Word disambiguation method, apparatus and electronic device

Abstract

Embodiments of the present application disclose a word disambiguation method, device and electronic equipment. A specific implementation of the method comprises: in response to viewing a word in a target word book, obtaining an explanation and a corresponding scene label of the viewed word, wherein the scene label comprises a spoken language scene and a written language scene, and the explanation and the scene label are determined based on content from which the viewed word originates; determining extended information of the viewed word based on the explanation and the scene label; and presenting the explanation and the extended information of the viewed word. The implementation makes the learned word more suitable for actual scenes, and improves learning efficiency.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and more specifically to word disambiguation methods, apparatus, and electronic devices. Background Technology

[0002] Currently, most users learn English by focusing on individual words. However, many words have multiple meanings, and this word-based learning lacks a clear objective, making it difficult for users to remember most of the definitions. Therefore, how to learn a word by focusing on a specific definition is a problem that urgently needs to be solved. Summary of the Invention

[0003] This disclosure is provided to briefly introduce the concepts, which will be described in detail in the subsequent Detailed Description section. This disclosure is not intended to identify key or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0004] In a first aspect, embodiments of this disclosure provide a word disambiguation method, comprising: in response to viewing words in a target vocabulary book, obtaining the definition and corresponding scene tags of the searched word, wherein the scene tags include spoken language scenes and written language scenes, and the definition and scene tags are determined based on the content from which the searched word originates; determining extended information of the searched word based on the definition and scene tags; and presenting the definition and extended information of the searched word.

[0005] Secondly, embodiments of this disclosure provide a word disambiguation device, comprising: an acquisition unit, configured to acquire the definition and corresponding scene tags of the searched word in response to viewing a word in a target vocabulary book, wherein the scene tags include spoken language scenes and written language scenes, and the definition and scene tags are determined based on the content from which the searched word originates; a determination unit, configured to determine extended information of the searched word based on the definition and scene tags; and a presentation unit, configured to present the definition and extended information of the searched word.

[0006] Thirdly, embodiments of this disclosure provide an electronic device, including: one or more processors; and a storage device for storing one or more programs, which, when executed by the one or more processors, cause the one or more processors to implement the word disambiguation method as described in the first aspect.

[0007] Fourthly, embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon that, when executed by a processor, implements the steps of the word disambiguation method as described in the first aspect.

[0008] The word disambiguation method, apparatus, and electronic device provided in this disclosure obtain the definition and corresponding scene tag of the searched word in response to viewing words in a target vocabulary book; then, based on the definition and scene tag, determine the extended information of the searched word; and finally, present the definition and extended information of the searched word. Since the definition and scene tag are determined based on the content from which the searched word originates, and the scene tag includes spoken and written scenes, this method ensures that the definition of the viewed word is the definition found in the content from which the word originates, and associates the extended information of the word with the scene, making the learned words more relevant to real-world scenarios and improving learning efficiency. Attached Figure Description

[0009] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0010] Figure 1 This is a flowchart of an embodiment of the word disambiguation method according to the present disclosure;

[0011] Figure 2 This is a schematic diagram of an application scenario of the word disambiguation method according to this disclosure;

[0012] Figure 3 This is a schematic diagram of the structure of one embodiment of the word disambiguation device according to the present disclosure;

[0013] Figure 4 These are exemplary system architecture diagrams to which the various embodiments of this disclosure can be applied;

[0014] Figure 5 This is a schematic diagram of the structure of a computer system suitable for implementing the electronic device of the present disclosure. Detailed Implementation

[0015] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0016] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0017] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0018] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0019] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0020] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0021] Please refer to Figure 1 The diagram illustrates a flow 100 of an embodiment of a word disambiguation method according to the present disclosure. The word disambiguation method includes the following steps:

[0022] Step 101: In response to viewing the words in the target vocabulary list, obtain the definition and corresponding scene tags of the searched words.

[0023] In this embodiment, the entity executing the word disambiguation method can detect whether the user has viewed words in the target vocabulary list. The target vocabulary list may include, but is not limited to, at least one of the following: words actively added by the user and words the user misread.

