Analysis system, server, analysis method, and program

Abstract

In the present invention, extraction of features included in data pertaining to particulate matter is performed efficiently and accurately. An analysis system (100) comprises a data acquisition unit (1), a feature extraction unit (35), and an output unit (37). The data acquisition unit (1) acquires related data (RD) related to the particulate matter. The feature extraction unit (35) executes prescribed feature extraction processing that takes the related data (RD) as input to extract features included in the related data (RD). The output unit (37) outputs information relating to the features extracted by the feature extraction unit (35).

Description

Analysis system, server, analysis method, and program

[0001] The present invention relates to an analysis system for analyzing particulate matter, a server for performing analysis of particulate matter, an analysis method for particulate matter, and a program for causing a computer to execute the analysis method.

[0002] In recent years, various types of particulate matter (e.g., PM2.5) have become a major environmental problem. For this reason, a system is known that acquires data related to particulate matter, such as the concentration of particulate matter in a predetermined area and information about elements contained in the particulate matter (e.g., elements contained in the particulate matter and the amount of the element contained), and performs analysis of the particulate matter based on the acquired data (see, for example, Patent Document 1).

[0003] International Publication No. 2018 / 117146

[0004] To accurately analyze particulate matter, it is necessary to extract features contained in data related to particulate matter, which requires analyzing a large amount of data.In conventional systems, users had to analyze large amounts of data to extract features, making it difficult to efficiently and accurately extract features contained in data related to particulate matter.

[0005] An object of the present invention is to efficiently and accurately extract features contained in data relating to particulate matter.

[0006] Below, several aspects will be described as means for solving the problems. These aspects can be combined as desired as necessary. An analysis system according to one aspect of the present invention is a system for analyzing particulate matter. The analysis system includes a data acquisition unit, a feature extraction unit, and an output unit. The data acquisition unit acquires related data related to particulate matter. The feature extraction unit executes a predetermined feature extraction process using the related data as input, thereby extracting features contained in the related data. The output unit outputs information related to the features extracted by the feature extraction unit.

[0007] In the above analysis system, the feature extraction unit automatically executes a predetermined feature extraction process using the related data related to particulate matter obtained by the data acquisition unit as input, thereby automatically extracting features contained in the related data. In this way, the feature extraction unit automatically extracts features contained in the related data, allowing the features contained in the related data to be extracted efficiently and accurately. Since the features contained in the related data characterize the particulate matter being analyzed, the ability to efficiently and accurately extract features contained in the related data allows for efficient analysis of particulate matter. Furthermore, the output unit outputs information related to the features extracted by the feature extraction unit, thereby enabling the user to see what features have been extracted from the related data.

[0008] In the above analysis system, the feature extraction unit may extract related data whose instantaneous values ​​exceed a first threshold. In this case, the output unit may display a list of information related to the related data whose instantaneous values ​​exceed the first threshold. This allows the system to automatically extract related data whose instantaneous values ​​exceed the first threshold and contain an abnormality, and to present to the user which related data contains the abnormality.

[0009] In the above analysis system, the feature extraction unit may extract related data whose average or median exceeds a second threshold. In this case, the output unit may display a list of information related to the related data whose average or median exceeds the second threshold. This allows the system to automatically extract related data whose average or median exceeds the second threshold and contains an abnormality, and to indicate to the user which related data has the abnormality.

[0010] In the above analysis system, the output unit may display a graph of related data corresponding to specified information from the displayed list, thereby allowing fluctuations in the related data, including abnormalities, to be visually confirmed.

[0011] In the above analysis system, the feature extraction unit may calculate correlations between multiple pieces of related data and extract information related to the related data for which the calculated correlation is equal to or greater than a third threshold. This eliminates the need for the user to calculate and analyze correlations between various combinations of multiple pieces of related data, thereby enabling efficient and accurate extraction of highly correlated related data.

[0012] In the analysis system, the output unit may display a scatter plot of the plurality of pieces of associated data whose correlation is equal to or greater than a third threshold, thereby allowing the degree of correlation of the extracted associated data to be visually confirmed.

[0013] In the analysis system, the output unit may display multiple scatter plots of the multiple related data, and highlight the scatter plots of the multiple related data whose correlation is equal to or greater than a third threshold, thereby allowing the user to visually recognize which of all the related data has a high correlation.

[0014] In the above analysis system, the related data may be data that changes over time. In this case, the feature extraction unit may calculate the correlation of multiple related data for a predetermined time interval. This allows the correlation of multiple related data for a specific time interval to be calculated. The correlation of the related data for a specific time interval can provide information about events that occurred during that time interval.

[0015] In the above analysis system, the predetermined time interval may be variable, thereby enabling flexible setting of the time interval for calculating the correlation between a plurality of related data.

[0016] In the analysis system, the feature extraction unit may calculate the correlation of multiple pieces of related data in each of multiple small sections included in a predetermined time period, thereby obtaining more detailed information about events that occurred during a specific period based on the correlation of the related data in a specific small section.

[0017] The output unit may display a graph of the change over time of the plurality of associated data whose correlation is equal to or greater than the third threshold, thereby allowing the change over time of the plurality of associated data that are related to each other to be visually confirmed.

[0018] In the above analysis system, the data acquisition unit may acquire the mass concentration of the particulate matter and information related to elements contained in the particulate matter as associated data, thereby enabling analysis of the particulate matter to be performed based on features extracted from the mass concentration of the particulate matter and / or the information related to the elements contained in the particulate matter.

[0019] In the above analysis system, the data acquisition unit may acquire the wind direction at the location where the particulate matter was collected as the related data. In this case, the feature extraction unit may extract, from the related data for a specific wind direction, related data in which the instantaneous content value of an element contained in the particulate matter exceeds a first threshold value, or the average or median content value of an element contained in the particulate matter exceeds a second threshold value. This makes it possible to extract related data indicative of an abnormality in particulate matter coming from a specific direction, i.e., particulate matter coming from a specific source.

[0020] In the above-described analysis system, the data acquisition unit may acquire information about particle diameters of particulate matter as the related data. In this case, the feature extraction unit may extract, from the related data, related data in which the particulate matter has a predetermined particle diameter range. This makes it possible to extract features related to the source of the particulate matter, such as whether the source is close or far.

[0021] In the above-described analysis system, the data acquisition unit may acquire data on gases present at locations where particulate matter is collected as related data. In this case, the feature extraction unit may extract related data on gases of a predetermined type from the related data. This allows extraction of features related to the atmospheric conditions at the installation location of the data acquisition unit, such as whether or not corrosive gases are present at the installation location of the data acquisition unit.

[0022] In the above-described analysis system, the data acquisition unit may acquire data on the wind speed at the location where the particulate matter was collected as the related data. In this case, the feature extraction unit may extract, from the related data, related data in which the wind speed exceeds a predetermined threshold or is equal to or less than a predetermined threshold. This makes it possible to extract features related to the source of the particulate matter, such as whether the source is close or far away.

[0023] In the above analysis system, when the feature extraction unit extracts related data that matches a predetermined index for a predetermined feature from the related data, the output unit may generate an alert, thereby allowing visual and / or audible confirmation that related data that matches the predetermined index has been acquired.

[0024] A server according to another aspect of the present invention is a server that acquires and analyzes related data related to particulate matter. The server includes a feature extraction unit and an output unit. The feature extraction unit executes a predetermined feature extraction process using the related data as input to extract features contained in the related data. The output unit outputs information related to the features extracted by the feature extraction unit.

[0025] In the above server, the feature extraction unit automatically executes a predetermined feature extraction process using related data related to particulate matter as input, thereby automatically extracting features contained in the related data. In this way, the feature extraction unit automatically extracts features contained in the related data, allowing the features contained in the related data to be extracted efficiently and accurately. Since the features contained in the related data characterize the particulate matter being analyzed, the ability to efficiently and accurately extract features contained in the related data allows for efficient analysis of particulate matter. Furthermore, the output unit outputs information related to the features extracted by the feature extraction unit, thereby enabling the user to see what features have been extracted from the related data.

[0026] An analytical method according to yet another aspect of the present invention is an analytical method for particulate matter. The analytical method includes the following steps: a step of acquiring relevant data related to particulate matter; a step of extracting features contained in the relevant data by executing a predetermined feature extraction process using the relevant data as input; and a step of outputting information related to the extracted features.

[0027] In the above analysis method, a predetermined feature extraction process is automatically performed using related data related to particulate matter as input, and features contained in the related data are automatically extracted. By automatically extracting features contained in the related data in this way, the features contained in the related data can be extracted efficiently and accurately. Since the features contained in the related data characterize the particulate matter being analyzed, the ability to efficiently and accurately extract features contained in the related data allows for efficient analysis of particulate matter. Furthermore, by outputting information related to the extracted features, it is possible to show the user what features have been extracted from the related data.

[0028] A program according to yet another aspect of the present invention is a program for causing a computer to execute the above-described analysis method.

