Information processing system, information processing method, and information processing program

Abstract

To provide an information processing system, an information processing method, and an information processing program that analyze an observation result of a better target material.SOLUTION: In an information processing system 1, an acquisition unit of an information processing device 2 acquires a first observation result and a second observation result for a target material. The first observation result is the result obtained by performing the observation on a first region containing the target material and includes first positional information indicating a position within the first region, a first observation value being the observation value for each position and an attribute corresponding to the first positional information. The second observation result is the result obtained by performing the observation on a second region containing the target material and includes second positional information indicating the position within the second region and a second observation value being the observation value for each position. The first positional information and second positional information are configured to be mutually positioned. The output unit identifies the attribute of the second positional information on the basis of the attribute of the first positional information and outputs distribution information regarding a distribution of the second observation values for each attribute of the second positional information.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to an information processing system, an information processing method, and an information processing program. [Background technology]

[0002] Non-Patent Document 1 discloses the results of an investigation into the degradation behavior of lithium-ion pouch full cells. The investigation results were conducted using SEM images of samples taken with a scanning electron microscope (SEM) and the results of energy dispersive X-ray spectroscopy (EDS) of the samples. [Prior art documents] [Non-patent literature]

[0003] [Non-Patent Document 1] Li H., Chen L. and Chen Z. "High-temperature storage deterioration behaviors of lithium-ion batteries using nickel-rich cathode and SiO-C composite anode." SN Appl. Sci. 2, 1136 (2020). Summary of the Invention [Problem to be solved by the invention]

[0004] However, there is still room for improvement in the technology for analyzing the observation results of target substances such as lithium-ion materials.

[0005] In view of the above circumstances, the present invention provides a technique for better analyzing the observation results of a target substance. [Means for solving the problem]

[0006] According to one aspect of the present invention, an information processing system is provided. The information processing system includes a processor configured to execute a program that executes the following steps. In the acquisition step, a first observation result and a second observation result for a target substance are acquired. The first observation result is a result of performing a first observation on a first region including the target substance. The first observation result includes first position information indicating a position in the first region, a first observation value that is an observation value for each position, and an attribute corresponding to the first position information. The attribute is identified based on the first observation result. The second observation result is a result of performing a second observation on a second region including the target substance. The second observation result includes second position information indicating a position in the second region, and a second observation value that is an observation value for each position. The first position information and the second position information are configured to be mutually positionable. In the output step, an attribute of the second position information is identified based on the attribute of the first position information, and distribution information regarding a distribution of the second observation value for each attribute of the second position information is output.

[0007] With this configuration, it is possible to provide a technique for better analyzing the observation results of a target substance. [Brief description of the drawings]

[0008] [Figure 1] 1 is a configuration diagram illustrating an information processing system 1. [Diagram 2] 2 is a block diagram showing a hardware configuration of an information processing device 2. FIG. [Diagram 3] FIG. 2 is a block diagram showing a hardware configuration of a user terminal 3. [Figure 4] FIG. 2 is a block diagram showing a hardware configuration of a measuring device 4. [Diagram 5] FIG. 2 is a diagram illustrating an example of a functional unit included in a processor 23. [Figure 6] 2 is an activity diagram showing an example of the flow of information processing executed in the information processing system 1. FIG. [Figure 7] FIG. 11 is a diagram showing an example of an output process and an output mode of distribution information IF1 and distribution visual information IF2. [Figure 8] FIG. 13 is a diagram showing an example of an output process and an output mode of information regarding the distance between distributions. [Figure 9] FIG. 13 is a diagram showing another example of an output mode of information regarding the distance between distributions. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described with reference to the drawings. Various characteristic features shown in the following embodiments can be combined with each other.

[0010] Incidentally, a program for realizing the software appearing in one embodiment may be provided as a non-transitory computer-readable recording medium, or may be provided so as to be downloadable from an external server, or may be provided so that the program is launched on an external computer and its functions are realized on a client terminal (so-called cloud computing).

[0011] In one embodiment, the term "unit" may include, for example, a combination of hardware resources implemented by a circuit in the broad sense and software information processing that can be specifically realized by these hardware resources. In one embodiment, various information is handled, and this information is represented by, for example, physical values ​​of signal values ​​representing voltage and current, high and low signal values ​​as a binary bit collection consisting of 0 or 1, or quantum superposition (so-called quantum bits), and communication and calculation can be performed on the circuit in the broad sense.

[0012] In addition, a circuit in the broad sense is a circuit realized by at least appropriately combining a circuit, circuitry, a processor, and a memory, etc. In other words, it includes an application specific integrated circuit (ASIC), a programmable logic device (e.g., a simple programmable logic device (SPLD), a complex programmable logic device (CPLD), and a field programmable gate array (FPGA)), etc.

[0013] 1. Hardware Configuration This section describes the hardware configuration.

