KR20240068958A - Apparatus of processing data of sensor materials and system therefor - Google Patents

Abstract

A sensor material data processing device and system are disclosed. The sensor material data processing device according to an embodiment of the present invention includes a memory; And a processor that communicates with the memory to exchange data, wherein the processor collects sample data for each chemical sensor material group from the terminal, extracts sensor material analysis data from the collected sample data for each chemical sensor material group, and extracts Compare and analyze the spectrum between the sensor material analysis data, fit the data as a result of the spectral comparison analysis, generate and provide feature data for predicting machine learning-based gas sensing data, and collect gas sensing data from sample data for each chemical sensor material group collected. A platform is provided that extracts, compares and analyzes the extracted gas sensing data, fits the results, and then generates and provides a dataset for predicting fitting parameters according to the gas sensing data based on machine learning.

Description

Sensor material data processing device and system {APPARATUS OF PROCESSING DATA OF SENSOR MATERIALS AND SYSTEM THEREFOR}

The present invention relates to a device and system for processing sensor material data, and more specifically, to a device and system capable of collecting and providing datasets for sensor material research and processing related data based on machine learning.

Machine learning is receiving significant attention in the fields of physics, chemistry, and materials science due to its computational efficiency and remarkable prediction accuracy in predicting material and molecular properties. However, machine learning algorithms in the field of materials science require enormous computational or experimental costs to build a large materials database for each application, so training data for materials science is insufficient. There are a lot.

In the past, each person conducted individual research on sensor material data, and when the results were made public through papers, etc., they were used as a reference.

As such, according to the prior art, when collecting and using various sensor material data, there is a time gap, so there is a possibility of overlapping research, which is inefficient in terms of manpower, time, and cost due to unnecessary research. .

Therefore, a more efficient data processing method for processing such sensor material data is required.

Korean Patent Publication No. 10-2022-0073649 (Publication date: June 3, 2022)

One object of the present invention is to provide a platform to efficiently collect data such as research results on the latest sensor materials, as well as a sensor material data processing device that processes data so that anyone can quickly search in real time and receive search results. To provide a system.

Another object of the present invention is to provide a sensor material data processing device and system that provides comparative analysis results for samples of the latest sensor materials by providing the platform.

Another task of the present invention is to provide a sensor material data processing device and system that can provide a dataset for research on new sensor materials through the latest data analysis based on machine learning on the platform.

The technical problems to be achieved in the present invention are not limited to the above technical problems, and other technical problems not mentioned will be clearly understood by those skilled in the art from the description below.

A sensor material data processing device according to an embodiment of the present invention to solve the above-described problem includes a memory and a processor that communicates with the memory to exchange data, wherein the processor receives sample data for each chemical sensor material group from a terminal. Collects, extracts sensor material analysis data from the sample data for each chemical sensor material group collected, performs spectral comparison and analysis between the extracted sensor material analysis data, fits the spectral comparison analysis result data, and performs gas sensing based on machine learning. A target data set for data prediction can be created and provided.

According to one embodiment of the present invention, the processor may assign a unique identifier to each sample for each first sensor material group.

According to an embodiment of the present invention, the collected sample data for each chemical sensor material group may further include experimental conditions and analysis result data and gas sensor measurement data for each sample for each chemical sensor material group in addition to the sensor material analysis data. .

According to an embodiment of the present invention, the processor may predict gas sensor characteristics based on the provided dataset and predict gas sensor data based on the predicted gas sensor characteristics.

According to one embodiment of the present invention, the processor may provide a search function for samples for each chemical sensor material group for at least one chemical sensor material group stored in the memory.

According to one embodiment of the present invention, the processor receives a search request according to the use of the search function through the platform, and provides sample search result data for each chemical sensor material group corresponding to the received search request to the terminal. You can.

According to an embodiment of the present invention, the extracted sensor material analysis data may include at least one of Raman, XPS, XRD, and SEM.

According to an embodiment of the present invention, the processor may provide amplitude, peak position, and width information for each fitting component according to fitting of the spectrum comparison analysis result data. .

According to one embodiment of the present invention, the processor extracts and stores each fitting parameter according to the gas on-off of the gas sensor, but stores only the representative value of each fitting parameter extracted according to the gas on-off. there is.

