Display method, display device, electronic device, storage medium, and program

Abstract

To provide a display method and a display device configured to enhance the understanding of users on to-be-displayed contents.SOLUTION: A display method comprises: acquiring to-be-displayed content; extracting a target term from the content by using a term extraction rule; in response to the extracted at least one target term, acquiring annotation information for the at least one target term; and displaying the annotation information and content of the at least one target term.EFFECT: The display method and the display device can provide intelligent natural language processing services under the condition of less or no manual intervention, and convenient term customization services for users, so that the understanding of the users on to-be-displayed contents is enhanced.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present disclosure relates to the fields of natural language processing and display, particularly to term annotation techniques, and more particularly to display methods and devices. [Background technology]

[0002] Natural language processing technology has been attracting more and more attention as the foundation of artificial intelligence. However, due to the existence of many specialized industry terms in different fields, current natural language processing technology has difficulty in processing these terms accurately and precisely.

[0003] In particular, with regard to simultaneous interpretation technology, current simultaneous interpretation devices have many errors in speech recognition and translation of industry terms, making it difficult to meet the needs of different fields of expertise. In addition, users may be unfamiliar with some terms, which may affect their understanding of the content. Summary of the Invention [Problem to be solved by the invention]

[0004] The present disclosure provides a display method, a display device, an electronic device, a storage medium, and a program. [Means for solving the problem]

[0005] According to one aspect of the present disclosure, there is provided a display method, comprising: Obtaining content to be displayed; extracting target terms from the content using term extraction rules; In response to extracting the at least one target term, obtaining annotation information for the at least one target term; and displaying annotation information of the at least one target term and the content.

[0006] According to another aspect of the present disclosure, there is provided a display device, comprising: a content retrieval module configured to retrieve content to be displayed; a term extraction module configured to extract target terms from the content using term extraction rules; an annotation information obtaining module configured to obtain annotation information for the at least one target term in response to extracting the at least one target term; a display module configured to display annotation information of the at least one target term and the content.

[0007] According to another aspect of the present disclosure, there is provided an electronic device including at least one processor and a memory communicatively coupled to the at least one processor, wherein instructions executable by the at least one processor are stored in the memory, and the instructions are executed by the at least one processor such that the at least one processor can perform a method according to an exemplary embodiment of the present disclosure.

[0008] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium having stored thereon computer instructions for causing the computer to perform a method according to an exemplary embodiment of the present disclosure is provided.

[0009] According to another aspect of the present disclosure, there is provided a computer program product which, when executed by a processor, implements a method according to an exemplary embodiment of the present disclosure.

[0010] It should be understood that the contents described in this section are not intended to depict key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will be readily understood from the following description.

[0011] BRIEF DESCRIPTION OF THE DRAWINGS The drawings are used for a better understanding of the present solution and are not intended to limit the present disclosure. [Brief explanation of the drawings]

[0012] [Figure 1] 1 is an example of an application scene of a display method and a display device according to an exemplary embodiment of the present disclosure. [Figure 2] 1 is a flowchart of a display method according to an exemplary embodiment of the present disclosure. [Figure 3] 10 is a flowchart illustrating another example of a display method according to an exemplary embodiment of the present disclosure. [Figure 4A] 10 is a flowchart of an example of operations for determining candidate terms and candidate term annotation information according to an exemplary embodiment of the present disclosure. [Figure 4B] 10 is a flowchart of another example of operations for determining candidate terms and candidate term annotation information according to an exemplary embodiment of the present disclosure. [Figure 5A] 1 is an interface for displaying an example of annotation information about content and terms according to an exemplary embodiment of the present disclosure. [Figure 5B] 10 is an interface for showing another example of annotation information regarding content and terms according to an exemplary embodiment of the present disclosure. [Figure 6] FIG. 1 is a block diagram of an example of a display device according to an exemplary embodiment of the present disclosure. [Figure 7A] FIG. 10 is a block diagram of another example of a display device according to an exemplary embodiment of the present disclosure. [Figure 7B] FIG. 7B is a diagram showing the signal flow between the modules of the display device shown in FIG. 7A. [Figure 8] FIG. 10 is a block diagram for realizing another example of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0013] Hereinafter, exemplary embodiments of the present disclosure will be described with reference to the drawings, which will help to understand various details of the embodiments of the present disclosure and should be considered as examples. Therefore, those skilled in the art may make various changes and modifications to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and simplicity, descriptions of known functions and structures will be omitted in the following description.

