Information providing system

Abstract

An information providing system is provided. Provided is an information provision system that selects reference information suitable for a user performing a job related to a medical device to perform the job, the information provision system including a first database constructed by machine learning using a data structure for machine learning having a plurality of pieces of learning data, and a second database constructed by machine learning using a plurality of pieces of learning data. The learning data includes evaluation target information including image data including an image representing the medical device and an identification tag for identifying the medical device, and a meta ID associated with a content ID corresponding to the reference information.

Description

[0001] This application is a divisional application of a patent application for an invention titled "Learning Method and Information Provision System" with an application date of March 25, 2020, and an application number of 202080002662.6 (international application number PCT / JP2020 / 013352). Technical Field

[0002] The present invention relates to an information provision system. Background Art

[0003] In recent years, technologies for providing prescribed information to a user based on an acquired image have drawn attention. For example, in Patent Document 1, an image of a crop is acquired from a wearable terminal, and a predicted harvest time is displayed in an augmented reality manner on a display panel of the wearable terminal.

[0004] The wearable terminal display system of Patent Document 1 displays the harvest time of a crop on a display panel of the wearable terminal, and includes: an image acquisition unit that acquires an image of a crop that has entered the field of view of the wearable terminal; a determination unit that analyzes the image to determine the type of the crop; a selection unit that selects a determination criterion according to the type; a determination unit that analyzes the image according to the determination criterion to determine color and size; a prediction unit that predicts the harvest time of the crop according to the determination result; and a harvest time display unit that displays the predicted harvest time in an augmented reality manner on the display panel of the wearable terminal for the crop seen through the display panel.

[0005] Prior Art Documents

[0006] Patent Documents

[0007] Patent Document 1: Japanese Patent Publication No. 6267841 Summary of the Invention

[0008] Problems to be Solved by the Invention

[0009] However, the wearable terminal display system disclosed in Patent Document 1 determines the type of a crop by analyzing an image. Therefore, in the case where a new relationship between an image and a crop is acquired, it is necessary to relearn this relationship by machine learning. Therefore, there is a problem that it takes time to update when a new relationship is acquired.

[0010] Therefore, the present invention has been made in view of the above problems, and an object thereof is to provide a learning method and an information provision system capable of performing operations in a short time.

[0011] Means for Solving the Problems

[0012] The data structure for machine learning of the present invention is used to construct a first database utilized when selecting reference information for a user to perform an operation suitable for performing an operation related to a medical device, and is stored in a storage unit of a computer. The data structure for machine learning is characterized in that it has a plurality of learning data, the learning data includes evaluation object information having image data and a meta ID, the image data includes an image representing the medical device and an identification label for identifying the medical device, the meta ID is associated with a content ID corresponding to the reference information, and the plurality of learning data is used to construct the first database through machine learning performed by a control unit of the computer.

[0013] The learning method of the present invention is characterized in that machine learning is performed using the data structure for machine learning of the present invention. The data structure for machine learning is used to construct a first database utilized when selecting reference information for a user to perform an operation suitable for performing an operation related to a medical device, and the data structure for machine learning is stored in a storage unit of a computer.

[0014] The information providing system of the present invention selects reference information for a user to perform an operation suitable for performing an operation related to a medical device. The information providing system is characterized in that it has a first database, and the first database is constructed through machine learning using the data structure for machine learning of the present invention.

[0015] The information providing system of the present invention selects reference information for a user to perform an operation suitable for performing an operation related to a medical device. The information providing system is characterized in that it has: an acquisition unit that acquires acquisition data including first image data, the first image data being image data obtained by photographing a specific medical device and a specific identification label for identifying the specific medical device; a first database that is constructed through machine learning using a data structure for machine learning, the data structure for machine learning including a plurality of learning data, the learning data including evaluation object information having image data and a meta ID associated with the evaluation object information; a meta ID selection unit that refers to the first database and selects a first meta ID from among the plurality of meta IDs according to the acquisition data; a second database that stores a plurality of content IDs associated with the meta IDs and a plurality of the reference information corresponding to the content IDs; a content ID selection unit that refers to the second database and selects a first content ID from among the plurality of content IDs according to the first meta ID; and a reference information selection unit that refers to the second database and selects a first reference information from among the plurality of reference information according to the first content ID, the image data including an image representing the medical device and an identification label for identifying the medical device.

[0016] Advantages of the Invention

[0017] According to the present invention, operations can be performed in a short time. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 is a schematic diagram showing an example of the structure of the information providing system in the present embodiment.

[0019] Figure 2 is a schematic diagram showing an example of using the information providing system in the present embodiment.

[0020] Figure 3 is a schematic diagram showing an example of the database for meta-ID estimation processing and the reference database in the present embodiment.

[0021] Figure 4 is a schematic diagram showing an example of the data structure for machine learning in the present embodiment.

[0022] Figure 5 is a schematic diagram showing an example of the structure of the information providing apparatus in the present embodiment.

[0023] Figure 6 is a schematic diagram showing an example of the function of the information providing apparatus in the present embodiment.

[0024] Figure 7 is a flowchart showing an example of the operation of the information providing system in the present embodiment.

[0025] Figure 8 is a schematic diagram showing a modified example of the function of the information providing apparatus in the present embodiment.

[0026] Figure 9 is a schematic diagram showing a modified example of using the information providing system in the present embodiment.

[0027] Figure 10 is a schematic diagram showing an example of the scenario model database in the present embodiment.

[0028] Figure 11 is a schematic diagram showing an example of the scenario model table in the present embodiment.

[0029] Figure 12 is a schematic diagram showing an example of the content model table for scenarios in the present embodiment.

[0030] Figure 13 is a schematic diagram showing an example of the scenario table in the present embodiment.

[0031] Figure 14 is a schematic diagram showing a modified example of using the information providing system in the present embodiment.

[0032] Figure 15 It is a schematic diagram showing an example of the content database in the present embodiment.

[0033] Figure 16 It is a schematic diagram showing an example of the abstract table in the present embodiment.

[0034] Figure 17 It is a schematic diagram showing an example of the reference abstract list in the present embodiment.

[0035] Figure 18 It is a flowchart showing a modified example of the operation of the information providing system in the present embodiment.

[0036] Figure 19 It is a schematic diagram showing a second modified example of the functions of the information providing device in the present embodiment.

[0037] Figure 20 It is a schematic diagram showing a second modified example of the information providing system in the present embodiment.

[0038] Figure 21 It is a schematic diagram showing an example of the content relevance database.

[0039] Figure 22A It is a schematic diagram showing an example of the content relevance database.

[0040] Figure 22B It is a schematic diagram showing an example of the external information similarity calculation database.

[0041] Figure 23A It is a schematic diagram showing an example of the content relevance database.

[0042] Figure 23B It is a schematic diagram showing an example of the data block reference information similarity calculation database.

[0043] Figure 24 It is a flowchart showing a second modified example of the operation of the information providing system in the present embodiment.

[0044] Figure 25 It is a flowchart showing a third modified example of the operation of the information providing system in the present embodiment. Detailed Embodiments

[0045] Next, an example of a data structure, a learning method, and an information providing system for machine learning in the embodiments of the present invention will be described with reference to the drawings.

[0046] (Structure of Information Providing System 100)

[0047] Refer to Figures 1 to 7An example of the structure of the information providing system 100 in the present embodiment will be described. Figure 1 It is a block diagram showing the overall structure of the information providing system 100 in the present embodiment.

[0048] The information providing system 100 is used by users such as medical-related personnel including clinical engineers who use medical devices. The information providing system 100 is mainly used for the medical device 4 used by medical-related personnel such as clinical engineers. The information providing system 100 selects, from the acquisition data having the image data of the medical device 4, the first reference information suitable for the user who performs an operation related to the medical device 4 to perform the operation. In addition to being able to provide, for example, the user manual of the medical device 4 to the user, the information providing system 100 can also provide, for example, event information related to the medical device 4 to the user. Thereby, the user can master the user manual of the medical device 4 and the events related to the medical device 4.

[0049] As Figure 1 shown, the information providing system 100 includes an information providing device 1. The information providing device 1 can be connected to at least any one of the user terminal 5 and the server 6 via, for example, a public communication network 7.

[0050] Figure 2 It is a schematic diagram showing an example of using the information providing system 100 in the present embodiment. The information providing device 1 acquires the acquisition data having the first image data. The information providing device 1 selects the first meta ID according to the acquired acquisition data and sends it to the user terminal 5. The information providing device 1 acquires the first meta ID from the user terminal 5. The information providing device 1 selects the first reference information according to the acquired first meta ID and sends it to the user terminal 5. Thereby, the user can master the first reference information including the user manual of the medical device 4 and the like.

[0051] Figure 3 It is a schematic diagram showing an example of the meta ID estimation processing database and the reference database in the present embodiment. The information providing device 1 refers to the meta ID estimation processing database (the first database) and selects the first meta ID from among the plurality of meta IDs according to the acquired acquisition data. The information providing device 1 refers to the reference database (the second database) and selects the first content ID from among the plurality of content IDs according to the selected first meta ID. The information providing device 1 refers to the reference database and selects the first reference information from among the plurality of reference information according to the selected first content ID.

[0052] The database for meta-ID estimation processing is constructed by machine learning using the data structure for machine learning to which the present invention is applied. The data structure for machine learning to which the present invention is applied is used to construct the database for meta-ID estimation processing, which is utilized by a user who performs operations related to the medical device 4 when selecting reference information suitable for implementing the operations. The data structure for machine learning is stored in the storage unit 104 of the information providing device 1 (computer).

