Information processing device, information processing method, and program

Abstract

An information processing device and the like capable of effectively supporting the acquisition of chemical materials is provided. The system includes a data input unit that receives input of data transmitted from a user terminal, a model creation unit that creates a predictive model based on the data input via the data input unit, an extraction unit that performs a search using the predictive model to extract a target chemical material, and a connection unit that connects the user terminal to a product information site for the target chemical material extracted by the extraction unit. The model creation unit may perform machine learning to learn the correspondence between the chemical structure of a substance as data and the properties of the substance to create a predictive model.

Description

[Technical field]

[0001] The present disclosure relates to an information processing device, an information processing method, and a program. [Background technology]

[0002] Patent Document 1 discloses a technique for searching for manufacturing conditions using a prediction model, and determining the manufacturing conditions whose evaluation satisfies a predetermined standard as the manufacturing conditions for the product. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2020-166749 A Summary of the Invention [Problem to be solved by the invention]

[0004] For example, it is possible to search for suitable experimental conditions using the above-mentioned prediction model, but the cost of obtaining chemical materials such as reagents that match the extracted experimental conditions may be large.

[0005] Therefore, in one aspect, the present invention has an object to provide an information processing device and the like that can effectively support the acquisition of chemical materials. [Means for solving the problem]

[0006] In one embodiment, a data input unit that accepts input of data transmitted from a user terminal; a model creation unit that creates a prediction model based on the data input via the data input unit; an extraction unit that performs a search using the prediction model and extracts chemical materials; a connection unit that connects the user terminal to a product information site of the chemical material extracted by the extraction unit; An information processing device comprising: Effect of the Invention

[0007] In one aspect, the present invention can effectively assist in obtaining chemical materials. [Brief description of the drawings]

[0008] [Figure 1] 1 is a diagram illustrating an example of the configuration of an information processing system including an information processing apparatus according to an embodiment of the present invention. [Diagram 2] 2 is a diagram illustrating an example of a hardware configuration of the information processing device illustrated in FIG. 1. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] FIG. 1 is a diagram showing an example of the configuration of an information processing system having an information processing device according to this embodiment.

[0010] As shown in FIG. 1, the information processing system includes an information processing device 10 as a server and a user terminal 20. The information processing device 10 provides a data analysis and machine learning cloud service in the chemical field to a user who uses the user terminal 20. The information processing device 10 also provides a service to support the user in obtaining necessary chemical materials. In this disclosure, "chemical materials" include reagents used in chemical analysis, experiments, test research, inspections, etc., as well as industrial chemicals and industrial raw materials used in the manufacture of various products. Furthermore, "chemical materials" include drugs and medicines used in the biochemistry and medical fields. Hereinafter, an example of supporting the acquisition of reagents as "chemical materials" will be mainly described, but the "chemical materials" are not limited to the examples.

[0011] 1, the information processing system further includes a database 30 that identifies purchasable reagents, and a sales server 40 that provides a service for purchasing the reagents. Note that the data stored in the database 30 and the services provided by the sales server 40 can be changed as appropriate depending on the type of "chemical material."

[0012] As shown in FIG. 1, the information processing device 10 includes a data input unit 11 that accepts input of data transmitted from a user terminal 20, a model creation unit 12 that creates a predictive model based on the data input via the data input unit 11, an extraction unit 13 that performs a search using the predictive model and extracts target reagents, a connection unit 14 that connects the user terminal 20 to a product information site for the target reagent extracted by the extraction unit 13, and a memory unit 15 that stores various data such as input data from a user, the predictive model, and prediction results using the predictive model.

[0013] The information processing device 10 is implemented with programs corresponding to the functions of a data input unit 11, a model creation unit 12, an extraction unit 13, and a connection unit 14. In addition, the user terminal 20 is implemented with programs corresponding to a function for connecting to the information processing device 10, a user interface, and other functions necessary for receiving services provided by the information processing device 10.

[0014] FIG. 2 is a diagram illustrating an example of a hardware configuration of the information processing device illustrated in FIG.

[0015] In the example shown in FIG. 2, the information processing device 10 includes a CPU (Central Processing Unit) 111, a GPU (Graphics Processing Unit) 111A, a RAM (Random Access Memory) 112, a ROM (Read Only Memory) 113, an auxiliary storage device 114, a drive device 115, and a communication interface 117, all connected by a bus 119, as well as a wired transceiver unit 118A and a wireless transceiver unit 118B connected to the communication interface 117.