[0014] The display method and display device according to the exemplary embodiment of the present disclosure can be applied to various natural language processing scenarios, such as subtitle translation, machine simultaneous interpretation, content summary extraction, etc. As an application example, Fig. 1 illustrates the application of the display method and display device according to the exemplary embodiment of the present disclosure to a machine simultaneous interpretation scenario. Fig. 1 will be described in detail below.

[0015] Machine simultaneous interpretation utilizes speech recognition and machine translation technology to automatically recognize the content of a speaker's speech, convert the speech into text, and translate it into the target language. With the development of globalization and the increasing frequency of international exchanges, the demand for machine simultaneous interpretation is increasing, and there is a wide scope for its development.

[0016] As shown in FIG. 1, in a natural language processing scenario such as machine simultaneous translation, there may be multiple users 101-104, one of which (e.g., user 101 is the speaker) speaks, while the other users 102, 103, and 104 view the translation results of the machine simultaneous translation on their respective devices (e.g., electronic devices such as mobile phones, personal computers, and monitors). When user 101 speaks, his or her voice is collected and speech recognition is performed thereon, and whether or not an industry term exists in the corresponding speech recognition result can be determined through a speech processing method according to an exemplary embodiment of the present disclosure. If an industry term exists, the corresponding content can be processed using the speech processing method according to an embodiment of the present disclosure.

[0017] Those skilled in the art will appreciate that the present disclosure is not limited to this scene, but can be applied to a variety of scenes requiring natural language processing.

[0018] FIG. 2 shows a flowchart of a display method according to an exemplary embodiment of the present disclosure. As shown in FIG. 2, a display method 200 according to an exemplary embodiment of the present disclosure may include the following operations.

[0019] In step S210, the content to be displayed is obtained, which may include at least one of audio, text, and image.

[0020] For example, if the content to be displayed includes audio, the speaker's audio may be collected when the speaker speaks and processed to obtain audio processing results. For example, the collected audio may be recognized using audio recognition technology and processed using semantic analysis technology, translation technology, etc., to obtain audio processing results. In one example, the collected audio may be recognized using various trained audio recognition models, and the recognition is essentially real-time. For example, audio recognition may be performed based on a network model such as a Bidirectional Encoder Representations of Transformers (BERT) network or a TRANSFORMER network.

[0021] In another example, if the content to be displayed includes an image, the image can be recognized using a character recognition technique such as Optical Character Recognition (OCR), thereby obtaining an image recognition result.

[0022] As another example, when the content to be displayed contains text, for example, in the application scene of subtitle translation or text summary extraction, the content to be displayed may be text with a large number of characters, and natural language processing technology is used to recognize the characters contained therein and to perform subsequent target term extraction.

[0023] In step S220, target terms are extracted from the content using term extraction rules. The term extraction rules can be based on at least one of a trained tagging model, word frequency analysis, text style difference, etc. For example, the trained tagging model can be a tagging model employing, for example, the BERT architecture, and the term extraction model is realized by training on a term tagging dataset. As will be appreciated by those skilled in the art, the architecture of the tagging model is not limited to the BERT network, and various types of training models capable of realizing term extraction can be adopted. As another example, term extraction rules based on word frequency analysis can be based on the fact that terms always appear less frequently in general domains and more frequently in specialized domains. Therefore, by calculating word probabilities, words that meet the above conditions can be found and used as terms. Furthermore, if the content to be displayed includes text, the term extraction rules can be based on text style difference. In one example, keywords can be extracted for specific styles in text, such as bold, italics, and short, independent appearances. As will be appreciated by those skilled in the art, the above term extraction rules may be used alone or in combination in any combination manner.

[0024] In step S230, in response to extracting at least one target term, annotation information for the at least one target term is acquired. The annotation information may include at least one of information such as an interpretation or explanation of the target term, a translation result corresponding to the target term, etc. In one example, the annotation information for the at least one target term can be acquired by querying a local database or accessing the Internet. For querying, the local database can store accumulated industry terms for each field and their corresponding annotation information. In addition, acquiring the annotation information for the at least one target term via the Internet can include providing a service for accessing, for example, various encyclopedia apps via the Internet, thereby acquiring annotation information related to the term.