[0053] Figure 4 It is a schematic diagram showing an example of the data structure for machine learning in the present embodiment. The data structure for machine learning to which the present invention is applied has a plurality of learning data. The plurality of learning data are used to construct the database for meta-ID estimation processing through machine learning executed by the control unit 18 of the information providing device 1. The database for meta-ID estimation processing may also be a learned complete model constructed by performing machine learning using the data structure for machine learning.

[0054] The learning data has evaluation object information and a meta-ID. The database for meta-ID estimation processing is stored in the storage unit 104.

[0055] The evaluation object information has image data. The image data has an image representing the medical device 4 and an identification label for identifying the medical device 4. The image may be a static image or a dynamic image. The identification label may use a management number or the like composed of a string such as a shape name, a type name, a user, etc. given for identifying the medical device 4, or may use a one-dimensional code such as a barcode, a two-dimensional code such as a QR code (registered trademark), etc. The evaluation object information may also have event information.

[0056] The event information includes near misses in the medical device 4, accident cases of the medical device 4 issued by administrative agencies such as the Ministry of Health, Labour and Welfare, etc. The event information may include alarm information related to an alarm generated by the medical device 4. The event information may be, for example, a file such as sound, or a file of translated sound such as a foreign language corresponding to Japanese. For example, if the sound language of a certain country is registered, the corresponding translated sound file of the foreign language may also be stored accordingly.

[0057] The meta-ID is composed of a string and is associated with the content ID. The capacity of the meta-ID is smaller than the capacity of the reference information. The meta-ID includes a device meta-ID for classifying the medical device 4 shown in the image data, and an operation order meta-ID related to the operation order of the medical device 4 shown in the image data. The meta-ID may also include an event meta-ID related to the event information shown in the acquired data.

[0058] The acquired data has first image data. The first image data is an image obtained by photographing a specific medical device and a specific identification label for identifying the specific medical device. The first image data is, for example, image data photographed by a camera of the user terminal 5. The acquired data may also have event information.

[0059] As Figure 3 shown, the meta-correlation degree between the evaluation object information and the meta-ID is stored in the database for meta-ID estimation processing. The meta-correlation degree indicates the degree of correlation between the evaluation object information and the meta-ID, and is represented by, for example, a grade of three or more grades such as a percentage, 10 grades, or 5 grades. For example, in Figure 3 it, the "image data A" included in the evaluation object information shows a meta-correlation degree of "20%" with the meta-ID "IDaa" and a meta-correlation degree of "50%" with the meta-ID "IDab". In this case, "IDab" indicates a stronger correlation with "image data A" than "IDaa".

[0060] The database for meta-ID estimation processing may also have an algorithm capable of calculating the meta-correlation degree, for example. As the database for meta-ID estimation processing, for example, a function (classifier) optimized according to the evaluation object information, the meta-ID, and the meta-correlation degree can be used.

[0061] The database for meta-ID estimation processing is constructed using machine learning, for example. As a method of machine learning, deep learning is used, for example. The database for meta-ID estimation processing is composed of a neural network, for example. In this case, the meta-correlation degree can be represented by a hidden layer and weight variables.

[0062] The reference database stores a plurality of content IDs and a plurality of reference information. The reference database is stored in the storage unit 104.

[0063] The content ID is composed of a string and is associated with one or more meta-IDs. The capacity of the content ID is smaller than the capacity of the reference information. The content ID has a device ID for classifying the medical device 4 shown in the reference information, and a job order ID related to the job order of the medical device 4 shown in the reference information. The content ID may also have an event ID related to the event information of the medical device 4 shown in the reference information. The device ID is associated with the device meta-ID in the meta-ID, the job order ID is associated with the job order meta-ID in the meta-ID, and the event ID is associated with the event meta-ID.

[0064] Reference information corresponds to a content ID. One content ID is assigned to one piece of reference information. The reference information has information related to the medical device 4. The reference information includes the user manual of the medical device 4, the split user manual, event information, document information, historical information, etc. The reference information can be a data block structure obtained by aggregating meaningful information into a group of data. The reference information can be a dynamic image file. The reference information can also be a sound file, or a file such as a translated sound corresponding to a foreign language corresponding to Japanese. For example, if the sound language of a certain country is registered, the translated sound file of the corresponding foreign language can also be stored correspondingly.

[0065] The user manual has device information and operation sequence information. The device information is information for classifying the medical device 4, including specifications (descriptions), operation and maintenance manuals, etc. The operation sequence information has information related to the operation sequence of the medical device 4. It is also possible that the device information is associated with a device ID, and the operation sequence information is associated with an operation sequence ID. The reference information can also have device information and operation sequence information.

[0066] The split user manual is obtained by splitting the user manual within a specified range. The split user manual can be obtained, for example, by splitting the user manual by each page, each chapter, or each data block structure obtained by aggregating meaningful information into a group of data. The user manual and the split user manual can be dynamic images or sound data.

[0067] As described above, the event information includes near misses in the medical device 4, accident cases of the medical device 4 issued by administrative agencies such as the Ministry of Health, Labour and Welfare, etc. In addition, as described above, the event information can include alarm information related to the alarms generated by the medical device 4. At this time, the event information can be associated with at least any one of the device ID and the operation sequence ID.

[0068] The document information has the design specifications, reports, reports, etc. of the medical device 4.

[0069] The historical information is information related to the maintenance, failures, repairs, etc. of the medical device 4.

[0070] The information providing system 100 has a meta-ID estimation processing database (first database), which is constructed by machine learning using a data structure for machine learning. The data structure for machine learning stores a plurality of learning data, and the learning data includes evaluation object information having image data of the medical device 4 and a meta-ID, and the meta-ID is associated with a content ID. Therefore, when the reference information is updated again, it is only necessary to change the association between the meta-ID and the content ID corresponding to the reference information, or to change the correspondence between the updated reference information and the content ID, and it is not necessary to update the relationship between the evaluation object information and the meta-ID again. Thus, it is not necessary to reconstruct the meta-ID estimation processing database along with the update of the reference information. As a result, the update operation can be performed in a short time.

[0071] In addition, in the information providing system 100, the learning data has a meta-ID. Therefore, when constructing the meta-ID estimation processing database, machine learning can be performed using a meta-ID with a smaller capacity than the capacity of the reference information. Thus, compared with performing machine learning using the reference information, the meta-ID estimation processing database can be constructed in a shorter time.

[0072] In addition, when the information providing system 100 retrieves the reference information, it uses a meta-ID with a smaller capacity than the capacity of the image data as a search term and returns a content ID with a smaller capacity than the capacity of the reference information as a result that matches or partially matches the search term. Therefore, the data communication volume and processing time in the retrieval process can be reduced.

[0073] In addition, in the case of a system that uses machine learning based on a data structure for machine learning to establish retrieval of reference information, the information providing system 100 can use the image data as acquisition data (input information) corresponding to the search keyword. Therefore, the user does not need to verbalize the information to be retrieved and a specific medical device using text input or voice, and can perform retrieval even if the concept and name are unknown.

[0074] The learning method in the embodiment performs machine learning using the data structure for machine learning in the embodiment. The data structure for machine learning is used to construct a meta-ID estimation processing database, which is used by a user who performs operations related to a medical device when selecting reference information suitable for performing the operation, and the learning method is stored in the storage unit 104 of the computer. Therefore, even when the reference information is updated again, it is only necessary to change the association between the meta-ID and the content ID corresponding to the reference information, and it is not necessary to re-update the relationship between the evaluation object information and the meta-ID. Thus, it is not necessary to reconstruct the meta-ID estimation processing database along with the update of the reference information. As a result, the update operation can be performed in a short time.

[0075] <Information providing device 1>

[0076] Figure 5 This is a schematic diagram showing an example of the structure of the information providing device 1. As the information providing device 1, in addition to a personal computer (PC), electronic devices such as a smartphone and a tablet terminal can also be used. The information providing device 1 includes a housing 10, a CPU 101, a ROM 102, a RAM 103, a storage unit 104, and I / Fs 105 to 107. Each of the components 101 to 107 is connected by an internal bus 110.

[0077] The CPU (Central Processing Unit) 101 controls the entire information providing device 1. The ROM (ReadOnly Memory) 102 stores the operation codes of the CPU 101. The RAM (Random Access Memory) 103 is a working area used when the CPU 101 operates. The storage unit 104 stores various information such as data structures for machine learning, acquired data, a meta-ID estimation processing database, a reference database, a content database described later, and a scenario model database described later. As the storage unit 104, for example, in addition to an HDD (Hard Disk Drive), an SSD (solid state drive) or the like is also used.

[0078] The I / F 105 is an interface for transmitting and receiving various information to and from a user terminal 5 or the like via a public communication network 7. The I / F 106 is an interface for transmitting and receiving various information to and from an input unit 108. For example, a keyboard is used as the input unit 108, and a user of the information providing system 100 inputs or selects various information or control commands of the information providing device 1 via the input unit 108. The I / F 107 is an interface for transmitting and receiving various information to and from an output unit 109. The output unit 109 outputs various information stored in the storage unit 104 or the processing status of the information providing device 1. A display is used as the output unit 109, and for example, it can be a touch panel type. In this case, it can also be configured such that the output unit 109 includes the input unit 108.

[0079] Figure 6 This is a schematic diagram showing an example of the functions of the information providing device 1. The information providing device 1 includes an acquisition unit 11, a meta-ID selection unit 12, a content ID selection unit 13, a reference information selection unit 14, an input unit 15, an output unit 16, a storage unit 17, and a control unit 18. In addition, the CPU 101 uses the RAM 103 as a working area to execute programs stored in the storage unit 104 or the like, thereby implementing Figure 6Each function shown. In addition, each function can also be controlled by artificial intelligence, for example. Here, "artificial intelligence" can be artificial intelligence based on any well-known artificial intelligence technology.

