Information processing device, information processing system, inference device, machine learning device, information processing method, inference method, and machine learning method

Abstract

To provide an information processing device capable of detecting a foreign object that is present in a sample with high accuracy.SOLUTION: An information processing device 5 performs material analysis on a sample. The information processing device 5 includes: an input information acquisition unit 501 configured to acquire input information 111 including sample measurement data 111a and incidental information 111b associated with the sample; and a foreign object information output unit 502 configured to output, based on the input information 111, foreign object information 112 indicating information about one or more components present as a foreign object in the sample, or a "None" message if the foreign object information is not present.SELECTED DRAWING: Figure 5

Description

[Technical Field]

[0001] The present invention relates to an information processing device, an information processing system, an inference device, a machine learning device, an information processing method, an inference method, and a machine learning method. [Background technology]

[0002] A data processing device has been disclosed that identifies an unknown substance by searching for a spectrum highly similar to the spectrum of the unknown substance acquired by an infrared spectrophotometer from a library that accumulates spectra of known substances (see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 3577281 Summary of the Invention [Problem to be solved by the invention]

[0004] The data processing device disclosed in Patent Document 1 identifies unknown substances based solely on spectral similarity, and its accuracy is questionable.

[0005] In view of the above-mentioned problems, an object of the present invention is to provide an information processing device, an information processing system, an inference device, a machine learning device, an information processing method, an inference method, and a machine learning method that can search for foreign matter present in a sample with high accuracy. [Means for solving the problem]

[0006] In order to achieve the above object, an information processing device according to one aspect of the present invention comprises: An information processing device for performing material analysis of a sample, an input information acquisition unit that acquires input information including measurement data of the sample and additional information associated with the sample; a foreign matter information output unit that outputs foreign matter information indicating information on one or more components present as foreign matters in the sample based on the input information, or outputs "none" if there is no foreign matter information; Equipped with [Effects of the Invention]

[0007] According to an information processing device according to an aspect of the present invention, foreign matter present in a sample can be searched for with high accuracy.

[0008] Problems, configurations, and effects other than those described above will become apparent from the detailed description of the invention that follows. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is an overall configuration diagram showing an example of an information processing system 1 according to a first embodiment. [Figure 2] 1 shows an example of a data structure diagram of component information 110 stored in a database device 3 of the first embodiment. [Figure 3] 1 shows examples of chemical characteristics, physical characteristics, and administrative characteristics stored in the database device 3 of the first embodiment. [Figure 4] 2 is a block diagram showing an example of an information processing device 5 according to the first embodiment. FIG. [Figure 5] 1 shows an example of foreign substance information 112 output by the information processing device 5 of the first embodiment. [Figure 6] FIG. 2 is a block diagram showing an example of a user terminal device 6 in the first embodiment. [Figure 7] FIG. 9 is a hardware configuration diagram illustrating an example of a computer 900 according to the first embodiment. [Figure 8] 5 is a flowchart showing an example of an information processing method performed by the information processing device 5 and the user terminal device 6 of the first embodiment. [Figure 9] 1 shows an example of an input screen of a user terminal device 6 in the first embodiment. [Figure 10] 1 shows an example of an output screen of a user terminal device 6 in the first embodiment. [Figure 11]FIG. 10 is an overall configuration diagram showing an example of an information processing system 1 according to a second embodiment. [Figure 12] FIG. 10 is a block diagram illustrating an example of a machine learning device 4 according to a second embodiment. [Figure 13] 10 is a diagram showing an example of a learning model 10 and learning data 11 according to a second embodiment. FIG. [Figure 14] 10 is a flowchart showing an example of a machine learning method performed by the machine learning device 4 of the second embodiment. [Figure 15] FIG. 10 is a block diagram showing an example of an information processing device 5 according to a second embodiment. [Figure 16] FIG. 10 is a functional explanatory diagram illustrating an example of an information processing device 5 according to a second embodiment. [Figure 17] FIG. 10 is a block diagram showing an example of a user terminal device 6 according to a second embodiment. [Figure 18] 10 is a flowchart showing an example of an information processing method performed by the information processing device 5 and the user terminal device 6 of the second embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, an embodiment for carrying out the present invention will be described with reference to the drawings. The scope necessary for the explanation to achieve the object of the present invention will be schematically shown, and the scope necessary for explaining the relevant part of the present invention will be mainly explained, and the parts that are omitted from the explanation will be based on publicly known techniques.

[0011] (Information Processing System 1) FIG. 1 is an overall configuration diagram showing an example of an information processing system 1 according to a first embodiment. The information processing system 1 according to this embodiment functions as a system for searching for information related to components of foreign matter. The information processing system 1 mainly comprises a measuring device 2, a database device 3, an information processing device 5, and a user terminal device 6. The database device 3, the information processing device 5, and the user terminal device 6 are configured, for example, as general-purpose or dedicated computers (see FIG. 7 described below), and are connected to a wired or wireless network 7 so as to be able to mutually transmit and receive various data (in FIG. 1, transmission and reception of some data is indicated by dashed arrows). Note that the numbers of the measuring devices 2, the database device 3, the information processing device 5, and the user terminal devices 6, as well as the connection configuration of the network 7, are not limited to the example shown in FIG. 1 and may be changed as appropriate.

[0012] In this embodiment, the term "foreign matter" refers to a substance or component that should not be present in a sample. It also includes denatured materials that occur when manufacturing conditions are inappropriate or when necessary components are missing. For example, improper molding conditions during the manufacturing process can affect the molecular chain length (molecular weight) and crystallinity, resulting in changes in flexibility and strength, resulting in denatured materials. For example, polyethylene terephthalate (PET) may have the same structural formula, but its crystallinity varies depending on the heating and stretching conditions, resulting in different peak heights and shapes in its IR spectrum. In this case, polyethylene terephthalate with properties different from those intended is considered a foreign matter.