[0025] In step S240, annotation information for at least one target term and the content are displayed. That is, both the content and the annotation information for the target term included in the content can be displayed. In one example, annotation information for a term can be displayed simultaneously with the content. Furthermore, a term corresponding to annotation information included in the content can be displayed with a different visual effect from other parts of the content so as to highlight and stand out.

[0026] An exemplary embodiment of the present disclosure provides a display method, automatically performs term extraction, obtains annotation information about terms, and displays the content and the annotation information about the terms, thereby providing intelligent natural language processing services with little or no manual intervention, and at the same time providing users with convenient term customization and enhancing their understanding of the content.

[0027] To further improve the efficiency of term extraction and the accuracy of the annotation information thereof, the display method according to the exemplary embodiment of the present disclosure may additionally include predetermining a plurality of candidate terms and their corresponding candidate annotation information for use in determining the target term. Figure 3 shows a flowchart of another example of the display method according to the embodiment of the present disclosure.

[0028] As shown in FIG. 3, the display method 300 may include the following operations. In step S305, a plurality of candidate terms and corresponding candidate term annotation information are determined based on the related content of the content to be displayed using the term extraction rules. The related content is content related to the content to be displayed, and in a conference scene, it may include the speaker's speech transcript, the speaker's screen image, a conference-related material library, etc.; in a subtitle translation scene, it may include movie-related subtitles, etc. In one example, a database of candidate terms and candidate term annotations can be created and stored based on the related content, so that terms can be quickly and accurately extracted and term annotation information can be obtained during term recognition.

[0029] In step S310, the content to be displayed can be obtained. Step S310 is similar to step S210 shown in Figure 2, and therefore a description thereof will be omitted.

[0030] Then, by performing an analysis on the content, target terms contained in the content can be extracted. Since a plurality of candidate terms and candidate term annotation information are determined in step S305, it can be determined in step S320 whether the content includes at least one candidate term, and in response to determining that the content includes a candidate term, the included candidate term is extracted as a target term.

[0031] In step S330, the stored candidate term annotation information corresponding to the candidate term may be obtained and used as annotation information for the target term.

[0032] In step S340, annotation information of the target term contained in the content can be displayed at the same time as the content is displayed. Step S340 is similar to step S240 shown in FIG. 2, and therefore a description thereof will be omitted.

[0033] Several examples for determining candidate terms and candidate term annotation information will now be described with reference to FIGS. 4A and 4B.

[0034] 4A is a flowchart of a first example of operations for determining candidate terms and candidate term annotation information according to an exemplary embodiment of the present disclosure. As shown in FIG. 4A, the operations may include the following operations:

[0035] In step S405-1a, related text related to the content to be displayed is received. In this example, the related text includes, but is not limited to, the speaker's transcript, the speaker's reference material, related subtitles, etc.

[0036] In step S405-2a, a plurality of candidate terms can be determined from the related text using the term extraction rules, and corresponding candidate term annotation information can be obtained. For example, the above-mentioned term extraction rules can be used to extract an initial candidate glossary from the speech manuscript (ppt) or related documents; and the initial candidate glossary can be selected and filtered to remove duplicates, thereby obtaining a final candidate glossary.

[0037] 4B is a flowchart of a second example of operations for determining candidate terms and candidate term annotation information according to an exemplary embodiment of the present disclosure. As shown in FIG. 4B, the operations may include the following operations.

[0038] In step 405-1b, a related image related to the content to be displayed is obtained, for example, the related image may be the screen image when the speaker speaks.

[0039] In step 405-2b, the related image is recognized to obtain a related image recognition result. For example, various recognition means can be used to recognize information contained in the screen, such as optical character recognition means to recognize character information contained in the related image.

[0040] In step 405-3b, a plurality of candidate terms can be determined from the related image recognition results using the term extraction rules as described above, and corresponding candidate term annotation information can be obtained.

