Knowledge presentation system and knowledge presentation method

Abstract

This knowledge presentation system 100 manages object basic information in which coordinate information of an object in a virtual space and basic information related to an attribute of the object are associated with each other. The knowledge presentation system 100 accepts a user's selection of an object, and acquires the basic information related to the object by referring to the object basic information on the basis of the coordinate information of the accepted selection of the object. The knowledge presentation system 100 converts each of the acquired basic information and knowledge to a feature quantity vector, and calculates a first relevance degree between the feature quantity vector obtained by converting the basic information and the feature quantity vector obtained by converting the knowledge. The knowledge presentation system 100 presents a list of knowledge with the first relevance degree equal to or greater than a predetermined value to the user via an output device.

Description

Knowledge presentation system and knowledge presentation method

[0001] The present invention relates to a knowledge presentation system and a knowledge presentation method.

[0002] The metaverse has traditionally been known as a communication tool between users, but in recent years, attempts have been made to utilize it in the industrial field. Examples of ways in which the metaverse can be utilized in the industrial field include data aggregation and visualization in combination with IoT, processing of collected data using AI, and sharing and presentation of knowledge. For example, Patent Literature 1 discloses a method for presenting content to users regarding the sharing and presentation of knowledge.

[0003] Japanese Patent Application Laid-Open No. 2021-86146

[0004] However, the above-mentioned conventional technology merely converts the movements and state changes of objects in virtual space into simple linguistic expressions at the word level according to predetermined rules and displays content to which the converted linguistic expressions are added. In other words, it is not possible to share or present the large amount of knowledge accumulated about objects in virtual space.

[0005] The present invention has been made in view of the above-mentioned problems, and has as its object to make it possible to share and present a large amount of accumulated knowledge about objects in a virtual space.

[0006] In order to achieve the above-mentioned object, one aspect of the present invention is a knowledge presentation system that presents knowledge related to objects placed in a virtual space, the knowledge presentation system having a processor and a memory, wherein the processor manages documents related to the objects as knowledge, manages object basic information that associates coordinate information of the objects in the virtual space with basic information related to attributes of the objects, accepts selection of the objects by a user, acquires the basic information related to the objects by referring to the object basic information based on the coordinate information of the objects whose selection has been accepted, converts the acquired basic information and the knowledge into feature vectors, calculates a first degree of relevance between the feature vector obtained by converting the basic information and the feature vector obtained by converting the knowledge, and presents to the user via an output device a list of the knowledge whose first degree of relevance is equal to or greater than a predetermined value.

[0007] According to the present invention, for example, a large amount of accumulated knowledge about objects in a virtual space can be shared and presented.

[0008] A diagram showing the configuration of a knowledge presentation system according to an embodiment. A diagram showing the configuration of work phase KPI tree data. A diagram showing the configuration of a 3D object data table. A diagram showing the configuration of a railway vehicle metaverse GUI. A flowchart showing knowledge acquisition processing according to an embodiment. A flowchart showing knowledge presentation processing according to an embodiment. A diagram showing presentation of knowledge candidates in the railway vehicle metaverse GUI. A diagram showing the configuration of computer hardware.

[0009] Hereinafter, embodiments of the present invention will be described with reference to the drawings. The embodiments are examples for explaining the present invention, and appropriate omissions and simplifications have been made for clarity of explanation. The present invention can be implemented in various other forms. Unless otherwise specified, each component may be singular or plural. The position, size, shape, range, etc. of each component shown in the drawings may not represent the actual position, size, shape, range, etc., in order to facilitate understanding of the invention. Therefore, the present invention is not necessarily limited to the position, size, shape, range, etc. disclosed in the drawings.

[0010] Examples of various types of information may be described using expressions such as "table," "list," "queue," and "database," but the various types of information may also be expressed using data structures other than these. For example, various types of information such as "XX table," "XX list," and "XX queue" may also be expressed as "XX information." When describing identification information, expressions such as "identification information," "identifier," "name," "ID," and "number" are used, but these are interchangeable.

[0011] When there are multiple components with the same or similar functions, they may be described using the same reference numeral with different subscripts. When there is no need to distinguish between these multiple components, the subscripts may be omitted.

[0012] The processing performed by executing a program may be described with the program as the subject. Here, a computer executes the program using a processor (e.g., a CPU (Central Processing Unit), a GPU (Graphics Processing Unit)), and performs the processing defined by the program using storage resources (e.g., memory) and interface devices (e.g., communication ports). Therefore, the subject of the processing performed by executing a program may be the processor.