[0013] (2 measuring devices, 3 database devices) An example of the measuring device 2 used in this embodiment measures analysis input data 111a as measurement data such as the spectrum, thermal properties, chromatogram, image, mass, etc. of a sample. The analysis input data 111a of the sample measured by the measuring device 2 is stored in the database device 3, used for search by the information processing device 5, or displayed on the user terminal device 6. The database device 3 The database device 3 stores component information 110 including one or more pieces of component type information indicating the components of the substance, measurement data, and additional information. The user U can store new component information 110 in the database device 3 at any time.

[0014] (Ingredient information) 2 shows an example of a data structure diagram of the component information 110 stored in the database device 3 of this embodiment. The component information 110 of this embodiment includes one or more pieces of component type information indicating the components of a substance, measurement data, and accompanying information.

[0015] In this embodiment, the component type information indicates the names of the basic components that make up a substance. The components are not limited to a single element, and may include pure substances made up of two or more elements. The measurement data indicates the chemical characteristics of the components, and the accompanying information indicates the physical characteristics and management characteristics.

[0016] 3A and 3B show examples of chemical characteristics, physical characteristics, and control characteristics of the characteristic elements of this embodiment. Fig. 3A shows an example of the chemical characteristics of the characteristic elements, Fig. 3B shows an example of the physical characteristics, and Fig. 3C shows an example of the control characteristics.

[0017] In this embodiment, the chemical characteristics may be analysis input data 111a related to the components. The analysis input data 111a may be at least one of a spectrum, thermal properties, a chromatogram, an image, and a mass. The spectrum may be, for example, an infrared absorption spectrum, a near-infrared absorption spectrum, a Raman spectrum, an ultraviolet-visible absorption spectrum, an X-ray spectrum, an atomic absorption spectrum, an ICP emission spectrum, or the like measured by an infrared spectrophotometer or the like. The thermal properties may be thermal property data such as specific heat, glass transition temperature, melting point, freezing point, boiling point, or crystallization temperature. The chromatogram may be, for example, a chromatogram measured by liquid chromatography or gas chromatography. The image may be image data acquired by a scanning electron microscope, or data such as a photograph or video taken by a camera or the like. The mass may be, for example, a mass spectrum measured by a mass spectrometer.

[0018] The physical characteristics in this embodiment may be at least one of color, hardness, brittleness, transparency, viscosity, and state. Color may be a color name or numerical data such as a color code or Munsell notation. Hardness may be expressed as hard / soft, or numerical data such as hardness. Brittleness may be expressed as brittle or hard, or numerical data of brittleness obtained from an impact test or the like. Transparency may be expressed as transparent, translucent, opaque, or numerical data such as transmittance. Viscosity may be the presence or absence of viscosity, or numerical data measured with a viscometer. State may indicate solid, semi-solid, liquid, gas, or the like.

[0019] In this embodiment, the management feature may be any one of a product feature, a facility feature, a process feature, and a reporting feature. The product feature indicates a product that uses a substance or ingredient, the facility feature indicates a facility that uses a substance or ingredient, and the process feature indicates a process that uses a substance or ingredient. The reporting feature indicates past reporting data for at least one of the product, facility, process, substance, and ingredient.

[0020] The product characteristic may be at least one of a product type characteristic indicating the type of product and a material component characteristic indicating the components of the material used in the product. Also, the material component characteristic may be at least one of a material component type characteristic and a material component origin characteristic. The material component type characteristic indicates the type of the component of the material, and the material component origin characteristic indicates the origin of the component of the material.

[0021] The product type feature may be a product name indicating the name of the product, for example, the product name may be a bottle or a cap. The material component type feature may be the name of a material component, for example, the material component name may be an element name or a pure substance name. The material component origin feature may be an existence feature indicating the cause of the component. The presence cause may be at least one of the following: a contamination occurrence location indicating the location where the component was mixed or generated; and a contamination occurrence process indicating the process where the component was mixed or generated. The presence cause may be a leak, splash, human error, heating conditions, etc. The contamination occurrence location may be the line name, etc. The contamination occurrence process may be the process name, etc.

[0022] The facility features may be a company name indicating the name of the company, a factory name indicating the name of the factory, a department name indicating the name of the department, and a facility location indicating the location of the facility. For example, the company name may be XX Co., Ltd., the factory name may be XX Factory, the department name may be XX Department XX Section, and the facility location may be an address or longitude and latitude.

[0023] The process feature indicates the use process using the component, and may be, for example, XX process, etc. The report feature indicates the data of the report created by the user U, and may be the content or keywords of the report, etc.

[0024] (Information processing device 5) 4 is a block diagram showing an example of the information processing device 5 of this embodiment. The information processing device 5 includes a control unit 50, a communication unit 51, and a storage unit 52, and searches for information related to components of a predetermined sample.

[0025] The control unit 50 functions as an input information acquisition unit 501 and a foreign substance information output unit 502 .

[0026] The input information acquisition unit 501 acquires, as input information 111, at least one of the analysis input data 111a measured by the measuring device 2 and the user input information 111b input by the user U to the user terminal device 6. In this embodiment, the input information acquisition unit 501 acquires (receives) the input information 111 from the measuring device 2 and the user terminal device 6 via the network 7 and the communication unit 51. The input information 111 in this embodiment may be one or more elements of the chemical characteristics, physical characteristics, or administrative characteristics shown in FIG. 3 .

[0027] The foreign substance information output unit 502 outputs foreign substance information 112 based on the input information 111 acquired by the input information acquisition unit 501. In this embodiment, the foreign substance information output unit 502 receives the input information 111 acquired by the input information acquisition unit 501, identifies relevant information from the component information 110 stored in the database device 3 and the preliminary component information 110a stored in the storage unit 52, and outputs foreign substance information 112 or "not applicable." In this embodiment, the foreign substance information output unit 502 transmits the foreign substance information 112 or "not applicable" to the user terminal device 6 via the communication unit 51 and the network 7, and the user terminal device 6 outputs a display screen or audio based on the foreign substance information 112 or "not applicable."

[0028] The communication unit 51 is connected to external devices (for example, the database device 3, the machine learning device 4, and the user terminal device 6) via the network 7, and functions as a communication interface for transmitting and receiving various types of data.