[0016] The GPU 111A performs various processes, which will be described later.

[0017] The auxiliary storage device 114 is, for example, a hard disk drive (HDD) or a solid state drive (SSD), and together with the RAM 112 and the ROM 113 constitutes the storage unit 15, etc.

[0018] Wired transceiver 118A includes a transceiver capable of communicating using a wired network.

[0019] The wireless transmission / reception unit 118B is a transmission / reception unit capable of communicating using a wireless network. The wireless network may include a wireless communication network of a mobile phone, the Internet, a Virtual Private Network (VPN), a Wide Area Network (WAN), etc. The wireless transmission / reception unit 118B may also include a Near Field Communication (NFC) unit, a Bluetooth (Bluetooth, registered trademark) communication unit, a Wireless-Fidelity (Wi-Fi, registered trademark) transmission / reception unit, an infrared transmission / reception unit, etc.

[0020] The wired transceiver 118A and the wireless transceiver 118B constitute, for example, the connection unit 14 shown in FIG.

[0021] The information processing device 10 may be connectable to a recording medium 116. The recording medium 116 stores a predetermined program. The program stored in the recording medium 116 is installed in the auxiliary storage device 114 or the like via the drive device 115. The installed predetermined program can be executed by the CPU 111 of the information processing device 10. For example, the recording medium 116 may be a recording medium that records information optically, electrically or magnetically, such as a CD (Compact Disc)-ROM, a flexible disk, a magneto-optical disk, or the like, or a semiconductor memory that records information electrically, such as a ROM, a flash memory, or the like. The recording medium 116 does not include a carrier wave.

[0022] Next, the operation of the information processing system will be described.

[0023] The data input unit 11 accepts input of data transmitted from the user terminal 20. The data is used as learning data for constructing a prediction model.

[0024] The content of the data that the data input unit 11 accepts as input is arbitrary, but the data includes the chemical structure of a substance and the properties of the substance. The data that the data input unit 11 accepts as input also includes the conditions of the experimental data and the results associated with the conditions.

[0025] The model creation unit 12 creates a prediction model based on the data input via the data input unit 11. Any algorithm can be used to create the prediction model, but for example, the model creation unit 12 can use the data input via the data input unit 11 as learning data and create a prediction model through machine learning using feature amounts.

[0026] For example, when the purpose is molecular design, the model creation unit 12 uses the chemical structure of a substance and the physical properties (properties) of the substance inputted via the data input unit 11 as learning data to create a prediction model. In this case, the prediction model is created as a trained model that uses the chemical structure of a substance as input data and outputs the physical properties of the substance as prediction data. The data format of the chemical structure as input data is arbitrary, and may be, for example, a character string according to the SMILES notation.

[0027] Also, for example, the model creation unit 12 performs machine learning on the experimental conditions input via the data input unit 11 and the experimental results associated with the conditions to create a prediction model. In this case, the prediction model is created as a trained model that uses the experimental conditions as input data and outputs the experimental results as prediction data.

[0028] Specifically, in the case of an experiment aimed at material design, for example, the model creation unit 12 uses the experimental conditions including the raw material blending recipe and the physical properties of the compound obtained by the blending recipe as learning data to create a prediction model. The raw material blending recipe is information including the chemical structure and blending ratio of the raw materials in the case of material design, for example. The data format of the chemical structure of the raw material is arbitrary, but may be, for example, a character string according to the SMILES notation. In addition, in the case of industrial raw materials, where the chemical structure of the raw material is not disclosed, the raw material may be selected based on information on the physical properties and property values ​​such as heat resistance and flexibility disclosed by the raw material manufacturer, etc. In such a case, the raw material blending recipe can be the selection, combination, and blending ratio of raw materials having the physical properties and property values.

[0029] The extraction unit 13 performs a search using the prediction model created by the model creation unit 12.

[0030] For example, the extraction unit 13 sequentially inputs the chemical structures of substances as input data into the prediction model, searches for chemical structures that provide good physical properties for the substance to be output as prediction data, and further extracts substances with chemical structures that provide good physical properties for the substance as target reagents.