[0013] Similarly, the entity that executes the program and performs the processing may be a controller, device, system, computer, or node having a processor. The entity that executes the program and performs the processing may be any computing unit, and may include a dedicated circuit that performs specific processing. Here, the dedicated circuit is, for example, an FPGA (Field Programmable Gate Array), an ASIC (Application Specific Integrated Circuit), or a CPLD (Complex Programmable Logic Device).

[0014] A program may be installed on a computer from a program source. The program source may be, for example, a program distribution server or a computer-readable storage medium. When the program source is a program distribution server, the program distribution server may include a processor and storage resources for storing the program to be distributed, and the processor of the program distribution server may distribute the program to be distributed to other computers. In addition, in an embodiment, two or more programs may be realized as one program, or one program may be realized as two or more programs.

[0015] In the following embodiment, an example will be described in which the virtual space is a metaverse configured to include 3D objects of railway vehicles, and when a user selects an object of railway vehicle equipment in the metaverse, knowledge candidates related to the equipment are presented to the user. The virtual space is not limited to a space configured to include the interior and exterior of a railway vehicle, and may be any space. Furthermore, the virtual space is not limited to a three-dimensional space, and may be a two-dimensional plane or a one-dimensional line.

[0016] 1 is a diagram showing the configuration of a knowledge presentation system 100 according to an embodiment. The knowledge presentation system 100 includes a user interface unit 101 and a controller unit 102.

[0017] The user interface unit 101 is composed of an input device and a display device for the user to operate the system. Here, a keyboard and a mouse are assumed as the input devices, but the input device may also be a microphone for voice input, etc. Furthermore, here, a display is assumed as the display device, but it may also be a head-mounted display, etc. The same number of user interface units 101 are prepared as the number of users participating in the metaverse controlled by the knowledge presentation system 100, and the same metaverse and related information are shared with each user.

[0018] The controller unit 102 processes input from the user interface unit 101 and controls display on the user interface unit 101. The controller unit 102 has functions similar to those of a personal computer. The controller unit 102 is equipped with components necessary for operating each unit, such as basic hardware such as a CPU, memory, communication devices, power supply, and wiring, as well as basic software such as an OS, various firmware, and drivers for controlling these components.

[0019] The controller unit 102 includes a work phase selection unit 103, a work phase KPI acquisition unit 104, a work phase KPI feature quantity vector conversion unit 105, a knowledge feature quantity vector acquisition unit 106, and a knowledge-work phase KPI relevance calculation unit 107. The controller unit 102 also includes a 3D object selection unit 108, a 3D object basic information acquisition unit 109, a basic information feature quantity vector conversion unit 110, a knowledge-3D object relevance calculation unit 111, and an overall relevance calculation unit 112. The controller unit 102 also includes a knowledge presentation candidate list calculation unit 113, a knowledge candidate presentation unit 114, a knowledge update determination unit 115, a knowledge acquisition unit 116, and a knowledge feature quantity vector conversion unit 117. The controller unit 102 also includes knowledge 118, work phase KPI tree information 119, and 3D object basic information 120. The knowledge 118, the work phase KPI tree information 119, and the 3D object basic information 120 are stored in a predetermined recording area such as a storage.

[0020] The work phase selection unit 103 acquires the results of work phase selection for railway vehicle maintenance work via the user interface unit 101. The work phase KPI acquisition unit 104 acquires, from the work phase KPI tree information 119, KPIs (Key Performance Indicators) or keywords (work phase KPI data) associated with the selected work phase.

[0021] The work phase KPI feature vector conversion unit 105 converts the work phase KPI data acquired by the work phase KPI acquisition unit 104 into feature vectors. The knowledge feature vector acquisition unit 106 acquires feature vectors of knowledge 118. The knowledge-work phase KPI relevance calculation unit 107 calculates the relevance between each of the acquired feature vectors of all knowledge 118 and the feature vector of the work phase KPI data.

[0022] The 3D object selection unit 108 detects the selection of a 3D object by the user in the metaverse space and records the name of the selected 3D object. While various methods for selecting a 3D object are conceivable, it is assumed here that the 3D object of a railcar and its equipment presented on the display is selected by clicking with a mouse. Alternatively, a pointing device linked to a head-mounted display or a touch panel may be used.