[0029] The storage unit 52 stores various types of information such as various programs (such as an operating system and an information processing program) and data (reserve component information 110a) used in the operation of the information processing device 5. The storage unit 52 may be substituted by a storage unit of an external computer (for example, a server-type computer or a cloud-type computer), and in that case, the foreign matter information output unit 502 may access the external computer.

[0030] 5 shows an example of the foreign matter information 112 of this embodiment. The foreign matter information 112 indicates information on one or more components present as foreign matter in a sample. The foreign matter information output unit 502 extracts component type information and component origin information related to the input information 111 from the database device 3 that stores component information 110 including component type information, measurement data, and accompanying information. Furthermore, if there is no foreign matter information 112, the foreign matter information output unit 502 outputs "not applicable." Component Type Information may be a component name stored in the database device 3 as a material component type characteristic. The component name may be an element name or a pure substance name, etc. The component origin information may be the origin of the component of the material stored in the database device 3 as a material component origin characteristic. The component origin information may be at least one of an existence cause indicating the cause of the component's existence, and a contamination occurrence location indicating the location where the component was mixed or occurred.

[0031] (User terminal device 6) 6 is a block diagram showing an example of a user terminal device 6 according to this embodiment. The user terminal device 6 is a device used by a user U when searching for information related to components of a sample. The user terminal device 6 may be a portable device such as a personal computer or a smartphone. The user terminal device 6 includes a control unit 60, a communication unit 61, a storage unit 62, an input unit 63, and an output unit 64.

[0032] The control unit 60 functions as a user input information processing unit 601 and a foreign object information processing unit 602. The user input information processing unit 601 executes processing for transmitting the user input information 111b input from the input unit 63 to the information processing device 5 via the network 7. The foreign object information processing unit 602 executes processing for outputting the foreign object information 112 transmitted from the information processing device 5 via the network 7 to the output unit 64.

[0033] The communication unit 61 is connected to external devices (e.g., the database device 3 and the information processing device 5) via the network 7, and functions as a communication interface for transmitting and receiving various data. The storage unit 62 stores various programs (such as an operating system and a user terminal program) and data used in the operation of the user terminal device 6.

[0034] The input unit 63 accepts various input operations and may be a keyboard, a voice input device, or the like. For example, the input unit 63 of this embodiment may input user input information 111b. The output unit 64 functions as a user interface by outputting various information via a display screen or voice. For example, the output unit 64 of this embodiment may output foreign object information 112.

[0035] (Hardware configuration of each device) 7 is a hardware configuration diagram showing an example of a computer 900 according to this embodiment. The control unit 50 of the information processing device 5, the user terminal device 6, etc. are configured by a general-purpose or dedicated computer 900.

[0036] The computer 900 includes, as its main components, a bus 910, a processor 912, a memory 914, an input device 916, an output device 917, a display device 918, a storage device 920, a communication I / F (interface) unit 922, an external device I / F unit 924, an I / O (input / output) device I / F unit 926, and a media input / output unit 928. Note that the above components may be omitted as appropriate depending on the application for which the computer 900 is used.

[0037] The processor 912 is composed of one or more arithmetic processing devices (such as a CPU (Central Processing Unit), MPU (Micro-Processing Unit), DSP (Digital Signal Processor), GPU (Graphics Processing Unit), or NPU (Neural Processing Unit)), and operates as a control unit that controls the entire computer 900. The memory 914 stores various data and programs 930, and is composed of, for example, a volatile memory (such as a DRAM or SRAM) that functions as a main memory, a non-volatile memory (ROM), a flash memory, etc.

[0038] The input device 916 is composed of, for example, a keyboard, a mouse, a numeric keypad, an electronic pen, etc., and functions as an input unit. The output device 917 is composed of, for example, a sound (audio) output device, a vibration device, etc., and functions as an output unit. The display device 918 is composed of, for example, a liquid crystal display, an organic EL display, electronic paper, a projector, etc., and functions as an output unit. The input device 916 and the display device 918 may be integrated into one device, such as a touch panel display. The storage device 920 is composed of, for example, an HDD, an SSD, etc., and functions as a storage unit. The storage device 920 stores various data necessary for executing the operating system and the program 930.

[0039] The communication I / F unit 922 is connected to a network 940 such as the Internet or an intranet (which may be the same as network 7 in FIG. 1) via a wired or wireless connection and functions as a communication unit that transmits and receives data to and from other computers in accordance with a predetermined communication protocol. The external device I / F unit 924 is connected to an external device 950 such as a camera, printer, scanner, or reader / writer via a wired or wireless connection and functions as a communication unit that transmits and receives data to and from the external device 950 in accordance with a predetermined communication protocol. The I / O device I / F unit 926 is connected to an I / O device 960 such as various sensors and actuators and functions as a communication unit that transmits and receives various signals and data, such as detection signals from sensors and control signals to actuators, to and from the I / O device 960. The media input / output unit 928 is composed of a drive device such as a DVD drive or CD drive, a memory card slot, and a USB connector, and reads and writes data from and to media (non-transitory storage media) 970 such as a DVD, CD, memory card, or USB memory.

[0040] In the computer 900 having the above configuration, the processor 912 loads a program 930 stored in the storage device 920 into the memory 914, executes the program, and controls each unit of the computer 900 via the bus 910. The program 930 may be stored in the memory 914 instead of the storage device 920. The program 930 may be recorded on the medium 970 in an installable file format or an executable file format and provided to the computer 900 via the media input / output unit 928. The program 930 may be provided to the computer 900 by being downloaded via the communication I / F unit 922 over the network 940. Furthermore, the computer 900 may implement various functions realized by the processor 912 executing the program 930 using hardware such as an FPGA (Field-Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit).

[0041] The computer 900 is, for example, a desktop computer or a portable computer, and is an electronic device of any type. The computer 900 may be a client computer, a server computer, a cloud computer, or an embedded computer called, for example, a control panel or a controller (including a microcomputer, a programmable logic controller, or a sequencer). The computer 900 may also be applied to devices other than the control unit 50 of the information processing device 5 and the user terminal device 6.

