Shortcut phrase trigger translation method and device and computer readable storage medium

Abstract

The invention discloses a shortcut phrase trigger translation method and device and a computer readable storage medium, and relates to the technical field of data processing, the shortcut phrase trigger translation method comprises the following steps: according to a dialogue field selected by a user, rendering and displaying a shortcut phrase corresponding to the dialogue field on a user side; in response to a trigger operation of the user side, determining a target shortcut phrase; matching a corresponding translation voice in a voice library according to the target shortcut phrase, and loading the translation voice to a playing queue; and playing the translated voice in real time according to the sequence of the playing queue. The technical effect of creating a pure foreign language communication environment to improve the foreign language learning effect is achieved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a quick phrase-triggered translation method, device, and computer-readable storage medium. Background Art

[0002] In the scenario of cultivating foreign language listening and speaking skills, especially for children's language enlightenment education, creating a foreign language environment is crucial to improving learning outcomes. However, in non-native foreign language families, parents and educators are limited by their own foreign language proficiency and find it difficult to continuously provide pure foreign language input. Traditional translation methods require inputting text word by word and waiting for translation results. Due to low efficiency, it is difficult to simulate a real language communication environment and effectively create a pure foreign language environment, which affects the immersion and effectiveness of foreign language learning.

[0003] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of this application is to provide a quick phrase-triggered translation method, device and computer-readable storage medium, aiming to solve the technical problem of how to create a pure foreign language communication environment to improve foreign language learning effects.

[0005] To achieve the above purpose, the present application proposes a quick phrase trigger translation method, which includes: According to the conversation field selected by the user, the quick phrase corresponding to the conversation field is rendered and displayed on the user terminal; In response to a trigger operation of the user terminal, determining a target shortcut phrase; Matching a corresponding translation voice in a voice library according to the target shortcut phrase, and loading the translation voice into a play queue; The translated speech is played in real time according to the order of the play queue.

[0006] In one embodiment, before the step of rendering and displaying the quick phrase corresponding to the conversation field selected by the user on the user side, the step includes: Collecting conversation data of the user; Analyzing the conversation data by statistical methods to identify common areas and common phrases of the users; Based on the common fields and the common phrases, construct a user profile and / or a knowledge graph; Based on the user portrait and / or the knowledge graph, generate and store the conversation domain and the corresponding shortcut phrase; Generate a translated speech corresponding to the shortcut phrase and store it in the speech library.

[0007] In one embodiment, the step of constructing a user profile and / or a knowledge graph based on the common fields and the common phrases includes: Constructing the user profile according to the user information bound to the user terminal, in combination with the common fields and the common phrases; and / or The translation resources of the common fields are collected, and entities and relationships are extracted to construct the knowledge graph of each common field.

[0008] In one embodiment, the quick phrase trigger translation method further includes: Inferring the conversation direction of the user according to the target shortcut phrase of the play queue in combination with the user portrait and / or the knowledge graph; Based on the conversation direction, searching a database for relevant quick phrases as recommended phrases; The recommended phrase is rendered to the user end.

[0009] In one embodiment, the step of rendering and displaying the quick phrase corresponding to the conversation field selected by the user on the user terminal includes: According to the conversation field selected by the user, searching a database for a shortcut phrase corresponding to the conversation field; A phrase selection interface is generated according to the shortcut phrase, and the phrase selection interface is rendered and displayed on the user end.

[0010] In one embodiment, the step of determining a target shortcut phrase in response to a trigger operation of the user terminal includes: Based on a triggering operation of a single shortcut phrase, identifying the shortcut phrase as the target shortcut phrase; or Based on the triggering operations of at least two of the shortcut phrases, the shortcut phrases are combined according to a preset rule to serve as the target shortcut phrase.

[0011] In one embodiment, the step of playing the translated speech in real time according to the order of the play queue further includes: Rendering the play queue to the user end; Based on the adjustment operation of the user terminal, the order of the translated voices in the play queue is adjusted to obtain a custom play queue; Based on the confirmation operation of the user terminal, the translated voice is played according to the custom play queue.

[0012] In one embodiment, after the step of playing the translated speech in real time according to the order of the play queue, the method further includes: If it is detected that the user starts the oral dialogue practice function, collecting the user's input voice; Using speech recognition technology to identify the speech features of the input speech; Based on the speech features, a speech evaluation report is generated and rendered to the user end.

[0013] In addition, to achieve the above-mentioned purpose, the present application also proposes a quick phrase triggered translation device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the quick phrase triggered translation method as described above.

[0014] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the quick phrase trigger translation method described above are implemented.