[0024] Users can enter the target vocabulary list and actively click on the words in the target vocabulary list. The aforementioned execution entity can also randomly push words from the target vocabulary list to users, thereby enabling them to view the words in the target vocabulary list.

[0025] If a view of a word in the target vocabulary list is detected, the executing entity can obtain the definition and corresponding context tag of the searched word. The context tag can include spoken language contexts and written language contexts. Spoken language typically refers to language used in everyday oral conversation, while written language typically refers to language used when writing and reading articles. Therefore, a spoken language context typically refers to a scenario where everyday spoken language is used for conversation, and a written language context typically refers to a scenario where written and read language is used. The definition typically refers to the explanation or interpretation of the word.

[0026] Here, the above definitions and scene tags are usually determined based on the content from which the searched words originate.

[0027] As an example, if the word searched above corresponds to three definitions: definition A, definition B, and definition C, and the definition of the word searched in the video being played is definition C, if the user searches for the definition of the word searched in the video and adds the word searched and its corresponding definition to the target vocabulary list, then the added definition will be the definition of the word searched in the video being played, i.e., definition C.

[0028] As an example, if the video from which the searched word originates presents a spoken language scene, then the scene tag corresponding to the searched word will be determined as a spoken language scene; if the video from which the searched word originates presents a written language scene, then the scene tag corresponding to the searched word will be determined as a written language scene.

[0029] Step 102: Based on the definition and context tags, determine the extended information of the searched word.

[0030] In this embodiment, the execution entity can determine the extended information of the searched word based on the above definition and the above scenario tags. This extended information is used by the user to further understand the searched word; for example, it may include phonetic information, which typically refers to…

[0031] Here, the aforementioned execution entity can first obtain candidate extended information corresponding to the definition of the searched word. If there are multiple extended information related to the scenario among the candidate extended information, the aforementioned execution entity can filter out the extended information that matches the scenario tag corresponding to the searched word from the candidate extended information.

[0032] As an example, if the word being searched has both colloquial and formal pronunciations, and the context tag for the word being searched is a colloquial context, then the executing entity can add the colloquial pronunciation of the word being searched to the extended information of the word being searched.

[0033] Step 103 presents the definition and extended information of the searched word.

[0034] In this embodiment, the executing entity can present the definition and extended information of the searched word. After viewing the words in the target vocabulary list, the user can jump to the word page, where the definition and extended information of the searched word can be presented. The word page can be presented in the form of a pop-up window.

[0035] The method provided in the above embodiments of this disclosure obtains the definition and corresponding scene tag of the searched word in response to viewing a word in a target vocabulary book; then, based on the definition and scene tag, it determines the extended information of the searched word; and then, it presents the definition and extended information of the searched word. Since the definition and scene tag are determined based on the content from which the searched word originates, and the scene tag includes spoken and written scenarios, this method ensures that the definition of the viewed word is the definition found in the content from which the word originates, and associates the word's extended information with the scenario. That is, if the content from which the word originates is a spoken scenario, then the word's extended information is the extended information of the spoken scenario; if the content from which the word originates is a written scenario, then the word's extended information is the extended information of the written scenario. This makes the learned words more relevant to real-world scenarios and improves learning efficiency.

[0036] In some optional implementations, before obtaining the definition and corresponding context tag of the searched word, the execution entity can add words and their corresponding definitions that meet at least one of the following conditions to the target vocabulary list: words tagged in videos and / or articles; words whose pronunciation does not conform to the preset standard during the oral practice stage; and words from questions answered incorrectly during the test-taking stage. This approach makes the generated target vocabulary list more aligned with user needs.

[0037] Here, users can annotate words while watching videos or reading articles, for example, by clicking or dragging. During the speaking practice phase, users will practice speaking questions. If a user's pronunciation does not meet the preset standard, the incorrectly pronounced words will be added to the target vocabulary list. During the quiz phase, users can add words from incorrectly answered questions to the target vocabulary list; for example, they can add keywords from incorrectly answered questions or words that match their difficulty level.

