Knowledge base construction methods, retrieval methods, systems, electronic devices, and storage media

Abstract

This disclosure provides a knowledge base construction method, retrieval method, system, electronic device, and storage medium. The knowledge base is applied to augmented reality (AR) scenarios. The knowledge base construction method includes: obtaining knowledge type keywords from industrial documents, whereby the knowledge type keywords represent interactive information in the AR scenario; obtaining component keywords from paragraphs in the industrial documents, whereby the component keywords represent location information in the AR scenario; marking the knowledge type keywords and the component keywords as feature information of the paragraphs, whereby the feature information is used to locate the paragraphs during retrieval; and constructing the knowledge base based on the paragraphs marked with the feature information, whereby the knowledge base provides data support for AR. This disclosure enables the summarization of discrete document data and the effective construction of a knowledge base. It helps users quickly locate relevant content and display it in AR images.

Description

Technical Field

[0001] This disclosure relates to the field of virtual reality, and more particularly to a knowledge base construction method, retrieval method, system, electronic device, and storage medium. Background Technology

[0002] As AR (Augmented Reality) technology becomes increasingly sophisticated, it has been applied in the industrial sector, for example, to assist in the operation and maintenance of industrial equipment. Therefore, some companies need to undergo digital transformation, digitizing existing documents and data to integrate with AR technology.

[0003] However, some enterprises started their digital transformation relatively late, resulting in a slow and incomplete knowledge base construction process. Furthermore, the differences in the technology stacks of AR and knowledge bases meant that they belonged to different technical teams, preventing effective integration of the knowledge base with AR. Therefore, an effective knowledge base construction method is urgently needed during the digital transformation phase of enterprises. Summary of the Invention

[0004] The problem this disclosure aims to solve is to overcome the shortcomings of existing technologies in which knowledge bases cannot be effectively integrated with AR, and to provide a knowledge base construction method, retrieval method, system, electronic device, and storage medium.

[0005] This disclosure solves the above-mentioned technical problems through the following technical solution:

[0006] This disclosure provides a method for constructing a knowledge base, wherein the knowledge base is applied to an augmented reality scenario, and the method for constructing the knowledge base includes:

[0007] Obtain knowledge type keywords from industrial documents, whereby these knowledge type keywords are used to characterize interactive information in augmented reality scenarios;

[0008] Obtain component keywords from paragraphs in the industrial document; these component keywords are used to characterize the positioning information of the augmented reality scene.

[0009] The knowledge type keywords and component keywords are marked as feature information of the paragraph, and the feature information is used to locate the paragraph during the retrieval process;

[0010] The knowledge base is constructed based on the paragraphs labeled with the feature information, and the knowledge base is used to provide data support for augmented reality.

[0011] Preferably, the knowledge type keywords for acquiring industrial documents include:

[0012] Match the keywords in the title of the industrial document with the keywords in the knowledge type library;

[0013] If the matching result is consistent, the matching keyword will be used as the knowledge type keyword for all paragraphs in the industrial document.

[0014] Preferably, the step of obtaining component keywords of paragraphs in the industrial document includes:

[0015] Match the keywords in the title of the industrial document with the keywords in the component library;

[0016] If the matching result is consistent, the matching keyword will be used as the main component keyword;

[0017] If the paragraph contains the main component keyword, then the main component keyword is used as the component keyword of the paragraph.

[0018] Preferably, the step of obtaining component keywords of paragraphs in the industrial document further includes:

[0019] Obtain the associated component keywords corresponding to the main component keywords; the associated component keywords and the main component keywords have a subordinate relationship.

[0020] If the paragraph contains the associated component keyword, then the associated component keyword is used as the component keyword of the paragraph.

[0021] Preferably, the step of obtaining component keywords of paragraphs in the industrial document further includes:

[0022] If the paragraph contains unmatched keywords other than the component keywords, then the unmatched keywords will be used as other keywords for the paragraph.

[0023] This disclosure also provides a retrieval method, which is applied to the knowledge base constructed by the knowledge base construction method described in any of the foregoing claims;

[0024] The retrieval method includes:

[0025] Obtain the user's search instructions;

[0026] Extract the knowledge type keywords and component keywords of the search command;

[0027] Match the knowledge type keywords and the component keywords with the content of the knowledge base;

[0028] The matching results are output and displayed at the corresponding locations in the augmented reality image.