[0042] (Information processing method) 8 is a flowchart showing an example of an information processing method by the information processing device 5 and the user terminal device 6 of this embodiment. The following shows an example in which a user U operates the user terminal device 6 to send input information 111 to the information processing device 5, and the information processing device 5 outputs foreign substance information 112 from component information 110 stored in the database device 3 to the user terminal device 6.

[0043] First, in step S110, the user operates the input unit 63 of the user terminal device 6 to input information. The input information 111 is transmitted to the information processing device 5. Here, the input information 111 may be at least one of user input information 111b input from the user terminal device 6 and analysis input data 111a input from the measuring device 2 by operating the user terminal device 6.

[0044] 9 shows an example of the input screen of the user terminal device 6 of this embodiment. The input screen of the user terminal device 6 of this embodiment is configured to allow selection of an item to be used as input information 111. The input information 111 may be one or more elements of the chemical characteristics, physical characteristics, or administrative characteristics shown in FIG. 3. When an item to be used as input information 111 is selected, the user can move from that item to a screen for further selecting input information 111 or entering a keyword, or the like.

[0045] For example, if a spectrum of chemical input information is selected, one or more spectral data measured by the measuring instrument 2 are displayed on the input screen, and the user can select the spectral data to search from among them. Also, if a color of physical input information is selected, an input screen for selecting the color name or inputting the color numerically is displayed, and the user U can select the color name or input the color numerically. Note that one or more pieces of input information 111 can be input during a search.

[0046] Next, in step S120, the input information acquisition unit 501 of the information processing device 5 receives the input information 111 transmitted in step S110.

[0047] Next, in step S130, the foreign substance information output unit 502 outputs foreign substance information 112 or no match from the component information 110 stored in the database device 3 based on the input information 111 acquired in step S120.

[0048] Next, in step S140, the database device 3 or the storage unit 52 stores the foreign substance information 112. By storing the foreign substance information 112, the search results can be kept as a record.

[0049] Next, in step S150, the foreign substance information output unit 502 transmits the foreign substance information 112 output in step S130 or "no match" to the user terminal device 6.

[0050] Next, in step S160, the foreign object information processing unit 602 of the user terminal device 6 receives the foreign object information 112 transmitted in step S150, and notifies the user U from the output unit 64 via voice or a display screen.

[0051] Fig. 10 shows an example of an output screen of the user terminal device 6 of this embodiment. The output screen of the user terminal device 6 of this embodiment displays the component name, cause of existence, and location of contamination or occurrence as foreign matter information 112. In the example shown in Fig. 10, spectra and incidental information similar to the searched spectrum are output as candidates with a high probability of being foreign matter.

[0052] The system also outputs the cause of the presence of components with a high probability of being contaminants, as well as the location of contamination or occurrence. In the example shown in Figure 10, for example, similar spectrum (1) is the spectrum of a line component. Even if the component name information is not registered in the database, it is displayed as a candidate based on spectral similarity, and information is output indicating that it is used in the XX line or XX process. Similarly, similar spectrum (2) is the spectrum of a lubricant used in the line. Based on the database information, the process of use, the purpose (lubricant) as the cause of the presence, and component information are output. Furthermore, similar spectrum (3) is resin B, whose flexibility and strength have changed due to inappropriate heating conditions in the past, which affected the molecular chain length or crystallinity, and the process in which it occurred, the heating conditions as the cause of the presence, and component information are output. The output screen is not limited to the diagram shown in Figure 10; any screen that allows the relationship to be understood is sufficient.

[0053] In this way, the information processing device 5 of this embodiment can appropriately search for information based on the presence or occurrence of foreign matter.

[0054] 11 is a diagram illustrating an overall configuration of an example of an information processing system 1 according to the second embodiment. The information processing system 1 according to the second embodiment includes a machine learning device 4. The other configurations are the same as those of the first embodiment, and therefore will not be described again.

[0055] The machine learning device 4 is a device that operates as a main player in the learning phase of machine learning. The machine learning device 4 generates a learning model 10 to be used in the information processing device 5 by machine learning, for example, based on a plurality of pieces of learning data 11. The trained learning model 10 is provided to the information processing device 5 via the network 7, a recording medium, or the like.

[0056] The information processing device 5 receives input information 111 from a user terminal device 6 operated by a user U at any time, and inputs the input information 111 into a learning model 10 provided by the machine learning device 4 to generate foreign object information 112, which is then transmitted to the user terminal device 6, etc. at any time.

[0057] (Machine Learning Device 4) 12 is a block diagram showing an example of the machine learning device 4. The machine learning device 4 includes a control unit 40, a communication unit 41, a learning data storage unit 42, a trained model storage unit 43, an input unit 44, and an output unit 45.

[0058] The control unit 40 functions as a learning data acquisition unit 400 and a machine learning unit 401. The communication unit 41 is connected to external devices (e.g., the database device 3, the information processing device 5, the user terminal device 6, etc.) via the network 7 and functions as a communication interface for transmitting and receiving various types of data. The input unit 44 accepts various input operations, and the output unit 45 functions as a user interface by outputting various types of information via a display screen or voice.

[0059] The learning data acquisition unit 400 acquires learning data 11 consisting of input information 111 as input data and foreign substance information 112 as output data. The learning data acquisition unit 400 may acquire the learning data 11, for example, in cooperation with an external device connected via the communication unit 41 and the network 7, or may acquire the learning data 11 by accepting an input operation via the input unit 44 and the output unit 45. The learning data 11 is data used as teacher data (training data), verification data, and test data in supervised learning. The foreign substance information 112 is data used as a correct answer label in supervised learning.

[0060] The learning data storage unit 42 is a database that stores a plurality of sets of learning data 11 acquired by the learning data acquisition unit 400. The specific configuration of the database that constitutes the learning data storage unit 42 may be designed as appropriate.