[0080] <Acquisition unit 11>

[0081] The acquisition unit 11 acquires various information such as acquisition data. The acquisition unit 11 acquires learning data for constructing a database for meta-ID estimation processing.

[0082] <Meta-ID selection unit 12>

[0083] The meta-ID selection unit 12 refers to the database for meta-ID estimation processing and selects the first meta-ID among multiple meta-IDs according to the acquisition data. For example, when using the Figure 3 shown database for meta-ID estimation processing, the meta-ID selection unit 12 selects evaluation object information (such as "Image Data A") that is the same as or similar to the "First Image Data" included in the acquisition data. In addition, for example, when using the Figure 3 shown database for meta-ID estimation processing, the meta-ID selection unit 12 selects evaluation object information (such as "Image Data B" and "Event Information A") that is the same as or similar to the "First Image Data" and "Event Information" included in the acquisition data.

[0084] As the evaluation object information, in addition to selecting information that is partially or completely consistent with the acquisition data, for example, similar (including the same concept, etc.) information is also used. Since the acquisition data and the evaluation object information respectively contain information with equivalent features, the accuracy of the evaluation object information to be selected can be improved.

[0085] The meta-ID selection unit 12 selects one or more first meta-IDs among the multiple meta-IDs associated with the selected evaluation object information. For example, when using the Figure 3 shown database for meta-ID estimation processing, the meta-ID selection unit 12 selects the meta-IDs "IDaa", "IDab", "IDac" among the multiple meta-IDs "IDaa", "IDab", "IDac", "IDba", "IDca" associated with the selected "Image Data A" as the first meta-IDs.

[0086] In addition, the meta-ID selection unit 12 can also set a threshold for the meta-association degree in advance and select a meta-ID with a meta-association degree higher than this threshold as the first meta-ID. For example, when setting the meta-association degree of 50% or more as the threshold, the meta-ID "IDab" with a meta-association degree of 50% or more can be selected as the first meta-ID.

[0087] <Content ID selection unit 13>

[0088] The content ID selection unit 13 refers to the reference database and selects the first content ID from among multiple content IDs according to the first meta ID. For example, when using the reference database shown in Figure 3 , the content ID selection unit 13 selects the content IDs (such as "Content ID - A" and "Content ID - B") associated with the selected first meta IDs "IDaa", "IDab", and "IDac" as the first content ID. In the reference database shown in Figure 3 , "Content ID - A" is associated with the meta IDs "IDaa" and "IDab", and "Content ID - B" is associated with the meta IDs "IDaa" and "IDac". That is, the content ID selection unit 13 selects the content ID associated with any one of or a combination of the first meta IDs "IDaa", "IDab", and "IDac" as the first content ID. The content ID selection unit 13 uses the first meta ID as a search term and selects the result that is the same as or partially matches the search term as the first content ID.

[0089] In addition, when the device meta ID among the selected first meta IDs is associated with the device ID of the content ID and the operation sequence meta ID is associated with the operation sequence ID of the content ID, the content ID selection unit 13 selects the content ID having the device ID associated with the device meta ID or the content ID having the operation sequence ID associated with the operation sequence meta ID as the first content ID.

[0090] <Reference information selection unit 14>

[0091] The reference information selection unit 14 refers to the reference database and selects the first reference information from among multiple reference information according to the first content ID. For example, when using the reference database shown in Figure 3 , the reference information selection unit 14 selects the reference information (such as "Reference information A") corresponding to the selected first content ID "Content ID - A" as the first reference information.

[0092] <Input unit 15>

[0093] The input unit 15 inputs various information to the information providing device 1. In addition to inputting various information such as learning data and acquisition data via the I / F 105, the input unit 15 also inputs various information from the input section 108 via the I / F 106, for example.

[0094] <Output unit 16>

[0095] The output unit 16 outputs the first meta ID, reference information, etc. to the output section 109, etc. The output unit 16 transmits the first meta ID, reference information, etc. to the user terminal 5, etc. via the public communication network 7, for example.

[0096] <Storage unit 17>

[0097] The storage unit 17 stores various information such as data structures for machine learning and acquired data in the storage unit 104, and retrieves various information stored in the storage unit 104 as needed. In addition, the storage unit 17 stores various databases such as a meta-ID estimation processing database, a reference database, a content database described later, and a scenario model database described later in the storage unit 104, and retrieves various databases stored in the storage unit 104 as needed.

[0098] <Control unit 18>

[0099] The control unit 18 performs machine learning for constructing the first database using the data structure for machine learning to which the present invention is applied. The control unit 18 performs machine learning by linear regression, logistic regression, support vector machine, decision tree, regression tree, random forest, gradient boosting tree, neural network, Bayesian, time series, clustering, ensemble learning, etc.

[0100] <Medical device 4>

[0101] The medical device 4 may include, for example, a pacemaker, a coronary stent, an artificial blood vessel, a PTCA catheter, a central venous catheter, an absorbable internal fixation bolt, a particle beam therapy device, an artificial dialysis machine, an epidural catheter, an infusion pump, an automatic peritoneal perfusion device, an artificial bone, a cardiopulmonary bypass device, a multi-person dialysis fluid supply device, a component blood collection device, a ventilator, a program, etc., which are advanced management medical devices (corresponding to the type classifications "Type III" and "Type IV" of the Global Harmonization Task Force (GHTF)).). The medical device 4 includes, for example, an X-ray imaging device, an electrocardiograph, an ultrasonic diagnostic device, an injection needle, a blood collection needle, a vacuum blood collection tube, an infusion component for an infusion pump, a urinary catheter, a suction catheter, a hearing aid, a home massager, a condom, a program, etc., which are management medical devices (corresponding to the type classification "Type II" of the GHTF).). The medical device 4 includes, for example, an enteral nutrition infusion component, a nebulizer, an X-ray film, a blood gas analysis device, a surgical non-woven fabric, a program, etc., which are general medical devices (corresponding to the type classification "Type I" of the GHTF).). The medical device 4 includes not only medical devices stipulated by laws and regulations, but also mechanical appliances similar to medical devices in appearance or structure not stipulated by laws and regulations (such as beds, etc.). The medical device 4 can be a device used in a medical site such as a hospital, and includes a medical information device storing a patient's medical record card or electronic medical record card or an information device storing information of hospital staff, etc.

[0102] <User terminal 5>

[0103] The user terminal 5 represents the terminal held by a user who manages the medical device 4. As the user terminal 5, it can mainly be a holographic lens (registered trademark), which is a type of HMD (head-mounted display). The user can confirm the first element ID and the first reference information of the user terminal 5 through a display unit that can perform see-through display, such as a head-mounted display or a holographic lens, and via an operation area or a specific medical device. Thus, the user can confirm the situation in front of them while referring to, for example, an operation manual selected based on the acquired data. In addition to electronic devices such as mobile phones (portable terminals), smartphones, tablet terminals, wearable terminals, personal computers, and IoT (Internet of Things) devices, the user terminal 5 can also be any specific device among all electronic devices. For example, in addition to being connected to the information providing device 1 via the public communication network 7, the user terminal 5 can also be directly connected to the information providing device 1. In addition to obtaining the first reference information from the information providing device 1 using the user terminal 5, the user can also control the information providing device 1, for example.

[0104] <Server 6>

[0105] The above various types of information are stored in the server 6. For example, various types of information sent via the public communication network 7 are stored in the server 6. For example, information identical to that in the storage unit 104 can be stored in the server 6, and various types of information can be transmitted and received between the server 6 and the information providing device 1 via the public communication network 7. That is, in the information providing device 1, the server 6 can be used instead of the storage unit 104.

[0106] <Public communication network 7>

[0107] The public communication network 7 is the Internet or the like that is connected to the information providing device 1 and others via a communication circuit. The public communication network 7 can be constituted by a so-called optical fiber communication network. In addition, the public communication network 7 is not limited to a wired communication network and can also be realized by a well-known communication network such as a wireless communication network.

[0108] (An example of the operation of the information providing system 100)

[0109] Next, an example of the operation of the information providing system 100 in the present embodiment will be described. Figure 7 It is a flowchart showing an example of the operation of the information providing system 100 in the present embodiment.

[0110] <Acquisition step S11>

[0111] First, the acquisition unit 11 acquires acquisition data (acquisition step S11). The acquisition unit 11 acquires the acquisition data via the input unit 15. The acquisition unit 11 acquires acquisition data including the first image data captured by the user terminal 5 and the event information stored in the server 6 or the like. The acquisition unit 11 saves the acquisition data in the storage unit 104 via the storage unit 17, for example.

[0112] The acquisition data can be generated by the user terminal 5. The user terminal 5 generates acquisition data including the first image data, which is the image data obtained by photographing a specific medical device and a specific identification label for identifying the specific medical device. The user terminal 5 can also generate event information and can also acquire event information from the server 6 or the like. The user terminal 5 can generate acquisition data including the first image data and the event information. The user terminal 5 sends the generated acquisition data to the information providing device 1. The input unit 15 receives the acquisition data, and the acquisition unit 11 acquires the acquisition data.

[0113] <Meta ID selection step S12>

[0114] Next, the meta ID selection unit 12 refers to the meta ID estimation processing database and selects the first meta ID from among a plurality of meta IDs based on the acquisition data (meta ID selection step S12). The meta ID selection unit 12 acquires the acquisition data acquired by the acquisition unit 11 and acquires the meta ID estimation processing database stored in the storage unit 104. In addition to selecting one first meta ID for one acquisition data, the meta ID selection unit 12 can select a plurality of first meta IDs for one acquisition data, for example. The meta ID selection unit 12 saves the selected first meta ID in the storage unit 104 via the storage unit 17, for example.

