracts the conductivity and temperature while distinguishing between them. In the example of FIG. 6A , the extraction unit 101 extracts the temperature and the corresponding conductivity for each scale on the x-axis of the graph. However, extraction is not required for each scale. For example, the extraction unit 101 may extract the temperature and the corresponding conductivity for each temperature indicated by an arbitrary temperature interval specified by the user. Specifically, in the example of FIG. 6A , the temperature and the corresponding conductivity are extracted for each of the temperatures of 1000°C, 1200°C, 1400°C, 1600°C, 1800°C, and 2000°C. In this case, the temperature interval is 200°C. However, the extraction unit 101 may set the temperature interval to 100°C in response to a user's input operation on the input unit 11. In this case, the extraction unit 101 extracts the temperature and the corresponding conductivity for each temperature indicated by 100°C temperature intervals in the range from 1000°C to 2000°C. That is, the extraction unit 101 extracts the temperatures of 1000°C, 1100°C, 1200°C, 1300°C, 1400°C, 1500°C, 1600°C, 1700°C, 1800°C, 1900°C, and 2000°C and the corresponding conductivity. This allows the user to reliably extract information such as conductivity and temperature that they wish to extract. Note that when extracting temperatures other than those marked with scales, the extraction unit 101 identifies the length between two scales and the temperatures on those scales, for example, by using an image recognition tool. Next, the extraction unit 101 interpolates the temperature at the midpoint between those scales using the identified length and temperature. This makes it possible to appropriately extract temperatures other than those marked on the scale and the conductivities corresponding to those temperatures.

[0091] 6B may also include line numbers or sentence numbers of sentences adjacent to the extracted figure numbers, making it possible to easily find sentences related to a figure by referring to the extraction list 33.

[0092] FIG. 7A shows an example of a diagram to be extracted by the extraction unit 101, and FIG. 7B shows an example of a diagram to be excluded from the extraction target by the extraction unit 101.

[0093] In addition to the figures related to the characteristic values ​​of materials, the main text data D1 also contains many figures unrelated to the characteristic values. Examples of figures unrelated to the characteristic values ​​include diagrams explaining the overview and experimental procedures, or photographs of experimental equipment and materials. Therefore, if all figures included in the main text data D1 are targeted for extraction, errors are likely to occur when extracting characteristic values, etc.

[0094] Therefore, the extraction unit 101 narrows down all diagrams included in the text data D1 to diagrams to be extracted as shown in FIG. 7A and excludes the diagrams shown in FIG. 7B from the extraction targets. Diagrams to be excluded from the extraction targets include, for example, diagrams showing reaction processes and diagrams showing material structures, as shown in FIG. 7B. For example, the extraction unit 101 narrows down the diagrams to be extracted by using an image recognition tool, a natural language processing tool, a deep learning tool, or the like. Examples of image recognition tools include OpenCV and Pillow. This allows for highly accurate narrowing down.

[0095] Alternatively, the extraction unit 101 may narrow down the figures to be extracted by using pattern matching using regular expressions. The extraction unit 101 extracts words, units, character strings, etc. from the captions, labels, etc. of the figures, and generates a regular expression from the extracted words, etc. The extraction unit 101 then compares the regular expression with a pattern, and treats figures containing a regular expression that matches the pattern as the figures to be extracted. Note that the above-mentioned labels are, for example, labels attached to the axes of a graph. This allows for highly accurate narrowing down of the figures.

[0096] Specifically, the extraction unit 101 extracts each word from the y-axis label "Conductivity (S / cm)" or the caption "Fig. 1. Temperature dependent electrical conductivity of Li6.25Al0.25La3Zr2O12 samples" of the graph shown in FIG. 6A, expresses these words as regular expressions, and compares the regular expressions with the patterns. For example, the regular expressions for "Conductivity" or "S / cm" included in the y-axis label match the patterns, and the regular expression for "conductivity" included in the caption matches the patterns. As a result, the extraction unit 101 treats the graph shown in FIG. 6A as the extraction target. This makes it possible to suppress processing that attempts to forcibly extract characteristic values ​​from diagrams that are not related to the characteristic values.

[0097] FIG. 8A shows an example of a table to be extracted from the main data D1, and FIG. 8B shows an example of characteristic values ​​extracted from the table to be extracted.

[0098] The extraction unit 101 extracts characteristic values ​​from the main data D1, for example, from Table 1 and Table 2 shown in Fig. 8A. To extract the characteristic values, the extraction unit 101 uses an image recognition tool, a deep learning tool, or pattern matching using regular expressions, as described above.

[0099] For example, in a table in which property values ​​are described, the column name cells may contain "conductivity," "eV," "S / cm," and "Scm －１" often contain keywords related to characteristic values. Therefore, the extraction unit 101 first detects these keywords from the table using a natural language processing tool, a deep learning tool, or pattern matching using regular expressions. The keywords may be registered in advance in the extraction unit 101. The extraction unit 101 then extracts characteristic values ​​from the table in which the keywords have been detected. For example, the extraction unit 101 detects keywords from column name cells of the table, detects material names from row name cells of the table, and extracts the value stored in the cell where the column of the column name cell intersects with the row of the row name cell as the characteristic value of the material name. This makes it possible to reliably extract characteristic values ​​related to pre-registered keywords.

[0100] Specifically, in Table 2 of the document ID “0001” in FIG. 8A, “Conductivity” and “Scm －１ " is written in one row name cell, and "Li6.25Al0.25La3Zr2O12(ours)" is written in one row name cell. Therefore, the extraction unit 101 detects a keyword for the characteristic value from the column name cell, detects the material name "Li6.25Al0.25La3Zr2O12(ours)" from the row name cell, and extracts the value "2.45" stored in the cell where the column of the column name cell intersects with the row of the row name cell as the characteristic value of that material name. The extraction unit 101 extracts the value "2.45" and the unit "Scm －１ " may be extracted as a characteristic value.

[0101] 8B , the extraction unit 101 records the detected material names, the detected keywords, and the extracted characteristic values ​​in the extraction list 34. At this time, the extraction unit 101 records the material names, for example, in the "row label" column in the extraction list 34, and records the keywords in the "column label" column in the extraction list 34. Furthermore, the extraction unit 101 records in the extraction list 34 the figure number of the table from which the characteristic values ​​were extracted and the document ID of the text data D1 that includes that table.

[0102] If a value other than conductivity, which is a characteristic value, is described in the table, the extraction unit 101 may extract that value as another characteristic value. For example, the value may be density. If a structure such as "Cubic" or "Hexagonal" is indicated, as in Table 1 of FIG. 8A , the extraction unit 101 may extract information indicating that structure. The extracted information indicating density and structure is recorded in the extraction list 34 together with conductivity. The information indicating density and structure may be treated as third information.

[0103] As described above, the extraction unit 101 in this embodiment extracts, for each of a plurality of materials, identification information (i.e., material name) for identifying the material and the characteristic value of the material from at least one piece of literature information D. The identification information is first information, and the characteristic value is second information. The extraction unit 101 extracts a plurality of type-specific characteristic values ​​as the characteristic values ​​of the material. The plurality of type-specific characteristic values ​​include a first-type characteristic value and a second-type characteristic value. For example, the first-type characteristic value is conductivity, and the second-type characteristic value is activation energy. Furthermore, the extraction unit 101 extracts, for each of the plurality of materials, attribute information indicating the attributes of the material from at least one piece of literature information D. The attribute information is third information. For example, the attributes include publication date, number of citations, author name, and temperature.

[0104] [Correction Process by First Information Processing Unit] The first information processing unit 102 acquires first information indicating the names of ingredients from the extraction unit 101. That is, the names of ingredients are acquired by the first information processing unit 102. In acquiring this first information, the first information processing unit 102 may acquire extraction lists 31 and 34 shown in FIGS. 5 and 8B, respectively, which include the first information, from the extraction unit 101. The first information processing unit 102 corrects the acquired ingredient names. This correction is also called a correction process or a normalization process.

[0105] FIG. 9 is a diagram showing an example of the normalization process of material names.

[0106] It is difficult to extract material names with 100% accuracy using natural language processing or machine learning such as deep learning. For example, material names are written in their official names (e.g., Li6.25Al0.25La3Zr2O12) at the beginning of a paper, but in the middle or later parts, they may be written in abbreviations (e.g., LALZO). Furthermore, material names may express the mixing ratio or state of each component. As a result, the name of a single material may be written in multiple forms. For example, multiple forms are written, such as sulfonated polyimide, SPI, SPI / poly(vinylidene fluoride) (PVDF) blends, 50 wt% of SPI content, etc. Therefore, as shown in FIGS. 5 and 9, the material name of the same material is recorded in a plurality of representations in the extraction list 31 generated by the extraction unit 101.

[0107] Therefore, the first information processing unit 102 converts the extraction list 31 into a corrected extraction list 31a by performing a normalization process that corrects the expression form of the material names included in the extraction list 31.

[0108] For example, the first information processing unit 102 recognizes the character string in parentheses of the material name "Li6.25Al0.25La3Zr2O12 (LALZ)" included in the extraction list 31 as an abbreviation for the character string outside the parentheses, and recognizes the character string outside the parentheses as the standard expression form of the material name. The first information processing unit 102 then determines that the abbreviation is equivalent to the standard expression form and deletes the parentheses and the abbreviation inside the parentheses from the material name. Furthermore, the first information processing unit 102 replaces the abbreviation included in the extraction list 31 with the standard expression form. Specifically, the first information processing unit 102 modifies the material name "LALZ" included in the extraction list 31 to "Li6.25Al0.25La3Zr2O12." Alternatively, the first information processing unit 102 deletes the abbreviation from the extraction list 31.

[0109] The first information processing unit 102 recognizes that x in the material name "Li6.25AlxLa(1-x)Zr2O12 (x = 0.1, 0.2, 0.3)" included in the extraction list 31 is a variable. The variable x indicates the mixing ratio of Al and La. The first information processing unit 102 then deletes (x = 0.1, 0.2, 0.3) from "Li6.25AlxLa(1-x)Zr2O12 (x = 0.1, 0.2, 0.3)" and substitutes the value of "x = 0.1, 0.2, 0.3" for the variable x of "Li6.25AlxLa(1-x)Zr2O12". As a result, the first information processing unit 102 decomposes “Li6.25AlxLa(1-x)Zr2O12 (x = 0.1, 0.2, 0.3)” into “Li6.25Al0.1La0.9Zr2O12”, “Li6.25Al0.2La0.8Zr2O12”, and “Li6.25Al0.3La0.7Zr2O12”. Then, the first information processing unit 102 corrects the pre-decomposition “Li6.25AlxLa(1-x)Zr2O12” included in the extraction list 31 into the three expression forms obtained by the decomposition.

[0110] The first information processing unit 102 compares the material name "60Li2SO4*40Li3BO3" and the material name "Li2SO4-Li3BO3" included in the extraction list 31, and determines that the material name "60Li2SO4*40Li3BO3" describes a mixing ratio. As a result, the first information processing unit 102 deletes "60Li2SO4*40Li3BO3" included in the extraction list 31. Alternatively, the first information processing unit 102 corrects "60Li2SO4*40Li3BO3" included in the extraction list 31 to "Li2SO4-Li3BO3".