[0029] Features contained in particulate matter data can be extracted efficiently and accurately.

[0030] 1 is a diagram showing the configuration of an analysis device. A diagram showing an example of the configuration of a first analysis device. A diagram showing the functional block configuration of an analysis server. A flowchart showing a peak search operation. A diagram showing an example of a list display of related data whose peak values ​​exceed a first threshold. A diagram showing an example of a graph showing changes over time in related data having peak values ​​equal to or greater than a first threshold. A flowchart showing an average value search operation. A diagram showing an example of a list display of related data including peak values ​​equal to or greater than a first threshold and related data including average values ​​equal to or greater than a second threshold. A diagram showing an example of a graph showing changes over time in related data including average values ​​equal to or greater than a second threshold. A flowchart showing an automatic correlation extraction operation. A diagram showing an example of a scatter plot in which multiple correlations are observed between two related data. A diagram showing an example of a scatter plot in which only scatter plots with high correlations are displayed. A diagram showing an example of a scatter plot in which high correlations are highlighted. A diagram showing an example of a graph displaying changes over time in correlation. A diagram showing an example of a graph displaying changes over time in values ​​of two related data with high correlations. A diagram showing a modified example of the first analysis device.

[0031] 1. First Embodiment (1) Analysis System The following describes an analysis system 100. The analysis system 100 is a system for acquiring data related to particulate matter (referred to as related data RD) and analyzing the particulate matter by extracting features included in the acquired related data RD.

[0032] The particulate matter that is the subject of analysis by the analysis system 100 is particulate matter on the order of micrometers that is generated, for example, by combustion processes in factories, brakes on various transportation devices (automobiles, ships, etc.), tires, internal combustion engines, steam engines, exhaust gas purification devices and motors, natural disasters such as volcanic eruptions, and mining development.

[0033] The configuration of an analysis system 100 will be described with reference to Fig. 1. Fig. 1 is a diagram showing the configuration of the analysis system. The analysis system 100 mainly comprises a data acquisition unit 1 and an analysis server 3.

[0034] The data acquisition unit 1 is placed at or near a source of particulate matter and acquires various data related to particulate matter generated from the source as related data RD. The data acquisition unit 1 is placed, for example, at or near a factory that may generate particulate matter, or along or near a road with heavy traffic (such as a main road or expressway). The data acquisition unit 1 may be mounted on a mobile object (such as an automobile) and made mobile.

[0035] The analysis server 3 is a computer system configured with a CPU, storage devices (RAM, ROM, SSD, HDD, etc.), various interfaces, etc. The analysis server 3 is connected to the data acquisition unit 1, and collects and stores the related data RD acquired by the data acquisition unit 1. The analysis server 3 also executes a predetermined feature extraction process using the related data RD collected from the data acquisition unit 1 as input, thereby extracting features contained in the related data RD.

[0036] The analysis server 3 is connected to a client terminal 5. The client terminal 5 is an information terminal used by a user, such as a personal computer, a tablet terminal, or a smartphone. The user can access the analysis server 3 using the client terminal 5 and view the related data RD stored in the analysis server 3, the analysis results of the related data RD output from the analysis server 3, and the like.

[0037] Note that Figure 1 shows an example of an analysis system 100 in which one data acquisition unit 1, one analysis server 3, and one client terminal 5 are provided, but the number of data acquisition units 1, one analysis server 3, and one client terminal 5 in the analysis system 100 is arbitrary.

[0038] (2) Data Acquisition Unit (2-1) Overall Configuration The specific configuration of the data acquisition unit 1 provided in the analysis system 100 will be described below with reference to Fig. 1. The data acquisition unit 1 has a first analysis device 11, a second analysis device 13, a third analysis device 15, and a data collection device 17.

[0039] The first analysis device 11 collects particulate matter present at the location where the data acquisition unit 1 is installed at predetermined times (e.g., every hour) and acquires the mass concentration of the collected particulate matter and information about the elements contained in the particulate matter as related data RD. Here, "information about the elements contained in the particulate matter" refers to the elements contained in the particulate matter and the amount of each element contained in the particulate matter. This information may also include the composition ratio (element ratio) of the elements contained in the particulate matter. By including the first analysis device 11 in the data acquisition unit 1, the analysis system 100 can perform analysis of the particulate matter based on features extracted from the mass concentration of the particulate matter and / or the information about the elements contained in the particulate matter.

[0040] Particulate matter may vary depending on the source, etc., but includes, for example, chromium (Cr), copper (Cu), iron (Fe), aluminum (Al), silicon (Si), lead (Pb), zinc (Zn), mercury (Hg), vanadium (V), calcium (Ca), potassium (K), arsenic (As), selenium (Se), sulfur (S), and elements that cause flame color reactions (e.g., strontium (Sr)). The first analyzer 11 can acquire information about at least these elements and other elements (the elements contained, the amount of each element contained).

[0041] A specific example of the configuration of the first analyzer 11 that can acquire the mass concentration of particulate matter and information about elements contained in the particulate matter will be described later.

[0042] The second analyzer 13 is a wind vane that acquires the wind direction and wind speed at the location where the data acquisition unit 1 is installed (the location where particulate matter was collected) at predetermined times (e.g., every hour) as related data RD. Particulate matter tends to travel by wind from its source. Therefore, by including the second analyzer 13 in the data acquisition unit 1, it is possible to identify the direction from which the particulate matter collected by the first analyzer 11 traveled.

[0043] The third analyzer 15 is a device that analyzes gases contained in the atmosphere around the location of the data acquisition unit 1 (the location where particulate matter is collected) at predetermined time intervals (e.g., every hour). Specifically, the third analyzer 15 identifies gases contained in the atmosphere around the location of the data acquisition unit 1 and / or acquires the concentrations of the gases as related data RD. Gases that can be analyzed by the third analyzer 15 include, for example, hydrocarbons, carbon monoxide (CO), carbon dioxide (CO), nitrogen oxides (NOx), ozone (O3), sulfur oxides (SOx), hydrogen sulfide (HS), and / or volatile organic compounds (VOCs) such as acetone, ethanol, toluene, benzene, and chlorofluorocarbons.

[0044] The data collection device 17 is a data logger that acquires the related data RD acquired by the first analysis device 11 to the third analysis device 15 and transmits it to the analysis server 3. The data collection device 17 determines the timing of acquiring the related data RD from each analysis device, taking into account the time difference between each analysis device and the data collection device 17. This ensures that the data collection device 17 does not miss any of the related data RD acquired by each analysis device. Furthermore, the data collection device 17 associates the time (timestamp) at which the related data RD acquired from each analysis device is acquired with the related data RD acquired from that analysis device. When transmitting the related data RD to the analysis server 3, the data collection device 17 also transmits the timestamp associated with the related data RD to the analysis server 3.

[0045] With the above configuration, the data acquisition unit 1 can acquire the mass concentration of particulate matter, information on elements contained in the particulate matter, wind direction, wind speed, and information on gases contained in the surrounding atmosphere as related data RD related to particulate matter, and provide this to the analysis server 3. Furthermore, since the related data RD acquired by each analysis device is acquired at predetermined time intervals, the related data RD is data whose results change over time. In other words, the related data RD is data in which the results (values, etc.) acquired at each time are arranged in chronological order.

[0046] The data acquisition unit 1 may include other measuring devices in addition to the first to third analysis devices 11 to 15. For example, the data acquisition unit 1 may include a positioning device such as a GPS that acquires the location of the data acquisition unit 1.

[0047] (2-2) Configuration of First Analytical Device A specific configuration example of the first analytical device 11 will be described with reference to Fig. 2. Fig. 2 is a diagram showing the configuration example of the first analytical device. The first analytical device 11 has a collection filter 111, a collection unit 113, a first analytical unit 115, a second analytical unit 117, and a control unit 119.

[0048] The collection filter 111 is a tape-shaped member formed by laminating a collection layer (sometimes referred to as a collection region) made of a porous fluororesin material having pores capable of capturing particulate matter on a reinforcing layer made of a nonwoven fabric of a polymer material (such as polyethylene). Other filters, such as a single-layer glass filter or a single-layer fluororesin material filter, can also be used as the collection filter 111.

[0049] In this embodiment, the collection filter 111 can be moved in the length direction (the direction indicated by the thick arrow in FIG. 2) by rotating the take-up reel 111b to take up the collection filter 111 fed from the feed reel 111a.

[0050] The collection unit 113 is provided to correspond to a first position P1 in the longitudinal direction of the collection filter 111. The collection unit 113, for example, sucks in air using the suction force of a suction port 135 connected to a suction pump 131, and blows the air from an outlet 133 onto a collection region located at the first position P1 of the collection filter 111, thereby collecting particulate matter contained in the air in the collection region.