A sensor material data processing system according to an embodiment of the present invention includes a terminal that requests a search for samples for each chemical sensor material group and a computing device that provides search result data corresponding to the search request, wherein the computing device , Collect sample data for each chemical sensor material group, extract sensor material analysis data from the collected sample data for each chemical sensor material group, perform spectral comparison analysis between the extracted sensor material analysis data, and fit the spectral comparison analysis result data. , A target data set for predicting gas sensing data can be created and provided based on machine learning.

According to at least one of the various embodiments of the present invention, the following effects are achieved.

First, it has the effect of providing a data processing platform so that anyone can quickly search data, including research results on the latest sensor materials, and receive search results in real time.

Second, it has the effect of providing comparative analysis results for samples of the latest sensor materials.

Third, it has the effect of providing a dataset for research on new sensor materials through the latest data analysis based on machine learning.

However, the effects that can be achieved through the present invention are not limited to this.

1 is a schematic diagram of a sensor material data processing system according to an embodiment of the present invention.
FIG. 2 is a block diagram of the computing device of FIG. 1.
Figure 3 is a flow chart illustrating a method of processing sensor material data according to an embodiment of the present invention.
4 to 11 are diagrams to explain a user interface (UI) provided by a computing device according to an embodiment of the present invention.

Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to the attached drawings. The detailed description set forth below in conjunction with the accompanying drawings is intended to illustrate exemplary embodiments of the invention and is not intended to represent the only embodiments in which the invention may be practiced.

These embodiments are provided solely to ensure that the disclosure of the present invention is complete and to fully inform those skilled in the art of the present invention of the scope of the invention, and that the present invention shall be defined by the scope of the claims. It's just that.

In some cases, in order to avoid ambiguity in the concept of the present invention, well-known structures and devices may be omitted, or may be shown in block diagram form focusing on the core functions of each structure and device. In addition, the same reference numerals are used to describe the same components throughout this specification.

Throughout the specification, when a part is said to "comprise" or "including" a certain component, this means that it does not exclude other components but may further include other components unless specifically stated to the contrary. do.

In addition, the term "part" described in the specification means a unit that processes at least one function or operation, and this may be implemented as hardware, software, or a combination of hardware and software. Furthermore, the terms “a” or “an”, “one”, and similar related terms may be used in the singular and plural in the context of describing the present invention, unless otherwise indicated herein or clearly contradicted by the context. It can be used in a meaning that includes.

In addition, specific terms used in the embodiments of the present invention are provided to aid understanding of the present invention, and unless otherwise defined, all terms used herein, including technical or scientific terms, refer to the present invention. It has the same meaning as generally understood by those with ordinary knowledge in the technical field to which it belongs. The use of these specific terms may be changed to other forms without departing from the technical spirit of the present invention.

In this specification, anyone can quickly search data, such as research results on the latest sensor materials, in real time and receive search results through the platform provided according to the present invention. Data processing, providing comparative analysis results for samples of the latest sensor materials by providing the platform, and providing data sets for research on new sensor materials through the latest data analysis based on machine learning on the platform. Disclosed is a sensor material data processing device and system.

In addition, in this specification, embodiments based on the field of materials science are described to aid understanding of the present invention and for convenience of explanation, but the present invention is not limited thereto. Therefore, even if not shown or explained in detail, the technical idea of the present invention can be used in the same or similar manner in other scientific fields or application fields.

Hereinafter, various embodiments according to the present invention will be described with reference to the attached drawings, as follows.

Figure 1 discloses a sensor material data processing system 1 according to an embodiment of the present invention.

Referring to FIG. 1, a sensor material data processing system 1 according to an embodiment of the present invention may be configured to include a terminal 100 and a computing device 150.

At this time, although not shown, the sensor material data processing system 1 may further include a database (DB). At this time, the database (DB) is an internal database (DB) built into or connected to the computing device 150 and accessible, and is not directly accessible by the computing device 150, but can be accessed by a third party. Possible external public databases (DBs) may also be included.

The sensor material data processing system 1 according to an embodiment of the present invention includes a terminal 100 that requests a search for a sample for each chemical sensor material group, and a computing device that provides search result data corresponding to the search request ( 150).

