CN116384418B - Data processing method and system for translating by using smart watch - Google Patents
Data processing method and system for translating by using smart watch Download PDFInfo
- Publication number
- CN116384418B CN116384418B CN202310592926.3A CN202310592926A CN116384418B CN 116384418 B CN116384418 B CN 116384418B CN 202310592926 A CN202310592926 A CN 202310592926A CN 116384418 B CN116384418 B CN 116384418B
- Authority
- CN
- China
- Prior art keywords
- text
- user
- translated
- preset
- translation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 10
- 238000013519 translation Methods 0.000 claims abstract description 167
- 238000012545 processing Methods 0.000 claims abstract description 13
- 238000000605 extraction Methods 0.000 claims description 42
- 238000004458 analytical method Methods 0.000 claims description 16
- 230000008451 emotion Effects 0.000 claims description 14
- 238000000034 method Methods 0.000 claims description 14
- 230000001502 supplementing effect Effects 0.000 claims description 10
- 230000009469 supplementation Effects 0.000 claims description 8
- 238000012795 verification Methods 0.000 claims description 8
- 239000013589 supplement Substances 0.000 abstract description 4
- 239000000284 extract Substances 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 2
- 230000001934 delay Effects 0.000 description 2
- 230000008909 emotion recognition Effects 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/40—Processing or translation of natural language
- G06F40/58—Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention provides a data processing method and a system for translating by applying a smart watch, which are applied to the field of translation data processing; according to the invention, after the text type required to be translated by the user is identified, the matched text object similar to the text type is called out from the preset database for the user to select the text type, when the user cannot confirm the text type, the user is endowed with a hand drawing right through the screen of the intelligent watch, the text to be translated is translated after the content of the text to be translated obtained by the hand drawing of the user is identified, the efficiency of translating the text is effectively improved, meanwhile, the user is confirmed after the text translation is completed, the data supplement is carried out on the translation text which is unsatisfactory to the user after the opinion feedback of the user is acquired, and a more accurate translation text is generated for the user to exchange and reference, so that the information accuracy of the translation text is effectively improved.
Description
Technical Field
The invention relates to the field of translation data processing, in particular to a data processing method and system for translating by applying a smart watch.
Background
At present, text or voice is often required to be translated in the work and life of people, and special translation application or machine translation (MT, machine Translation) can be generally performed through translation web pages, but machine translation sometimes has a situation of wrong translation, so when a machine translation technology is used in industry, combining with machine assisted translation (CAT, computer-Aided Translation) is a widely used practice, and various efficient CAT interaction modes are developed along with the progress and perfection of an MT system.
However, when the staff needs to translate the text content which is not seen by the staff, the staff cannot know the type of the text content and cannot know the type of the text content, so that the efficiency of translating the text is greatly reduced, and meanwhile, the staff needs to know the type of the text content from other ways, and then the staff can accurately translate the text content, so that the text translation process is quite complicated.
Disclosure of Invention
The invention aims to solve the problems that the efficiency of text translation is reduced and the text translation flow is complicated because the type of text content cannot be known and the text content cannot be translated, and provides a data processing method and a data processing system for translating by applying a smart watch.
The invention adopts the following technical means for solving the technical problems:
the invention provides a data processing method for translating by applying a smart watch, which comprises the following steps:
reading a text type to be translated input by a user, identifying at least one matched text object with similarity to the text type to be translated from a preset database, taking the similarity ratio of the similarity as a priority order to be matched, and presenting the matched text object to a screen preset by the intelligent watch according to the priority order;
judging whether the matched text object is selected by the user or not;
if not, requesting the user for obtaining the text content to be translated, analyzing the text characteristics of the text content to be translated based on a preset decoder, identifying the text type corresponding to the text content to be translated according to the text characteristics, translating the text content to be translated according to the text type, and generating translation data;
judging whether the translation data can be adopted by the user or not;
if the user cannot input the preset scheme, obtaining opinion feedback input by the user based on the preset scheme, supplementing the translation data according to the opinion feedback, and confirming completion of translation to the user after the supplementation is completed, wherein the preset scheme specifically comprises the steps of requesting the user to provide context about the translation data, requesting the user to carry out transliteration on the translation data and giving the user important verification on the translation data.
Further, the step of obtaining opinion feedback input by the user based on the preset scheme, supplementing the translation data according to the opinion feedback, and confirming that the translation is completed to the user after the supplementation is completed includes:
based on at least one preset scheme selected by the user, applying auxiliary measures corresponding to the preset scheme to assist the user in opinion feedback, wherein the auxiliary measures specifically comprise sending a context to be supplemented with a preset blank format to the user, providing a preset translation auxiliary tool for the user to assist in transliteration and authorizing the user to control the translation data;
judging whether the user finishes the opinion feedback;
if yes, receiving the opinion feedback based on a preset feedback channel, uploading the opinion feedback to the database, and binding and recording the opinion feedback and corresponding translation data.
Further, the step of requesting the user to acquire the text content to be translated includes:
acquiring text content to be translated input by the user based on a collection area preset by the intelligent watch;
judging whether the text content to be translated can be obtained by comparison in a preset database;
If not, extracting text features of text words corresponding to the text content to be translated, wherein the text feature extraction specifically comprises extraction of emotion features, extraction of grammar features, extraction of entity features and extraction of theme features.
Further, before the step of determining whether the translated data is acceptable to the user, the method includes:
identifying a text meaning of the translation data;
judging whether the text meaning has preset elegant words or not;
if yes, shielding the text content corresponding to the elegant word, and identifying the text speech segment corresponding to the elegant word in the translation data.
Further, the step of analyzing the text characteristics of the text content to be translated based on the preset decoder and identifying the text type corresponding to the text content to be translated according to the text characteristics further includes:
identifying the text length of the text content to be translated;
judging whether the text content to be translated belongs to a text sentence or not based on the text length;
if yes, acquiring the characteristic attribute of the text content to be translated, and identifying the text type of the text content to be translated according to the characteristic attribute, wherein the characteristic attribute specifically comprises word frequency statistics characteristics, TF-IDF characteristics, word vector characteristics and N-gram characteristics.
Further, the step of identifying at least one matching text object having a similarity to the text type to be translated from a preset database, and ranking the matching text object as a priority to be matched based on a similarity ratio of the similarity comprises:
inputting the text type to be translated into the preset database, and generating a gradient similarity ratio corresponding to the text type to be translated, wherein the gradient similarity ratio specifically applies text word extraction, text structure analysis and text semantic analysis to analyze the text type to be translated;
judging whether the gradient similarity ratio is larger than a preset comparison threshold value or not;
if so, the text type corresponding to the gradient similarity ratio is used as the matched text object, the matched text objects are ranked based on the optimal ratio of the gradient similarity ratio, and the optimal matched text object is obtained through ranking to the general matched text object, wherein the matched text object with the highest gradient similarity ratio is used as the optimal matched text object, the matched text object with the lowest gradient similarity ratio is used as the general matched text object, and the sub-optimal matched text object, the good matched text object and the sub-good matched text object are further included in the general matched text object.
Further, before the step of reading the text type to be translated entered by the user, the method further includes:
acquiring text information in a preset area by using a preset scanner, and identifying and obtaining a corresponding text type based on the text information;
judging whether the text type exists in the database;
if yes, the recorded information of the text type is presented to a screen preset by the intelligent watch, wherein the recorded information comprises text languages and text backgrounds.
The invention also provides a data processing system for translating by applying the intelligent watch, which comprises:
the reading module is used for reading the text type to be translated, which is input by a user, identifying at least one matched text object with similarity to the text type to be translated from a preset database, taking the similarity ratio based on the similarity as the priority order to be matched, and presenting the matched text object to a screen preset by the intelligent watch according to the priority order;
the judging module is used for judging whether the matched text object is selected by the user or not;
the execution module is used for requesting the user to acquire the text content to be translated, analyzing the text characteristics of the text content to be translated based on a preset decoder, identifying the text type corresponding to the text content to be translated according to the text characteristics, translating the text content to be translated according to the text type, and generating translation data;
The second judging module is used for judging whether the translation data can be adopted by the user or not;
the second execution module is used for providing a preset scheme for the user, obtaining opinion feedback input by the user based on the preset scheme, supplementing the translation data according to the opinion feedback, and confirming completion of translation to the user after the supplementation is completed, wherein the preset scheme specifically comprises the steps of requesting the user to provide context about the translation data, requesting the user to carry out transliteration on the translation data and giving the user important verification on the translation data.
Further, the second execution module further includes:
the auxiliary unit is used for assisting the user in opinion feedback by applying auxiliary measures corresponding to the preset schemes based on at least one preset scheme selected by the user, wherein the auxiliary measures specifically comprise sending a context to be supplemented with a preset blank format to the user, providing a preset translation auxiliary tool for the user to assist in transliteration and authorizing the user to control the translation data;
the judging unit is used for judging whether the user finishes the opinion feedback;
And the execution unit is used for receiving the opinion feedback based on a preset feedback channel if the opinion feedback is received, uploading the opinion feedback to the database, and binding and recording the opinion feedback and corresponding translation data.
Further, the execution module further includes:
the acquisition unit is used for acquiring the text content to be translated, which is input by the user, based on an acquisition area preset by the intelligent watch;
the second judging unit is used for judging whether the text content to be translated can be obtained by comparison in a preset database;
and the second execution unit is used for extracting text features of text words corresponding to the text content to be translated if not, wherein the text feature extraction specifically comprises extraction of emotion features, extraction of grammar features, extraction of entity features and extraction of theme features.
The invention provides a data processing method and a system for translating by applying a smart watch, which have the following beneficial effects:
according to the invention, after the text type required to be translated by the user is identified, the matched text object similar to the text type is called out from the preset database for the user to select the text type, when the user cannot confirm the text type, the user is endowed with a hand drawing right through the screen of the intelligent watch, the text to be translated is translated after the content of the text to be translated obtained by the hand drawing of the user is identified, the efficiency of translating the text is effectively improved, meanwhile, the user is confirmed after the text translation is completed, the data supplement is carried out on the translation text which is unsatisfactory to the user after the opinion feedback of the user is acquired, and a more accurate translation text is generated for the user to exchange and reference, so that the information accuracy of the translation text is effectively improved.
Drawings
FIG. 1 is a flow chart of an embodiment of a data processing method for performing translation using a smart watch according to the present invention;
FIG. 2 is a block diagram illustrating an embodiment of a data processing system for translating using a smart watch according to the present invention.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present invention, as the achievement, functional features, and advantages of the present invention are further described with reference to the embodiments, with reference to the accompanying drawings.
The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, a data processing method for translating by using a smart watch according to an embodiment of the present invention includes:
s1: reading a text type to be translated input by a user, identifying at least one matched text object with similarity to the text type to be translated from a preset database, taking the similarity ratio of the similarity as a priority order to be matched, and presenting the matched text object to a screen preset by the intelligent watch according to the priority order;
S2: judging whether the matched text object is selected by the user or not;
s3: if not, requesting the user for obtaining the text content to be translated, analyzing the text characteristics of the text content to be translated based on a preset decoder, identifying the text type corresponding to the text content to be translated according to the text characteristics, translating the text content to be translated according to the text type, and generating translation data;
s4: judging whether the translation data can be adopted by the user or not;
s5: if the user cannot input the preset scheme, obtaining opinion feedback input by the user based on the preset scheme, supplementing the translation data according to the opinion feedback, and confirming completion of translation to the user after the supplementation is completed, wherein the preset scheme specifically comprises the steps of requesting the user to provide context about the translation data, requesting the user to carry out transliteration on the translation data and giving the user important verification on the translation data.
In this embodiment, the system inputs the text to be translated in the scanning range by enabling the scanning function of the smart watch, applies the scanning function to input the text to be translated in the scanning range, reads the text type to be translated corresponding to the text to be translated, then identifies at least one matching text object having similarity with the text type to be translated from a preset database, uses the similarity ratio of the similarity as the priority ranking of the matching text objects, and sequentially presents the matching text objects to a preset screen of the smart watch according to the priority ranking, and simultaneously judges whether the matching text objects are selected by the user to execute the corresponding steps; for example, when the system determines that a certain object exists in the matched text objects and is selected by the user, the system needs to call the corresponding matched text object information from the database, translate the text content to be translated based on the matched text object information, and generate corresponding translation data on a preset screen, so that the user can exchange and reference; for example, when the system determines that the matching text objects are not selected by the user, the system needs to request to obtain text types to be translated, which are specific to the text types to be translated, from the user, because the text types to be translated after the smart watch is scanned and identified do not accord with the text types to be translated by the user, the user is required to manually draw the text types to a screen preset by the smart watch, after receiving the text contents to be translated input by the user through the hand drawing, the system analyzes text features of the text contents to be translated based on a preset decoder, namely, text types corresponding to the text contents to be translated can be obtained according to the text features, and corresponding translation is performed on the text types to the text contents to be translated, so as to generate translation data; then judging whether the generated translation data can be directly adopted by a user or not so as to execute corresponding steps; for example, after the system determines that the user adopts the translation data, the system can complete the translation work of the text content to be translated, and can translate other text contents again; for example, when the system determines that the user does not adopt the translation data, the system may present a preset scheme to the user to help the user solve the problem of doubt, where the scheme includes requesting the user to provide a context about the translation data, requesting the user to transliterate the translation data, giving the user a key verification of the translation data, then acquiring opinion feedback input after the user confirms the adopted scheme, supplementing the translation data which is not adopted by the user according to the opinion feedback, and confirming completion of the translation content to the user, so that other text contents can be translated again, and only after all work contents of a single translation are completed, the next translation can be performed, and two translation contents cannot be processed simultaneously.
In this embodiment, the step S5 of obtaining opinion feedback input by the user based on the preset scheme, supplementing the translation data according to the opinion feedback, and confirming that the translation is completed to the user after the supplementation is completed includes:
s51: based on at least one preset scheme selected by the user, applying auxiliary measures corresponding to the preset scheme to assist the user in opinion feedback, wherein the auxiliary measures specifically comprise sending a context to be supplemented with a preset blank format to the user, providing a preset translation auxiliary tool for the user to assist in transliteration and authorizing the user to control the translation data;
s52: judging whether the user finishes the opinion feedback;
s53: if yes, receiving the opinion feedback based on a preset feedback channel, uploading the opinion feedback to the database, and binding and recording the opinion feedback and corresponding translation data.
In this embodiment, the system assists the user in performing opinion feedback on the translation data by applying an auxiliary measure corresponding to the scheme based on a certain scheme selected by the user from all preset schemes, where the auxiliary measure includes sending a context to be supplemented with a preset blank format to the user, providing the user with a preset translation auxiliary tool to assist in performing transliteration and authorizing the control right of the user on the translation data, and simultaneously judging whether the user has completed opinion feedback on the translation data to execute the corresponding steps; for example, when the system determines that the user does not complete opinion feedback within a specified time, the system delays the feedback time for the user so that the user may submit the translated content after the specified time; for example, when the system determines that the user completes the opinion feedback, the system receives opinion feedback uploaded by the user based on a preset feedback channel, and uploads the opinion feedback and the translation data to a preset database after combining the opinion feedback with the translation data, so that the opinion feedback and the translation data are bundled and recorded, and the opinion feedback and the translation data can be used for reference by other users when the same translation content appears later.
In this embodiment, the step S3 of requesting the user to acquire the text content to be translated includes:
s31: acquiring text content to be translated input by the user based on a collection area preset by the intelligent watch;
s32: judging whether the text content to be translated can be obtained by comparison in a preset database;
s33: if not, extracting text features of text words corresponding to the text content to be translated, wherein the text feature extraction specifically comprises extraction of emotion features, extraction of grammar features, extraction of entity features and extraction of theme features.
In this embodiment, the system acquires text contents to be translated, which are input by a user through hand drawing, based on a preset acquisition area, and simultaneously determines whether the text contents to be translated can be obtained by comparison in a preset database, so as to execute corresponding steps; for example, when the system determines that the text content to be translated can be obtained by comparison in a preset database, the system can clearly know the corresponding information of the text content to be translated, including the format, language, length, theme, author and history of the text content to be translated, wherein the text type corresponding to the text content to be translated is recorded in the representative database; for example, when the system determines that the translated text content cannot be obtained by comparison in a preset database, the system extracts the corresponding text fonts in the text content to be translated independently, extracts text features of the text words, extracts the extracted text content including emotion features, grammar features, entity features and theme features, and can obtain the meaning corresponding to the text content more clearly through extracting the text words.
It should be noted that the emotion feature: the emotion tendencies expressed in the text can be used for emotion analysis and emotion recognition; grammar characteristics: the grammar structure in the text can be used for text analysis and information extraction; physical characteristics: refers to the portion of text that has a particular entity (e.g., name, place name, and organization) that can be used for entity identification and relationship extraction; theme characteristics: refers to topics or topics in text, which can be used for topic modeling and text classification.
In this embodiment, before step S4 of determining whether the translated data can be adopted by the user, the method includes:
s401: identifying a text meaning of the translation data;
s402: judging whether the text meaning has preset elegant words or not;
s403: if yes, shielding the text content corresponding to the elegant word, and identifying the text speech segment corresponding to the elegant word in the translation data.
In this embodiment, the system identifies text meanings of the translation completion data, and determines whether preset elegant words exist in the text meanings at the same time, so as to execute corresponding steps; for example, when the system determines that the translation data contains the elegant words, the system shields text contents corresponding to the elegant words, and marks text speech segments corresponding to the elegant words in the translation data at the same time, so that a user can clearly know which position of the elegant words in the corresponding text contents to be translated, and can discard the sentence according to the position of the elegant words, and the meaning that translation contents obtained by translation do not respect the unaesthetic appearance is avoided; for example, when the system determines that there is no elegant word in the translation data, the system confirms to the user whether to adopt the translation data, because the text content to be translated is already translated by the system, the user can execute other translation work again only after confirming that the translation is completed.
In this embodiment, based on the text feature of the text content to be translated parsed by the preset decoder, in step S3 of identifying the text type corresponding to the text content to be translated according to the text feature, the method further includes:
s35: identifying the text length of the text content to be translated;
s36: judging whether the text content to be translated belongs to a text sentence or not based on the text length;
s37: if yes, acquiring the characteristic attribute of the text content to be translated, and identifying the text type of the text content to be translated according to the characteristic attribute, wherein the characteristic attribute specifically comprises word frequency statistics characteristics, TF-IDF characteristics, word vector characteristics and N-gram characteristics.
In this embodiment, after identifying the text length of the text content to be translated, the system determines, based on the text length, whether the text content to be translated belongs to a text sentence, so as to execute a corresponding step; for example, when the system determines that the text content to be translated exceeds the preset text length and belongs to a text sentence, the system acquires the feature attribute of the text content to be translated, wherein the feature attribute comprises word frequency statistics features, TF-IDF features, word vector features and N-gram features, the text type of the text content to be translated is identified according to the feature data, and the corresponding translation work can be performed on the text content to be translated after the text type is known.
It should be noted that, word frequency statistics features: refers to the number of times each word in the text appears in the text. These features can be used for text classification and clustering; TF-IDF feature: the term frequency-inverse document frequency characteristic is used for calculating the importance of a word in a text. These features can be used for information retrieval and text classification; word vector feature: representing each word as a vector, which may be generated based on neural networks or other techniques, which features may be used for text classification and similarity calculation; n-gram characteristics: referring to a sequence of n words that are adjacent in text, these features can be used for text classification and information extraction.
In this embodiment, identifying at least one matching text object having a similarity with the text type to be translated from a preset database, and sorting the matching text object as a priority to be matched based on a similarity ratio of the similarity in step S1 includes:
s11, inputting the text type to be translated into the preset database, and generating a gradient similarity ratio corresponding to the text type to be translated, wherein the gradient similarity ratio specifically analyzes the text type to be translated by applying text word extraction, text structure analysis and text semantic analysis;
S12: judging whether the gradient similarity ratio is larger than a preset comparison threshold value or not;
s13: if so, the text type corresponding to the gradient similarity ratio is used as the matched text object, the matched text objects are ranked based on the optimal ratio of the gradient similarity ratio, and the optimal matched text object is obtained through ranking to the general matched text object, wherein the matched text object with the highest gradient similarity ratio is used as the optimal matched text object, the matched text object with the lowest gradient similarity ratio is used as the general matched text object, and the sub-optimal matched text object, the good matched text object and the sub-good matched text object are further included in the general matched text object.
In this embodiment, the system generates a gradient similarity ratio corresponding to the text type to be translated by inputting the text type to be translated into a preset database for comparison, wherein the gradient similarity ratio is a gradient with highest similarity to gradually lower similarity, the similarity ratio is specifically obtained by analyzing the text type to be translated through text word extraction, text structure analysis and text semantic analysis, the higher the ratio is, the more similar the text type to be translated is to a certain text type in the database, the lower the ratio is, the text type to be translated is not similar to most of the text types in the database, and the corresponding steps are executed by judging whether the gradient similarity ratio is greater than a preset comparison threshold; for example, when the system determines that the gradient similarity ratio cannot be greater than a preset comparison threshold, the system determines that a text type similar to the text type to be translated does not exist in the database, the user is required to manually draw the text content to be translated, and after the system identifies the text content to be translated, the system records the text type corresponding to the text content to be translated; for example, when the system determines that the gradient similarity ratio can be greater than the preset comparison threshold, the system takes the matching text object with the highest gradient similarity ratio as the preferred matching text object, takes the matching text object with the lowest gradient similarity ratio as the general matching text object, and meanwhile, three matching text objects are also existed in the preferred matching text object and the general matching text object for the user to select, and the three matching text objects comprise a suboptimal matching text object, a good matching text object and a suboptimal matching text object, because the similarity ratio of the three matching text objects is not high nor low, the system also generates for the user to select, so that the user is prevented from missing the most suitable matching text object.
It should be noted that, although the higher the similarity ratio is, the more the corresponding text type to be translated is approved by the system, the system is always approved, not the user's own approval, and the text type to be finally selected is also required to be confirmed by the user's own, and the system may be in error, so the user's own help the system to make secondary confirmation, and the translation efficiency can be effectively improved.
In this embodiment, before step S1 of reading the text type to be translated entered by the user, the method further includes:
s101: acquiring text information in a preset area by using a preset scanner, and identifying and obtaining a corresponding text type based on the text information;
s102: judging whether the text type exists in the database;
s103: if yes, the recorded information of the text type is presented to a screen preset by the intelligent watch, wherein the recorded information comprises text languages and text backgrounds.
In this embodiment, the system obtains text information in a preset area of the scanner by applying the preset scanner, identifies and obtains a corresponding text type to be translated based on the text information, and simultaneously judges whether the text type to be translated exists in a preset database or not so as to execute a corresponding step; for example, when the system determines that the text type to be translated does not exist in the database, the system considers that the user is required to draw the text content to be translated by hand, and after the system identifies the text content to be translated, the system records the text type corresponding to the text content to be translated; for example, when the system determines that the text type to be translated exists in the database, the system presents the recorded information corresponding to the text type to be translated to a screen preset by the smart watch, the recorded information comprises text languages and text backgrounds corresponding to the text type to be translated, and the recorded information is disclosed to the screen so that a user can refer to the text content to be translated which is not translated, and the understanding of the user on the translation data can be effectively improved.
Referring to fig. 2, a data processing system for translating by using a smart watch according to an embodiment of the present invention includes:
the reading module 10 is configured to read a text type to be translated entered by a user, identify at least one matching text object having similarity with the text type to be translated from a preset database, use a similarity ratio of the similarity as a priority order to be matched, and present the matching text object to a screen preset by the smart watch according to the priority order;
a judging module 20, configured to judge whether the matching text object is selected by the user;
the execution module 30 is configured to request the user to obtain text content to be translated, parse text features of the text content to be translated based on a preset decoder, identify a text type corresponding to the text content to be translated according to the text features, and translate the text content to be translated according to the text type to generate translation data;
a second judging module 40, configured to judge whether the translated data can be adopted by the user;
the second execution module 50 is configured to provide a preset scheme for the user, obtain opinion feedback input by the user based on the preset scheme, supplement the translation data according to the opinion feedback, and confirm completion of translation to the user after the supplement is completed, where the preset scheme specifically includes requesting the user to provide a context for the translation data, requesting the user to transliterate the translation data, and giving the user a key verification of the translation data.
In this embodiment, the reading module 10 inputs the text content to be translated in the scanning range by enabling the scanning function of the smart watch, applies the scanning function to input the text content to be translated, reads the text type to be translated corresponding to the text content to be translated, then identifies at least one matching text object having similarity with the text type to be translated from a preset database, uses the similarity ratio of the similarity as the priority ranking of the matching text objects, and presents the matching text objects one by one into a preset screen of the smart watch after the matching text objects are ranked according to the priority ranking, and meanwhile the judging module 20 judges whether the matching text objects are selected by the user to execute the corresponding steps; for example, when the system determines that a certain object exists in the matched text objects and is selected by the user, the system needs to call the corresponding matched text object information from the database, translate the text content to be translated based on the matched text object information, and generate corresponding translation data on a preset screen, so that the user can exchange and reference; for example, when the system determines that the matching text objects are not selected by the user, the execution module 30 needs to request to obtain text types to be translated from the user, and because the text types to be translated after the smart watch is scanned and identified do not conform to the text types to be translated by the user, the user is required to manually draw the text types to be translated into a screen preset by the smart watch, after receiving the text contents to be translated input by the user through the hand drawing, the system analyzes text features of the text contents to be translated based on a preset decoder, namely text types corresponding to the text contents to be translated can be obtained according to the text features, and corresponding translation is performed on the text types to the text contents to be translated, so as to generate translation data; then the second judging module 40 judges whether the generated translation data can be directly adopted by the user so as to execute the corresponding steps; for example, after the system determines that the user adopts the translation data, the system can complete the translation work of the text content to be translated, and can translate other text contents again; for example, when the system determines that the user does not adopt the translation data, the second execution module 50 may present a preset solution to the user to help the user solve the problem of difficulty, where the solution includes requesting the user to provide a context for the translation data, requesting the user to perform transliteration on the translation data, giving the user an important verification on the translation data, then acquiring opinion feedback input after the user confirms the adopted solution, supplementing the translation data that has not been adopted by the user according to the opinion feedback, and confirming completion of the translation content to the user, so that other text contents can be translated again, and only after all the work contents of a single translation are completed, the next translation can be performed, and two translation contents cannot be processed simultaneously.
In this embodiment, the second execution module further includes:
the auxiliary unit is used for assisting the user in opinion feedback by applying auxiliary measures corresponding to the preset schemes based on at least one preset scheme selected by the user, wherein the auxiliary measures specifically comprise sending a context to be supplemented with a preset blank format to the user, providing a preset translation auxiliary tool for the user to assist in transliteration and authorizing the user to control the translation data;
the judging unit is used for judging whether the user finishes the opinion feedback;
and the execution unit is used for receiving the opinion feedback based on a preset feedback channel if the opinion feedback is received, uploading the opinion feedback to the database, and binding and recording the opinion feedback and corresponding translation data.
In this embodiment, the system assists the user in performing opinion feedback on the translation data by applying an auxiliary measure corresponding to the scheme based on a certain scheme selected by the user from all preset schemes, where the auxiliary measure includes sending a context to be supplemented with a preset blank format to the user, providing the user with a preset translation auxiliary tool to assist in performing transliteration and authorizing the control right of the user on the translation data, and simultaneously judging whether the user has completed opinion feedback on the translation data to execute the corresponding steps; for example, when the system determines that the user does not complete opinion feedback within a specified time, the system delays the feedback time for the user so that the user may submit the translated content after the specified time; for example, when the system determines that the user completes the opinion feedback, the system receives opinion feedback uploaded by the user based on a preset feedback channel, and uploads the opinion feedback and the translation data to a preset database after combining the opinion feedback with the translation data, so that the opinion feedback and the translation data are bundled and recorded, and the opinion feedback and the translation data can be used for reference by other users when the same translation content appears later.
In this embodiment, the execution module further includes:
the acquisition unit is used for acquiring the text content to be translated, which is input by the user, based on an acquisition area preset by the intelligent watch;
the second judging unit is used for judging whether the text content to be translated can be obtained by comparison in a preset database;
and the second execution unit is used for extracting text features of text words corresponding to the text content to be translated if not, wherein the text feature extraction specifically comprises extraction of emotion features, extraction of grammar features, extraction of entity features and extraction of theme features.
In this embodiment, the system acquires text contents to be translated, which are input by a user through hand drawing, based on a preset acquisition area, and simultaneously determines whether the text contents to be translated can be obtained by comparison in a preset database, so as to execute corresponding steps; for example, when the system determines that the text content to be translated can be obtained by comparison in a preset database, the system can clearly know the corresponding information of the text content to be translated, including the format, language, length, theme, author and history of the text content to be translated, wherein the text type corresponding to the text content to be translated is recorded in the representative database; for example, when the system determines that the translated text content cannot be obtained by comparison in a preset database, the system extracts the corresponding text fonts in the text content to be translated independently, extracts text features of the text words, extracts the extracted text content including emotion features, grammar features, entity features and theme features, and can obtain the meaning corresponding to the text content more clearly through extracting the text words.
It should be noted that the emotion feature: the emotion tendencies expressed in the text can be used for emotion analysis and emotion recognition; grammar characteristics: the grammar structure in the text can be used for text analysis and information extraction; physical characteristics: refers to the portion of text that has a particular entity (e.g., name, place name, and organization) that can be used for entity identification and relationship extraction; theme characteristics: refers to topics or topics in text, which can be used for topic modeling and text classification.
In this embodiment, further comprising:
the identification module is used for identifying the text meaning of the translation data;
the third judging module is used for judging whether the text meaning has preset elegant words or not;
and the third execution module is used for shielding the text content corresponding to the elegant word if yes, and identifying the text speech segment corresponding to the elegant word in the translation data.
In this embodiment, the system identifies text meanings of the translation completion data, and determines whether preset elegant words exist in the text meanings at the same time, so as to execute corresponding steps; for example, when the system determines that the translation data contains the elegant words, the system shields text contents corresponding to the elegant words, and marks text speech segments corresponding to the elegant words in the translation data at the same time, so that a user can clearly know which position of the elegant words in the corresponding text contents to be translated, and can discard the sentence according to the position of the elegant words, and the meaning that translation contents obtained by translation do not respect the unaesthetic appearance is avoided; for example, when the system determines that there is no elegant word in the translation data, the system confirms to the user whether to adopt the translation data, because the text content to be translated is already translated by the system, the user can execute other translation work again only after confirming that the translation is completed.
In this embodiment, the execution module further includes:
the identification unit is used for identifying the text length of the text content to be translated;
a third judging unit, configured to judge whether the text content to be translated belongs to a text sentence based on the text length;
and the third execution unit is used for acquiring the characteristic attribute of the text content to be translated if yes, and identifying the text type of the text content to be translated according to the characteristic attribute, wherein the characteristic attribute specifically comprises word frequency statistics characteristics, TF-IDF characteristics, word vector characteristics and N-gram characteristics.
In this embodiment, after identifying the text length of the text content to be translated, the system determines, based on the text length, whether the text content to be translated belongs to a text sentence, so as to execute a corresponding step; for example, when the system determines that the text content to be translated exceeds the preset text length and belongs to a text sentence, the system acquires the feature attribute of the text content to be translated, wherein the feature attribute comprises word frequency statistics features, TF-IDF features, word vector features and N-gram features, the text type of the text content to be translated is identified according to the feature data, and the corresponding translation work can be performed on the text content to be translated after the text type is known.
It should be noted that, word frequency statistics features: refers to the number of times each word in the text appears in the text. These features can be used for text classification and clustering; TF-IDF feature: the term frequency-inverse document frequency characteristic is used for calculating the importance of a word in a text. These features can be used for information retrieval and text classification; word vector feature: representing each word as a vector, which may be generated based on neural networks or other techniques, which features may be used for text classification and similarity calculation; n-gram characteristics: referring to a sequence of n words that are adjacent in text, these features can be used for text classification and information extraction.
In this embodiment, the reading module further includes:
the generation unit is used for inputting the text type to be translated into the preset database and generating a gradient similarity ratio corresponding to the text type to be translated, wherein the gradient similarity ratio specifically applies text word extraction, text structure analysis and text semantic analysis to analyze the text type to be translated;
a fourth judging unit, configured to judge whether the gradient similarity ratio is greater than a preset comparison threshold;
and the fourth execution unit is used for taking the text type corresponding to the gradient similarity ratio as the matched text object, sorting the matched text objects based on the optimal ratio of the gradient similarity ratio to obtain a preferable matched text object to a general matched text object, wherein the matched text object with the highest gradient similarity ratio is taken as the preferable matched text object, the matched text object with the lowest gradient similarity ratio is taken as the general matched text object, and the preferable matched text object to the general matched text object further comprises a suboptimal matched text object, a good-order matched text object and a suboptimal matched text object.
In this embodiment, the system generates a gradient similarity ratio corresponding to the text type to be translated by inputting the text type to be translated into a preset database for comparison, wherein the gradient similarity ratio is a gradient with highest similarity to gradually lower similarity, the similarity ratio is specifically obtained by analyzing the text type to be translated through text word extraction, text structure analysis and text semantic analysis, the higher the ratio is, the more similar the text type to be translated is to a certain text type in the database, the lower the ratio is, the text type to be translated is not similar to most of the text types in the database, and the corresponding steps are executed by judging whether the gradient similarity ratio is greater than a preset comparison threshold; for example, when the system determines that the gradient similarity ratio cannot be greater than a preset comparison threshold, the system determines that a text type similar to the text type to be translated does not exist in the database, the user is required to manually draw the text content to be translated, and after the system identifies the text content to be translated, the system records the text type corresponding to the text content to be translated; for example, when the system determines that the gradient similarity ratio can be greater than the preset comparison threshold, the system takes the matching text object with the highest gradient similarity ratio as the preferred matching text object, takes the matching text object with the lowest gradient similarity ratio as the general matching text object, and meanwhile, three matching text objects are also existed in the preferred matching text object and the general matching text object for the user to select, and the three matching text objects comprise a suboptimal matching text object, a good matching text object and a suboptimal matching text object, because the similarity ratio of the three matching text objects is not high nor low, the system also generates for the user to select, so that the user is prevented from missing the most suitable matching text object.
It should be noted that, although the higher the similarity ratio is, the more the corresponding text type to be translated is approved by the system, the system is always approved, not the user's own approval, and the text type to be finally selected is also required to be confirmed by the user's own, and the system may be in error, so the user's own help the system to make secondary confirmation, and the translation efficiency can be effectively improved.
In this embodiment, further comprising:
the scanning module is used for acquiring text information in a preset area by applying a preset scanner, and identifying and obtaining a corresponding text type based on the text information;
a fourth judging module, configured to judge whether the text type exists in the database;
and the fourth execution module is used for presenting the recorded information of the text type to a screen preset by the intelligent watch if yes, wherein the recorded information comprises text languages and text backgrounds.
In this embodiment, the system obtains text information in a preset area of the scanner by applying the preset scanner, identifies and obtains a corresponding text type to be translated based on the text information, and simultaneously judges whether the text type to be translated exists in a preset database or not so as to execute a corresponding step; for example, when the system determines that the text type to be translated does not exist in the database, the system considers that the user is required to draw the text content to be translated by hand, and after the system identifies the text content to be translated, the system records the text type corresponding to the text content to be translated; for example, when the system determines that the text type to be translated exists in the database, the system presents the recorded information corresponding to the text type to be translated to a screen preset by the smart watch, the recorded information comprises text languages and text backgrounds corresponding to the text type to be translated, and the recorded information is disclosed to the screen so that a user can refer to the text content to be translated which is not translated, and the understanding of the user on the translation data can be effectively improved.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (8)
1. The data processing method for translating by using the intelligent watch is characterized by comprising the following steps of:
reading a text type to be translated input by a user, identifying at least one matched text object with similarity to the text type to be translated from a preset database, taking the similarity ratio of the similarity as a priority order to be matched, and presenting the matched text object to a screen preset by the intelligent watch according to the priority order;
judging whether the matched text object is selected by the user or not;
if not, requesting the user for obtaining the text content to be translated, analyzing the text characteristics of the text content to be translated based on a preset decoder, identifying the text type corresponding to the text content to be translated according to the text characteristics, translating the text content to be translated according to the text type, and generating translation data;
Judging whether the translation data can be adopted by the user or not;
if the user cannot input the preset scheme, acquiring opinion feedback input by the user based on the preset scheme, supplementing the translation data according to the opinion feedback, and confirming completion of translation to the user after the supplementation is completed, wherein the preset scheme specifically comprises the steps of requesting the user to provide context about the translation data, requesting the user to carry out transliteration on the translation data and giving the user important verification on the translation data;
the step of requesting the user to acquire the text content to be translated includes:
acquiring text content to be translated input by the user based on a collection area preset by the intelligent watch;
judging whether the text content to be translated can be obtained by comparison in a preset database;
if not, extracting text features of text words corresponding to the text content to be translated, wherein the text feature extraction specifically comprises extraction of emotion features, extraction of grammar features, extraction of entity features and extraction of theme features.
2. The method for processing translated data by using a smart watch according to claim 1, wherein the step of obtaining opinion feedback input by the user based on the preset scheme, supplementing the translated data according to the opinion feedback, and confirming completion of translation to the user after the supplementation is completed comprises:
Based on at least one preset scheme selected by the user, applying auxiliary measures corresponding to the preset scheme to assist the user in opinion feedback, wherein the auxiliary measures specifically comprise sending a context to be supplemented with a preset blank format to the user, providing a preset translation auxiliary tool for the user to assist in transliteration and authorizing the user to control the translation data;
judging whether the user finishes the opinion feedback;
if yes, receiving the opinion feedback based on a preset feedback channel, uploading the opinion feedback to the database, and binding and recording the opinion feedback and corresponding translation data.
3. The method for processing translated data according to claim 1, wherein before the step of determining whether the translated data is acceptable to the user, the method comprises:
identifying a text meaning of the translation data;
judging whether the text meaning has preset elegant words or not;
if yes, shielding the text content corresponding to the elegant word, and identifying the text speech segment corresponding to the elegant word in the translation data.
4. The method for processing data translated by an application smart watch according to claim 1, wherein the step of analyzing text features of the text content to be translated based on a preset decoder and identifying a text type corresponding to the text content to be translated according to the text features further comprises:
identifying the text length of the text content to be translated;
judging whether the text content to be translated belongs to a text sentence or not based on the text length;
if yes, acquiring the characteristic attribute of the text content to be translated, and identifying the text type of the text content to be translated according to the characteristic attribute, wherein the characteristic attribute specifically comprises word frequency statistics characteristics, TF-IDF characteristics, word vector characteristics and N-gram characteristics.
5. The method for processing data translated by an application smart watch according to claim 1, wherein the step of identifying at least one matching text object having a similarity to the text type to be translated from a preset database, and using a similarity ratio based on the similarity as a priority ranking to be matched, comprises:
inputting the text type to be translated into the preset database, and generating a gradient similarity ratio corresponding to the text type to be translated, wherein the gradient similarity ratio specifically applies text word extraction, text structure analysis and text semantic analysis to analyze the text type to be translated;
Judging whether the gradient similarity ratio is larger than a preset comparison threshold value or not;
if so, the text type corresponding to the gradient similarity ratio is used as the matched text object, the matched text objects are ranked based on the optimal ratio of the gradient similarity ratio, and the optimal matched text object is obtained through ranking to the general matched text object, wherein the matched text object with the highest gradient similarity ratio is used as the optimal matched text object, the matched text object with the lowest gradient similarity ratio is used as the general matched text object, and the optimal matched text object to the general matched text object further comprises a suboptimal matched text object, a good matched text object and a suboptimal matched text object.
6. The method for processing data translated by an application smart watch according to claim 1, wherein before the step of reading the text type to be translated entered by the user, further comprises:
acquiring text information in a preset area by using a preset scanner, and identifying and obtaining a corresponding text type based on the text information;
judging whether the text type exists in the database;
if yes, the recorded information of the text type is presented to a screen preset by the intelligent watch, wherein the recorded information comprises text languages and text backgrounds.
7. A data processing system for translating using a smart watch, comprising:
the reading module is used for reading the text type to be translated, which is input by a user, identifying at least one matched text object with similarity to the text type to be translated from a preset database, taking the similarity ratio based on the similarity as the priority order to be matched, and presenting the matched text object to a screen preset by the intelligent watch according to the priority order;
the judging module is used for judging whether the matched text object is selected by the user or not;
the execution module is used for requesting the user to acquire the text content to be translated, analyzing the text characteristics of the text content to be translated based on a preset decoder, identifying the text type corresponding to the text content to be translated according to the text characteristics, translating the text content to be translated according to the text type, and generating translation data;
the second judging module is used for judging whether the translation data can be adopted by the user or not;
the second execution module is used for providing a preset scheme for the user, acquiring opinion feedback input by the user based on the preset scheme, supplementing the translation data according to the opinion feedback, and confirming completion of translation to the user after the supplementation is completed, wherein the preset scheme specifically comprises the steps of requesting the user to provide a context related to the translation data, requesting the user to transliterate the translation data and giving the user important verification of the translation data;
Wherein the execution module further comprises:
the acquisition unit is used for acquiring the text content to be translated, which is input by the user, based on an acquisition area preset by the intelligent watch;
the second judging unit is used for judging whether the text content to be translated can be obtained by comparison in a preset database;
and the second execution unit is used for extracting text features of text words corresponding to the text content to be translated if not, wherein the text feature extraction specifically comprises extraction of emotion features, extraction of grammar features, extraction of entity features and extraction of theme features.
8. The data processing system for translating an application smart watch according to claim 7, wherein said second execution module further comprises:
the auxiliary unit is used for assisting the user in opinion feedback by applying auxiliary measures corresponding to the preset schemes based on at least one preset scheme selected by the user, wherein the auxiliary measures specifically comprise sending a context to be supplemented with a preset blank format to the user, providing a preset translation auxiliary tool for the user to assist in transliteration and authorizing the user to control the translation data;
The judging unit is used for judging whether the user finishes the opinion feedback;
and the execution unit is used for receiving the opinion feedback based on a preset feedback channel if the opinion feedback is received, uploading the opinion feedback to the database, and binding and recording the opinion feedback and corresponding translation data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310592926.3A CN116384418B (en) | 2023-05-24 | 2023-05-24 | Data processing method and system for translating by using smart watch |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310592926.3A CN116384418B (en) | 2023-05-24 | 2023-05-24 | Data processing method and system for translating by using smart watch |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116384418A CN116384418A (en) | 2023-07-04 |
| CN116384418B true CN116384418B (en) | 2023-08-15 |
Family
ID=86964234
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310592926.3A Active CN116384418B (en) | 2023-05-24 | 2023-05-24 | Data processing method and system for translating by using smart watch |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116384418B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101408874A (en) * | 2007-10-09 | 2009-04-15 | 深圳富泰宏精密工业有限公司 | Apparatus and method for translating image and character |
| CN108563644A (en) * | 2018-03-29 | 2018-09-21 | 河南工学院 | A kind of English Translation electronic system |
| CN110008839A (en) * | 2019-03-08 | 2019-07-12 | 西安研硕信息技术有限公司 | A kind of intelligent sign language interactive system and method for adaptive gesture identification |
| CN110444197A (en) * | 2018-05-10 | 2019-11-12 | 腾讯科技（北京）有限公司 | Data processing method, device, system and storage medium based on simultaneous interpretation |
| CN110688863A (en) * | 2019-09-25 | 2020-01-14 | 六维联合信息科技(北京)有限公司 | Document translation system and document translation method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6404511B2 (en) * | 2017-03-09 | 2018-10-10 | 楽天株式会社 | Translation support system, translation support method, and translation support program |
-
2023
- 2023-05-24 CN CN202310592926.3A patent/CN116384418B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101408874A (en) * | 2007-10-09 | 2009-04-15 | 深圳富泰宏精密工业有限公司 | Apparatus and method for translating image and character |
| CN108563644A (en) * | 2018-03-29 | 2018-09-21 | 河南工学院 | A kind of English Translation electronic system |
| CN110444197A (en) * | 2018-05-10 | 2019-11-12 | 腾讯科技（北京）有限公司 | Data processing method, device, system and storage medium based on simultaneous interpretation |
| CN110008839A (en) * | 2019-03-08 | 2019-07-12 | 西安研硕信息技术有限公司 | A kind of intelligent sign language interactive system and method for adaptive gesture identification |
| CN110688863A (en) * | 2019-09-25 | 2020-01-14 | 六维联合信息科技(北京)有限公司 | Document translation system and document translation method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116384418A (en) | 2023-07-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20070112553A1 (en) | System, method, and program for identifying the corresponding translation | |
| CN109145260B (en) | Automatic text information extraction method | |
| CN109801628B (en) | Corpus collection method, apparatus and system | |
| CA2413455C (en) | Systems and methods for translating languages | |
| CN110688863B (en) | Document translation system and document translation method | |
| CN108305618B (en) | Voice acquisition and search method, intelligent pen, search terminal and storage medium | |
| US11699034B2 (en) | Hybrid artificial intelligence system for semi-automatic patent infringement analysis | |
| CN112035652A (en) | Intelligent question-answer interaction method and system based on machine reading understanding | |
| Aumiller et al. | Klexikon: A German dataset for joint summarization and simplification | |
| CN111858842A (en) | Judicial case screening method based on LDA topic model | |
| CN111814485A (en) | Semantic analysis method and device based on massive standard document data | |
| CN105389303B (en) | A kind of automatic fusion method of heterologous corpus | |
| CN116468009A (en) | Article generation method, apparatus, electronic device and storage medium | |
| CN111680524A (en) | Human-machine feedback translation method and system based on reverse matrix analysis | |
| CN114239579A (en) | Electric power searchable document extraction method and device based on regular expression and CRF model | |
| CN116384418B (en) | Data processing method and system for translating by using smart watch | |
| CN111274354B (en) | Referee document structuring method and referee document structuring device | |
| CN113159969A (en) | Financial long text rechecking system | |
| Jui et al. | A machine learning-based segmentation approach for measuring similarity between sign languages | |
| CN113627200B (en) | International organization science and technology term topic sentence extraction method driven by multi-machine translation engine | |
| CN111310457B (en) | Word mismatching recognition method and device, electronic equipment and storage medium | |
| CN115908027A (en) | Financial data consistency auditing module of financial long text rechecking system | |
| CN113420124A (en) | Method for solving conflict under voice retrieval multi-condition | |
| CN114078470A (en) | Model processing method and device, and voice recognition method and device | |
| CN115204182B (en) | Method and system for identifying e-book data to be corrected |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address |
Address after: 4208, Tower A, Hongrongyuan North Station Center, Minzhi Street North Station Community, Longhua District, Shenzhen City, Guangdong Province, 518000 Patentee after: Shenzhen Weike Technology Co.,Ltd. Country or region after: China Address before: 518131, Building E, Phase II, Xinghe World, Minle Community, Minzhi Street, Longhua District, Shenzhen City, Guangdong Province 1501 Patentee before: SHENZHEN WAKE UP TECHNOLOGY CO.,LTD. Country or region before: China |
|
| CP03 | Change of name, title or address |