[0051] The first analysis unit 115 measures the amount of particulate matter trapped on the collection filter 111. Specifically, the first analysis unit 115 has a β-ray source 51 and a β-ray detector 53. The β-ray source 51 is provided at the outlet 133 of the collection unit 113 and emits β-rays to the collection region of the collection filter 111 located at the first position P1. The β-ray source 51 is, for example, a β-ray source using carbon-14 (14C).

[0052] The β ray detector 53 is provided at the suction port 135 of the collection unit 113 so as to face the β ray source 51, and measures the intensity of β rays that have passed through the particulate matter collected in the collection region at the first position P1. The β ray detector 53 is, for example, a photomultiplier tube equipped with a scintillator. The amount of collected particulate matter (mass concentration) is calculated based on the intensity of β rays measured by the β ray detector 53.

[0053] The second analysis unit 117 is provided to correspond to a second position P2 in the longitudinal direction of the collection filter 111, and measures data on fluorescent X-rays emitted from particulate matter present at the second position P2. Specifically, the second analysis unit 117 has an X-ray source 71 and a detector 73.

[0054] The X-ray source 71 irradiates X-rays onto the particulate matter present at the second position P2. The X-ray source 71 is, for example, a device that generates X-rays by irradiating a metal such as palladium with an electron beam. The detector 73 detects fluorescent X-rays emitted from the particulate matter. The detector 73 is, for example, a silicon semiconductor detector or a silicon drift detector.

[0055] The control unit 119 acquires data for calculating the mass concentration of particulate matter using the first analysis unit 115 provided at the first position P1. The control unit 119 also controls the take-up reel 111b to move the collection filter 111 in order to acquire elemental analysis results using the second analysis unit 117 provided at the second position P2. Specifically, each time the collection of particulate matter by the collection unit 113 ends and measurement of the collection amount is completed, the control unit 119 moves the collection region of the collection filter 111 (the region where particulate matter is collected) from the first position P1 where the first analysis unit 115 is provided toward the second position P2 where the second analysis unit 117 is provided.

[0056] After the collection area reaches the second position P2, the control unit 119 irradiates X-rays from the X-ray source 71 toward the second position P2, and acquires the fluorescent X-rays generated from the particulate matter in the collection area by the X-ray irradiation as data for elemental analysis.

[0057] The control unit 119 calculates the mass concentration of the particulate matter as related data RD based on the intensity of β rays measured by the first analysis unit 115. The control unit 119 also acquires fluorescent X-ray data (e.g., fluorescent X-ray spectrum) obtained by the second analysis unit 117, and calculates the elements contained in the particulate matter and their contents as related data RD based on the fluorescent X-ray data. The calculated related data RD is transmitted to the data collection device 17.

[0058] (3) Functional Block Configuration of Analysis Server The functional block configuration of the analysis server 3 will be described below with reference to FIG. 3. FIG. 3 is a diagram showing the functional block configuration of the analysis server. The functional blocks of the analysis server 3 described below may be stored in a storage device of the analysis server 3 and may be realized by a program executable by the analysis server 3. Furthermore, some of the functional blocks may be realized by hardware constituting the analysis server 3. The analysis server 3 has a storage unit 31, a data receiving unit 33, a feature extraction unit 35, and an output unit 37 as functional blocks.

[0059] The storage unit 31 stores various data, programs, setting values, etc. used by the analysis server 3. Specifically, the storage unit 31 stores the related data RD acquired by the data acquisition unit 1. By having the storage unit 31, the analysis server 3 functions as a database of the related data RD.

[0060] The data receiving unit 33 receives the related data RD from the data collecting device 17 of the data acquiring unit 1 and stores it in the memory unit 31. The data receiving unit 33 receives the related data RD accumulated in the data collecting device 17 at a predetermined timing. The data receiving unit 33 may receive the related data RD via the data collecting device 17 immediately after each analysis device outputs the related data RD (i.e., the related data RD is not accumulated in the data collecting device 17), or may receive the related data RD at a timing when the related data RD has accumulated to a certain extent in the data collecting device 17.

[0061] The feature extraction unit 35 executes a predetermined feature extraction process using the related data RD stored in the storage unit 31 as input, thereby extracting features contained in the related data RD. Specifically, as the predetermined feature extraction process, the feature extraction unit 35 statistically analyzes the related data RD to extract features contained in the related data RD. More specifically, the feature extraction unit 35 screens each value contained in the related data RD, whose value changes over time, and extracts features contained in the related data RD. This feature extraction process is called a data screening function.

[0062] Specifically, as a data screening function, the feature extraction unit 35 extracts a feature that a peak value (instantaneous value) included in the related data RD exceeds a first threshold, and notifies the output unit 37 of the time when the peak value that exceeded the first threshold was measured and information identifying the related data RD whose peak value exceeded the first threshold (for example, the data name, etc.). This feature extraction process is called a peak search function.

[0063] As another data screening function, the feature extraction unit 35 extracts a feature that the average value of the values ​​included in the related data RD exceeds a second threshold, and notifies the output unit 37 of the time at which the average value exceeds the second threshold and information identifying the related data RD whose average value exceeds the second threshold. This feature extraction process is called the average value search function. Note that the above average value is, for example, based on a specific time included in the related data RD, and is the average value of multiple values ​​included within a predetermined time range before and after that time. In this case, the "time at which the average value exceeds the second threshold" is the reference time when the average value is calculated. Note that in this data screening function, the median of the values ​​included in the related data RD may be used instead of the average value of the values ​​included in the related data RD.

[0064] The threshold value used in the data screening function may be a predetermined fixed value or may be a value that can be changed depending on the type of related data RD, etc. When the threshold value is made changeable, for example, the standard deviation of the related data RD that is the target of data screening can be calculated, and an integer multiple (for example, 1 or 2) of the standard deviation can be set as the threshold value.

[0065] Furthermore, the feature extraction unit 35 automatically calculates the correlation of the plurality of related data RD stored in the storage unit 31, extracts information related to the plurality of related data RD for which the calculated correlation is equal to or higher than a third threshold as a feature contained in the related data RD, and notifies the output unit 37. This feature extraction process is called an automatic correlation extraction function.

[0066] The feature extraction unit 35 may execute the above-mentioned data screening function and automatic correlation extraction function in response to a command from the client terminal 5, or may execute them automatically at a predetermined timing. Furthermore, when executing the automatic correlation extraction function, the multiple related data RD for which correlation is to be calculated may be selectable by the user using the client terminal 5, or the feature extraction unit 35 may automatically extract the multiple related data RD for which correlation is to be calculated.

[0067] The output unit 37 outputs information related to the features extracted by the feature extraction unit 35 to the client terminal 5. When the feature extraction unit 35 executes the data screening function, the output unit 37 displays, on the client terminal 5, a list of times at which peak values ​​equal to or greater than the first threshold occurred and / or times at which the average or median value became equal to or greater than the second threshold. Each time displayed in the list is provided with a link related to related data RD including the peak value and / or average value (median). When this link is selected, the output unit 37 displays, on the client terminal 5, the data value of the corresponding related data RD and / or a graph of the related data RD.

[0068] On the other hand, when the feature extraction unit 35 executes the automatic correlation extraction function, the output unit 37 outputs information related to a plurality of pieces of related data RD whose calculated correlation is equal to or higher than the third threshold to the client terminal 5. For example, the output unit 37 displays on the client terminal 5 a scatter plot of the plurality of pieces of related data RD whose correlation is equal to or higher than the third threshold.

[0069] Alternatively, the output unit 37 may output scatter diagrams for multiple combinations of associated data RD to the client terminal 5, and highlight, among the displayed scatter diagrams, scatter diagrams for combinations of associated data RD whose correlation is equal to or greater than a third threshold. Specifically, the highlighting can be performed, for example, by surrounding a scatter diagram for a combination of associated data RD whose correlation is equal to or greater than the third threshold with a frame of a predetermined color (e.g., red), or by displaying a scatter diagram for a combination of associated data RD whose correlation is smaller than the third threshold in a lighter color.

[0070] Additionally, the output unit 37 can display a scatter diagram for multiple pieces of related data RD specified by the user using the client terminal 5. For example, the output unit 37 can generate and display a scatter diagram of the content amounts of a combination of two elements from multiple elements selected by the user using the client terminal 5. For example, if the user selects three elements, the output unit 37 can display a scatter diagram of the content amounts of the two elements for each of three combinations of two elements further selected from the three elements on the client terminal 5. This allows the user to visually confirm combinations of related data RD that are highly correlated based on the multiple scatter diagrams displayed.

[0071] (4) Analyzing Operation of Related Data in Analysis System (4-1) Peak Search Operation The analyzing operation of related data RD in the analysis system 100 will be described below. First, the operation of the peak search function (peak search operation) as one of the data screening functions will be described using Figure 4. Figure 4 is a flowchart showing the peak search operation. The peak search operation shown in the flowchart of Figure 4 is executed by the analysis server 3.