[0031] The extraction unit 13 also sequentially inputs experimental conditions as input data into the prediction model, searches for chemical structures that give good experimental results that are output as predicted data, and extracts, as target reagents, substances that are used under experimental conditions that give good experimental results.

[0032] The search algorithm in the extraction unit 13 is arbitrary, but for example, the search may be repeated by determining the next candidate for input data based on the output predicted data until desirable predicted data is obtained.

[0033] The description method of the chemical structures handled by the extraction unit 13 may be SMILES notation.

[0034] The target reagents extracted by the extraction unit 13 can be limited to reagents that can be purchased (obtained). For example, the extraction unit 13 can access a database 30 (FIG. 1) that stores existing, i.e., purchasable, reagents, and search only for reagents in the database 30. In this case, for example, the chemical structures of substances input to the prediction model can be limited to the chemical structures of reagents in the database 30. Also, for example, the experimental conditions input to the prediction model can be limited to those using reagents in the database 30.

[0035] The database 30 may be prepared by, for example, a distributor or a reagent manufacturer that sells the reagents, or may be prepared by a provider of the service provided by the information processing device 10 receiving data from the distributor or the reagent manufacturer. The data format indicating the chemical structure of the reagent identified by the database 30 may be any format, and may be, for example, a character string conforming to the SMILES notation. By matching the description method of the chemical structure handled by the extraction unit 13 with the description method of the chemical structure of the reagent identified by the database 30, it becomes easy to search for the reagent in the database 30.

[0036] The extraction unit 13 may perform a search that is not limited to purchasable reagents. In this case, non-purchasable reagents are also extracted as target reagents. However, this extraction result may be useful information for the user. Even if the target reagent is not purchasable, the user may purchase a purchasable reagent that is similar to the target reagent, for example, has a similar chemical structure, and may use the same in an experiment.

[0037] The search results obtained by the extraction unit 13 are used by the user in any form. For example, based on the search results, the user can determine the materials (including reagents) and conditions to be used in the next experiment, and the new materials and conditions are applied to the user's next experiment. Furthermore, the new materials and conditions and the corresponding experimental results are input again via the data input unit 11 and reflected in the prediction model created by the model creation unit 12. This improves the accuracy of the prediction model, and more precise search results can be obtained in the extraction unit 13. By repeating this series of operations, the user can efficiently search for desirable materials and experimental conditions.

[0038] The extraction unit 13 may extract a single reagent or multiple reagents as the target reagent. When multiple reagents are extracted, the extraction unit 13 may assign information such as a priority order to the extracted target reagents based on the output value of the prediction model.

[0039] The connection unit 14 connects the user terminal 20 to a sales server 40 (FIG. 1) that provides a product information site for purchasing the target reagents extracted by the extraction unit 13.

[0040] For example, the connection unit 14 performs a predetermined display on the display screen of the user terminal 20 in a manner that allows the user terminal 20 to be connected to the product information site by a simple operation (e.g., a click operation) by the user on the display screen of the user terminal 20. The user can access the product information site (sales server 40) simply by performing an operation on the display screen of the user terminal 20.

[0041] The connection unit 14 may distinguish pages or the like in the product information site to which the connection is to be made depending on the type of the target reagent extracted by the extraction unit 13. For example, when the pages in the product information site differ depending on the attributes (e.g., substrate, solvent, reactant, additive, etc.) or chemical structure of the reagent, the connection unit 14 can connect the user terminal 20 to a page corresponding to the target reagent.

[0042] Furthermore, when connection to a plurality of product information sites is possible, the connection unit 14 can select a product information site where the target reagent can be purchased, and connect the user terminal 20 to that site.

[0043] According to this embodiment, since the user can easily access the product information site of the reagent, the burden of obtaining the reagent can be effectively reduced. For example, the user can create a prediction model and search for materials based on the experimental data at hand, and based on the search results, determine the next material to be considered and purchase it. By repeating this series of operations using the service of the information processing device 10, the appropriate material can be finally selected from a huge number of candidates. According to this embodiment, not only can the reagent required for the experiment be easily determined, but the reagent can also be easily purchased. Therefore, the labor involved in purchasing the reagent can be reduced, and the time required to complete the experiment can be shortened.