The computing device 150 according to an embodiment of the present invention provides a memory 210 and a platform, collects sample data for each chemical sensor material group through the platform, and collects sample data for each chemical sensor material group among the collected sample data for each chemical sensor material group. Extracts sensor material analysis data, performs spectral comparison and analysis between the extracted sensor material analysis data, fits the spectrum comparison analysis result data, and generates and provides a dataset for predicting gas sensor data fitting parameters based on machine learning. May include a processor 220.

The terminal 100 may search for a sensor material through a platform provided by the computing device 150 or output sensor material data provided through the platform.

The terminal 100 may provide a user interface for searching sensor materials through the platform.

The terminal 100 may provide a user interface necessary to input user information for using the platform.

The terminal 100 may upload data input through the user interface to the computing device 150.

The various data processing disclosed in this specification is explained by taking processing on a platform as an example, but this is an application or program installed on each device such as the terminal 100 or provided and downloaded and installed by the computing device 150. Software may be processed by execution in the terminal 100. In this case, the terminal 100 may be responsible for processing all sensor material data, but only part of it may be uploaded to the computing device 150 for processing, and data such as the processing results may be downloaded and provided to the user. there is.

Meanwhile, although only one terminal is illustrated in Figure 1, it is not limited thereto. For example, two separate terminals may each utilize the platform provided by the computing device 150. Depending on the embodiment, there are two individual terminals, and sensor material search, etc. may be output from the first terminal, and result data according to the search through the first terminal may be output from the second terminal.

The terminal 100 and the computing device 150 may perform data communication using a wired/wireless communication protocol (eg, web-based). In the above, when data communication is performed on a web basis, the interface provided by the terminal 100 may be a web-based user interface. In addition to the terminal 100 and computing device 150 shown in FIG. 1, a database (DB) (not shown) can also perform web-based data communication.

However, the data communication method between the components of the sensor material data processing system 1 described above is not limited to web-based, and if other methods are used, the interface may also vary accordingly.

The terminal 100 may include both fixed terminals such as PCs, laptops, digital TVs, etc. and mobile terminals such as mobile phones, smartphones, tablet PCs, etc., and depending on the embodiment, may perform sensor material data search, etc. in relation to the present invention. It may be a dedicated terminal for this purpose. Additionally, depending on the embodiment, the terminal 100 may be in the form of a wearable device or a terminal linked thereto.

The terminal 100 is preferably equipped with a display to provide the user with the interface and the provided physical property prediction result data, and includes a microphone, speaker, or voice recognition sensor related to voice data for convenience in inputting and outputting related data. Additional smart speakers, etc. may be provided.

The terminal 100 may support data communication within the sensor material data processing system 1 according to the present invention, including software or firmware such as an application or program. Meanwhile, the terminal 100 may download and install software such as applications and programs provided by the computing device 150 in advance. The terminal 100 may include an application program interface (API) or embedded software related thereto.

The computing device 150 may be described as one of a server, a controller, a processor, a control device, etc., depending on the embodiment.

The computing device 150 does not necessarily have to have a built-in database (DB), and it is sufficient as long as it is accessible or connectable from the computing device 150, so it does not matter if it is an external database. It does not necessarily need to be one, but may be plural. there is.

As mentioned above, the database does not have to be one, and may be a public database provided by a related industry or professional organization.

The computing device 150 may collect sensor material data from the public database (DB).

The computing device 150 provides search result data according to the user's sensor material or sensor material group sample to the terminal 100, and if there is feedback data about the search result data of the user of the terminal 100, , it can be used for user customization.

The data described in this specification is not limited to text but may include various forms such as audio, video, and images (including graphs).

Meanwhile, the present invention relates to sensor material data processing using artificial intelligence technology such as machine learning algorithms described later in this specification, and, if necessary, such as blockchain technology, extended reality (XR: eXtended Reality), etc. You can also use ICT (Information and Communication Technology) technology.

The aforementioned computing device 150 is a cloud server, an IP multimedia subsystem (IMS) server, a telephony application server, an instant messaging (IM) server, a media gateway control function (MGCF) server, and a messaging (MSG) server. It may be at least one of a gateway) server, a CSCF (call session control function) server, etc.

Data communication may be provided between the terminal 100 and the computing device 150 that constitute the sensor material data processing system 1 described above according to wired/wireless communication protocols.