[0023] The 3D object basic information acquisition unit 109 acquires basic information corresponding to the selected 3D object from the 3D object basic information 120. The basic information feature vector conversion unit 110 converts the basic information acquired by the 3D object basic information acquisition unit 109 into a feature vector. The knowledge-3D object relevance calculation unit 111 calculates the relevance between each of the feature vectors of all acquired knowledge 180 and the feature vector of the basic information.

[0024] The overall relevance calculation unit 112 calculates the overall relevance between the work phase selected for each knowledge and the 3D object based on the relevance obtained by the knowledge / work phase KPI relevance calculation unit 107 and the knowledge / 3D object relevance calculation unit 111.

[0025] The knowledge presentation candidate list calculation unit 113 uses the overall relevance of each piece of knowledge obtained by the overall relevance calculation unit 112 to narrow down the knowledge candidates to be presented, and creates a knowledge candidate list in which the knowledge candidates are listed.

[0026] The knowledge candidate presentation unit 114 controls the user interface unit 101 to present the knowledge candidate list created by the knowledge presentation candidate list calculation unit 113 to the user.

[0027] The knowledge update determination unit 115 determines whether or not there has been an update to the data of each piece of knowledge stored in the knowledge 118, such as whether or not the knowledge has been added, changed, or deleted. When there has been an update to each piece of knowledge stored in the knowledge 118, the knowledge acquisition unit 116 acquires the updated knowledge.

[0028] The knowledge feature vector conversion unit 117 converts into a feature vector each piece of updated knowledge acquired by the knowledge acquisition unit 116. In this embodiment, the knowledge 118 refers to documents related to the maintenance of railway vehicles, and is assumed to be data in the form of a file, database, or the like.

[0029] The work phase KPI tree information 119 (FIG. 2) relating to the KPIs for each work phase and the relationships between the KPIs is stored in the work phase KPI tree information 119. The 3D object basic information 120 (FIG. 3) including information such as the model number, specifications, classification, and placement location of the 3D object is stored in the work phase KPI tree information 119.

[0030] (Configuration of Work Phase KPI Tree Information 119) Fig. 2 is a diagram showing the configuration of the work phase KPI tree information 119. The work phase KPI tree information 119 is an example of keyword information.

[0031] The work phase KPI tree information 119 is data in which KPIs or keywords related to work for each work phase of work performed on a railway vehicle are listed to form tree data based on a hierarchical relationship.

[0032] For example, in the example of Figure 2, the work phases include, in order of execution, "Installation of air conditioning," "Confirmation of air conditioning operation," and "Confirmation of operation of interior equipment." KPIs or keywords for the work phase "Installation of air conditioning" include "Installation of air conditioning duct" and "Installation of control board" under "Installation of air conditioning duct." Furthermore, under "Installation of air conditioning duct" are "Connector connection" and "Screw torque check."

[0033] In the example of Figure 2, the KPIs or keywords for the work phase "Check air conditioning operation" include "Air volume control accuracy" and "Temperature control accuracy" under "Check air conditioning operation." Also, under "Air volume control accuracy" is "Voltage and current of fan 1." Downstream of "Voltage and current of fan 1" is "Voltage and current of fan n." Under "Voltage and current of fan n" is "Installation of air conditioning." Also, under "Temperature control accuracy" are "Voltage and current of cooler 1 and heater 1." Downstream of "Voltage and current of cooler 1 and heater 1" is "Voltage and current of cooler m and heater m."

[0034] In the example of Figure 2, the KPIs or keywords for the work phase "Check the operation of on-board equipment" include "Check the operation of air conditioning," ... "Check the operation of display" under "Check the operation of on-board equipment."

[0035] A weighting coefficient may be assigned to the KPIs or keywords that make up each node on the work phase KPI tree information 119 shown in Fig. 2. For example, the weighting coefficient for each KPI or keyword may be set to a larger value the lower the KPI or keyword is in the work phase KPI tree information 119. When a KPI or keyword corresponding to a work phase is selected, the weighting coefficient may be adjusted by normalization or other means between the KPIs or keywords within the selected range.

[0036] (Configuration of 3D object basic information 120) Fig. 3 is a diagram showing the configuration of the 3D object basic information 120. The 3D object basic information 120 has columns for "coordinate information" and "basic information." The "basic information" further has items for 3D object attribute information, such as "3D object name," "model number," "specifications," "classification," and "location."

[0037] "Coordinate information" is the coordinates in the metaverse space where the facility or equipment represented by the 3D object identified by the "3D object name" is located.

