Abstract: In order to provide a case search system in which a search case corresponding to the notation fluctuation of a word within a sentence is a learning object, a sentence constituting a search target case is divided into a plurality of words by a morphological analysis, and a synonym integration unit 20 converts a predetermined word group within the sentence based on the relationship between the plurality of words into a single word consisting of another language in a synonym relationship with the word group. Further, the predetermined word group within the sentence is converted to a sentence with words stored in the corpus and the sentence is integrated, and the search target case composed of the integrated sentence is vectorized by leaning.

Abstract: Degradation in performance of document search is automatically detected. When document data is added to a database, a learning unit updates a language model by machine learning. A performance evaluation unit respectively calculates a first statistical value and a second statistical value related to ranking of each of a plurality of specific document data from a result of the document search using each of a plurality of first labels and second labels attached to a plurality of specific document data as a search query. The performance evaluation unit detects the degradation in performance of the document search when a variation value of the first statistical value due to update of a language model accompanying addition of at least one piece of document data is larger than a first threshold, and when a variation value of the second statistical value due to update is larger than a second threshold.

Abstract: An appropriate answer to a question about an analysis device is automatically provided. A system generates an answer to a question about an analysis device. The system includes: a terminal device; and a server device. The terminal device receives an input of the question. The server device receives the question from the terminal device and transmits the answer to the terminal device. The server device includes an inference unit. The inference unit infers the answer from the question by using a trained answer inferring model that can generate a distributed representation of a specific natural language corresponding to manual data including a procedure about the analysis device. The trained answer inferring model is generated by machine learning that uses the manual data and question-answer data, the question-answer data being a combination of questions and answers about the analysis device.

Abstract: Degradation in performance of document search is automatically detected. When document data is added to a database, a learning unit updates a language model-by machine learning. A performance evaluation unit respectively calculates a first statistical value and a second statistical value related to ranking of each of a plurality of specific document data from a result of the document search using each of a plurality of first labels and second labels attached to a plurality of specific document data as a search query. The performance evaluation unit-detects the degradation in performance of the document search when a variation value of the first statistical value due to update of a language model accompanying addition of at least one piece of document data is larger than a first threshold, and when a variation value of the second statistical value due to update is larger than a second threshold.

Abstract: Provided are a document search method and a document search system for retrieving a search target semantically relevant to a search keyword. A search processing unit 20 interprets the semantic content of document data relevant to a search query and identifies, based on the interpretation result, a location in the retrieved document data highly semantically relevant to the search query. Then, the document name and the specified location of the retrieved document data are displayed.

Abstract: In order to provide a case search method and a case search system for providing a case of an analysis device, preprocessing, etc., associated with a sample that a user, etc., wishes to analyze, with respect to an analysis case for a presented case, a search unit 29 interprets the semantic content contained in a search string input by a user, and retrieves, based on the interpretation result, an analysis case relating to a sample which coincides with or is similar to the presented sample, out of analysis cases stored in advance in databases A, B, and outputs the retrieved case.

Abstract: In order to provide a case search system in which a search case corresponding to the notation fluctuation of a word within a sentence is a learning object, a sentence constituting a search target case is divided into a plurality of words by a morphological analysis, and a synonym integration unit 20 converts a predetermined word group within the sentence based on the relationship between the plurality of words into a single word consisting of another language in a synonym relationship with the word group. Further, the predetermined word group within the sentence is converted to a sentence with words stored in the corpus and the sentence is integrated, and the search target case composed of the integrated sentence is vectorized by leaning.

Abstract: Provided are a document search method and a document search system for retrieving a search target semantically relevant to a search keyword. A search processing unit 20 interprets the semantic content of document data relevant to a search query and identifies, based on the interpretation result, a location in the retrieved document data highly semantically relevant to the search query. Then, the document name and the specified location of the retrieved document data are displayed.

Abstract: A diagnosis assistance system (100) includes a determiner (21) configured to receive trained model information (M) generated by a trained model generator (11) via an external network (30), the determiner (21) being configured to determine, based on the received trained model information (M), a presence or absence of a disease in a patient (P2) who is not included in a patient group (PF).

Abstract: Based on the m/z of a precursor ion used in an MS2 analysis of a test sugar chain, a plurality of sugar-chain structure candidates are extracted from a sugar-chain database in which various sugar-chain structures are related to m/z (S2). Product ions that can be generated by cutting one sugar-chain bond are calculated for each sugar-chain structure candidate (S3). For each combination of two sugar-chain structure candidates, the product ions of one candidate are compared with those of the other to extract characteristic product ions for each sugar-chain structure candidate, and their m/z values are calculated (S4). Whether or not an MS2 spectrum of the test sugar chain has a peak located at m/z of any of the characteristic product ions is determined, and based on the determination result, the sugar-chain structure candidates are narrowed down (S5) and the obtained result is shown on a display unit (S6).