[0029] This disclosure also provides a knowledge base construction system, wherein the knowledge base is applied to an augmented reality scenario, and the knowledge base construction system includes:

[0030] The first acquisition module is used to acquire knowledge type keywords from industrial documents, wherein the knowledge type keywords are used to characterize interactive information in augmented reality scenarios;

[0031] The second acquisition module is used to acquire component keywords of paragraphs in the industrial document, wherein the component keywords are used to characterize the positioning information of the augmented reality scene;

[0032] A tagging module is used to tag the knowledge type keywords and the component keywords as feature information of the paragraph, and the feature information is used to locate the paragraph during the retrieval process;

[0033] A building module is used to construct the knowledge base based on the paragraphs labeled with the feature information, the knowledge base being used to provide data support for augmented reality.

[0034] Preferably, the first acquisition module includes:

[0035] The first matching unit is used to match the keywords of the title of the industrial document with the knowledge type keywords in the knowledge type base;

[0036] The first matching unit is further configured to, if the matching result is consistent, use the consistent keyword as the knowledge type keyword for all paragraphs in the industrial document.

[0037] Preferably, the second acquisition module includes:

[0038] The second matching unit is used to match the keywords of the title of the industrial document with the keywords of the components in the component library;

[0039] The second matching unit is further configured to, if the matching result is consistent, use the consistent keyword as the main component keyword;

[0040] The second matching unit is further configured to, if the paragraph contains the main component keyword, use the main component keyword as the component keyword of the paragraph.

[0041] Preferably, the second acquisition module further includes:

[0042] The third matching unit is used to obtain the associated component keywords corresponding to the main component keywords; the associated component keywords and the main component keywords have a subordinate relationship.

[0043] The third matching unit is further configured to, if the paragraph contains the associated component keyword, use the associated component keyword as the component keyword of the paragraph.

[0044] Preferably, the second acquisition module further includes:

[0045] The fourth matching unit is used to treat unmatched keywords other than the component keywords as other keywords of the paragraph if the paragraph contains such unmatched keywords.

[0046] This disclosure also provides a retrieval system, which is applied to the knowledge base constructed by any of the preceding knowledge base construction methods;

[0047] The retrieval system includes:

[0048] The instruction acquisition module is used to acquire the user's search instructions;

[0049] The extraction module is used to extract knowledge type keywords and component keywords from the search command;

[0050] A matching module is used to match the knowledge type keywords and the component keywords with the content of the knowledge base;

[0051] The output module is used to output the matching results and display the results at the corresponding positions in the augmented reality image.

[0052] This disclosure also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and used to run on the processor, wherein the processor executes the computer program to implement the aforementioned knowledge base construction method.

[0053] This disclosure also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the aforementioned knowledge base construction method.

[0054] Based on common knowledge in the field, the above-mentioned preferred conditions can be combined arbitrarily to obtain various preferred embodiments of this disclosure.

[0055] The positive advancements of this disclosure are as follows: The knowledge base construction method acquires knowledge type keywords and component keywords from paragraphs within industrial documents, tags these keywords in the documents, and incorporates them into the knowledge base. This effectively summarizes discrete document data and constructs a knowledge base. Furthermore, the retrieval method utilizes search instructions containing knowledge type keywords and component keywords to help users quickly locate relevant content and display it within AR images. These technical means not only provide a convenient database construction method, saving costs, but also achieve effective integration with AR, improving the user experience. Attached Figure Description

[0056] Figure 1 A flowchart illustrating a knowledge base construction method provided as an exemplary embodiment of this disclosure;

[0057] Figure 2 An animated file illustration provided as an exemplary embodiment of this disclosure;

[0058] Figure 3 A schematic diagram of a text file provided as an exemplary embodiment of this disclosure;

[0059] Figure 4 A flowchart of a retrieval method provided as an exemplary embodiment of this disclosure;

[0060] Figure 5 A schematic diagram of a knowledge base construction system provided as an exemplary embodiment of this disclosure;

[0061] Figure 6 A schematic diagram of a retrieval system provided as an exemplary embodiment of this disclosure;

[0062] Figure 7 This is a schematic diagram of the structure of an electronic device provided as an exemplary embodiment of the present disclosure. Detailed Implementation

[0063] The present disclosure is further illustrated below by way of embodiments, but the present disclosure is not limited to the scope of the embodiments described herein.