[0041] In another example, a general-purpose or industry-specific term library can be added, so that terms included in the corresponding library can be used as candidate terms. For example, in a scenario where simultaneous interpretation is performed during a conference, the term library can be a database provided by the conference organizer, which can enable faster and more accurate extraction of terms and acquisition of annotation information related to the terms.

[0042] Although the above describes some examples of operations for determining candidate terms, those skilled in the art will recognize that the concept of the present invention can include other examples, and different examples can be combined in any manner without departing from the concept of the present invention.

[0043] The candidate terms determined in this manner can be applied to the extraction of all target terms. Alternatively, after the above-described process of determining candidate terms, the first K candidate terms can be selected by a voting mechanism as a final candidate glossary, which can then be applied to the extraction of target terms. As described above, after obtaining content to be displayed, it is determined whether the content includes at least one of multiple candidate terms. In response to determining that the content includes at least one candidate term, corresponding candidate terms and their corresponding candidate term annotation information can be extracted as target terms and annotation information for the target terms. Therefore, by predetermining multiple candidate terms and their corresponding candidate annotation information, it is possible to not only accelerate the extraction of target terms, but also improve the accuracy of annotation information, thereby enhancing the user's understanding of the content.

[0044] Furthermore, in the example of determining candidate terms and their corresponding candidate term annotation information as described above, the method according to the embodiment of the present disclosure may further include an operation of auditing the determined plurality of candidate terms and their corresponding candidate term annotations. For example, the plurality of candidate terms and / or their corresponding candidate term annotations determined by an auditor may be audited manually. As will be understood by those skilled in the art, in addition to the artificial auditing, an appropriate auditing algorithm may be additionally combined or an auditing algorithm may be used alone to audit the candidate terms and / or related annotation information. This allows for the extraction and annotation of terms with less manual effort, thereby providing more specialized term annotations.

[0045] 5A and 5B are examples for displaying annotation information about content and terms according to an embodiment of the present disclosure.

[0046] 5A and 5B show display screens of a user device using a display method according to an exemplary embodiment of the present disclosure. The display method according to an exemplary embodiment of the present disclosure can display both annotation information for at least one target term and content to be displayed. As shown in FIGS. 5A and 5B, the display screen may include a first area 510 for displaying the content to be displayed, a second area 520a or 520b for displaying annotation information for the term, and a third area 530 for displaying other content. Specifically, FIG. 5A shows an exemplary screen displaying annotations for the target term in only the target language in the second area 520a; and FIG. 5B shows an exemplary screen displaying annotations for the target term in both the target language and the source language in the second area 520b.

[0047] In a simultaneous interpretation scenario, the first area 510 displays the speaker's speech content and the corresponding translation results, the second area 520a / 520b displays annotations of target terms included in the speech content, and the third area 530 displays a screen of the conference site. For example, if a speaker utters the phrase "We implanted an intelligent brain into the robot," the speech can be acquired based on the display method of the embodiment of the present disclosure, and speech recognition and processing technologies can be used to recognize that the source language of the speech is English and the speech content is "We implanted an intelligent brain into the robot." Furthermore, as can be seen from the system settings, the target language is, for example, Japanese or Chinese. In this situation, as shown in FIGS. 5A and 5B, the first area 510 displays the Japanese phrase, i.e., "We implant an intelligent brain into the robot" (or, in Chinese,

[0048]

number

[0049] ) to display the translation results of the spoken content. Then, by analyzing the content using term recognition rules or matching against a candidate glossary, it can be determined that "intelligent brain" is a term 515 included in the phrase, and therefore annotation information corresponding to "intelligent brain" can be obtained. Thus, in this example, as shown in FIG. 5A, "intelligent brain" in Japanese (Chinese:

[0050]

number

[0051] ) 515. Alternatively, as shown in FIG. 5B, annotation information for the term can be displayed in both Japanese and English in the second area 520b, which can help source language users and target language users better understand the related content.

[0052] It should also be noted that in the first area for displaying the content, the visual effect of the target term is set to be different from the visual effect of other parts of the content. For example, as shown in Figures 5A and 5B, the target term can be highlighted in the form of highlighting, which indicates to the user that the word belongs to an industry term and has viewable annotation information, and thereby helps the user quickly understand the related audio content by combining the annotation information. As will be appreciated by those skilled in the art, in addition to highlighting, other styles, such as italics, bold, underline, etc., can be used to distinguish and display the target term.