[0111] The first information processing unit 102 corrects the expression forms of the material names included in the extraction list 31, thereby generating a corrected extraction list 31a.

[0112] The first information processing unit 102 may search the extraction list 31 for two material names whose start points or end points of the spans are close to each other and whose expression forms are similar to each other, and if the two material names are found, may determine that the material names are used for the same material. The first information processing unit 102 may determine that material names in multiple expression forms are used for the same material by performing dependency analysis or the like in natural language processing on the sentences in the text data D1.

[0113] When the extraction unit 101 extracts ingredient names and the like, garbled characters, extraction errors, and the like may occur. Garbled characters may occur, for example, due to an error when converting image data contained in a PDF or XML format file into text data. Extraction errors may occur, for example, due to corrupted characters. The first information processing unit 102 may detect such garbled characters and extraction errors and correct the ingredient names contained in the extraction list 31.

[0114] [Correction Process by Second Information Processing Unit] The second information processing unit 103 acquires second information indicating the property values ​​of the material from the extraction unit 101. That is, the property values ​​are acquired by the second information processing unit 103. In acquiring this second information, the first information processing unit 102 may acquire extraction lists 32, 33, and 34 shown in FIGS. 5, 6B, and 8B, respectively, which include the second information, from the extraction unit 101. The second information processing unit 103 corrects the acquired property values. This correction is also called a correction process or a conversion process.

[0115] FIG. 10 shows an example of a process for converting the characteristic values ​​of a material.

[0116] The second information processing unit 103 converts the combination of a number and a unit included in the characteristic value extracted by the extraction unit 101 into a number. The second information processing unit 103 converts the number in the characteristic value extracted by the extraction unit 101 into a number expressed using a reference unit, for example, by using a dictionary in which units frequently appearing in materials papers are registered in advance, and deletes the unit included in the characteristic value. The second information processing unit 103 may also convert the representation of a number using a power of 10 included in the characteristic value into a representation of a number that does not use a power of 10.

[0117] For example, as shown in FIG. 10, the second information processing unit 103 extracts the characteristic value “4.6×10 －３ SCM －１ ", by substituting "10-3" with 0.001 and calculating "4.6 x 0.001", the characteristic value "4.6 x 10 －３ SCM －１ The second information processing unit 103 converts the extracted characteristic value "5.4 mScm －１ " and then replace "m" with 0.001 and perform the calculation "5.4 x 0.001" to obtain the characteristic value "5.4 mScm －１ " is converted to "0.0054".

[0118] For example, "2.0-2.2 mScm －１ ", the extracted characteristic value may indicate a numerical range. In this case, the second information processing unit 103 detects the hyphenation symbol and recognizes that the characteristic value indicates a numerical range. As a result, the second information processing unit 103 interpolates the characteristic value between the numerical ranges to obtain the characteristic value "2.0-2.2 mScm －１ " to "0.0020, 0.0021, 0.0022." In this example, the second information processing unit 103 interpolates the characteristic values ​​at intervals of 0.0001, but the intervals may be changed automatically or may be set in response to an input operation by the user to the input unit 11.

[0119] For example, "4.38 (6) x 10 －３ SCM －１ The extracted characteristic value may contain an error, such as "4.38(6)×10". The error is indicated by a number in parentheses. In this case, the third information processing unit 104 calculates, for example, "0.00438±0.00006" to obtain the characteristic value "4.38(6)×10". －３ SCM －１ " is converted to "0.00444, 0.00432." In other words, the characteristic value including an error is converted to the maximum and minimum values ​​of the characteristic value within the error range.

[0120] The characteristic values ​​extracted by the extraction unit 101 from the figures in the main text data D1 may be incorrect. For example, the image of the figure to be extracted may be unclear, the multiple polygonal lines included in the figure may overlap too much, the polygonal lines may be unclear, or the figure may be too small. In such cases, the characteristic values ​​after extraction may be incorrect. Specifically, as shown in FIG. 6A , the graph in the main text data D1 for document ID "0002" includes a partially enlarged figure. This partially enlarged figure may be the cause of the incorrect characteristic values ​​extracted by the extraction unit 101.

[0121] The second information processing unit 103 may correct or delete such erroneous characteristic values. For example, the second information processing unit 103 may use an image recognition tool to estimate portions of a figure where errors are likely to occur and delete characteristic values ​​extracted from those portions. Alternatively, the second information processing unit 103 may compare characteristic values ​​extracted from a figure with characteristic values ​​extracted from other figures in the same text data D1, detect characteristic values ​​that are significantly different from each other, and delete those characteristic values. If the characteristic value is conductivity, the second information processing unit 103 may use, for example, a dictionary in which the range of values ​​that conductivity can take is pre-registered, and delete the extracted conductivity if it falls outside the registered range. Alternatively, the second information processing unit 103 may clip the conductivity to the upper or lower limit of the range.

[0122] The extraction list 34, which includes the characteristic values ​​extracted by the extraction unit 101 from the table of the text data D1, may be incorrect. For example, as shown in FIG. 8A, Table 2 of document ID "0001" has two rows of column labels. That is, there is a column label in which "Experimental1" is written and a column label in which "Conductivity (mScm-1)" is written. In this case, as shown in FIG. 8B, the extraction unit 101 may erroneously record "Experimental1" in the column of column labels in the extraction list 34 when it should record "Conductivity (mScm-1)."

[0123] In this case, the second information processing unit 103 compares the characteristic value "2.45" shown in the extraction list 34 with the range of values ​​that conductivity can take in the dictionary. If the characteristic value is within the range of values, the second information processing unit 103 determines that the characteristic value is associated with "Conductivity (mScm-1)" even if "Experimental1" is associated with the characteristic value in the extraction list 34. As a result, the second information processing unit 103 replaces "Experimental1" in the extraction list 34 with "Conductivity (mScm-1)" and treats the characteristic value as conductivity.

[0124] The characteristic value extracted from the table of the text data D1 by the extraction unit 101 may be incorrect. For example, if the table is unclear, the extracted characteristic value may be incorrect. In this case, the second information processing unit 103 may detect an error in the characteristic value by comparing the characteristic value with the range of values ​​that the characteristic value can take, which is registered in the dictionary.

[0125] [Correction Process by Third Information Processing Unit] The third information processing unit 104 acquires third information indicating the attributes of the material from the extraction unit 101. That is, the attributes are acquired by the third information processing unit 104. In acquiring this third information, the third information processing unit 104 may acquire an extraction list 33 shown in FIG. 6B , which includes the third information, from the extraction unit 101. The extraction list 33 indicates the temperature, which is the x value, as the third information. The third information processing unit 104 corrects this acquired third information, i.e., the attributes, in the same manner as the first information processing unit 102 and the second information processing unit 103.

[0126] [Integration of Information] The derivation unit 105 generates integrated information by acquiring and integrating the information output from the first information processing unit 102, the second information processing unit 103, and the third information processing unit 104 for each piece of text data D1. That is, the derivation unit 105 associates the processed first information output from the first information processing unit 102, the processed second information output from the second information processing unit 103, and the processed third information output from the third information processing unit 104 with the document ID of the text data D1. The processed first information, the processed second information, and the processed third information indicate the corrected material name, the corrected characteristic value, and the corrected attribute, respectively. This generates integrated information in which the material name, the characteristic value, and the attribute are associated with the document ID.

[0127] For example, the derivation unit 105 acquires corrected extraction lists (e.g., extraction list 31a) from the first information processing unit 102, the second information processing unit 103, and the third information processing unit 104 for each of the text data D1. The derivation unit 105 then determines the distance between the material name and the characteristic value and the distance between the material name and the attribute based on the figure number, extracted line number, span, etc., indicated in the extraction lists, and associates the material name, characteristic value, and attribute. The derivation unit 105 associates material names, characteristic values, and attributes extracted from the same sentence or figure. Furthermore, the derivation unit 105 can also associate material names, characteristic values, and attributes extracted from multiple adjacent sentences. The distance may be the difference between the extracted line numbers in which the two pieces of information are written, or it may be a distance based on the extracted line number and the span. For example, the derivation unit 105 may determine the distance between the material name and the characteristic value by calculating the number of characters from the end point of the material name to the start point of the characteristic value. The derivation unit 105 may create an association rule based on the distance, or may associate the material name, the property value, and the attribute using a dependency tool for natural language processing, such as ChemDataExtractor.

[0128] Then, the derivation unit 105 outputs the integrated information of each of the plurality of pieces of text data D1 to the image processing unit 106. The image processing unit 106 acquires the integrated information from the derivation unit 105 and updates the extracted information table 22 by including the integrated information in the extracted information table 22.

[0129] FIG. 11 is a diagram showing an example of the extracted information table 22 after updating.

[0130] The updated extracted information table 22 includes integrated information extracted from each piece of text data D1, namely, first information, second information, and third information. The first information indicates the name of the final material, the two second information items indicate the conductivity and activation energy values, respectively, and the two third information items indicate the author name and the research institution name, respectively. Note that "author" and "research institution," which are listed as information type names in the extracted information table 22, refer to the author name and the research institution name, respectively.

[0131] 11, the author name and the research institution name are extracted as third information, i.e., as attributes, from the main text data D1. However, these attributes may be extracted from the metadata D2 of the document information D. In the example shown in FIG. 11, the final material name is "LiSo...", but specific examples of the final material name include "Li7La3Zr2O12", "LiCoO2", "Li3P-LiCl", "Li1.33Ti1.67O4", and "Li2CO3".

[0132] FIG. 12 is a diagram showing an example of the display screen 20 including the updated extracted information table 22.

[0133] As shown in FIG. 12 , the image processing unit 106 displays a display screen 20 including the updated extracted information table 22 on the display unit 13. At this time, the image processing unit 106 includes a graph display start button 23c on the display screen 20. The graph display start button 23c is a button for starting the display of a characteristic value graph. In the example of FIG. 12 , conductivity and activation energy are characteristic values. The characteristic value graph is a graph showing characteristic values ​​indicated in each piece of literature information D. Note that although the extracted information table 22 shown in FIG. 12 does not show author names and research institution names, these names may also be shown.

[0134] By referring to the extracted information table 22 on the display screen 20, the user can confirm which materials have which characteristic values ​​are described in which publication dates. The display screen 20 shown in FIG. 12 does not include the literature list window 21 shown in FIGS. 2A and 2B, but the literature list window 21 may be included. In this case, the user may deselect the icon of literature information D in the literature list window 21 or select a new icon by performing an input operation on the input unit 11. In response to this selection or deselection, the image processing unit 106 may update the extracted information table 22. Using this extracted information table 22, analysis by era or analysis narrowed down to a specific material field can be performed.

[0135] Fig. 13 is a diagram showing an example of a graph display screen including a characteristic value graph. "Activation" in Figs. 13, 14, 15A, 15B, and 15C means "activation energy."

[0136] For example, the user selects the graph display start button 23c on the display screen 20 shown in Fig. 12 by performing an input operation on the input unit 11. This causes the input unit 11 to output an input signal prompting the display of a characteristic value graph to the image processing unit 106. Upon receiving the input signal, the image processing unit 106 switches the display screen 20 displayed on the display unit 13 to a graph display screen 20a.