[0061] The machine learning unit 401 performs machine learning using multiple sets of learning data 11 stored in the learning data storage unit 42. That is, the machine learning unit 401 inputs multiple sets of learning data 11 to the learning model 10 and causes the learning model 10 to learn the correlation between the input information 111 and the foreign substance information 112 contained in the learning data 11, thereby generating a trained learning model 10.

[0062] The trained model storage unit 43 is a database that stores the trained learning model 10 (specifically, a set of adjusted weight parameters) generated by the machine learning unit 401. The trained learning model 10 stored in the trained model storage unit 43 is provided to a real system (for example, an information processing device 5) via a network 7, a recording medium, etc. Although the training data storage unit 42 and the trained model storage unit 43 are shown as separate storage units in FIG. 12, they may be configured as a single storage unit.

[0063] 13 is a diagram showing an example of the learning model 10 and the learning data 11. The learning data 11 used for machine learning of the learning model 10 is composed of input information 111 and foreign substance information 112.

[0064] The input information 111 constituting the training data 11 may be at least one of analysis input data 111a measured by the measuring device 2 and user input information 111b input by the user U to the user terminal device 6. In this embodiment, the training data acquisition unit 400 experimentally acquires (receives) the input information 111 from the measuring device 2 and the user terminal device 6 via the network 7 and the communication unit 41. The input information 111 in this embodiment may be one or more elements of the chemical characteristics, physical characteristics, or management characteristics shown in FIG. 3.

[0065] For example, if the circumstances under which a foreign object was discovered in the past are recorded, the learning data acquisition unit 400 acquires the learning data 11 by inputting the record as input information 111 and foreign object information 112. The foreign object information 112 may be input by the tester via the user terminal device 6, or may be input via the input unit 44 and the output unit 45.

[0066] The learning model 10 employs, for example, a neural network structure and includes an input layer 101, an intermediate layer 102, and an output layer 103. Synapses (not shown) that connect each neuron are laid between each layer, and each synapse is associated with a weight. A group of weight parameters consisting of the weights of each synapse is adjusted by machine learning.

[0067] The input layer 101 has neurons whose number corresponds to input information 111 as input data, and the input information 111 is input to each neuron. The output layer 103 has neurons whose number corresponds to foreign object information 112 as output data, and the prediction result (inference result) of the foreign object information 112 for the input information 111 is output as output data.

[0068] The number of learning models 10 stored in the trained model storage unit 43 is not limited to one, and multiple learning models 10 with different conditions, such as machine learning techniques, types of input information 111, and types of foreign object information 112, may be stored. In this case, the training data storage unit 42 may store multiple types of training data 11 having data structures corresponding to the multiple training models 10 with different conditions.

[0069] (machine learning methods) FIG. 14 is a flowchart showing an example of a machine learning method performed by the machine learning device 4.

[0070] First, in step S210, the learning data acquisition unit 400 acquires a desired number of pieces of learning data 11 as a preliminary preparation for starting machine learning, and stores the acquired learning data 11 in the learning data storage unit 42. The number of pieces of learning data 11 to be prepared here may be set in consideration of the inference accuracy required for the learning model 10 to be finally obtained.

[0071] Next, in step S220, in order to start machine learning, the machine learning unit 401 prepares a pre-learning learning model 10. The pre-learning learning model 10 prepared here is configured as a neural network model, and the weight of each synapse is set to an initial value.

[0072] Next, in step S230, the machine learning unit 401 acquires, for example, one set of training data 11 at random from the multiple sets of training data 11 stored in the training data storage unit .

[0073] Next, in step S240, the machine learning unit 401 inputs input data (input information 111) included in one set of learning data 11 to the input layer 101 of the prepared learning model 10 before learning (or during learning). As a result, output data (foreign substance information 112) is output as an inference result from the output layer 103 of the learning model 10, and this output data has been generated by the learning model 10 before learning (or during learning). Therefore, in the state before learning (or during learning), the output data output as an inference result indicates information different from the correct label (foreign substance information 112) included in the learning data 11.

[0074] Next, in step S250, the machine learning unit 401 performs machine learning by comparing the correct label included in the set of learning data 11 acquired in step S230 with the output data output as an inference result from the output layer 103 in step S240 and performing a process of adjusting the weight of each synapse (backpropagation).In this way, the machine learning unit 401 causes the learning model 10 to learn the correlation between the input data and the output data.

[0075] Next, in step S260, the machine learning unit 401 determines whether a predetermined learning termination condition has been met, for example, based on the evaluation value of an error function based on the correct label included in the learning data 11 and the output data output as the inference result, or the remaining number of unlearned learning data 11 stored in the learning data storage unit 42.

[0076] In step S260, if the machine learning unit 401 determines that the learning termination condition is not satisfied and that machine learning should continue (No in step S260), the process returns to step S230, and performs steps S230 to S250 multiple times on the learning model 10 under training using unlearned training data 11. On the other hand, in step S260, if the machine learning unit 401 determines that the learning termination condition is satisfied and that machine learning should end (Yes in step S260), the process proceeds to step S270.

[0077] Then, in step S270, the machine learning unit 401 stores the trained learning model 10 (adjusted weight parameter group) generated by adjusting the weights associated with each synapse in the trained model storage unit 43, and ends the series of machine learning methods shown in Fig. 14. In the machine learning method, step S210 corresponds to a learning data storage step, steps S220 to S260 correspond to a machine learning step, and step S270 corresponds to a trained model storage step.

[0078] As described above, the machine learning device 4 and machine learning method according to this embodiment can provide a learning model 10 that can predict (infer) foreign object information 112 from input information 111 entered by the user U when the user U operates the user terminal device 6.

[0079] (Information processing device 5) Fig. 15 is a block diagram showing an example of an information processing device 5 according to the second embodiment. Fig. 16 is a functional explanatory diagram showing an example of the information processing device 5 according to the second embodiment. The information processing device 5 includes a control unit 50, a communication unit 51, and a storage unit 52, and searches for information related to components of a predetermined sample.

[0080] The control unit 50 functions as an input information acquisition unit 501 and a foreign substance information output unit 502 .