[0053] This allows the display method according to the exemplary embodiment of the present disclosure to simultaneously display content and perform terminology intervention, providing annotations to the terms, thereby allowing the user to better understand the associated content.

[0054] Moreover, the exemplary embodiment of the present disclosure further provides a display device, as shown in Figure 6. Figure 6 is a block diagram of an example of a display device according to the exemplary embodiment of the present disclosure.

[0055] As shown in FIG. 6, the display device 600 may include a content obtaining module 610 , a term extraction module 620 , an annotation information obtaining module 630 and a display module 640 .

[0056] The content acquisition module 610 may be configured to acquire content to be displayed. The content to be displayed may include at least one of audio, text, and images. For example, the content acquisition module 610 may include an audio processing submodule 611, which is configured to process audio and acquire audio processing results when the content to be displayed includes audio. The content acquisition module 610 may also include an image recognition submodule 612, which is configured to perform optical character recognition on the image and acquire image recognition results when the content to be displayed includes an image. As another example, the content acquisition module 610 may also include a text submodule 613, which is configured to acquire and process text included in the content when the content to be displayed includes text.

[0057] The term extraction module 620 may be configured to extract target terms from content using term extraction rules, which may be based on at least one of a trained tagging model, word frequency analysis, text style differences, etc. As will be appreciated by those skilled in the art, the above term extraction rules may be used alone or in any combination.

[0058] The annotation information acquisition module 630 may be configured to acquire annotation information for the at least one target term in response to extracting the at least one target term. The annotation information acquisition module 630 may acquire annotation information for the at least one target term, such as information on the interpretation and explanation of the target term, translation results corresponding to the target term, etc., by querying a local database or accessing the Internet.

[0059] The display module 640 may be configured to display annotation information for at least one target term and the content to be displayed. As described above, the display module 640 may display annotation information for a term simultaneously with displaying the content, where a term corresponding to annotation information included in the content may be displayed with a visual effect different from other parts other than the term, thereby emphasizing and highlighting the term. In one example, the display module 640 is further configured to display the translation result of the content in the target language in the first area, and to display annotation information for at least one target term in the target language in the second area. Optionally, the display module 640 is further configured to display the translation result of the content in the target language in the first area, and to display annotation information for at least one target term in both the source language of the speech and the target language in the second area.

[0060] Exemplary embodiments of the present disclosure can provide a display device and provide intelligent natural language processing services with little or no manual intervention, while providing users with convenient terminology customization and enhancing their understanding of the content.

[0061] FIG. 7A is a block diagram illustrating another example of a display device according to an exemplary embodiment of the present disclosure. The display device 700 shown in FIG. 7A may include a content acquisition module 710, a term extraction module 720, an annotation information acquisition module 730, and a display module 740, and is similar to the display device 600 shown in FIG. 6. The display device 700 may additionally include a database module 750, which can directly add a term library containing multiple industry terms and use the multiple industry terms as multiple candidate terms. The voice processing sub-module 711, image recognition sub-module 712, and text sub-module 713 in the content acquisition module 710 can also receive related content related to the content to be displayed, thereby predetermining multiple candidate terms and their corresponding candidate annotation information. This improves the efficiency of term extraction and the accuracy of the annotation information.

[0062] In one example, the text sub-module 713 may be configured to receive related text related to the content to be displayed, in which case the term extraction module 720 may be further configured to determine a plurality of candidate terms from the related text using the term extraction rules, and, in response to determining that the content to be displayed includes at least one of the plurality of candidate terms, extract the at least one candidate term as a target term.

[0063] In another example, the image recognition sub-module 712 may be configured to obtain related images related to the content to be displayed, recognize the related images, and obtain related image recognition results, wherein the term extraction module 720 may be further configured to determine a plurality of candidate terms from the related image recognition results using the term extraction rules, and extract the at least one candidate term as a target term in response to determining that the content includes at least one of the plurality of candidate terms.

[0064] In yet another example, the database module 750 may be configured to add a database in which a plurality of industry terms are stored, and to set the plurality of industry terms as a plurality of candidate terms. The term extraction module 720 may be further configured to extract at least one candidate term as a target term in response to determining that the content to be displayed includes at least one of the plurality of candidate terms. Figure 7B illustrates signal flows between modules of a display device according to an exemplary embodiment of the present disclosure.