[0115] The meta ID selection unit 12 sends the first meta ID to the user terminal 5 to cause the display unit of the user terminal 5 to display the first meta ID. Thereby, the user can confirm the selected first meta ID and the like. In addition, the meta ID selection unit 12 can also cause the output unit 109 of the information providing device 1 to display the first meta ID. The meta ID selection unit 12 can omit the step of sending the first meta ID to the user terminal 5.

[0116] <Content ID selection step S13>

[0117] Next, the content ID selection unit 13 refers to the reference database and selects the first content ID from among the multiple content IDs based on the first meta ID (content ID selection step S13). The content ID selection unit 13 acquires the first meta ID selected by the meta ID selection unit 12 and acquires the reference database stored in the storage unit 104. In addition to selecting one first content ID for the first meta ID, the content ID selection unit 13 can, for example, select multiple first content IDs for one first meta ID. That is, the content ID selection unit 13 uses the first meta ID as a search term and selects as the first content ID a result that is identical to or partially matches the search term. The content ID selection unit 13 stores the selected first content ID in the storage unit 104 via the storage unit 17, for example.

[0118] <Reference information selection step S14>

[0119] Next, the reference information selection unit 14 refers to the reference database and selects the first reference information from among the multiple reference information based on the first content ID (reference information selection step S14). The reference information selection unit 14 acquires the first content ID selected by the content ID selection unit 13 and acquires the reference database stored in the storage unit 104. The reference information selection unit 14 selects one first reference information corresponding to one first content ID. When multiple first content IDs are selected, the reference information selection unit 14 can select each first reference information corresponding to each first content ID. Thereby, multiple first reference information are selected. The reference information selection unit 14 stores the selected first reference information in the storage unit 104 via the storage unit 17, for example.

[0120] For example, the output unit 16 sends the first reference information to the user terminal 5 or the like. The user terminal 5 displays the selected one or more first reference information on the display unit. The user can select one or more first reference information from the displayed one or more first reference information. Thereby, the user can grasp the existence of one or more first reference information such as a user manual. That is, since one or more candidates for the first reference information suitable for the user can be retrieved from the image data of the medical device 4 and the user can select from the retrieved one or more first reference information, it can play a greater role as a on-site work solution provided to the user performing operations related to the medical device 4 on-site.

[0121] In addition, the information providing device 1 can also cause the output unit 109 to display the first reference information. As described above, the operation of the information providing system 100 in the present embodiment ends.

[0122] According to this embodiment, the meta ID is associated with the content ID corresponding to the reference information. Thus, when updating the reference information, it is only necessary to update the association between the content ID corresponding to the reference information and the meta ID, or to change the correspondence between the updated reference information and the content ID, without the need to re-update the learning data. Therefore, there is no need to reconstruct the database for meta ID estimation processing along with the update of the reference information. Thus, along with the update of the reference information, the database can be constructed in a short time.

[0123] In addition, according to this embodiment, when constructing the database for meta ID estimation processing, machine learning can be performed using a meta ID with a smaller capacity than the capacity of the reference information. Therefore, compared with performing machine learning using the reference information, the database for meta ID estimation processing can be constructed in a shorter time.

[0124] In addition, according to this embodiment, when retrieving the reference information, a meta ID with a smaller capacity than the capacity of the image data is used as the retrieval term, and a content ID with a smaller capacity than the capacity of the reference information is returned as a result that is identical or partially identical to the retrieval term. Therefore, the data communication volume and processing time in the retrieval process can be reduced.

[0125] In addition, according to this embodiment, in the case of using machine learning based on the data structure for machine learning to establish a system for retrieving reference information, image data can be used as the acquired data (input information) corresponding to the retrieval keyword. Therefore, the user does not need to verbalize the information to be retrieved and a specific medical device using text input or voice, and can perform the retrieval even without knowing the concept and name.

[0126] According to this embodiment, the device meta ID is associated with the device ID, and the operation sequence meta ID is associated with the operation sequence ID. Thus, when selecting the content ID according to the meta ID, the range of selection targets of the content ID can be narrowed down. Therefore, the selection accuracy of the content ID can be improved.

[0127] According to this embodiment, the meta ID is associated with at least one of the content IDs in a reference database different from the database for meta ID estimation processing, and the reference database stores a plurality of reference information and a plurality of content IDs. Therefore, when updating the database for meta ID estimation processing, there is no need to update the reference database. In addition, when updating the reference database, there is no need to update the database for meta ID estimation processing. Thus, the update operations of the database for meta ID estimation processing and the reference database can be performed in a short time.

[0128] According to this embodiment, the reference information includes the user manual of the medical device 4. Thus, the user can immediately grasp the user manual of the target medical device. Therefore, the time for searching for the user manual can be shortened.

[0129] According to the present embodiment, the reference information has a divided user manual obtained by dividing the user manual of the medical device 4 within a specified range. Thus, the user can master the user manual in a state where the range of the corresponding part in the user manual is further narrowed. Therefore, the time for searching for the corresponding part in the user manual can be shortened.

[0130] According to the present embodiment, the reference information further includes the event information of the medical device 4. Thus, the user can master the event information. Therefore, the user can immediately respond to near misses and accidents.

[0131] According to the present embodiment, the evaluation object information further includes the event information of the medical device 4. Thus, when selecting the first meta ID according to the evaluation object information, the event information can be considered, and the range of selection targets for the first meta ID can be narrowed. Therefore, the selection accuracy of the first meta ID can be improved.

[0132] <The first modification example of the information providing device 1>

[0133] Next, a first modification example of the information providing device 1 will be described. In this modification example, mainly the first acquisition unit 21, the first evaluation unit 22, the first generation unit 23, the acquisition unit 11, the meta ID selection unit 12, and the content ID selection unit 13 are different from the above embodiment. Below, mainly these differences will be described. Figure 8 It is a schematic diagram showing a first modification example of the functions of the information providing device 1 in the present embodiment. In addition, the CPU 101 uses the RAM 103 as a work area and executes the programs stored in the storage unit 104 and the like, thereby realizing Figure 8 the various functions shown. In addition, each function can also be controlled by artificial intelligence, for example. Here, "artificial intelligence" can be based on any well-known artificial intelligence technology.

[0134] Figure 9 It is a schematic diagram showing a first modification example of the information providing system 100 using the present embodiment. The information providing device 1 in this modification example acquires acquisition data, which includes the first image data and the first scene ID as a set of data. The information providing device 1 selects the first meta ID according to the acquired acquisition data and sends it to the user terminal 5. Therefore, the information providing device 1 in this modification example can further improve the selection accuracy of the first meta ID.

[0135] <The first acquisition unit 21>

[0136] The first acquisition unit 21 acquires first image information. The first acquisition unit 21 acquires the first image information from the user terminal 5. The first image information is of equipment, components, etc. photographed by an operator, for example, photographed by an HMD (head-mounted display), a holographic lens, etc. The photographed image can be sent to the server 6 in real time. In addition, the photographed image can be acquired as the first image information. The first image information is, for example, an image photographed by a camera of the user terminal 5 possessed by a user on site. The first image information can be, for example, either a still image or a moving image, and can be photographed by the user or automatically photographed through the settings of the user terminal 5. Then, it can be read into the image information recorded in the memory, etc. of the user terminal 5, or acquired via the public communication network 7, etc.

[0137] <The first evaluation unit 22>

[0138] The first evaluation unit 22 refers to the scene model database and acquires a list of scene IDs including the first scene correlation degree between the first image information and the scene information, where the scene information includes scene IDs. The first evaluation unit 22 refers to the scene model database, selects past first image information that is the same as, partially the same as, or similar to the acquired first image information, selects the scene information including scene IDs associated with the selected past first image information, and calculates the first scene correlation degree based on the scene correlation degree between the selected past first image information and the scene information. The first evaluation unit 22 acquires the scene IDs including the calculated first scene correlation degree, and displays the list of scene names selected according to the list of scene IDs on the user terminal 5.

[0139] Figure 10 It is a schematic diagram showing an example of the scene model database in this embodiment. The scene model database is stored in the storage unit 104. The scene model database stores pre-acquired past first image information, scene information including scene IDs associated with the past first image information, and a scene correlation degree of three or more levels between the past first image information and the scene information.

[0140] The scene model database is constructed by machine learning using an arbitrary model such as a neural network. The scene model database is constructed based on the evaluation results of the first image information obtained through machine learning, the past first image information, and the scene ID, and stores various relationships as scene correlation degrees, for example. The scene correlation degree represents the degree of correlation between the past first image information and the scene information. For example, the higher the scene correlation degree, the stronger the correlation between the past first image information and the scene information can be judged. The scene correlation degree can be represented not only by using three or more values (three or more levels) such as percentages, but also by using two values (two levels). For example, the scene correlation degree between the "01" of the past first image information and the scene ID "A" is 70%, the scene correlation degree between the scene ID "D" is 50%, and the scene correlation degree between the scene ID "C" is 10%, etc., and they are stored in this way. The first image information obtained from the user terminal 5 undergoes machine learning to construct evaluation results such as the similarity with the previously obtained past first image information. For example, by performing deep learning, it is also possible to handle information that is different but similar.

[0141] The scene model database stores a scene ID list and a scene name list. The scene ID list shows, for example, the calculated first scene correlation degree and the scene ID. The scene model database stores the results of this evaluation, that is, the content in a list form. The content in the list form is, for example, scene IDs such as "Scene ID A: 70%", "Scene ID B: 50%", etc., showing the relationship of the scene correlation degrees from high to low.