[0072] The peak search operation may be performed on all related data RD (including values ​​that change over time) stored in the memory unit 31, or on a plurality of pre-specified related data RD. For example, the peak search operation may be performed on other related data RD (e.g., related data RD related to the content of a specific element) acquired during a period in which a specific wind direction is indicated in the related data RD related to wind direction acquired by the second analyzer 13. By performing a peak search on the related data RD acquired during a specific wind direction, it is possible to monitor, for example, the state of particulate matter from a specific source.

[0073] For example, if the related data RD representing the content of elements contained in particulate matter is the target of peak search, it is possible to extract related data RD in which the peak value of the content of elements contained in particulate matter exceeds the first threshold when a specific wind direction is observed, thereby extracting related data indicative of an abnormality in particulate matter coming from a specific direction, i.e., particulate matter coming from a specific source.

[0074] First, in step S11, the feature extraction unit 35 searches for a peak value included in the related data RD that is the target of the peak search. For example, if the related data RD is data on the content of an element included in particulate matter, the feature extraction unit 35 searches for the peak value of the content. For example, the feature extraction unit 35 scans each value included in the related data RD, and if the currently scanned value is greater than the values ​​before and after it, the feature extraction unit 35 determines the currently scanned value as a sub-peak value, and determines the largest of all sub-peak values ​​included in the related data RD as the peak value.

[0075] Next, in step S12, the feature extraction unit 35 determines whether the peak value found by executing step S11 is equal to or greater than a first threshold. For example, it determines whether the peak value of the element content is equal to or greater than a first threshold. The first threshold can be determined appropriately depending on the type of element, etc. If the peak value is not equal to or greater than the first threshold ("No" in step S12), the feature extraction unit 35 determines that the related data RD currently being the target of the peak search does not contain a peak value equal to or greater than the first threshold, and terminates the peak search operation. If there is other related data RD that is the target of the peak search, the feature extraction unit 35 performs the peak search operation on that related data RD.

[0076] On the other hand, if the peak value found by executing step S11 is equal to or greater than the first threshold value ("Yes" in step S12), in step S13, the feature extraction unit 35 notifies the output unit 37 of the time when the peak value occurred in the related data RD and information identifying the related data RD including this peak value. For example, if the peak value of the content of an element is equal to or greater than the first threshold value, the feature extraction unit 35 outputs to the output unit 37 the time when the peak value of the content of the element occurred and information identifying the related data RD including this peak value.

[0077] In step S14, the output unit 37, which has received the above-mentioned time and the identification information of the related data RD, causes the client terminal 5 to display the time when a peak value equal to or greater than the first threshold occurred. When the client terminal 5 accesses the analysis server 3 using a web browser or the like, the output unit 37 generates an HTML file that displays a table listing the above-mentioned times, as shown in FIG. 5, for example. In the list display shown in FIG. 5, the time when the peak value occurred is displayed in the "Date" column, and a display (Peak) indicating that a peak value equal to or greater than the first threshold is included is displayed in the "Type" column. FIG. 5 is a diagram showing an example of a list display of related data whose peak values ​​exceed the first threshold.

[0078] Furthermore, the output unit 37 generates a link for displaying on the client terminal 5 a graph showing the time-dependent changes in values ​​in the associated data RD, based on the information identifying the associated data RD received from the feature extraction unit 35 in step S13. The output unit 37 attaches the generated link to the display portion of the time at which a peak value included in the associated data RD occurs in the list display of times. In the list display shown in FIG. 5, the underline attached to each time indicates that the above-mentioned link is attached.

[0079] By selecting (e.g., clicking) a time associated with the above-mentioned link on the client terminal 5, a graph such as that shown in Fig. 6 is displayed on the client terminal 5. The graph shown in Fig. 6 is a graph showing the change over time in the content of a specific element A. Fig. 6 is a diagram showing an example of a graph showing the change over time in related data having a peak value equal to or greater than the first threshold.

[0080] The above peak search operation allows the analysis server 3 to automatically, efficiently, and accurately extract characteristics indicating that the related data RD contains large peak values. For example, if a peak value exceeding the first threshold indicates the occurrence of an abnormality, the analysis server 3 can use the above peak search operation to automatically extract related data RD containing the abnormality whose peak value exceeds the first threshold, and can indicate to the user which related data RD contains the abnormality. Furthermore, by displaying the related data RD containing large peak values ​​in a graph on the client terminal 5, the user can visually confirm, for example, the temporal fluctuation of the related data RD containing the abnormality.

[0081] (4-2) Mean Value Search Operation Next, the operation of the mean value search function (mean value search operation) as another data screening function will be described with reference to Fig. 7. Fig. 7 is a flowchart showing the mean value search operation. The mean value search operation shown in the flowchart of Fig. 7 is executed by the analysis server 3.

[0082] Like the peak search operation, the average value search operation may be performed on all related data RD stored in the storage unit 31, or may be performed on a plurality of pre-specified related data RD.

[0083] For example, if the related data RD representing the content of elements contained in particulate matter is the target of the average value search operation, it is possible to extract related data RD in which the average or median content of elements contained in particulate matter exceeds the second threshold when a specific wind direction is observed. This makes it possible to extract related data that indicates an abnormality in particulate matter that has come from a specific direction, i.e., particulate matter that has come from a specific source.

[0084] First, in step S21, the feature extraction unit 35 calculates the average value of the related data RD that is the target of the average value search. For example, if the related data RD is data on the content of elements contained in particulate matter, the average value of the content is calculated. For example, the feature extraction unit 35 uses one value included in the related data RD as a reference and calculates the average value of the reference value and a predetermined number of values ​​before and after the reference value. The feature extraction unit 35 calculates this average value while changing the reference value from the first value to the last value of the related data RD. As a result, for example, if the related data RD includes N values ​​that change over time and the average value of three values ​​centered around the reference value is calculated, N-2 average values ​​are calculated. In other words, by executing step S21, multiple average values ​​are calculated for one piece of related data RD.

[0085] The average value can also be calculated by calculating a moving average of the related data RD. Alternatively, the median value may be calculated instead of the average value.

[0086] Next, in step S22, the feature extraction unit 35 determines whether any of the multiple average values ​​calculated by executing step S21 is equal to or greater than a second threshold. For example, it determines whether the average content value of an element is equal to or greater than the second threshold. The second threshold can be determined appropriately depending on the type of element, etc. If none of the multiple average values ​​is equal to or greater than the second threshold ("No" in step S22), the feature extraction unit 35 determines that the related data RD does not contain an average value equal to or greater than the second threshold, and terminates the average value search operation. If there is other related data RD that is the target of the average value search, the feature extraction unit 35 performs the average value search operation on that related data RD.

[0087] On the other hand, if any of the multiple average values ​​calculated in step S21 is equal to or greater than the second threshold value ("Yes" in step S22), in step S23, the feature extraction unit 35 notifies the output unit 37 of the time when the average value became equal to or greater than the second threshold value and information identifying the related data RD from which this average value was calculated. For example, if the average value of the content of an element is equal to or greater than the second threshold value, the feature extraction unit 35 outputs to the output unit 37 the time when the average value of the content of the element became equal to or greater than the second threshold value and identification information of the related data RD including this average value.

[0088] In step S24, the output unit 37, which has received the above-mentioned time and the identification information of the related data RD, causes the client terminal 5 to display the time at which the average value became equal to or greater than the second threshold. This time is displayed together with the time at which the peak value occurred in a table that lists the times at which peak values ​​equal to or greater than the first threshold occurred, as shown in FIG. 8 . In the row (the third row in FIG. 8 ) in the “Type” column corresponding to the time at which the average value becomes equal to or greater than the second threshold, a display (Average) is displayed indicating that the related data RD includes an average value equal to or greater than the second threshold. FIG. 8 is a diagram showing an example of a list display of related data including peak values ​​equal to or greater than the first threshold and related data including average values ​​equal to or greater than the second threshold.

[0089] In addition, based on the information identifying the related data RD received from the feature extraction unit 35 in step S23, the output unit 37 generates a link to display on the client terminal 5 a graph showing the change in values ​​in the related data RD over time, and attaches the link to the display of the time at which the average value became equal to or greater than the second threshold value.

[0090] By selecting (e.g., clicking) a linked time on the client terminal 5, a graph such as that shown in FIG. 9 is displayed on the client terminal 5. The graph shown in FIG. 9 is a graph showing the change over time in the content of a specific element B. FIG. 9 is a diagram showing an example of a graph showing the change over time in related data including an average value equal to or greater than the second threshold. Furthermore, by selecting the above link, the value included in the corresponding related data RD may be displayed.

[0091] By performing the above-described average value search operation, the analysis server 3 can automatically, efficiently, and accurately extract the characteristic that the related data RD contains a large average value or median. For example, if an average value or median exceeding the second threshold indicates the occurrence of an abnormality, the analysis server 3 can automatically extract the related data RD containing the abnormality whose average value or median exceeds the second threshold through the above-described average value search operation, and can indicate to the user which related data RD contains the abnormality. Furthermore, by displaying the related data RD containing the large average value or median in a graph on the client terminal 5, the user can visually confirm, for example, the fluctuation over time of the related data RD containing the abnormality.