[0081] The input information acquisition unit 501 acquires, as input information 111, at least one of the analysis input data 111a measured by the measuring device 2 and the user input information 111b input by the user U to the user terminal device 6. In this embodiment, the input information acquisition unit 501 acquires (receives) the input information 111 from the measuring device 2 and the user terminal device 6 via the network 7 and the communication unit 51. The input information 111 in this embodiment may be one or more elements of the chemical characteristics, physical characteristics, or administrative characteristics shown in FIG. 3 .

[0082] The foreign object information output unit 502 outputs foreign object information 112 based on the input information 111 acquired by the input information acquisition unit 501. In this embodiment, the foreign object information output unit 502 inputs the input information 111 acquired by the input information acquisition unit 501 into the learning model 10, which has performed machine learning to determine the correlation between the input information 111 and the foreign object information 112, and outputs foreign object information 112 or no match for the input information 111. The foreign object information output unit 502 transmits the foreign object information 112 or no match to the user terminal device 6 via the communication unit 51 and the network 7, and the user terminal device 6 outputs a display screen or audio based on the foreign object information 112 or no match.

[0083] The communication unit 51 is connected to external devices (for example, the database device 3, the machine learning device 4, and the user terminal device 6) via the network 7, and functions as a communication interface for transmitting and receiving various types of data.

[0084] The storage unit 52 stores various programs (such as an operating system or an information processing program) used in the operation of the information processing device 5, and a trained learning model 10 used by the foreign object information output unit 502. The number of learning models 10 stored in the storage unit 52 is not limited to one, and multiple trained models with different conditions, such as machine learning techniques, types of input information 111, and types of foreign object information 112, may be stored and used selectively or in parallel. The storage unit 52 may be substituted by a storage unit of an external computer (such as a server-type computer or a cloud-type computer), in which case the foreign object information output unit 502 may access the external computer.

[0085] (User terminal device 6) 17 is a block diagram showing an example of a user terminal device 6. The user terminal device 6 is a device used by a user U when searching for information related to the components of a sample. The user terminal device 6 may be a portable device such as a personal computer or a smartphone. The user terminal device 6 includes a control unit 60, a communication unit 61, a storage unit 62, an input unit 63, and an output unit 64.

[0086] The control unit 60 functions as a user input information processing unit 601 and a foreign object information processing unit 602. The user input information processing unit 601 executes processing for transmitting the user input information 111b input from the input unit 63 to the information processing device 5 via the network 7. The foreign object information processing unit 602 executes processing for outputting the foreign object information 112 transmitted from the information processing device 5 via the network 7 to the output unit 64.

[0087] The communication unit 61 is connected to external devices (e.g., the database device 3, the machine learning device 4, and the information processing device 5) via the network 7, and functions as a communication interface for transmitting and receiving various types of data. The storage unit 62 stores various programs (such as an operating system and a user terminal program) and data used in the operation of the user terminal device 6.

[0088] The input unit 63 receives various input operations and may be a keyboard, a voice input device, etc. For example, the input unit 63 of this embodiment receives the user input information 111b. The output unit 64 functions as a user interface by outputting various information via a display screen or audio. For example, the output unit 64 of this embodiment may output foreign substance information 112.

[0089] (Information processing method) 18 is a flowchart showing an example of an information processing method by the information processing system 1. The following shows an example in which a user U operates the user terminal device 6 to send input information 111 to the information processing device 5, and the information processing device 5 outputs foreign object information 112 from the learning model 10 to the user terminal device 6.

[0090] First, in step S310, as in the first embodiment, for example, input information 111 is sent to the information processing device 5 by operating the input screen shown in FIG. 9 as an example of the input unit 63 of the user terminal device 6. Here, the input information 111 may be at least one of user input information 111b input from the user terminal device 6 and analysis input data 111a input from the measuring instrument 2 by operating the user terminal device 6.

[0091] Next, in step S320, the input information acquisition unit 501 of the information processing device 5 receives the input information 111 transmitted in step S310.

[0092] Next, in step S330, the foreign substance information output unit 502 inputs the input information 111 acquired in step S320 to the learning model 10, and outputs the foreign substance information 112 or no match.

[0093] Next, in step S340, the database device 3 or the storage unit 52 stores the foreign substance information 112. By storing the foreign substance information 112, the search results can be kept as a record.

[0094] Next, in step S350, the foreign substance information output unit 502 transmits the foreign substance information 112 output in step S330 or "no match" to the user terminal device 6.

[0095] Next, in step S360, the foreign object information processing unit 602 of the user terminal device 6 receives the foreign object information 112 transmitted in step S350, and notifies the user U from the output unit 64 of the user terminal device 6 via voice or an example of an output screen shown in FIG. 10.

[0096] In this way, the information processing device 5 of this embodiment can appropriately search for information based on the presence or occurrence of foreign matter.

[0097] (Other embodiments) The present invention is not limited to the above-described embodiment, and various modifications can be made without departing from the spirit and scope of the present invention, all of which are included in the technical concept of the present invention.

[0098] In the above embodiment, the database device 3, the machine learning device 4, the information processing device 5, and the user terminal device 6 are described as being configured as separate devices, but these four devices may be configured as a single device, or any two or three of these four devices may be configured as a single device. Furthermore, at least one of the machine learning device 4 and the information processing device 5 may be incorporated into the user terminal device 6. For example, the learning model 10 may be stored in the storage unit 62 of the user terminal device 6, and the control unit 60 of the user terminal device 6 may function as the input information acquisition unit 501 and the foreign substance information output unit 502. Furthermore, the component information, etc. may be stored in the storage unit 52 of the database device 3, the storage unit 52 of the information processing device 5, and the storage unit 502 of the user terminal device 6. It is sufficient that the information is stored in at least one of the memory areas 62, 63, etc.