[0142] The scene name list is generated by the first generation unit 23 described later. For example, in the scene ID list, the first evaluation unit 22 obtains the scene names corresponding to the scene IDs and stores them in the scene name list. The scene name list stored in the scene model database is sent to the user terminal 5 in subsequent processing. The user refers to the scene name list received by the user terminal 5 to grasp the scene corresponding to the first image information.

[0143] In addition, when there is no scene information corresponding to the first image information and no scene name corresponding to the scene ID in the scene model database due to updates to the scene model database, corrections and additions to the registered data, etc., it is possible to perform the acquisition process of the first image information in other views, or to use the prepared substitute scene information or scene ID when there is no correspondence to perform the correspondence again, generate a scene name list with additional substitute scenes, and send it to the user terminal 5.

[0144] <The first generation unit 23>

[0145] The first generation unit 23 generates a scene name list corresponding to the scene ID list obtained by the first evaluation unit 22. The generated scene name list has, for example, "Scene ID", "Scene correlation degree", etc.

[0146] The scenario ID is associated with, for example, Figure 11 the scenario model table shown and Figure 12 the content model table (OFE) for the scenario shown. In the scenario model table, for example, the scenario ID, learning model, etc. are stored, and in the content model table for the scenario, the content ID, learning model, etc. are stored. The first generation unit 23 generates a scenario name list based on this information.

[0147] Figure 11 The scenario model table shown is stored in the scenario model database. In the scenario model table, for example, the scenario ID for identifying each operation performed by the user on-site and the learning model corresponding to the scenario ID are stored correspondingly. There are multiple scenario IDs, and the learning models corresponding to the respective scenario IDs are stored correspondingly with the image information.

[0148] Figure 12 The content model table for the scenario shown stores the content ID and learning model in each scenario ID correspondingly. In Figure 12 the content model table for the scenario shown, for example, in the case where the scenario ID is "OFE", the content IDs corresponding to various scenarios are stored respectively. There are multiple content IDs, and the learning models corresponding to the respective scenarios are stored correspondingly with the image information. In addition, the content ID may include content for which the scenario is not specified. In this case, "NULL" is stored in the content ID.

[0149] Figure 13 It is a schematic diagram showing an example of the scenario table. Figure 13 The scenario table shown is stored in the scenario model database. In the scenario table, for example, the summary of the image information of each operation performed by the user on-site and the scenario ID for identifying the summary operation are stored correspondingly. There are multiple scenario IDs, and the scenario names corresponding to the respective scenario IDs are stored correspondingly.

[0150] <Acquisition unit 11>

[0151] The acquisition unit 11 acquires acquisition data, and the acquisition data has the first image data and the first scenario ID corresponding to the scenario name selected from the scenario name list as a set of data.

[0152] <Meta ID selection unit 12>

[0153] Figure 14This is a schematic diagram showing a modified example of the information providing system in the present embodiment. The meta-ID selection unit 12 refers to the meta-ID estimation processing database, extracts a plurality of meta-IDs based on the acquired data, and generates a meta-ID list including the plurality of meta-IDs. The meta-ID list lists the plurality of meta-IDs. The meta-ID selection unit 12 generates a reference abstract list corresponding to the meta-ID list. Specifically, the meta-ID selection unit 12 refers to the content database and acquires the content IDs associated with the respective meta-IDs included in the generated meta-ID list.

[0154] Figure 15 This is a schematic diagram showing an example of the content database. In the content database, a meta-ID, a content ID, and the content association degree between the meta-ID and the content ID can be stored. The content association degree indicates the degree to which the meta-ID and the content ID are associated, and is represented by, for example, a percentage, or a scale of three or more levels such as a 10-level scale or a 5-level scale. For example, in Figure 15 "IDaa" included in the meta-ID shows that the association degree with "Content ID-A" included in the content ID is "60%", and shows that the association degree with "Content ID-B" is "40%". In this case, "IDaa" shows that the association with "Content ID-A" is stronger than that with "Content ID-B".

[0155] The content database may also have an algorithm capable of calculating the content association degree, for example. As the content database, for example, a function (classifier) optimized according to the meta-ID, the content ID, and the content association degree can be used.

[0156] The content database is constructed using machine learning, for example. As a method of machine learning, deep learning is used, for example. The content database is constituted by a neural network, for example. In this case, the association degree can be represented by a hidden layer and a weight variable.

[0157] The meta-ID selection unit 12 may also refer to the content association degree and acquire the content IDs associated with the plurality of meta-IDs included in the meta-ID list. For example, the meta-ID selection unit 12 can acquire the content IDs with high content association degrees based on the meta-IDs.

[0158] The meta-ID selection unit 12 refers to the abstract table and acquires the abstracts of the reference information corresponding to the acquired content IDs. Figure 16 This shows an example of the abstract table. The abstract table includes a plurality of content IDs and the abstracts of the reference information corresponding to the content IDs. The abstract table is stored in the storage unit 104. The abstract of the reference information represents the summary of the content of the reference information, etc.

[0159] The meta-ID selection unit 12 generates a reference abstract list based on the acquired abstracts of the reference information. Figure 17An example of a reference abstract list is shown. The reference abstract list includes abstracts of a plurality of reference information and a plurality of meta-IDs corresponding to the abstracts of the reference information. The meta-ID selection unit 12 sends the reference abstract list to the user terminal 5. The user terminal 5 selects an abstract of reference information from the sent reference abstract list, selects a meta-ID based on the selected abstract of reference information, and sends the selected meta-ID to the information providing device 1. Then, the meta-ID selection unit 12 selects the meta-ID selected by the user terminal 5 from the reference abstract list as the first meta-ID.

[0160] <Content ID selection unit 13>

[0161] The content ID selection unit 13 refers to the reference database and the content database, and selects the first content ID from among a plurality of content IDs according to the first meta-ID. For example, when using the Figure 15 shown content database, the content ID associated with the first meta-ID "IDaa" (such as "Content ID-A", "Content ID-B", etc.) is selected as the first content ID. At this time, "Content ID-A" with a relatively high content association degree (for example, a content association degree of 60%) may also be selected. A threshold value for the content association degree may be set in advance, and a content ID having a content association degree higher than the threshold value may be selected as the first content ID.

[0162] (First modification example of the operation of the information providing system 100)

[0163] Next, a first modification example of the operation of the information providing system 100 in the present embodiment will be described. Figure 18 It is a flowchart showing a first modification example of the operation of the information providing system 100 in the present embodiment.

[0164] <First acquisition step S21>

[0165] First, the first acquisition unit 21 acquires first image information from the user terminal 5 (first acquisition step S21). The first acquisition unit 21 acquires the first image information obtained by the user terminal 5 photographing a specific medical device 4.

[0166] <First evaluation step S22>

[0167] Next, the first evaluation unit 22 refers to the scene model database and acquires a scene ID list including the first scene association degree between the acquired first image information and the scene information (first evaluation step S22).

[0168] <First generation step S23>

[0169] Next, the first generation unit 23 generates a list of scene names corresponding to the list of scene IDs obtained by the first evaluation unit 22 (first generation step S23). The first generation unit 23 refers to, for example, Figure 13 the scene table shown, and generates a list of scene names corresponding to the obtained list of scene IDs. For example, when the scene ID included in the list of scene IDs obtained by the first evaluation unit 22 is "OFD", a scene name such as "Restart of ABC-999 device" is selected as the scene name. For example, when the scene ID is "OFE", a scene name such as "Remove the memory of ABC-999 device" is selected as the scene name.

[0170] <Acquisition step S24>

[0171] Next, the acquisition unit 11 acquires acquisition data, which includes the first image data and the first scene ID corresponding to the scene name selected from the list of scene names as a set of data (acquisition step S24). The scene ID corresponding to the scene name selected from the list of scene names becomes the first scene ID.

[0172] <Meta ID selection step S25>

[0173] Next, the meta ID selection unit 12 extracts a plurality of meta IDs from the acquisition data and generates a list of meta IDs including the plurality of meta IDs (meta ID selection step S25). The meta ID selection unit 12 generates a list of reference abstracts corresponding to the list of meta IDs. The meta ID selection unit 12 sends the generated list of reference abstracts to the user terminal 5. Then, the user terminal 5 selects one or more reference information abstracts and the meta IDs corresponding to the reference information abstracts from the sent list of reference abstracts. The user terminal 5 sends the selected reference information abstracts and meta IDs to the information providing device 1. Then, the meta ID selection unit 12 selects the meta ID selected by the user terminal 5 from the list of reference abstracts as the first meta ID.

[0174] <Content ID selection step S26>

[0175] Next, the content ID selection unit 13 refers to the reference database and the content database, and selects the first content ID from among the plurality of content IDs according to the first meta ID (content ID selection step S26). The content ID selection unit 13 acquires the first meta ID selected by the meta ID selection unit 12, and acquires the reference database and the content database stored in the storage unit 104. In addition to selecting one first content ID for the first meta ID, the content ID selection unit 13 can, for example, also select a plurality of first content IDs for one first meta ID. The content ID selection unit 13 stores the selected first content ID in the storage unit 104 via the storage unit 17, for example.

[0176] Then, the above reference information selection step S14 is performed, and it is completed.

[0177] According to this modification example, the meta-ID selection unit 12 extracts a plurality of first meta-IDs from the plurality of meta-IDs, generates a meta-ID list including the plurality of first meta-IDs, generates a reference abstract list corresponding to the meta-ID list, and selects the first meta-ID selected from the reference abstract list. Thus, the first meta-ID can be selected according to the reference abstract list. Therefore, the selection accuracy of the first meta-ID can be improved.