[0038] "3D object name" is the name or identification information of the facility or equipment represented by the corresponding 3D object. "Model number" is the model number of the facility or equipment represented by the corresponding 3D object. "Specifications" is specification information including information about the material and design of the facility or equipment represented by the corresponding 3D object. "Classification" is classification information of the facility or equipment represented by the corresponding 3D object. "Location" indicates the location where the facility or equipment represented by the corresponding 3D object is installed on the railway vehicle.

[0039] (Configuration of Railroad Vehicle Metaverse GUI 101D) Fig. 4 is a diagram showing the configuration of the railroad vehicle metaverse GUI (Graphical User Interface) 101D. The railroad vehicle metaverse GUI 101D is a screen presented to the user via the user interface unit 101. The railroad vehicle metaverse GUI 101D has a metaverse space 401, a work phase selection operation unit 402, and a knowledge candidate presentation unit 403.

[0040] The metaverse space 401 represents a virtual space simulating the interior of a railcar, including 3D objects 404 of railcar equipment, and a space such as a garage that houses the railcar body. The work phase selection operation unit 402 is operated by the user when selecting a work phase. The knowledge candidate presentation unit 403 displays knowledge candidates related to the 3D object selected from the metaverse space 401 by the user.

[0041] 5 is a flowchart showing the knowledge acquisition process according to the embodiment. By the knowledge acquisition process, each piece of knowledge is converted into a feature vector, which is stored in the knowledge 118 and can be used in the knowledge presentation process (FIG. 6).

[0042] First, in step S501, the knowledge update determination unit 115 determines whether the knowledge 118 has been updated. An update to the knowledge 118 includes adding the knowledge 118, changing the content, deleting the knowledge 118, etc. The knowledge update determination unit 115 records reference information for each piece of updated knowledge in a list. If an update has been made (step S501: YES), the knowledge update determination unit 115 proceeds to step S502, and if no update has been made (step S501: NO), the knowledge update determination unit 115 proceeds to step S504.

[0043] In step S502, the knowledge acquisition unit 116 acquires the knowledge that was updated in step S510. Here, each piece of knowledge is acquired based on the reference information recorded in the list in step S501.

[0044] Next, in step S503, the knowledge feature vector conversion unit 117 converts the knowledge acquired in step S502 into a feature vector and stores the obtained feature vector in the knowledge 118. For example, text data such as railway vehicle maintenance work records and instructions is converted into numerical data corresponding to the feature vector and recorded.

[0045] Next, in step S504, the knowledge update determination unit 115 determines whether to terminate the knowledge acquisition process. If the knowledge acquisition process is to be terminated in response to a user instruction or the like (step S504 YES), the knowledge update determination unit 115 terminates the process. If the knowledge acquisition process is to be continued (step S504 NO), the knowledge update determination unit 115 proceeds to step S501 and continues detecting knowledge updates.

[0046] (Knowledge Presentation Process According to the Embodiment) Fig. 6 is a flowchart showing the knowledge presentation process according to the embodiment. The knowledge presentation process is executed in a state where the railcar metaverse GUI 101D is presented to the user.

[0047] First, in step S601, the work phase selection unit 103 detects the work phase selected by the work phase selection operation unit 402. Next, in step S602, the work phase selection unit 103 determines whether the work phase detected in step S601 has changed from the previously detected work phase. If the work phase has changed, the work phase selection unit 103 proceeds to step S603, and if the work phase has not changed, the work phase selection unit 103 proceeds to step S607.

[0048] In step S603, the work phase KPI acquisition unit 104 acquires corresponding work phase KPIs from the work phase KPI tree information 119 for the work phases detected in step S601 and determined to have been changed in step S602. The work phase KPI tree information 119 represents the relationships between KPIs for each work phase using a KPI tree structure. For example, as shown in FIG. 4, when "Checking Air Conditioner Operation" is selected as the work phase, work phase KPI data (data related to KPI names and tree structure) for the range corresponding to the work phase "Checking Air Conditioner Operation" in FIG. 2 is acquired.

[0049] Next, in step S604, the work phase KPI feature vector conversion unit 105 converts the work phase KPI data acquired in step S603 into a feature vector. For example, text data such as "air volume control accuracy" and "fan voltage and current" listed as work phase KPIs for "air conditioning operation check" in Fig. 2 is converted into numerical data corresponding to the feature vector and recorded.