[0099] In the above embodiment, a case has been described in which a neural network is used as the learning model 10 for realizing machine learning by the machine learning unit 401, but other machine learning models may also be used. Examples of other machine learning models include tree types such as decision trees and regression trees, ensemble learning such as bagging and boosting, and neural network types (deep learning) such as recurrent neural networks, convolutional neural networks, and LSTM. hierarchical clustering, non-hierarchical clustering, k-nearest neighbors, k-means, etc. Examples include rastering type, principal component analysis, factor analysis, multivariate analysis such as logistic regression, and support vector machines.

[0100] (Machine learning programs and information processing programs) The present invention can also be provided in the form of a program (machine learning program) that causes the computer 900 to function as each unit included in the machine learning device 4, or a program (machine learning program) that causes the computer 900 to execute each step included in the machine learning method. The present invention can also be provided in the form of a program (information processing program) that causes the computer 900 to function as each unit included in the information processing device 5 or the user terminal device 6, or a program (information processing program) that causes the computer 900 to execute each step included in the information processing method according to the above embodiment.

[0101] (Inference device, inference method and inference program) The present invention can be provided not only in the form of the information processing device 5 (information processing method or information processing program) according to the above embodiment, but also in the form of an inference device (inference method or inference program) used to infer information processing. In this case, the inference device (inference method or inference program) includes a memory and a processor, and the processor executes a series of processes. The series of processes includes an input process (input information acquisition step) for acquiring input information 111, and an inference process (inference step) for inferring foreign object information 112 or no match based on the input information 111 once the input information 111 has been acquired in the input information acquisition process.

[0102] By providing it in the form of an inference device (inference method or inference program), it can be more easily applied to various devices than when it is implemented in the information processing device 5. It will be obvious to those skilled in the art that when the inference device (inference method or inference program) infers the foreign substance information 112 or no match, it may apply the inference method implemented by the foreign substance information output unit 502 using the machine learning device 4 and trained learning model 10 generated by the machine learning method according to the above embodiment.

[0103] Various aspects of this embodiment will be described below as supplementary notes.

[0104] (Appendix 1) An information processing device for performing material analysis of a sample, an input information acquisition unit that acquires input information including measurement data of the sample and additional information associated with the sample; a foreign matter information output unit that outputs foreign matter information indicating information on one or more components present as foreign matters in the sample based on the input information, or outputs "none" if there is no foreign matter information; Equipped with Information processing device. (Appendix 2) The measurement data is chemical analysis input data. 10. The information processing device according to claim 1. (Appendix 3) The analysis input data is Spectrum, Thermal properties, chromatogram, image, and, mass, At least one of 3. The information processing device according to claim 2. (Appendix 4) The additional information is physical input information of the sample; and, administrative input information for said sample; At least one of 4. An information processing device according to any one of claims 1 to 3. (Appendix 5) The physical input information is color, Hardness, fragility, transparency, viscosity, and, situation At least one of 5. The information processing device according to claim 4. (Appendix 6) The administrative input information is product input information indicating a product in which the sample is used; Facility input information indicating the facility where the sample was collected; process input information indicating the process at which the sample was taken; and, reporting input information indicating past reporting data for at least one of the product, the facility, the process, and the sample; At least one of 5. The information processing device according to claim 4. (Appendix 7) The product input information is Product type input information indicating the type of the product; and, Material composition input information indicating the composition of materials used in said product; At least one of 7. The information processing device according to claim 6. (Appendix 8) The product type input information is the name of the product. 8. The information processing device according to claim 7. (Appendix 9) The material component input information is the name of the component of the material. 9. The information processing device according to claim 7 or 8. (Appendix 10) The facility input information is the name of the company that owns said facility; the factory name of said facility; The department name of the facility; and, the location of said facility; At least one of 10. An information processing device according to any one of Supplementary Note 6 to Supplementary Note 9. (Appendix 11) The process input information is a process in which the sample is used. 11. An information processing device according to any one of Supplementary Note 6 to Supplementary Note 10. (Appendix 12) The foreign matter information is component type information indicating the type of the component; and, ingredient origin information indicating the origin of the ingredient; At least one of 12. An information processing device according to any one of claims 1 to 11. (Appendix 13) The component type information is the name of the component. 13. The information processing device according to claim 12. (Appendix 14) The ingredient origin information is the reason for the presence of said component; and, The location where the component was mixed or generated, At least one of 14. The information processing device according to claim 12 or 13. (Appendix 15) The foreign substance information output unit outputs the foreign substance information by inputting the input information into a learning model that has learned a correlation between the input information and the foreign substance information through machine learning. 15. An information processing device according to any one of claims 1 to 14. (Appendix 16) a learning data storage unit that stores multiple sets of learning data, each set consisting of sample input information and foreign substance information that indicates information on one or more components present as foreign substances in the sample; a machine learning unit that inputs the multiple sets of learning data into a learning model, thereby causing the learning model to learn a correlation between the input information and the foreign substance information; and a trained model storage unit that stores the learning model that has learned the correlation by the machine learning unit; an information processing device including a foreign substance information output unit that inputs the input information to the learning model and outputs the foreign substance information for the input information; Equipped with Information processing system. (Appendix 17) An inference device comprising a memory and a processor, The processor: an input information acquisition unit that acquires input information including measurement data of a sample and additional information associated with the sample; an inference process for inferring, upon receiving the input information, foreign matter information indicating information on one or more components present as foreign matters in the sample; To execute Reasoning device. (Appendix 18) a learning data storage unit that stores a plurality of sets of learning data, each set comprising input information including measurement data of a sample and additional information attached to the sample, and foreign matter information indicating information on one or more components present as foreign matter in the sample; a machine learning unit that inputs a plurality of sets of the learning data into a learning model, thereby causing the learning model to learn a correlation between the input information and the foreign substance information; a learned model storage unit that stores the learned model in which the correlation is learned by the machine learning unit; Equipped with Machine learning device. (Appendix 19) An information processing method for performing material analysis of a sample, comprising: an input information step of acquiring input information including measurement data of the sample and additional information associated with the sample; a foreign matter information output step of outputting foreign matter information indicating information on one or more components present as foreign matters in the sample based on the input information; Equipped with Information processing methods. (Appendix 20) An inference method executed by an inference device having a memory and a processor, The processor: an input information step of acquiring input information including measurement data of a sample and additional information associated with the sample; an inference step of inferring, upon receiving the input information, foreign substance information indicating information on one or more components present as foreign substances in the sample; To execute Reasoning method. (Appendix 21) a learning data storage step of storing, in a learning data storage unit, a plurality of sets of learning data each of which is composed of input information including measurement data of a sample and additional information attached to the sample, and foreign matter information indicating information on one or more components present as foreign matters in the sample; a machine learning process of inputting a plurality of sets of the learning data into a learning model, thereby causing the learning model to learn a correlation between the input information and the foreign substance information; and a learned model storage step of storing the learned model, which has learned the correlation through the machine learning step, in a learned model storage unit. Machine learning methods. [Explanation of symbols]