[0038] In some optional implementations, before adding the word and its corresponding definition to the target vocabulary, the executing agent can detect whether the user performs a word lookup operation (e.g., clicks or drags a word) within the video or article. If a word lookup operation is detected within the video or article, the executing agent can input the source content of the query word and at least two definitions of the query word (usually all definitions of the word) into a pre-trained disambiguation model to obtain the definition of the query word in the video or article. This disambiguation model can be used to characterize the correspondence between the source content of the word and all definitions of the word, and the definition of the word in the source content.

[0039] Here, Oxford Dictionary data can be used as training samples to train the initial model and obtain the aforementioned disambiguation model. Furthermore, information such as part-of-speech and grammatical features can be added to the definitions to expand them, and the expanded definitions can be used as part of the training data.

[0040] The content from which the above query word originates may include at least one of the following: a video from which the above query word originates contains a sentence fragment of the above query word; an article from which the above query word originates contains a sentence fragment of the above query word; and the title from which the above query word originates.

[0041] The aforementioned executing entity can then present the definitions output by the disambiguation model within the aforementioned video or article. For example, the resulting definitions can be presented around the query word (e.g., to the right). This approach allows users to learn the meanings of words within their usage contexts while learning new words, further improving learning efficiency.

[0042] In some optional implementations, after adding the word and its corresponding definition to the target vocabulary, the executing entity can input the content from which the added word originates into a pre-trained scene label recognition model to obtain the scene label corresponding to the added word. The scene label recognition model can be used to represent the correspondence between the content from which the word originates and the scene label corresponding to the word. The content from which the added word originates can include at least one of the following: a video from which the added word originates contains a sentence fragment containing the added word; an article from which the added word originates contains a sentence fragment containing the added word; or the title from which the added word originates. This approach can make the identified scene labels more accurate.

[0043] In some optional implementations, before adding the words and their corresponding definitions to the target vocabulary list, the implementing entity can obtain at least one of the following as content to be pushed: videos, articles, and questions at the target difficulty level, and then push this content. The target difficulty level can be a level that matches the user's language ability; that is, the implementing entity can obtain and push videos, articles, or questions that match the user's language ability. Pushing learning content that matches the user's language ability in this way makes the pushed content more targeted.

[0044] In some optional implementations, the extended information may include example sentences and / or videos, which are typically example sentences and / or videos containing the searched word. The executing entity can determine the extended information of the searched word based on the definition and scenario tags as follows: the executing entity can obtain example sentences and / or videos corresponding to the searched word and definition; the executing entity can obtain example sentences and / or videos matching the searched word and definition from a pre-set example sentence library and / or video library. Then, the executing entity can filter out example sentences and / or videos matching the scenario tags as extended information. This method allows users to learn words by studying example sentences and videos in usage scenarios (spoken or written), further improving learning efficiency.

[0045] In some cases, example sentences and videos can be scene-specific; that is, example sentences can include both colloquial and formal examples, and video subtitles can also include both colloquial and formal subtitles. If the scene tag corresponding to the searched word is a colloquial scene, then colloquial example sentences can be filtered from the corresponding example sentences; if the scene tag corresponding to the searched word is a formal scene, then formal videos can be filtered from the corresponding videos.

[0046] In some optional implementations, the extended information may include at least one of the following: synonyms and antonyms. For example, if the scenario tag corresponding to the searched word is a spoken language scenario, then synonyms and antonyms with the same spoken language scenario tag can be obtained as extended information; if the scenario tag corresponding to the searched word is a written language scenario, then synonyms and antonyms with the same written language scenario tag can be obtained as extended information. This allows users to learn synonyms and antonyms of words in their usage scenarios (spoken or written language scenarios) while learning vocabulary.