[0137] 13, the graph display screen 20a includes a characteristic value graph 24, a reliability display button 23d, and a return button 23e. The reliability display button 23d is a button for displaying the reliability of the characteristic value corresponding to the mark plotted on the characteristic value graph 24. The return button 23e is a button for returning the graph display screen 20a to the display screen 20 in FIG. 12, and this return button 23e has a character string such as "Return to table" attached to it.

[0138] The characteristic value graph 24 is a graph in which the horizontal axis indicates activation energy values ​​and the vertical axis indicates conductivity. For each material name (i.e., final material name) listed in the extracted information table 22, the image processing unit 106 plots marks on the characteristic value graph 24 at positions corresponding to two types of characteristic values ​​associated with that material name. The two types of characteristic values ​​are a first-type characteristic value and a second-type characteristic value, specifically, conductivity and activation energy values. In the example shown in FIG. 13 , the marks are x marks. The image processing unit 106 then assigns the corresponding material names near the marks. As a result, a characteristic value graph 24 showing the conductivity and activation energy values ​​of each of the multiple materials extracted from the multiple literature information D selected by the user is displayed on the graph display screen 20 a. The characteristic value graph 24 shows the conductivity and activation energy values ​​associated with the material names.

[0139] The materials or material names corresponding to the marks plotted on the characteristic value graph 24 may be the same or different. For example, these materials may be materials for the same purpose, such as those used in the negative or positive electrodes of a battery, and each may contain the element Li. These materials may each contain the same multiple element species, but may have different composition ratios of these element species. In the examples shown in FIGS. 13 to 15C, the material name is "LiSo...", but specific examples of such material names include "Li7La3Zr2O12", "LiCoO2", "Li3P-LiCl", "Li1.33Ti1.67O4", and "Li2CO3".

[0140] For example, a user such as a materials researcher can refer to such a graph display screen 20a to search for a material that is suitable for his / her own experimental environment or experimental subject, taking into consideration the balance of characteristic values.

[0141] The image processing unit 106 may automatically adjust the scales of the vertical and horizontal axes of the characteristic value graph 24. Such an automatic scale adjustment function is expected to help the user accurately grasp the overall picture of the characteristic values. For example, the image processing unit 106 determines a scale according to the maximum and minimum values ​​of the characteristic values ​​shown in the extracted information table 22. In a specific example, the image processing unit 106 sets the minimum value of the characteristic value to the origin of the characteristic value graph 24 and the maximum value to the end of the axis of the characteristic value graph 24. However, if the extracted information table 22 contains outliers as characteristic values, the presence of the outliers may make it difficult to observe characteristic values ​​other than the outliers on the characteristic value graph 24. In a specific example, 99% of all characteristic values ​​included in the extracted information table 22 are within the range of 0 to 0.001, and the remaining 1% are within the range of 1.0 to 2.0. In this case, the 1% characteristic values ​​are outliers. If the scale is determined using these characteristic values, a 1% outlier will result in the axis of the characteristic value graph 24 corresponding to that characteristic value being scaled in 0.1 increments in the range of 0 to 2.0. As a result, it becomes difficult to properly observe the 99% of characteristic values ​​that are the intended target of observation. Therefore, the image processing unit 106 may omit the outliers included in the extracted information table 22 and generate the characteristic value graph 24 based on the characteristic values ​​other than those outliers. This allows proper observation of the intended target of observation characteristic values.

[0142] Alternatively, the image processing unit 106 may adjust the scales of the vertical and horizontal axes of the characteristic value graph 24 according to the type of material. For example, the image processing unit 106 identifies the type of material from the material name of the material and sets the scales of the characteristic values ​​associated with that type as the scales of the vertical and horizontal axes of the characteristic value graph 24. In a specific example, when a solid electrolyte is identified as the type of material, the conductivity of solid electrolytes is 0 to 0.001 S / cm, so the image processing unit 106 sets the scale of the axis corresponding to conductivity in the characteristic value graph 24 to 0 to 0.001. This range of conductivity of solid electrolytes may be registered in memory in advance. The image processing unit 106 may adjust the scales of the vertical and horizontal axes of the characteristic value graph 24 in response to a user's input operation on the input unit 11. When the image processing unit 106 determines that the characteristic value is conductivity, it may set a logarithmic scale predetermined for conductivity as the axis of the characteristic value graph 24.

[0143] When a mark is selected in response to a user's input operation on the input unit 11, the image processing unit 106 may obtain literature information D, which describes the material name and two types of characteristic values ​​corresponding to the mark, via the extraction unit 101 and display it on the display unit 13.

[0144] [Reliability Deriving Process] For example, the user selects the reliability display button 23d on the graph display screen 20a shown in FIG. 13 by performing an input operation on the input unit 11. As a result, the input unit 11 outputs an input signal prompting the display of reliability to the derivation unit 105. Upon receiving the input signal, the derivation unit 105 derives the reliability of the conductivity and activation energy value of each material shown in the characteristic value graph 24. The derivation unit 105 then outputs an output signal including the derived reliability to the image processing unit 106. Upon receiving the output signal from the derivation unit 105, the image processing unit 106 changes the display mode of the mark of each material plotted on the characteristic value graph 24 to one that corresponds to the reliability derived for the conductivity and activation energy value of that material.

[0145] In a specific example, the derivation unit 105 calculates the distance between the mark of the material to be derived and the marks of each of the other materials, and further calculates the average value of these distances. The distance may be Euclidean distance, Manhattan distance, or other distances. Next, the derivation unit 105 calculates the similarity of the characteristic values ​​of the material to be derived. The larger the average value of the distances between the mark of the material to be derived and the marks of each of the other materials, the smaller the similarity, and vice versa. For example, the similarity is expressed as a numerical value ranging from 0 to 100. The characteristic values ​​are conductivity and activation energy. Next, the derivation unit 105 determines the reliability of the similarity. In this manner, in this embodiment, one reliability is calculated for two types of characteristic values ​​of the material to be derived.

[0146] The above process will be exemplified for a case where eight different coordinates are displayed on the characteristic value graph 24 in Fig. 13 (the updated extracted information table 22 in Fig. 12 has data ID001 to ID008). The coordinate (0.41, 0.048) corresponding to the first pair of conductivity and activation energy values ​​identified by ID001 will be called the first coordinate, and the coordinate (0.15, 0.077) corresponding to the eighth pair of conductivity and activation energy values ​​identified by ID008 will be called the eighth coordinate. The number of different coordinates may be any number other than eight.

[0147] The derivation unit 105 calculates the distance L12 between the first coordinate and the second coordinate, L18 between the first coordinate and the eighth coordinate, L23 between the second coordinate and the third coordinate, L28 between the second coordinate and the eighth coordinate, L78 between the seventh coordinate and the eighth coordinate. The number of calculated distances is (8 × 7) / 2 = 28.

[0148] The derivation unit 105 calculates the average for the first coordinate, L(avg1) = (L12 + ... + L18) / 7, the average for the second coordinate, L(avg2) = (L12 + L23 + ... + L28) / 7, ..., the average for the eighth coordinate, L(avg8) = (L18 + L28 + ... + L78) / 7.

[0149] The derivation unit 105 sets the similarity of the conductivity and activation energy value for the n-th set to be small when L(avgn) is large, and sets the similarity of the conductivity and activation energy value for the n-th set to be large when L(avgn) is small, where n is a natural number from 1 to 8.

[0150] FIG. 14 is a diagram showing an example of a graph display screen 20a showing the reliability.

[0151] As shown in FIG. 14 , the image processing unit 106 displays each mark plotted on the characteristic value graph 24 in a manner corresponding to the reliability of the two characteristic values ​​of the material represented by the mark, i.e., the reliability of the conductivity and activation energy value. In a specific example, the marks are circular, and the image processing unit 106 darkens the color of the mark corresponding to the two characteristic values ​​as the reliability of the two characteristic values ​​increases, and lightens the color of the mark corresponding to the two characteristic values ​​as the reliability of the two characteristic values ​​decreases. In other words, the image processing unit 106 darkens the color of multiple marks as the density of the marks increases on the characteristic value graph 24, and lightens the color of the marks as the density decreases. Therefore, marks located far from many other marks are displayed lighter, allowing the user to determine that the characteristic values ​​of the material corresponding to the marks are relatively unreliable. Conversely, marks located close to each other are displayed darker, allowing the user to determine that the characteristic values ​​of the material corresponding to the marks are relatively reliable.

[0152] The image processing unit 106 displays a reliability hide button 23f on the graph display screen 20a instead of the reliability display button 23d. The reliability hide button 23f is a button for hiding the reliability, and is a button for returning the graph display screen 20a shown in Fig. 14 to the graph display screen 20a shown in Fig. 13, for example.

[0153] In this manner, in this embodiment, the reliability of the property values ​​extracted from the literature information D is presented to the user. If the multiple literature information D selected by the user are electronic data of papers related to material synthesis experiments, the reliability is an index representing the reproducibility of a single experiment described in that paper, estimated based on information extracted from a single paper. Reproducibility is an index indicating the ratio of the number of successes to the number of attempts when an experiment is actually performed multiple times. If a single author conducts similar experiments, obtains materials with similar property values, and publishes them in multiple papers, the greater the number of publications, the higher the probability of success in the synthesis experiment of that material. Therefore, reproducibility can also be calculated from the number of papers published by a single author. If similar property values ​​are described in papers published by different authors or different research institutions, a high reliability can be presented, and the reliability can be visualized taking into account the development skills of the authors or research institutions. Even if multiple property values ​​are measured using different devices, if the property values ​​are similar, the reliability of the property values ​​can be determined to be high, which is expected to have the effect of increasing the accuracy of the reliability. Therefore, it is expected that this embodiment will be useful for material researchers who place importance on the number of papers on material synthesis that have been reported in the past when searching for desired materials.

[0154] In this embodiment, the reliability of two characteristic values, conductivity and activation energy, is presented. However, these may be other characteristic values, or the reliability of one characteristic value may be presented. In this embodiment, the characteristic value graph 24 is configured with two axes representing conductivity and activation energy. However, it may also be configured with three axes representing three characteristic values. In other words, the characteristic value graph 24 may be configured as a three-dimensional graph. One of the three characteristic values ​​may be a condition used in material synthesis, such as temperature or time. Furthermore, the characteristic value graph 24 may be configured with four or more axes. In other words, this characteristic value graph 24 shows four or more characteristic values. Note that, because it is difficult to visualize a characteristic value graph 24 with four or more axes, the characteristic value graph 24 may be configured by reducing the number of axes to two or three using a dimensionality reduction method such as PCA (Principal Component Analysis) or t-SNE (t-Distributed Stochastic Neighbor Embedding). The image processing unit 106 may select the type and number of axes in response to a user's input operation on the input unit 11. Such selection of the type of axis and increase in the number of axes can improve the expressiveness of characteristic values, allowing for more detailed analysis.

[0155] The function of changing the color intensity of the mark corresponding to a material depending on the reliability of the material's property value is a necessary function for materials researchers to quickly check a large number of property values, and has the effect of clearly indicating areas of interest in the property value graph 24. For example, when a user is searching for a material with an emphasis on high reproducibility, they can search for materials by focusing on materials with darker marks. Conversely, when a user is searching for a material with an emphasis on rarity, they can search for materials by focusing on materials with lighter marks. This enables materials to be searched for according to the objectives of users such as materials researchers.