[0050] Next, in step S605, the knowledge feature vector acquisition unit 106 acquires the feature vector of the knowledge 118. The feature vector of the knowledge 118 has already been converted by the knowledge acquisition process (FIG. 5).

[0051] Next, in step S606, the knowledge-work phase KPI relevance calculation unit 107 calculates the relevance between the work phase and the knowledge. Here, the relevance is calculated as the similarity between the feature vector of the work phase KPI data corresponding to the work phase acquired in step S604 and the feature vector of the knowledge 118 acquired in step S605. Such relevance is calculated and recorded for the work phase KPI data and all the knowledge 118.

[0052] Next, in step S607, the 3D object selection unit 108 selects a 3D object. In step S607, the selection of a 3D object by the user in the metaverse space is detected, and the name of the selected 3D object is recorded. For example, in the metaverse space 401 of a railcar as shown in FIG. 4 , the user clicks on an air conditioning duct with the mouse, thereby selecting the 3D object 404 of the air conditioning duct.

[0053] Next, in step S608, the 3D object selection unit 108 determines whether a 3D object has been selected in response to the selection operation in step S607. If the 3D object selection unit 108 determines that a 3D object has been selected (YES in step S608), the process proceeds to step S609, and if the 3D object selection unit 108 determines that a 3D object has not been selected (NO in step S608), the process returns to step S607.

[0054] In step S609, the 3D object basic information acquisition unit 109 acquires basic information. The basic information is data such as specifications corresponding to the 3D object, and is acquired from the 3D object basic information 120. The 3D object basic information 120 stores the basic information in a table format. The 3D object basic information acquisition unit 109 references the 3D object basic information 120 based on the coordinates of the 3D object and can acquire basic information including the name, model number, specifications, classification, and location of the facility or equipment represented by the 3D object in the interior space of the railway vehicle. For example, if an air conditioning duct is selected as the 3D object 404 as shown in FIG. 4, basic information corresponding to the "3D object name and coordinates" "air conditioning duct" is acquired from the 3D object basic information 120 in FIG. 3.

[0055] Next, in step S610, the basic information feature vector conversion unit 110 converts the basic information acquired in step S609 into a feature vector. For example, text data such as "Material: Aluminum" in Fig. 3 is converted into numerical data corresponding to the feature vector and recorded.

[0056] Next, in step S611, the knowledge-3D object relevance calculation unit 111 acquires a feature vector of the knowledge, similarly to step S605.

[0057] Next, in step S612, the knowledge-3D object relevance calculation unit 111 calculates the relevance between the basic information acquired in step S610 and the knowledge 118 acquired in step S611. In step S612, the similarity between the feature vector of the basic information and the feature vector of the knowledge 118 is calculated as the relevance. This relevance is calculated for the basic information acquired in step S610 and all of the knowledge 118 and is recorded.

[0058] Next, in step S613, the overall relevance calculation unit 112 calculates the overall relevance. The overall relevance is a weighted sum of the relevance between each piece of knowledge and the work phase and the relevance between the knowledge and the 3D object, which were calculated before step S613. The overall relevance may also be a simple sum of the relevance between each piece of knowledge and the work phase and the relevance between the knowledge and the 3D object. The overall relevance determines the degree of relevance between each piece of knowledge and the currently selected work phase and the 3D object.

[0059] Next, in step S614, the knowledge presentation candidate list calculation unit 113 generates a knowledge presentation candidate list. The knowledge candidate list is a list of knowledge items sorted in descending order of the overall relevance of each piece of knowledge calculated in step S613.

[0060] Next, in step S615, the knowledge candidate presentation unit 114 presents the knowledge candidate list generated in step S614, thereby presenting a knowledge candidate list 701 to the user, as shown in FIG.

[0061] In step S615, the controller unit 102 presents a knowledge candidate list to the multiple users participating in the three-dimensional metaverse space via the user interface units 101 of the multiple users. The controller unit 102 also accepts a knowledge selection from the knowledge candidate list presented by any of the multiple users via the user interface units 101. The controller unit 102 then presents the selected knowledge to the multiple users via the user interface units 101 of the multiple users.

[0062] (Variations of the embodiment) (1) Regarding the first relevance, second relevance, and overall relevance, in the above-described embodiment, a list of knowledge related to a selected 3D object is presented in descending order of overall relevance, which is based on the relevance between the knowledge and the work phase (second relevance) and the relevance between the knowledge and the 3D object (first relevance), and is equal to or greater than a predetermined value.