[0178] According to this modification example, the acquisition unit 11 acquires acquisition data, and the acquisition data includes the first image data and the first scene ID corresponding to the scene name selected from the scene name list as a set of data. Thus, the meta-ID can be selected considering the first scene ID. Therefore, the selection accuracy of the meta-ID can be improved.

[0179] According to this modification example, the content ID selection unit 13 refers to the reference database and the content database, and selects the first content ID from the plurality of content IDs according to the first meta-ID. Thus, when selecting the content ID according to the meta-ID, the range of the selection object of the content ID can be further narrowed with reference to the content relevance. Therefore, the selection accuracy of the first content ID can be further improved.

[0180] <Second Modification Example of Information Providing Device 1>

[0181] Next, a second modification example of the information providing device 1 will be described. In this modification example, it is mainly different from the above-described embodiment in that it further includes an external information acquisition unit 31, an external information comparison unit 32, an external information similarity calculation unit 33, a data block reference information extraction unit 34, and a data block reference information similarity calculation unit 35. In addition, it is different from the above-described embodiment in that a content relevance database, an external information similarity calculation database, and a data block reference information similarity estimation processing database are also stored in the storage unit 104. Hereinafter, these differences will be mainly described. Figure 19 It is a schematic diagram showing a second modification example of the functions of the information providing device 1 in the present embodiment. In addition, the CPU 101 uses the RAM 103 as a work area to execute the programs stored in the storage unit 104 and the like, thereby implementing Figure 19 the various functions shown. In addition, each function can also be controlled by artificial intelligence, for example. Here, "artificial intelligence" can be based on any well-known artificial intelligence technology.

[0182] Figure 20It is a schematic diagram showing a second modified example of the information providing system 100 in the present embodiment. In this modified example, the information providing device 1 acquires specific external information x. The information providing device 1 calculates the external information similarity corresponding to the acquired specific external information x. The information providing device 1 selects the first external information b1 from a plurality of external information according to the calculated external information similarity. The information providing device 1 refers to the content relevance database and extracts the data block reference information B1 corresponding to the selected first external information b1 as the first data block reference information B1. Thus, it is possible to grasp the situation of the data block reference information B1 corresponding to the external information b1 similar to the acquired specific external information x being the changed part based on the specific external information x. Therefore, when updating the reference information such as editing, it is only necessary to update the first data block reference information B1, and the reference information update operation can be performed in a shorter time.

[0183] In addition, the information providing device 1 refers to the database for estimating data block reference information similarity and calculates the data block reference information similarity corresponding to the first data block reference information B1. The information providing device 1 extracts the second data block reference information B2 different from the first data block reference information B1 according to the calculated data block reference information similarity. Thus, it is possible to grasp the situation of the second data block reference information B2 similar to the first data block reference information B1 being the changed part based on the specific external information x. Therefore, when updating the reference information such as editing, it is only necessary to update the first data block reference information and the second data block reference information, and the reference information update operation can be performed in a shorter time.

[0184] <Content relevance database>

[0185] Figure 21 It is a schematic diagram showing an example of the content relevance database. The content relevance database stores a plurality of data block reference information obtained by dividing the reference information into a data block structure, and the external information used to generate the data block reference information.

[0186] The data block reference information includes sentence information. The data block reference information may also include chart information. The data block reference information may include a data block reference information label composed of a string for identifying the data block reference information. For example, when the reference information is a user manual of a medical device, the data block reference information is the information obtained by dividing the user manual according to the data block structure, and the data block structure is a block of data assembled from meaningful information. The data block reference information is, for example, the information obtained by dividing according to the data block structure such as each sentence, each chapter, each paragraph, each page, etc. of the user manual.

[0187] The external information includes sentence information. The external information may also include diagram information. The external information may also include external information tags composed of strings for identifying the external information. The external information and the data block reference information are stored in the content relevance database in a one-to-one correspondence. For example, in the case where the reference information is a user manual of a device such as an instrument device, the external information is the information obtained by dividing the design specification for generating the user manual according to the data block structure, and the data block structure is a block of aggregated data. The external information is, for example, the information obtained by dividing according to the data block structure such as each sentence, each chapter, each paragraph, each page, etc. of the design specification. As the information for generating the reference information, in addition to the information obtained by dividing the design specification into a data block structure, for example, it may also be event information, various papers, information obtained by dividing the information that is the original text of the reference information, etc. into a data block structure. In addition, when the data block reference information is generated in a first language such as Japanese, the external information may be generated in a second language such as English different from the first language.

[0188] Figure 22A It is a schematic diagram showing an example of the content relevance database. Figure 22B It is a schematic diagram showing an example of the database for calculating the similarity of external information. Figure 22A The "A" in Figure 22B is connected to the "A" in Figure 22A The "B" in Figure 22B is connected to the "B" in Figure 23A It is a schematic diagram showing an example of the content relevance database. Figure 23B It is a schematic diagram showing an example of the database for calculating the similarity of data block reference information. Figure 23A The "C" in Figure 23B is connected to the "C" in

[0189] <Database for calculating the similarity of external information>

[0190] The database for calculating the similarity of external information is constructed by machine learning using external information. As a method of machine learning, for example, after vectorizing the external information, it is used as teacher data for learning. The vectorized external information is stored in the database for calculating the similarity of external information corresponding to the external information tags in the external information. The vectorized external information may also be stored in the database for calculating the similarity of external information corresponding to the external information.

[0191] <Database for estimating the similarity of data block reference information processing>

[0192] The database for estimating the similarity of data block reference information is constructed by machine learning using the data block reference information. As a machine learning method, for example, after vectorizing the data block reference information, it is used as teacher data for learning. The vectorized data block reference information is stored in the database for estimating the similarity of data block reference information corresponding to the data block reference information tags in the data block reference information. The vectorized data block reference information may also be stored in the database for estimating the similarity of data block reference information corresponding to the data block reference information.

[0193] <External information acquisition unit 31>

[0194] The external information acquisition unit 31 acquires various information such as external information and specific external information. The specific external information is the external information that should be the object for calculating the external information similarity later.

[0195] <External information comparison unit 32>

[0196] The external information comparison unit 32 compares the external information stored in the content relevance database with the specific external information acquired by the external information acquisition unit 31. The external information comparison unit 32 determines whether the external information and the specific external information are the same or different.

[0197] In Figure 22A and Figure 22B example, assume that the specific external information acquired by the external information acquisition unit 31 includes "External information x", "External information a1", and "External information c1". Moreover, the external information comparison unit 32 compares "External information x", "External information a1", and "External information c1" included in the specific external information with the external information stored in the content relevance database. Assume that "External information a1" and "External information c1" are stored in the content relevance database, and "External information x" is not stored. At this time, the external information comparison unit 32 determines that "External information a1" and "External information c1" included in the specific external information are the same as the external information stored in the content relevance database. In addition, the external information comparison unit 32 determines that "External information x" is different from the external information stored in the content relevance database.

[0198] <External information similarity calculation unit 33>

[0199] When the external information comparison unit 32 determines that the external information and specific external information do not match, the external information similarity calculation unit 33 refers to the external information similarity calculation database and calculates the external information similarity indicating the similarity between the external information stored in the external information similarity calculation database and the specific external information obtained by the external information acquisition unit 31. The external information similarity calculation unit 33 calculates the external information similarity using the feature quantity of the external information. As the feature quantity of the external information, for example, the external information can be vectorized for representation. After vectorizing the specific external information, the external information similarity calculation unit 33 calculates the external information similarity between the specific external information and the external information by performing vector operations on the vectorized specific external information and the vectorized external information in the external information similarity calculation database.

[0200] In addition, when the external information comparison unit 32 determines that the external information and specific external information match, the external information similarity calculation unit 33 does not calculate the external information similarity.

[0201] The external information similarity indicates the degree of similarity between the specific external information and the external information, and is represented, for example, by a decimal number, a percentage, a 10-level or 5-level, etc. with 100 levels between 0 and 1 such as "0.97".

[0202] In Figure 22A and Figure 22B example, the external information comparison unit 32 determines that the "external information x" included in the specific external information does not match the external information stored in the content relevance database. In this case, the external information similarity calculation unit 33 refers to the external information similarity calculation database and calculates the external information similarity between the "external information x" included in the specific external information and the "external information a1", "external information b1", "external information c1", and "external information b2" stored in the external information similarity calculation database respectively. Regarding the external information similarity between "external information x" and "external information a1", by calculating the inner product of the feature quantity q2 of "external information x" and the feature quantity p1 of "external information a1", it is calculated as "0.20", for example. Similarly, the external information similarity between "external information x" and "external information b1" is "0.98". The external information similarity between "external information x" and "external information c1" is "0.33". The external information similarity between "external information x" and "external information b2" is "0.85". In this case, "external information x" shows, for example, a situation where it is more similar to "external information b1" than to "external information a1".

[0203] <Data block reference information extraction unit 34>

[0204] Based on the calculated external information similarity, the data block reference information extraction unit 34 selects the first external information from multiple external information, refers to the content relevance database, and extracts the data block reference information corresponding to the selected first external information as the first data block reference information. When the data block reference information extraction unit 34 selects one first external information from multiple external information, it extracts one data block reference information corresponding to the selected one first external information as the first data block reference information. In addition, when multiple first external information are selected, the data block reference information extraction unit 34 can extract the data block reference information corresponding to each of the selected first external information as the first data block reference information respectively.