[0156] The color of the mark for a material plotted on the characteristic value graph 24 may be the same as the color used for the main component element of that material in the element symbol table commonly used by the user. For example, if the main component element of a material is Li, and the Li region in the element symbol table is displayed in yellow, the image processing unit 106 may display the mark for that material in yellow on the display unit 13. In a specific example, the image processing unit 106 stores data indicating the element symbol table commonly used by the user in advance, identifies the main component element of the material displayed in the extracted information table 22, and determines the color corresponding to that element based on the previously stored data. The image processing unit 106 then sets the color of the mark corresponding to that material to the color determined as described above and plots the mark of that color on the characteristic value graph 24. This allows the user to easily identify the main component of the corresponding material from the color of each mark displayed on the characteristic value graph 24, thereby further improving the efficiency of data analysis.

[0157] In this manner, the derivation unit 105 in this embodiment derives the reliability of the characteristic value of each of the plurality of materials based on the similarity of the characteristic value between that material and one or more other materials. Then, the image processing unit 106 generates a first image that (i) displays the characteristic value of each of the plurality of materials in a display format corresponding to the reliability derived for that material's characteristic value, and (ii) associates the characteristic value with the material's identification information, and outputs the first image to the display unit 13. The first image is, for example, the graph display screen 20a shown in FIG. 14 . As a result, in the displayed first image, the characteristic value of each of the plurality of materials is displayed in a display format corresponding to the reliability of that characteristic value, and the characteristic value is associated with the material's identification information. Therefore, by viewing the first image, a user such as a materials researcher can easily grasp the reliability of the characteristic values ​​of materials described in the vast amount of literature information D stored in the literature database 12.

[0158] The image processing unit 106 sets a characteristic map on the first image, the characteristic map being configured with a first coordinate axis for indicating the first-type characteristic value, which is conductivity, and a second coordinate axis for indicating the second-type characteristic value, which is activation energy. This characteristic map is, for example, the characteristic value graph 24 of FIG. 14 . The image processing unit 106 then superimposes marks corresponding to each of the multiple materials on the characteristic map at positions corresponding to the first-type characteristic value and the second-type characteristic value of that material, in a display mode corresponding to the reliability derived for that material's characteristic value. This makes it easier to grasp the overall reliability of the multiple type characteristic values ​​possessed by each material.

[0159] The derivation unit 105 determines the similarity of the characteristic values ​​of a material based on the distance between the mark corresponding to the material and the marks corresponding to each of one or more other materials. This allows one similarity to be appropriately determined for multiple type characteristic values ​​of the material, and as a result, allows the reliability based on the similarity to be appropriately derived.

[0160] The image processing unit 106 determines the display mode of the material characteristic value, with a darker color intensity corresponding to a higher reliability of the characteristic value, and generates a first image showing the characteristic value in the determined color intensity. This allows the user to visually easily grasp the reliability of the characteristic value. Note that in this embodiment, the characteristic value graph 24 is used, and a mark indicating the characteristic value is displayed in the determined color intensity. However, if the characteristic value graph 24 is not used, the numerical value of the characteristic value itself may be displayed in the determined color intensity.

[0161] FIG. 15A is a diagram showing another example of the graph display screen 20a showing the reliability.

[0162] In the example shown in FIG. 14 , the derivation unit 105 derives the similarity based on the distance as the reliability. That is, if the similarity is R0 and the reliability is K, the derivation unit 105 calculates the reliability K by K = 1 × R0. However, the derivation unit 105 may also reflect the similarity R0 and attribute values ​​corresponding to the material attributes in the reliability K calculation. For example, if the four attribute values ​​are R1, R2, R3, and R4, the derivation unit 105 calculates the reliability K by K = (p × R0) + (a × R1) + (b × R2) + (c × R3) + (d × R4), that is, by weighting and adding the four attribute values ​​R1 to R4 and the similarity R0. p is the weight for the similarity R0, a is the weight for the attribute value R1, and b is the weight for the attribute value R2. c is a weight for attribute value R3, and d is a weight for attribute value R4. In other words, the derivation unit 105 applies multiple types of bias to the derivation of the reliability K. The weights p and a to d satisfy p+a+b+c+d=1 and are set to values ​​according to the input operation by the user to the input unit 11. Note that the weight p for similarity R0 satisfies 0<p≦1, and each of the weights a to d for attribute values ​​R1 to R4 satisfies 0≦[a, b, c, d]<1. The weights are also called biases.

[0163] For example, as shown in FIG. 15A, the image processing unit 106 displays slider bars 25a to 25d for adjusting the weights a to d of the attribute values ​​R1 to R4 on the graph display screen 20a.

[0164] The slider bar 25a is a display element for setting the weight a of the publication date-based attribute value R1 according to the position of the slider 1sa. The publication date is the publication date of the literature information D from which the material name, conductivity, and activation energy values ​​of the material were extracted, and is an attribute of the material. The derivation unit 105 determines the publication date-based attribute value R1 to be a value closer to 100 the more recent the publication date, and closer to 0 the older the publication date. The derivation unit 105 sets the weight a to 0 when the slider 1sa is at the left end and to a value that increases as the slider 1sa approaches the right end. For example, when the slider 1sa is at the center of the slider bar 25a, the weight a may be 0.5.

[0165] The slider bar 25b is a display element for setting the weight b of the citation-based attribute value R2 according to the position of the slider 1sb. The citation count is the number of citations of the literature information D from which the material name, conductivity, and activation energy value of a material have been extracted, and is an attribute of that material. The derivation unit 105 determines the citation-based attribute value R2 to be a value closer to 100 the greater the citation count, and closer to 0 the smaller the citation count. The derivation unit 105 sets the weight b to 0 when the slider 1sb is at the left end and to a value that increases as the slider 1sb approaches the right end. For example, when the slider 1sb is at the center of the slider bar 25b, the weight b may be 0.5.

[0166] The slider bar 25c is a display element for setting the weight c of the author-name-based attribute value R3 according to the position of the slider 1sc. The author name is the name of the author of the literature information D from which the material name, conductivity, and activation energy values ​​of the material were extracted, and is an attribute of the material. The derivation unit 105 determines the author-name-based attribute value R3 to be a value closer to 100 the more well-known the author name is, and a value closer to 0 the less well-known the author name is. Note that the information providing device 100 may store data indicating the well-known level of each author name. The derivation unit 105 sets the weight c to 0 when the slider 1sc is at the left end and a value that increases as the slider 1sc approaches the right end. For example, when the slider 1sc is at the center of the slider bar 25c, the weight c may be 0.5.

[0167] The slider bar 25d is a display element for setting the weight d of the temperature-based attribute value R4 according to the position of the slider 1sd. The temperature is the temperature used to synthesize the material of the extracted material name and is an attribute of that material. This temperature can also be considered one of the conditions included in the material synthesis method. The derivation unit 105 calculates the difference between the temperature of the material and the temperature of one or more other materials, and determines the temperature-based attribute value R4 of that material as a value closer to 100 when the average value of the differences is smaller and closer to 0 when the average value is larger. In other words, this attribute value R4 indicates the temperature similarity. The derivation unit 105 sets the weight d to 0 when the slider 1sd is at the left end and a value that increases as the slider 1sd approaches the right end. For example, when the slider 1sd is at the center of the slider bar 25d, the weight d may be 0.5.

[0168] The publication date, the number of citations, the author's name, and the temperature are each extracted by the extraction unit 101 as third information.

[0169] The user adjusts the positions of sliders 1sa to 1sd of slider bars 25a to 25d by performing an input operation on the input unit 11. For example, the user moves each of sliders 1sa to 1sd to the left end. In this case, the derivation unit 105 sets weights a to d for publication date, citation count, author name, and temperature to 0 and sets weight p for similarity R0 to 1 in accordance with the input signal output from the input unit 11 by the user's input operation. As a result, the derivation unit 105 calculates the reliability K using similarity R0 as K = (1 × R0) + (0 × R1) + (0 × R2) + (0 × R3) + (0 × R4), as in the example shown in FIG. 14 . As a result, the image processing unit 106 displays a characteristic value graph 24 similar to the example shown in FIG. 14 on the display unit 13, including it in the graph display screen 20a, as shown in FIG. 15A.

[0170] In this manner, the derivation unit 105 in this embodiment derives the reliability K of the characteristic value of a material based on the similarity R0 of the characteristic value of the material and the attribute information extracted for that material. That is, the derivation unit 105 derives the reliability K of the characteristic value of a material by weighting the similarity R0 of the characteristic value of the material and the attribute values ​​R1 to R4 based on the attribute information extracted for that material. This derives the reliability K of the characteristic value based on the similarity R0 of the characteristic value and the attributes of the material, allowing the reliability K to be derived from multiple angles, thereby improving the accuracy of the reliability K. By adjusting the weights of the similarity R0 and the attributes as biases, the reliability K can be derived according to the user's purpose.

[0171] 15B and 15C are diagrams showing an example of the graph display screen 20a after the bias has been changed.

[0172] As shown in FIG. 15B, the user performs an input operation on the input unit 11 to move slider 1sa, one of sliders 1sa to 1sd of slider bars 25a to 25d, from the position shown in FIG. 15A to the far right. In this case, the derivation unit 105 sets the weight a for the publication date to, for example, 0.9, the weights b to d for the citation count, author name, and temperature to 0, and the weight p for the similarity R0 to 0.1, in response to the input signal output from the input unit 11 in response to the input operation. As a result, the derivation unit 105 calculates the reliability K by K = (0.1 × R0) + (0.9 × R1) + (0 × R2) + (0 × R3) + (0 × R4), i.e., by heavily biasing the publication date. As a result, the image processing unit 106 displays a characteristic value graph 24, different from the examples shown in FIGS. 14 and 15A, on the display unit 13, including it in the graph display screen 20a, as shown in FIG. 15B. In other words, the publication date has a greater influence on the reliability K than the similarity R0, and the earlier the publication date of the document information D, the darker the color of the mark corresponding to the material name, conductivity, and activation energy value extracted from that document information D is likely to be displayed.

[0173] In other words, simply because the plotted marks are densely packed does not cause the colors of those marks to become darker; the closer the plotted marks are and the more recent the publication dates corresponding to those marks, the darker the colors of those marks will be displayed. Thus, with the settings of slider bars 25a to 25d shown in FIG. 15B , the newer the document information D from which characteristic values ​​and the like are extracted, the higher the reliability K of that characteristic value, i.e., the darker the mark corresponding to that characteristic value will be displayed. Therefore, it is expected that this embodiment will be useful for materials researchers who place importance on the recency of document information D, such as papers, when searching for desired materials.

[0174] As described above, in this embodiment, the attribute information indicates, as an attribute, the publication date of at least one piece of literature information D, which contains the identification information and characteristic values ​​of the material corresponding to the attribute information. The publication date is the publication date described above, and may also be the publication date. The derivation unit 105 then derives the reliability K of the characteristic value using the attribute value R1, which indicates the recency of the publication date. Specifically, the attribute value R1 indicates a larger value the more recently the publication date. The derivation unit 105 then derives a larger value as the reliability K of the characteristic value of the material, the higher the similarity R0 of the characteristic value of the material and the larger the attribute value R1 corresponding to the material. This makes it possible to derive a relatively high reliability K for characteristic values ​​described in new literature information D. Therefore, it is possible to derive an appropriate reliability K for users who place importance on the publication date.