[0015] The present application provides a method for triggering translation by quick phrases. The present application first renders and displays the quick phrases corresponding to the dialogue field on the user side according to the dialogue field selected by the user, responds to the trigger operation of the user side, determines the target quick phrase, matches the corresponding translation voice in the voice library according to the target quick phrase, loads the translation voice to the play queue, and plays the translation voice in real time according to the order of the play queue. By rendering and displaying the quick phrases corresponding to the dialogue field selected by the user, so that the user can quickly find and trigger the required phrases, the time cost of communication is reduced, the target quick phrase is determined in response to the trigger operation of the user side, and the corresponding translation voice is matched in the voice library, the efficiency of translation is improved, and the translation voice is loaded into the play queue, and the translation voice is played in real time according to the order of the play queue to form a pure foreign language auditory environment. The present application achieves the technical effect of creating a pure foreign language communication environment to improve the effect of foreign language learning. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0018] Figure 1 A flowchart diagram of the first embodiment of the quick phrase trigger translation method of the present application; Figure 2A flowchart diagram of the second embodiment of the quick phrase trigger translation method of the present application; Figure 3 A flowchart diagram of the third embodiment of the quick phrase trigger translation method of the present application; Figure 4 A flowchart diagram of the fourth embodiment of the quick phrase trigger translation method of the present application; Figure 5 A schematic diagram of a silencer device of a silencer mask device with a translation function involved in the quick phrase trigger translation method in an embodiment of the present application; Figure 6 A schematic diagram of a translation device of a noise-cancelling mask device with a translation function involved in the quick phrase-triggered translation method in an embodiment of the present application; Figure 7 Schematic diagram of the device structure of the hardware operating environment involved in the quick phrase trigger translation method in the embodiment of the present application.

[0019] Reference numerals: 11. Outer shell; 12. Speaker hole; 14. Screen; 15. Main button; 16. Second audio connection hole; 17. Charging hole; 21. Silencer assembly; 211. First audio connection hole; 215. Silencer shell; 218. Front shell; 219. Back shell; 22. Skin-friendly sound insulation pad.

[0020] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0021] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0022] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0023] The main solutions of the embodiments of this application are: At present, in the process of cross-language communication, foreign languages ​​need to be used frequently for communication. The traditional translation method requires inputting text word by word and waiting for the translation results. It takes a long time to translate, resulting in low communication efficiency and unable to meet the needs of communication in situations that require quick response.

[0024] This application renders and displays the shortcut phrases corresponding to the dialogue field on the user side according to the dialogue field selected by the user, determines the target shortcut phrase in response to the trigger operation of the user side, matches the corresponding translated voice in the voice library according to the target shortcut phrase, loads the translated voice to the play queue, and plays the translated voice in real time according to the order of the play queue. By rendering and displaying the shortcut phrases corresponding to the dialogue field selected by the user, so that the user can quickly find and trigger the required phrases, the time cost of communication is reduced, the target shortcut phrase is determined in response to the trigger operation of the user side, and the corresponding translated voice is matched in the voice library, the efficiency of translation is improved, and the translation voice is loaded into the play queue, and the translated voice is played in real time according to the order of the play queue to ensure the immediacy of translation. This application achieves the technical effect of improving the efficiency of cross-language communication.

[0025] It should be noted that the execution subject of this embodiment can be a silencer mask with a translation function, or a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or a control device that can trigger the translation of a quick phrase capable of realizing the above functions, etc., and this embodiment does not specifically limit this. The following takes a silencer mask with a translation function as an example of the execution subject to illustrate this embodiment and the following embodiments.

[0026] Embodiment 1 Based on this, the present application proposes a quick phrase trigger translation method of the first embodiment, please refer to Figure 1 , the quick phrase triggering translation method comprises: Step S10, according to the conversation field selected by the user, the quick phrase corresponding to the conversation field is rendered and displayed on the user terminal.

[0027] Dynamically display relevant shortcut phrases based on the conversation area selected by the user, thereby helping users communicate more efficiently.

[0028] In this embodiment, the dialogue field is the topic or scene involved in the conversation between the user, including travel, shopping, business, education, etc. Different dialogue fields contain different professional terms and expressions. Quick phrases are short phrases preset for the dialogue field, which are used to quickly convey user intentions to improve communication efficiency. Rendering refers to displaying the quick phrases on the user-side screen in a preset layout. The user end refers to the interface used by the user to access and operate, including the mobile phone APP (Application), the operation screen of the silencer mask with translation function, etc.

[0029] As an optional implementation, a selection interface for a dialogue domain is rendered and displayed on the user side, and based on the user's operation on the selection interface, the dialogue domain selected by the user is determined, and the shortcut phrase corresponding to the dialogue domain is rendered and displayed on the user side.

[0030] Optionally, according to the conversation domain selected by the user, shortcut phrases related to the conversation domain are screened from a database containing all shortcut phrases, a corresponding phrase selection interface is generated according to the screened shortcut phrases, and the phrase selection interface is rendered and displayed on the user end.

[0031] Optionally, step S10 includes: Step S11, according to the conversation field selected by the user, searching a database for a quick phrase corresponding to the conversation field.

[0032] As an optional implementation, the table storing quick phrases in the database includes a field for identifying the conversation field. According to the conversation field selected by the user, a query statement is constructed to retrieve the quick phrases corresponding to the conversation field.