[0105] 1 Information processing system, 2 Measuring instrument, 3 Database device, 4 machine learning device, 5 information processing device, 6 user terminal device, 7 Network, 10 Learning model, 11 Training data, 40 control unit, 41 communication unit, 42 learning data storage unit, 43 trained model memory unit, 44 input unit, 45 output unit, 50 control unit, 51 communication unit, 52 storage unit, 60 control unit, 61 communication unit, 62 memory unit, 64 input unit, 65 output unit, 110 component information, 111 input information, 112 foreign matter information, 501 input information acquisition unit, 502 foreign substance information output unit, 601 user input information processing unit, 602 foreign object information processing unit, 900 Computer, U User

Claims

1. An information processing device for performing material analysis of a sample, an input information acquisition unit that acquires input information including measurement data of the sample and additional information associated with the sample; a foreign matter information output unit that outputs foreign matter information indicating information on one or more components present as foreign matters in the sample based on the input information, or outputs "none" if there is no foreign matter information; Equipped with Information processing device.

2. The measurement data is chemical analysis input data. The information processing device according to claim 1 .

3. The analysis input data is Spectrum, Thermal properties, chromatogram, image, and, mass, At least one of The information processing device according to claim 2 .

4. The additional information is physical input information of the sample; and, administrative input information for said sample; At least one of The information processing device according to claim 1 .

5. The physical input information is color, Hardness, fragility, transparency, viscosity, and, situation At least one of The information processing device according to claim 4 .

6. The administrative input information is product input information indicating a product in which the sample is used; Facility input information indicating the facility where the sample was collected; process input information indicating the process at which the sample was taken; and, reporting input information indicating past reporting data for at least one of the product, the facility, the process, and the sample; At least one of The information processing device according to claim 4 .

7. The product input information is Product type input information indicating the type of the product; and, Material composition input information indicating the composition of materials used in said product; At least one of The information processing device according to claim 6 .

8. The product type input information is the name of the product. The information processing device according to claim 7 .

9. The material component input information is the name of the component of the material. The information processing device according to claim 7 .

10. The facility input information is the name of the company that owns said facility; the factory name of said facility; The department name of the facility; and, the location of said facility; At least one of The information processing device according to claim 6 .

11. The process input information is a process in which the sample is used. The information processing device according to claim 6 .

12. The foreign matter information is component type information indicating the type of the component; and, ingredient origin information indicating the origin of the ingredient; At least one of The information processing device according to claim 1 .

13. The component type information is the name of the component. The information processing device according to claim 12.

14. The ingredient origin information is the reason for the presence of said component; and, The location where the component was mixed or generated, At least one of The information processing device according to claim 12.

15. The foreign substance information output unit outputs the foreign substance information by inputting the input information into a learning model that has learned a correlation between the input information and the foreign substance information through machine learning. The information processing device according to claim 1 .

16. a learning data storage unit for storing a plurality of sets of learning data each of which is composed of input information about a sample and foreign substance information indicating information about one or more components present as foreign substances in the sample; a machine learning device including: a machine learning unit that inputs training data into a learning model, thereby causing the learning model to learn a correlation between the input information and the foreign substance information; and a trained model storage unit that stores the learning model that has learned the correlation by the machine learning unit; an information processing device including a foreign substance information output unit that inputs the input information to the learning model and outputs the foreign substance information for the input information; Equipped with Information processing system.

17. An inference device comprising a memory and a processor, The processor: an input information acquisition unit that acquires input information including measurement data of a sample and additional information associated with the sample; an inference process for inferring, upon receiving the input information, foreign substance information indicating information on one or more components present as foreign substances in the sample; To execute Reasoning device.

18. a learning data storage unit that stores a plurality of sets of learning data, each set comprising input information including measurement data of a sample and additional information attached to the sample, and foreign matter information indicating information on one or more components present as foreign matter in the sample; a machine learning unit that inputs a plurality of sets of the learning data into a learning model, thereby causing the learning model to learn a correlation between the input information and the foreign substance information; a learned model storage unit that stores the learned model in which the correlation is learned by the machine learning unit; Equipped with Machine learning device.

19. An information processing method for performing material analysis of a sample, comprising: an input information step of acquiring input information including measurement data of the sample and additional information associated with the sample; a foreign matter information output step of outputting foreign matter information indicating information on one or more components present as foreign matters in the sample based on the input information; Equipped with Information processing methods.

20. An inference method executed by an inference device having a memory and a processor, The processor: an input information step of acquiring input information including measurement data of a sample and additional information associated with the sample; an inference step of inferring, upon receiving the input information, foreign substance information indicating information on one or more components present as foreign substances in the sample; To execute Reasoning method.

21. a learning data storage step of storing, in a learning data storage unit, a plurality of sets of learning data each of which is composed of input information including measurement data of a sample and additional information attached to the sample, and foreign matter information indicating information on one or more components present as foreign matter in the sample; a machine learning process of inputting a plurality of sets of the learning data into a learning model, thereby causing the learning model to learn a correlation between the input information and the foreign substance information; The learning model that has learned the correlation through the machine learning process is stored as a learned model. and a learned model storage step of storing the learned model in a memory unit. Machine learning methods.

Images