[0064] Figure 1 A flowchart illustrating an exemplary embodiment of this disclosure provides a method for constructing a knowledge base, which is applied to an augmented reality scenario. The method includes:

[0065] Step 101: Obtain knowledge type keywords from industrial documents. Knowledge type keywords are used to represent interactive information in augmented reality scenarios.

[0066] In this step, industrial documents include, but are not limited to, text files, image files, video files, and CAD files. Due to the special characteristics of industrial documents, knowledge type keywords are generally related to common knowledge types in industry, such as assembly or maintenance. The process of obtaining knowledge type keywords from industrial documents includes the following steps:

[0067] Step 1011: Match the keywords in the title of the industrial document with the knowledge type keywords in the knowledge type library.

[0068] This step involves extracting keywords from the titles of industrial documents. Titles typically contain several keywords, which are then matched against type keywords in a knowledge type library. It's important to understand that industrial document titles generally follow naming conventions; any non-standard naming can be manually corrected. The knowledge type library is pre-edited and includes commonly used knowledge type keywords in the industrial field. Additionally, keywords not yet added to the library can be manually added. Knowledge type keywords represent interactive information in augmented reality scenarios; they describe the type of assistance AR users need, such as process-related, maintenance-related, or equipment status-related information.

[0069] Step 1012: If the matching result is consistent, then the matching keywords will be used as the knowledge type keywords for all paragraphs in the industrial document.

[0070] In this step, a matching result indicates that a knowledge type keyword matching the title exists in the knowledge type base. This knowledge type keyword is the knowledge type keyword of the current industrial document, and therefore all paragraphs in the document are related to this knowledge type keyword. For example, if a text file is titled "Assembly Instructions for a Steam Turbine," then the keyword "assembly" is the knowledge type keyword for this document, and all paragraphs in the text file contain "assembly" as their knowledge type keyword. In other words, the entire content of the text file is related to "assembly."

[0071] Step 102: Obtain component keywords from paragraphs in the industrial document. Component keywords are used to represent the positioning information of the augmented reality scene.

[0072] It should be understood that steps 102 and 101 are parallel and not necessarily sequential.

[0073] In this step, the final augmented reality presentation should be specific to the location of the component. Therefore, to more accurately represent the augmented reality scene, it is necessary to locate the relevant content of the corresponding component in the industrial document. Component keywords are keywords used to describe this relevant content. Component keywords can include component name, component location, or model information. Component keywords can be hierarchically organized according to the component hierarchy of the original CAD model of the equipment.

[0074] This includes retrieving component keywords from paragraphs in industrial documents, including:

[0075] Step 1021: Match the keywords in the title of the industrial document with the keywords in the component library.

[0076] This step involves extracting keywords from the titles of industrial documents. Titles typically contain several keywords, which are then matched against component keywords in a component library. It's important to understand that industrial document titles generally follow standardized naming conventions. If a title contains non-standard names, manual intervention is possible to correct them. The component library is pre-edited and includes common component keywords from the current industrial sector. Furthermore, any component keywords not yet included in the library can be manually added.

[0077] Step 1022: If the matching result is consistent, then the matching keywords will be used as the main component keywords.

[0078] In this step, a matching result indicates that a component keyword exists in the component library that matches the title's keyword. This component keyword is the component keyword to which the current industrial document belongs. Therefore, it can be determined that the content involved in the industrial document is related to this component keyword, and thus, this component keyword is used as the primary component keyword. For example, if a text file is titled "Assembly Instructions for a Steam Turbine," then the keyword "steam turbine" is the primary component keyword for this document, and all paragraphs in the text file revolve around the content of "steam turbine."

[0079] Step 1023: If a paragraph contains main component keywords, then use the main component keywords as the paragraph's component keywords.

[0080] In this step, it is necessary to determine whether the paragraphs in the industrial document contain keywords related to the main components. If a paragraph contains such keywords, then the paragraph can be considered to contain content related to those keywords. In other words, the component keywords in that paragraph are considered main component keywords.