[0033] As another optional implementation, the table storing the quick phrases in the database does not directly include the identifier of the dialog domain, but includes a field for describing the context or purpose of the quick phrases. Based on the text content of the quick phrases, keyword matching, semantic analysis and other technologies, the association rules between the quick phrases and the dialog domain are defined. According to the dialog domain selected by the user, all the quick phrases in the database are retrieved, and the quick phrases are screened according to the defined association rules to determine the quick phrases corresponding to the dialog domain.

[0034] Optionally, the retrieved shortcut phrases are further screened according to the user's usage preference, and a predetermined number of shortcut phrases are selected.

[0035] Step S12, generating a phrase selection interface according to the shortcut phrase, and rendering and displaying the phrase selection interface on the user terminal.

[0036] In this embodiment, the phrase selection interface is an interface for displaying and selecting quick phrases, and the user can select the desired phrase through interactive methods such as clicking and sliding.

[0037] Exemplarily, quick phrase data related to the dialogue field retrieved from a database is received, the quick phrase data is filled in according to a preset phrase selection interface layout, and the filled phrase selection interface is converted into rendering data and transmitted to the user end for rendering and display.

[0038] Optionally, the layout of the phrase selection interface is designed according to the user terminal interface, including the display mode, font size, color, spacing, etc. of the shortcut phrases.

[0039] Step S20: determining a target shortcut phrase in response to a trigger operation of the user terminal.

[0040] Based on the trigger operation on the user side, the specific phrase that the user wants to use is identified and selected from the predefined shortcut phrase list. The user does not need to manually enter the entire phrase, but can select the predefined shortcut phrase through simple interactive operations, further improving the efficiency of communication.

[0041] In this embodiment, the trigger operation is an operation performed by the user on the user terminal to perform a certain action, such as clicking a button, sliding the screen, issuing a voice command, etc. The target shortcut phrase is a shortcut phrase selected by the user through the trigger operation and used for subsequent operations.

[0042] As an optional implementation, an event of triggering an operation on the user side is monitored, an associated identifier is obtained, and a shortcut phrase corresponding to the identifier is determined as a target shortcut phrase.

[0043] Optionally, step S20 includes: Step S21: based on a triggering operation of a single shortcut phrase, identifying the shortcut phrase as the target shortcut phrase.

[0044] Exemplarily, the triggering operation of a user on a single shortcut phrase is monitored, and the corresponding shortcut phrase is identified as the target shortcut phrase.

[0045] Step S22: Based on the triggering operations of at least two of the shortcut phrases, the shortcut phrases are combined according to a preset rule to serve as the target shortcut phrase.

[0046] In this embodiment, the preset rule is a rule for combining shortcut phrases, which defines how to combine multiple shortcut phrases into one shortcut phrase combination.

[0047] Exemplarily, the triggering operation of the user on at least two shortcut phrases is monitored, the shortcut phrases are combined according to the triggering order, and a shortcut phrase combination is generated as a target shortcut phrase.

[0048] Optionally, after the quick phrase combination is generated, a confirmation window is rendered to the user end, and the target quick phrase is determined according to the user's confirmation operation.

[0049] Step S30, matching the corresponding translated speech in the speech library according to the target shortcut phrase, and loading the translated speech into the play queue.

[0050] In this embodiment, the voice library is a database storing translated voices, and each translated voice corresponds to a specific shortcut phrase. The play queue is a list for managing the voices to be played, and when the translated voices are loaded into the play queue, they are played in sequence according to the order in the queue.

[0051] Optionally, the voice database contains translated voices of one or more foreign languages ​​of the shortcut phrase. For a voice database having translated voices of at least two foreign languages, the corresponding translated voice is determined according to the language selected by the user.

[0052] Exemplarily, according to the identifier of the quick phrase selected by the user, the corresponding translated voice is searched in the voice library and loaded into the play queue. If there are other voices in the play queue, the newly loaded translated voice will be added to the end of the queue and wait for playback.

[0053] Step S40, playing the translated speech in real time according to the order of the play queue.

[0054] The translated speech is played to the user in real time according to the order of the speech in the playback queue. Through real-time playback, the user can immediately obtain the translation result to improve the efficiency of cross-language communication.

[0055] In this embodiment, real-time playback refers to playing the translated speech immediately and continuously according to the order of the playback queue.

[0056] As an optional implementation, the play queue is monitored, and when the translated speech of the quick phrase exists in the play queue, the translated speech is played immediately.

[0057] Exemplarily, during the playback process, the playback queue is continuously monitored to ensure that the next voice starts playing immediately after the current voice is finished playing.

[0058] Optionally, step S40 further includes: Step S41, rendering the play queue to the user terminal.

[0059] Rendering the playback queue to the user side allows users to intuitively view and manage the translated voices in the playback queue. Through the visual interface, users can clearly understand which voices are included in the current playback queue, their playback order, and detailed information about each voice.

[0060] Exemplarily, based on the title, duration, play status and other information of each voice in the play queue, rendering data of the list view of the play queue is generated, rendered and displayed in the user-side interface.

[0061] Step S42: Based on the adjustment operation of the user terminal, the order of the translated speech in the play queue is adjusted to obtain a custom play queue.