[0014] <Information Processing System 1> FIG. 1 is a configuration diagram showing an information processing system 1. The information processing system 1 includes an information processing device 2 and a user terminal 3. The information processing device 2, the user terminal 3, and a measuring device 4 are configured to be able to communicate with each other via an electric communication line. In one embodiment, the information processing system 1 is made up of one or more devices or components. For example, if the information processing system 1 is made up of only the information processing device 2, the information processing system 1 can be the information processing device 2. These components will be described below.

[0015] <Information processing device 2> 2 is a block diagram showing a hardware configuration of the information processing device 2. The information processing device 2 includes a communication unit 21, a storage unit 22, and at least one processor 23, and these components are electrically connected via a communication bus 20 inside the information processing device 2. Each component will be further described.

[0016] The communication unit 21 is preferably a wired communication means such as USB, IEEE1394, Thunderbolt (registered trademark), wired LAN network communication, etc., but may also include wireless LAN network communication, mobile communication such as 3G / LTE / 5G, BLUETOOTH (registered trademark) communication, etc. as necessary. In other words, it is more preferable to implement it as a collection of multiple communication means. In other words, the information processing device 2 may communicate various information from the outside via the communication unit 21 and the network.

[0017] The storage unit 22 stores various information defined by the above description. This can be implemented, for example, as a storage device such as a solid state drive (SSD) that stores various programs and the like related to the information processing device 2 executed by the processor 23, or as a memory such as a random access memory (RAM) that stores temporarily required information (arguments, arrays, etc.) related to the program calculations. The storage unit 22 stores various programs, variables, etc. related to the information processing device 2 executed by the processor 23.

[0018] The processor 23 processes and controls the overall operations related to the information processing device 2. The processor 23 is, for example, a central processing unit (CPU) not shown. The processor 23 realizes various functions related to the information processing device 2 by reading out a predetermined program stored in the storage unit 22. That is, information processing by software stored in the storage unit 22 can be specifically realized by the processor 23, which is an example of hardware, and executed as each functional unit included in the processor 23. These will be described in more detail in the next section. The processor 23 is not limited to being single, and may be implemented with multiple processors 23 for each function. Also, a combination of these may be used.

[0019] <User terminal 3> 3 is a block diagram showing a hardware configuration of the user terminal 3. The user terminal 3 includes a communication unit 31, a storage unit 32, a processor 33, a display unit 34, and an HMI device 35, and these components are electrically connected via a communication bus 30 inside the user terminal 3. Descriptions of the communication unit 31, the storage unit 32, and the processor 33 are omitted because they are similar to the descriptions of the respective units in the information processing device 2.

[0020] The display unit 34 may be included in the housing of the user terminal 3 or may be externally attached. The display unit 34 displays a screen of a graphical user interface (GUI) that can be operated by the user. This is preferably implemented by using display devices such as a CRT display, a liquid crystal display, an organic EL display, and a plasma display according to the type of the user terminal 3.

[0021] The HMI device 35 is a human-machine interface device. The HMI device 35 may be included in the housing of the user terminal 3, or may be externally attached. For example, the HMI device 35 may be implemented as a touch panel integrated with the display unit 34. If it is a touch panel, the user can input a tap operation, a swipe operation, or the like. Of course, instead of the touch panel, a switch button, a mouse, a QWERTY keyboard, a voice recognition device, a gesture detection device, a gaze detection device, a biosignal detection device, an imaging device, or the like may be adopted. That is, the HMI device 35 accepts an operation input made by a user. In response, the HMI device 35 transfers a signal corresponding to the operation input to the processor 33 via the communication bus 30. The processor 33 can execute a predetermined control or calculation as necessary. It can be said that the HMI device 35 includes an input unit configured to be able to accept an input from a user.

[0022] <Measurement device 4> 4 is a block diagram showing a hardware configuration of the measurement device 4. The measurement device 4 is configured to perform various spatial measurements on the target material Ob, for example, configured to perform SEM-EDS to measure the appearance of the target material Ob and the composition at each position of the appearance. The target material Ob is a positive electrode material of a storage battery, for example, a lithium element-containing material used in the positive electrode material of a lithium ion storage battery. In one embodiment, the measurement device 4 includes an electron gun 40, a first measurement unit 41, and a second measurement unit 42.

[0023] The electron gun 40 is configured to irradiate the target material Ob with an electron beam B1.

[0024] The first measurement unit 41 is configured to be able to perform SEM (Scanning Electron Microscopy) measurement as the first observation, and is configured to be able to measure the intensity of a reflected electron beam B2 emitted from the target material Ob as the first observation value. This allows the first measurement unit 41 to generate SEM image data D1 that can construct an SEM image showing the appearance of the target material Ob. The SEM image data D1 is a result of performing SEM measurement on a first region including the target material Ob. The SEM measurement is an example of the first observation. In other words, the first observation result includes SEM image data D1 that shows the result of SEM measurement on the target material Ob. The SEM image data D1 includes first position information that indicates a position in the first region, and a first observation value that is an observation value for each position. The SEM image data D1 includes an imaging result of the appearance of the target material Ob. In one embodiment, the appearance represented by the SEM image data D1 is represented as an image model on a two-dimensional plane represented by the first position information and the intensity of the reflected electron beam B2 at the first position information, but is not limited to this, and the appearance may be represented as an image model on a two-dimensional curved surface or as a three-dimensional solid model. In other words, the first position information is not limited to being represented two-dimensionally, and may be represented three-dimensionally. The SEM image data D1 is not limited to the image itself displayed on the display unit 34, etc., and may also include command codes, binary data, etc. for generating the image.

