CN108549493B - Candidate word screening method and related equipment - Google Patents
Candidate word screening method and related equipment Download PDFInfo
- Publication number
- CN108549493B CN108549493B CN201810299350.0A CN201810299350A CN108549493B CN 108549493 B CN108549493 B CN 108549493B CN 201810299350 A CN201810299350 A CN 201810299350A CN 108549493 B CN108549493 B CN 108549493B
- Authority
- CN
- China
- Prior art keywords
- tone
- pinyin
- user
- track
- syllable
- 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
- 238000000034 method Methods 0.000 title claims abstract description 79
- 238000012216 screening Methods 0.000 title claims abstract description 35
- 238000012549 training Methods 0.000 claims description 19
- 238000013136 deep learning model Methods 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 230000007246 mechanism Effects 0.000 claims description 2
- 238000007873 sieving Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 19
- 230000003993 interaction Effects 0.000 description 10
- 230000008569 process Effects 0.000 description 9
- 230000009471 action Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000001544 dysphoric effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000036651 mood Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 210000001015 abdomen Anatomy 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/02—Input arrangements using manually operated switches, e.g. using keyboards or dials
- G06F3/023—Arrangements for converting discrete items of information into a coded form, e.g. arrangements for interpreting keyboard generated codes as alphanumeric codes, operand codes or instruction codes
- G06F3/0233—Character input methods
- G06F3/0237—Character input methods using prediction or retrieval techniques
-
- 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
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
- G10L15/1807—Speech classification or search using natural language modelling using prosody or stress
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/90—Pitch determination of speech signals
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
- G10L2015/027—Syllables being the recognition units
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Acoustics & Sound (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Document Processing Apparatus (AREA)
Abstract
The invention discloses a candidate word screening method and related equipment. The method comprises the following steps: obtaining pinyin and tone tracks input by a user; the pinyin comprises at least one syllable; identifying a pitch of the pitch track; establishing a matching relation between the identified tone and the final of the syllable according to a preset matching rule; and selecting a candidate word which accords with the pinyin and the matching relation from a word bank, displaying the selected candidate word, selecting a candidate word which accords with the tone matched with the pinyin and the pinyin from the word bank, and displaying the selected candidate word. The technical scheme provided by the invention can reduce the time and attention spent by the user for searching the words which the user wants to input, thereby effectively improving the user experience.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a candidate word screening method and related equipment.
Background
With the development of science and technology, people and machines such as smart machine interact more and more frequently. Currently, one of the portals for communicating with the machine is an input method, where the user enters text messages through a physical or virtual keyboard.
At present, in the field of Chinese input methods, most users input Chinese characters by using pinyin, because Chinese is popular and profound, the number of candidate words obtained by the pinyin is very large, especially under the condition of single words, so that in the actual input process of the users, more time and attention are needed to be spent to switch multiple screens to find the words to be input, and therefore dysphoric mood is inevitably generated.
That is, the current technology seriously affects the user experience.
Disclosure of Invention
In view of this, embodiments of the present invention provide a candidate word screening method and related devices, which can reduce time and attention spent by a user in searching words that the user wants to input, thereby effectively improving user experience.
In order to achieve the above purpose, the embodiments of the present invention provide the following technical solutions:
a candidate word screening method is applied to intelligent equipment comprising a touch screen, and comprises the following steps:
obtaining pinyin and tone tracks input by a user; the pinyin comprises at least one syllable;
identifying a pitch of the pitch track;
and selecting candidate words which accord with the pinyin and the tones matched with the pinyin from a word stock, and displaying the selected candidate words.
Optionally, the acquiring a pitch track input by a user includes:
acquiring a tone track input by a user in a virtual keyboard area displayed on the touch screen;
or acquiring a tone track input by a user in a tone input area displayed on the touch screen; the tone input regions are created in advance by the input method application or in response to a user trigger.
Optionally, the selecting a candidate word that matches the pinyin and the tone matching the pinyin from the word stock, and displaying the selected candidate word includes:
establishing a matching relation between the identified tone and the final of the syllable according to a preset matching rule;
and selecting candidate words which accord with the pinyin and the matching relation from a word bank, and displaying the selected candidate words.
Optionally, the establishing a matching relationship between the identified tone and the final of the syllable according to a preset matching rule includes:
determining syllable dividing results of the pinyin and the number of tone tracks input by a user;
if the syllable dividing result of the pinyin is one and comprises at least two syllables, and the number of the tone tracks is less than or equal to that of the syllables in the pinyin, establishing a matching relation between the identified tones and the vowels of the syllables according to a preset tone selection sequence and a preset syllable selection sequence;
and if the pinyin comprises at least two syllable dividing results, taking the syllable dividing result with the tone track number syllables as a syllable dividing result to be used, and establishing a matching relation between the identified tone and the final sound of the syllable in the syllable dividing result to be used.
Optionally, after acquiring the pitch track input by the user, the method further includes:
displaying the pitch track;
and acquiring a tone track clearing instruction input by a user, and clearing the tone track to acquire an audio track input by the user again.
Optionally, the selecting a candidate word that matches the pinyin and the tone matching the pinyin from the word stock, and displaying the selected candidate word includes:
and sequencing the candidate words which accord with the pinyin and the tones matched with the pinyin in the word bank according to the sequence of the use frequency of the user from top to bottom, and displaying the sequenced candidate words on the touch screen.
Optionally, the identifying the pitch of the pitch track includes:
identifying the tone of the tone track according to a pre-trained tone track identification model;
the tone track recognition model is obtained by training a pre-established deep learning model through the picture of the tone handwritten by the user and the marking data of the tone in the picture.
A candidate word sieving mechanism is applied to the smart machine including touch screen, the device includes:
the pinyin and tone track acquisition module is used for acquiring pinyin and tone tracks input by a user; the pinyin comprises at least one syllable;
a pitch identification module for identifying a pitch of the pitch track;
and the candidate word pushing module is used for selecting a candidate word which accords with the pinyin and the tone matched with the pinyin from the word stock and displaying the selected candidate word.
Optionally, the pinyin and tone track acquisition module includes:
the first tone track acquisition unit is used for acquiring a tone track input by a user in a virtual keyboard area displayed on the touch screen;
the second tone track acquisition unit is used for acquiring a tone track input by a user in a tone input area displayed on the touch screen; the tone input regions are created in advance by the input method application or in response to a user trigger.
Optionally, the candidate word pushing module includes:
the matching relation establishing unit is used for establishing the matching relation between the identified tone and the final of the syllable according to a preset matching rule;
and the candidate word display unit is used for selecting the candidate words meeting the pinyin and the matching relation from the word stock and displaying the selected candidate words.
Optionally, the matching relationship establishing unit includes:
syllable dividing result and tone track number determining subunit, for determining syllable dividing result of the pinyin and tone track number inputted by user;
a first matching relationship establishing subunit, configured to establish, if the syllable division result of the pinyin is one type and includes at least two syllables, a matching relationship between the identified tone and the final of the syllable according to a preset tone selection sequence and a preset syllable selection sequence if the number of the tone tracks is less than or equal to the number of the syllables in the pinyin;
and the second matching relation establishing subunit is used for taking the syllable dividing result with the tone track number syllables as a syllable dividing result to be used and establishing the matching relation between the identified tones and the final sound of the syllables in the syllable dividing result to be used if the pinyin comprises at least two syllable dividing results.
Optionally, the method further includes:
a display module for displaying the pitch track;
and the tone track clearing module is used for acquiring a tone track clearing instruction input by the user and clearing the tone track to acquire the audio track input by the user again.
Optionally, the candidate word pushing module is specifically configured to:
and sequencing the candidate words which accord with the pinyin and the tones matched with the pinyin in the word bank according to the sequence of the use frequency of the user from top to bottom, and displaying the sequenced candidate words on the touch screen.
Optionally, the tone recognition module is specifically configured to:
identifying the tone of the tone track according to a pre-trained tone track identification model;
the tone track recognition model is obtained by training a pre-established deep learning model through the picture of the tone handwritten by the user and the marking data of the tone in the picture.
A smart device, comprising:
a processor and a memory, the processor and memory connected by a communication bus:
the processor is used for calling and executing the program stored in the memory;
the memory is used for storing a program, and the program is at least used for executing the candidate word screening method.
A storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of the candidate word screening method as described above.
Compared with the prior art, the technical scheme provided by the invention provides a candidate word screening method and related equipment. The technical scheme provided by the invention comprises the steps of firstly obtaining pinyin and a tone track input by a user, identifying the tone of the tone track, selecting candidate words according with the tone matched with the pinyin and the pinyin from a word stock, and displaying the selected candidate words. It can be understood that, after the tones are matched to the pinyin, the range of candidate words conforming to the pinyin can be significantly narrowed, that is, the technical scheme provided by the invention can further significantly narrow the range of the searched candidate words by matching the tones to the pinyin on the basis of the candidate words searched by the pinyin in the prior art, so that the user only needs to select words to be input by the user from fewer candidate words, the time and the attention spent by the user for searching the words to be input by the user can be reduced, and the user experience can be effectively improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of a candidate word screening method according to an embodiment of the present invention;
FIG. 2 is a process diagram of the pitch track recognition model according to the embodiment of the present invention;
FIG. 3 is a schematic diagram of a human-computer interaction interface applied to an input method after pinyin (xian) input in the prior art;
FIG. 4 is a schematic diagram of a human-computer interface applied in an input method after inputting pinyin (xian) and tone tracks according to an embodiment of the present invention;
FIG. 5 is a diagram of a human-computer interface for an alternative input method application after inputting pinyin (xian) and tone tracks according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a human-computer interaction interface applied in an input method after pinyin (xian) input according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of a human-computer interface applied in another input method after inputting pinyin (xian) and pitch tracks according to an embodiment of the present invention;
FIG. 8 is a diagram illustrating training data for a pitch track recognition model according to an embodiment of the present invention;
fig. 9 is a structural diagram of a candidate word screening apparatus according to an embodiment of the present invention;
fig. 10 is a hardware structure diagram of an intelligent device according to an embodiment of the present invention.
Detailed Description
The technical solutions in 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 obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Prior to proceeding to a further detailed description of the present invention, the prior art will first be briefly described.
In the prior art, in the field of a Chinese input method, because Chinese is boldly and profound, the number of candidate words obtained through pinyin is very large, especially under the condition of single words, so that a user is required to slide gestures in a candidate word area to switch multiple screens, and meanwhile, visual search is carried out to find words to be input, so that the user is required to spend more time and attention. In addition, it is difficult to accurately search candidate words by human eyes in the visual sense of small-screen devices such as mobile phones, and some unusual words need more time spent by users and attention to be searched by repeatedly turning pages, so that the users are inevitably easy to generate dysphoric mood, and the use experience of the users is seriously influenced.
Therefore, the inventor of the present application, through creative thinking and experiments, proposes a technology capable of determining candidate words more accurately, so as to reduce the number of candidate words, and enable a user to find a word that the user wants to input more easily, so as to improve user experience, which is described in detail in the following embodiments.
Examples
The embodiment of the invention provides a candidate word screening method which can be applied to intelligent equipment comprising a touch screen, such as man-machine interaction equipment of a smart phone, a tablet personal computer and the like.
Referring to fig. 1, fig. 1 is a flowchart of a candidate word screening method according to an embodiment of the present invention. As shown in fig. 1, the method includes:
s11, obtaining pinyin and tone tracks input by a user;
specifically, the pinyin comprises at least one syllable.
Wherein, the syllable is the smallest phonetic structure unit formed by the phoneme combination, and the syllable is formed into three parts of head, abdomen and tail, so that the syllable has obvious perception boundary. In the chinese language, the pronunciation of a chinese character is a syllable. For example, if the pinyin is huan, the pinyin includes a syllable; the pinyin is huan' le, and the pinyin comprises two syllables.
Step S12, identifying the tone of the tone track;
optionally, the pitch of the pitch track is identified according to a pre-trained pitch track identification model.
Specifically, the pitch track acquired in step S11 is input to a pitch track recognition model obtained through pre-training, and a pitch corresponding to the pitch track output by the pitch track recognition model is obtained.
Optionally, referring to fig. 2, fig. 2 is a schematic diagram illustrating a process of recognizing a pitch of a pitch track by a pitch track recognition model according to an embodiment of the present invention. As shown in fig. 2, the pitch trajectory is input to a pitch trajectory recognition model obtained by training in advance, and the model calculates the score of the pitch trajectory matching each pitch, that is, the product of the probability that the current pitch trajectory belongs to each pitch and 100, and selects the pitch with the largest score as the recognition result of the current pitch trajectory. It should be noted that the above-mentioned manner of determining the recognition result of the current pitch track is only an example, and the recognition result may also be determined by other manners, for example, only comparing the probability that the current pitch track belongs to each tone, and selecting the tone with the highest probability as the recognition result of the current pitch track, and these adaptive changes do not depart from the scope of the present invention.
S13, selecting a candidate word which accords with the pinyin and the tone matched with the pinyin from a word stock, and displaying the selected candidate word;
specifically, candidate words that simultaneously conform to the pinyin and the tone matched with the pinyin are screened from the word stock, and compared with the method that only candidate words that conform to the pinyin are screened in the prior art, the method has the advantages that the range of the screened candidate words is much smaller, and then the selected candidate words are displayed.
In order to visually display the effect of the technical scheme, the invention also provides a schematic diagram of a human-computer interaction interface applied by the input method after the prior art and the scheme of the invention are used. Referring to fig. 3 and 4, fig. 3 is a schematic diagram of a human-computer interaction interface applied by an input method after pinyin (xian) input in the prior art, and fig. 4 is a schematic diagram of a human-computer interaction interface applied by an input method after pinyin (xian) and tone tracks are input according to an embodiment of the present invention. As shown in fig. 4 and the direction of the tone trajectory 41 inputted by the user, the tone corresponding to the tone trajectory 41 may be determined as the fourth tone. By comparison, it can be determined that the technical scheme provided by the embodiment can reduce the time and attention required by the user to select the word desired to be input by the user by narrowing the candidate word to the range of the tone which is in line with pinyin matching.
It can be determined from the above disclosure that, after the tones are matched to the pinyin, the range of the candidate words conforming to the pinyin can be significantly narrowed, that is, the technical scheme provided by the embodiment of the present invention can further significantly narrow the range of the searched candidate words by matching the tones to the pinyin on the basis of the candidate words searched by the pinyin in the prior art, so that the user only needs to select the words that the user wants to input from a few candidate words, the time and the attention spent by the user for searching the words that the user wants to input can be reduced, and the user experience can be effectively improved.
Further, in the candidate word screening method provided in the embodiment of the present invention, the step S11 may be implemented by:
the first mode is as follows:
acquiring a tone track input by a user in a virtual keyboard area displayed on the touch screen;
specifically, referring to fig. 4, the tone trace 41 is input by the user on the virtual keyboard displayed on the touch screen.
The second mode is as follows:
acquiring a tone track input by a user in a tone input area displayed on the touch screen;
optionally, the tone input region is created in advance by an input method application. Referring to fig. 5, fig. 5 is a schematic diagram of a human-computer interaction interface of another input method application after inputting pinyin (xian) and tone tracks according to an embodiment of the present invention. As shown in fig. 5, the tone input area 51 is created in advance by an input method application, and is located below the virtual keyboard, and a tone trajectory 52 is displayed in the tone input area 51. It should be noted that the positional relationship between the virtual keyboard and the tone input area shown in fig. 5 is merely an example, and the present invention is not limited thereto, and the positional relationship between the two may be changed without departing from the scope of the present invention.
Optionally, the tone input region is created by the input method application in response to a user trigger. Referring to fig. 6, fig. 6 is a schematic diagram of a human-computer interaction interface applied to an input method after pinyin (xian) input according to an embodiment of the present invention. As shown in fig. 6, the virtual keyboard provided by the input method application provides a virtual key 61 (i.e. a "tone" key at the bottom right corner of the virtual keyboard in fig. 6), and optionally, after the user clicks the "tone" key, the virtual keyboard is switched to a blank area by the input method application, where the blank area is a tone input area. It should be noted that the triggering manner corresponding to fig. 6 is only an example, and the triggering manner is not limited in the present invention, and the triggering manner may further include: pressing a preset key for a preset time in the virtual keyboard; pressing a preset key drags the key to a position far away from the key, and the like. I.e. a simple modification of the triggering mode, without departing from the scope of protection of the present invention.
Further, in the candidate word screening method provided in the embodiment of the present invention, the step S13 may include:
step A, establishing a matching relation between the identified tone and the final of the syllable according to a preset matching rule;
specifically, the identified tone is matched to the final of the syllable according to a preset matching rule. For example, the pinyin is huan' le, the tone tracks input by the user have two tones from left to right (assuming that the corresponding recognized tones are the first tone and the fourth tone), and the preset matching rule is to sequentially match the recognized tones to the finals of the left-to-right syllables in the pinyin from left to right and from top to bottom, in the example: the first tone is matched to a in huan and the fourth tone is matched to e in le.
B, selecting a candidate word which accords with the pinyin and the matching relation from a word stock, and displaying the selected candidate word;
specifically, candidate words which simultaneously accord with the pinyin and the matching relation are selected from a word stock and displayed.
Further, in the candidate word screening method provided in the embodiment of the present invention, the step a may include:
step A1, determining syllable dividing results of the pinyin and the number of tone tracks input by a user;
specifically, as in the pinyin huan' le above, the syllable division result is as follows: huan and le.
Step A2, if the syllable dividing result of the pinyin is one and comprises at least two syllables, and the number of the tone tracks is less than or equal to that of the syllables in the pinyin, establishing a matching relation between the identified tones and the finals of the syllables according to a preset tone selection sequence and a preset syllable selection sequence;
specifically, the step A2 includes two technical scenarios:
the first technical scenario is that the number of the tone tracks is equal to the number of syllables in the pinyin, and then, optionally, the preset tone selection sequence is as follows: the user inputs the sequence of the tone tracks, or the tone tracks are arranged in the layout of the touch screen from left to right and from top to bottom (according to the habit of the user, the sequence is generally consistent with the sequence of the tone tracks input by the user); the preset syllable selection sequence is the sequence of all syllables in the pinyin from left to right;
the second technical scenario is that the number of the tone tracks is less than the number of syllables in the pinyin, at the moment, the preset tone selection sequence is consistent with the preset tone selection sequence in the first technical scenario, and the preset syllable selection sequence is consistent with the preset tone selection sequence in the first technical scenario; since the number of tone tracks is less than the number of syllables in the pinyin, syllables in later positions in the pinyin have no chance of matching tones.
For example, the pinyin is huan' le, and the tone trajectory is only one, and assuming that the recognized tone is the first tone, the first tone is matched with the first syllable huan in the pinyin.
Step A3, if the pinyin comprises at least two syllable dividing results, taking the syllable dividing result with the tone track number syllables as a syllable dividing result to be used, and establishing a matching relation between the recognized tones and the vowels of the syllables in the syllable dividing result to be used;
specifically, the situation that one pinyin has more than one syllable dividing result sometimes occurs in Chinese, the step A3 can creatively and automatically select the required syllable dividing result according to the number of the input tone tracks, a user does not need to input separators specially in the pinyin, and the user experience can be further improved.
For example, in the pinyin xian, the syllable division result may be xi' an (two syllables xi and an) or xian (one syllable), and in this case, as shown in fig. 4, if the number of the tone tracks input by the user is 1, the xian (one syllable) is automatically selected as the syllable division result to be used, and the identified tone (fourth tone) is matched to a in the xian.
Referring to fig. 7, fig. 7 is a schematic diagram of a human-computer interaction interface applied to another input method after inputting pinyin (xian) and pitch tracks according to an embodiment of the present invention. As shown in fig. 7, if the number of tone tracks 71 input by the user is 2, xi' an (two syllables xi and an) is automatically selected as a result of the syllable division to be used, and the identified tone (two first tones) is matched to i in xi and a in an.
Optionally, in the step A3, a matching relationship between the recognized tone and the vowel of the syllable in the to-be-used syllable dividing result is established according to the preset tone selection sequence and the preset syllable selection sequence in the step A2.
Of course, if the syllable dividing result of the pinyin and the number of the tone tracks input by the user are both one, the tone obtained by identification is directly matched with the final of the pinyin.
Further, the candidate word screening method provided in the embodiment of the present invention may further include, after the obtaining of the pitch track input by the user in step S11:
displaying the pitch track;
specifically, the tone track is displayed on a touch screen.
Acquiring a tone track clearing instruction input by a user, and clearing the tone track to acquire an audio track input by the user again;
alternatively, the clear tone track instruction may be generated by a user clicking a preset virtual key in the virtual keyboard, which represents the clear tone track. Referring to FIG. 4, the user clicks the virtual key "clear" to clear the tone track 41. It should be noted that there are many ways of generating the clear tone track command triggered by the user, the example in fig. 4 is only one of them, the invention is not limited to this, and these ways may also include sliding a key, pressing a key for a certain time, and the like, and these simple changes do not depart from the scope of the invention.
Further, in the candidate word screening method provided in the embodiment of the present invention, step S13 may also be implemented in the following manner:
and sorting the candidate words in the word bank according with the pinyin and the tones matched with the pinyin according to the sequence of the use frequency of the user from top to bottom, and displaying the sorted candidate words on the touch screen.
According to the method, on one hand, the range of the searched candidate words can be obviously reduced by matching the tones through pinyin, on the other hand, the candidate words with the reduced range are sequenced according to the sequence of the use frequency of the user from top to bottom, and the sequenced candidate words are displayed on the touch screen, so that the probability that the words which the user wants to input are displayed in front can be further improved, even the user can see the words which the user wants to input without turning over the screen, the time and the attention of the user for searching the words which the user wants to input can be further reduced, and the user experience can be further improved.
Specifically, in the above embodiment of the present invention, in the step S12, the pitch of the pitch track may be identified by using a pitch track recognition model that has been trained in advance, it is understood that the pitch track recognition model needs to be trained in advance, and a training process of the pitch track recognition model will be described below.
Firstly, acquiring pictures of a plurality of user hand-written tones, and taking mark data corresponding to the pictures of the user hand-written tones as training data;
specifically, the mark data is a tone indicated by a tone track included in the picture of the user handwritten tone, specifically, a first tone, a second tone, a third tone, or a fourth tone. Optionally, referring to fig. 8, fig. 8 is a schematic diagram of training data of a pitch track recognition model according to an embodiment of the present invention. As shown in fig. 8, each set of training data 81 (a picture of the user's handwritten tones and the tones indicated by it) contains only one complete tone trace.
Then, inputting training data into a pre-established deep learning model, outputting the probability of the pitch track corresponding to each tone, selecting the tone with the maximum probability as the tone predicted by the current model, training model parameters according to the difference between the tone of the labeled data and the predicted tone, and obtaining a pitch track recognition model after training.
Specifically, the deep learning model may be constructed by a classification model commonly used in pattern recognition, such as a convolutional neural network model, a deep neural network model, and the like, which is not limited in the present invention.
It should be noted that, for smart devices such as smart phones, due to hardware resource limitation, it may be difficult to execute a training process, so the training process may be executed at one end of a server, and smart devices such as smart phones may directly acquire a trained pitch track recognition model from one end of the server, and when the acquisition mode is applicable by downloading an input method, the input method may carry the pitch track recognition model by itself.
In addition, the intelligent device can also send the tone track input by the user to the remote server, the tone track is recognized by the trained tone track recognition model of the remote server, the recognition result is fed back to the intelligent device, and the intelligent device can recognize the tone of the tone track through the recognition result.
In order to more fully explain the technical solution provided by the present invention, the present invention discloses a candidate word screening apparatus corresponding to the candidate word screening method provided by the embodiment of the present invention. The candidate word screening device provided by the embodiment of the invention can be applied to intelligent equipment comprising a touch screen, such as man-machine interaction equipment like a smart phone and a tablet personal computer.
Referring to fig. 9, fig. 9 is a structural diagram of a candidate word screening apparatus according to an embodiment of the present invention. As shown in fig. 9, the apparatus includes:
a pinyin and tone track acquisition module 11, configured to acquire pinyin and tone tracks input by a user; the pinyin comprises at least one syllable;
a pitch identification module 12 for identifying the pitch of the pitch track;
optionally, the tone recognition module 12 is specifically configured to:
the pitch of the pitch track is identified according to a pre-trained pitch track identification model.
The tone track recognition model is obtained by training a pre-established deep learning model through the picture of the tone handwritten by the user and the marking data of the tone in the picture.
And the candidate word pushing module 13 is configured to select a candidate word that matches the pinyin and the tone matched with the pinyin from the word bank, and display the selected candidate word.
It can be understood that, after the tones are matched to the pinyin, the range of candidate words conforming to the pinyin can be significantly narrowed, that is, the candidate word screening device provided in the embodiment of the present invention can further significantly narrow the range of the searched candidate words by matching the tones to the pinyin on the basis of the candidate words searched by the prior art through the pinyin, so that the user only needs to select words that the user wants to input from a small number of candidate words, the time and attention spent by the user for searching words that the user wants to input can be reduced, and the user experience can be effectively improved.
Further, in the apparatus for screening candidate words provided in the embodiment of the present invention, the pinyin and tone trajectory obtaining module 11 includes:
the first tone track acquisition unit is used for acquiring a tone track input by a user in a virtual keyboard area displayed on the touch screen;
the second tone track acquisition unit is used for acquiring a tone track input by a user in a tone input area displayed on the touch screen; the tone input region is created in advance by an input method application or in response to a user trigger.
Further, in the candidate word screening apparatus provided in the embodiment of the present invention, the candidate word pushing module 13 includes:
a matching relation establishing unit for establishing a matching relation between the identified tone and the final of the syllable according to a preset matching rule;
and the candidate word display unit is used for selecting candidate words which accord with the pinyin and the matching relation from a word bank and displaying the selected candidate words.
Optionally, the matching relationship establishing unit includes:
syllable dividing result and tone track number determining subunit, for determining syllable dividing result of the pinyin and tone track number inputted by user;
a first matching relationship establishing subunit, configured to establish, if the syllable division result of the pinyin is one type and includes at least two syllables, a matching relationship between the identified tone and the final of the syllable according to a preset tone selection sequence and a preset syllable selection sequence if the number of the tone tracks is less than or equal to the number of the syllables in the pinyin;
and the second matching relation establishing subunit is used for taking the syllable dividing result with the tone track number syllables as a syllable dividing result to be used and establishing the matching relation between the identified tones and the final sound of the syllables in the syllable dividing result to be used if the pinyin comprises at least two syllable dividing results.
Further, the candidate word screening apparatus provided in the embodiment of the present invention further includes:
a display module for displaying the pitch track;
and the tone track clearing module is used for acquiring a tone track clearing instruction input by the user and clearing the tone track to acquire the audio track input by the user again.
Further, in the candidate word screening apparatus provided in the embodiment of the present invention, the candidate word pushing module 13 is specifically configured to:
and sorting the candidate words in the word bank according with the pinyin and the tones matched with the pinyin according to the sequence of the use frequency of the user from top to bottom, and displaying the sorted candidate words on the touch screen.
Specifically, the candidate word screening apparatus provided in the embodiment of the present invention further includes:
and the tone track recognition model training module is used for training a pre-established deep learning model through the picture of the handwritten tones of the user and the marking data of the tones in the picture to obtain the tone track recognition model.
In order to more fully illustrate the technical solution provided by the present invention, the present invention discloses an intelligent device corresponding to the candidate word screening method provided by the embodiment of the present invention, where the intelligent device may be a local terminal (such as a local computer, a mobile terminal, etc.), or a remote server, etc.
Referring to fig. 10, fig. 10 is a hardware structure diagram of an intelligent device according to an embodiment of the present invention. As shown in fig. 10, the smart device includes:
a processor 1, a communication interface 2, a memory 3 and a communication bus 4;
the processor 1, the communication interface 2 and the memory 3 complete mutual communication through a communication bus 4;
a processor 1 for calling and executing the program stored in the memory;
a memory 3 for storing a program;
the program may include program code comprising computer operating instructions; in an embodiment of the present invention, the program may include: and the program corresponding to the candidate word screening method.
The processor 1 may be a central processing unit CPU or an Application Specific Integrated Circuit ASIC (Application Specific Integrated Circuit) or one or more Integrated circuits configured to implement embodiments of the present invention.
The memory 3 may comprise high-speed RAM memory and may also comprise non-volatile memory, such as at least one disk memory.
Wherein the program is specifically operable to:
obtaining pinyin and tone tracks input by a user; the pinyin comprises at least one syllable;
identifying a pitch of the pitch track;
and selecting candidate words which accord with the pinyin and the tones matched with the pinyin from a word stock, and displaying the selected candidate words.
It can be understood that, after the tones are matched to the pinyin, the range of candidate words conforming to the pinyin can be significantly narrowed, that is, the intelligent device provided by the invention can further significantly narrow the range of the searched candidate words by matching the tones to the pinyin on the basis of the candidate words searched by the pinyin in the prior art, so that the user only needs to select words to be input by the user from fewer candidate words, the time and the attention spent by the user for searching the words to be input by the user can be reduced, and the user experience can be effectively improved.
In addition, an embodiment of the present invention further provides a storage medium, where the storage medium stores a computer program, and when the computer program is executed by a processor, the computer program is configured to execute the steps of the candidate word screening method according to the foregoing embodiment.
Through the technical scheme, compared with the prior art, the invention provides a candidate word screening method and related equipment. The technical scheme provided by the invention comprises the steps of firstly obtaining pinyin and a tone track input by a user, identifying the tone of the tone track, selecting candidate words according with the tone matched with the pinyin and the pinyin from a word stock, and displaying the selected candidate words. It can be understood that, after the tones are matched to the pinyin, the range of candidate words conforming to the pinyin can be significantly narrowed, that is, the technical scheme provided by the invention can further significantly narrow the range of the searched candidate words by matching the tones to the pinyin on the basis of the candidate words searched by the pinyin in the prior art, so that the user only needs to select words to be input by the user from fewer candidate words, the time and the attention spent by the user for searching the words to be input by the user can be reduced, and the user experience can be effectively improved.
Finally, it should also be noted that, in this document, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or smart device that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or smart device. Without further limitation, an element defined by the phrases "comprising one of 8230; \8230;" 8230; "does not exclude the presence of additional identical elements in a process, method, article, or smart device that comprises the element.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The apparatus, the intelligent device and the storage medium disclosed in the embodiments correspond to the method disclosed in the embodiments, so the description is relatively simple, and the relevant points can be referred to the description of the method.
Those of skill would further appreciate that the various illustrative components and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the components and steps of the various examples have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the technical solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, or any other form of storage medium known in the art.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (16)
1. A candidate word screening method is applied to intelligent equipment comprising a touch screen, and is characterized by comprising the following steps:
obtaining pinyin and tone tracks input by a user; the pinyin comprises at least one syllable;
identifying a pitch of the pitch track;
selecting a candidate word which accords with the matching relation between the pinyin, the tone and the final of the syllable from a word stock, and displaying the selected candidate word; the matching relation is established by sequentially matching the identified tones to the finals of all syllables from left to right in the pinyin from left to right and from top to bottom; the matching relation between the tone and the final of the syllable comprises the following steps: determining syllable dividing results of the pinyin and the number of tone tracks input by a user; and if the pinyin comprises at least two syllable dividing results, taking the syllable dividing result with the tone track number syllables as a syllable dividing result to be used, and establishing a matching relation between the identified tone and the final of the syllables in the syllable dividing result to be used.
2. The method of claim 1, wherein the obtaining a pitch track of a user input comprises:
acquiring a tone track input by a user in a virtual keyboard area displayed on the touch screen;
or acquiring a tone track input by a user in a tone input area displayed on the touch screen; the tone input regions are created in advance by the input method application or in response to a user trigger.
3. The method of claim 1, wherein selecting a candidate word from a lexicon that matches the matching relationship between the pinyin and the tones with the vowels of the syllables, and displaying the selected candidate word comprises:
establishing a matching relation between the identified tone and the final of the syllable according to a preset matching rule; the preset matching rule is that the tones obtained by recognition are sequentially matched with the finals of all syllables from left to right in the pinyin from left to right and from top to bottom;
and selecting candidate words which accord with the pinyin and the matching relation from a word bank, and displaying the selected candidate words.
4. The method according to claim 3, wherein the establishing of the matching relationship between the recognized tone and the final of the syllable according to the preset matching rule further comprises:
determining syllable dividing results of the pinyin and the number of tone tracks input by a user;
and if the syllable dividing result of the pinyin is one and comprises at least two syllables, and the number of the tone tracks is less than or equal to that of the syllables in the pinyin, establishing the matching relation between the identified tones and the finals of the syllables according to a preset tone selection sequence and a preset syllable selection sequence.
5. The method of claim 1, wherein after obtaining the pitch track of the user input, further comprising:
displaying the pitch track;
and acquiring a tone track clearing instruction input by the user, and clearing the tone track to acquire the audio track input by the user again.
6. The method of claim 1, wherein selecting a candidate word from a lexicon that matches the matching relationship between the pinyin and the tones with the vowels of the syllables, and displaying the selected candidate word comprises:
and sequencing the candidate words which are in accordance with the matching relation between the pinyin and the tones and the vowels of the syllables in the word bank according to the sequence from high frequency to low frequency of the user, and displaying the sequenced candidate words on the touch screen.
7. The method according to any one of claims 1 to 6, wherein the identifying the pitch of the pitch track comprises:
recognizing the tone of the tone track according to a pre-trained tone track recognition model;
the tone track recognition model is obtained by training a pre-established deep learning model through the picture of the tone handwritten by the user and the marking data of the tone in the picture.
8. The utility model provides a candidate word sieving mechanism, is applied to the smart machine including the touch-sensitive screen, its characterized in that, the device includes:
the pinyin and tone track acquisition module is used for acquiring pinyin and tone tracks input by a user; the pinyin comprises at least one syllable;
a pitch identification module for identifying a pitch of the pitch track;
the candidate word pushing module is used for selecting candidate words which accord with the matching relation between the pinyin and the tones and the vowels of the syllables from a word stock and displaying the selected candidate words; the matching relationship is established by sequentially matching the tones obtained by identification to the finals of all syllables from left to right in the pinyin from left to right and from top to bottom; the matching relationship establishing unit includes: syllable dividing result and tone track number determining subunit, for determining syllable dividing result of the pinyin and tone track number inputted by user; and the second matching relation establishing subunit is used for taking the syllable dividing result with the tone track number syllables as a syllable dividing result to be used if the pinyin comprises at least two syllable dividing results, and establishing the matching relation between the identified tones and the final sound of the syllables in the syllable dividing result to be used.
9. The apparatus of claim 8, wherein the pinyin and tone track acquisition module comprises:
the first tone track acquisition unit is used for acquiring a tone track input by a user in a virtual keyboard area displayed on the touch screen;
the second tone track acquisition unit is used for acquiring a tone track input by a user in a tone input area displayed on the touch screen; the tone input regions are created in advance by the input method application or in response to a user trigger.
10. The apparatus of claim 8, wherein the candidate word pushing module comprises:
the matching relation establishing unit is used for establishing the matching relation between the identified tone and the final of the syllable according to a preset matching rule; the preset matching rule is that the tones obtained by identification are sequentially matched with the finals of all syllables from left to right in the pinyin from left to right and from top to bottom;
and the candidate word display unit is used for selecting the candidate words meeting the pinyin and the matching relation from the word stock and displaying the selected candidate words.
11. The apparatus according to claim 10, wherein the matching-relation establishing unit further comprises:
and the first matching relation establishing subunit is used for establishing a matching relation between the identified tone and the final of the syllable according to a preset tone selection sequence and a preset syllable selection sequence if the syllable dividing result of the pinyin is one type and comprises at least two syllables, and the number of the tone tracks is less than or equal to the number of the syllables in the pinyin.
12. The apparatus of claim 8, further comprising:
a display module for displaying the pitch track;
and the tone track clearing module is used for acquiring a tone track clearing instruction input by the user and clearing the tone track to acquire the audio track input by the user again.
13. The apparatus of claim 8, wherein the candidate word pushing module is specifically configured to:
and sequencing the candidate words which are in accordance with the matching relation between the pinyin and the tones and the vowels of the syllables in the word bank according to the sequence from high frequency to low frequency of the user, and displaying the sequenced candidate words on the touch screen.
14. The apparatus according to any one of claims 8 to 13, wherein the tone recognition module is specifically configured to:
recognizing the tone of the tone track according to a pre-trained tone track recognition model;
the tone track recognition model is obtained by training a pre-established deep learning model through the picture of the handwritten tone of the user and the marking data of the tone in the picture.
15. A smart device, comprising:
a processor and a memory, the processor and memory connected by a communication bus:
the processor is used for calling and executing the program stored in the memory;
the memory is used for storing a program, and the program is at least used for executing the candidate word screening method according to any one of claims 1 to 7.
16. A storage medium on which a computer program is stored, the computer program, when executed by a processor, implementing the steps of the candidate word screening method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810299350.0A CN108549493B (en) | 2018-04-04 | 2018-04-04 | Candidate word screening method and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810299350.0A CN108549493B (en) | 2018-04-04 | 2018-04-04 | Candidate word screening method and related equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108549493A CN108549493A (en) | 2018-09-18 |
| CN108549493B true CN108549493B (en) | 2022-10-04 |
Family
ID=63513972
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810299350.0A Active CN108549493B (en) | 2018-04-04 | 2018-04-04 | Candidate word screening method and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108549493B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111310440B (en) * | 2018-11-27 | 2023-05-30 | 阿里巴巴集团控股有限公司 | Text error correction method, device and system |
| CN111078028B (en) * | 2019-12-09 | 2023-11-21 | 科大讯飞股份有限公司 | Input method, related device and readable storage medium |
| CN111090341A (en) * | 2019-12-24 | 2020-05-01 | 科大讯飞股份有限公司 | Input method candidate result display method, related equipment and readable storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102478969A (en) * | 2010-11-25 | 2012-05-30 | 腾讯科技（深圳）有限公司 | Method and device for screening candidate Chinese characters |
| KR20120134580A (en) * | 2011-06-02 | 2012-12-12 | 주식회사 참글 | A letter input method of chinese with function of intonation choice for touch screen |
| CN103383699A (en) * | 2013-06-28 | 2013-11-06 | 安徽科大讯飞信息科技股份有限公司 | Character string retrieval method and system |
| CN103713845A (en) * | 2013-12-16 | 2014-04-09 | 北京搜狗科技发展有限公司 | Method for screening candidate items and device thereof, text input method and input method system |
| CN104635949A (en) * | 2015-01-07 | 2015-05-20 | 三星电子（中国）研发中心 | Chinese character input device and method |
| CN106033316A (en) * | 2015-03-13 | 2016-10-19 | 北京搜狗科技发展有限公司 | Method and device for hand input |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6562078B1 (en) * | 1999-06-29 | 2003-05-13 | Microsoft Corporation | Arrangement and method for inputting non-alphabetic language |
| CN100517190C (en) * | 2006-11-08 | 2009-07-22 | 丁树雄 | Chinese character phonetic input technology plan by specific latin alphabet and tone |
| JP5438909B2 (en) * | 2008-03-14 | 2014-03-12 | ソニーモバイルコミュニケーションズ株式会社 | Character input device, character input support method, and character input support program |
| KR20100003831A (en) * | 2008-07-02 | 2010-01-12 | 삼성전자주식회사 | Chinese character input apparatus, and method thereof |
| CN102279652A (en) * | 2010-06-11 | 2011-12-14 | 宏达国际电子股份有限公司 | Electronic device and input method thereof |
| CN102520874B (en) * | 2011-12-30 | 2013-10-16 | 楚博纯 | Pinyin input method based on touch screen and device |
| CN104102438B (en) * | 2013-04-08 | 2018-03-09 | 储振华 | A kind of Chinese character pinyin input method based on touch panel device |
| CN103886043B (en) * | 2014-03-11 | 2017-10-20 | 北京搜狗科技发展有限公司 | A kind of method and device for showing candidate item |
| CN107037887B (en) * | 2016-02-03 | 2021-11-02 | 北京搜狗科技发展有限公司 | Method and device for Chinese character input and electronic equipment |
-
2018
- 2018-04-04 CN CN201810299350.0A patent/CN108549493B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102478969A (en) * | 2010-11-25 | 2012-05-30 | 腾讯科技（深圳）有限公司 | Method and device for screening candidate Chinese characters |
| KR20120134580A (en) * | 2011-06-02 | 2012-12-12 | 주식회사 참글 | A letter input method of chinese with function of intonation choice for touch screen |
| CN103383699A (en) * | 2013-06-28 | 2013-11-06 | 安徽科大讯飞信息科技股份有限公司 | Character string retrieval method and system |
| CN103713845A (en) * | 2013-12-16 | 2014-04-09 | 北京搜狗科技发展有限公司 | Method for screening candidate items and device thereof, text input method and input method system |
| CN104635949A (en) * | 2015-01-07 | 2015-05-20 | 三星电子（中国）研发中心 | Chinese character input device and method |
| CN106033316A (en) * | 2015-03-13 | 2016-10-19 | 北京搜狗科技发展有限公司 | Method and device for hand input |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108549493A (en) | 2018-09-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107230475B (en) | Voice keyword recognition method and device, terminal and server | |
| CN106774970B (en) | Method and device for sorting candidate items of input method | |
| EP2960761B1 (en) | Method, system and device for inputting text by consecutive slide | |
| CN105810188B (en) | Information processing method and electronic equipment | |
| CN108700996B (en) | System and method for multiple input management | |
| CN108846037B (en) | Method and device for prompting search terms | |
| CN108549493B (en) | Candidate word screening method and related equipment | |
| CN105869640B (en) | Method and device for recognizing voice control instruction aiming at entity in current page | |
| JP2017514248A (en) | A superimposed handwritten character recognition technology system and a superimposed handwritten character recognition technology method. | |
| CN104199606B (en) | A kind of method and apparatus sliding input | |
| WO2014190732A1 (en) | Method and apparatus for building a language model | |
| CN101681198A (en) | Providing relevant text auto-completions | |
| CN103713845B (en) | Method for screening candidate items and device thereof, text input method and input method system | |
| KR20130058053A (en) | Method and apparatus for segmenting strokes of overlapped handwriting into one or more groups | |
| CN114365075A (en) | Method for selecting a graphical object and corresponding device | |
| JP2005508031A (en) | Adaptable stroke order system based on radicals | |
| WO2014181508A1 (en) | Information processing apparatus, information processing method, and program | |
| CN105260113B (en) | Slide input method, device and terminal device | |
| CN105353957A (en) | Information display method and terminal | |
| US7979795B2 (en) | System and method for inputting syllables of a phonetic script into a computer | |
| CN114049890A (en) | Voice control method and device and electronic equipment | |
| CN103294223A (en) | Input method and terminal device for Chinese Pinyin | |
| KR20120063407A (en) | Rapid text input method using a touch screen and a device for the same | |
| CN111428487B (en) | Model training method, lyric generation method, device, electronic equipment and medium | |
| JP2011237876A (en) | Character input device, character input method, and character input program |
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 |