[0063] However, the present invention is not limited to this, and a list of knowledge related to the selected 3D object may be presented in descending order of the degree of association between the knowledge and the work phase, which is independently a predetermined value or greater, or a list of knowledge related to the selected 3D object may be presented in descending order of the degree of association between the ledge and the 3D object, which is independently a predetermined value or greater.

[0064] Furthermore, when calculating the overall relevance, the relevance between the knowledge and the work phase may be multiplied by a weighting coefficient assigned to a KPI or keyword included in the work phase.The overall relevance may then be calculated by adding the relevance between the knowledge and the 3D object and the relevance between the knowledge and the work phase for each KPI or keyword multiplied by the weighting coefficient for each KPI or keyword.

[0065] (2) Conversion of Basic Information into Feature Vectors In step S609 ( FIG. 6 ) of the above-described embodiment, basic information corresponding to the coordinates of the 3D object selected in step S607 is acquired from the 3D object basic information 120 and converted into a feature vector. However, this is not limited to this. Based on the coordinate information of the 3D object selected in step S607, other basic information including items that are the same as or similar to items included in the basic information related to this 3D object may be acquired by referring to the 3D object basic information 120. The acquired other basic information is then converted into a feature vector. The relevance between the feature vector obtained by converting the other basic information and the feature vector obtained by converting the knowledge is then calculated, and a list of knowledge whose relevance is equal to or greater than a predetermined value is presented to the user via the output device (user interface unit 101).

[0066] Specifically, suppose that a 3D object whose "3D object name" in the first line of the 3D object basic information 120 ( FIG. 3 ) is "Cable 100" is selected by the user. The "Classification" of this "Cable 100" is "Display." Other 3D objects whose "Classification" is "Display" are "3D object name" "Connector 200" in the third line and "3D object name" "Screw 300" in the fifth line. Therefore, in addition to the "3D object name" "Cable 100" in the 3D object basic information 120, the basic information of "Connector 200" and "Screw 300" are also converted into feature vectors, and the knowledge is used to calculate the degree of relevance with the converted feature vector.

[0067] (Effects of the embodiment) In the above-described embodiment, a first relevance between a feature vector obtained by converting basic information related to the attributes of an object selected in a virtual space and a feature vector obtained by converting knowledge is calculated. Then, a list of knowledge whose first relevance is equal to or greater than a predetermined value is presented to the user via an output device. Therefore, for example, knowledge that is highly relevant to equipment or a work site environment represented by a 3D object in the metaverse space can be automatically linked, and knowledge related to the equipment or work site environment can be shared among users involved in the work. Furthermore, linking 3D objects and knowledge is performed automatically, eliminating the need for manual linking work.

[0068] In the above-described embodiment, a second relevance is calculated between a feature vector obtained by converting KPIs or keywords related to a work phase selected by a user and a feature vector obtained by converting knowledge. Then, a list of knowledge whose overall relevance based on the first relevance and the second relevance is equal to or greater than a predetermined value is presented to the user via an output device. Therefore, by dynamically changing the knowledge associated with the 3D object according to the work phase, the user can easily find important knowledge that is highly relevant to KPIs or keywords for each work phase.

[0069] In the above-described embodiment, a list of highly relevant knowledge is presented based on an overall relevance that is based on the first relevance and the second relevance for each KPI or keyword multiplied by a weighting coefficient. Therefore, knowledge related to a KPI or keyword that is deemed important by a larger weighting coefficient is listed at the top as more important knowledge, allowing the user to easily find it.

[0070] In the above-described embodiment, basic information having items identical or similar to the coordinate information items of the selected object is converted into a feature vector, and the knowledge is included in the calculation of the third relevance with the converted feature vector. Then, a list of knowledge having a third relevance equal to or greater than a predetermined value is presented to the user via an output device. Therefore, when a 3D object is selected, knowledge related to other objects having the same or similar basic information can also be presented.

[0071] In the above-described embodiment, the virtual space is a three-dimensional metaverse space, and a list is presented to multiple users via their respective output devices. Furthermore, a knowledge selection from the list presented via the output device of any of the multiple users is accepted, and the selected knowledge is presented to the multiple users via their respective output devices. This facilitates maintenance work by multiple users in railways, electric power, social and public systems, manufacturing, and the like, and also enables the efficient transfer of skills and knowledge.