[0081] Optionally, retrieving component keywords from paragraphs in industrial documents also includes:

[0082] Step 1024: Obtain the related component keywords corresponding to the main component keywords. The related component keywords and the main component keywords have a subordinate relationship.

[0083] In this step, because components in actual industrial scenarios do not exist independently but are interconnected to form a large and complex system, further keyword targeting is needed to more accurately locate specific components. It should be understood that the relationships between components conform to applicable rules of industrial scenarios; therefore, the number of components associated with a given component is limited and can be statistically included. For example, when the main component keyword is "steam turbine," the associated components could be: cylinder, rotor, coupling, stationary blades, moving blades, steam seals, and bearings. Furthermore, associated components can be further extended to include sub-components. For example, bearing sub-components include: multi-wedge bearings (three-wedge, four-wedge), round bearings, elliptical bearings, tilting pad bearings, and thrust bearings. Both associated component keywords and their sub-components can be used to establish a correspondence between associated component keywords and the main component keywords.

[0084] Step 1025: If a paragraph contains related component keywords, then use the related component keywords as the paragraph's component keywords.

[0085] In this step, it is necessary to determine whether the paragraphs in the industrial document contain keywords related to related components. If a paragraph contains keywords related to related components, then the paragraph can be considered to contain content related to those keywords. That is, the component keywords in the paragraph also include keywords related to related components.

[0086] Optionally, retrieving component keywords from paragraphs in industrial documents also includes:

[0087] Step 1026: If a paragraph contains unmatched keywords other than component keywords, then treat the unmatched keywords as other keywords for the paragraph.

[0088] In this step, if a paragraph contains neither main component keywords nor related component keywords, it can be considered that the paragraph is not highly relevant to the main component keywords and / or related component keywords. However, as part of industrial documentation, keyword extraction should still be performed to facilitate comprehensive and detailed searches by users. Optionally, keywords without matching results can be used as alternative keywords. These alternative keywords can be used to assist users in conducting more precise searches, building upon the main component keywords and related component keywords.

[0089] It should be understood that the content of a paragraph includes its subheadings and the body text under each subheading. The key idea behind the above steps is to retrospectively compare the results with the headings after comparing the keyword searches for subheadings or paragraph components, in order to determine which of these component keywords within the paragraph are more relevant to the main component keywords. This makes the search results more accurate and better meet the user's expectations.

[0090] Step 103: Mark the knowledge type keywords and component keywords as paragraph feature information. The feature information is used to locate paragraphs during the retrieval process.

[0091] In this step, after the knowledge type keywords and component keywords are determined in steps 101 and 102 respectively, the knowledge type keywords and component keywords can be used as feature information of paragraphs in industrial documents. This feature information is used to more accurately locate the corresponding content in the paragraphs during the retrieval process.

[0092] Step 104: Construct a knowledge base based on paragraphs labeled with feature information. The knowledge base is used to provide data support for augmented reality.

[0093] In this step, the paragraph content with tagged feature information was completed and added to the knowledge base. This knowledge base, after its initial construction, can be updated as needed. It serves to provide data support for augmented reality, enabling more accurate and richer presentation of augmented reality scenes.

[0094] Additionally, it should be understood that the knowledge base is a place to store and categorize industrial documents, including equipment information, equipment manuals, and maintenance guidance documents. In one embodiment, during use, this content is listed as knowledge entries below the search box. Different types of entries will have different colors on the UI (user interface), and clicking on them will display the corresponding instance. This instance can be a PDF document, a model, an XR-IoT instance, or an XR operation assistance animation. The knowledge base has a search box that can be accessed at any time. Furthermore, when appropriate IoT data is integrated, the knowledge base can push more valuable industrial documents based on the corresponding IoT data.

[0095] To illustrate the industrial documents in the database, two specific examples are given below. Figure 2 A schematic diagram of an animation file provided for an exemplary embodiment of this disclosure; see reference Figure 2It is known that the animation file, titled "Welding Instructions for the Shell," contains a total of 2938 frames. The reinforcement details are located from frames 1029 to 1422. The main component keyword is "shell," the knowledge type keyword is "welding," and other keywords include "reinforcement components." If a user needs to display content related to the shell reinforcement components in an augmented reality scene, the augmented reality scene display effect will be: the content from frames 1029 to 1422 of this animation file will be played at the location of the shell.