The wired/wireless communication network refers to a data communication network that supports various types of data communication such as text, digital image, digital video, and digital voice information, and is not particularly limited in type, for example, Internet Protocol (IP). It can be an IP network that supports large-capacity data communication or an All IP network that integrates different IP networks, a wired network, a mobile communication network including WCDMA, a high speed downlink packet access (HSDPA) network, and a long term LTE (LTE) network. evolution) network, a mobile communication network including LTE advanced (LTE-A), a mobile communication network including 5G (generation), a satellite communication network, and a Wi-Fi network, or a combination of at least one of these. It may be possible.

Figure 2 is a block diagram of the computing device 150 according to an embodiment of the present invention.

Figure 3 is a flow chart illustrating a method of processing sensor material data according to an embodiment of the present invention.

4 to 11 are diagrams to explain a user interface (UI) provided by the computing device 150 (or the display of the terminal 100) according to an embodiment of the present invention.

Referring to FIG. 2, the sensor material data processing device, that is, the computing device 150, may be configured to include a memory 210 and a processor 220 that communicates with the memory 210 to exchange data.

The processor 220 may collect sample data for each chemical sensor material group from at least one of various external sources, including the above-described public database (DB) and the terminal 100.

The processor 220 may extract sensor material analysis data from the collected sample data for each chemical sensor material group.

The processor 220 may perform spectrum comparative analysis between the extracted sensor material analysis data.

The processor 220 can perform a fitting process on the spectrum comparison analysis result data and generate and provide a feature data set for predicting machine learning-based gas sensing data.

The processor 220 may extract gas sensing data from the collected sample data for each chemical sensor material group.

The processor 220 may perform comparative analysis between the extracted gas sensing data.

The processor 220 can perform a fitting process on the gas sensing comparative analysis result data and generate and provide a parameter prediction data set (target data set) according to the machine learning-based gas sensing data.

Figure 3 shows the processing process of sensor material data in a computing device. However, this is only an example and is not limited thereto.

Additionally, specific operations shown in FIG. 3 may be omitted or may be operated in a different order than shown.

The computing device 150 may collect sample data for each chemical sensor material group through the platform (S11).

The computing device 150 may extract sensor material analysis data from the collected sample data for each chemical sensor material group (S13).

The computing device 150 may compare and analyze the spectrum between the extracted sensor material analysis data (S15).

The computing device 150 may perform a fitting process on the spectrum comparison analysis result data (S17).

The computing device 150 may generate and provide a feature data set for predicting machine learning-based gas sensing data (S19).

The computing device 150 may extract gas sensing data from the collected sample data for each chemical sensor material group (S21).

The computing device 150 may perform comparative analysis between the extracted gas sensing data (S23).

The computing device 150 may perform a fitting process on the gas sensing data comparison and analysis result data (S25).

The computing device 150 may generate and provide a target data set for predicting fitting parameters according to gas sensing data based on machine learning (S27).

Referring to Figure 4, a first user interface (UI) is shown.

The first user interface displayed experimental conditions and analysis result data for each sensor material group.

As described above, when the computing device 150 collects sensor material data, it extracts experimental condition data for each sensor material group and analysis result data according to the experimental conditions from the collected sensor material data, and based on the extracted data, Sensor material data may be provided through the first user interface.

Figure 4 (a) shows experimental condition data (410, 420) for each sensor material group from the collected sensor material data.

In (b) of FIG. 4, experimental analysis result data 430 and 440 for each sensor material group based on the experimental condition data for each sensor material group are shown.

In the first user interface of FIG. 4, information on collected data for each sensor material can be easily checked by selecting items 410 and 420.

Referring to Figure 5, a second user interface (UI) is shown.

The second user interface may provide information for each sensor material group item 510.

This second user interface updates the items when new sensor material group data is collected, allowing users to immediately check various sensor material group data by simply selecting an item without switching to a separate screen, thereby improving user convenience. can be improved.

As described above, when data for each sensor material group is collected, the computing device 150 classifies it separately and provides data for each sensor material group as shown in the second user interface, but in this case, history information collected before or after is also provided. It can be provided together. By processing in this way, the experiment or research history of the target sensor material group can be checked at once, improving user convenience.

Referring to Figure 6, a third user interface and a fourth user interface are shown.