[0072] (Hardware Configuration of Computer 1000) Fig. 8 is a diagram showing the hardware configuration of the computer 1000. The computer 1000 realizes each unit of the knowledge presentation system 100 by executing a predetermined program.

[0073] The computer 1000 comprises a processor 1001 including a CPU, a main memory device 1002, an auxiliary memory device 1003, a network interface 1004, an input device 1005, and an output device 1006, all of which are interconnected via an internal communication line 1007 such as a bus.

[0074] The processor 1001 controls the overall operation of the computer 1000. The main memory device 1002 is composed of, for example, a volatile semiconductor memory, and is used as a work memory for the processor 1001. The auxiliary memory device 1003 is composed of a large-capacity nonvolatile memory device such as a hard disk device, an SSD (Solid State Drive), or a flash memory, and is used to store various programs and data.

[0075] The executable program 1003 a stored in the auxiliary storage device 1003 is loaded into the main storage device 1002 when the computer 1000 is started up or when necessary, and is executed by the processor 1001 .

[0076] The executable program 1003a may be recorded on a non-transitory recording medium, read from the non-transitory recording medium by a medium reading device, and loaded into the main memory device 1002. Alternatively, the executable program 1003a may be obtained from an external computer via a network and loaded into the main memory device 1002.

[0077] The network interface 1004 is an interface device for connecting the computer 1000 to each network within the system or for communicating with other computers. The network interface 2004 is configured, for example, by a NIC (Network Interface Card) for a wired LAN (Local Area Network) or a wireless LAN.

[0078] The input device 1005 is composed of a keyboard, a pointing device such as a mouse, and the like, and is used by the user to input various instructions and information to the computer 1000. The output device 1006 is composed of a display device such as a liquid crystal display or an organic EL (Electro Luminescence) display, and an audio output device such as a speaker, and is used to present necessary information to the user when necessary.

[0079] The present invention is not limited to the above-described embodiments, and includes various modifications. Furthermore, the above-described embodiments have been described in detail to clearly explain the present invention, and are not necessarily limited to those having all of the described configurations. Furthermore, not only are such configurations removed, but replacement or addition of configurations is also possible. Furthermore, embodiments of the present invention also include those in which some or all of the above-described embodiments are appropriately combined to be consistent. Furthermore, the order of execution of each step of the various processes in the above-described embodiments can be changed as long as the processing results are the same.

[0080] Furthermore, the above-described configurations, functions, processing units, processing means, etc. may be partially or entirely implemented in hardware, for example, by designing them as integrated circuits. The present invention can also be implemented by software program code that implements the functions of the embodiments. In this case, a recording medium on which the program code is recorded is provided to a computer, and a processor within the computer reads the program code stored in the recording medium.

[0081] In this case, the program code itself read from the recording medium will realize the functions of the above-described embodiment, and the program code itself and the recording medium on which it is stored constitute the present invention. Examples of recording media for supplying such program code include flexible disks, CD-ROMs, DVD-ROMs, hard disks, SSDs (Solid State Drives), optical disks, magneto-optical disks, CD-Rs, magnetic tapes, non-volatile memory cards, ROMs, etc.

[0082] Furthermore, the program code that realizes the functions described in this embodiment can be implemented in a wide range of program or script languages, such as assembler, C / C++, perl, Shell, PHP, and Java (registered trademark).

[0083] In the above-described embodiment, the control lines and information lines are those that are considered necessary for the explanation, and not all control lines and information lines in the product are necessarily shown. All components may be interconnected.

[0084] 100: Knowledge presentation system, 1000: Computer, 1001: Processor, 1002: Main memory device, 1006: Output device.

Claims

1. A knowledge presentation system that presents knowledge related to objects placed in a virtual space, the knowledge presentation system having a processor and memory, wherein the processor manages documents related to the objects as the knowledge, manages object basic information that associates coordinate information of the objects in the virtual space with basic information related to the attributes of the objects, accepts selection of the objects by a user, acquires the basic information related to the object by referring to the object basic information based on the coordinate information of the object whose selection has been accepted, converts the acquired basic information and knowledge into feature vectors, calculates a first degree of relevance between the feature vector obtained by converting the basic information and the feature vector obtained by converting the knowledge, and presents to the user via an output device a list of the knowledge whose first degree of relevance is equal to or greater than a predetermined value.