[0205] The data block reference information extraction unit 34 can select from each external information tag included in multiple external information as the first external information according to the calculated external information similarity. The data block reference information extraction unit 34 can extract the data block reference information stored in the content relevance database corresponding to the external information tag as the first data block reference information according to the selected external information tag (the first external information). For example, the data block reference information extraction unit 34 can also select the external information tag 21, and extract the data block reference information B1 stored in the content relevance database corresponding to the external information tag 21 as the first data block reference information according to the selected external information tag 21. Since the external information tag is composed of a string, compared with storing external information including sentence information, the capacity of the database for calculating external information similarity can be reduced.

[0206] In Figure 22A and Figure 22B In the example of, the result of the data block reference information extraction unit 34 calculating the external information similarity is that among "external information a1", "external information b1", "external information c1", and "external information b2", the external information similarity of "external information b1" is the highest, and this "external information b1" is selected as the first external information. When selecting the first external information, a threshold can also be set for the external information similarity, and the external information with an external information similarity calculated above or below the threshold can be selected as the first external information. This threshold can be appropriately set on the user side.

[0207] Then, the data block reference information extraction unit 34 refers to the content relevance database and extracts "data block reference information B1" corresponding to the "external information b1" selected as the first external information as the first data block reference information.

[0208] Furthermore, the data block reference information extraction unit 34 also extracts one or more second data block reference information different from the first data block reference information from the content relevance database according to the data block reference information similarity described later.

[0209] The data block reference information extraction unit 34 may also select one or more data block reference information labels from the data block reference information labels included in the plurality of data block reference information according to the calculated data block reference information similarity. The data block reference information extraction unit 34 may also extract, as the second data block reference information, the data block reference information stored in the content relevance database corresponding to the selected data block reference information label according to the selected data block reference information label. For example, the data block reference information extraction unit 34 may select the data block reference information label 122 and extract, as the second data block reference information, the data block reference information B2 stored in the content relevance database corresponding to the data block reference information label 122 according to the selected external information label 122. Since the data block reference information label is composed of a character string, the capacity of the database for calculating the data block reference information similarity can be reduced compared with storing the data block reference information including sentence information.

[0210] <Data block reference information similarity calculation unit 35>

[0211] The data block reference information similarity calculation unit 35 refers to the database for data block reference information similarity estimation processing and calculates the data block reference information similarity indicating the similarity between the data block reference information and the first data block reference information extracted by the data block reference information extraction unit 34. The data block reference information similarity calculation unit 35 calculates the data block reference information similarity using the feature amount of the data block reference information. As the feature amount of the data block reference information, for example, the data block reference information can be vectorized for representation. After vectorizing a specific data block reference information, the data block reference information similarity calculation unit 35 calculates the data block reference information similarity between the specific data block reference information and the data block reference information by performing vector operations on the vectorized specific data block reference information and the data block reference information vectorized in the database for data block reference information similarity estimation processing.

[0212] The data block reference information similarity indicates the degree of similarity between the first data block reference information and the data block reference information, and is represented, for example, by a decimal number, a percentage, or a grade of 100 levels from 0 to 1 such as "0.97", or a grade of three levels or more such as 10 levels or 5 levels.

[0213] In Figure 23A and Figure 23BIn the example, the data block reference information similarity calculation unit 35 refers to the database for calculating data block reference information similarity, and calculates the data block reference information similarities between the "data block reference information B1" extracted by the data block reference information extraction unit 34 as the first data block reference information and the "data block reference information A1", "data block reference information B1", "data block reference information C1", and "data block reference information B2" stored in the database for calculating data block reference information similarity, respectively. Regarding the data block reference information similarity between the "data block reference information B1" and the "data block reference information A1", the inner product of the "feature quantity Q1 of the data block reference information B1" and the "feature quantity P1 of the data block reference information A1" is calculated, for example, as "0.30". Similarly, the data block reference information similarity between the "data block reference information B1" and the "data block reference information B1" is "1.00". The data block reference information similarity between the "data block reference information B1" and the "data block reference information C1" is "0.20". The data block reference information similarity between the "data block reference information B1" and the "data block reference information B2" is "0.95". In this case, the "data block reference information B1" shows, for example, a situation that is more similar to the "data block reference information B2" than to the "data block reference information A1".

[0214] As described above, the data block reference information extraction unit 34 further extracts one or more second data block reference information different from the first data block reference information according to the data block reference information similarity.

[0215] In Figure 23A and Figure 23B In the example, the data block reference information extraction unit 34 extracts the "data block reference information B2" that calculates a specified data block reference information similarity as the second data block reference information from the "data block reference information A1", "data block reference information B1", "data block reference information C1", and "data block reference information B2" according to the result of calculating the data block reference information similarity. When selecting the second data block reference information, a threshold value can also be set for the data block reference information similarity, and the data block reference information with an external information similarity calculated above or below the threshold value can be selected. This threshold value can be appropriately set on the user side. In addition, regarding the data block reference information with a calculated data block reference information similarity of "1.00", since it is the same as the first data block reference information, it can be not selected as the second data block reference information.

[0216] (Second Variation of the Operation of the Information Providing System 100)

[0217] Next, a second variation of the operation of the information providing system 100 in the present embodiment will be described. Figure 24It is a flowchart showing a second modified example of the operation of the information providing system 100 in the present embodiment.

[0218] <External information acquisition step S31>

[0219] The external information acquisition unit 31 acquires, for example, one or more pieces of external information obtained by dividing a design specification or the like into a data block structure as specific external information (external information acquisition step S31). The external information acquisition step S31 is performed after the reference information selection step S14.

[0220] <External information comparison step S32>

[0221] Next, the external information comparison unit 32 compares the external information stored in the content relevance database with the specific external information acquired by the external information acquisition unit 31 (external information comparison step S32). The external information comparison unit 32 determines whether the external information and the specific external information are the same or different.

[0222] <External information similarity calculation step S33>

[0223] Next, when the external information comparison unit 32 determines that the external information and the specific external information are different, the external information similarity calculation unit 33 refers to the external information similarity calculation database and calculates an external information similarity indicating the similarity between the external information stored in the external information similarity calculation database and the specific external information acquired by the external information acquisition unit 31. (External information similarity calculation step S33).

[0224] <First data block reference information extraction step S34>

[0225] The data block reference information extraction unit 34 selects the first external information from the plurality of external information according to the calculated external information similarity, and refers to the content relevance database to extract the data block reference information corresponding to the selected first external information as the first data block reference information. (First data block reference information extraction step S34).

[0226] <Data block reference information similarity calculation step S35>

[0227] Next, the data block reference information similarity calculation unit 35 refers to the data block reference information similarity estimation processing database and calculates a data block reference information similarity indicating the similarity between the data block reference information stored in the data block reference information similarity estimation processing database and the first data block reference information extracted by the data block reference information extraction unit 34 (data block reference information similarity calculation step S35).

[0228] <Second data block reference information extraction step S36>

[0229] Next, the data block reference information extraction unit 34 further extracts one or more second data block reference information different from the first data block reference information based on the data block reference information similarity (second data block reference information extraction step S36).

[0230] As described above, the second modification of the operation of the information providing system 100 ends.

[0231] According to the present embodiment, there are provided: a content relevance database that stores a plurality of data block reference information obtained by dividing reference information into a data block structure, and external information corresponding to each data block reference information and used for generating the data block reference information; an external information similarity calculation database that is constructed by machine learning using a plurality of external information; an external information acquisition unit 31 that acquires specific external information; an external information comparison unit that compares the external information with the specific external information; an external information similarity calculation unit 33 that, when it is determined by the external information comparison unit 32 that the external information and the specific external information do not match, refers to the external information similarity calculation database and calculates an external information similarity indicating the similarity between the external information and the specific external information; and a data block reference information extraction unit 34 that selects first external information from a plurality of external information based on the external information similarity, and refers to the content relevance database to extract data block reference information corresponding to the first external information as the first data block reference information.

[0232] According to the present embodiment, the external information similarity calculation unit 33 calculates the external information similarity for specific external information determined by the external information comparison unit 32 to be inconsistent with the external information stored in the content relevance database. That is, for specific external information determined by the external information comparison unit 32 to be consistent with the external information stored in the content relevance database, it is not necessary to calculate the external information similarity. Therefore, the external information similarity can be calculated more efficiently.

[0233] In particular, according to the present embodiment, the first external information is selected from a plurality of external information based on the external information similarity, and the data block reference information corresponding to the first external information is extracted from the content relevance database as the first data block reference information. Thus, by selecting the first external information similar to the specific external information based on the quantitatively evaluated external information similarity, the accuracy of the selection of the first external information can be improved.

[0234] In particular, according to the present embodiment, data block reference information corresponding to the first external information is extracted as the first data block reference information with reference to the content relevance database. Therefore, when new information is included in or there are changes in specific external information, the user can immediately grasp which part of the reference information corresponds to the data block reference information after segmentation. Therefore, when updating the reference information, it is only necessary to update the data block reference information extracted as the first data block reference information, and the reference information update operation can be performed in a short time.

[0235] That is, when a certain device is upgraded from version 1 to version 2 and a part of the past design specification is changed to a new design specification, the past user manual of the product generated based on the past design specification also needs to be generated as a new user manual. According to the present embodiment, the past design specification selected as a candidate for change is selected from the new design specification, and the situation where the past user manual corresponding to the past design specification needs to be changed due to the new design specification can be grasped. At this time, the new design specification, the past design specification, and the past user manual are each divided into a data block structure. Therefore, it is possible to efficiently extract only the parts of the past user manual that have changed due to the new design specification. Therefore, the user can easily grasp the corresponding parts of the past user manual that should be changed according to the new design specification. Thus, for example, when generating a new user manual, for the parts of the design specification that have not been changed, the past user manual is directly used, and only the parts of the design specification that have changed need to be regenerated. In other words, only the parts of the design specification that have changed need to be separately edited. Therefore, the editing operation of the user manual can be easily performed.