[0047] See also Figure 2 , Figure 2 This is a schematic diagram illustrating an application scenario of the word disambiguation method according to this embodiment. Figure 2In the application scenario, when a user clicks on word A in "My Word Book" indicated by icon 201, the user terminal obtains the definition of word A and its corresponding scene tag. Here, the obtained definition is definition C indicated by icon 202, and the scene tag is the spoken language scene indicated by icon 203. The user terminal can use the two pieces of information, definition C and spoken language scene, to determine that the example sentence for word A is a spoken language example sentence 204 containing word A, and to determine that the video for word A is a spoken language video 205 containing word A, and the definition of word A in the spoken language example sentence 204 and the spoken language video 205 is definition C.

[0048] Further reference Figure 3 As an implementation of the methods shown in the above figures, this application provides an embodiment of a word disambiguation device, which is similar to... Figure 1 Corresponding to the method embodiments shown, this device can be specifically applied to various electronic devices.

[0049] like Figure 3 As shown, the word disambiguation device 300 of this embodiment includes: an acquisition unit 301, a determination unit 302, and a presentation unit 303. The acquisition unit 301 is used to acquire the definition and corresponding scene tag of the searched word in response to viewing a word in a target vocabulary book. The scene tag includes spoken language scenes and written language scenes, and the definition and scene tag are determined based on the content from which the searched word originates. The determination unit 302 is used to determine the extended information of the searched word based on the definition and scene tag. The presentation unit 303 is used to present the definition and extended information of the searched word.

[0050] In this embodiment, the specific processing of the acquisition unit 301, determination unit 302, and presentation unit 303 of the word disambiguation device 300 can be referred to Figure 1 The corresponding steps are 101, 102 and 103 in the embodiment.

[0051] In some optional implementations, the word disambiguation device 300 may further include an adding unit (not shown in the figure). The adding unit may be used to add words and their corresponding definitions that meet at least one of the following conditions to the target vocabulary list: words marked in videos and / or articles; words whose pronunciation does not conform to a preset standard during the oral practice stage; and words in questions answered incorrectly during the question-answering stage.

[0052] In some optional implementations, the word disambiguation device 300 may further include a disambiguation unit (not shown in the figure) and a definition presentation unit (not shown in the figure). The disambiguation unit can be used to, in response to performing a word lookup operation in a video or article, input the content from which the query word originates and at least two definitions of the query word into a pre-trained disambiguation model to obtain the definition of the query word in the video or article. The content from which the query word originates includes at least one of the following: the video or article from which the query word originates contains a sentence fragment containing the query word and the title from which the query word originates. The definition presentation unit can be used to present the obtained definition in the video or article.

[0053] In some optional implementations, the word disambiguation device 300 may further include a scene label recognition unit (not shown in the figure). The scene label recognition unit is used to input the content from which the added word originates into a pre-trained scene label recognition model to obtain the scene label corresponding to the added word. The content from which the added word originates includes at least one of the following: a video or article from which the added word originates contains a sentence fragment containing the added word and the title from which the added word originates.

[0054] In some optional implementations, the word disambiguation device 300 may further include a content acquisition unit (not shown in the figure) and a push unit (not shown in the figure). The content acquisition unit may be used to acquire at least one of videos, articles, and questions with a difficulty level of the target difficulty level as content to be pushed; the push unit may be used to push the content to be pushed.

[0055] In some optional implementations, the extended information includes example sentences and / or videos; and the determining unit 302 can be further configured to determine the extended information of the searched word based on the definition and the scene tag in the following manner: obtaining example sentences and / or videos corresponding to the searched word and the definition; and selecting example sentences and / or videos that match the scene tag from the example sentences and / or videos as extended information.

[0056] In some alternative implementations, the extended information mentioned above includes at least one of the following: synonyms and antonyms.

[0057] Figure 4 An exemplary system architecture 400 is shown, in which embodiments of the word disambiguation methods disclosed herein can be applied.

[0058] like Figure 4As shown, system architecture 100 may include terminal devices 4011, 4012, and 4013, network 402, and server 403. Network 402 is used as a medium to provide a communication link between terminal devices 4011, 4012, and 4013 and server 403. Network 402 may include various connection types, such as wired or wireless communication links or fiber optic cables, etc.