[0065] 7B, the content acquisition module 710 can acquire content to be displayed. The content to be displayed is provided to the term extraction module 720, which uses term extraction rules to recognize target terms from the content. In response to extracting at least one target term from the content to be displayed, the term extraction module 720 provides the target term to the annotation information acquisition module 730, so that the annotation information acquisition module 730 acquires annotation information corresponding to the target term.

[0066] The display module 740 receives the content to be displayed from the content acquisition module 710, the target terms from the term extraction module 720, and the annotation information from the annotation information acquisition module 730, and displays the content to be displayed in the first area of the display module and the annotation information in the second area, where the target terms included in the content to be displayed are displayed with a different display effect from other parts other than the target terms, for example, the target terms are highlighted in the first area.

[0067] Additionally, the display device 700 can predetermine candidate terms and candidate annotation information, thereby further improving the efficiency of term extraction and the accuracy of the annotation information.

[0068] In an example of determining candidate terms and candidate annotation information, the speech processing device 700 may additionally include a database module 750. The text sub-module 713 may provide relevant text related to the content to be displayed to the term extraction module 720 to determine candidate terms. The image recognition sub-module 712 may receive relevant images related to the content to be displayed, obtain relevant image recognition results using, for example, OCR recognition technology, and provide the relevant image recognition results to the term extraction module 720 to determine candidate terms. The database module 750 may directly receive a relevant term library and use terms included in the term library as candidate terms, where the term library may be a general-purpose term library or a dedicated term library.

[0069] If a candidate term is determined, the annotation information acquisition module 730 may acquire annotation information about the candidate term.

[0070] As described above, by predetermining multiple candidate terms and their corresponding candidate annotation information, it is possible to not only accelerate the extraction of target terms, but also improve the accuracy of the annotation information, thereby enhancing the user's understanding of the content.

[0071] As shown in Figure 7B, when determining candidate terms and candidate annotation information, the auditor / auditor algorithm can audit multiple candidate terms and / or their corresponding candidate term annotations. In this way, term extraction and term annotation can be achieved with low manual intervention.

[0072] Therefore, the display device provided by this exemplary embodiment can not only provide intelligent natural language processing services with little or no manual intervention, but also provide users with convenient term customization services, thereby enhancing users' understanding of the content. Furthermore, by predetermining multiple candidate terms and their corresponding candidate annotation information, it is possible to accelerate the extraction of target terms and improve the accuracy of annotation information, thereby improving users' understanding of the content.

[0073] In the technical solution disclosed herein, the acquisition, storage, application, etc. of user personal information comply with the provisions of relevant laws and regulations and are not contrary to public order and morals.

[0074] According to embodiments of the present disclosure, the present disclosure further provides an electronic device, a readable storage medium, and a computer program product.

[0075] 8 illustrates a schematic block diagram of an example electronic device 800 capable of implementing embodiments of the present disclosure. The electronic device is intended to represent various types of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. The electronic device may also represent various types of mobile devices, such as personal digital assistants, mobile phones, smartphones, wearable devices, and other similar computing devices. The components, their connections and relationships, and their functions illustrated herein are merely exemplary and do not limit the implementation of the present disclosure as described and / or claimed herein.

[0076] 8, the electronic device 800 includes a computing unit 801, which can perform various appropriate operations and processes based on a computer program stored in a read-only memory (ROM) 802 or loaded from a storage unit 808 into a random access memory (RAM) 803. The RAM 803 can further store various programs and data necessary for the operation of the electronic device 800. The computing unit 801, the ROM 802, and the RAM 803 are interconnected by a bus 804. An input / output interface 805 is further connected to the bus 804.

[0077] The components of the electronic device 800 are connected to an I / O interface 805, which includes an input unit 806, such as a keyboard, a mouse, etc., an output unit 807, such as various types of displays, speakers, etc., a storage unit 808, such as a magnetic disk, an optical disk, etc., and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 enables the device 800 to exchange information / data with other devices via a computer network, such as the Internet, and / or various telecommunication networks.