Referring to (a) of FIG. 6, the computing device 150 may assign a unique identifier (Identifier) 610 to individual samples for each sensor material group through a third user interface. By assigning a unique identifier, the computing device 150 not only makes it easier and simpler to manage samples, but also maps various information, such as which sensor material group the sample belongs to, through the identifier. , can contribute to user convenience. That is, samples belonging to one material group can be defined including a common sub-identifier and an individual sub-identifier.

Referring to (b) of FIG. 6, the computing device 150 may provide gas sensor measurement data 620 and 630 through the fourth user interface. At this time, the gas sensor measurement data may be provided by extracting and mapping, for example, the sample of (a) of FIG. 6 described above, that is, in units of identifiers. That is, the fourth user interface can be provided by classifying and defining data on a sample basis. For example, if a specific sample identifier with a unique identifier is selected in (a) of FIG. 6, the user interface (b) of FIG. 6 may be provided.

Referring to Figure 7, a fifth user interface is shown.

At this time, the fifth user interface may also be classified and defined in sample units as shown in (a) of FIG. 6 and provided.

Figure 7 (a) shows Raman spectroscopy information as the analysis result required for sensor material analysis.

Figure 7 (b) shows XPS (X-ray Photoelectron Spectroscopy) information as the analysis result required for sensor material analysis.

Figure 7 (c) shows XRD (X-ray Diffraction) information as the analysis result required for sensor material analysis.

Figure 7(d) shows SEM (Scanning Electron Microscopy) information as the analysis result required for sensor material analysis.

Referring to Figure 8, a sixth user interface is shown.

At this time, the sixth user interface displayed, for example, comparative analysis data of analysis result data for a plurality of samples shown in (a) of FIG. 6.

That is, the computing device 150 may compare and analyze analysis result data of samples by setting or selection among sensor material data in sample units, and provide result data 810 as shown in FIG. 8 .

Referring to FIG. 8, the computing device 150 may provide the analysis result data in a graph form and process it so that comparative analysis results for target samples can be intuitively identified.

Referring to Figure 9, a seventh user interface is shown.

At this time, the seventh user interface provides a fitting function for the spectrum analysis results.

Referring to FIG. 9, the computing device 150 may provide at least one information 910 of amplitude, peak position, width, etc. for each fitting component. .

For example, FIG. 9 may provide a fitting function for each analysis result in the sample unit shown in (a) of FIG. 6.

Referring to Figure 10, an eighth user interface is shown.

At this time, the eighth user interface may be related to the search function provided by the platform.

Figure 10(a) shows the user interface screen before search, and Figure 10(b) shows the user interface screen after search.

That is, when a search request is received through the pre-search screen in (a) of FIG. 10, the computing device 150 extracts and filters the search from the memory 210 or the database (DB) according to the received search request. The resulting data can be provided as shown in (b) of FIG. 10.

When a refresh or re-search request or a search request including a new search term is received within a predetermined time after the search result data is provided, the computing device 150 generates log data for the previous request and its results, so that it can be referred to in future searches. .

After providing the search result data, the computing device 150 generates log data about the user's input, such as the selected data, data selection order, data access time, and whether the data is downloaded, to perform later searches and provide search result data. You can refer to it.

Referring to Figure 11, the 9th and 10th user interfaces are shown.

At this time, the ninth user interface shown in (a) of FIG. 11 represents a fitting parameter dataset (target dataset) for machine learning-based gas sensing data prediction.

The tenth user interface shown in (b) of FIG. 11 represents a reference or a database storing data created based on the ninth user interface.

Regarding FIG. 11, the machine learning may use at least one artificial intelligence platform among SimPL-ML, ChemAI, etc.

The computing device 150 can instantly create a machine learning prediction model using the artificial intelligence platform and use it for learning to predict fitting parameters for the gas sensing data.

The computing device 150 can predict gas sensing data fitting parameters using each sensor material characteristic and gas sensing experiment condition dataset as shown in (b) of FIG. 11.

The computing device 150 may perform prediction of gas sensing data based on gas sensing data fitting parameter prediction information using the dataset as shown in (b) of FIG. 11 above.

Referring to (a) of FIG. 11, the computing device 150 may extract fitting parameters in each case of gas on and off.