[0096] Figure 3 A schematic diagram of a text file provided for an exemplary embodiment of this disclosure, with reference to Figure 3 It is known that the title of this text file is "Welding Precautions for the Shell," with the main component keyword being "shell," the knowledge type keyword being "welding," and other keywords being "reinforcement components." If the user needs to display content related to the shell reinforcement components in an augmented reality scene, the augmented reality scene display effect will be: displaying the Nth paragraph of this text file at the location of the shell.

[0097] In this embodiment, discrete document data is summarized to effectively construct a knowledge base. Furthermore, the retrieval method utilizes search instructions containing knowledge type keywords and component keywords to help users quickly locate relevant content and display it within the AR image. This not only provides a convenient database construction method, saving costs, but also achieves effective integration with AR, improving the user experience.

[0098] Reference Figure 4 The flowchart illustrates an exemplary embodiment of this disclosure, wherein the retrieval method is applied to a knowledge base constructed by any of the foregoing knowledge base construction methods; the retrieval method includes:

[0099] Step 201: Obtain the user's search instructions.

[0100] In this step, since the user's search is targeting a pre-built knowledge base, the user's search command should follow the knowledge base's search command format. For example, the search format could be "component keyword + knowledge type keyword," specifically, "steam turbine maintenance," where "steam turbine" is the component keyword and "maintenance" is the knowledge type keyword. Alternatively, for more refined searching, other keywords can be added, such as "component keyword + knowledge type keyword + other keywords," specifically, "steam turbine + maintenance + pressure data," where "steam turbine" is the component keyword, "maintenance" is the knowledge type keyword, and "pressure data" is another keyword. It should be understood that the search format is not limited to the above description and can be adjusted according to actual needs.

[0101] Step 202: Extract the knowledge type keywords and component keywords of the search command.

[0102] In this step, after obtaining the user's search instructions, knowledge type keywords and component keywords are extracted to accurately locate the content that the user needs to display in augmented reality.

[0103] Step 203: Match knowledge type keywords and component keywords with the content of the knowledge base.

[0104] In this step, the purpose of matching is to find content that corresponds to the user's search query.

[0105] Step 204: Output the matching results and display them in the corresponding positions in the augmented reality image.

[0106] In this step, after retrieving content corresponding to the user's search query, this content is displayed as a matching result in the augmented reality scene. It should be understood that building a knowledge base is not a one-step process; there may be instances where no matching results are output. If the reason for no matching results is that the knowledge base lacks corresponding knowledge type keywords or component keywords, manual intervention is required to add them manually.

[0107] In this embodiment, the retrieval method utilizes retrieval instructions containing knowledge type keywords and component keywords to help users quickly locate relevant content and display it in the AR image. This achieves effective integration with AR and improves the user experience.

[0108] Reference Figure 5 This is a schematic diagram of a knowledge base construction system provided as an exemplary embodiment of the present disclosure. This knowledge base construction system corresponds to the aforementioned knowledge base construction method. The knowledge base construction system includes:

[0109] The first acquisition module 31 is used to acquire knowledge type keywords from industrial documents. These knowledge type keywords are used to represent interactive information in augmented reality scenarios.

[0110] The second acquisition module 32 is used to acquire component keywords of paragraphs in industrial documents. Component keywords are used to represent the positioning information of augmented reality scenes.

[0111] The tagging module 33 is used to tag knowledge type keywords and component keywords as paragraph feature information, which is used to locate paragraphs during the retrieval process.

[0112] Module 34 is used to build a knowledge base based on paragraphs with tagged feature information, which is used to provide data support for augmented reality.

[0113] Optionally, the first acquisition module 31 includes:

[0114] The first matching unit is used to match the keywords in the title of the industrial document with the knowledge type keywords in the knowledge type base.

[0115] The first matching unit is also used to use the matching keywords as knowledge type keywords for all paragraphs in the industrial document if the matching results are consistent.

[0116] Optionally, the second acquisition module 32 includes:

[0117] The second matching unit is used to match the keywords in the title of the industrial document with the keywords in the parts library.

[0118] The second matching unit is also used to use the matching keywords as the main component keywords if the matching results are consistent.

[0119] The second matching unit is also used to use the main component keywords as the component keywords of the paragraph if the paragraph contains main component keywords.