[0078] The computing unit 801 may be a general-purpose and / or dedicated processing module having various processing and computation capabilities. Examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various operational machine learning model algorithm computing units, a digital signal processor (DSP), any suitable processor, controller, microcontroller, etc. The computing unit 801 performs each of the methods and steps described above, such as the methods and steps shown in FIGS. 2-5B. For example, in some embodiments, the methods and steps shown in FIGS. 2-5B are implemented as computer software programs tangibly contained in a machine-readable medium, such as the storage unit 808. In some embodiments, some or all of the computer programs are loaded and / or installed into the device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, it can perform one or more steps of the above-described methods. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the above methods and steps in any other suitable manner (eg, via firmware).

[0079] Various embodiments of the systems and techniques described herein may be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include one or more computer programs executed and / or interpreted by a programmable system including at least one programmable processor, which may be a special purpose or general purpose programmable processor, capable of receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

[0080] The program code for implementing the methods of the present disclosure can be written in any combination of one or more languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus, so that when the program code is executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are performed. The program code may be executed entirely on a device, partially on a device, as part of a separate software package and partially on a remote device, or entirely on a remote device or server.

[0081] In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain or store a program for use with or in connection with an instruction execution system, device, or apparatus. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium includes, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include one or more wire-based electrical connections, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact flash memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0082] To provide for user interaction, the systems and techniques described herein can be implemented on a computer that includes: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) through which a user can provide input to the computer. Other types of devices can also be used to provide for user interaction; for example, the feedback provided to the user can be any form of sensing feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and can receive input from the user in any form (including voice input, audio input, or tactile input).

[0083] The systems and techniques described herein can be implemented in a computing system that includes background components (e.g., a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with embodiments of the systems and techniques described herein), or a computing system that includes any combination of such background, middleware, or front-end components. The components of the system can be connected to each other by any form or medium of digital data communication (e.g., a communications network). Examples of communications networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0084] A computer system may include clients and servers. Clients and servers are generally remote and typically interact through a communication network. The relationship of client and server is created by computer programs running on the corresponding computers and having a client-server relationship.

[0085] It should be understood that steps may be rearranged, added, or deleted using various types of flows shown above. For example, the steps described in the present disclosure may be performed in parallel, sequentially, or in a different order, and the present specification is not limited thereto as long as the desired results of the technical solutions of the present disclosure can be achieved.

[0086] The above specific embodiments do not limit the scope of protection of the present disclosure. Those skilled in the art should understand that various modifications, combinations, subcombinations, and substitutions can be made based on design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principle of the present disclosure should be included within the scope of protection of the present disclosure.

Claims

1. A display method by a processor, comprising: Obtaining content to be displayed; extracting target terms from the content using term extraction rules; In response to extracting the at least one target term, obtaining annotation information for the at least one target term; displaying annotation information of the at least one target term and the content; the term extraction rules are based on at least one of a trained tagging model, a word frequency analysis, and a text style difference; Annotation information for the at least one target term can be obtained by querying a local database or accessing the Internet, and the annotation information includes at least one of an interpretation or explanation of the target term and information on a translation result corresponding to the target term; Displaying the annotation information of the at least one target term and the content includes: displaying the content in a first area and displaying annotation information for the at least one target term in a second area; wherein, in the first region, the display visual effect of the at least one target term is different from the display visual effect of other parts of the content; Displaying the content in the first area and displaying annotation information for the at least one target term in the second area includes: displaying a translation result of the content in a target language in a first area, and displaying annotation information for the at least one target term in the target language in a second area; obtaining a related image related to the content; performing optical character recognition on the related image to obtain a related image recognition result; determining a plurality of candidate terms from the related image recognition results using the term extraction rules; further comprising predetermining a plurality of candidate terms and corresponding candidate term annotation information; receiving associated text related to the content; determining a plurality of candidate terms from the related text using the term extraction rules; Here, extracting target terms from the content using the term extraction rules includes: responsive to determining that the content includes at least one of the plurality of candidate terms, extracting the at least one candidate term as the target term; A database of candidate terms and candidate term annotation information is created and stored based on the related image or the related text, and when a candidate term is determined, the stored candidate term annotation information corresponding to the candidate term is obtained and used as annotation information for the target term. Display method.