2. A knowledge presentation system as described in claim 1, wherein the processor manages keyword information that associates work phases with keywords related to the work phases, accepts a selection of a work phase by the user, obtains the keywords related to the work phase selected from the keyword information, converts the obtained keywords into feature vectors, calculates a second relevance between the feature vector obtained by converting the keywords and the feature vector obtained by converting the knowledge, and presents to the user via the output device a list of the knowledge whose overall relevance based on the first relevance and the second relevance is equal to or greater than a predetermined value.

3. A knowledge presentation system as described in claim 2, wherein the multiple keywords form tree data based on a hierarchical relationship, and the processor assigns a weighting coefficient to each of the keywords related to the work phase obtained from the keyword information, multiplies the second relevance of each keyword by the weighting coefficient assigned to each keyword, and presents to the user via the output device a list of knowledge whose overall relevance, based on the first relevance and the second relevance of each keyword multiplied by the weighting coefficient, is equal to or greater than a predetermined value.

4. A knowledge presentation system as described in claim 1, wherein the basic information includes a plurality of items, and the processor, based on the coordinate information of the object for which selection has been accepted, refers to the object basic information to acquire second basic information including items that are identical or similar to the items included in the basic information relating to the object, converts the acquired second basic information into a feature vector, calculates a third relevance between the feature vector obtained by converting the second basic information and the feature vector obtained by converting the knowledge, and presents to the user via the output device a list of the knowledge for which the third relevance is equal to or greater than a predetermined value.

5. A knowledge presentation system as described in claim 1, wherein the virtual space is a three-dimensional metaverse space, and the processor presents the list to a plurality of users participating in the three-dimensional metaverse space via the output device of each of the users.

6. A knowledge presentation system as described in claim 5, characterized in that the processor accepts a selection of the knowledge from the list presented via the output device by any of the plurality of users, and presents the knowledge whose selection has been accepted to the plurality of users via the output device of each of the plurality of users.

7. A knowledge presentation method executed by a knowledge presentation system that presents knowledge related to objects placed in a virtual space, the knowledge presentation system having a processor and a memory, wherein the processor: manages documents related to the objects as the knowledge; manages object basic information that associates coordinate information of the objects in the virtual space with basic information related to the attributes of the objects; accepts selection of the object by a user; acquires the basic information related to the object by referring to the object basic information based on the coordinate information of the object whose selection has been accepted; converts the acquired basic information and knowledge into feature vectors; calculates a first degree of relevance between the feature vector obtained by converting the basic information and the feature vector obtained by converting the knowledge; and presents to the user via an output device a list of the knowledge whose first degree of relevance is equal to or greater than a predetermined value.

8. A knowledge presentation method according to claim 7, characterized in that the processor: manages keyword information associating work phases with keywords related to the work phases; accepts a selection of a work phase by the user; acquires the keywords related to the work phase selected from the keyword information; converts the acquired keywords into feature vectors; calculates a second relevance between the feature vector converted from the keywords and the feature vector converted from the knowledge; and presents to the user via the output device a list of the knowledge whose overall relevance based on the first relevance and the second relevance is equal to or greater than a predetermined value.

9. A knowledge presentation method as described in claim 8, wherein the multiple keywords form tree data based on a hierarchical relationship, and the processor assigns a larger weighting coefficient to each keyword related to the work phase obtained from the keyword information, the lower the keyword in the tree data, the greater the weighting coefficient the keyword is, multiplies the second relevance of each keyword by the weighting coefficient assigned to each keyword, and presents to the user via the output device a list of knowledge whose overall relevance, based on the first relevance and the second relevance of each keyword multiplied by the weighting coefficient, is equal to or greater than a predetermined value.

10. A knowledge presentation method according to claim 7, wherein the basic information includes a plurality of items, and the processor, based on the coordinate information of the object for which selection has been accepted, refers to the object basic information to acquire second basic information including items that are identical or similar to the items included in the basic information relating to the object, converts the acquired second basic information into a feature vector, calculates a third relevance between the feature vector obtained by converting the second basic information and the feature vector obtained by converting the knowledge, and presents to the user via the output device a list of the knowledge for which the third relevance is equal to or greater than a predetermined value.

11. A knowledge presentation method as described in claim 6, wherein the virtual space is a three-dimensional metaverse space, and the processor presents the list to a plurality of users participating in the three-dimensional metaverse space via the output device of each of the users.

12. A method of presenting knowledge as described in claim 11, characterized in that the processor accepts a selection of the knowledge from the list presented via the output device by any of the plurality of users, and presents the knowledge whose selection has been accepted to the plurality of users via their respective output devices.

Images