[0059] Users can use terminal devices 4011, 4012, and 4013 to interact with server 403 via network 402 to send or receive messages, etc. For example, server 403 can receive extended information retrieval requests sent by terminal devices 4011, 4012, and 4013. Various communication client applications can be installed on terminal devices 4011, 4012, and 4013, such as English learning applications, word lookup applications, video applications, reading applications, instant messaging software, etc.

[0060] Terminal devices 4011, 4012, and 4013, in response to viewing words in a target vocabulary list, can obtain the definition and corresponding context tags of the searched words. The context tags include spoken and written contexts, and the definition and context tags are determined based on the content from which the searched words originate. Subsequently, based on the definition and context tags, extended information about the searched words can be determined. Finally, the definition and extended information about the searched words can be presented.

[0061] Terminal devices 4011, 4012, and 4013 can be either hardware or software. When terminal devices 4011, 4012, and 4013 are hardware, they can be various electronic devices with displays and supporting information interaction, including but not limited to smartphones, tablets, and laptops. When terminal devices 4011, 4012, and 4013 are software, they can be installed in the aforementioned electronic devices. They can be implemented as multiple software programs or software modules (e.g., multiple software programs or software modules used to provide distributed services) or as a single software program or software module. No specific limitations are imposed here.

[0062] Server 403 can be a server that provides various services. For example, it can be a backend server that provides extended information to terminal devices 4011, 4012, and 4013.

[0063] It should be noted that a server 403 can be either hardware or software. When the server 403 is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or as a single server. When the server 403 is software, it can be implemented as multiple software programs or software modules (e.g., used to provide distributed services), or as a single software program or software module. No specific limitations are made here.

[0064] It should also be noted that the word disambiguation method provided in this embodiment is usually executed by terminal devices 4011, 4012, and 4013, and the word disambiguation device is usually set in terminal devices 4011, 4012, and 4013.

[0065] It should be understood that Figure 4 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0066] The following is for reference. Figure 5 It illustrates an electronic device suitable for implementing embodiments of the present disclosure (e.g., Figure 4 A schematic diagram of the structure of the terminal device 500. The terminal device in the embodiments of this disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this disclosure.

[0067] like Figure 5 As shown, the electronic device 500 may include a processing unit (e.g., a central processing unit, a graphics processor, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 into a random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of the electronic device 500. The processing unit 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0068] Typically, the following devices can be connected to I / O interface 505: input devices 506 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 507 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; and communication devices 509. Communication device 509 allows electronic device 500 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 5 An electronic device 500 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 5Each box shown can represent a device or multiple devices as needed.

[0069] Specifically, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 509, or installed from a storage device 508, or installed from a ROM 502. When the computer program is executed by a processing device 501, it performs the functions defined in the methods of embodiments of this disclosure. It should be noted that the computer-readable medium described in embodiments of this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In embodiments of this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In embodiments of this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0070] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: in response to viewing words in a target vocabulary book, obtain the definition and corresponding context tags of the searched word, wherein the context tags include spoken and written contexts, and the definition and context tags are determined based on the content from which the searched word originates; determine extended information about the searched word based on the definition and context tags; and present the definition and extended information about the searched word.

[0071] Computer program code for performing the operations of embodiments of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0072] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0073] According to one or more embodiments of this disclosure, a word disambiguation method is provided, the method comprising: in response to viewing words in a target vocabulary book, obtaining the definition and corresponding scene tags of the searched word, wherein the scene tags include spoken language scenes and written language scenes, and the definition and scene tags are determined based on the content from which the searched word originates; determining extended information of the searched word based on the definition and scene tags; and presenting the definition and extended information of the searched word.

[0074] According to one or more embodiments of this disclosure, before viewing words in a target vocabulary list and obtaining the definition and corresponding scene tag of the searched word, the method includes: adding words and corresponding definitions that meet at least one of the following conditions to the target vocabulary list: words tagged in videos and / or articles; words whose pronunciation does not conform to a preset standard during oral practice; and words in questions answered incorrectly during question-taking.