[0044] As described above, according to this embodiment, Extraction part Since the system includes a connection unit for connecting a user terminal to the product information site of the target chemical material extracted by the above, it is possible to effectively assist the user in obtaining the target chemical material. Although each embodiment has been described above in detail, the present invention is not limited to the specific embodiment, and various modifications and changes are possible within the scope of the claims. In addition, it is also possible to combine all or a plurality of the components of the above-described embodiments. [Explanation of symbols]

[0045] 10. Information processing device 11 Data Entry Section 12 Model Creation Department 13 Extraction part 14 Connection 15 Storage section

Claims

1. A data input unit that accepts input data transmitted from a user terminal; a model creation unit that creates a prediction model based on the input data input via the data input unit; an extraction unit which sequentially inputs the chemical structures of substances as the input data into the prediction model as the input data for a search that is not limited to target chemical materials that are available for purchase, searches for target chemical materials with chemical structures that have good physical properties of the target chemical materials that are output as prediction data, and extracts target chemical materials that are also not available for purchase; a connection unit that displays a predetermined content on a display screen of the user terminal in such a manner that the user terminal can be connected to a product information site of the target chemical material extracted by the extraction unit in response to a user operation on a display screen of the user terminal; The connection unit, when the target chemical material extracted by the extraction unit is available for purchase, causes a predetermined display to be displayed on the display screen of the user terminal in a manner that allows the user terminal to be connected to different connection destinations depending on the target chemical material, and when the page within the product information site to which the user terminal is connected differs depending on the extracted target chemical material, causes a predetermined display to be displayed on the display screen of the user terminal in a manner that allows the user terminal to be connected to a page corresponding to the extracted target chemical material.

2. The information processing apparatus according to claim 1 , wherein the model creation unit creates the prediction model by machine learning a correspondence between a chemical structure of a substance as the input data and a physical property of the substance.

3. The information processing apparatus according to claim 1 , wherein the input data is experimental data, and the model creation unit creates the prediction model by machine learning the correspondence between experimental conditions and experimental results of the experimental data.

4. An information processing device as described in Claim 1, wherein, when the target chemical material extracted by the extraction unit is not available for purchase, the connection unit causes a predetermined display of the target chemical material as the extraction result on the display screen of the user terminal.

5. A data input step of accepting input data transmitted from a user terminal; a model creation step of creating a prediction model based on the input data inputted through the data input step; an extraction step of sequentially inputting the chemical structures of substances as the input data into the prediction model as the input data for a search that is not limited to commercially available target chemical materials, searching for target chemical materials having chemical structures with favorable physical properties of the target chemical materials output as predicted data, and extracting target chemical materials including those that are not commercially available; a connection step of causing a predetermined display to be performed on a display screen of the user terminal in such a manner that the user terminal can be connected to a product information site of the target chemical material extracted in the extraction step by a user operation on a display screen of the user terminal, In the connection step, if the target chemical material extracted in the extraction step is available for purchase, a predetermined display is made on the display screen of the user terminal in a manner that allows the user terminal to be connected to different connection destinations depending on the target chemical material, and if the page within the product information site to which the product information site is connected differs depending on the extracted target chemical material, a predetermined display is made on the display screen of the user terminal in a manner that allows the user terminal to be connected to a page corresponding to the extracted target chemical material.

6. A data input step of accepting input data transmitted from a user terminal; a model creation step of creating a prediction model based on the input data inputted through the data input step; an extraction step of sequentially inputting the chemical structures of substances as the input data into the prediction model as the input data for a search that is not limited to commercially available target chemical materials, searching for target chemical materials having chemical structures with favorable physical properties of the target chemical materials output as predicted data, and extracting target chemical materials including those that are not commercially available; a connection step of causing a predetermined display to be performed on the display screen of the user terminal in a manner that allows the user terminal to be connected to a product information site of the target chemical material extracted in the extraction step by a user operation on a display screen of the user terminal; In the connection step, if the target chemical material extracted in the extraction step is available for purchase, a predetermined display is made on the display screen of the user terminal in a manner that allows the user terminal to be connected to different connection destinations depending on the target chemical material, and if the page within the product information site to which the product information site is connected differs depending on the extracted target chemical material, a predetermined display is made on the display screen of the user terminal in a manner that allows the user terminal to be connected to a page corresponding to the extracted target chemical material.

Images