[0062] In this embodiment, the adjustment operation is a modification operation performed by the user on the order of voices in the play queue through the user terminal, including moving the position of the voice, deleting the voice, adding a new voice to the queue, etc. The custom play queue is the play queue obtained after the user adjustment operation.

[0063] Exemplarily, based on the captured user operations, the play queue data is updated in real time to obtain a custom play queue, and rendering data of a list view of the custom play queue is generated, rendered, and displayed in a user-side interface.

[0064] Step S43: based on the confirmation operation of the user terminal, playing the translated voice according to the custom play queue.

[0065] Exemplarily, when the user completes the adjustment operation and clicks the confirmation or play button, the voice starts to be played in the order of the custom play queue.

[0066] Optionally, during the playback process, playback control functions are provided, including pausing, continuing, stopping, and displaying the currently playing voice information and the remaining playback time.

[0067] As an example of an application scenario of the present application, the shortcut phrase selected by the user in the mobile phone APP interface is sent to a silencer mask device with a translation function connected to the mobile phone, and the translation voice corresponding to the shortcut phrase is broadcast through the silencer mask device.

[0068] Optionally, according to the quick phrase selected by the user in the mobile phone APP interface, the translation voice corresponding to the quick phrase is broadcasted through the built-in translation and broadcasting function of the mobile phone.

[0069] Optionally, based on the shortcut phrase selected by the user in the touch screen interface of the silencer mask device with a translation function, the translation voice corresponding to the shortcut phrase is broadcasted through the silencer mask device.

[0070] As an example of this embodiment, during daily family communication, parents wear the silencer mask device with translation function in this application, and without speaking, click on the quick phrases in the life scene to let the child improve the foreign language listening and speaking ability in a pure foreign language environment, and use it in conjunction with the parents' actions to help the child better understand the meaning of foreign languages ​​and use these phrases in real life. For example, at breakfast time, parents choose the field about breakfast, and the device displays quick phrases related to breakfast, such as "What do you want to eat for breakfast today?", "Bread", "Do you want milk?", etc. Parents choose the phrase "Do you want milk?", and the device immediately loads the corresponding translated voice into the play queue and plays it. At the same time, the parent makes a gesture of pointing to the milk on the table, allowing the child to feel the atmosphere of the foreign language both visually and auditorily.

[0071] The present embodiment provides a method for triggering translation by using a quick phrase. The present embodiment first renders and displays the quick phrase corresponding to the conversation field on the user side according to the conversation field selected by the user, determines the target quick phrase in response to the trigger operation of the user side, matches the corresponding translation voice in the voice library according to the target quick phrase, loads the translation voice into the play queue, and plays the translation voice in real time according to the order of the play queue. By rendering and displaying the quick phrase corresponding to the conversation field selected by the user, the user can quickly find and trigger the required phrase, thereby reducing the time cost of communication, determining the target quick phrase in response to the trigger operation of the user side, and matching the corresponding translation voice in the voice library, thereby improving the efficiency of translation, and forming a pure foreign language auditory environment by loading the translation voice into the play queue and playing the translation voice in real time according to the order of the play queue.

[0072] Based on Example 1, Example 2 of the present application proposes a quick phrase trigger translation method, referring to Figure 2 , before step S10, including: Step S50, collecting the user's conversation data.

[0073] In this embodiment, the conversation data is history data of conversations conducted by users through translation.

[0074] As an optional implementation, the historical usage data of the user recorded in the database is used as the conversation data.

[0075] Step S60: Analyze the conversation data by statistical methods to identify the user's frequently used fields and frequently used phrases.

[0076] In this embodiment, the commonly used domain is the topic, theme or domain that the user most often involves or discusses in the conversation data. Common phrases are words, phrases or sentences frequently used by users in the conversation data, reflecting the user's language habits, interest preferences or demand patterns.

[0077] As an optional implementation, the collected conversation data is cleaned and preprocessed to remove irrelevant information, and the frequency of each word, phrase or sentence in the conversation data is counted to identify high-frequency words and phrases, and the user's common phrases are screened out based on the frequency distribution. The conversation data is analyzed using a topic modeling algorithm to identify the user's common areas.

[0078] Exemplarily, the frequency of occurrence of each word, phrase or sentence in the conversation data is counted, and based on the statistical results, the words and phrases with high occurrence frequency are identified, and the user's common phrases are further screened out by combining the context information and the association between words.

[0079] Exemplarily, a topic modeling algorithm is selected to perform topic analysis on the conversation data. The number of topics to be extracted is determined based on the scale and complexity of the conversation data. The user's frequently used areas are identified by analyzing the vocabulary and phrases under each topic in combination with the user's actual background and conversation content.

[0080] Step S70, constructing a user portrait and / or a knowledge graph based on the common fields and the common phrases.

[0081] In this embodiment, the user portrait is a comprehensive description based on user data, including the user's basic information, interest preferences, behavior patterns, etc. Knowledge graph is a structured knowledge representation method that represents the association information between entities through nodes (entities) and edges (relationships).