[0075] According to one or more embodiments of this disclosure, before adding words and corresponding definitions that meet at least one of the following conditions to the target vocabulary, the method includes: in response to performing a word lookup operation in a video or article, inputting the content from which the query word originates and at least two definitions of the query word into a pre-trained disambiguation model to obtain the definition of the query word in the video or article, wherein the content from which the query word originates includes at least one of the following: the video or article from which the query word originates contains a sentence fragment of the query word and the title from which the query word originates; and presenting the obtained definition in the video or article.

[0076] According to one or more embodiments of this disclosure, after adding words and their corresponding definitions that meet at least one of the following conditions to the target vocabulary, the method includes: inputting the content from which the added words originate into a pre-trained scene label recognition model to obtain scene labels corresponding to the added words, wherein the content from which the added words originate includes at least one of the following: the video or article from which the added words originate contains a sentence fragment of the added words and the title from which the added words originate.

[0077] According to one or more embodiments of this disclosure, before adding words and their corresponding definitions that meet at least one of the following conditions to the target vocabulary list, the method includes: obtaining at least one of videos, articles, and questions with a difficulty level of a target difficulty level as content to be pushed; and pushing the content to be pushed.

[0078] According to one or more embodiments of this disclosure, the extended information includes example sentences and / or videos; and the determining unit can be further configured to determine the extended information of the searched word based on the definition and the scene tag in the following manner: obtaining example sentences and / or videos corresponding to the searched word and the definition; and filtering out example sentences and / or videos that match the scene tag from the example sentences and / or videos as extended information.

[0079] According to one or more embodiments of this disclosure, the above extended information includes at least one of the following: synonyms and antonyms.

[0080] According to one or more embodiments of this disclosure, a word disambiguation device is provided, the device comprising: an acquisition unit, configured to acquire the definition and corresponding scene tag of the searched word in response to viewing a word in a target vocabulary book, wherein the scene tag includes spoken language scene and written language scene, and the definition and scene tag are determined based on the content from which the searched word originates; a determination unit, configured to determine extended information of the searched word based on the definition and scene tag; and a presentation unit, configured to present the definition and extended information of the searched word.

[0081] According to one or more embodiments of this disclosure, the word disambiguation device includes an adding unit for adding words and their corresponding definitions that meet at least one of the following conditions to the target vocabulary book: words marked in videos and / or articles; words whose pronunciation does not meet a preset standard during oral practice; and words in questions answered incorrectly during the question-answering stage.

[0082] According to one or more embodiments of this disclosure, the word disambiguation device includes a disambiguation unit and a definition presentation unit. The disambiguation unit is configured to, in response to performing a word lookup operation in a video or article, input the content from which the query word originates and at least two definitions of the query word into a pre-trained disambiguation model to obtain the definition of the query word in the video or article. The content from which the query word originates includes at least one of the following: the video or article from which the query word originates contains a sentence fragment of the query word and the title from which the query word originates. The definition presentation unit is configured to present the obtained definition in the video or article.

[0083] According to one or more embodiments of this disclosure, the word disambiguation device includes a scene label recognition unit, which is used to input the content from which the added word originates into a pre-trained scene label recognition model to obtain the scene label corresponding to the added word. The content from which the added word originates includes at least one of the following: the video or article from which the added word originates contains a sentence fragment containing the added word and the title from which the added word originates.

[0084] According to one or more embodiments of this disclosure, the word disambiguation device includes a content acquisition unit and a push unit. The content acquisition unit is used to acquire at least one of videos, articles, and questions with a difficulty level of a target difficulty level as content to be pushed; the push unit is used to push the content to be pushed.

[0085] According to one or more embodiments of this disclosure, the extended information includes example sentences and / or videos; and the determining unit is further configured to determine the extended information of the searched word based on the definition and the scene tag in the following manner: obtaining example sentences and / or videos corresponding to the searched word and the definition; and filtering out example sentences and / or videos that match the scene tag from the example sentences and / or videos as extended information.

[0086] According to one or more embodiments of this disclosure, the above extended information includes at least one of the following: synonyms and antonyms.

[0087] The units described in the embodiments of this disclosure can be implemented in software or hardware. The described units can also be housed in a processor; for example, a processor may be described as including an acquisition unit, a determination unit, and a presentation unit. The names of these units do not necessarily limit the unit itself; for example, a presentation unit may also be described as "a unit that presents the definition and extended information of the searched word."

[0088] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. A word disambiguation method, characterized in that, include: In response to performing a word lookup operation in a video or article, the content from which the query word originates and at least two definitions of the query word are input into a pre-trained disambiguation model to obtain the definition of the query word in the video or article. The content from which the query word originates includes at least one of the sentence fragments containing the query word in the video or article from which the query word originates, and the title from which the query word originates. The interpretations presented in the aforementioned video or article; In response to viewing words in the target vocabulary list, the definition and corresponding scene tags of the searched words are obtained, wherein the scene tags include spoken language scenes and written language scenes, and the definition and scene tags are determined based on the content from which the searched words originate; Based on the definition and the scene tag, the extended information of the searched word is determined, wherein the extended information includes content that matches the scene tag, and the extended information is semantically consistent with the definition; The definition and extended information of the searched word are presented.

2. The method according to claim 1, characterized in that, Before the step of viewing words in the target vocabulary and obtaining the definition and corresponding scene tag of the searched word, the method includes: Add words that meet at least one of the following conditions and their corresponding definitions to the target vocabulary list: The words that are tagged in the video and / or article; During the oral practice phase, words whose pronunciation does not meet the preset standard; During the test-taking phase, review the words from the questions you answered incorrectly.

3. The method according to claim 2, characterized in that, After adding words and their corresponding definitions that meet at least one of the following conditions to the target vocabulary list, the method includes: The content from which the added word originates is input into a pre-trained scene label recognition model to obtain the scene label corresponding to the added word. The content from which the added word originates includes at least one of the following: the video or article from which the added word originates contains a sentence fragment containing the added word and the title from which the added word originates.

4. The method according to claim 2, characterized in that, Before adding words and their corresponding definitions that meet at least one of the following conditions to the target vocabulary list, the method includes: Select at least one of the following—videos, articles, and questions—that are at the target difficulty level as content to be pushed out. The content to be pushed is then pushed.

5. The method according to claim 1, characterized in that, The extended information includes example sentences and / or videos; as well as The process of determining the extended information of the searched word based on the definition and the scene tag includes: Obtain example sentences and / or videos corresponding to the searched word and its definition; Select example sentences and / or videos that match the scene tags from the example sentences and / or videos as extended information.

6. The method according to any one of claims 1-5, characterized in that, The extended information includes at least one of the following: synonyms and antonyms.

7. A word disambiguation device, characterized in that, include: An input unit is configured to, in response to performing a word lookup operation in a video or article, input the content from which the query word originates and at least two definitions of the query word into a pre-trained disambiguation model to obtain the definition of the query word in the video or article. The content from which the query word originates includes at least one of the sentence fragments containing the query word in the video or article from which the query word originates, and the title from which the query word originates. The first presentation unit is used to present the obtained interpretation in the video or article; The acquisition unit is used to acquire the definition and corresponding scene tag of the searched word in response to viewing the words in the target vocabulary book. The scene tag includes spoken language scene and written language scene. The definition and the scene tag are determined based on the content from which the searched word comes. A determining unit is configured to determine extended information of the searched word based on the definition and the scene tag, wherein the extended information includes content that matches the scene tag, and the extended information is semantically consistent with the definition; The second presentation unit is used to present the definition and extended information of the searched word.

8. An electronic device, characterized in that, include: One or more processors; A storage device having stored one or more programs thereon, which, when executed by the one or more processors, cause the one or more processors to perform the method of any one of claims 1-6.

9. A computer-readable medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-6.

Images