[0092] (4-3) Automatic Correlation Extraction Operation The operation of the automatic correlation extraction function (automatic correlation extraction operation) will be described further with reference to Fig. 10. Fig. 10 is a flowchart showing the automatic correlation extraction operation. The automatic correlation extraction operation shown in the flowchart of Fig. 10 is executed by the analysis server 3.

[0093] First, in step S31, the feature extraction unit 35 selects a plurality of related data RD (two related data RD) for which correlation is to be calculated. For example, before executing step S31, a user selects a plurality of related data RD (a plurality of data items for which correlation is to be calculated) for which correlation is to be examined using the client terminal 5. Thereafter, in step S31, the feature extraction unit 35, which has received the selection result from the user, selects two related data RD for which correlation is to be calculated from the plurality of related data RD selected by the user.

[0094] Alternatively, the feature extraction unit 35 may automatically select two pieces of related data RD whose correlation is to be examined from all of the related data RD stored in the storage unit 31. Furthermore, a plurality of pieces of related data RD when a specific wind direction is observed in the related data RD related to wind direction may be used as targets for calculating the correlation.

[0095] Next, in step S32, the feature extraction unit 35 calculates the correlation between the two associated data RD selected by executing step S31. Specifically, the feature extraction unit 35 uses a value included in one of the two associated data RD as a first element (x) and a value included in the other as a second element (y) to calculate a coefficient of determination (the square of the correlation coefficient) that represents the degree of correlation between the two associated data RD.

[0096] The data acquisition unit 1 acquires the values ​​of the related data RD at predetermined time intervals, so the related data RD contains multiple values ​​that change over time. When the related data RD contains many values, i.e., when the related data RD is obtained as a result of measurements over a long period of time, multiple significant correlations may be observed between two pieces of related data RD, as shown in FIG. 11 . In the example shown in FIG. 11 , two significant correlations are observed in the area surrounded by an ellipse. Note that the coefficient of determination calculated for values ​​of related data RD that contain multiple significant correlations tends to be small. In other words, the coefficient of determination calculated from long-term related data RD may not indicate the existence of multiple significant correlations. FIG. 11 is a diagram illustrating an example of a scatter diagram in which multiple correlations are observed between two pieces of related data.

[0097] The observation of multiple large correlations between multiple pieces of related data RD indicates, for example, that the characteristics of particulate matter generated from a specific source changed during the period in which the related data RD was acquired. It is important in analyzing particulate matter to understand at what point during the period in which the related data RD was acquired the characteristics of the particulate matter changed.

[0098] Therefore, the feature extraction unit 35 not only calculates the coefficient of determination using the values ​​for the entire period during which the related data RD was acquired, but also divides that period into multiple subperiods and calculates the coefficient of determination using the values ​​within those subperiods. For example, if the related data RD to be examined for correlation was data acquired over a one-year period, the feature extraction unit 35 can repeatedly calculate the coefficient of determination using the values ​​for the first month included in the related data RD and then using the values ​​for the next month, thereby calculating a total of 12 coefficients of determination for the related data RD acquired over a one-year period.

[0099] As described above, by calculating the coefficient of determination for each of a plurality of sub-periods included in the long period of time for the related data RD obtained over that long period of time, information about events that occurred during that sub-period can be obtained. For example, if the coefficient of determination for a specific sub-period is small (the correlation between the related data RD is small) while the coefficient of determination for another sub-period is large (the correlation between the related data RD is large), it can be inferred that a special event occurred between these two sub-periods in terms of the generation of particulate matter.

[0100] The above-mentioned short period may be variable. For example, the coefficient of determination can be calculated using the values ​​for the first month included in the related data RD, and then the coefficient of determination can be calculated using the values ​​for the first two months included in the related data RD. In this way, by making the above-mentioned period flexibly settable, it is possible to identify the period during which a change in the correlation of the related data occurred. For example, if no significant correlation is observed in the related data RD for the first month (the coefficient of determination is small), while a relatively significant correlation is observed in the related data RD for the first two months (the coefficient of determination is relatively large), it can be determined that a change in the correlation of the related data RD occurred in at least the latter month of the two-month period. In other words, it can be determined that the characteristics of particulate matter have changed in at least the latter month.

[0101] The above-mentioned short period may also be divided into smaller sub-intervals, and the coefficient of determination may be calculated for each sub-interval. For example, the related data RD acquired over a one-year period may be divided into one-month sub-intervals, and each one-month sub-interval may be further divided into one-week sub-intervals. In this case, more detailed information about events occurring during each sub-interval may be obtained. Furthermore, the above-mentioned sub-intervals may be variable, just like the sub-intervals.

[0102] As described above, when calculating the correlation (coefficient of determination) between two related data RD, by dividing the related data RD into short periods and calculating the coefficient of determination, it is possible to analyze in more detail the timing when changes in the characteristics of particulate matter occur, and to analyze in more detail the timing when specific events occur at the source of particulate matter, etc.

[0103] After calculating the correlation between the two pieces of related data RD, the feature extraction unit 35 determines in step S33 whether the correlation (coefficient of determination) calculated in step S32 is equal to or greater than a third threshold. Since multiple coefficients of determination are calculated in step S32, the feature extraction unit 35 determines whether any of the multiple coefficients of determination is equal to or greater than the third threshold. The third threshold for evaluating the magnitude of the correlation can be determined appropriately depending on the magnitude of the coefficient of determination at which it is determined that there is a correlation.

[0104] If none of the calculated coefficients of determination is greater than or equal to the third threshold ("No" in step S33), the feature extraction unit 35 determines that the correlation between the two currently selected related data RD is low, and proceeds to step S35.

[0105] On the other hand, if any of the calculated coefficients of determination is equal to or greater than the third threshold value ("Yes" in step S33), the feature extraction unit 35 determines that the correlation between the two currently selected related data RD is high, and in step S34 notifies the output unit 37 of information identifying the two currently selected related data RD. At this time, the feature extraction unit 35 notifies the output unit 37 of information identifying the two related data RD as well as information regarding the period during which the coefficient of determination is equal to or greater than the third threshold value.

[0106] After performing the above steps S32 to S34 using the currently selected combination of two associated data RD, the feature extraction unit 35 determines in step S35 whether correlations (coefficients of determination) have been calculated for all combinations of two associated data RD specified by the user or included in all associated data RD stored in the storage unit 31. If correlations have not been calculated for all combinations ("No" in step S35), the feature extraction unit 35 returns to step S31, selects another combination of two associated data RD, and performs steps S32 to S34 for the other combination.

[0107] On the other hand, if correlations are calculated for all combinations ("Yes" in step S35), the output unit 37 displays in step S35 a predetermined graph for multiple related data RDs with high correlations, based on the information identifying the two related data RDs notified by the feature extraction unit 35 in step S34 and the period during which the correlation (coefficient of determination) between the two related data RDs was equal to or greater than the third threshold.

[0108] The output unit 37 generates a scatter plot of the values ​​of the two highly correlated related data RD within the notified period, and outputs it to the client terminal 5 .

[0109] When outputting a scatter diagram of two associated data RD having a correlation (coefficient of determination) equal to or greater than the third threshold, the output unit 37 may display on the client terminal 5 only the scatter diagram of the two associated data RD having a correlation equal to or greater than the third threshold, as shown in Fig. 12, or may display multiple scatter diagrams for all combinations of two associated data RD and highlight the scatter diagrams having a correlation (coefficient of determination) equal to or greater than the third threshold, for example, by surrounding them with a frame, as shown in Fig. 13. Fig. 12 is a diagram showing an example of a display of only scatter diagrams having a high correlation. Fig. 13 is a diagram showing an example of a display of scatter diagrams having a high correlation.

[0110] Furthermore, the output unit 37 can display a graph of the change over time of the multiple highly correlated related data RD based on the information identifying the two related data RD notified by the feature extraction unit 35 in step S34 and the period during which the correlation between the two related data RD was equal to or greater than the third threshold. It can be arbitrarily determined whether to display a scatter plot or a graph of the change over time, or both.

[0111] For example, if the result of executing the automatic correlation extraction function shows that, between time T1 and time T2, there is a high correlation between the content of element C and the content of element D (the coefficient of determination is equal to or greater than the third threshold (TH3)), there is a high correlation between the content of element E and the content of element F, and there is a high correlation between the content of element G and the content of element H, then a graph such as that shown in FIG. 14 can be displayed for each combination of these three elements. In FIG. 14 , the time change graph of the correlation between the content of element C and the content of element D is represented by a solid line, the time change graph of the correlation between the content of element E and the content of element F is represented by a dashed line, and the time change graph of the correlation between the content of element G and the content of element H is represented by a dashed line. FIG. 14 is a diagram showing an example of a graph displaying changes in correlation over time.

[0112] The above-described automatic correlation extraction operation allows the analysis server 3 to automatically, efficiently, and accurately extract features that indicate a high correlation between multiple pieces of related data RD. For example, if there is a high correlation between the contents of multiple elements, it can be inferred that particulate matter with the same contents (element ratios) of the multiple elements was measured during the period in which the correlation was observed.

[0113] Furthermore, by displaying a scatter plot of two highly correlated related data RD, it is possible to visually confirm the magnitude of the correlation between the two related data RD. Furthermore, by displaying multiple scatter plots regardless of the magnitude of the correlation and highlighting the scatter plot with a high correlation among the multiple displayed scatter plots, it is possible to visually confirm which of all the related data RD has a high correlation.

[0114] Furthermore, by graphically displaying the time change in correlation for a plurality of pieces of highly correlated related data RD, it is possible to visually confirm how the correlation of the plurality of pieces of related data RD changes over time.

[0115] For example, if the related data RD is data representing the content of elements contained in particulate matter, it is possible to visually confirm how the correlation between the content of multiple elements changes over time. A high correlation between the content of multiple elements means that the particulate matter contains multiple elements that are highly correlated in a certain composition ratio. The types and composition ratios of elements contained in particulate matter depend greatly on the characteristics of the particulate matter, such as the source and / or generation conditions of the particulate matter.

[0116] Therefore, by graphically displaying the change in correlation over time for the content of multiple elements that have a high correlation, a user can, for example, visually confirm the change in correlation over time and infer changes in the characteristics of the particulate matter, i.e., at what point in time and from which source the particulate matter is arriving, and / or at what point in time the conditions for generating the particulate matter have changed.

[0117] When a scatter diagram of two highly correlated associated data RD is specified while the scatter diagram is being displayed, the output unit 37 may graphically display the change over time in the values ​​of the two associated data RD that generated the scatter diagram, as shown in Fig. 15. Fig. 15 is a diagram showing an example of a graphical display of the change over time in the values ​​of two highly correlated associated data. Fig. 15 shows an example of a graphical display of the change over time in the content of element C and the change over time in the content of element D, which are displayed side by side, by specifying a scatter diagram of the content of element C and the content of element D, which are highly correlated, as shown in Fig. 12.

[0118] While it is unclear from only a scatter diagram such as that of Fig. 12 over which period the correlation between the two pieces of related data RD becomes large, it is possible to estimate over which period the correlation becomes large by graphically displaying the change over time as in Fig. 14. In the example shown in Fig. 14, the tendency of increase / decrease in the content of element C and the tendency of increase / decrease in the content of element D are the same between time T1 and time T2, and it can be estimated that the correlation between the content of element C and the content of element D becomes large over this period.

[0119] 11 , the output unit 37 may color-code points of the related data RD for periods with high correlation and output the result to the client terminal 5. This allows multiple correlations between two highly correlated related data RD to be identified by the colors of the points on the scatter plot, even if the two related data RD include multiple periods with high correlation. For example, if the two related data RD are data on particulate matter generated from the same source, it is possible to visually confirm that the properties of the particulate matter (e.g., elemental composition ratios) are changing over time.

[0120] (5) Modification of First Analytical Device The first analytical device 11 that acquires the related data RD regarding particulate matter is not limited to the configuration shown in Fig. 2. Specifically, as shown in Fig. 16, the first analytical device 11 may include a light source 51' and a scattered light detection unit 53' instead of the beta ray source 51 and beta ray detector 53 that measure the amount of captured particulate matter. Fig. 16 is a diagram showing a modification of the first analytical device.

[0121] The light source 51' emits laser light L toward the inside of the exhaust port 133. The scattered light detection unit 53' detects scattered light generated when the laser light L is scattered by particulate matter while passing through the inside of the exhaust port 133. The scattered light detection unit 53' is, for example, a photodetector such as a photodiode. This allows the control unit 119 to acquire information about particulate matter contained in the atmosphere at the location where the first analyzer 11 is installed, based on the intensity of the scattered light detected by the scattered light detection unit 53'. Specifically, based on the intensity of the scattered light, data about the particle size of particulate matter contained in the atmosphere (e.g., the particle size distribution of particulate matter) can be acquired as related data RD. Furthermore, based on the intensity of the scattered light, data about the content of particulate matter, such as the number of particulate matter particles contained in the atmosphere, can be acquired as related data RD.

[0122] (6) Application Examples of the Analysis System The following describes application examples of the above-described analysis system 100. The above-described analysis system 100 can be applied, for example, to environmental management of storage locations for products, etc. Specifically, the above-described analysis system 100 can be used to analyze whether or not corrosive gases, corrosive particulate matter, etc. that may affect products, etc., are present in a storage location for products, etc.

[0123] More specifically, the first analysis device 11 to the third analysis device 15 are installed in a storage location for products, etc., and related data RD regarding elements contained in particulate matter present in the space of the storage location, related data RD regarding the particle size of the particulate matter, related data RD regarding gases present in the space of the storage location, related data RD regarding wind direction at the storage location, and related data RD regarding wind speed at the storage location are obtained, and environmental management of the storage location can be performed based on this related data RD.

[0124] As a method for obtaining related data RD regarding the particle size of particulate matter, a method can be used in which a first analysis device 11 such as that shown in Figure 16 is used to obtain related data RD regarding particle size based on the intensity of scattered light generated at the outlet 133.

[0125] Alternatively, the related data RD related to particle size can be obtained using a plurality of first analyzers 11 as shown in Fig. 2. Specifically, each of the plurality of first analyzers 11 is provided with a collection unit 113 that collects particulate matter of different particle size ranges, and the related data RD (related data RD related to elements contained in the particulate matter, related data RD related to the content (mass concentration) of the particulate matter) acquired by the plurality of first analyzers 11 is classified according to which first analyzer 11 the related data RD was acquired by, thereby making it possible to acquire the related data RD classified according to the particle size of the particulate matter (i.e., related data RD including data related to the particle size of the particulate matter).

[0126] In addition to the first analysis device 11 to the third analysis device 15, another analysis device capable of measuring the particle size of particulate matter may be connected to the data collection device 17, and related data RD regarding the particle size of the particulate matter may be measured using this analysis device.

[0127] In this case, the feature extraction unit 35 of the analysis server 3 executes a feature extraction process to extract related data RD indicating that particulate matter has a predetermined particle size range from the related data RD stored in the storage unit 31. For example, when the feature extraction unit 35 extracts related data RD indicating that particulate matter has a predetermined particle size range, the output unit 37 of the analysis server 3 can output information indicating that particulate matter having this particle size range is present in the space of the storage location.

[0128] For example, when the feature extraction unit 35 extracts the related data RD indicating that the particulate matter has a large particle size equal to or greater than a predetermined threshold, the output unit 37 can output information that the space where the product, etc. is stored contains particulate matter that was generated in a relatively nearby location. On the other hand, when the feature extraction unit 35 extracts the related data RD indicating that the particulate matter has a small particle size equal to or less than a predetermined threshold, the output unit 37 can output information that the space where the product, etc. is stored contains particulate matter that was generated in a relatively distant location.

[0129] The feature extraction unit 35 can extract related data RD related to particulate matter that arrives from a specific direction, contains a specific element, and has a specific particle size range, based on information about the particle size of the particulate matter, information about wind direction, information about wind speed, information about the elements contained in the particulate matter, etc. This allows more detailed information about the source of the particulate matter to be obtained. When the feature extraction unit 35 extracts related data RD related to particulate matter generated from a specific source, the output unit 37 can output information that particulate matter generated from the specific source is present in the storage space.

[0130] As described above, by extracting related data RD based on information regarding the particle size of particulate matter, information regarding wind direction, information regarding wind speed, and information regarding the elements contained in the particulate matter, it is possible to determine whether the related data RD is related data RD regarding particulate matter that has been artificially generated by factory operations, etc., or related data RD regarding particulate matter that exists naturally in soil, etc.

[0131] For example, if the feature extraction unit 35 extracts the related data RD related to particulate matter that arrives from a specific direction, contains a specific element that is likely to be generated from a specific factory, and has a large particle size, the output unit 37 can output information that the storage location contains particulate matter that originates from a factory located nearby in the specific direction.Furthermore, if the feature extraction unit 35 extracts the related data RD related to particulate matter that arrives from another direction, contains a specific element that is contained in soil, and has a small particle size, the output unit 37 can output information that the storage location contains particulate matter that originates from soil located farther in the other direction.

[0132] Furthermore, when the feature extraction unit 35 extracts related data RD indicating that the wind speed exceeds a predetermined threshold from the related data RD stored in the storage unit 31, the output unit 37 can output information suggesting that particulate matter may be coming from a relatively distant position. On the other hand, when the feature extraction unit 35 extracts related data RD indicating that the wind speed is equal to or less than the predetermined threshold, the output unit 37 can output information suggesting that particulate matter may be coming from a relatively close position.