[0120] Optionally, the second acquisition module 32 further includes:

[0121] The third matching unit is used to obtain the related component keywords corresponding to the main component keywords; the related component keywords and the main component keywords have a subordinate relationship.

[0122] The third matching unit is also used to treat the related component keywords as the component keywords of the paragraph if the paragraph contains related component keywords.

[0123] Optionally, the second acquisition module 32 further includes:

[0124] The fourth matching unit is used to treat unmatched keywords as other keywords in the paragraph if the paragraph contains unmatched keywords other than component keywords.

[0125] In this embodiment, discrete document data is summarized to effectively construct a knowledge base. Furthermore, the retrieval method utilizes search instructions containing knowledge type keywords and component keywords to help users quickly locate relevant content and display it within the AR image. This not only provides a convenient database construction method, saving costs, but also achieves effective integration with AR, improving the user experience.

[0126] Reference Figure 6 This is a schematic diagram of a retrieval system provided in an exemplary embodiment of the present disclosure. The retrieval system corresponds to the aforementioned retrieval method. The retrieval system is applied to a knowledge base constructed by any of the aforementioned knowledge base construction methods; the retrieval system includes:

[0127] Instruction acquisition module 41 is used to acquire the user's search instructions;

[0128] Extraction module 42 is used to extract knowledge type keywords and component keywords for retrieval commands.

[0129] Matching module 43 is used to match knowledge type keywords and component keywords with the content of the knowledge base.

[0130] Output module 44 is used to output the matching results and display the results at the corresponding positions in the augmented reality image.

[0131] In this embodiment, the retrieval method utilizes retrieval instructions containing knowledge type keywords and component keywords to help users quickly locate relevant content and display it in the AR image. This achieves effective integration with AR and improves the user experience.

[0132] Figure 7 This is a schematic diagram of the structure of an electronic device provided in this embodiment. The electronic device includes a memory, a processor, and a computer program stored in the memory and used to run on the processor. When the processor executes the program, it implements the knowledge base construction method or retrieval method provided in any of the above embodiments. Figure 7 The electronic device 300 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0133] Reference Figure 7 The electronic device 300 can be manifested in the form of a general-purpose computing device, such as a server device. The components of the electronic device 300 may include, but are not limited to: at least one processor 301, at least one memory 302, and a bus 303 connecting different system components (including memory 302 and processor 301).

[0134] Bus 303 includes a data bus, an address bus, and a control bus.

[0135] The memory 302 may include volatile memory, such as random access memory (RAM) 321 and / or cache memory 322, and may further include read-only memory (ROM) 323.

[0136] The memory 302 may also include a program / utility 325 having a set (at least one) of program modules 324, including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0137] The processor 301 executes various functional applications and data processing by running computer programs stored in the memory 302, such as the knowledge base construction method or retrieval method of the embodiments of this disclosure.

[0138] Electronic device 300 can also communicate with one or more external devices 304 (e.g., keyboard, pointing device, etc.). This communication can be performed through input / output (I / O) interface 305. Furthermore, the model-generated device 300 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public network, such as the Internet) via network adapter 306. As shown, network adapter 306 communicates with other modules of the model-generated device 300 via bus 303. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the model-generated device 300, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems.

[0139] It should be noted that although several units / modules or sub-units / modules of the electronic device have been mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided and embodied by multiple units / modules.

[0140] This embodiment also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the knowledge base construction method or retrieval method provided in any of the above embodiments.

[0141] The readable storage medium may be more specifically adopted, including but not limited to: portable disk, hard disk, random access memory, read-only memory, erasable programmable read-only memory, optical storage device, magnetic storage device, or any suitable combination thereof.

[0142] In possible implementations, this disclosure can also be implemented as a program product comprising program code, which, when the program product is run on a terminal device, is used to cause the terminal device to execute the knowledge base construction method or retrieval method provided in any of the above embodiments.

[0143] The program code for executing this disclosure can be written in any combination of one or more programming languages, and the program code can be executed entirely on a user device, partially on a user device, as a stand-alone software package, partially on a user device and partially on a remote device, or entirely on a remote device.

[0144] While specific embodiments of this disclosure have been described above, those skilled in the art should understand that these are merely illustrative examples, and the scope of protection of this disclosure is defined by the appended claims. Those skilled in the art can make various changes or modifications to these embodiments without departing from the principles and essence of this disclosure, but all such changes and modifications fall within the scope of protection of this disclosure.