[0236] In addition, according to the present embodiment, there are provided: a database for estimating the similarity of data block reference information, which is constructed by machine learning using a plurality of data block reference information; and a data block reference information similarity calculation unit 35, which refers to the database for estimating the similarity of data block reference information and calculates a data block reference information similarity indicating the similarity between the data block reference information and the first data block reference information. The data block reference information extraction unit 34 further extracts a second data block reference information different from the first data block reference information based on the data block reference information similarity.

[0237] According to the present embodiment, the second data block reference information different from the first data block reference information is further extracted based on the similarity of the data block reference information. Thus, by selecting the second data block reference information similar to the first data block reference information based on the similarity of the data block reference information obtained by quantitatively evaluating, the accuracy of the selection of the second data block reference information can be improved. Therefore, in the case where new information is included in the specific external information or there is a change, since the second data block reference information similar to the first data block reference information is also extracted, the user can immediately grasp which part of the reference information corresponds to the divided data block reference information. Therefore, when updating the reference information, it is only necessary to update the data block reference information extracted as the first data block reference information and the second data block reference information, and the reference information update operation can be performed in a short time.

[0238] That is, when a certain device has multiple versions and a part of it is changed from multiple past design specifications to become a new design specification, each past user manual generated based on the multiple past design specifications of the product also needs to be generated as a new user manual. According to the present embodiment, by selecting the past design specification that is a candidate for change from the new design specification, it is possible to grasp the situation where the past user manual corresponding to the past design specification and other past user manuals similar to the past user manual need to be changed due to the new design specification. At this time, the new design specification, the past design specification, and the past user manual are each divided into a data block structure. Therefore, it is possible to efficiently extract only the parts that have changed due to the new design specification from the past user manual. At this time, multiple similar past user manuals can be extracted as objects. Therefore, the user can easily grasp the corresponding parts of the multiple past user manuals that should be changed according to the new design specification at the same time. Thus, for example, when generating a new user manual, the parts in the design specification that have not changed are directly adopted from the past user manual, and only the parts in the design specification that have changed need to be generated. In other words, it is only necessary to perform differential editing on the parts in the design specification that have changed. Therefore, the editing operation of the user manual can be easily performed.

[0239] According to the present embodiment, the external information acquisition step S31 is performed after the reference information selection step S14. Thus, the user can compare the first reference information selected by the reference information selection unit 14, and the first data block reference information and the second data block reference information extracted by the data block reference information extraction unit 34. Therefore, it is possible to immediately grasp the corresponding part that should be changed in the first reference information such as the user manual.

[0240] <The third modification example of the information providing device 1>

[0241] In the third modification example of the information providing apparatus 1, there are an external information acquisition unit 31, an external information comparison unit 32, an external information similarity calculation unit 33, a data block reference information extraction unit 34, and a data block reference information similarity calculation unit 35. Further, a content relevance database, an external information similarity calculation use database, and a data block reference information similarity estimation process use database are also stored in the storage unit 104.

[0242] Figure 25 FIG. 4 is a flowchart showing a third modification example of the operation of the information providing system 100 in the present embodiment. In the second modification example, an example in which the external information acquisition step S31 is performed after the reference information selection step S14 has been described. In the third modification example, the reference information selection step S14 may be omitted, and the external information acquisition step S31, the external information comparison step S32, the external information similarity calculation step S33, the first data block reference information extraction step S34, the data block reference information similarity calculation step S35, and the second data block reference information extraction step S36 may be performed.

[0243] <Fourth Modification Example of Information Providing Apparatus 1>

[0244] In the fourth modification example of the information providing apparatus 1, it is different from the second and third modification examples in that it further has an access control unit. For example, the CPU 101 implements the access control unit by executing programs stored in the storage unit 104 and the like using the RAM 103 as a work area.

[0245] The access control unit controls access to the data block reference information. The access includes full access, read access, write access, proofreading-only access, annotation-only access, read-only access, and access prohibition. The access control unit performs control according to the access control information. The access control information includes a user name and an access method assigned to each user name. The access control information is stored, for example, in the storage unit 104.

[0246] When a user is assigned the full access method, the user has full read and write access rights to the data block reference information, and furthermore, the user can use any method of the user interface. For example, in the case of full access, the user can change the format of the data block reference information. When the user has read and write access rights, the user has read and write rights to the data block reference information, but cannot change the format. In the case of proofreading-only access, the user can change the traced data block reference information. In the case of annotation-only access, the user can insert an annotation into the data block reference information, but cannot change the sentence information located in the data block reference information. In the case of read-only access, the user can view the data block reference information, but cannot make any changes to the data block reference information or insert any annotations.

[0247] For example, it is assumed that new data block reference information is generated based on external information, and the generated new data block reference information is updated. At this time, according to the present embodiment, there is also an access control unit. Thus, one or more specific users among multiple users can perform specified access according to the access control information. That is, for multiple users who use the data block reference information, it is possible to associate the control of editing categories such as read-only and full access with the permissions based on user attributes, and manage them for each data block reference information. In particular, by setting the case of only viewing to also be able to perform access, and only permitting users with permissions to perform editing such as writing, unintended editing can be prevented.

[0248] The embodiments of the present invention have been described, but the embodiments are shown as examples and are not intended to limit the scope of the invention. These new embodiments can be implemented in various other ways, and various omissions, substitutions, and changes can be made without departing from the gist of the invention. These embodiments and their modifications are included in the scope and gist of the invention, and are included in the invention described in the claims and its equivalents.

[0249] Reference Signs Explanation

[0250] 1: Information providing device;

[0251] 4: Medical device;

[0252] 5: User terminal;

[0253] 6: Server;

[0254] 7: Public communication network;

[0255] 10: Housing;

[0256] 11: Acquisition unit;

[0257] 12: Meta ID selection unit;

[0258] 13: Content ID selection unit;

[0259] 14: Reference information selection unit;

[0260] 15: Input unit;

[0261] 16: Output unit;

[0262] 17: Storage unit;

[0263] 18: Control unit;

[0264] 21: First acquisition unit;

[0265] 22: First evaluation unit;

[0266] 23: First generation unit;

[0267] 31: External information acquisition unit;

[0268] 32: External information comparison unit;

[0269] 33: External information similarity calculation unit;

[0270] 34: Data block reference information extraction unit;

[0271] 35: Data block reference information similarity calculation unit;

[0272] 100: Information providing system;

[0273] 101: CPU;

[0274] 102: ROM;

[0275] 103: RAM;

[0276] 104: Storage unit;

[0277] 105: I / F;

[0278] 106: I / F;

[0279] 107: I / F;

[0280] 108: Input part;

[0281] 109: Output part;

[0282] 110: Internal bus;

[0283] S11: Acquisition step;

[0284] S12: Meta ID selection step;

[0285] S13: Content ID selection step;

[0286] S14: Reference information selection step;

[0287] S21: First acquisition step;

[0288] S22: First evaluation step;

[0289] S23: First generation step;

[0290] S24: Acquisition step;

[0291] S25: Meta ID selection step;

[0292] S26: Content ID selection step;

[0293] S31: External information acquisition step;

[0294] S32: External information comparison step;

[0295] S33: External information similarity calculation step;

[0296] S34: First data block reference information extraction step;

[0297] S35: Data block reference information similarity calculation step;

[0298] S36: Second data block reference information extraction step.

Claims

1. An information providing system, characterized in that, the information providing system has: a content relevance database that stores a plurality of data block reference information obtained by dividing reference information into a data block structure, and external information corresponding to each data block reference information and used for generating the data block reference information; an external information similarity calculation database that is constructed by machine learning using a plurality of external information; an external information acquisition unit that acquires specific external information; an external information comparison unit that compares external information with the specific external information; an external information similarity calculation unit that, when it is determined by the external information comparison unit that the external information is inconsistent with the specific external information, refers to the external information similarity calculation database and calculates an external information similarity representing the similarity between the external information and the specific external information; and a data block reference information extraction unit that selects first external information from a plurality of the external information according to the external information similarity, and refers to the content relevance database to extract data block reference information corresponding to the first external information as first data block reference information, the external information similarity calculation unit calculates an external information similarity for specific external information determined by the external information comparison unit to be inconsistent with the external information stored in the content relevance database.

2. The information providing system according to claim 1, characterized in that, the information providing system has: a data block reference information similarity estimation processing database that is constructed by machine learning using a plurality of data block reference information; and a data block reference information similarity calculation unit that refers to the data block reference information similarity estimation processing database and calculates a data block reference information similarity representing the similarity between the data block reference information and the first data block reference information, the data block reference information extraction unit further extracts second data block reference information different from the first data block reference information according to the data block reference information similarity.

3. The information providing system according to claim 1 or 2, characterized in that, the data block reference information extraction unit further extracts second data block reference information different from the first data block reference information according to the data block reference information similarity.

4. The information providing system according to claim 1, characterized in that, the information providing system further has an access control unit that controls access to the data block reference information, the access control unit refers to access control information including a user name and access assigned to each user name, and performs full access, read access, write access, review-only access, annotation-only access, read-only access, and access prohibition on the data block reference information.

5. The information providing system according to claim 4, characterized in that, the access control unit generates new data block reference information based on the external information, and based on the generated new data block reference information, specific one or more users among a plurality of users perform specified access.

Images