[0025] The second measurement unit 42 is configured to perform EDS (Energy Dispersive X-ray Spectroscopy) as the second observation and to be able to measure the intensity of characteristic X-rays B3 generated by an electron beam B1 irradiated onto the target material Ob as the second observation value. This allows the second measurement unit 42 to generate EDS data D2 as the second observation result. The EDS data D2 is a result of EDS measurement performed on a second region including the target material Ob, and is an example of a second observation result for the target material Ob. In other words, the second observation result includes EDS data D2 indicating the result of EDS measurement for the target material Ob. With this configuration, the material characteristics of the storage battery can be intuitively grasped from the correlation with the appearance obtained from the SEM image. The EDS data D2 includes second position information and a second observation value. The second position information indicates a position within the second region. The second observation value is an observation value of the EDS measurement (second observation) for each position, and for example, the second observation value includes a composition obtained from the number of measurements of characteristic X-rays B3 of an element contained in the position, for example, a content ratio of a certain element. The number of measurements of characteristic X-rays B3 increases according to an increase in the content of an element in a specific region in the target material. Therefore, the physical property value includes information on the composition of the target material Ob corresponding to the second position information. According to such a configuration, it becomes easier to analyze the correlation between the appearance of the target material Ob and the composition of the target material Ob, so that, for example, information obtained when analyzing the target material Ob in an appearance inspection or the like can be increased. The EDS data D2 is not limited to the image itself displayed on the display unit 34, etc., but may also include command codes, binary data, etc. for generating the image.

[0026] In one embodiment, the first region, which is a region observed by the first observation (SEM), and the second region, which is a region observed by the second observation (EDS), are configured to be substantially coincident with each other, whereby the first position information and the second position information are configured to be positionable with respect to each other.

[0027] 2. Functional configuration of information processing device 2 Fig. 5 is a diagram showing an example of functional units included in the processor 23. As shown in Fig. 5, the processor 23 includes an acquisition unit 231, an identification unit 232, and an output unit 233. In this section, an overview of these functional units will be described. Details of each functional unit will be described together with information processing described later.

[0028] The acquisition unit 231 is configured to be able to acquire information from the user terminal 3 or other devices. The acquisition unit 231 is configured to be able to acquire various pieces of information by reading out various pieces of information stored in a storage area that is at least a part of the memory unit 22 and writing the read out information in a working area that is at least a part of the memory unit 22. The storage area is, for example, an area of ​​the memory unit 22 that is implemented as a storage device such as an SSD. The working area is, for example, an area that is implemented as a memory such as a RAM. Note that acquisition by the acquisition unit 231 includes acquiring output results of each functional unit included in the processor 23.

[0029] The identifying unit 232 is configured to be able to identify various pieces of information based on the information acquired by the acquiring unit 231 and the like.

[0030] The output unit 233 is configured to be able to output various information based on the SEM image data D1, the EDS data D2, the identification result of the identification unit 232, and the like.

[0031] 3. Information processing In this section, the information processing executed in the information processing system 1 will be described.

[0032] 3.1. Information processing flow 6 is an activity diagram showing an example of the flow of information processing executed in the information processing system 1. The information processing may include any exception processing not shown. Exception processing includes interruption of the information processing and omission of each process. Selection or input performed in the information processing may be based on a user operation or may be performed automatically without relying on a user operation.

[0033] [Activity A1] First, in activity A1, the output unit 233 outputs a command to the measurement device 4 to perform measurement on the target substance Ob in response to an operation by a user.

[0034] [Activity A11, Activity A12] Next, the process proceeds to activity A11, and the measuring device 4 performs measurement on the target material Ob based on the command. In detail, the first measuring unit 41 performs SEM measurement on the target material Ob, and the second measuring unit 42 performs EDS measurement on the target material Ob. As a result, the process proceeds to activity A12, and the measuring device 4 generates SEM image data D1 and EDS data D2.

[0035] [Activity A2] Next, the process proceeds to activity A2, where the acquisition unit 231 acquires SEM image data D1 and EDS data D2.

[0036] [Activity A3] Next, the process proceeds to activity A3, and the processor 23 executes an attribute specification process based on the acquired SEM image data D1. In the attribute specification process, the processor 23 specifies an attribute of the SEM image data D1 according to the first position information. The attribute is specified based on the first observation result, and includes, for example, an appearance feature. The appearance feature is, for example, a quantity that is correlated with the texture, particle size, disorder, etc. of the appearance of the target material Ob. Examples of such feature include handcraft features such as GLCM features and SIFT features, and features obtained by machine learning, etc. The feature is specified based on, for example, the first position information and the intensity of the reflected electron beam B2 at the position indicated by the first position information. Here, an example of a feature specification process using a trained model that has been trained in advance will be described. The trained model is configured to be able to output at least the appearance feature using image data as input, and includes an input layer, a hidden layer, and an output layer. The trained model may be stored in the storage unit 22, or in an external device other than the information processing device 2. Furthermore, the attribute specification process may be performed by a device located outside the information processing system 1.

[0037] First, the processor 23 divides the acquired SEM image data D1 according to a preset unit. The unit is defined, for example, by a resolution at which the trained model can process the image data. Here, the SEM image data D1 is divided into rectangular image data of a certain size. Hereinafter, for convenience of explanation, each of the divided image data may be referred to as patch image data D11. The patch image data D11 is defined in a manner that allows a correspondence relationship with the first position information to be determined. Therefore, the patch image data D11 includes data indicating the first position information.

[0038] Next, the processor 23 inputs the multiple patch image data D11 obtained by the division into the trained model. The trained model converts the input patch image data D11 into parameters that can be input to the input layer, and transmits the parameters to the output layer via at least one hidden layer. As a result, at least one feature value is output from the output layer for each patch image data D11. Since the patch image data D11 is obtained by dividing the SEM image data D1, it is configured to be associated with the first position information. Therefore, the feature value output from the patch image data D11 is configured to be associated with the first position information, and can be said to be an attribute of the first position information. The feature value output from the trained model may be grouped into multiple groups based on a predetermined criterion. The group representing the grouped feature value is also one of the feature values. This makes it possible to express a complex system with fewer attributes, thereby reducing the analysis load on the user.

[0039] The learning method of the trained model used in the attribute identification process may be any method such as supervised learning, unsupervised learning, or reinforcement learning. As the type of trained model, linear regression, logistic regression, random forest, boosting, support vector machine, neural network, etc. can be adopted. In particular, when the input includes images, it is preferable to use a convolutional neural network (CNN). When the input includes time-series data, it is preferable to use a recurrent neural network (RNN). As the clustering technique, it is possible to adopt spectral clustering, DBSCAN (Density-Based Spatial Clustering of Applications with Noise), k-means method, etc., and as the segmentation technique, it is possible to adopt U-Net, etc. The learning may be performed by the processor 23 itself or by a device other than the processor 23.

[0040] Furthermore, the attribute identification process is not limited to being performed using a trained model, and may be performed using any reference information indicating the correspondence between the SEM image data D1 and the attributes, such as a lookup table or a function, etc. Such reference information is obtained, for example, by a simulation, a calibration experiment, or the like, corresponding to the first observation result to be observed.

[0041] [Activity A4] Next, the process proceeds to activity A4, where the acquisition unit 231 acquires a feature amount as an attribute obtained based on the attribute specification process.

[0042] [Activity A5] Next, the process proceeds to activity A5, where the identifying unit 232 identifies the feature amount (i.e., attribute) of the second position information based on the feature amount corresponding to the first position information in the SEM image data D1, in other words, the attribute of the first position information. Here, since the first position information of the SEM image data D1 is associated in advance with the second position information of the EDS data D2, the identifying unit 232 identifies the second position information by assuming that the feature amount of the second position information is the same as the attribute of the first position information corresponding to the second position information.

[0043] [Activity A21] After that, in activity A21, the processor 33 of the user terminal 3 displays an SEM image on which the feature amount is superimposed on the display unit 34 based on the identification result.

[0044] [Activity A6] Also, in activity A6, the output unit 233 outputs distribution information IF1 regarding the distribution of the second observation value for each attribute (e.g., feature amount) of the second location information. The distribution information IF1 is output, for example, as table data indicating the correspondence between the feature amount, the second location information, and the second observation value, or as a statistical value obtained by aggregating the table data. In one embodiment, the distribution information IF1 includes distribution visual information IF2. The distribution visual information IF2 visually indicates the distribution regarding the number of second location information corresponding to the second observation value for each attribute. With this configuration, it becomes easier to identify the correlation between the attribute having a correlation with the first location information and the second observation value. The distribution visual information IF2 is output in a form that allows the user to grasp the overall picture regarding the distribution, such as a histogram, a line graph, a pie chart, or a scatter diagram.

[0045] [Activity A22] After the processing of activity A6, in activity A22, the processor 33 of the user terminal 3 displays distribution visual information IF2 of the EDS data D2 on the display unit 34 based on the output result of activity A6.

[0046] [Activity A7] Next, the process proceeds to activity A7, and the output unit 233 outputs the distance between the distributions for each feature amount based on the distribution information IF1. In other words, the output unit 233 outputs the distance between the distributions of the second observation values ​​between two different attributes (for example, feature amounts). With this configuration, it is possible to quantitatively evaluate the difference in the distribution of the characteristic X-rays B3 specific to the contained element for each different attribute inherent in the target substance Ob. The method of calculating the distance between the distributions can be any method such as the Wasserstein distance or the KL divergence. In one embodiment, the information regarding the distance is output in a manner that allows the output of information visible to the user as distance visual information.

[0047] [Activity A23] After that, in activity A23, the processor 33 of the user terminal 3 displays, on the display unit 34, distance visual information relating to the distance.

[0048] According to the above configuration, it is possible to grasp the tendency of the second observed value for each attribute specified according to the first observed value as a distribution, which makes it easier to perform an analysis based on the correlation between the first observed value and the second observed value.

[0049] 3.3 Details of data processing In this section, the above-mentioned information processing will be described in detail.

[0050] 3.3.1. Output process and output mode of distribution information IF1 and visual distribution information IF2 FIG. 7 is a diagram showing an example of an output process and an output mode of the distribution information IF1 and the distribution visual information IF2. As shown in FIG. 7, the processor 23 first divides the SEM image data D1 into a plurality of patch image data D11. An image corresponding to the SEM image data D1 is shown in FIG. 7 as a first SEM image IM1a. Each of the patch image data D11 is divided into rectangular regions, and each is configured to be equal to or smaller than a certain specified size. A feature amount is specified for each of the patch image data D11 divided in this manner. The output unit 233 superimposes a color corresponding to the feature amount specified for each of the patch image data D11 on the SEM image IM1a based on the specified feature amount and the SEM image data D1. As a result, a second SEM image IM1b in which a color corresponding to the feature amount is superimposed for each position corresponding to the patch image data D11 on the first SEM image IM1a is displayed on the display unit 34. It is optional whether or not to display the second SEM image IM1b. In this embodiment, the features are classified into three groups ("Group 1", "Group 2", and "Group 3") after grouping, and each group is displayed in a different display manner, for example, in a different color, so that they can be distinguished.

[0051] On the other hand, the acquiring unit 231 acquires the EDS data D2. In FIG. 7, an image displayed on the display unit 34 based on the EDS data D2 is shown as an EDS map IM2. The EDS map IM2 expresses the distribution of one kind of element, for example, fluorine element, by a brightness map. The distribution is not limited to fluorine element, and may be any element such as carbon element or oxygen element, or may be a distribution of multiple elements. Thereafter, the identifying unit 232 performs division on the EDS data D2 having second position information associated with the first position information of the SEM image data D1 in the same manner as the patch image data D11. The division may be performed by generating multiple divided data from the EDS data D2, or by virtually dividing the EDS data D2 into regions based on the second position information. Thereafter, the identifying unit 232 identifies patch image data D11 corresponding to each of the divided regions in the EDS data D2 based on the correspondence between the first position information and the second position information, for example, an index of the image data or position information of a boundary position, and identifies the feature amount of the corresponding patch image data D11 as the feature amount of the region. This allows the correspondence between the second position information of the EDS data D2, the fluorine element content at the position, and the feature amount corresponding to the second position information to be obtained.

[0052] Thereafter, the output unit 233 outputs distribution visual information IF2 based on the corresponding relationship, and causes the display unit 34 to display the distribution visual information IF2. In the present embodiment, the distribution visual information IF2 displays the distribution of each of the three grouped features (specifically, the distribution H1 corresponding to the first group, the distribution H2 corresponding to the second group, and the distribution H3 corresponding to the third group) and the distribution HT of the entire EDS data D2 that is not distinguished by features in a manner that allows viewing, for example, in a histogram. This allows the information of the entire system that is not based on the features to be easily compared with the information for each feature based on the difference in their distribution shapes, making it easier to identify features that show a different tendency from the tendency of the entire system. In addition to such distribution visual information IF2, the distribution information IF1 may also include statistics such as the average value, median, and variance of each distribution H1, H2, H3, and HT.

[0053] 3.3.2. Output process and format of information on distance between distributions Fig. 8 is a diagram showing an example of an output process and an output mode of information on the distance between distributions. Note that Fig. 8 shows that distance visual information IF3, which is an example of information on the distance between distributions, is output based on distribution visual information IF2, but this is for convenience of explanation only, and it is not necessary to output distance visual information IF3 from distribution visual information IF2 itself.

[0054] First, the processor 23 extracts the distributions H1 to H3 of the EDS data D2 corresponding to each feature from the distribution HT of the entire EDS data D2. Then, the processor 23 calculates the distance of each of the distributions H1 to H3 of the EDS data D2 corresponding to each feature from the distribution HT of the entire EDS data D2. The above-mentioned Wasserstein distance is used as the distance. Then, the output unit 233 outputs the calculated distance between each of the distributions H1 to H3, and displays each of them on the display unit 34 in a comparable manner. Here, the distance between each of the distributions H1 to H3 is displayed as a bar graph in a comparable manner. In this way, by outputting the distance between the distributions of each feature from a specific distribution that serves as a reference, a more quantitative evaluation of the distribution of each feature can be performed. In particular, by using the distribution HT of the entire EDS data D2 as a reference as in this embodiment, the tendency of each of the distributions H1 to H3 can be more objectively analyzed. In addition, the information regarding the distance between the distributions is not limited to the distance between each of the distributions H1 to H3 of the EDS data D2 corresponding to each feature amount relative to the distribution HT of the entire EDS data D2, but may also include information regarding the distance between each of the distributions H1 to H3.

[0055] Note that the output mode of the information regarding the distance between distributions is arbitrary and is not limited to the mode shown in Fig. 8. For example, Fig. 9 is a diagram showing another example of the output mode of the information regarding the distance between distributions. For convenience of explanation, the distance visual information IF3 shown in Fig. 8 may be referred to as the first distance visual information IF3, and the distance visual information IF4 shown in Fig. 9 may be referred to as the second distance visual information IF4 below.

[0056] 3.3.3. Processing when multiple SEM image data D1 and EDS data D2 are acquired The above information processing can also be applied when multiple SEM image data D1 and EDS data D2 are acquired, for example, when multiple target substances Ob exist or when multiple SEM-EDS measurements are performed on the same target substance Ob.

[0057] For example, in activity A3, the acquisition unit 231 may acquire SEM image data D1 and EDS data D2 corresponding to each of a plurality of target materials Ob. In this case, the output unit 233 may output distribution information IF1 corresponding to each of the target materials Ob. With this configuration, it is possible to compare the correspondence between the attributes and the second observation results between different objects, making it easier to remove bias in the distribution of individual target materials Ob.

[0058] Here, an output mode of distance visual information IF4 will be described as an example of an output mode of distribution information IF1 when multiple SEM image data D1 and EDS data D2 are acquired. Here, a case will be described in which the acquisition unit 231 acquires SEM image data D1 and EDS data D2 for each of three target materials Ob, that is, a first target material Ob1, a second target material Ob2, and a third target material Ob3.

[0059] In this embodiment, the processor 23 calculates the distance of each of the distributions H1 to H3 of the EDS data D2 corresponding to each feature amount to the distribution HT of the entire EDS data D2 for each of the target substances Ob1 to Ob3, and the distance between the distributions H1 to H3. Then, the processor 23 calculates the distance between the distributions HT of the entire EDS data D2 for different target substances Ob1 to Ob3. Then, the output unit 233 displays, as the second distance visual information IF4, a graph network having nodes corresponding to the respective distributions H1, H2, H3, and HT of the target substances Ob1 to Ob3 and edges of lengths according to the calculated distance between the distributions on the display unit 34. G1 to G3 in FIG. 9 represent nodes corresponding to the distributions H1 to H3 for each feature amount, and T represents a node corresponding to the distribution HT of the entire EDS data D2 for each of the target substances Ob1 to Ob3. This makes it easier to intuitively analyze multiple target substances Ob or multiple observation results for one target substance Ob. This method is also applicable to the case where only one SEM image data D1 and one EDS data D2 are acquired.

[0060] 4.Other The above information processing mode is merely an example and is not limited to this.

[0061] The SEM image data D1 or the EDS data D2 may be associated with label information on a predetermined label that is assigned in advance according to the corresponding target material Ob. For example, a label related to the degree of deterioration of the capacity may be assigned to the SEM image data D1 by performing a capacity measurement or inputting the data into a trained model. In this case, the output unit 233 may output distribution information IF1 for each label and output a comparison result of the distribution information IF1 for different labels. With this configuration, the behavior of the second observation value for each preset label can be compared between different labels.

[0062] The processor 23 does not need to divide the SEM image data D1 into patch image data D11 and specify attributes such as feature amounts with the patch image data D11 as the smallest unit. For example, the processor 23 may specify attributes such as feature amounts for each piece of first position information of the SEM image data D1, for example, in pixel units. The processor 23 may also divide a plurality of SEM image data D1 to generate a set of patch image data D11 and specify attributes such as feature amounts for each piece of patch image data D11.

[0063] The second observation result is not limited to the observation result of the composition distribution of the substance represented by the EDS data D2, etc., but may include an observation result regarding the distribution of any observation value, such as Young's modulus, strain, stress, elastic constant, thermal expansion coefficient, resistance value, dielectric constant, polarization, piezoelectric constant, magnetization, magnetic susceptibility, magnetic permeability, reflectance, transmittance, and domain distribution. According to this configuration, the correlation between the appearance of the target substance Ob and the physical property value corresponding to the position of the appearance can be expressed as the distribution of the physical property value for each feature amount. Therefore, it becomes easy to analyze the characteristics related to the physical property of the target substance Ob based on the appearance, which is information that can be intuitively grasped. In other words, the second observation result includes the physical property value of the target substance Ob corresponding to the second position information.

[0064] The attributes are not limited to the above-mentioned features output from the trained model, for example, but may include any attributes assigned by an evaluator who evaluates the first observation result.

[0065] The first observation result is not limited to the result obtained by SEM measurement, such as the SEM image data D1. For example, the first observation result may be an observation result of the appearance using a contact microscope such as an AFM (Atomic Force Microscope) as the first measurement unit 41. In this case, the second observation result may include a piezoelectric response tensor or a magnetic domain orientation as a second observation value, such as a PFM (Piezoresponse Force Microscopy) or an MFM (Magnetic Force Microscopy). The first observation result may be an optical imaging result of the appearance of the target material Ob using an optical device such as a visible light camera or an infrared camera as the first measurement unit 41.

[0066] The first observation result is not limited to an image of the appearance of the target material Ob. For example, the first observation result may include a real space distribution of any first observation value. For example, the first observation result may indicate a composition distribution of an element different from that of the second observation result. This makes it easier to analyze the correlation between the distributions of different elements. The first observation result may also be an observation result of a spatial distribution, particularly a real space distribution, of the first observation value. Similarly, the second observation result may also be an observation result of a spatial distribution, particularly a real space distribution, of the second observation value.

[0067] The first measurement unit 41 and the second measurement unit 42 do not have to be incorporated as an integrated device like the measurement device 4 capable of performing SEM-EDS, and each may be implemented as an independent device. Furthermore, the first position information and the second position information do not have to be configured to match at the measurement stage of the first measurement unit 41 and the second measurement unit 42. For example, the first position information and the second position information may be configured to be positionable by providing a specific landmark for alignment, for example a specific pattern, on the target material Ob or a stage on which the target material Ob is placed.

[0068] The target substance Ob to which the information processing is applied is not limited to the positive electrode material of a storage battery. It may be the negative electrode material of a storage battery. The target substance Ob is not limited to the material contained in a storage battery, and may be composed of any material, such as an inorganic material or an organic material. The target substance Ob is not limited to polycrystals, and may have any structure, such as single crystals, quasicrystals, and amorphous. The target substance Ob is not limited to substances composed of simple substances or compounds, and may be substances that constitute complex systems, such as biological tissues and structures.

[0069] The information processing device 2 may be an on-premise type or a cloud type. As the information processing device 2 in the cloud type, the above-mentioned functions and processes may be provided in the form of, for example, SaaS (Software as a Service) or cloud computing.

[0070] In the above embodiment, the information processing device 2 performs various storage and control, but multiple external devices may be used instead of the information processing device 2. That is, various information and programs may be distributed and stored in multiple external devices using block chain technology or the like.

[0071] The above embodiment is not limited to the information processing system 1, and may be an information processing method or an information processing program. The information processing method includes each step of the information processing system 1. The information processing program causes at least one computer to execute each step of the information processing system 1.

[0072] The information processing system 1 and the like may be provided in the following aspects.

[0073] (1) An information processing system comprising a processor configured to execute a program that performs the following steps: in an acquisition step, a first observation result and a second observation result for a target substance are acquired, wherein the first observation result is a result of a first observation performed on a first region containing the target substance, and includes first position information indicating a position within the first region, a first observation value that is an observation value for each position, and an attribute corresponding to the first position information, and the attribute is identified based on the first observation result; the second observation result is a result of a second observation performed on a second region containing the target substance, and includes second position information indicating a position within the second region and a second observation value that is an observation value for each position, and the first position information and the second position information are configured to be positionable with respect to each other; and in an output step, an attribute of the second position information is identified based on the attribute of the first position information, and distribution information regarding a distribution of the second observation values ​​for each attribute of the second position information is output.

[0074] According to this configuration, it is possible to grasp the tendency of the second observed value for each attribute specified according to the first observed value as a distribution, which makes it easier to perform an analysis based on the correlation between the first observed value and the second observed value.

[0075] (2) In the information processing system described in (1) above, the distribution information includes distribution visual information that visually shows a distribution regarding the number of the second location information corresponding to the second observation value for each of the attributes.

[0076] With this configuration, it becomes easier to identify the correlation between the attribute having a correlation with the first location information and the second observation value.

[0077] (3) In the information processing system described in any one of (1) or (2) above, the output step outputs information regarding the distance between the distributions of the second observation value between two different attributes.

[0078] According to this configuration, it is possible to quantitatively evaluate the difference in distribution of the second physical quantity for each different attribute inherent in the target substance.

[0079] (4) In the information processing system described in any one of (1) to (3) above, the first observation result includes an imaging result of the appearance of the target substance, the attribute includes a feature of the appearance, and the second observation result includes a physical property value of the target substance corresponding to the second location information.

[0080] With this configuration, the correlation between the appearance of the target substance and the physical property value corresponding to the position of the appearance can be expressed as a distribution of the physical property value for each feature amount, making it easy to analyze the characteristics related to the physical property of the target substance based on the appearance, which is information that can be intuitively grasped.

[0081] (5) In the information processing system described in (4) above, the physical property value includes information regarding the composition of the target substance corresponding to the second position information.

[0082] With such a configuration, it becomes easier to analyze the correlation between the appearance of the target substance and the composition of the target substance, thereby increasing the amount of information that can be obtained when analyzing the target substance, for example, through visual inspection.

[0083] (6) In the information processing system described in any one of (1) to (5) above, the acquisition step acquires the first observation result and the second observation result corresponding to each of a plurality of target substances, and the output step outputs the distribution information corresponding to each of the target substances.

[0084] According to such a configuration, it is possible to compare the correspondence between the attributes and the second observation results between different objects, which makes it easier to remove bias in the distribution of individual objects of the object substance.

[0085] (7) In the information processing system described in (6) above, the first observation result or the second observation result is associated with label information regarding a predetermined label that is assigned in advance according to the corresponding target substance, and in the output step, the distribution information is output for each of the labels, and a comparison result of the distribution information for each of the different labels is output.

[0086] According to this configuration, the behavior of the second observation value for each preset label can be compared between different labels.

[0087] (8) In the information processing system described in any one of (1) to (7) above, the target substance is a positive electrode material or a negative electrode material of a storage battery, the first observation result includes SEM image data indicating a result of an SEM measurement of the target substance, and the second observation result includes EDS data indicating a result of an EDS measurement of the target substance.

[0088] With this configuration, the material properties of the storage battery can be intuitively understood from correlation with the appearance obtained from the SEM image.

[0089] (9) An information processing method, comprising each step of the information processing system according to any one of (1) to (8) above.

[0090] According to this configuration, a nonlinear physical model capable of reproducing physical phenomena with high accuracy can be constructed based on the input data.

[0091] (10) An information processing program that causes at least one computer to execute each step of the information processing system described in any one of (1) to (8) above.

[0092] According to this configuration, a nonlinear physical model capable of reproducing physical phenomena with high accuracy can be constructed based on the input data. Of course, this is not the case.

[0093] Finally, although various embodiments according to the present disclosure have been described, these are presented as examples and are not intended to limit the scope of the invention. The novel embodiment can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. The embodiments and their modifications are included within the scope and spirit of the invention, and are included in the scope of the invention and its equivalents described in the claims. [Explanation of symbols]

[0094] 1: Information processing system 2: Information processing equipment 20: Communication bus 21: Communications Department 22: Storage section 23: Processor 231: Acquisition Department 232: Specific part 233: Output section 3: User terminal 30: Communication bus 31: Communications Department 32: Storage section 33: Processor 34:Display section 35: HMI device 4: Measuring equipment 40: Electron gun 41: First measurement section 42: Second measurement section B1:Electron beam B2: Backscattered electron beam B3:Characteristic X-ray D1: SEM image data D11: Patch image data D2: EDS data H1: Distribution H2: Distribution H3: Distribution HT: Distribution IF1: Distribution information IF2: Distribution visual information IF3: Distance visual information IF4: Distance visual information IM1a: First SEM image IM2b: Second SEM image IM2: EDS Map Ob: Target substance Ob1: First target substance Ob2: Second target substance Ob3: Third object

Claims

1. An information processing system, A processor configured to execute a program to perform the following steps: In the acquisition step, a first observation result and a second observation result for the target substance are acquired, where the first observation result is a result of performing a first observation on a first region including the target substance, The first location information includes first location information indicating a location within the first region, a first observation value that is an observation value for each location, and an attribute corresponding to the first location information; the attribute is determined based on the first observation; the second observation result is a result of performing a second observation on a second region including the target substance, The second position information indicates a position in the second region, and a second observation value is an observation value for each of the positions, The first position information and the second position information are configured to be positionable relative to each other, In the output step, an attribute of the second location information is identified based on an attribute of the first location information, and distribution information regarding a distribution of the second observation value for each attribute of the second location information is output.

2. 2. The information processing system according to claim 1, The distribution information includes distribution visual information visually indicating a distribution regarding the number of the second location information corresponding to the second observation value for each of the attributes.

3. 2. The information processing system according to claim 1, The output step outputs information regarding the distance between the distributions of the second observations between two different attributes.

4. 2. The information processing system according to claim 1, the first observation result includes an imaging result of an appearance of the target substance; The attribute includes a feature amount of the appearance, The second observation result includes a physical property value of the target substance corresponding to the second position information.

5. 5. The information processing system according to claim 4, The physical property value includes information regarding the composition of the target substance corresponding to the second position information.

6. 2. The information processing system according to claim 1, In the obtaining step, the first observation result and the second observation result corresponding to each of a plurality of target substances are obtained, The output step outputs the distribution information corresponding to each of the target substances.

7. 7. The information processing system according to claim 6, The first observation result or the second observation result is associated with label information regarding a predetermined label that is assigned in advance according to the corresponding target substance; In the output step, the distribution information is output for each of the labels, and a comparison result of the distribution information for each of the different labels is output.

8. 2. The information processing system according to claim 1, the target substance is a positive electrode material or a negative electrode material of a storage battery, the first observation result includes SEM image data indicative of a result of a SEM measurement of the target material; The second observation result includes EDS data indicating the result of an EDS measurement on the target substance.

9. 1. An information processing method, comprising: A method comprising the steps of the information processing system according to any one of claims 1 to 8.

10. An information processing program, A method for causing at least one computer to execute each step of the information processing system according to any one of claims 1 to 8.

Images