[0175] Next, as shown in FIG. 15C , the user moves each of sliders 1sa to 1sd of slider bars 25a to 25d to the right by performing an input operation on input unit 11. Derivation unit 105 sets weights p and a to d according to the input signal output from input unit 11 in response to the input operation, i.e., according to the distance from the left end of each of sliders 1sa to 1sd. The ratio of each of weights a to d is set to the ratio of the distance from the left end of each of sliders 1sa to 1sd. For example, in the example of FIG. 15C , weights a to d are set as follows: (temperature weight d) > (author name weight c) > (citation count weight b) = (publication date weight a), and weight p for similarity R0 is set as p = 1 - (a + b + c + d).

[0176] As a result, the derivation unit 105 calculates the reliability K by K = (p × R0) + (a × R1) + (b × R2) + (c × R3) + (d × R4), i.e., by biasing the similarity R0, publication date, citation count, author name, and temperature by a value greater than zero. As a result, the image processing unit 106 displays a characteristic value graph 24 on the display unit 13, which is different from the examples in FIGS. 14, 15A, and 15B, including it in the graph display screen 20a, as shown in FIG. 15C. In other words, the more similar the temperature of the material synthesis to that of other materials, the more well-known the author name, the more citations, and the earlier the publication date, the darker the color of the corresponding material mark will likely be. Setting the slider bars 25a-25d in this way is expected to be useful for materials researchers who wish to search for materials from multiple perspectives or in a sophisticated manner.

[0177] As described above, in this embodiment, the attribute information indicates, as an attribute, the number of citations of at least one piece of literature information D containing the identification information and characteristic values ​​of the material corresponding to the attribute information. The derivation unit 105 then derives the reliability K of the characteristic value using an attribute value R2 corresponding to the number of citations. Specifically, the greater the number of citations, the greater the attribute value R2. The derivation unit 105 then derives a greater value as the reliability K of the characteristic value of the material, the higher the similarity R0 of the characteristic value of the material and the greater the attribute value R2 corresponding to the material. This allows a relatively high reliability K to be derived for characteristic values ​​described in literature information D with a high number of citations. Therefore, it is possible to derive an appropriate reliability K for a user who places importance on the number of citations.

[0178] In this embodiment, the attribute information indicates the synthesis method of the material corresponding to the attribute information as an attribute. The derivation unit 105 then derives the reliability K of the characteristic value using an attribute value R4 corresponding to the degree of similarity between the synthesis method of the material and each of the synthesis methods of one or more other materials. The synthesis method of the material is the temperature conditions used for material synthesis, as in the example of FIG. 15C . Note that the synthesis method may not be the temperature conditions, but may be the time conditions or the type of equipment used for material synthesis. In other words, the synthesis method of the material may include at least one of the temperature conditions, time conditions, and type of equipment used for material synthesis. Specifically, the attribute value R4 indicates a larger value as the degree of similarity between the synthesis method of the material and each of the synthesis methods of one or more other materials increases. The derivation unit 105 derives a larger value as the reliability K of the characteristic value of the material increases as the similarity R0 of the characteristic value of the material increases and as the attribute value R4 corresponding to the material increases. As a result, if the document information D describes that a material with that characteristic value is synthesized using the same synthesis method as other document information D, a relatively high reliability K can be derived for that characteristic value. Therefore, it is possible to derive an appropriate reliability K for a user who places importance on the synthesis method.

[0179] In this embodiment, the attribute information indicates, as an attribute, the author of at least one piece of literature information D, which contains the identification information and characteristic values ​​of the material corresponding to the attribute information. The deriving unit 105 then derives the reliability K of the characteristic value using an attribute value R3 corresponding to the name recognition of the author of the literature information D. Specifically, the attribute value increases as the name recognition of the author increases. The deriving unit 105 then derives a larger value as the similarity R0 of the characteristic value of the material increases and the attribute value R3 corresponding to the material increases. This allows a relatively high reliability K to be derived for characteristic values ​​described in literature information D whose authors are highly known. Therefore, it is possible to derive an appropriate reliability K for a user who places importance on the name recognition of the author of the literature information D.

[0180] The derivation unit 105 may derive the reliability K of the characteristic value using an attribute value R3a corresponding to whether the author of the document information D is the same as each of the authors of one or more other documents D. That is, the attribute value R3a may be used instead of the attribute value R3. Specifically, the attribute value R3a increases as the number of authors of the one or more other documents D who are different from the author of the document information D increases. The derivation unit 105 derives a higher value as the similarity R0 of the characteristic value of the material increases and the attribute value R3a corresponding to the material increases. This allows a relatively high reliability K to be derived for characteristic values ​​described in document information D written by an author different from the authors of many other documents D. That is, if characteristic values ​​described in many documents D written by different authors are similar, a high reliability K is derived for those characteristic values. On the other hand, even if similar characteristic values ​​are described in many pieces of document information D, if those pieces of document information D are written by the same author, a low reliability K is derived for those characteristic values. Therefore, it is possible to derive an appropriate reliability for a user who places importance on the identity of the author of the document information D.

[0181] 15A to 15C, the bias is adjusted for each of the four attributes, namely, publication date, number of citations, author name, and temperature, but the bias may also be adjusted for another attribute (i.e., third information) included in the extracted information table 22 of Fig. 11 or 12. In response to an input operation by the user to the input unit 11, the image processing unit 106 may increase or decrease the number of slider bars for adjusting the bias.

[0182] If the document D is a paper, the publication date, submission date, and adoption date may be indicated in the metadata D2. In this case, the extraction unit 101 may extract the submission date and adoption date from the metadata D2 as material attributes, and the derivation unit 105 may include these attributes in the extracted information table 22. The derivation unit 105 may then use an attribute value R5 corresponding to the period from the submission date to the adoption date instead of the attribute value R1 based on the publication date, or may use the attribute value R5 together with the attribute value R1 to calculate the reliability K. In this case, the derivation unit 105 may determine, for example, as the attribute value R5, a value closer to 100 the shorter the period from the submission date to the adoption date, and a value closer to 0 the longer the period. The derivation unit 105 then calculates the reliability K by performing weighted addition including the attribute value R5.

[0183] This allows the reliability K to be presented taking into account the period from the submission date to the acceptance date, providing meaningful information to materials researchers who place importance on such periods. In other words, if the period from the submission date to the acceptance date is long, the paper corresponding to that period may have undergone repeated revisions based on shortcomings identified by peer reviewers. Such repeated revisions can reduce the reliability of the paper, i.e., the reliability of the material property values ​​published in that paper. Therefore, by presenting the reliability K taking into account the period from the submission date to the acceptance date as described above, the accuracy of the reliability K can be improved.

[0184] If the magazine name and impact factor (also referred to as IF) are included as attributes in the extracted information table 22, the derivation unit 105 may calculate the reliability K by weighting and adding attribute values ​​based on these attributes. The attribute value based on the magazine name is closer to 100 the more well-known the magazine name is, and closer to 0 the less well-known the magazine name is. The attribute value based on the IF is closer to 100 the larger the IF is, and closer to 0 the smaller the IF is.

[0185] It can be said that the popularity of such a journal name and IF indicate the quality of the paper, which is the document information D. Therefore, by using attribute values ​​based on the journal name and IF to present the reliability K that takes into account the quality of the paper, the accuracy of the reliability K can be improved.

[0186] If the magazine name and IF are not extracted from the document information D and are not included as attributes in the extracted information table 22, the derivation unit 105 may estimate those attributes. For example, the derivation unit 105 compares document information D whose magazine name and IF are known with document information D whose magazine name and IF are unknown, for example, using a natural language processing tool, and determines whether the similarity between the document information D is equal to or greater than a threshold. If the similarity is equal to or greater than the threshold, the derivation unit 105 may estimate the known magazine name and IF as the magazine name and IF of the unknown document information D. This makes it possible to calculate a high reliability K even for unknown document information D.

[0187] 15A to 15C, the derivation unit 105 determines the similarity of the temperature of the material as the attribute value R4. However, the derivation unit 105 may determine, as the attribute value R4 based on the temperature of the material, a value closer to 100 as the temperature of the material is higher and a value closer to 0 as the temperature of the material is lower.

[0188] [Processing Operation] FIG. 16 is a flowchart showing an example of the overall processing operation of the information providing device 100 according to this embodiment.

[0189] (Step S110) First, the extraction unit 101 of the information providing device 100 receives an input signal output from the input unit 11 in response to an input operation by a user to the input unit 11. This input signal is, for example, a signal for identifying one or more pieces of literature information D selected by the user's input operation from among multiple pieces of literature information D stored in the literature database 12. For example, the input signal may indicate the literature ID of the literature information D.

[0190] (Step S120) Next, the extraction unit 101 identifies one or more pieces of literature information D identified by the input signal received in step S110 and extracts various pieces of information for each of the multiple materials from the literature information D. The various pieces of information extracted include the first information, second information, and third information described above, i.e., the material name, characteristic values, and attributes. The material name is identification information for identifying the material. In other words, the extraction unit 101 extracts, for each of the multiple materials, identification information for identifying the material and the characteristic values ​​of the material from at least one piece of literature information D.

[0191] (Step S130) Next, the derivation unit 105 derives the reliability of the characteristic value of each material based on the material names, characteristic values, and attributes of the multiple materials extracted in step S120. For example, the derivation unit 105 derives the reliability of the characteristic value of each material based on the similarity of the characteristic values ​​between that material and one or more other materials.

[0192] (Step S140) Next, based on the reliability of the property value of each material derived in step S130, image processing unit 106 generates a first image showing those property values ​​in a display format corresponding to the reliability. This first image is, for example, the property value graph 24 shown in Figures 14 to 15C. That is, image processing unit 106 generates a first image that (i) shows the property value of each of the multiple materials in a display format corresponding to the reliability derived for that material's property value, and (ii) shows the property value in association with the identification information of that material.

[0193] (Step S150) Next, the image processing unit 106 displays the first image generated in step S140 on the display unit 13. That is, the image processing unit 106 outputs the first image to the display unit 13.

[0194] Fig. 17 is a flowchart showing an example of processing by the extraction unit 101. That is, Fig. 17 is a flowchart showing in detail the processing operation of step S120 in Fig. 16.

[0195] (Step S121) First, the extraction unit 101 acquires the document information D specified by the input signal from the document database 12.

[0196] (Step S122) Next, the extraction unit 101 performs a process of searching for and extracting the first information, that is, the material name, from the document information D.

[0197] (Step S123) Next, the extraction unit 101 determines whether or not a material name has been extracted from the literature information D by the processing of step S122. If the extraction unit 101 determines that a material name has not been extracted (No in step S123), it repeats the processing from step S121. When the processing of step S121 is repeated, the extraction unit 101 obtains literature information D that has not yet been obtained from the literature database 12.

[0198] (Step S124) Then, when the extracting unit 101 determines in step S123 that a material name has been extracted from the literature information D (yes in step S123), it extracts second information and third information from the literature information D. The second information and third information are characteristic values ​​and attributes of the material corresponding to the already extracted material name.

[0199] 18A is a block diagram showing a configuration example of an information providing system according to a modification of embodiment 1. Note that, among the components in this modification, the same components as those in embodiment 1 are denoted by the same reference numerals as those in embodiment 1, and detailed description thereof will be omitted.