[0133] Furthermore, when the feature extraction unit 35 extracts related data RD indicating that the particle size of the particulate matter is small and that the wind speed exceeds a predetermined threshold, the output unit 37 can output information suggesting that the particulate matter may be coming from a very distant location. On the other hand, when the feature extraction unit 35 extracts related data RD indicating that the particle size of the particulate matter is large and that the wind speed is equal to or less than a predetermined threshold, the output unit 37 can output information suggesting that the particulate matter may be coming from a very close location.

[0134] As described above, the feature extraction unit 35 extracts a feature that combines a feature related to wind speed and a feature related to particle size of particulate matter, thereby enabling more accurate identification of the source of particulate matter.

[0135] By extracting the features related to particulate matter as described above, it is possible to determine how to deal with products stored in the storage location based on the properties of the particulate matter present in the storage location. For example, if the feature extraction unit 35 extracts related data RD indicating that particulate matter that has a corrosive or other effect on the product is present in the storage location, measures can be taken, such as moving the product to another location, covering the product to prevent the particulate matter from adhering to the product, or cleaning the product by spraying water.

[0136] Furthermore, the feature extraction unit 35 executes a feature extraction process to extract related data RD indicating that a predetermined type of gas is contained from the related data RD stored in the storage unit 31. For example, when the feature extraction unit 35 extracts related data RD indicating that a predetermined type of gas is contained, the output unit 37 can output information indicating that this predetermined type of gas is present in the space of the storage location.

[0137] For example, when the feature extraction unit 35 extracts related data RD indicating the presence of corrosive gases such as sulfur oxides (SOx) and hydrogen sulfide (HS), the output unit 37 can output information indicating the presence of corrosive gases in the storage space. This allows measures to be taken, such as moving the product to another location, when information indicating the presence of corrosive gases in the storage space is output.

[0138] When the feature extraction unit 35 extracts related data RD that matches a predetermined index for a predetermined feature, such as the particle size of the particulate matter exceeding a predetermined threshold, the wind direction pointing in a specific direction, the wind speed exceeding a predetermined threshold, the particulate matter containing a predetermined element, or the presence of a predetermined type of gas, the output unit 37 can also generate an alert. The output unit 37 can generate an alert by, for example, emitting a sound or displaying a predetermined message on the display unit of the analysis server 3.

[0139] By generating an alert when related data RD that matches a predetermined index is extracted, the user can be made aware visually and / or audibly of, for example, the presence of particulate matter and / or gas that may affect the product in the storage space. As a result, when an alert is generated, measures such as moving the product can be taken quickly.

[0140] 2. Features of the Embodiments The embodiments described above can also be expressed as follows: (1) The analysis system is a system that performs analysis on particulate matter. The analysis system includes a data acquisition unit, a feature extraction unit, and an output unit. The data acquisition unit acquires related data on particulate matter. The feature extraction unit executes a predetermined feature extraction process using the related data as input, thereby extracting features contained in the related data. The output unit outputs information related to the features extracted by the feature extraction unit.

[0141] In the above analysis system, the feature extraction unit automatically executes a predetermined feature extraction process using the related data related to particulate matter obtained by the data acquisition unit as input, thereby automatically extracting features contained in the related data. In this way, the feature extraction unit automatically extracts features contained in the related data, allowing the features contained in the related data to be extracted efficiently and accurately. Since the features contained in the related data characterize the particulate matter being analyzed, the ability to efficiently and accurately extract features contained in the related data allows for efficient analysis of particulate matter. Furthermore, the output unit outputs information related to the features extracted by the feature extraction unit, thereby enabling the user to see what features have been extracted from the related data.

[0142] (2) In the analysis system of (1), the feature extraction unit may extract related data whose instantaneous values ​​exceed a first threshold. In this case, the output unit may display a list of information related to the related data whose instantaneous values ​​exceed the first threshold. This allows the system to automatically extract related data whose instantaneous values ​​exceed the first threshold and contain an abnormality, and to present to the user which related data contains the abnormality.

[0143] (3) In the analysis system of (1) or (2) above, the feature extraction unit may extract related data whose average or median exceeds a second threshold. In this case, the output unit may display a list of information related to the related data whose average or median exceeds the second threshold. This allows the system to automatically extract related data whose average or median exceeds the second threshold and contains an abnormality, and to indicate to the user which related data has the abnormality.

[0144] (4) In the analysis system of (2) or (3), the output unit may display a graph of related data corresponding to specified information from the displayed list, thereby allowing the user to visually check fluctuations in the related data, including abnormalities.

[0145] (5) In the analysis systems of (1) to (4) above, the feature extraction unit may calculate correlations between multiple pieces of related data and extract information related to the related data for which the calculated correlation is equal to or greater than a third threshold. This eliminates the need for the user to calculate and analyze correlations between various combinations of multiple pieces of related data, allowing for efficient and accurate extraction of highly correlated related data.

[0146] (6) In the analysis system of (5), the output unit may display a scatter plot of the plurality of related data whose correlation is equal to or greater than a third threshold, thereby allowing the degree of correlation of the extracted related data to be visually confirmed.

[0147] (7) In the analysis system of (5), the output unit may display multiple scatter plots of the multiple related data, and highlight the scatter plots of the multiple related data whose correlation is equal to or greater than a third threshold. This allows visual recognition of which data among all the related data has a high correlation.

[0148] (8) In the analysis systems of (5) to (7) above, the related data may be data that changes over time. In this case, the feature extraction unit may calculate the correlation of multiple related data in a predetermined time interval. This allows the correlation of multiple related data in a specific time interval to be calculated. The correlation of the related data in a specific time interval can provide information about events that occurred in that time interval.

[0149] (9) In the analysis system of (8), the predetermined time interval may be variable, thereby enabling flexible setting of the time interval for calculating the correlation between a plurality of related data.

[0150] (10) In the analysis system of (8) or (9), the feature extraction unit may calculate correlations of multiple pieces of related data in each of multiple small sections included in a predetermined time period. This allows for more detailed information about events that occurred during a specific period to be obtained based on the correlations of the related data in specific small sections.

[0151] (11) In the analysis system of (8) to (10), the output unit may display a graph of the change over time of the plurality of related data whose correlation is equal to or greater than a third threshold, thereby allowing the change over time of the plurality of related data to be visually confirmed.

[0152] (12) In the analysis system according to any one of (1) to (11), the data acquisition unit may acquire, as associated data, the mass concentration of the particulate matter and information related to elements contained in the particulate matter, thereby enabling analysis of the particulate matter to be performed based on features extracted from the mass concentration of the particulate matter and / or the information related to the elements contained in the particulate matter.

[0153] (13) In the analysis system of (12), the data acquisition unit may acquire, as the related data, the wind direction at the location where the particulate matter was collected. In this case, the feature extraction unit may extract, from the related data for a specific wind direction, related data in which the instantaneous content value of an element contained in the particulate matter exceeds a first threshold value, or the average or median content value of an element contained in the particulate matter exceeds a second threshold value. This makes it possible to extract related data indicative of an abnormality in particulate matter coming from a specific direction, i.e., particulate matter coming from a specific source.

[0154] (14) In the analysis system of (1) to (13), the data acquisition unit may acquire information about particle size of particulate matter as the related data. In this case, the feature extraction unit may extract, from the related data, related data in which the particulate matter has a predetermined particle size range. This makes it possible to extract features related to the source of the particulate matter, such as whether the source is close or far.

[0155] (15) In the analysis system according to any one of (1) to (14), the data acquisition unit may acquire data on gases present at locations where particulate matter is collected as related data. In this case, the feature extraction unit may extract related data on gases present at predetermined types of gases from the related data. This allows extraction of features related to the atmospheric conditions at the location where the data acquisition unit is installed, such as whether or not corrosive gases are present at the location where the data acquisition unit is installed.

[0156] (16) In the analysis system of any one of (1) to (15), the data acquisition unit may acquire data on wind speed at the location where the particulate matter was collected as the related data. In this case, the feature extraction unit may extract, from the related data, related data in which the wind speed exceeds a predetermined threshold or is equal to or less than a predetermined threshold. This allows extraction of features related to the source of the particulate matter, such as whether the source is close or far away.

[0157] (17) In the analysis systems of (1) to (16) above, when the feature extraction unit extracts related data that matches a predetermined index for a predetermined feature from the related data, the output unit may generate an alert, thereby allowing visual and / or audible confirmation that related data that matches the predetermined index has been acquired.

[0158] (18) The server acquires and analyzes related data related to particulate matter. The server includes a feature extraction unit and an output unit. The feature extraction unit executes a predetermined feature extraction process using the related data as input to extract features contained in the related data. The output unit outputs information related to the features extracted by the feature extraction unit.