Abstract: Provided is a technique for accurately identifying a peptide even if the peptide cannot be identified by MS/MS ion search or de novo sequencing. The technique uses an MSn spectrum for a low m/z precursor ion. Such a spectrum contains a rather small amount of information, but this information is highly reliable when used for deducing an amino acid sequence by de novo sequencing. Accordingly, an MSn spectrum for a precursor ion having an m/z value of 500 or less is intentionally obtained, and de novo sequencing is performed on this spectrum to deduce the amino acid sequence covering the range from the m/z of the precursor ion and m/z=0. A highly reliable sequence tag can be generated from the deduced amino acid sequence, the m/z of the precursor ion of the MSn analysis, and the m/z of the precursor ion of the MS2 analysis.

Abstract: There are provided a mass spectrometer and a mass spectrometry method which can realize shortening of the measurement time and reduction of the consumption of a sample. Ions, in which the intensity distribution forms a peak waveform at both of each retention time and each mass-to-charge ratio (peaks P11, P21, P22 and P32) are detected as MS/MS precursor ions based on three-dimensional information of a retention time, a mass-to-charge ratio and an intensity. Whether or not MS3 analysis is performed for each ion is determined beforehand based on whether or not the isotopic distributions of a plurality of ions are superimposed at each retention time rt1 to rt3. Ions (peaks P21 and P22) for which MS3 analysis is performed and ions (peaks P11 and P32) for which MS3 analysis is not performed can be hereby determined at the time the MS spectrum is measured to detect MS/MS precursor ions.

Abstract: There are provided a mass spectrometer and a mass spectrometry method which can realize shortening of the measurement time and reduction of the consumption of a sample. Ions, in which the intensity distribution forms a peak waveform at both of each retention time and each mass-to-charge ratio (peaks P11, P21, P22 and P32) are detected as MS/MS precursor ions based on three-dimensional information of a retention time, a mass-to-charge ratio and an intensity. Whether or not MS3 analysis is performed for each ion is determined beforehand based on whether or not the isotopic distributions of a plurality of ions are superimposed at each retention time rt1 to rt3. Ions (peaks P21 and P22) for which MS3 analysis is performed and ions (peaks P11 and P32) for which MS3 analysis is not performed can be hereby determined at the time the MS spectrum is measured to detect MS/MS precursor ions.

Abstract: A mass spectrometry using helium as cooling gas is performed to obtain a first mass spectrum (S1), and another mass spectrometry using argon, which is heavier than helium, as cooling gas is performed to obtain a second mass spectrum for the same sample (S2). Due to the difference between the two gases in terms of the effect of promoting dissociation of modifications, an ion peak originating from a target compound from which all the modifications have been dissociated will appear with a higher intensity on the second mass spectrum. The peak patterns of the two mass spectra are compared to locate the all-dissociated ion peak while excluding unnecessary peaks (S3). Based on that peak, the assignment of each peak is determined (S4).

Abstract: Based on the m/z of a precursor ion used in an MS2 analysis of a test sugar chain, a plurality of sugar-chain structure candidates are extracted from a sugar-chain database in which various sugar-chain structures are related to m/z (S2). Product ions that can be generated by cutting one sugar-chain bond are calculated for each sugar-chain structure candidate (S3). For each combination of two sugar-chain structure candidates, the product ions of one candidate are compared with those of the other to extract characteristic product ions for each sugar-chain structure candidate, and their m/z values are calculated (S4). Whether or not an MS2 spectrum of the test sugar chain has a peak located at m/z of any of the characteristic product ions is determined, and based on the determination result, the sugar-chain structure candidates are narrowed down (S5) and the obtained result is shown on a display unit (S6).

Abstract: A mass spectrometry using helium as cooling gas is performed to obtain a first mass spectrum (S1), and another mass spectrometry using argon, which is heavier than helium, as cooling gas is performed to obtain a second mass spectrum for the same sample (S2). Due to the difference between the two gases in terms of the effect of promoting dissociation of modifications, an ion peak originating from a target compound from which all the modifications have been dissociated will appear with a higher intensity on the second mass spectrum. The peak patterns of the two mass spectra are compared to locate the all-dissociated ion peak while excluding unnecessary peaks (S3). Based on that peak, the assignment of each peak is determined (S4).