[0200] As shown in FIG. 18A, an information providing system 1001 in this modification includes an information providing device 100, an input unit 11, a literature database 12, a display unit 13, and a material property database (DB) 14.

[0201] The material property database 14 is a recording medium that stores, in advance, the material name of each of a plurality of materials, in association with the property values ​​and attributes of that material. Such a recording medium may be a hard disk drive, RAM, ROM, or semiconductor memory. The recording medium may be either volatile or non-volatile.

[0202] The derivation unit 105 of the information providing device 100 in this modification uses the material property database 14. For example, the derivation unit 105 determines whether a characteristic value and an attribute are associated with each of the material names of the multiple materials listed in the extracted information table 22. If the derivation unit 105 determines that a characteristic value and an attribute are not associated with the material name, it treats the material name as the name of the material to be processed and refers to the material property database 14. The derivation unit 105 then searches the material property database 14 for the name of the material to be processed and extracts the characteristic values ​​and attributes associated with the material name to be processed from the material property database 14. The derivation unit 105 records the extracted characteristic values ​​and attributes in the extracted information table 22 in association with the name of the material to be processed.

[0203] As a result, even if it is not possible to extract the characteristic values ​​and attributes of a material from the multiple pieces of literature information D stored in the literature database 12, the characteristic values ​​and attributes can be supplemented by using the material property database 14.

[0204] FIG. 18B is a block diagram showing another example of the configuration of the information providing system 1001 according to the modification of the first embodiment.

[0205] The information providing system 1001 may include a materials database 15 instead of the material property database 14 shown in FIG. 18A. The materials database 15 is an open-access database and is a recording medium that stores various information about each of a plurality of materials. Such a recording medium may be a hard disk drive, RAM, ROM, or semiconductor memory. The recording medium may be volatile or non-volatile.

[0206] The derivation unit 105 extracts the characteristic values ​​and attributes corresponding to the name of the material to be processed from the material database 15, similarly to the extraction unit 101. The derivation unit 105 may estimate the characteristic values ​​and attributes corresponding to the name of the material to be processed by referring to the material database 15.

[0207] (Embodiment 2) The information providing system 1000 and the information providing device 100 in this embodiment have the same configuration as the information providing system 1000 and the information providing device 100 in embodiment 1. The information providing device 100 in this embodiment has a document display function in addition to the function of the information providing device 100 in embodiment 1, i.e., the reliability derivation function. The document display function is a function for displaying some information of the plurality of document information D stored in the document database 12 on the display unit 13 as document information. Note that, of the components in this embodiment, the same components as those in embodiment 1 are assigned the same reference numerals as those in embodiment 1, and detailed description thereof will be omitted.

[0208] FIG. 19 is a diagram showing an example of a material display screen in this embodiment.

[0209] After the reliability is derived by the reliability derivation function, the user performs an input operation on the input unit 11 to instruct the information providing device 100 to display the document display screen 40. When the image processing unit 106 acquires an input signal corresponding to the input operation from the input unit 11, it displays, for example, the document display screen 40 shown in FIG.

[0210] The material display screen 40 includes a document list window 21, a material window 41, a material window 42, an amount adjustment window 46, and a return button 43b.

[0211] The document list window 21 displays a list of document information D stored in the document database 12. In the list, icons of document information D selected by the user for deriving reliability are displayed in a manner that distinguishes them from icons of document information D that has not been selected.

[0212] The material window 41 is a window for displaying material conditions input by the user. The material conditions are, for example, conditions related to the element species or composition that make up the material.

[0213] The amount adjustment window 46 is a window for adjusting the amount of materials displayed and includes slider bars 46a to 46f. Slider bar 46a is a display element for adjusting the amount of materials related to publication dates displayed depending on the position of slider 2sa. Slider bar 46b is a display element for adjusting the amount of materials related to conductivity displayed depending on the position of slider 2sb. Slider bar 46c is a display element for adjusting the amount of materials related to temperature displayed depending on the position of slider 2sc. Slider bar 46d is a display element for adjusting the amount of materials related to structure displayed depending on the position of slider 2sd. Slider bar 46e is a display element for adjusting the amount of materials related to research institution names displayed depending on the position of slider 2se. Slider bar 46f is a display element for adjusting the amount of materials related to author names displayed depending on the position of slider 2sf.

[0214] Each of the sliders 2sa to 2sf indicates a smaller amount as it is moved closer to the left end, and a larger amount as it is moved closer to the right end. The publication date, conductivity, temperature, structure, research institution name, and author name are all material attributes. In other words, these sliders 2sa to 2sf are used to adjust the bias of the amount of material displayed for each attribute, such as the publication date. The bias of the amount of material is also called the weight of the amount of material.

[0215] The document window 42 is a window for displaying documents related to materials that meet the material conditions entered by the user. Documents related to publication date, conductivity, temperature, structure, research institution name, and author name are displayed in the amount adjusted by the amount adjustment window 46.

[0216] The return button 43b is a button for returning the material display screen 40 displayed on the display unit 13 to the display screen 20 or graph display screen 20a of the first embodiment.

[0217] FIG. 20 is a diagram showing another example of the material display screen 40 in this embodiment.

[0218] The user inputs material conditions by operating the input unit 11 and manipulates the slider 2sb of the slider bar 46b. As a result, the extraction unit 101 acquires the material conditions corresponding to the input operation. The image processing unit 106 then displays "Li-Al-La-Zr-O" as the material condition in the material window 41. Furthermore, the image processing unit 106 moves the slider 2sb of the slider bar 46b to the right end. Note that the sliders 2sa and 2sc to 2sf of the slider bars 46a and 46c to 46f are at the left end. The quantity adjustment window 46 in this state displays information related to conductivity in the entire information window 42. Furthermore, the image processing unit 106 displays the information display button 43a on the information display screen 40. This information display button 43a is a button for displaying information in the information window 42.

[0219] Next, the extraction unit 101 extracts information about the conductivity of materials having material names that match the material condition "Li-Al-La-Zr-O" from each piece of literature information D in the literature database 12 selected by the user. Specifically, the extraction unit 101 first searches for material names containing the element species Li, Al, La, Zr, and O from the extraction lists 31 to 34 and 31a, etc., of the first embodiment. Next, the extraction unit 101 identifies the literature ID and conductivity associated with the material name from the extraction lists 31 to 34 and 31a, etc. Then, the extraction unit 101 extracts, as an extracted image, a graph, figure, table, sentence, etc., in which the conductivity is described, from the literature information D having the literature ID.

[0220] The extraction unit 101 outputs information including the document ID, the conductivity, and the extracted image as display information candidates to the derivation unit 105. Here, when multiple material names are found by the above-mentioned material name search, the extraction unit 101 performs the same process as described above for each of the multiple material names and outputs display information candidates to the derivation unit 105.

[0221] When the derivation unit 105 acquires the plurality of display information candidates, it narrows down the display information from the plurality of display information candidates based on the reliability of the conductance included in the display information candidates. That is, the derivation unit 105 selects, from the plurality of display information candidates, display information candidates including a reliability equal to or greater than a threshold as display information. Then, the derivation unit 105 outputs the selected one or more pieces of display information to the image processing unit 106.

[0222] When the image processing unit 106 acquires one or more pieces of display information from the derivation unit 105 , it combines the one or more pieces of display information to generate edited material, and displays the edited material in the material window 42 on the material display screen 40 .

[0223] FIG. 21 is a diagram showing an example of the material display screen 40 on which edited material is displayed.

[0224] The image processing unit 106 displays the edited material as a "Report on Li-Al-La-Zr-O Materials" on the material display screen 40. The edited material is, for example, a material showing a conductivity ranking, as shown in FIG. 21. In the example of FIG. 21, the slider 2sb of the slider bar 46b corresponding to conductivity is at the right end, so the material related to conductivity is displayed across the entire material display screen 40. The conductivity ranking shows the conductivities in descending order of conductivity, along with the document IDs of the document information D in which the conductivities are described. The first- and second-place conductivities are each accompanied by an extracted image, such as a graph, in which the conductivities are described.

[0225] The image processing unit 106 may also display a save button 43c on the material display screen 40. The save button 43c is a button for saving the edited material. When the save button 43c is selected by the user's input operation on the input unit 11, the image processing unit 106 saves the edited material in a recording medium such as a memory provided in the information providing device 100.

[0226] FIG. 22 is a diagram showing another example of the material display screen 40 on which edited material is displayed.

[0227] Next, the user operates the sliders 2sa and 2sc of the slider bars 46a and 46c by performing an input operation on the input unit 11. This causes the image processing unit 106 to move the sliders 2sa and 2sc to the right. For example, the slider 2sb corresponding to conductivity moves the most to the right, while the slider 2sa corresponding to the publication date and the slider 2sc corresponding to the temperature move less to the right than the slider 2sb.

[0228] In this case, the extraction unit 101 searches for a material name corresponding to the material condition "Li-Al-La-Zr-O" from the extraction lists 31 to 34 and 31a, etc., and identifies the document ID, publication date, conductivity, and temperature of the document information D associated with that material name. Then, the extraction unit 101 extracts, as an extracted image, a graph, figure, table, sentence, etc. in which the conductivity is described from the document information D having that document ID.

[0229] Next, the extraction unit 101 outputs information including the document ID, material name, publication date, conductivity, temperature, and extracted image as display information candidates to the derivation unit 105. Here, when multiple material names are found by the above-mentioned material name search, the extraction unit 101 performs the same process as described above for each of the multiple material names and outputs display information candidates to the derivation unit 105.

[0230] When the derivation unit 105 acquires the plurality of display information candidates, it narrows down the display information from the plurality of display information candidates based on the reliability of the conductance included in the display information candidates. That is, the derivation unit 105 selects, from the plurality of display information candidates, display information candidates including a reliability equal to or greater than a threshold as display information. Then, the derivation unit 105 outputs the selected one or more pieces of display information to the image processing unit 106.

[0231] When the image processing unit 106 acquires one or more pieces of display information from the derivation unit 105, it combines the one or more pieces of display information to generate edited material and displays the edited material in the material window 42 of the material display screen 40. The edited material consists of a first material, a second material, and a third material, which will be described later. Specifically, based on the states of the slider bars 46a to 46f in the amount adjustment window 46, the image processing unit 106 allocates half of the total area of ​​the material window 42 to conductivity, a quarter to the publication date, and the remaining quarter to temperature. Then, the image processing unit 106 displays the first material, which shows a conductivity ranking similar to the example in FIG. 21 , in the left half of the material window 42. Furthermore, the image processing unit 106 displays a graph relating to conductivity and temperature as a second document in the upper right quarter of the document window 42, and displays a graph relating to conductivity and publication date as a third document in the lower right quarter of the document window 42. The second document is a graph showing temperature on the horizontal axis and conductivity on the vertical axis, with points plotted at positions corresponding to the temperature and conductivity of each material. The names of the materials may also be added to those positions. The third document is a graph showing publication date on the horizontal axis and conductivity on the vertical axis, with multiple points plotted on the graph. Each of the multiple points is plotted at a position corresponding to the publication date and conductivity of literature information D in which the material is described. The names of the materials may also be added to those positions.

[0232] FIG. 23 is a diagram showing another example of the material display screen 40 on which edited material is displayed.

[0233] The user operates sliders 2sa and 2sd to 2sf of slider bars 46a and 46d to 46f by performing an input operation on input unit 11 from the state of amount adjustment window 46 in Fig. 19. This causes image processing unit 106 to move sliders 2sa and 2sd to 2sf to the right. For example, slider 2sd corresponding to structure moves the most to the right, while slider 2sa corresponding to publication date, slider 2se corresponding to research institution name, and slider 2sf corresponding to author name move less to the right than slider 2sd.

[0234] In this case, the extraction unit 101 searches for a material name corresponding to the material condition "Li-Al-La-Zr-O" from the extraction lists 31 to 34 and 31a, etc., and identifies the document ID, publication date, conductivity, structure, research institution name, and author name of the document information D associated with that material name. Then, the extraction unit 101 extracts, as an extracted image, a graph, figure, table, etc. in which the structure is described from the document information D having that document ID.

[0235] The extraction unit 101 outputs information including the document ID, publication date, conductivity, structure, research institution name, author name, and extracted image as display information candidates to the derivation unit 105. Here, when multiple material names are found by the above-mentioned material name search, the extraction unit 101 performs the same process as described above for each of the multiple material names and outputs display information candidates to the derivation unit 105.

[0236] When the derivation unit 105 acquires the plurality of display information candidates, it narrows down the display information from the plurality of display information candidates based on the reliability of the conductance included in the display information candidates. That is, the derivation unit 105 selects, from the plurality of display information candidates, display information candidates including a reliability equal to or greater than a threshold as display information. Then, the derivation unit 105 outputs the selected one or more pieces of display information to the image processing unit 106.

[0237] When the image processing unit 106 acquires one or more pieces of display information from the derivation unit 105, it combines the one or more pieces of display information to generate an edited material and displays the edited material in the material window 42 of the material display screen 40. The edited material consists of a fourth material, a fifth material, and a sixth material, which will be described later. Specifically, based on the states of the slider bars 46a to 46f in the amount adjustment window 46, the image processing unit 106 allocates half of the total area of ​​the material window 42 to the structure and publication date, a quarter to the author name, and the remaining quarter to the research institution name. The image processing unit 106 then displays a fourth material, which shows extracted images of the structure of each material in order of publication date, in the left half of the material window 42. Furthermore, the image processing unit 106 displays information regarding the author's name as the fifth document in the upper right quarter of the document window 42, and displays information regarding the research institution's name as the sixth document in the lower right quarter of the document window 42.

[0238] In the fourth document, the earlier the publication date of the document information D, the closer to the beginning the extracted image of the structure described in that document information D is placed. The document ID and the publication year may be attached to the extracted image.

[0239] The fifth material indicates the names of three authors who are first, second, and third most well-known among the one or more author names included in the one or more pieces of display information acquired by the image processing unit 106, and information related to the three authors. The image processing unit 106 may generate the fifth material by, for example, referencing author data indicating the well-known levels of multiple authors and information about those authors. The author data may be stored in a server connected to the information providing device 100 via a communication network such as the Internet, or may be stored in the image processing unit 106 or the information providing device 100.

[0240] The sixth material indicates the names of the research institutions with the highest and second highest name recognition among the one or more research institutions included in the one or more pieces of display information acquired by the image processing unit 106, and information related to the two research institutions. The image processing unit 106 may generate the sixth material, for example, by referencing research institution data indicating the name recognition of multiple research institutions and information about those research institutions. The research institution data may be stored in a server connected to the information providing device 100 via a communication network such as the Internet, or may be stored in the image processing unit 106 or the information providing device 100.

[0241] As described above, in this embodiment, the extraction unit 101 acquires material conditions and extracts information about each of one or more materials that meet the material conditions from at least one document information D as display information candidates. The image processing unit 106 then acquires weights for each of multiple attributes of the material. The weights for each of the multiple attributes are, for example, weights or biases for the publication date, conductivity, temperature, structure, research institution name, and author name. Next, the image processing unit 106 selects, from the multiple display information candidates extracted by the extraction unit 101, one or more display information candidates corresponding to materials having characteristic values ​​for which reliability equal to or exceeds a threshold, as display information. The image processing unit 106 then generates a second image that displays, from the one or more display information pieces, display information corresponding to each of the multiple attributes in an amount corresponding to the respective weights of the multiple attributes, and outputs the second image to the display unit 13. The second image is, for example, edited material in the document display screen 40 or document window 42 shown in FIGS. 21 to 23 .

[0242] This allows the amount of display information corresponding to each of the multiple attributes displayed in the second image to be changed by adjusting the bias, which is the weight of each of the multiple attributes. Therefore, the user can arbitrarily adjust the amount of display information for each attribute so that more display information related to attributes of the user's interest is displayed and less display information related to attributes of the user's disinterest is displayed. Furthermore, since the displayed display information is information about materials with a reliability above a threshold, the user can use the displayed display information with confidence for work such as materials research. Display information for materials that match material conditions is displayed, and the material conditions are, for example, conditions related to the element species contained in the material or the material composition. This allows the one or more pieces of display information to be limited to materials of the user's interest. In this embodiment, edited materials according to the user's wishes can be automatically generated as technical materials, thereby reducing the labor required for creating technical materials.

[0243] FIG. 24 is a flowchart showing an example of the overall processing operation of the information providing device 100 according to this embodiment.

[0244] (Step S210) First, the information providing device 100 performs a reliability derivation process. This reliability derivation process is a process of deriving reliability for each characteristic value of a plurality of materials, as in the first embodiment, and may include the processes of steps S110 to S130 in FIG. 16 or may include the processes of steps S110 to S150.

[0245] (Step S220) The extraction unit 101 acquires material conditions in response to an input operation by the user to the input unit 11. Furthermore, the image processing unit 106 acquires biases for each of a plurality of types of attributes in response to an input operation by the user to the input unit 11.

[0246] (Step S230) Next, the extraction unit 101 searches for the material name that matches the material condition acquired in step S220. For example, the extraction unit 101 searches for the material name from the extraction lists 31 to 34 and 31a generated in the reliability derivation process in step S210.

[0247] (Step S240) Next, for each of the one or more material names found in step S230, the extraction unit 101 generates display information candidates related to the material name. That is, the extraction unit 101 identifies various information, including the document ID, associated with the material name from the extraction lists 31 to 34 and 31a. Note that this various information includes characteristic values ​​of the material having that material name. Furthermore, the extraction unit 101 extracts, as extracted images, graphs, figures, tables, sentences, or the like that describe the various information from the document information D that has that document ID. The extraction unit 101 then generates information including the document ID, the various information, and the extracted image as display information candidates.

[0248] (Step S250) Next, after acquiring the plurality of display information candidates, the derivation unit 105 narrows down the display information from the plurality of display information candidates based on the reliability of the conductance included in the display information candidates. That is, the derivation unit 105 selects, from the plurality of display information candidates, display information candidates including a reliability equal to or greater than a threshold as display information.

[0249] (Step S260) Next, when the image processing unit 106 acquires one or more pieces of display information from the derivation unit 105, the image processing unit 106 generates a second image by combining the one or more pieces of display information. That is, the image processing unit 106 generates a second image that shows the display information corresponding to each of the multiple types of attributes from the one or more pieces of display information in an amount corresponding to the bias of each of the multiple types of attributes acquired in step S220.

[0250] (Step S270) Then, the image processing unit 106 displays the generated second image on the display unit 13.

[0251] While the information processing device according to one or more aspects has been described above based on the above-mentioned embodiments and variations, the present disclosure is not limited to these embodiments and variations. As long as it does not deviate from the spirit of the present disclosure, various modifications conceivable by a person skilled in the art to the above-mentioned embodiments and variations, and forms constructed by combining components of different embodiments or variations may also be included within the scope of the present disclosure.

[0252] For example, in the above embodiments and modifications, the document information D is electronic data of a paper, but it may be electronic data of a textbook, a magazine, a patent document, or the like.

[0253] In the above embodiments and modifications, the information providing device 100 is configured as a single device such as a personal computer, but may also be configured as multiple devices. In this case, the extraction unit 101, the first information processing unit 102, the second information processing unit 103, the third information processing unit 104, the derivation unit 105, and the image processing unit 106 are not provided in the same device but are distributed across multiple devices.

[0254] 13 to 15C and 21 to 23 in the above-described embodiments do not include the document list window 21 of FIG. 2A and 2B, but the document list window 21 may be included. In this case, the user may deselect the icon of document information D in the document list window 21 or select a new icon by performing an input operation on the input unit 11. In response to the selection or deselection, the image processing unit 106 may update the characteristic value graph 24 or the document window 42.

[0255] In the above-described embodiments and modifications, the types of characteristic values ​​and attributes of a material extracted by the extraction unit 101 may be specified in response to an input operation by a user to the input unit 11. That is, the extraction unit 101 may acquire an input signal from the input unit 11 and extract characteristic values ​​and attributes of the type indicated by the input signal from the literature information D. As a result, the extraction unit 101 may extract, for example, density instead of the conductivity of a material as a characteristic value. The types of characteristic values ​​and attributes to be extracted may be determined in advance.

[0256] In the second embodiment, the display information is narrowed down from a plurality of display information candidates based on the reliability of the characteristic values. However, this narrowing down may not be necessary. In this case, the image processing unit 106 may treat all of the display information candidates generated by the extraction unit 101 as display information and combine these pieces of display information to generate the second image.

[0257] In the above-described embodiments and modifications, each component may be configured with dedicated hardware or may be realized by executing a software program suitable for each component. Each component may be realized by a program execution unit such as a CPU or processor reading and executing a software program recorded on a recording medium such as a hard disk or semiconductor memory. Here, the software program realizing the information providing device 100 of each of the above-described embodiments and modifications causes a computer to execute each step included in at least one of the flowcharts shown in Figures 16, 17, and 24.

[0258] It goes without saying that the present disclosure is not limited to the above-described embodiments and modifications. The following cases are also included in the present disclosure.

[0259] (1) Each of the above devices is specifically a computer system consisting of a microprocessor, ROM, RAM, hard disk unit, display unit, keyboard, mouse, etc. A computer program is stored in the RAM or hard disk unit. Each device achieves its function when the microprocessor operates in accordance with the computer program. Here, a computer program is composed of a combination of multiple instruction codes that indicate commands to the computer to achieve a specified function.

[0260] (2) Some or all of the components constituting each of the above devices may be configured as a single system LSI (Large Scale Integration). A system LSI is an ultra-multifunctional LSI manufactured by integrating multiple components on a single chip, and specifically, is a computer system configured to include a microprocessor, ROM, RAM, etc. A computer program is stored in the RAM. The system LSI achieves its functions when the microprocessor operates in accordance with the computer program.

[0261] (3) Some or all of the components constituting each of the above devices may be configured as an IC card or a standalone module that can be attached to each device. The IC card or module is a computer system composed of a microprocessor, ROM, RAM, etc. The IC card or module may include the above-mentioned ultra-multifunctional LSI. The IC card or module achieves its functions when the microprocessor operates according to a computer program. The IC card or module may be tamper-resistant.

[0262] (4) The present disclosure may be embodied as the methods described above, a computer program for implementing these methods on a computer, or a digital signal comprising the computer program.

[0263] The present disclosure may be a computer program or a digital signal recorded on a computer-readable recording medium, such as a flexible disk, a hard disk, a CD-ROM, an MO, a DVD, a DVD-ROM, a DVD-RAM, a BD (Blu-ray (registered trademark) Disc), a semiconductor memory, etc. It may also be a digital signal recorded on such a recording medium.

[0264] The present disclosure may be such that the computer program or digital signal is transmitted via a telecommunications line, a wireless or wired communication line, a network such as the Internet, data broadcasting, or the like.

[0265] The present disclosure may also be a computer system having a microprocessor and a memory, the memory storing the above-described computer program, and the microprocessor operating in accordance with the computer program.

[0266] The program or digital signal may be recorded on a recording medium and transferred, or the program or digital signal may be transferred via a network or the like, so that the program or digital signal can be implemented by another independent computer system.

[0267] (Others) The device according to one aspect of the present disclosure may be a device as described below.

[0268] an extracting unit that extracts a plurality of material names, a plurality of values ​​of a first characteristic, and a plurality of values ​​of a second characteristic from at least one document; an introducing unit that calculates a plurality of distances, each of the plurality of distances being a distance between two different coordinates included in n different coordinates, where n is a natural number equal to or greater than 2; the n different coordinates being a first coordinate corresponding to a first material name, to, an nth coordinate corresponding to an nth material name; the first coordinate being a pair of a first value of the first characteristic and a first value of the second characteristic, to, the nth coordinate being a pair of an nth value of the first characteristic and an nth value of the second characteristic; the plurality of material names including the first material name, to, the nth material name; the plurality of values ​​of the first characteristic including the first value of the first characteristic, to, the nth value of the first characteristic; and the plurality of values ​​of the second characteristic including the first value of the second characteristic, to, the nth value of the second characteristic. and an image processing unit that determines a display mode on a two-dimensional plane for each of the first coordinate, to, and the nth coordinate based on the calculated distances, and outputs the determined display correspondence for the first coordinate and the determined display correspondence for the nth coordinate to a display unit.

[0269] The first material name, to the nth material name may be a plurality of final material names listed in the final material name column shown in FIG.

[0270] The first value of the first characteristic, through the n-th value of the first characteristic may be a plurality of values ​​listed in the column of conductivity values ​​listed in FIG.

[0271] The first value of the second property, through the nth value of the second property, may be any of the values ​​listed in the column of activation energy values ​​listed in FIG.

[0272] The first coordinate, to the nth coordinate may be a coordinate whose x-axis coordinate value is the activation energy value corresponding to ID=001 in FIG. 11 and whose y-axis coordinate value is the conductivity value, or a coordinate whose x-axis coordinate value is the activation energy value corresponding to ID=n (not shown) to, and whose y-axis coordinate value is the conductivity value.

[0273] The first coordinate, to, n-th coordinate may be a plurality of coordinates indicated by x in FIG.

[0274] The display manner of each of the first coordinate, to, n-th coordinate may be the density (the number of points inside the circle) shown inside each of the multiple circles in FIG.

[0275] The multiple distances may be, in FIG. 11 , the distance between the two-dimensional data (activation energy value, conductivity value) corresponding to document ID=001 and the two-dimensional data (activation energy value, conductivity value) corresponding to document ID=002, ∼, the distance between the two-dimensional data (activation energy value, conductivity value) corresponding to document ID=001 and the two-dimensional data (activation energy value, conductivity value) corresponding to document ID=n (not shown), the distance between the two-dimensional data (activation energy value, conductivity value) corresponding to document ID=002 and the two-dimensional data (activation energy value, conductivity value) corresponding to document ID=003, ∼, the distance between the two-dimensional data (activation energy value, conductivity value) corresponding to document ID=002 and the two-dimensional data (activation energy value, conductivity value) corresponding to document ID=n (not shown), ∼, the distance between the two-dimensional data (activation energy value, conductivity value) corresponding to document ID=(n−1) and the two-dimensional data (activation energy value, conductivity value) corresponding to document ID=n (not shown).

[0276] The number of distances for n different coordinates is n(n-1) / 2.

[0277] The information providing device of the present disclosure can appropriately provide information about materials, and is useful for devices or systems for conducting material research, material development, or new material synthesis.

[0278] 1sa to 1sd sliders 2sa to 2sf sliders 11 input unit 12 literature database 13 display unit 20 display screen 20a graph display screen 21 literature list window 22 extracted information table 23a extraction start button 23b replenishment start button 23c graph display start button 23d reliability display button 23e return button 23f reliability hide button 24 characteristic value graph 25a to 25d slider bar 31 extraction list 31a extraction list 32 extraction list 33 extraction list 34 extraction list 40 material display screen 41 material window 42 material window 43a material display button 43b return button 43c save button 46 amount adjustment window 46a to 46f slider bar 100 information providing device 101 extraction unit 102 first information processing unit 103 Second information processing unit 104 Third information processing unit 105 Derivation unit 106 Image processing unit D Literature information D1 Body data D2 Metadata

Claims

1. an extracting unit that extracts, from at least one piece of literature information, identification information for identifying each of a plurality of materials, a characteristic value of each of the plurality of materials, and attribute information indicating an attribute of each of the plurality of materials; a derivation unit that derives a reliability of a characteristic value of the material based on a similarity of the characteristic value between the material and one or more other materials and the attribute information of the material; an image processing unit that (i) displays the characteristic value of each of the plurality of materials in a display mode corresponding to the reliability derived for the characteristic value of the material, and (ii) generates a first image that displays the characteristic value of each of the plurality of materials in association with the identification information of the material, and outputs the first image to a display unit; An information providing device comprising:

2. An extraction unit that extracts identification information for identifying each of a plurality of materials from at least one document information and characteristic values ​​of each of the plurality of materials; a derivation unit that derives a reliability of a characteristic value of the material based on a similarity of the characteristic value between the material and one or more other materials; an image processing unit that (i) displays the characteristic value of each of the plurality of materials in a display mode corresponding to the reliability derived for the characteristic value of the material, and (ii) generates a first image that displays the characteristic value of each of the plurality of materials in association with the identification information of the material, and outputs the first image to a display unit; Equipped with The extraction unit further extracting attribute information indicating attributes of each of the plurality of materials from the at least one piece of literature information; The lead-out portion is deriving a reliability of the characteristic value of the material based on the similarity of the characteristic value of the material and the attribute information extracted for the material; Information provision device.

3. The lead-out portion is deriving the reliability of the characteristic value of the material by performing a weighted addition of the similarity of the characteristic value of the material and an attribute value based on the attribute information extracted for the material; 3. The information providing device according to claim 2.

4. the attribute information indicates, as an attribute, a publication date of the literature information in which identification information and characteristic values ​​of the material corresponding to the attribute information are written, among the at least one piece of literature information; The lead-out portion is deriving the reliability of the characteristic value using the attribute value indicating the recency of the publication date; 4. The information providing device according to claim 3.

5. the attribute value is larger the more recently the publication date is, The lead-out portion is a higher value is derived as the reliability of the characteristic value of the material as the similarity of the characteristic value of the material is higher and as the attribute value corresponding to the material is larger; 5. The information providing device according to claim 4.

6. The attribute information indicates, as an attribute, the number of citations of literature information in which identification information and characteristic values ​​of the material corresponding to the attribute information are written, among the at least one piece of literature information; The lead-out portion is deriving a reliability of the characteristic value using the attribute value according to the number of citations; 4. The information providing device according to claim 3.

7. the attribute value is larger as the number of citations is larger; The lead-out portion is a higher value is derived as the reliability of the characteristic value of the material as the similarity of the characteristic value of the material is higher and as the attribute value corresponding to the material is larger; 7. The information providing device according to claim 6.

8. the attribute information indicates, as the attribute, an author of the literature information in which identification information and characteristic values ​​of the material corresponding to the attribute information are written, among the at least one literature information; The lead-out portion is deriving the reliability of the characteristic value using the attribute value according to whether or not the author of the document information is the same as each of the authors of one or more other document information; 4. The information providing device according to claim 3.

9. the attribute value is larger as the number of authors different from the author of the document information among the authors of the one or more other document information is larger, The lead-out portion is a higher value is derived as the reliability of the characteristic value of the material as the similarity of the characteristic value of the material is higher and as the attribute value corresponding to the material is larger; 7. The information providing device according to claim 6.

10. The attribute information indicates a synthesis method of the material corresponding to the attribute information as the attribute, The lead-out portion is deriving a reliability of the characteristic value using the attribute value according to a degree of similarity between the synthesis method of the material and each of the synthesis methods of the one or more other materials; 4. The information providing device according to claim 3.

11. the attribute value indicates a larger value as the degree of similarity between the synthesis method of the material and each of the synthesis methods of the one or more other materials increases, The lead-out portion is a higher value is derived as the reliability of the characteristic value of the material as the similarity of the characteristic value of the material is higher and as the attribute value corresponding to the material is larger; The information providing device according to claim 10.

12. The method of synthesis of the material includes at least one of temperature conditions, time conditions, and type of equipment used to synthesize the material; The information providing device according to claim 10.

13. An extraction unit that extracts identification information for identifying each of a plurality of materials from at least one document information and characteristic values ​​of each of the plurality of materials; a derivation unit that derives a reliability of a characteristic value of the material based on a similarity of the characteristic value between the material and one or more other materials; an image processing unit that (i) displays the characteristic value of each of the plurality of materials in a display mode corresponding to the reliability derived for the characteristic value of the material, and (ii) generates a first image that displays the characteristic value of each of the plurality of materials in association with the identification information of the material, and outputs the first image to a display unit; Equipped with The extraction unit further acquires material conditions, and for each of one or more materials that meet the material conditions, extracts information about the material from the at least one document information as a display information candidate; The image processing unit further includes: Obtain the weights of the various attributes of the material. selecting, from the plurality of display information candidates extracted by the extraction unit, one or more display information candidates corresponding to materials having characteristic values ​​from which the reliability equal to or greater than a threshold is derived, as display information; generating a second image showing display information corresponding to each of the plurality of types of attributes among the one or more pieces of display information in an amount corresponding to a weight of each of the plurality of types of attributes, and outputting the second image to a display unit; Information provision device.

14. 1. A method for providing information executed by one or more computers, comprising: extracting, from at least one piece of literature information, identification information for identifying each of a plurality of materials, characteristic values ​​of each of the plurality of materials, and attribute information indicating attributes of each of the plurality of materials; Deriving a reliability of the characteristic value of the material based on a similarity of the characteristic value between the material and one or more other materials and the attribute information of the material; (i) displaying the characteristic value of each of the plurality of materials in a display mode corresponding to the reliability derived for the characteristic value of the material, and (ii) generating a first image showing the characteristic value of each of the plurality of materials in association with the identification information of the material, and outputting the first image to a display unit. Information provision method.

15. extracting, from at least one piece of literature information, identification information for identifying each of a plurality of materials, characteristic values ​​of each of the plurality of materials, and attribute information indicating attributes of each of the plurality of materials; Deriving a reliability of the characteristic value of the material based on a similarity of the characteristic value between the material and one or more other materials and the attribute information of the material; (i) displaying the characteristic value of each of the plurality of materials in a display mode corresponding to the reliability derived for the characteristic value of the material, and (ii) generating a first image showing the characteristic value of each of the plurality of materials in association with the identification information of the material, and outputting the first image to a display unit. A program that causes a computer to do something.