2. The content includes at least one of audio, text, and images. The display method according to claim 1 .

3. If the content includes audio, extracting target terms from the content using term extraction rules further includes: processing the audio to obtain an audio processing result; and extracting target terms from the speech processing result using the term extraction rules. The display method according to claim 2.

4. If the content includes an image, extracting target terms from the content using term extraction rules further includes: performing optical character recognition on the image to obtain an image recognition result; and extracting target terms from the image recognition results using the term extraction rules. The display method according to claim 2.

5. The method further includes adding a database in which a plurality of industry terms are stored, and setting the plurality of industry terms as a plurality of candidate terms; Here, extracting target terms from the content using the term extraction rules includes: responsive to determining that the content includes at least one of the plurality of candidate terms, extracting the at least one candidate term as the target term. The display method according to claim 1 .

6. Displaying the content in the first area and displaying annotation information for the at least one target term in the second area includes: displaying a translation result of the content in a target language in a first area, and displaying annotation information for the at least one target term in both the source language of the content and the target language in a second area. The display method according to claim 1 .

7. a content retrieval module configured to retrieve content to be displayed; a term extraction module configured to extract target terms from the content using term extraction rules; an annotation information obtaining module configured to obtain annotation information for the at least one target term in response to extracting the at least one target term; a display module configured to display annotation information of the at least one target term and the content; the term extraction rules are based on at least one of a trained tagging model, a word frequency analysis, and a text style difference; Annotation information for the at least one target term can be obtained by querying a local database or accessing the Internet, and the annotation information includes at least one of an interpretation or explanation of the target term and information on a translation result corresponding to the target term; the display module is configured to display the content in a first area and display annotation information for the at least one target term in a second area; wherein, in the first region, the display visual effect of the at least one target term is different from the display visual effect of other parts of the content; the display module is further configured to display a translation result of the content in a target language in a first area, and display annotation information for the at least one target term in the target language in a second area; further including an image recognition sub-module configured to obtain related images related to the content, recognize the related images, and obtain related image recognition results; wherein the term extraction module is further configured to determine a plurality of candidate terms from the related image recognition results using the term extraction rule, and in response to determining that the content includes at least one of the plurality of candidate terms, extract the at least one candidate term as the target term; The content acquisition module: further comprising a text sub-module configured to receive associated text related to the content; wherein the term extraction module is further configured to determine a plurality of candidate terms from the related text using the term extraction rules; and in response to determining that the content includes at least one of the plurality of candidate terms, extract the at least one candidate term as the target term; A database of candidate terms and candidate term annotation information is created and stored based on the related images or the related text. When a candidate term is determined, the annotation information acquisition module acquires the stored candidate term annotation information corresponding to the candidate term and uses it as annotation information for the target term. Display device.

8. The content includes at least one of audio, text, and images. The display device according to claim 7 .

9. the content acquisition module further includes an audio processing sub-module configured to process the audio to obtain an audio processing result when the content includes audio; wherein the term extraction module is configured to extract target terms from the speech processing result using the term extraction rules. The display device according to claim 8 .

10. The content acquisition module further includes an image recognition sub-module configured to, when the content includes an image, acquire an image recognition result by performing optical character recognition on the image; wherein the term extraction module is configured to extract target terms from the image recognition result using the term extraction rules. The display device according to claim 8 .

11. a database module configured to add a database in which a plurality of industry terms are stored and to set the plurality of industry terms as a plurality of candidate terms; wherein the term extraction module is further configured, in response to determining that the content includes at least one of the plurality of candidate terms, to extract the at least one candidate term as the target term. The display device according to claim 7 .

12. The display module is further configured to display a translation result of the content in a target language in a first area, and to display annotation information for the at least one target term in both the source language of the content and the target language in a second area. The display device according to claim 7 .

13. at least one processor; a memory communicatively coupled to the at least one processor; The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, causing the at least one processor to perform the method of any one of claims 1 to 6.

14. A non-transitory computer-readable storage medium having computer instructions stored thereon, comprising: The computer instructions cause a computer to carry out the method of any one of claims 1 to 6 storage medium.

15. A computer program which, when executed by a processor, implements the method according to any one of claims 1 to 6.

Images