Claims

1. A method for constructing a knowledge base, characterized in that, The knowledge base is applied to augmented reality scenarios, and the knowledge base construction method includes: Obtain knowledge type keywords from industrial documents, whereby these knowledge type keywords are used to characterize interactive information in augmented reality scenarios; Obtain component keywords from paragraphs in the industrial document; these component keywords are used to characterize the positioning information of the augmented reality scene. The knowledge type keywords and component keywords are marked as feature information of the paragraph, and the feature information is used to locate the paragraph during the retrieval process; The knowledge base is constructed based on the paragraphs labeled with the feature information, and the knowledge base is used to provide data support for augmented reality. The step of obtaining knowledge type keywords for industrial documents includes: matching the keywords in the title of the industrial document with knowledge type keywords in a knowledge type library; if the matching result is consistent, then the consistent keywords are used as the knowledge type keywords for all paragraphs in the industrial document; and / or, the step of obtaining component keywords for paragraphs in the industrial document includes: matching the keywords in the title of the industrial document with component keywords in a component library; if the matching result is consistent, then the consistent keywords are used as the main component keywords; if the paragraph contains the main component keywords, then the main component keywords are used as the component keywords for the paragraph.

2. The knowledge base construction method according to claim 1, characterized in that, The step of obtaining component keywords from paragraphs in the industrial document also includes: Obtain the associated component keywords corresponding to the main component keywords; the associated component keywords and the main component keywords have a subordinate relationship. If the paragraph contains the associated component keyword, then the associated component keyword is used as the component keyword of the paragraph.

3. The knowledge base construction method according to claim 2, characterized in that, The step of obtaining component keywords from paragraphs in the industrial document also includes: If the paragraph contains unmatched keywords other than the component keywords, then the unmatched keywords will be used as other keywords for the paragraph.

4. A retrieval method, characterized in that, The retrieval method is applied to the knowledge base constructed by the knowledge base construction method according to any one of claims 1 to 3; The retrieval method includes: Obtain the user's search instructions; Extract the knowledge type keywords and component keywords of the search command; Match the knowledge type keywords and the component keywords with the content of the knowledge base; The matching results are output and displayed at the corresponding locations in the augmented reality image.

5. A knowledge base construction system, characterized in that, The knowledge base is applied to augmented reality scenarios, and the knowledge base construction system includes: The first acquisition module is used to acquire knowledge type keywords from industrial documents, wherein the knowledge type keywords are used to characterize interactive information in augmented reality scenarios; The second acquisition module is used to acquire component keywords of paragraphs in the industrial document, wherein the component keywords are used to characterize the positioning information of the augmented reality scene; A tagging module is used to tag the knowledge type keywords and the component keywords as feature information of the paragraph, and the feature information is used to locate the paragraph during the retrieval process; A construction module is used to build the knowledge base based on the paragraphs labeled with the feature information, the knowledge base being used to provide data support for augmented reality; The first acquisition module includes a first matching unit, configured to match keywords in the title of the industrial document with knowledge type keywords in a knowledge type library; if the matching result is consistent, the matching keywords are used as the knowledge type keywords for all paragraphs in the industrial document; and / or, the second acquisition module includes a second matching unit, configured to match keywords in the title of the industrial document with component keywords in a component library; if the matching result is consistent, the matching keywords are used as the main component keywords; if the paragraph contains the main component keywords, the main component keywords are used as the component keywords for the paragraph.

6. A retrieval system, characterized in that, The retrieval system is applied to the knowledge base constructed by the knowledge base construction method according to any one of claims 1 to 3; The retrieval system includes: The instruction acquisition module is used to acquire the user's search instructions; The extraction module is used to extract knowledge type keywords and component keywords from the search command; A matching module is used to match the knowledge type keywords and the component keywords with the content of the knowledge base; The output module is used to output the matching results and display the results at the corresponding positions in the augmented reality image.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and for running on the processor, characterized in that, When the processor executes the computer program, it implements the knowledge base construction method of any one of claims 1 to 3 or the retrieval method of claim 4.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the knowledge base construction method of any one of claims 1 to 3 or the retrieval method of claim 4.

Images