Referring to (a) of FIG. 11, the computing device 150 can separately store the extracted parameters in the database shown in (b) of FIG. 11 and process them so that they can be downloaded upon request. .

Referring to (a) of FIG. 11, the computing device 150 can control to store only predefined representative values for gas on-off in the database shown in (b) of FIG. 11.

As described above, according to at least one of the various embodiments of the present invention, a data processing platform can be provided so that anyone can quickly search data, such as research results on the latest sensor materials, in real time and receive search results. , Through the above platform, comparative analysis results of samples of the latest sensor materials can be provided, and data sets for research on new sensor materials can be provided through the latest data analysis based on machine learning.

Meanwhile, the numbers mentioned above in this specification are based on the time of experiment and may vary depending on various situations such as updates to the system or database (DB).

Meanwhile, the above-described method can be written as a program that can be executed on a computer, and can be implemented in a general-purpose digital computer that operates the program using a computer-readable medium. Additionally, the structure of data used in the above-described method may be recorded on a computer-readable medium through various means. Computer-readable media storing executable computer code for performing the various methods of the present invention include magnetic storage media (e.g., ROM, floppy disk, hard disk, etc.), optical readable media (e.g., CD-ROM, DVD, etc.) etc.) and other storage media.

Those skilled in the art related to the embodiments of the present invention will understand that the above-described material may be implemented in a modified form without departing from its essential characteristics. Therefore, the disclosed methods should be considered from an explanatory rather than a restrictive perspective. The scope of the present invention is indicated in the claims, not the detailed description of the invention, and all differences within the equivalent scope should be construed as being included in the scope of the present invention.

Claims (10)

Memory; and
Including a processor that communicates with the memory to exchange data,
The processor,
Collect sample data for each chemical sensor material group from the terminal,
Sensor material analysis data is extracted from the collected sample data for each chemical sensor material group, and spectral comparison and analysis is performed between the extracted sensor material analysis data to fit the spectrum comparison analysis result data,
Generate and provide feature data for machine learning-based gas sensing data prediction,
Extract gas sensing data from the collected sample data for each chemical sensor material group,
After comparative analysis between extracted gas sensing data and fitting the results, a target data set for predicting gas sensing data is generated and provided based on machine learning.
Sensor material data processing device. According to paragraph 1,
The processor,
A unique identifier is assigned to each sample for each first sensor material group,
Sensor material data processing device. According to paragraph 2,
In the sample data for each chemical sensor material group collected above,
In addition to the sensor material analysis data, experimental conditions and analysis result data and gas sensor measurement data of each sample for each chemical sensor material group are further included,
Sensor material data processing device. According to paragraph 3,
The processor,
Predict gas sensor characteristics based on the provided dataset,
Predicting gas sensor data based on the predicted gas sensor characteristics,
Sensor material data processing device. According to paragraph 4,
The processor,
Providing a search function for samples by chemical sensor material group for at least one or more stored in the memory,
Sensor material data processing device. According to clause 5,
The processor,
Receiving a search request according to the use of the search function through the platform, and providing sample search result data for each chemical sensor material group corresponding to the received search request to the terminal,
Sensor material data processing device. According to clause 6,
In the extracted sensor material analysis data,
Including at least one of Raman, XPS, XRD and SEM,
Sensor material data processing device. In clause 7,
The processor,
Provides amplitude, peak position, and width information for each fitting component according to fitting of the data as a result of the spectrum comparison analysis.
Sensor material data processing device. According to clause 8,
The processor,
Extracting and storing each fitting parameter according to the gas on-off of the gas sensor, but storing only representative values of each fitting parameter extracted according to the gas on-off,
Sensor material data processing device. A terminal requesting a search for samples by chemical sensor material group; and
Including; a computing device that provides search result data corresponding to the search request;
The computing device is,
Collecting sample data for each chemical sensor material group, extracting sensor material analysis data from the collected sample data for each chemical sensor material group, performing spectral comparison and analysis between the extracted sensor material analysis data, and fitting the spectrum comparison analysis result data, Create and provide feature data for machine learning-based gas sensing data prediction, extract gas sensing data from sample data for each chemical sensor material group, perform comparative analysis between the extracted gas sensing data, and fit the results. A sensor material data processing system that generates and provides target data sets for predicting gas sensing data based on machine learning.