[0082] Exemplarily, the identified common fields and common phrases are integrated with the basic information of the user to form a complete user data set, and key features are extracted from the user data set to build a user profile to describe the user's interests, preferences, etc. Common fields and common phrases are used as entities in the knowledge graph, and the association relationship between entities is analyzed. Based on the entities and relationships, a structured knowledge graph is generated to display the association information between users, fields, and phrases.

[0083] Optionally, step S70 includes: Step S71, constructing the user portrait according to the user information bound to the user terminal, combined with the common fields and the common phrases.

[0084] Exemplarily, based on the user information bound to the user end, combined with the common fields and common phrases identified in the conversation data, a user feature data set is formed. Feature extraction is performed on the user feature data set, and corresponding tags are assigned to these features to form a tag system for user portraits. Based on the tag system, a comprehensive user portrait is generated.

[0085] Optionally, the portrait is optimized through a machine learning algorithm to improve the accuracy of the portrait.

[0086] Step S72, collecting translation resources of the common fields, extracting entities and relationships, and constructing the knowledge graph of each common field.

[0087] In this embodiment, the translation resources are knowledge resources in common fields, including professional terms, common concepts, entity relationships, and the like.

[0088] Exemplarily, knowledge resources in common fields are collected, natural language processing technology is used to perform pre-processing such as word segmentation and part-of-speech tagging on the knowledge in common fields, named entity recognition (NER) technology is applied to extract entities in the field, relationship extraction technology is used to identify and extract the associations between entities, and a structured knowledge graph is constructed based on the extracted entities and relationships.

[0089] Step S80: Based on the user portrait and / or the knowledge graph, generate and store the conversation domain and the corresponding shortcut phrase.

[0090] Based on the user profile and knowledge graph that have been built, we generate shortcut phrases related to the conversation domain and store these shortcut phrases and their corresponding conversation domains. Through the user profile, we understand the user's interests, preferences and behavior patterns, so as to generate shortcut phrases that better meet the user's needs. Through the knowledge graph, we provide structured knowledge in the domain, which helps to generate accurate and informative shortcut phrases.

[0091] As an optional implementation, the interest preferences and behavior patterns in the user profile are analyzed to generate shortcut phrases that meet the user's needs. If the user profile shows that the user likes traveling, then travel-related shortcut phrases are generated, such as "check travel routes" and "book a hotel".

[0092] As another optional implementation, the entities and relationships in the knowledge graph are used to generate accurate and informative shortcut phrases. In the field of science and technology, shortcut phrases related to the latest technology products, technology trends, etc. are generated.

[0093] As another optional implementation, the interest preferences and behavior patterns in the user portrait, as well as the entities and relationships in the knowledge graph, are analyzed to generate shortcut phrases that meet user needs and are related to the conversation field.

[0094] Step S90: Generate a translated speech corresponding to the shortcut phrase and store it in the speech library.

[0095] Exemplarily, according to the language setting of the user, the target language for which the translated speech needs to be generated is determined, the translated speech of the corresponding language is generated, and stored in the speech library.

[0096] Optionally, the target language may be one or more than one.

[0097] As an example of this embodiment, historical data of users using the translation function of the silencer mask to conduct conversations is extracted from the database. The collected conversation data is cleaned and preprocessed to remove irrelevant information. The frequency of each word, phrase or sentence in the conversation data is counted using statistical methods, and high-frequency words and phrases are identified. Combined with the context information and the association between words, the user's common phrases are further screened out. At the same time, the topic modeling algorithm is applied to the conversation data for topic analysis to identify the user's common fields. According to the user information bound to the user end, combined with the common fields and common phrases identified in the conversation data, a user feature data set is formed, and the user feature data set is grouped by a clustering algorithm, and a corresponding label is assigned to each group to form a label system for user portraits. A comprehensive portrait of the user is generated according to the label system to describe the user's interest preferences, behavior patterns and other characteristics. For each common field, relevant translation resources are collected, named entity recognition technology is used to extract entities in the field, and application relationship extraction technology is used to identify and extract the association between entities. A structured knowledge graph is constructed based on the extracted entities and relationships to display the association information between users, fields, and phrases. Based on the user portrait and knowledge graph that have been built, analyze the interests, preferences and behavior patterns in the user portrait, as well as the entities and relationships in the knowledge graph, generate shortcut phrases that meet user needs and are related to the dialogue field, and store the generated shortcut phrases and the corresponding dialogue field in the database. According to the user's language setting, determine the target language for generating translated speech. Use text-to-speech technology to translate the shortcut phrases into the target language, generate the corresponding translated speech and store it in the speech library.

[0098] The present embodiment provides a quick phrase trigger translation method. The present embodiment first collects and analyzes the user's conversation data, identifies the user's frequently used fields and frequently used phrases, and then constructs an accurate user portrait and knowledge graph, which can more accurately understand the user's needs. Based on the user portrait and knowledge graph, quick phrases closely related to the conversation field are generated and stored for quick call, which shortens the response time of the quick phrase trigger translation and improves the fluency and coherence of the conversation. By generating the translated speech of the quick phrase and storing it in the voice library, the application scenarios of the quick phrase trigger translation method are broadened, and the user experience is further optimized.

[0099] Based on Example 1, Example 3 of the present application proposes a quick phrase trigger translation method, referring to Figure 3 , the quick phrase triggering translation method further includes: Step S100, inferring the conversation direction of the user based on the target shortcut phrase of the play queue in combination with the user portrait and / or the knowledge graph.

[0100] By analyzing the target shortcut phrases in the current playback queue and combining them with the user's personalized information, the user's possible conversation needs or topic direction can be predicted.

[0101] In this embodiment, the conversation direction refers to the topic or demand direction that the user may continue to discuss, which is inferred based on information such as the current conversation content, user portrait, and knowledge graph.

[0102] As an optional implementation method, the target shortcut phrase in the playback queue is analyzed to extract key information such as keywords, themes or intentions. Based on the extracted key information, relevant personalized information such as interest preferences and historical behaviors is searched in the user portrait. The key information of the target shortcut phrase and the personalized information in the user portrait are combined to infer the topic or demand direction that the user continues to discuss.

[0103] As another optional implementation, the target shortcut phrase in the playback queue is analyzed to extract key information such as keywords, topics or intentions. Based on the extracted key information, relevant structured knowledge such as entities, relationships or attributes are searched in the knowledge graph. The key information of the target shortcut phrase and the structured knowledge in the knowledge graph are combined to infer the topic or demand direction that the user continues to discuss.

[0104] As another optional implementation, the target shortcut phrase in the playback queue is analyzed to extract key information such as keywords, themes or intentions. Based on the extracted key information, relevant personalized information such as interest preferences and historical behaviors is searched in the user portrait, and relevant structured knowledge such as entities, relationships or attributes is searched in the knowledge graph. A comprehensive analysis is performed based on the key information of the target shortcut phrase, the personalized information in the user portrait and the structured knowledge in the knowledge graph to infer the topic or demand direction that the user continues to discuss.

[0105] Step S110 , based on the conversation direction, searching a database for relevant quick phrases as recommended phrases.

[0106] In this embodiment, the recommended phrases are quick phrases that are retrieved from a database according to the conversation direction and are related to the user's conversation needs.

[0107] According to the inferred conversation direction, the search conditions are determined, the relevant quick phrases are searched in the database using the search conditions, the search results are sorted or filtered, and the recommended phrases that meet the user's needs are determined.

[0108] Optionally, a machine learning algorithm is used to rank the search results to improve the accuracy of the recommendations.

[0109] Step S120: Rendering the recommended phrase to the user terminal.

[0110] Exemplarily, according to the layout of the user terminal, the rendering format of the recommended phrase is determined, and the rendering data is generated and sent to the user terminal, and rendered by the user terminal device.

[0111] The present embodiment provides a quick phrase trigger translation method. The present embodiment firstly combines the user portrait and / or the knowledge graph to more accurately infer the user's conversation direction. The quick phrase retrieval based on the conversation direction can quickly provide the user with relevant phrase suggestions, thereby improving the user experience. By providing quick phrases related to the conversation direction, it helps to maintain the continuity of communication. By intuitively displaying the recommended phrases on the user side, it helps the user understand and select the recommended phrases.

[0112] Based on Example 1, Example 4 of the present application proposes a quick phrase trigger translation method, referring to Figure 4 , after step S40, further comprising: Step S130: if it is detected that the user starts the oral dialogue practice function, the user's input voice is collected.

[0113] When the user starts the oral dialogue practice function, the user's input voice is collected in a timely manner for subsequent voice recognition and evaluation.

[0114] In this embodiment, the oral conversation practice function is a function provided by the noise cancelling mask device with a translation function, allowing the user to practice conversation with the noise cancelling mask device through voice to improve oral expression ability. The input voice is a voice signal input by the user through a device such as a microphone.

[0115] Exemplarily, the activation of the oral dialogue practice function is detected by monitoring the user's operation or receiving the user's voice command. After detecting that the function is activated, the microphone and other devices are immediately started to start collecting the user's input voice and store the collected voice signal.

[0116] Step S140: recognizing the voice features of the input voice through voice recognition technology.

[0117] In this embodiment, the speech recognition technology is a technology for identifying speech features in speech signals. Speech features are key information in speech signals, including pitch, volume, speech speed, pronunciation clarity, etc., which are used to reflect the user's oral expression ability.

[0118] Exemplarily, the collected input speech is preprocessed by denoising, filtering, etc., and the speech features in the input speech are extracted using a speech recognition algorithm.

[0119] Step S150: Generate a speech evaluation report based on the speech features and render it to the user end.

[0120] In this embodiment, the speech evaluation report is an evaluation result based on speech feature analysis, and is used to reflect the user's oral expression ability level.

[0121] Exemplarily, based on the extracted speech features, an evaluation algorithm is used to calculate the user's oral expression ability score, and corresponding evaluations and suggestions are given as evaluation results. The evaluation results are filled into a speech evaluation report template and rendered on the user's screen.

[0122] As an example of this embodiment, in the process of students learning English, the silencer mask with translation function in this application is used to practice oral dialogue, and the students' voices are collected according to the oral dialogue practice function that the students choose to turn on. Using speech recognition technology, the students' input voice is processed in real time to identify and extract key features in the voice, including pronunciation clarity, intonation fluctuations, speaking speed, etc. Based on the extracted voice features, a detailed voice evaluation report is generated, which includes key indicators such as the students' pronunciation scores, intonation scores, speaking speed scores, and corresponding evaluations and suggestions. The evaluation report is rendered to the user end in a combination of charts and text to ensure that students can clearly see their oral level and areas that need improvement.

[0123] The present embodiment provides a quick phrase triggered translation method. The present embodiment first detects the operation of the user to start the oral dialogue practice function in real time, and quickly enters the voice collection stage, thereby efficiently and accurately collecting the user's input voice, and accurately identifies the voice features in the user's input voice through voice recognition technology, and generates a detailed voice evaluation report, thereby improving the user's experience in oral practice and improving practice efficiency.

[0124] Based on Example 1, Example 5 of the present application proposes a quick phrase trigger translation method, referring to Figure 5 and Figure 6 , Figure 5 and Figure 6 A schematic diagram of a noise-cancelling mask device with a translation function involved in a quick phrase-triggered translation method is provided, specifically: In this embodiment, the noise cancelling mask device with translation function is a head-mounted device that integrates noise cancelling technology and real-time voice translation function, including Figure 5 The translation equipment shown and Figure 6 The translation device includes a housing 11, a second audio connection hole 16 and a charging hole 17 are arranged on one side of the housing 11, a speaker hole 12 is opened at one end of the housing 11, and a screen 14 and a main button 15 are arranged at the other end of the housing 11. The screen 14 is used to display the status of the translation device. The main button 15 is operated to light up or turn off the screen.

[0125] The first audio connection hole 211 of the mute device is connected to the second audio connection hole 16 of the translation device via an audio connection line.

[0126] The silencer device includes a silencer assembly 21, which includes a front shell 218 and a rear shell 219. The front shell 218 and the rear shell 219 are combined to form a mask-shaped structure. A recessed silencer shell 215 is arranged in the front shell 218. The bottom and inner wall of the inner cavity of the silencer shell 215 are covered with sound insulation cotton. When sound passes through the sound insulation cotton, the sound insulation cotton is used to silence the sound and reduce the vibration caused by the sound. A microphone is fixed inside the silencer shell 215.

[0127] Exemplarily, the user selects a conversation area through a conversation area selection interface on screen 14 of the device.

[0128] Optionally, the conversation field displayed in the conversation field selection interface is obtained by the silencer mask device through collecting historical data of the user for analysis, obtaining a user portrait and a knowledge graph, and then analyzing the user's preference field based on the user portrait and the knowledge graph.

[0129] Furthermore, the translation device loads the shortcut phrases related to the conversation field from the preset shortcut phrase library according to the conversation field selected by the user through the screen 14, generates a shortcut phrase selection interface and renders it to the screen 14 for display. Among them, the shortcut phrase library contains a field for identifying the conversation field. The translation device constructs a query statement according to the conversation field selected by the user, and can retrieve the shortcut phrases corresponding to the conversation field.

[0130] Furthermore, the user triggers the shortcut phrase selection operation by clicking the shortcut phrase option in the shortcut phrase selection interface. After receiving the user's trigger operation, the translation device determines the target shortcut phrase and target language selected by the user, matches them with the built-in voice library, and finds the corresponding translation voice.

[0131] Optionally, the voice database is a pre-set database containing translated voices of the shortcut phrases in at least one language.

[0132] After the match is successful, the translation device will load the translated voice into the play queue. If there are other voices waiting to be played in the play queue, the newly loaded translated voice will be queued in the order of the queue.

[0133] Furthermore, the translation device plays the translated voice in the queue in real time through the speaker hole 12 according to the order of the play queue. The play process is real-time, that is, the translation device can respond to the user's trigger operation immediately and quickly play the corresponding translated voice.

[0134] Optionally, the translation device provides a speaking practice function, in which the user's input voice is collected through a microphone arranged in a silencer shell 215 of the silencer device, and the voice is transmitted to a second audio connection port 16 of the translation device through an audio connection line connected to a first audio connection port 211 of the silencer device. The translation device uses speech recognition technology to identify and extract key features in the input voice, and generates a report containing a speaking score and corresponding evaluations and suggestions.

[0135] The entire process is designed to provide a quick phrase-triggered translation method that integrates noise cancellation technology and real-time voice translation functions, which is achieved through a noise cancellation mask device with translation function. Through the pre-set quick phrase library, users can quickly select and trigger commonly used communication sentences to improve the efficiency of cross-language communication. Combined with noise cancellation technology and real-time translation functions, the device can provide instant and accurate translation services and oral practice functions while protecting user privacy. By analyzing user historical data, the device can understand user preferences and conversation areas, thereby providing more personalized quick phrase selection and translation services.

[0136] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the quick phrase trigger translation method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0137] The present application provides a quick phrase trigger translation device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the quick phrase trigger translation method in the above-mentioned embodiment 1.

[0138] Reference below Figure 7 , which shows a schematic diagram of the structure of a quick phrase trigger translation device suitable for implementing the embodiment of the present application. The quick phrase trigger translation device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 7 The quick phrase-triggered translation device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0139] like Figure 7As shown, the quick phrase trigger translation device may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the quick phrase trigger translation device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. Communication device 1009 can allow the quick phrase trigger translation device to communicate wirelessly or wired with other devices to exchange data. Although the quick phrase trigger translation device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0140] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0141] The quick phrase trigger translation device provided by the present application adopts the quick phrase trigger translation method in the above embodiment, which can solve the technical problem of how to improve the efficiency of cross-language communication. Compared with the prior art, the beneficial effects of the quick phrase trigger translation device provided by the present application are the same as the beneficial effects of the quick phrase trigger translation method provided by the above embodiment, and other technical features in the quick phrase trigger translation device are the same as the features disclosed in the previous embodiment method, which will not be repeated here.

[0142] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0143] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0144] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the quick phrase-triggered translation method in the above-mentioned embodiment.

[0145] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0146] The computer-readable storage medium may be included in the quick phrase-triggered translation device; or may exist independently without being assembled into the quick phrase-triggered translation device.

[0147] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the quick phrase trigger translation device, the quick phrase trigger translation device can be written in one or more programming languages ​​or a combination thereof to write computer program codes for performing the operations of the present application. The programming languages ​​include object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "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 an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0148] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0149] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0150] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned quick phrase trigger translation method, and can solve the technical problem of how to improve the efficiency of cross-language communication. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the quick phrase trigger translation method provided by the above-mentioned embodiment, and will not be repeated here.

[0151] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A quick phrase triggering translation method, characterized in that: The quick phrase trigger translation method comprises: According to the conversation field selected by the user, the quick phrase corresponding to the conversation field is rendered and displayed on the user terminal; In response to a trigger operation of the user terminal, determining a target shortcut phrase; Matching a corresponding translation voice in a voice library according to the target shortcut phrase, and loading the translation voice into a play queue; The translated speech is played in real time according to the order of the play queue.

2. The quick phrase trigger translation method according to claim 1, characterized in that: Before the step of rendering and displaying the quick phrase corresponding to the conversation field selected by the user on the user side, the method includes: Collecting conversation data of the user; Analyzing the conversation data by statistical methods to identify common areas and common phrases of the users; Based on the common fields and the common phrases, construct a user profile and / or a knowledge graph; Based on the user portrait and / or the knowledge graph, generate and store the conversation domain and the corresponding shortcut phrase; Generate a translated speech corresponding to the shortcut phrase and store it in the speech library.

3. The quick phrase trigger translation method as claimed in claim 2, characterized in that: The step of constructing a user portrait and / or a knowledge graph based on the common fields and the common phrases includes: Constructing the user profile according to the user information bound to the user terminal, in combination with the common fields and the common phrases; and / or The translation resources of the common fields are collected, and entities and relationships are extracted to construct the knowledge graph of each common field.

4. The quick phrase-triggered translation method according to claim 1, wherein: The quick phrase trigger translation method further includes: Inferring the conversation direction of the user according to the target shortcut phrase of the play queue in combination with the user portrait and / or the knowledge graph; Based on the conversation direction, searching a database for relevant quick phrases as recommended phrases; The recommended phrase is rendered to the user end.

5. The quick phrase-triggered translation method according to claim 1, characterized in that: The step of rendering and displaying the quick phrase corresponding to the conversation field on the user side according to the conversation field selected by the user includes: According to the conversation field selected by the user, searching a database for a shortcut phrase corresponding to the conversation field; A phrase selection interface is generated according to the shortcut phrase, and the phrase selection interface is rendered and displayed on the user end.

6. The quick phrase-triggered translation method according to claim 1, characterized in that: The step of determining a target shortcut phrase in response to a trigger operation of the user terminal includes: Based on a triggering operation of a single shortcut phrase, identifying the shortcut phrase as the target shortcut phrase; or Based on the triggering operations of at least two of the shortcut phrases, the shortcut phrases are combined according to a preset rule to serve as the target shortcut phrase.

7. The quick phrase-triggered translation method according to claim 1, characterized in that: The step of playing the translated speech in real time according to the order of the play queue also includes: Rendering the play queue to the user end; Based on the adjustment operation of the user terminal, the order of the translated voices in the play queue is adjusted to obtain a custom play queue; Based on the confirmation operation of the user terminal, the translated voice is played according to the custom play queue.

8. The quick phrase-triggered translation method according to claim 1, wherein: After the step of playing the translated speech in real time according to the order of the play queue, the method further comprises: If it is detected that the user starts the oral dialogue practice function, collecting the user's input voice; Using speech recognition technology to identify the speech features of the input speech; Based on the speech features, a speech evaluation report is generated and rendered to the user end.

9. A quick phrase-triggered translation device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the quick phrase-triggered translation method according to any one of claims 1 to 8.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the quick phrase triggering translation method according to any one of claims 1 to 8 are implemented.

Images