[0159] In the above server, the feature extraction unit automatically executes a predetermined feature extraction process using related data related to particulate matter as input, thereby automatically extracting features contained in the related data. In this way, the feature extraction unit automatically extracts features contained in the related data, allowing the features contained in the related data to be extracted efficiently and accurately. Since the features contained in the related data characterize the particulate matter being analyzed, the ability to efficiently and accurately extract features contained in the related data allows for efficient analysis of particulate matter. Furthermore, the output unit outputs information related to the features extracted by the feature extraction unit, thereby enabling the user to see what features have been extracted from the related data.

[0160] (19) The analysis method is an analysis method for particulate matter. The analysis method includes the following steps: A step of acquiring related data related to particulate matter; A step of extracting features contained in the related data by executing a predetermined feature extraction process using the related data as input; and A step of outputting information related to the extracted features.

[0161] In the above analysis method, a predetermined feature extraction process is automatically performed using related data related to particulate matter as input, and features contained in the related data are automatically extracted. By automatically extracting features contained in the related data in this way, the features contained in the related data can be extracted efficiently and accurately. Since the features contained in the related data characterize the particulate matter being analyzed, the ability to efficiently and accurately extract features contained in the related data allows for efficient analysis of particulate matter. Furthermore, by outputting information related to the extracted features, it is possible to show the user what features have been extracted from the related data.

[0162] (20) A program according to yet another aspect of the present invention is a program for causing a computer to execute the above-described analysis method.

[0163] 3. Other Embodiments While several embodiments of the present invention have been described above, the present invention is not limited to the above embodiments, and various modifications are possible without departing from the spirit of the invention. In particular, the several embodiments and modifications described in this specification can be arbitrarily combined as needed. (A) The order and / or processing content of each step shown in the flowcharts of Figures 4, 7, and 10 may be changed without departing from the spirit of the invention.

[0164] (B) The above-mentioned peak search function and average value search function may be provided in the data collection device 17 of the data acquisition unit 1. When the related data RD accumulated in the data collection device 17 contains a peak value equal to or greater than the first threshold value and / or contains an average value equal to or greater than the second threshold value, the data collection device 17 having the peak search function and average value search function transmits an email to the outside to that effect and / or to issue a warning.

[0165] More specifically, for example, when there is related data RD accumulated in the data collection device 17 in which the concentration of a specific component detected in a specific wind direction has exceeded a certain value for a certain period of time, the data collection device 17 can issue an alert email.

[0166] (C) In the automatic correlation extraction operation, when calculating the correlation using the elemental ratio of elements contained in particulate matter, the correlation (coefficient of determination) may be calculated by removing data in which the elemental ratio is extremely small or large.

[0167] (D) In ​​the first embodiment described above, the analysis system 100 was a so-called "client-server system" having the analysis server 3, but is not limited to this. For example, the data acquisition unit 1 (each analysis device or data collection device 17) may be provided with the functions of the feature extraction unit 35 and / or the output unit 37, thereby forming an analysis system as so-called "edge computing." In this case, the data acquisition unit 1 may transmit, in addition to the related data RD, features extracted from the related data RD to the analysis server.

[0168] (E) The feature extraction unit 35 may realize the feature extraction process using, for example, a machine learning algorithm such as a neural network. Specifically, for example, a trained model of a neural network may be generated using related data RD having the feature to be extracted and the features of this related data RD as training data, and this model may be used as the feature extraction unit 35. By inputting the related data RD to be analyzed into the feature extraction unit 35, which is a trained model, the features contained in the related data RD can be extracted.

[0169] (F) The feature extraction unit 35 can extract features contained in the related data RD using other statistical analysis methods such as data mining of the related data RD, in addition to the statistical analysis method described in the first embodiment above.

[0170] (G) The feature extraction unit 35 may extract features contained in the related data RD by setting a predetermined threshold and executing multiple algorithms that determine whether the data values ​​contained in the related data RD exceed the threshold.

[0171] (H) The analysis server 3 may be capable of predicting the analysis results (related data RD) of particulate matter in the analysis devices (first analysis device 11 to third analysis device 15) based on information about various processes in a factory, etc. (e.g., temperature, humidity, pressure, gas flow rate, etc.). Specifically, for example, it can create models of various processes that predict the analysis results and predict the analysis results from the calculation results of the models.

[0172] The present invention can be widely applied to analytical systems for analyzing particulate matter.

[0173] 100: Analysis system 1 Data acquisition unit 11 First analysis device 111 Collection filter 111a Delivery reel 111b Take-up reel P1 First position P2 Second position 113 Collection unit 115 First analysis unit 51 β-ray source 53 β-ray detector 51' Light source 53' Scattered light detection unit 117 Second analysis unit 71 X-ray source 73 Detector 119 Control unit 131 Suction pump 133 Discharge port 135 Suction port 13 Second analysis device 15 Third analysis device 17 Data collection device 3 Analysis server 31 Memory unit 33 Data receiving unit 35 Feature extraction unit 37 Output unit 5 Client terminal RD Related data

Claims

1. An analysis system for performing analysis on particulate matter, a data acquisition unit that acquires relevant data regarding the particulate matter; a feature extraction unit that extracts features included in the related data by executing a predetermined feature extraction process using the related data as input; an output unit that outputs information related to the features extracted by the feature extraction unit; An analysis system comprising:

2. the feature extraction unit extracts the related data whose instantaneous value exceeds a first threshold; the output unit displays a list of information related to the associated data whose instantaneous value exceeds a first threshold. The analytical system of claim 1 .

3. the feature extraction unit extracts the related data whose average value or median value exceeds a second threshold; the output unit displays a list of information related to the related data whose average value or median value exceeds a second threshold. The analysis system according to claim 1 or 2.

4. The analysis system according to claim 2 , wherein the output unit displays the related data corresponding to specified information from among the displayed list of information in a graph.

5. The analysis system according to claim 1 , wherein the feature extraction unit calculates correlations between a plurality of pieces of related data, and extracts information about the related data for which the calculated correlation is equal to or greater than a third threshold value.

6. The analysis system according to claim 5 , wherein the output unit displays a scatter plot of the plurality of related data whose correlation is equal to or greater than the third threshold.

7. The analysis system according to claim 5 , wherein the output unit displays a plurality of scatter plots of the plurality of associated data, and highlights the scatter plots of the plurality of associated data whose correlation is equal to or greater than the third threshold.

8. the related data is data that changes over time; The analysis system according to claim 5 , wherein the feature extraction unit calculates correlations between a plurality of related data items in a predetermined time period.

9. The analytical system of claim 8 , wherein the predetermined time interval is variable.

10. The analysis system according to claim 8 , wherein the feature extraction unit calculates correlations of a plurality of related data in each of a plurality of small sections included in the predetermined time section.

11. The analysis system according to claim 8 , wherein the output unit displays a graph of a change over time in a plurality of pieces of related data whose correlation is equal to or greater than the third threshold.

12. The analysis system according to claim 1 , wherein the data acquisition unit acquires, as the associated data, information relating to a mass concentration of the particulate matter and information relating to elements contained in the particulate matter.

13. the data acquisition unit acquires, as the related data, a wind direction at a location where the particulate matter is collected; The analysis system of claim 12, wherein the feature extraction unit extracts the related data for a specific wind direction in which the instantaneous value of the content of elements contained in the particulate matter exceeds a first threshold value, or the average or median value of the content of elements contained in the particulate matter exceeds a second threshold value.

14. the data acquisition unit acquires information about particle diameters of the particulate matter as the related data; The analysis system according to claim 1 , wherein the feature extraction unit extracts, from the associated data, the associated data in which the particulate matter has a predetermined particle size range.

15. the data acquisition unit acquires data relating to gas at a location where the particulate matter is collected as the related data; The analysis system according to claim 1 , wherein the feature extraction unit extracts the associated data in which the gas is a predetermined type of gas from the associated data.

16. the data acquisition unit acquires data on wind speed at a location where the particulate matter is collected as the related data; The analysis system according to claim 1 , wherein the feature extraction unit extracts, from the related data, the related data in which the wind speed exceeds a predetermined threshold or is equal to or less than a predetermined threshold.

17. The analysis system according to claim 1 or 2, wherein when the feature extraction unit extracts, from the related data, the related data that matches a predetermined index for a predetermined feature, the output unit generates an alert.

18. A server that acquires and analyzes relevant data related to particulate matter, a feature extraction unit that extracts features included in the related data by executing a predetermined feature extraction process using the related data as input; an output unit that outputs information related to the features extracted by the feature extraction unit; A server comprising:

19. An analytical method for particulate matter, comprising: obtaining relevant data regarding said particulate matter; extracting features included in the related data by executing a predetermined feature extraction process using the related data as input; outputting information related to the extracted features; An analysis method comprising:

20. obtaining relevant data regarding particulate matter; extracting features included in the related data by executing a predetermined feature extraction process using the related data as input; outputting information related to the extracted features; A program for causing a computer to execute an analytical method including the steps of: