CN106896936B - Vocabulary pushing method and device - Google Patents
Vocabulary pushing method and device Download PDFInfo
- Publication number
- CN106896936B CN106896936B CN201710102235.5A CN201710102235A CN106896936B CN 106896936 B CN106896936 B CN 106896936B CN 201710102235 A CN201710102235 A CN 201710102235A CN 106896936 B CN106896936 B CN 106896936B
- Authority
- CN
- China
- Prior art keywords
- word
- candidate
- vocabulary
- syllable unit
- sentence
- 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
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
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Document Processing Apparatus (AREA)
- Machine Translation (AREA)
Abstract
The application discloses a vocabulary pushing method and device. One embodiment of the method comprises: receiving at least one syllable unit input by a user; responding to the input position corresponding to the at least one syllable unit to have the above words, and acquiring the above words; detecting whether a candidate word having an association relation with the above word vocabulary exists in the candidate words corresponding to the first syllable unit of the at least one syllable unit; determining the sentence head of the semantic unit corresponding to the at least one syllable unit according to the detection result; and selecting candidate words for each syllable unit based on the determined sentence start for vocabulary pushing. This embodiment may improve the effectiveness of vocabulary pushing.
Description
Technical Field
The application relates to the technical field of computers, in particular to the technical field of data processing, and particularly relates to a vocabulary pushing method and device.
Background
At present, in the interaction process between a terminal and a user, the information input by the user is often required to be received and identified. In some terminal applications, after the information input by the user is further recognized, a plurality of recognition results are listed for the user to select, for example, a plurality of vocabularies are listed for the user to select according to the syllable unit input by the user. Taking an input method as an example, in the existing input method, in the process of pushing a Chinese vocabulary, the vocabulary is pushed by matching a syllable unit input by a user with a syllable unit in a preset dictionary. In the predetermined dictionary, each syllable unit may correspond to one or more words, phrases, and the like, for example, the syllable unit "danyuan" may correspond to "unit", "wish" or "source of nitrogen", and the like. If the syllable unit input by the user comprises a plurality of syllable units in the dictionary, the Chinese character corresponding to each syllable unit is often obtained, the probability P1 of the candidate word corresponding to the first syllable unit is calculated, the probability P2 of the conversion of the candidate word corresponding to the first syllable unit to the second syllable unit is calculated, and the like is repeated until the probability P2 of the conversion of the candidate word corresponding to the last syllable unit from the last syllable unit to the last syllable unit is calculated, and the vocabulary is selected from large to small according to the total probability obtained by the product of P1 multiplied by P2 multiplied by P3 … …. Therefore, there is a need to further combine context and context to improve the accuracy and pertinence of vocabulary push, thereby achieving more efficient vocabulary push.
Disclosure of Invention
It is an object of the present application to provide an improved vocabulary pushing method and apparatus to solve the technical problems mentioned in the background section above.
In a first aspect, the present application provides a vocabulary pushing method, including: receiving at least one syllable unit input by a user; responding to the input position corresponding to the at least one syllable unit to have the above words, and acquiring the above words; detecting whether a candidate word having an association relation with the above word vocabulary exists in the candidate words corresponding to the first syllable unit of the at least one syllable unit; determining the sentence head of the semantic unit corresponding to the at least one syllable unit according to the detection result; and selecting candidate words for each syllable unit based on the determined sentence start for vocabulary pushing.
In some embodiments, determining the beginning of the semantic unit corresponding to the at least one syllable unit according to the detection result includes: determining the word assembly as a sentence head in response to detecting that a candidate word having an association relation with the word assembly exists in the candidate words corresponding to the first syllable unit of the at least one syllable unit; and in response to detecting that no candidate word having an association relation with the word set exists in the candidate words corresponding to the first syllable unit of the at least one syllable unit, determining the starting position of the at least one syllable unit input by the user as the beginning of the sentence.
In some embodiments, selecting candidate words for each syllable unit based on the determined beginning of the sentence for lexical push comprises: sequentially combining the candidate words corresponding to the syllable units to generate a candidate pushed vocabulary combination; determining the importance coefficient of each candidate vocabulary combination based on the conversion probability of the adjacent vocabulary in the candidate pushed vocabulary combination; and selecting the vocabulary combination from the candidate pushed vocabulary combinations according to the sequence of the importance coefficients from large to small for pushing.
In some embodiments, the importance coefficient includes a product of a probability of a beginning of a period, a probability of a conversion of the beginning of the period with a first word in the candidate pushed word combination, and probabilities of conversions of adjacent words in the candidate pushed word combination.
In some embodiments, when there is no candidate word associated with the word group in the candidate word corresponding to the first syllable unit, the product of the probability of the beginning of the sentence and the probability of the conversion of the beginning of the sentence and the first word in the candidate pushed word combination is calculated by using the frequency of the first word in the candidate pushed word combination as the beginning of the sentence/the total word frequency of the first word in the candidate pushed word combination; and when the candidate words corresponding to the first syllable unit have the candidate words having the association relation with the words in the text, replacing the product of the probability of the beginning of the sentence and the conversion probability of the beginning of the sentence and the first word in the candidate pushed word combination with the occurrence probability of the first word in the candidate pushed word combination.
In some embodiments, the association relationship comprises: the transition probability is higher than a preset probability threshold.
In some embodiments, the conversion probability comprises: frequency of the last/total frequency of the last vocabulary.
In a second aspect, the present application further provides an apparatus for pushing vocabulary, the apparatus including: a receiving module configured to receive at least one syllable unit input by a user; the obtaining module is configured to respond to the situation that the input position corresponding to the at least one syllable unit has the above vocabulary, and obtain the above vocabulary; the detection module is configured to detect whether a candidate word having an association relation with the above vocabulary exists in the candidate word corresponding to the first syllable unit of the at least one syllable unit; a determining module configured to determine a sentence start of the semantic unit corresponding to the at least one syllable unit according to the detection result; and the pushing module is configured for selecting candidate words for each syllable unit based on the determined sentence start to carry out vocabulary pushing.
In some embodiments, the determining module is further configured to: determining the word assembly as a sentence head in response to detecting that a candidate word having an association relation with the word assembly exists in the candidate words corresponding to the first syllable unit of the at least one syllable unit; and in response to detecting that no candidate word having an association relation with the word set exists in the candidate words corresponding to the first syllable unit of the at least one syllable unit, determining the starting position of the at least one syllable unit input by the user as the beginning of the sentence.
In some embodiments, the push module comprises: the combination unit is configured to sequentially combine the candidate words corresponding to the syllable units to generate a candidate pushed vocabulary combination; the determining unit is configured to determine an importance coefficient of each candidate vocabulary combination based on the conversion probability of adjacent vocabularies in the candidate pushed vocabulary combination; and the pushing unit is configured to select a vocabulary combination from the candidate pushed vocabulary combinations according to the sequence of the importance coefficients from large to small for pushing.
In some embodiments, the importance coefficient includes a product of a probability of a beginning of a period, a probability of a conversion of the beginning of the period with a first word in the candidate pushed word combination, and probabilities of conversions of adjacent words in the candidate pushed word combination.
In some embodiments, when there is no candidate word associated with the word group in the candidate word corresponding to the first syllable unit, the product of the probability of the beginning of the sentence and the probability of the conversion of the beginning of the sentence and the first word in the candidate pushed word combination is calculated by using the frequency of the first word in the candidate pushed word combination as the beginning of the sentence/the total word frequency of the first word in the candidate pushed word combination;
and when the candidate words corresponding to the first syllable unit have the candidate words having the association relation with the words in the text, replacing the product of the probability of the beginning of the sentence and the conversion probability of the beginning of the sentence and the first word in the candidate pushed word combination with the occurrence probability of the first word in the candidate pushed word combination.
In some embodiments, the association relationship comprises: the transition probability is higher than a preset probability threshold.
In some embodiments, the conversion probability comprises: frequency of the last/total frequency of the last vocabulary.
In a third aspect, the present application further provides a computing device comprising: one or more processors; storage means for storing one or more programs; when executed by the one or more processors, cause the one or more processors to implement the methods described above.
The vocabulary pushing method and the device provided by the application receive at least one syllable unit input by a user, then respond to the situation that the input position corresponding to the syllable unit has the vocabulary, obtain the vocabulary, then detect whether the candidate word corresponding to the first syllable unit in the syllable unit has the candidate word which has the association relation with the vocabulary, then determine the sentence head of the semantic unit corresponding to the syllable unit according to the detection result, and then select the candidate word for each syllable unit based on the determined sentence head to push the vocabulary. Because the vocabulary is selected to be pushed based on the incidence relation between the candidate word corresponding to the first syllable unit and the word of the previous sentence, the relation between the currently input byte unit and the context is fully considered, the accuracy and pertinence of the vocabulary pushing can be improved, and the more effective vocabulary pushing is realized.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:
FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;
FIG. 2 is a flow diagram of one embodiment of a vocabulary push method in accordance with the present application;
FIGS. 3a and 3b are schematic diagrams of application scenarios of an embodiment of a vocabulary pushing method according to the application;
FIG. 4 is a flow diagram of another embodiment of a vocabulary push method in accordance with the present application;
FIG. 5 is a schematic diagram of generating candidate vocabulary combinations according to an embodiment of the vocabulary pushing method of the present application;
FIG. 6 is a schematic diagram illustrating one embodiment of a vocabulary pushing apparatus according to the present application;
fig. 7 is a schematic structural diagram of a computer system suitable for implementing the terminal device or the server according to the embodiment of the present application.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
FIG. 1 illustrates an exemplary system architecture 100 to which embodiments of the vocabulary pushing method or apparatus of the present application may be applied.
As shown in fig. 1, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The terminal devices 101, 102, 103 may have installed thereon various communication client applications, such as an input method application, a web browser application, a shopping application, a search application, an instant messaging tool, a mailbox client, social platform software, and the like.
The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting voice or symbol input, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving picture Experts Group Audio Layer III, motion picture Experts compression standard Audio Layer 3), MP4 players (Moving picture Experts Group Audio Layer IV, motion picture Experts compression standard Audio Layer 4), laptop and desktop computers, and the like.
The server 105 may be a server that provides various services, such as a background server that provides support for input methods displayed on the terminal devices 101, 102, 103, and the like. The server 105 may analyze and otherwise process data such as the received vocabulary input request, and feed back the processing result (e.g., the pushed vocabulary) to the terminal device.
It should be noted that the vocabulary pushing method provided in the present application may be executed by the server 105, the terminal devices 101, 102, and 103, or the server 105 and the terminal devices 101, 102, and 103 may execute some steps therein, which is not limited in the present application. Accordingly, the vocabulary pushing apparatus may be disposed in the server 105, or in the terminal devices 101, 102, 103, or in the server 105 and the terminal devices 101, 102, 103, respectively, as part of the modules or units therein.
It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation. For example, when the vocabulary pushing method provided by the present application is executed by the terminal apparatuses 101, 102, 103, the number of networks and servers, respectively, may be zero.
With continued reference to FIG. 2, a flow 200 of one embodiment of a vocabulary push method in accordance with the present application is illustrated. The vocabulary pushing method comprises the following steps:
at step 201, at least one syllable unit input by a user is received.
In this embodiment, the electronic device (e.g., the terminal device 101, 102, or 103 shown in fig. 1) on which the vocabulary pushing method operates may receive at least one syllable unit input by the user through the input device.
The input device herein may include, but is not limited to, at least one of the following: a microphone, a keyboard, a touch screen, a stylus, etc. Accordingly, the at least one syllable unit input by the user may also include, but is not limited to, one or more of speech, characters, and the like.
It is understood that in this embodiment, a syllable unit may include one or more syllables, for example, in chinese, a reading of a chinese character is usually a syllable, and a syllable unit may include a chinese character or a pinyin of a word. When the vocabulary pushing method of the present application is applied to an input method application including chinese, the syllable unit input by the user may also be abbreviated pinyin, such as two initials (or the first letter of pinyin) "dy", which may be syllable units "danyuan", "dingyu", "duiying", and so on, and the electronic device may determine that it matches with the initial (or the first letter of pinyin) of the preset vocabulary in the preset dictionary, which is not described herein again. The preset vocabulary in the preset dictionary can be captured from the existing tool book (such as a modern Chinese dictionary), and statistics can also be performed by acquiring a large number of documents or vocabulary selections input by a user, which is not limited in the application. Alternatively, when the statistics is performed by acquiring a large number of documents, adjacent chinese characters having a conversion probability greater than a preset threshold value, such as "unit", "input method", and the like, may be used as words. Where the transition probability may be used to indicate the probability that adjacent words appear together, or the probability that a subsequent word appears after a previous word. By way of example, the probability of a transition between "single" and "element" may be calculated by: in the counted text, the frequency of occurrence of the meta word after the single word is divided by the total frequency of occurrence of the single word.
In this embodiment, the electronic device (for example, the terminal device 101, 102, or 103 shown in fig. 1) on which the vocabulary pushing method is executed may then detect whether the input location corresponding to the at least one syllable unit has the above vocabulary, and in response to the input location corresponding to the at least one syllable unit having the above vocabulary, obtain the detected above vocabulary.
Here, the electronic device may detect an input environment to determine an input position corresponding to the at least one syllable unit. For example, when the input environment is a text, the electronic device may determine the input position corresponding to the at least one syllable unit by positioning a cursor, and when the input environment is a voice, the electronic device may determine the input position corresponding to the at least one syllable unit by detecting a language pause of the user, and the like. After determining the input position, the electronic device may further detect whether the input position has a text vocabulary for different input environments, for example, when the input environment is text, detect whether a character before the cursor is a punctuation mark or a word, if the punctuation mark is the punctuation mark, determine that the input position does not have the text vocabulary, if the text is the word, determine that the input position has the text vocabulary, and further determine the text vocabulary according to whether the word is a single word or a word before the word. As an example, if the word "syllable" is in front of the cursor, the electronic device first detects that the character before the cursor is the word "syllable", and then determines that the above word exists at the input position, and further, if the electronic device detects that the character "sound" before "syllable" is a word "syllable" together with "syllable", then obtains the above word "syllable". Similarly, when the input environment is speech, for example, the electronic device may identify a place where the pause duration exceeds a preset pause threshold (e.g., 0.5 second) when the user inputs speech as a punctuation mark in the text, and obtain the above vocabulary by a method similar to the text, which is not described herein again.
In this embodiment, the electronic device (for example, the terminal device 101, 102, or 103 shown in fig. 1) on which the vocabulary pushing method operates may further detect a candidate word corresponding to a first syllable unit of the at least one syllable unit to determine whether there is a candidate word having an association relationship with the above vocabulary. Here, the candidate word may include a word or a word corresponding to a syllable unit, and the number of words included in the candidate word is the same as the number of syllables included in the syllable unit.
It will be appreciated that a syllable unit may correspond to one or more candidates, for example for syllable unit "dan," the candidate may correspond to "but", "single", "egg", "dan", "light", etc. In some implementations, the syllable units may have different syllable divisions, so as to correspond to different candidate words, for example, the syllable unit "xian" may be divided into one syllable, corresponding to the candidate word "first, present, or county …", or may be divided into two syllables, corresponding to the candidate word "shaan, west bank …", which may all be used as the candidate word corresponding to the syllable unit "xian"; for another example, the syllable unit "mingan" may be divided into "ming 'an" corresponding candidate word "light and shade, hit …", and may also be divided into "min' gan" corresponding candidate word "sensitive …", and the candidate words "light and shade, hit, sensitive …" may all be used as candidate words corresponding to the syllable unit "mingan"; this is not limited in this application. It is worth mentioning that the electronic device may match the obtained at least one syllable unit with syllables in a preset dictionary to obtain syllable units of which the at least one syllable unit is divided according to possible situations. In some implementations, in order to reduce the data processing amount of the electronic device, the electronic device may only select words with a user selection frequency greater than a preset threshold (e.g., 10%) as candidate words of corresponding syllable units, or select a preset number (e.g., 10) of words arranged at the top as candidate words by sorting the user selection frequencies of the words from high to low. Wherein the user selection frequency can be calculated by dividing the number of times a certain vocabulary is selected when the user inputs the corresponding syllable unit by the total number of times the user inputs the syllable unit. In other implementations, for example, the candidate word "bo" corresponding to the syllable unit "bo" may not be able to be selected according to the aforementioned user selection frequency, however, if the user inputs the syllable unit "bo" after inputting the "brute" word, the user is likely to want to input the "brute bo", and therefore, in order to avoid missing the vocabulary really wanted to be input by the user, the electronic device may use all the vocabularies possibly corresponding to the syllable unit as candidate words.
In general, some words may have some correlation between them (word to word ). For example, two words that can be grouped into words (e.g., "single" and "element") have relevance, some words or words in common vocabulary collocations (e.g., "car" and "ride") have relevance, and so on. Here, the electronic device may express such correlation by an association relationship. In some implementations, the association relationship may include: the transition probability is higher than a preset probability threshold. The conversion probability can be used to represent the probability of continuous occurrence of words. For example, the word "device" may appear after the word "electronic", the word "device" appears once after the word "electronic", there is a conversion from the word "electronic" to the word "device", and the probability of conversion between the word "electronic" and the word "device" may be the probability of the word "device" appearing after the word "electronic". Alternatively, the conversion probability may be calculated by: frequency of the last/total frequency of the last vocabulary. The word frequency can be used for representing the number of times of occurrence of words in the statistical file, and the frequency can be used for representing the number of times.
Therefore, the electronic device can detect whether the candidate word corresponding to the first syllable unit of the at least one syllable unit input by the user is included in the candidate word with the association relation in the obtained word set.
In this embodiment, the electronic device may further determine a beginning of a semantic unit corresponding to at least one syllable unit according to a detection result of step 203, where the detection result indicates whether a candidate word associated with the word group exists in the candidate word corresponding to the first syllable unit of the at least one syllable unit input by the user. Here, the term may be a start word or a start position of the semantic unit.
It will be appreciated that one or more syllable units may correspond to semantic units, each of which may have a start word or start position. Different words corresponding to syllable units may form different semantic units, and these semantic units are all semantic units corresponding to one or more syllable units. For example, the syllable units "yinjie" and "danyuan" may correspond to the semantic units "syllable unit" or "musical scale wish", and so on. These semantic units may be found in an existing dictionary or may be defined by the user himself, which is not limited in this application.
In practice, when a user inputs at least one syllable unit, the user often wants to input a corresponding semantic unit. For example, a user entering "yinjie danyuan" may wish to enter the semantic unit "syllable unit". However, the user may not input the syllable unit according to the splitting of the semantic unit, for example, when the semantic unit "syllable unit" is input, the user may input the "tone" first, and then input the syllable unit "jie danyuan", at this time, if the position of inputting the "jie danyuan" is taken as the beginning of the corresponding semantic unit, the semantic unit such as "order taker" may be obtained. What the user wants to get is the self-defined semantic unit "syllable unit" to form the semantic unit "syllable unit" with the above vocabulary "sound". At this time, the electronic device may determine the beginning of the sentence based on the detection result that the candidate word "node, miss …" corresponding to the first syllable unit "jie" has the association relationship "node" with the word "tone".
In an alternative implementation manner of this embodiment, the electronic device may determine the above word assembly as a beginning of a sentence in response to detecting that a candidate word having an association relationship with the above word assembly exists in the candidate word corresponding to the first syllable unit of the at least one syllable unit, such as determining the above word assembly "sound" as a beginning of a semantic unit corresponding to the at least one byte unit "jiedanyuan" in the foregoing example; in response to detecting that there is no candidate word having an association with the above word group in the candidate word corresponding to the first syllable unit of the above at least one syllable unit, the start position of the user input of the at least one syllable unit is determined as the beginning of the sentence, and as the beginning of the sentence, the start position of the user input of "yinjie danyuan" is determined as the beginning of the sentence in the foregoing example. Optionally, when the input position corresponding to the at least one syllable unit does not have the above vocabulary, for example, the input position is a beginning of a text, a beginning of a paragraph, and the like, in this case, the electronic device may also determine the starting position of the at least one syllable unit as a beginning of a sentence.
In this embodiment, the electronic device on which the vocabulary pushing method operates may further select the candidate words of each syllable unit of the at least one syllable unit according to the beginning of the sentence determined in step 204, so as to select the corresponding vocabulary for the at least one syllable unit for pushing to the user.
Taking the above-mentioned upper vocabulary as "sound", and the obtained at least one syllable unit includes "jiedanyuan", the electronic device may select the candidate word "syllable, order …" corresponding to the syllable unit "jie", the candidate word "syllable" unit corresponding to the syllable unit "danyuan", but wish, nitrogen source … ", and so on, according to the determined sentence head" sound ", and push the combination of words to the user. The words can be pushed to the user after being combined, or candidate words can be selected and pushed to the user for each syllable unit in sequence, which is not limited in the present application.
As an application scenario, the vocabulary pushing method provided by the present application may be applied to an input method application, as shown in fig. 3a and 3b, which may be installed and run on the terminal 300. In the application scenario of fig. 3a and 3b, the input method application is invoked when a user interacts through a social client running on the terminal 300.
Referring first to fig. 3a, a user has entered the text 301 "next to work" and entered at least one syllable unit 302 "qihuiqu" through a social class client running on a terminal 300. The terminal 300 receives the at least one syllable unit 302 "qihuiqu"; next, the terminal 300 detects the input environment of the at least one syllable unit 302, determines that the above word "one" exists, and the terminal 302 obtains the above word "one"; then, the terminal 300 can match at least one syllable unit 302 "qihuiqu" with syllable units in a preset dictionary, and if "qi" (e.g. corresponding candidate word, its beginning, its ride, etc.), "qihui" (e.g. corresponding candidate word, its grey, etc.), "qihuiqu" (e.g. corresponding candidate word rides back, etc.) can be matched with the corresponding syllable unit, they can all be the first syllable unit, and the terminal 300 can further detect whether there is a candidate word having an association relationship with the previous word in each of their corresponding candidate words, where, for example, there is an association relationship between the candidate word "beginning" and the previous word "one"; then, according to the detection result, the terminal 300 may determine that the beginning of the semantic unit corresponding to the at least one syllable unit 302 "qihuiqu" is "one"; then, the terminal 300 may select candidate words "start" and "go back" for syllable units such as "qi" and "huiqu" respectively according to the determined sentence head "one" to obtain the vocabulary 303 "start going back" for vocabulary pushing. It should be noted that, in this application scenario, the terminal 300 may only push the vocabulary "back" to the user, or may use "back" as the first pushed vocabulary, and other selectable vocabularies are provided later, which is not limited in this application.
To more clearly illustrate the effect achieved by the embodiment of the vocabulary pushing method of the present application, please continue to refer to fig. 3 b. Fig. 3b is similar to the scenario of fig. 3a, with at least one syllable unit 305 "qihuiqu" entered by the user coinciding with at least one syllable unit 302, except that: the text input by the user through the terminal 300 is the text 304 "go to work and hold a car"; the above words obtained by the terminal 300 are summarized as "vehicle"; the candidate word "ride" is associated with the above word "car" in the candidate word corresponding to the first syllable unit of the at least one syllable unit 305; the determined sentence head is 'car'; the vocabulary 306 "ride back" is selected as the first pushed vocabulary for vocabulary pushing according to the sentence head "car".
It is understood that, although the application scenarios in fig. 3a and 3b are described in the context of the terminal 300 executing the vocabulary pushing method in the present application, the terminal 300 may also upload at least one syllable unit input by the user to a background server providing support for the input method application, execute the vocabulary pushing method in the present application by the background server, and send the vocabulary selected by the vocabulary pushing method in the present application to the terminal 300 for presentation.
Therefore, in the vocabulary pushing method of the embodiment, because the vocabulary is selected to be pushed based on the association relationship between the candidate word corresponding to the first syllable unit and the vocabulary in the above text, the relation between the currently input byte unit and the context is fully considered, the accuracy and pertinence of the vocabulary pushing can be improved, and the more effective vocabulary pushing is realized.
With continued reference to FIG. 4, a flow 400 of another embodiment of a vocabulary push method in accordance with the present application is illustrated. The vocabulary pushing method comprises the following steps:
at step 401, at least one syllable unit input by a user is received.
In this embodiment, the electronic device (e.g., the terminal device 101, 102, or 103 shown in fig. 1) on which the vocabulary pushing method operates may receive at least one syllable unit input by the user through the input device. Wherein a syllable unit may comprise one or more syllables.
In this embodiment, the electronic device may then detect whether the input location corresponding to the at least one syllable unit has the above vocabulary, and obtain the detected above vocabulary in response to the input location corresponding to the at least one syllable unit having the above vocabulary. The electronic device may determine the input position corresponding to the at least one syllable unit according to an input environment, for example, the input position is determined by positioning a cursor in a text input environment, the input position is determined by detecting a language pause of a user in a speech input environment, and the like, which is not limited in the present application.
In this embodiment, the electronic device may further detect a candidate word corresponding to a first syllable unit of the at least one syllable unit to determine whether there is a candidate word having an association relationship with the above vocabulary. Wherein the incidence relation can be used for representing the relevance between the vocabularies. In some implementations, the association relationship may include: the transition probability is higher than a preset probability threshold. The transition probability here may mean the probability of the vocabulary occurring successively. Alternatively, the conversion probability may be calculated by: the number of times the next vocabulary appears after the previous vocabulary/the total number of times the previous vocabulary has appeared.
In this embodiment, the electronic device may further determine, according to the detection result detected in step 403, a beginning of a semantic unit corresponding to the at least one syllable unit. Here, the term may be a start word or a start position of the semantic unit.
In an optional implementation manner of this embodiment, the electronic device may determine, in response to detecting that a candidate word having an association relationship with the previous word exists in the candidate words corresponding to the first syllable unit of the at least one syllable unit, the previous word as a beginning of a sentence; and in response to detecting that no candidate word having an association relation with the word set exists in the candidate words corresponding to the first syllable unit of the at least one syllable unit, determining the starting position of the at least one syllable unit input by the user as the beginning of the sentence.
And 405, sequentially combining the candidate words corresponding to the syllable units to generate a candidate word combination.
In this embodiment, the electronic device may further combine the candidate words corresponding to the syllable units according to the beginning of the sentence determined in step 404, and generate a candidate vocabulary combination.
As an example, as shown in fig. 5, assuming that the above text of the at least one syllable unit 502 "ceuchinpyinshuru" input by the user is "yes here", the above electronic apparatus obtains the above vocabulary "yes". Further, by detecting that the electronic device determines that no candidate word having an association relationship with the word "yes" exists in the candidate words corresponding to the syllable unit "ce", "ceshi", or "cehisin", the determined sentence start 501 is the input position of at least one syllable unit 502. In the electronic apparatus, at least one syllable unit 502 "processinylacuu" is divided into syllable unit combinations such as "ce" shi 'pin "yin" shu "ru", "processi' pinin 'shu' ru", "ce 'shipin' yinhu 'ru", "processi' pinin 'shu' ru", "ce 'shipin' shu" and "ce 'shi pin' yin 'shu' ru" … … according to different syllable unit dividing methods, and candidate words corresponding to each syllable unit are obtained. Further, the electronic device may combine the corresponding candidate words according to the syllable unit combination to form the word graph 503. In the word graph 503, the sequential combination of words in each path is a candidate pushed word combination, for example, "measure-food-quote-in" is a candidate pushed word combination.
In this embodiment, the electronic device may further obtain, for each candidate pushed vocabulary combination, a conversion probability of an adjacent vocabulary, and calculate an importance coefficient of the corresponding candidate pushed vocabulary combination according to the obtained conversion probability.
The importance coefficient here can be used to quantify the probability that each candidate word in the candidate pushed word combination is combined together. In practice, in the candidate pushed vocabulary combination, the higher the conversion probability of each adjacent vocabulary is, the higher the importance coefficient thereof is. In some implementations, the importance coefficient may include a product of a probability of a beginning of a period, a probability of conversion of the beginning of the period with a first word in the candidate pushed word combination, and probabilities of conversion of adjacent words in the candidate pushed word combination. For example, the importance coefficient may be calculated by the following formula:
P(S)＝P($)*P(w1|$)*P(w2|w1)...*P(wn|wn-1)；
wherein P (S) represents a candidate pushed vocabulary combinationThe importance coefficient, $ represents the sentence head, P ($) represents the sentence head probability, W1、W2、……WnRepresenting each word of the candidate pushed word combination, n representing the number of words in the candidate pushed word combination, P (w)1| $) represents the probability of the conversion of the sentence start to the first vocabulary in the candidate pushed vocabulary combination, P (w)2|w1)、...、P(wn|wn-1) Respectively representing the conversion probability of each adjacent candidate word in the candidate word combination.
In some optional implementations, when there is no candidate word having an association relationship with the word group in the candidate word corresponding to the first syllable unit, the product of the probability of the beginning of the sentence and the probability of the conversion of the beginning of the sentence and the first word in the candidate pushed word combination is calculated by using the frequency of the first word in the candidate pushed word combination as the beginning of the sentence/the total word frequency of the first word in the candidate pushed word combination, that is: p ($) P (w)1|$)＝p($,w1)＝c($,w1)/c(w1) Wherein, c ($, w)1) Indicating the frequency of the first word as the beginning of the sentence in the candidate pushed word combination, c (w)1) Representing a total word frequency of a first word in the candidate pushed word combination;
when a candidate word having an association relation with the word group in the text exists in the candidate word corresponding to the first syllable unit, replacing the product of the probability of the beginning of the sentence and the conversion probability of the beginning of the sentence and the first word in the candidate pushed word combination with the occurrence probability of the first word in the candidate pushed word combination, namely: p ($) P (w)1I $ is replaced by p (w)1). Wherein, p (w)1)＝c(w1) /Σ c, where p (w)1) Representing the probability of occurrence of the first word in the candidate pushed word combination in the text under statistics, c (w)1) Indicates the frequency of occurrence of the first vocabulary in the candidate pushed vocabulary combination in the text under statistics, and Σ c indicates the sum of the vocabulary frequencies of all the vocabularies in the text under statistics.
Since the result of multiplying the probability may be a fraction with a large number of fractions, in some implementations the above calculation of the product may be converted into a summation calculation by logarithmizing the individual multipliers, for example:
P(S)＝lnP($)+lnP(w1|$)+lnP(w2|w1)...+lnP(wn|wn-1) (ii) a Wherein the meaning of each parameter in the formula is the same as above, and is not repeated herein.
In this embodiment, the electronic device may select one or more vocabulary combinations from the candidate pushed vocabulary combinations to push the selected vocabulary combinations according to the descending order of the importance coefficients of the candidate pushed vocabulary combinations. When a vocabulary combination is selected for pushing, the electronic equipment can select the candidate pushed vocabulary combination with the maximum importance coefficient for pushing through comparison. When a plurality of vocabulary combinations are selected for pushing, the electronic equipment can select a preset number of candidate pushed vocabulary combinations for pushing after the importance coefficients of the candidate pushed vocabulary combinations are arranged from large to small; and selecting a candidate pushed vocabulary combination with the importance coefficient larger than the preset importance coefficient threshold value according to the preset importance coefficient threshold value for pushing, wherein the candidate pushed vocabulary combination is not limited in the application. For example, in fig. 5, the electronic device may push only the vocabulary on the path 504 with the largest importance coefficient of the candidate pushed vocabulary combination for pushing, or may select the vocabulary on another path after the vocabulary on the path 504 for pushing.
As can be seen from fig. 4, compared to the embodiment corresponding to fig. 2, the process 400 of the vocabulary pushing method in the present embodiment highlights the step of selecting candidate words for each syllable unit based on the determined sentence start. Therefore, the scheme described in the embodiment can provide more accurate calculation for vocabulary selection, so that more accurate vocabulary pushing is realized.
With further reference to fig. 6, as an implementation of the above vocabulary pushing method, the present application provides an embodiment of a vocabulary pushing apparatus, which corresponds to the embodiment of the method shown in fig. 2.
As shown in fig. 6, the vocabulary pushing apparatus 600 of the present embodiment includes: the device comprises a receiving module 601, an obtaining module 602, a detecting module 603, a determining module 604 and a pushing module 605. Wherein, the receiving module 601 may be configured to receive at least one syllable unit input by a user; the obtaining module 602 may be configured to obtain the above vocabulary in response to the input location corresponding to the at least one syllable unit having the above vocabulary; the detecting module 603 may be configured to detect whether a candidate word having an association relationship with the above vocabulary exists in the candidate word corresponding to the first syllable unit of the at least one syllable unit; the determining module 604 may be configured to determine a beginning of the semantic unit corresponding to the at least one syllable unit according to the detection result; the push module 605 may be configured to select candidate words for each syllable unit based on the determined beginning of the sentence for vocabulary pushing.
In some optional implementations of this embodiment, the determining module 604 may be further configured to: determining the word assembly as a sentence head in response to detecting that a candidate word having an association relation with the word assembly exists in the candidate words corresponding to the first syllable unit of the at least one syllable unit; and in response to detecting that no candidate word having an association relation with the word set exists in the candidate words corresponding to the first syllable unit of the at least one syllable unit, determining the starting position of the at least one syllable unit input by the user as the beginning of the sentence. Wherein the incidence relation can be used to express the relevance between such words. In some implementations, the association relationship may include: the transition probability is higher than a preset probability threshold. Alternatively, the transition probability may be calculated by the frequency of occurrence of the next vocabulary after the previous vocabulary/the total frequency of occurrence of the previous vocabulary.
In some optional implementations of this embodiment, the pushing module 605 may include: a combining unit (not shown) configured to sequentially combine the candidate words corresponding to the respective syllable units to generate a candidate pushed vocabulary combination; a determining unit (not shown) configured to determine an importance coefficient of each candidate vocabulary combination based on a conversion probability of an adjacent vocabulary in the candidate pushed vocabulary combination; and a pushing unit (not shown) configured to select a vocabulary combination from the candidate pushed vocabulary combinations in an order from large to small according to the importance coefficient for pushing. The importance coefficient herein may be used to quantify the likelihood that candidate words in a candidate pushed vocabulary combination are combined together. In some implementations, the importance coefficient may be calculated by a product of a probability of a beginning of a period, a probability of a conversion of the beginning of the period with a first word in the candidate pushed word combination, and probabilities of respective conversions of adjacent words in the candidate pushed word combination. In practice, when there is no candidate word associated with the word group in the candidate word corresponding to the first syllable unit, the product of the probability of the beginning of the sentence and the conversion probability of the beginning of the sentence and the first word in the candidate pushed word combination can be calculated by using the first word in the candidate pushed word combination as the frequency of the beginning of the sentence/the total word frequency of the first word in the candidate pushed word combination; when a candidate word having an association relation with the word group in the text exists in the candidate word corresponding to the first syllable unit, the product of the probability of the beginning of the sentence and the conversion probability of the beginning of the sentence and the first word in the candidate pushed word combination can be replaced by the occurrence probability of the first word in the candidate pushed word combination.
It should be noted that the modules described in the vocabulary pushing apparatus 600 correspond to the steps in the method described with reference to fig. 2. Thus, the operations and features described above for the method are also applicable to the apparatus 600 and the modules or units included therein, and are not described herein again.
Those skilled in the art will appreciate that the vocabulary pushing apparatus 600 described above may also include other well-known structures, such as processors, memories, etc., which are not shown in fig. 6 in order to not unnecessarily obscure embodiments of the present disclosure.
Referring now to FIG. 7, shown is a block diagram of a computer system 700 suitable for use in implementing the terminal device/server of an embodiment of the present application. The terminal device/server shown in fig. 7 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.
As shown in fig. 7, the computer system 700 includes a Central Processing Unit (CPU)701, which can perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)702 or a program loaded from a storage section 708 into a Random Access Memory (RAM) 703. In the RAM703, various programs and data necessary for the operation of the system 700 are also stored. The CPU701, the ROM 702, and the RAM703 are connected to each other via a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.
The following components are connected to the I/O interface 705: an input portion 706 including a keyboard or a touch panel; an output section 707 including a display device such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), or the like; a storage section 708 including a hard disk and the like; and a communication section 709 including a network interface card such as a LAN card, a modem, or the like. The communication section 709 performs communication processing via a network such as the internet. A drive 710 is also connected to the I/O interface 705 as needed. A removable medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 710 as necessary, so that a computer program read out therefrom is mounted into the storage section 708 as necessary.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication section 709, and/or installed from the removable medium 711. The computer program, when executed by a Central Processing Unit (CPU)701, performs the above-described functions defined in the method of the present application. It should be noted that the non-volatile computer readable medium described herein may be a non-volatile computer readable signal medium or a non-volatile computer readable storage medium or any combination of the two. A non-transitory computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the non-volatile computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a non-transitory computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present application may be implemented by software or hardware. The described modules may also be provided in a processor, which may be described as: a processor comprises a receiving module, an obtaining module, a detecting module, a determining module and a pushing module. Where the names of these modules do not in some cases constitute a limitation of the unit itself, for example, the receiving module may also be described as a "module configured to receive at least one syllable unit entered by a user".
As another aspect, the present application also provides a computer-readable medium, which may be contained in the apparatus described in the above embodiments; or may be present separately and not assembled into the device. The computer readable medium carries one or more programs which, when executed by the apparatus, cause the apparatus to: receiving at least one syllable unit input by a user; responding to the input position corresponding to the at least one syllable unit to have the above words, and acquiring the above words; detecting whether a candidate word having an association relation with the above word vocabulary exists in the candidate words corresponding to the first syllable unit of the at least one syllable unit; determining the sentence head of the semantic unit corresponding to the at least one syllable unit according to the detection result; and selecting candidate words for each syllable unit based on the determined sentence start for vocabulary pushing.
The above description is only a preferred embodiment of the application and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention herein disclosed is not limited to the particular combination of features described above, but also encompasses other arrangements formed by any combination of the above features or their equivalents without departing from the spirit of the invention. For example, the above features may be replaced with (but not limited to) features having similar functions disclosed in the present application.
Claims (12)
1. A method of vocabulary pushing, the method comprising:
receiving at least one syllable unit input by a user;
responding to the input position corresponding to the at least one syllable unit to have the above words, and acquiring the above words;
detecting whether a candidate word having an association relation with the above word vocabulary exists in the candidate words corresponding to the first syllable unit of the at least one syllable unit;
determining a sentence start of the semantic unit corresponding to the at least one syllable unit according to the detection result, wherein the sentence start comprises a start word or a start position of the semantic unit;
sequentially combining the candidate words corresponding to the syllable units to generate a candidate pushed vocabulary combination;
determining an importance coefficient of each candidate vocabulary combination based on the conversion probability of the adjacent vocabulary in the candidate pushed vocabulary combination, wherein the importance coefficient comprises the product of the sentence head probability, the conversion probability of the sentence head and the first vocabulary in the candidate pushed vocabulary combination, and the conversion probability of the adjacent vocabulary in the candidate pushed vocabulary combination;
and selecting a vocabulary combination from the candidate pushed vocabulary combinations according to the sequence of the importance coefficients from large to small for pushing.
2. The method according to claim 1, wherein said determining the beginning of the semantic unit corresponding to the at least one syllable unit according to the detection result comprises:
determining the word assembly as a sentence start in response to detecting that a candidate word having an association relation with the word assembly exists in the candidate words corresponding to the first syllable unit of the at least one syllable unit;
and in response to detecting that no candidate word having an association relation with the word set in the text does not exist in the candidate word corresponding to the first syllable unit of the at least one syllable unit, determining the starting position of the at least one syllable unit input by the user as the beginning of the sentence.
3. The method of claim 1, wherein:
when no candidate word with the incidence relation with the word group of the character is existed in the candidate word corresponding to the first syllable unit, the product of the probability of the beginning of the sentence and the conversion probability of the beginning of the sentence and the first word in the candidate pushed word combination is calculated by using the frequency of the first word in the candidate pushed word combination as the beginning of the sentence/the total word frequency of the first word in the candidate pushed word combination;
and when the candidate words corresponding to the first syllable unit have the candidate words having the association relation with the words in the text, replacing the product of the probability of the beginning of the sentence and the conversion probability of the beginning of the sentence and the first word in the candidate pushed word combination with the occurrence probability of the first word in the candidate pushed word combination.
4. The method of claim 1, wherein the association comprises: the transition probability is higher than a preset probability threshold.
5. The method of any one of claims 1-4, wherein the transition probabilities include: frequency of the last/total frequency of the last vocabulary.
6. An apparatus for vocabulary pushing, the apparatus comprising:
a receiving module configured to receive at least one syllable unit input by a user;
the obtaining module is configured to respond to the situation that the input position corresponding to the at least one syllable unit has the above vocabulary, and obtain the above vocabulary;
the detection module is configured to detect whether a candidate word having an association relation with the above vocabulary exists in the candidate word corresponding to the first syllable unit of the at least one syllable unit;
the determining module is configured to determine a sentence start of the semantic unit corresponding to the at least one syllable unit according to the detection result, wherein the sentence start comprises a start word or a start position of the semantic unit;
the pushing module is configured to sequentially combine the candidate words corresponding to the syllable units to generate a candidate pushed vocabulary combination; determining an importance coefficient of each candidate vocabulary combination based on the conversion probability of the adjacent vocabulary in the candidate pushed vocabulary combination, wherein the importance coefficient comprises the product of the sentence head probability, the conversion probability of the sentence head and the first vocabulary in the candidate pushed vocabulary combination, and the conversion probability of the adjacent vocabulary in the candidate pushed vocabulary combination; and selecting a vocabulary combination from the candidate pushed vocabulary combinations according to the sequence of the importance coefficients from large to small for pushing.
7. The apparatus of claim 6, wherein the determining module is further configured to:
determining the word assembly as a sentence start in response to detecting that a candidate word having an association relation with the word assembly exists in the candidate words corresponding to the first syllable unit of the at least one syllable unit;
and in response to detecting that no candidate word having an association relation with the word set in the text does not exist in the candidate word corresponding to the first syllable unit of the at least one syllable unit, determining the starting position of the at least one syllable unit input by the user as the beginning of the sentence.
8. The apparatus of claim 6, wherein:
when no candidate word with the incidence relation with the word group of the character is existed in the candidate word corresponding to the first syllable unit, the product of the probability of the beginning of the sentence and the conversion probability of the beginning of the sentence and the first word in the candidate pushed word combination is calculated by using the frequency of the first word in the candidate pushed word combination as the beginning of the sentence/the total word frequency of the first word in the candidate pushed word combination;
and when the candidate words corresponding to the first syllable unit have the candidate words having the association relation with the words in the text, replacing the product of the probability of the beginning of the sentence and the conversion probability of the beginning of the sentence and the first word in the candidate pushed word combination with the occurrence probability of the first word in the candidate pushed word combination.
9. The apparatus of claim 6, wherein the association comprises: the transition probability is higher than a preset probability threshold.
10. The apparatus of any of claims 6-9, wherein the transition probabilities comprise: frequency of the last/total frequency of the last vocabulary.
11. A computing device, comprising:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-5.
12. A non-transitory computer-readable storage medium, on which a computer program is stored, the program, when executed by a processor, implementing the method according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710102235.5A CN106896936B (en) | 2017-02-24 | 2017-02-24 | Vocabulary pushing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710102235.5A CN106896936B (en) | 2017-02-24 | 2017-02-24 | Vocabulary pushing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106896936A CN106896936A (en) | 2017-06-27 |
| CN106896936B true CN106896936B (en) | 2020-06-12 |
Family
ID=59184080
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710102235.5A Active CN106896936B (en) | 2017-02-24 | 2017-02-24 | Vocabulary pushing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106896936B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109426357B (en) * | 2017-09-01 | 2023-05-12 | 百度在线网络技术（北京）有限公司 | Information input method and device |
| CN109669549B (en) * | 2017-10-16 | 2023-04-28 | 北京搜狗科技发展有限公司 | Candidate content generation method and device for candidate content generation |
| CN111198620B (en) * | 2018-11-20 | 2024-07-19 | 北京搜狗科技发展有限公司 | Method, device and equipment for presenting input candidate items |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101122901A (en) * | 2007-09-25 | 2008-02-13 | 腾讯科技（深圳）有限公司 | Chinese integral sentence generation method and device |
| CN101256448A (en) * | 2008-03-24 | 2008-09-03 | 腾讯科技（深圳）有限公司 | Method, apparatus and client terminal for implementing input method |
| CN103365573A (en) * | 2012-03-27 | 2013-10-23 | 北京搜狗科技发展有限公司 | Method and device for identifying multi-key input characters |
-
2017
- 2017-02-24 CN CN201710102235.5A patent/CN106896936B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101122901A (en) * | 2007-09-25 | 2008-02-13 | 腾讯科技（深圳）有限公司 | Chinese integral sentence generation method and device |
| CN101256448A (en) * | 2008-03-24 | 2008-09-03 | 腾讯科技（深圳）有限公司 | Method, apparatus and client terminal for implementing input method |
| CN103365573A (en) * | 2012-03-27 | 2013-10-23 | 北京搜狗科技发展有限公司 | Method and device for identifying multi-key input characters |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106896936A (en) | 2017-06-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11164573B2 (en) | Method and apparatus for controlling page | |
| US11217236B2 (en) | Method and apparatus for extracting information | |
| CN111428010B (en) | Man-machine intelligent question-answering method and device | |
| US20190377956A1 (en) | Method and apparatus for processing video | |
| US9697819B2 (en) | Method for building a speech feature library, and method, apparatus, device, and computer readable storage media for speech synthesis | |
| CN107241260B (en) | News pushing method and device based on artificial intelligence | |
| CN110069698B (en) | Information pushing method and device | |
| CN106774975B (en) | Input method and device | |
| US11758088B2 (en) | Method and apparatus for aligning paragraph and video | |
| CN107437417B (en) | Voice data enhancement method and device based on recurrent neural network voice recognition | |
| US11651015B2 (en) | Method and apparatus for presenting information | |
| CN113657113B (en) | Text processing method and device and electronic equipment | |
| CN109858045B (en) | Machine translation method and device | |
| CN112559800A (en) | Method, apparatus, electronic device, medium, and product for processing video | |
| CN114861889B (en) | Deep learning model training method, target object detection method and device | |
| CN109582825B (en) | Method and apparatus for generating information | |
| CN110232920B (en) | Voice processing method and device | |
| CN111738791B (en) | Text processing method, device, equipment and storage medium | |
| CN106896936B (en) | Vocabulary pushing method and device | |
| CN112988753B (en) | Data searching method and device | |
| CN110738056B (en) | Method and device for generating information | |
| CN109190123B (en) | Method and apparatus for outputting information | |
| CN113761923A (en) | Named entity recognition method and device, electronic equipment and storage medium | |
| CN110245334B (en) | Method and device for outputting information | |
| CN106873798B (en) | Method and apparatus for outputting information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |