WO2014040510A1 - 在输入法中实现智能联想的方法、装置及终端设备 - Google Patents

在输入法中实现智能联想的方法、装置及终端设备 Download PDF

Info

Publication number
WO2014040510A1
WO2014040510A1 PCT/CN2013/082911 CN2013082911W WO2014040510A1 WO 2014040510 A1 WO2014040510 A1 WO 2014040510A1 CN 2013082911 W CN2013082911 W CN 2013082911W WO 2014040510 A1 WO2014040510 A1 WO 2014040510A1
Authority
WO
WIPO (PCT)
Prior art keywords
weight value
words
input
keyboard code
candidate character
Prior art date
Application number
PCT/CN2013/082911
Other languages
English (en)
French (fr)
Inventor
林森
Original Assignee
腾讯科技(深圳)有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 腾讯科技(深圳)有限公司 filed Critical 腾讯科技(深圳)有限公司
Priority to US14/427,346 priority Critical patent/US10049091B2/en
Publication of WO2014040510A1 publication Critical patent/WO2014040510A1/zh

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00Handling natural language data
    • G06F40/10Text processing
    • G06F40/166Editing, e.g. inserting or deleting
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/332Query formulation
    • G06F16/3322Query formulation using system suggestions
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/3331Query processing
    • G06F16/3332Query translation
    • G06F16/3334Selection or weighting of terms from queries, including natural language queries
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00Input 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
    • G06F3/01Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/02Input arrangements using manually operated switches, e.g. using keyboards or dials
    • G06F3/023Arrangements 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
    • G06F3/0233Character input methods
    • G06F3/0237Character input methods using prediction or retrieval techniques
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00Input 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
    • G06F3/01Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/048Interaction techniques based on graphical user interfaces [GUI]
    • G06F3/0484Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
    • G06F3/04842Selection of displayed objects or displayed text elements
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00Handling natural language data
    • G06F40/10Text processing
    • G06F40/12Use of codes for handling textual entities
    • G06F40/126Character encoding
    • G06F40/129Handling non-Latin characters, e.g. kana-to-kanji conversion
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00Handling natural language data
    • G06F40/20Natural language analysis
    • G06F40/274Converting codes to words; Guess-ahead of partial word inputs

Definitions

  • the subject matter disclosed herein relates to the field of computer technology, and in particular, to a method, an apparatus, and a terminal device for implementing intelligent association in an input method.
  • the intelligent association method used in the input methods of various types of mobile phones, computers and other terminal devices can make a form of association with the content currently being input.
  • the inventor found that there is a certain limitation on the association of the content currently being input into the form of phonetic semantics, and the content of the words or words guessed by the association may be different from the real content requirement of the user. Lenovo's hit rate is not high, reducing the character input speed. Summary of the invention
  • the embodiment of the invention provides a method, a device and a terminal device for implementing intelligent association in an input method, which can improve the association hit rate and ensure the user character input speed.
  • a method for implementing intelligent association in an input method is provided, which can improve the association hit rate.
  • the method for implementing intelligent association in the input method includes the following steps:
  • the weight value of the corresponding candidate character is updated according to the calculated weight value of each combined keyword, and each candidate character is displayed according to the updated weight value for the user to select and confirm.
  • - wherein, in the word or word that has been selected last time, the word or word selected by the keyboard code is associated with each candidate character as a combined keyword to search in the preset vocabulary, and each one is calculated according to the search result.
  • the steps further include:
  • the weight value of the combined keyword of the search but miss data is assigned to the preset base value.
  • the calculating the weight value of each candidate character is to calculate the weight value of each candidate character according to the use frequency of each candidate character;
  • the calculating the weight value of each combined keyword is based on the frequency of use of the combined keyword of the search and hit data, and calculates the weight value of the combined keyword of each search and hit data.
  • the weight value of the corresponding candidate character is updated according to the calculated weight value of each combined keyword, and each candidate character is displayed according to the updated weight value, and the step further comprises: calculating each combined key according to the calculated key
  • the weight value of the word is updated to the weight value of the corresponding candidate character; the candidate characters after updating the weight value are sorted according to the order of the weight values; the sorted candidate characters are displayed.
  • the method further includes the steps of: outputting a selection result of the displayed candidate characters by the user, and storing the selection result in the context database for associating words and/or words associated with the next input keyboard code .
  • the method further comprises the steps of:
  • the detection result is that the currently input keyboard code is a character keyboard code, performing the search into the preset vocabulary to search for words and/or words associated with the keyboard code as candidate characters, and calculating a weight value of each candidate character. ;
  • the words or words selected in the context database according to the last input keyboard code are deleted.
  • the step of receiving the currently input keyboard code further includes the following steps: After the user inputs a certain keyboard code and selects a corresponding word or word, the word or word input by the user is temporarily stored in the context database.
  • the method further comprises the steps of: scanning the "cursor" - - The word or word that the previous user has entered.
  • an apparatus for implementing intelligent association in an input method comprising:
  • the receiving module receives the currently input keyboard code.
  • the calculation module searches the preset vocabulary for the words and/or words associated with the keyboard code as candidate characters, and calculates the weight value of each candidate character.
  • a search module which associates the selected word or word of the last input keyboard code with each candidate character as a combined keyword into the preset vocabulary for searching, and calculates each combined keyword according to the search result. Weights.
  • the update module updates the weight value of each candidate character based on the calculated weight value of each combined keyword.
  • the display module displays each candidate character according to the updated weight value for the user to select and confirm.
  • the search module includes:
  • the search unit searches for the selected word or word of the keyboard code that was last input, and associates each of the candidate characters as a combined keyword into the preset vocabulary for searching.
  • the determining unit calculates the weight value of the combined keyword of the search and hit data, and assigns the weight value of the combined keyword of the search but missed data to zero.
  • the calculation module calculates a weight value of each candidate character according to a frequency of use of each candidate character
  • the determining unit calculates the weight value of the combined keyword for each search and hit data based on the frequency of use of the combined keyword of each search and hit data.
  • the display module specifically displays candidate characters sorted by the sorting module.
  • the method further includes: an output module, outputting a selection result of the displayed candidate characters by the user, and storing the selection result in a context database for associating words and/or words associated with the next input keyboard code .
  • the detecting module detects the type of the currently input keyboard code received by the receiving module. - - The notification module notifies the calculation module to perform a search and a calculation operation when the detection result is that the currently input keyboard code is a character keyboard code.
  • the deleting module deletes the word or word selected according to the last input keyboard code saved in the context database when the detection result is that the received keyboard code is an input breaking control operation.
  • an embodiment of the present invention further provides a terminal device with an input method, including the foregoing device for implementing intelligent association in an input method.
  • the receiving module receives a keyboard code input by a hardware keyboard.
  • the receiving module receives the keyboard code input by the touch screen keyboard.
  • the preset the thesaurus has been set when the input method is created, and automatically learns according to the input condition of the user and updates the thesaurus during the use of the user after installation.
  • the terminal device scans a word or a word that the user has input before the "cursor".
  • the embodiment of the present invention can perform the search for the corresponding candidate characters and the update and determination of the weight values of each candidate character according to the character or word input by the user last time as a reference, and according to the updated final weight value.
  • the user displays each candidate character, which can effectively improve the hit rate of the character association of the keyboard code and improve the character input speed of the user.
  • FIG. 1 is a schematic flow chart of a first embodiment of a method for implementing intelligent association in an input method of the present invention
  • FIG. 2 is a schematic flow chart of a second embodiment of a method for implementing intelligent association in an input method of the present invention
  • FIG. 3 is a schematic flow chart of a method for calculating a weight value of each combined keyword according to an embodiment of the present invention
  • FIG. 4 is a schematic flow chart of a candidate character display method according to an embodiment of the present invention
  • FIG. 5 is a schematic structural diagram of a first embodiment of an apparatus for implementing intelligent association in an input method according to the present invention
  • Figure 6 is a schematic structural view of a second embodiment of an apparatus for implementing intelligent association in an input method of the present invention
  • FIG. 7 is a block diagram showing the structure of the search module of Figure 6. detailed description
  • FIG. 1 is a schematic flowchart of a first embodiment of a method for implementing intelligent association in an input method according to the present invention.
  • the embodiment of the present invention can be applied to a device capable of implementing an input method, such as a mobile phone or a computer, and the embodiment of the present invention is based on The word or word that was input last time associates the word or word corresponding to the currently input keyboard code to complete the association of the word or word corresponding to the keyboard code.
  • the method in the embodiment of the present invention starts from step S101:
  • step S101 receiving a currently input keyboard code
  • the corresponding keyboard code can be input through the hardware keyboard of the device such as a mobile phone or a touch screen keyboard, and the device such as the mobile phone receives the corresponding keyboard code in S101.
  • step S102 searching for a word and/or a word associated with the keyboard code as a candidate character in a preset vocabulary, and calculating a weight value of each candidate character;
  • the thesaurus is already set when the input method is created, and in the process of using the user after installation, the user can automatically learn according to the input condition of the user, and update the thesaurus, that is, the thesaurus includes basic Words or words, including common words or words that are based on user habits. After the words and/or words as candidate characters are found, the candidate characters can be calculated by the weighting algorithm, and the corresponding weight values can be calculated according to the frequency of use of the words or words recorded in the machine.
  • step S103 the selected word or word of the last input keyboard code is associated with each candidate character as a combined keyword to search in the preset vocabulary, and each combined keyword is calculated according to the search result. Weight value.
  • each candidate character and the last input word or word combination are searched as a keyword into the lexicon, and the basic word and/or word, or common words and/or words are determined whether the group exists.
  • - - Combine keywords, and when the query is obtained, calculate the weight value of the corresponding combined keyword.
  • the weight value of the combined keyword may be assigned a basic value such as an assignment of zero.
  • step S104 the weight value of the corresponding candidate character is updated according to the calculated weight value of each combined keyword, and each candidate character is displayed according to the updated weight value for the user to select and confirm.
  • the weight value of the weighted value of each candidate character that has been calculated may be added, and the weight value of the combined keyword corresponding to the candidate character is obtained, and the final weight value of the candidate character is obtained, and the final weight value may be used according to the final weight value.
  • Each candidate character is sorted and displayed for the user to select and confirm.
  • the embodiment of the present invention can perform the search for the corresponding candidate characters and the update and determination of the weight values of each candidate character according to the character or word input by the user last time as a reference, and according to the updated final weight value.
  • the user displays each candidate character, which can effectively improve the hit rate of the character association of the keyboard code and improve the character input speed of the user.
  • FIG. 2 is a schematic flowchart of a second embodiment of a method for implementing intelligent association in an input method according to the present invention.
  • the embodiment of the present invention can be applied to a device capable of implementing an input method, such as a mobile phone or a computer.
  • the words or words corresponding to the currently input keyboard code are associated to complete the association of the words or words corresponding to the keyboard code.
  • the method of the embodiment of the present invention includes:
  • step S201 detecting the type of the currently input keyboard code received
  • the detection result is that the currently input keyboard code is a character keyboard code
  • the following S202 is performed. If the detection result is that the received keyboard code is an input interrupt control operation, deleting the word or word selected in the context database according to the last input keyboard code to avoid input to the new position word or word The result is interference.
  • the word or word input by the user may be temporarily stored in a context database, so as to facilitate the word corresponding to the keyboard code of the input immediately thereafter. Or words for intelligent association.
  • the interrupt control operation may include: the user deletes the last input word or word by using the "backspace key", or the user uses the "direction key” to move the "cursor" to another word or word in the document. At this time, there is no need to perform intelligent association based on the last input word or word, and it is necessary to delete the word or word selected in the context database according to the last input keyboard code to avoid input to the new position word or word. Interference. - Of course, in other embodiments, the words or words that the user has entered before the "cursor" can also be intelligently scanned to facilitate intelligent association of words or words corresponding to the keyboard code of the input that follows.
  • step S202 a word and/or a word associated with the keyboard code is searched for as a candidate character in a preset vocabulary, and a weight value of each candidate character is calculated.
  • the preset vocabulary includes: a basic vocabulary for storing basic words and/or words, and a common vocabulary for storing words and/or words that have been used at the local end.
  • the weight value of each candidate character is calculated, and the weight value of each candidate character is calculated according to the frequency of use of each candidate character.
  • step S203 the selected word or word of the last input keyboard code is associated with each candidate character as a combined keyword to search in the preset vocabulary, and each combined keyword is calculated according to the search result.
  • Weight value
  • the calculating the weight value of each combined keyword is calculated according to the frequency of use of the combined keyword of each search and hit data, and the weight value of the combined keyword of each search and hit data is calculated, and the search but misses the data.
  • the weight value of the combined keyword is assigned to the base value, such as the assignment
  • step S204 the weight value of the corresponding candidate character is updated according to the calculated weight value of each combined keyword, and each candidate character is displayed according to the updated weight value for the user to select and confirm.
  • the weight value of the weight value of each candidate character that has been calculated may be added, and the weight value of the combined keyword corresponding to each candidate character is added, and the final weight value of each candidate character is obtained, and the final weight may be used.
  • the value is sorted and displayed for each candidate character for the user to select and confirm.
  • step S205 the user's selection result of the displayed candidate characters is output, and the selection result is stored in the context database for associating words and/or words associated with the next input keyboard code. After the user selects to confirm a candidate character, the candidate character selected by the user is output to the corresponding position of the corresponding document.
  • FIG. 3 is a schematic flowchart of a method for calculating a weight value of each combined keyword according to an embodiment of the present invention.
  • the method for calculating a weight value of each combined keyword in this embodiment corresponds to the foregoing input method.
  • the method of implementing the intelligent association is S103 in the first embodiment, or S203 in the second embodiment of the method corresponding to the above-described method of implementing intelligent association in the input method.
  • the method for calculating the weight value of each combined keyword in this embodiment includes:
  • step S301 the selected word or word of the keyboard code input last time is associated with each candidate character as a combined keyword to search in the preset vocabulary.
  • step S302 for the combined keyword of the search and hit data, the weight value of the combined keyword of each search and hit data is calculated.
  • step S303 for the combined keyword of the search but miss data, the weight value of the combined keyword of the search but miss data is assigned to the preset basic value.
  • the data is hit, and then the frequency of use of the combined keyword may be determined according to the searched data to calculate the weight value of the corresponding combined keyword.
  • its weight value can be directly assigned to a preset base value such as zero.
  • FIG. 4 is a schematic flowchart of a candidate character display method according to an embodiment of the present invention
  • candidate characters are sorted according to the weight value of the candidate character after updating, and
  • the method of displaying the sorting result to the user may be corresponding to S104 in the foregoing embodiment.
  • the method in this embodiment includes:
  • step S401 the weight value of the corresponding candidate character is updated according to the calculated weight value of each combined keyword.
  • the weight value of each updated candidate character can be obtained by adding the weight value of the combined keyword to the weight value of the current candidate character.
  • step S402 candidate characters after updating the weight value are sorted in descending order of weight values.
  • the ordering may be in the order of large to small, left to right, or top to bottom.
  • step S403 the sorted candidate characters are displayed.
  • the user inputs the "zaixian" keyboard code using the Pinyin input method. After receiving the key code, the mobile phone and other devices determine that the keyboard code is the character keyboard code.
  • the embodiment of the present invention can perform the search for the corresponding candidate characters and the update and determination of the weight values of each candidate character according to the character or word input by the user last time as a reference, and according to the updated final weight value.
  • the user displays each candidate character, which can effectively improve the hit rate of the character association of the keyboard code and improve the character input speed of the user.
  • the candidate characters are displayed to the user, they are displayed in descending order according to the updated weight values, which is convenient for the user to view and select.
  • the last input word or word of the last temporary storage is automatically deleted to stop the subsequent intelligent association operation, thereby avoiding interference with the input result of the new position word or word, further realizing the intelligence. Automation.
  • FIG. 5 there is shown a block diagram of a first embodiment of an apparatus for implementing intelligent association in an input method of the present invention.
  • the device of the embodiment of the present invention can be applied to a device capable of implementing an input method, such as a mobile phone or a computer.
  • the embodiment of the present invention associates a word or a word corresponding to the currently input keyboard code according to a word or a word input last time. To complete the association of words or words corresponding to the keyboard code.
  • the apparatus of the embodiment of the present invention includes:
  • the receiving module 11 receives the currently input keyboard code.
  • the corresponding key can be input through a hardware keyboard or a touch screen keyboard.
  • the receiving module 11 receives the corresponding keyboard code, for example, the receiving module 11 receives the keyboard code of the "shipin" input by the user.
  • the calculating module 12 searches for a word and/or a word associated with the keyboard code as a candidate character in a preset vocabulary, and calculates a weight value of each candidate character.
  • the thesaurus is already set when the input method is created, and in the process of using the user after installation, the user can automatically learn according to the input condition of the user, and update the thesaurus, that is, the thesaurus includes basic Words or words, including common words or words that are based on user habits. After the words and/or words as candidate characters are found, the candidate characters can be calculated by the weighting algorithm, and the corresponding weight values can be calculated according to the frequency of use of the words or words recorded in the machine.
  • a candidate character of [50]" wherein the value in the square brackets is a weight value of the corresponding candidate character calculated by the calculation module 12 according to the frequency of use.
  • the search module 13 searches for the selected word or word of the last input keyboard code, and associates each candidate character into the preset vocabulary as a combined keyword, and calculates each combined keyword according to the search result. Weight value.
  • the search module 13 searches each candidate character and the last input word or word combination as a keyword into the vocabulary to determine whether the basic word and/or word, or common words and/or words exist in the combination.
  • the keyword and when the query gets the hit data, calculate the weight value of the corresponding combined keyword.
  • the weight value of the combined keyword may be assigned a basic value, such as an assignment of zero.
  • the search module 13 uses “online food”, “online video”, “online jewelry”, “online poetic”, and “online is” as the key combination. Searching for related words in the word to the lexicon, in the current search, the search module 13 only searches for words about "online video” and their frequency of use, and derives the weight value of each combined keyword according to the search result" 1, online food [0]; 2, online video [50]; 3, online jewelry [0]; 4, online poetry [0]; 5, online is [0]", which, “online food” “online Jewelry “Online poetic” "Online” Since there is no database search for it has been used, there is no hit data, so the value of "Online Food” “Online Jewelry” “Online Poetry” “Online Yes” is 0.
  • the update module 14 updates each of the calculated weight values of each combined keyword according to the calculation. - - The weight value of the selected character.
  • the updating module 14 may add the weight value of the combined keyword corresponding to the candidate character to the weight value of each candidate character that has been calculated, and obtain the final weight value of the candidate character, and may follow the weight value of the candidate character. The final weight value, sorting and displaying each candidate character for the user to select and confirm.
  • the weight value of each candidate character is updated, and the weight value of the combined keyword is added to the weight value of the candidate character corresponding to the combined keyword, and “1” can be obtained.
  • food [90]; 2, video [130]; 3, jewelry [70]; 4, poetry [60]; 5, is [50],,.
  • the display module 15 displays each candidate character according to the updated weight value for the user to select and confirm.
  • the display module 15 sorts each candidate character according to the magnitude of the weight value, and displays the sorted candidate characters to the user, so that the user can select more quickly and complete the character input.
  • the calculation module 12 calculates a weight value of each candidate character according to the frequency of use of each candidate character.
  • the embodiment of the present invention can perform the search for the corresponding candidate characters and the update and determination of the weight values of each candidate character according to the character or word input by the user last time as a reference, and according to the updated final weight value.
  • the user displays each candidate character, which can effectively improve the hit rate of the character association of the keyboard code and improve the character input speed of the user.
  • FIG. 6 is a schematic structural diagram of a second embodiment of an apparatus for implementing intelligent association in an input method according to the present invention.
  • the device of the embodiment of the present invention can be applied to a device capable of implementing an input method, such as a mobile phone or a computer.
  • the embodiment of the present invention associates a word or a word corresponding to the currently input keyboard code according to a word or a word input last time.
  • the device of the embodiment of the present invention includes the receiving module 11 , the calculating module 12 , the searching module 13 , the updating module 14 , and the display module 15 in the first embodiment of the foregoing apparatus, in order to complete the association of the words or words corresponding to the keyboard code.
  • the device in the embodiment of the present invention further includes:
  • the output module 16 outputs a selection result of the user to the displayed candidate characters, and stores the selection result in the context database for the word and/or associated with the next input keyboard code. - - Words are associated.
  • the candidate character selected by the user is output to the corresponding position of the corresponding document.
  • the apparatus for implementing intelligent association in the input method further includes: a detection module 17, a notification module 18, and a deletion module 19.
  • the device determines the keyboard code input by the user through the three modules to determine whether to notify the receiving module 11, the calculating module 12, the searching module 13, the updating module 14, and the display module 15 to perform corresponding intelligent association operations. specific:
  • the detecting module 17 detects the type of the currently input keyboard code received by the receiving module 11.
  • the deleting module 19 deletes the word or word selected according to the last input keyboard code saved in the context database when the detection result is that the received keyboard code is an input breaking control operation.
  • the word or word input by the user may be temporarily stored in a context database, so as to facilitate the word corresponding to the keyboard code of the input immediately thereafter.
  • a context database so as to facilitate the word corresponding to the keyboard code of the input immediately thereafter.
  • words for intelligent association can also be intelligently scanned to facilitate intelligent association of words or words corresponding to the keyboard code of the input that follows.
  • the interrupt control operation detected by the detecting module 17 may include: the user deletes the last input word or word by using the "backspace key", or the user uses the "direction key” to move the "cursor" to another in the document. After the word or word, at this time, there is no need to perform intelligent association based on the last input word or word. It is necessary to delete the word or word saved in the context database according to the last input keyboard code to avoid the word located in the new position. Or the input of the word produces interference.
  • the device for implementing intelligent association in the input method further includes:
  • the sorting module 20 sorts the candidate characters after updating the weight value by the update module according to the order of the weight values; the sorting module 20 may be from the left to the size of the updated candidate character weight value.
  • Candidate characters are sorted in right or top to bottom order.
  • the display module 15 specifically displays candidate characters sorted by the sorting module. - - Further, please refer to FIG. 7 , which is a schematic structural diagram of the search module in FIG. 6 , and the search module 13 specifically includes:
  • the searching unit 131 searches the selected word or word of the last input keyboard code as each of the candidate characters as a combined keyword into the preset thesaurus for searching.
  • the determining unit 132 calculates a weight value of the combined keyword of the search and hit data, and assigns a weight value of the combined keyword of the search but miss data to zero.
  • the weight value of the corresponding combined keyword may be calculated according to the frequency of use of the combined keyword corresponding to the searched data.
  • its weight value can be directly assigned to a preset base value such as zero.
  • the embodiment of the present invention can perform the search for the corresponding candidate characters and the update and determination of the weight values of each candidate character according to the character or word input by the user last time as a reference, and according to the updated final weight value.
  • the user displays each candidate character, which can effectively improve the hit rate of the character association of the keyboard code and improve the character input speed of the user.
  • the candidate characters are displayed to the user, they are displayed in descending order according to the updated weight values, which is convenient for the user to view and select.
  • the last input word or word of the last temporary storage is automatically deleted to stop the subsequent intelligent association operation, thereby avoiding interference with the input result of the new position word or word, further realizing the intelligence. Automation.
  • the method of implementing intelligent association in the input method according to Fig. 1 may be a method performed by each unit in the apparatus for realizing intelligent association in the input method shown in Fig. 5.
  • the steps S101-S105 shown in Fig. 1 can be performed by the receiving module 11, the calculating module 12, the searching module 13, and the updating module 14 shown in Fig. 5.
  • each unit in the apparatus for implementing intelligent association in the input method shown in FIG. 5 may be separately or entirely combined into one or several additional units, or some of them (some The unit can also be split into multiple functionally smaller units.
  • the computing module 12 can be combined with the search module 13 to form a single computing module
  • the updating module 14 can be combined with the display module 15 to form a single update module or the like, which can achieve the same operation without affecting the present invention. Implementation of the technical effects of the embodiments.
  • intelligent association in the input method is implemented according to FIG.
  • the - method may be a method performed by each unit in the apparatus for implementing intelligent association in the input method shown in Figs.
  • steps S201, S205, S301, S402, and S403 shown in FIG. 2 can be executed by the detection module 17, the output module 16, the search unit 131, the sorting module 20, and the display module 15 shown in FIGS.
  • each unit in the apparatus for implementing intelligent association in the input method shown in FIGS. 6 and 7 may be separately or entirely combined into one or several additional units, or one of them.
  • the (some) units can also be split into multiple functionally smaller units.
  • the detecting module 17 can be combined with the notification module 18 and the deleting module 19 to form a single judging module.
  • the searching unit 131 can be combined with the determining unit 132 to form a single evaluation module or the like, which can achieve the same operation. The implementation of the technical effects of the embodiments of the present invention is not affected.
  • the program may be stored in a computer readable storage medium, and the storage medium may include: a flash disk, a read only memory (Read-Only Memory, ROM) ), Random Access Memory (RAM), disk or CD.
  • a computer readable storage medium may include: a flash disk, a read only memory (Read-Only Memory, ROM) ), Random Access Memory (RAM), disk or CD.
  • the method for implementing intelligent association in the input method and the device for implementing intelligent association in the input method can effectively improve the hit rate of character association for the keyboard code and improve the user.
  • the character input speed has a strong practical value.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Artificial Intelligence (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Human Computer Interaction (AREA)
  • Mathematical Physics (AREA)
  • Input From Keyboards Or The Like (AREA)
  • Document Processing Apparatus (AREA)

Abstract

本发明实施例提供了一种在输入法中实现智能联想的方法、装置及终端设备,其中,所述方法包括:接收当前输入的键盘码;到预置的词库中搜索所述键盘码关联的字和/或词语作为候选字符,并计算每一个候选字符的权重值;将上一次输入的键盘码已选择的字或词语,与每一个候选字符关联作为组合关键字到所述预置的词库中进行搜索,并根据搜索结果计算每一个组合关键字的权重值;根据计算得到的每一个组合关键字的权重值更新对应候选字符的权重值,按照更新后的权重值显示每一个候选字符,以供用户选择确认。采用本发明,可有效地提高对键盘码进行字符联想的命中率,提高用户的字符输入速度。

Description

一 一
在输入法中实现智能联想的方法、 装置及终端设备 本专利申请要求 2012 年 9 月 12 日提交的中国专利申请号为 201210337043.X, 发明名称为 "一种在输入法中实现智能联想的方法、 装置及 终端设备" 的优先权, 该申请的全文以引用的方式并入本申请中。 技术领域
这里公开的主题内容涉及计算机技术领域,尤其涉及一种在输入法中实现 智能联想的方法、 装置及终端设备。 背景技术
当前各类手机、 电脑等终端设备的输入法中所采用的智能联想方式, 可以 对当前正在输入的内容做语音语意等形式的联想。发明人在实施现有技术时发 现,对当前正在输入的内容做语音语意等形式的联想存在一定的局限性,联想 猜测出来的字或词语等内容与用户真实的内容需求可能有一定的差别,联想命 中率不高, 降低了的字符输入速度。 发明内容
本发明实施例提供了一种在输入法中实现智能联想的方法、装置及终端设 备, 可提高联想命中率, 保证用户字符输入速度。
有鉴于此,根据本发明的一个方面,提供了一种在输入法中实现智能联想 的方法, 该方法能够提高联想命中率。
该在输入法中实现智能联想的方法包括以下步骤:
接收当前输入的键盘码;
到预置的词库中搜索所述键盘码关联的字和 /或词语作为候选字符, 并计 算每一个候选字符的权重值;
将上一次输入的键盘码已选择的字或词语,与每一个候选字符关联作为组 合关键字到所述预置的词库中进行搜索,并根据搜索结果计算每一个组合关键 字的权重值;
根据计算得到的每一个组合关键字的权重值更新对应候选字符的权重值, 按照更新后的权重值显示每一个候选字符, 以供用户选择确认。 - - 其中,在所述将上一次输入的键盘码已选择的字或词语, 与每一个候选字 符关联作为组合关键字到所述预置的词库中进行搜索,并根据搜索结果计算每 一个组合关键字的权重值中, 进一步包括步骤:
将上一次输入的键盘码已选择的字或词语,与每一个候选字符关联作为组 合关键字到所述预置的词库中进行搜索;
计算每一个搜索并命中数据的组合关键字的权重值;
将搜索但未命中数据的组合关键字的权重值赋值为预设的基本值。
其中, 所述计算每一个候选字符的权重值,是根据每一个候选字符的使用 频率计算得到每一个候选字符的权重值;
所述计算每一个组合关键字的权重值,是根据搜索并命中数据的组合关键 字的使用频率, 计算得到每一个搜索并命中数据的组合关键字的权重值。
其中,在所述根据计算得到的每一个组合关键字的权重值更新对应候选字 符的权重值, 按照更新后的权重值显示每一个候选字符中, 还包括步骤: 根据计算得到的每一个组合关键字的权重值更新对应候选字符的权重值; 按照权重值由大到小的顺序, 对更新权重值后的候选字符进行排序; 显示排序后的候选字符。
其中, 还包括步骤: 输出用户对所述显示的候选字符的选择结果, 并将所 述选择结果存储到所述上下文数据库中以供对下一次输入的键盘码关联的字 和 /或词语进行联想。
其中, 在所述接收当前输入的键盘码在, 进一步包括步骤:
检测接收到的当前输入的键盘码的类型;
若检测结果为当前输入的键盘码为字符键盘码,则执行所述到预置的词库 中搜索所述键盘码关联的字和 /或词语作为候选字符, 并计算每一个候选字符 的权重值;
若检测结果为所述接收到的键盘码为输入打断控制操作,则删除所述上下 文数据库中保存的根据上一次输入的键盘码已选择的字或词语。
其中, 在所述接收当前输入的键盘码中, 进一步包括步骤: 用户输入某一 键盘码并选择得到相应的字或词语后,通过所述上下文数据库暂存用户输入的 该字或词语。
其中, 在所述接收当前输入的键盘码中, 进一步包括步骤: 扫描 "光标" - - 前用户已经输入的字或词语。
根据本发明的另一方面,还提供一种在输入法中实现智能联想的装置, 包 括:
接收模块, 接收当前输入的键盘码。
计算模块, 到预置的词库中搜索所述键盘码关联的字和 /或词语作为候选 字符, 并计算每一个候选字符的权重值。
搜索模块,将上一次输入的键盘码已选择的字或词语, 与每一个候选字符 关联作为组合关键字到所述预置的词库中进行搜索,并根据搜索结果计算每一 个组合关键字的权重值。
更新模块,根据计算得到的每一个组合关键字的权重值更新每一个候选字 符的权重值。
显示模块,按照更新后的权重值显示每一个候选字符,以供用户选择确认。 其中, 所述搜索模块包括:
搜索单元,将上一次输入的键盘码已选择的字或词语, 与每一个候选字符 关联作为组合关键字到所述预置的词库中进行搜索。
确定单元,计算搜索并命中数据的组合关键字的权重值, 并将搜索但未命 中数据的组合关键字的权重值赋值为零。
其中,所述计算模块是根据每一个候选字符的使用频率计算得到每一个候 选字符的权重值;
所述确定单元是根据每一个搜索并命中数据的组合关键字的使用频率,计 算得到每一个搜索并命中数据的组合关键字的权重值。
其中, 还包括:
排序模块,按照权重值由大到小的顺序,对由所述更新模块更新权重值后 的候选字符进行排序
所述显示模块具体是显示由所述排序模块排序后的候选字符。
其中, 还包括: 输出模块, 输出用户对所述显示的候选字符的选择结果, 并将所述选择结果存储到上下文数据库中以供对下一次输入的键盘码关联的 字和 /或词语进行联想。
其中, 还包括:
检测模块, 检测所述接收模块接收到的当前输入的键盘码的类型。 - - 通知模块,在检测结果为当前输入的键盘码为字符键盘码时, 则通知所述 计算模块执行搜索以及计算操作。
删除模块,在检测结果为所述接收到的键盘码为输入打断控制操作时, 删 除上下文数据库中保存的根据上一次输入的键盘码已选择的字或词语。
相应地, 本发明实施例还提供了一种带输入法的终端设备, 包括上述的在 输入法中实现智能联想的装置。
其中, 所述接收模块接收硬件键盘输入的键盘码。
其中, 所述接收模块接收触摸屏键盘输入的键盘码。
其中, 所述预置的词库在该输入法创建的时候已经被设置,且在用户安装 后使用的过程中, 根据用户的输入情况自动学习, 并更新词库。
其中, 所述终端设备扫描 "光标" 前用户已经输入的字或词语。
实施本发明实施例, 具有以下有益效果:
本发明实施例能够根据用户上一次输入的字符或者词语作为参考,对本次 输入的键盘码进行对应候选字符的搜索以及各候选字符权重值的更新和确定, 并按照更新后的最终权重值向用户显示各候选字符,可以有效地提高对键盘码 进行字符联想的命中率, 提高用户的字符输入速度。 附图说明
为了更清楚地说明本发明实施例或现有技术中的技术方案,下面将对实施 例或现有技术描述中所需要使用的附图作简单地介绍,显而易见地, 下面描述 中的附图仅仅是本发明的一些实施例, 对于本领域普通技术人员来讲,在不付 出创造性劳动的前提下, 还可以根据这些附图获得其他的附图。
图 1 是本发明的在输入法中实现智能联想的方法的第一实施例流程示意 图;
图 2是本发明的在输入法中实现智能联想的方法的第二实施例流程示意 图;
图 3 是本发明实施例的计算每一个组合关键字的权重值的方法流程示意 图;
图 4是本发明实施例的其中一种候选字符显示方法的流程示意图; 图 5 是本发明的在输入法中实现智能联想的装置的第一实施例结构示意 图;
图 6是本发明的在输入法中实现智能联想的装置的第二实施例结构示意 图;
图 7是图 6中的搜索模块的结构示意图。 具体实施方式
下面将结合本发明实施例中的附图详细描述对本发明的各个实施例, 显 然, 所描述的实施例仅仅是本发明一部分实施例, 而不是全部的实施例。 基于 本发明中的实施例,本领域普通技术人员在没有作出创造性劳动前提下所获得 的所有其他实施例, 都属于本发明保护的范围。
请参见图 1 , 是本发明的在输入法中实现智能联想的方法的第一实施例流 程示意图, 本发明实施例可应用于手机、 电脑等能够实现输入法的设备中, 本 发明实施例根据上一次输入的字或词语,对当前输入的键盘码对应的字或者词 语进行联想, 以完成键盘码对应的字或词语的联想。 具体的, 本发明实施例的 所述方法从步骤 S101开始:
在步骤 S101 , 接收当前输入的键盘码;
当用户需要输入文字时, 可通过手机等设备的硬件键盘、或触摸屏键盘等 输入相应的键盘码, 手机等设备在 S101中接收相应的键盘码。
在步骤 S102, 到预置的词库中搜索所述键盘码关联的字和 /或词语作为候 选字符, 并计算每一个候选字符的权重值;
所述词库在该输入法创建的时候已经被设置,并且在用户安装后使用的过 程中, 可以根据用户的输入情况自动学习, 并更新词库, 也就是说, 该词库中 包括基本的字或词语,也包括根据用户习惯得到的常用字或词语。 查找到作为 候选字符的字和 /或词语后, 可通过权重算法对这些候选字符进行计算, 具体 可以根据本机中记录的这些字或词语的使用频率来计算对应的权重值。
在步骤 S103 , 将上一次输入的键盘码已选择的字或词语, 与每一个候选 字符关联作为组合关键字到所述预置的词库中进行搜索,并根据搜索结果计算 每一个组合关键字的权重值。
即将每一个候选字符和上一次输入的字或词语组合作为一个关键字到词 库中搜索, 确定基本的字和 /或词语、 或者常用字和 /或词语中, 是否存在该组 - - 合关键字, 并在查询得到时, 计算相应组合关键字的权重值。 其中, 对于没有 查询命中数据的组合关键字,可对该组合关键字的权重值赋值为基本值如赋值 为零。
在步骤 S104, 根据计算得到的每一个组合关键字的权重值更新对应候选 字符的权重值,按照更新后的权重值显示每一个候选字符,以供用户选择确认。
具体可以在已计算得到的每一个候选字符的权重值的基石出上,再加上候选 字符对应的组合关键字的权重值,得到该候选字符的最终权重值, 并可以按照 最终权重值, 对每一个候选字符进行排序显示, 以供用户选择确认。
本发明实施例能够根据用户上一次输入的字符或者词语作为参考,对本次 输入的键盘码进行对应候选字符的搜索以及各候选字符权重值的更新和确定, 并按照更新后的最终权重值向用户显示各候选字符,可以有效地提高对键盘码 进行字符联想的命中率, 提高用户的字符输入速度。
再请参见图 2, 是本发明的在输入法中实现智能联想的方法的第二实施例 流程示意图; 本发明实施例可应用于手机、 电脑等能够实现输入法的设备中, 本发明实施例根据上一次输入的字或词语,对当前输入的键盘码对应的字或者 词语进行联想联, 以完成键盘码对应的字或词语的联想。 具体的, 本发明实施 例的所述方法包括:
在步骤 S201, 检测接收到的当前输入的键盘码的类型;
若检测结果为当前输入的键盘码为字符键盘码, 则执行下述的 S202。 若检测结果为所述接收到的键盘码为输入打断控制操作,则删除上下文数 据库中保存的根据上一次输入的键盘码已选择的字或词语,以避免对位于新位 置字或词语的输入结果产生干扰。
具体的,在用户输入某一键盘码并选择得到相应的字或词语后, 可以通过 一个上下文数据库暂存用户输入的该字或词语,以便于对紧随其后的输入的键 盘码对应的字或词语进行智能联想。
所述的打断控制操作可以包括: 用户使用了 "退格键"删除了上一次输入 的字或词语, 或者用户使用 "方向键" 将 "光标" 移动到文档中另一个字或词 语之后, 此时, 不需要根据上一次输入的字或词语进行智能联想, 需要删除上 下文数据库中保存的根据上一次输入的键盘码已选择的字或词语,以避免对位 于新位置字或词语的输入结果产生干扰。 - - 当然, 在其他实施例中, 也可以智能地扫描 "光标"前用户已经输入的字 或词语, 以便于对紧随其后的输入的键盘码对应的字或词语进行智能联想。
在步骤 S202, 到预置的词库中搜索所述键盘码关联的字和 /或词语作为候 选字符, 并计算每一个候选字符的权重值。
所述预置的词库包括: 用于存储基本字和 /或词语的基本词库, 和用于存 储本端已使用过的字和 /或词语的常用词库。 所述计算每一个候选字符的权重 值, 是根据每一个候选字符的使用频率计算得到每一个候选字符的权重值。
在步骤 S203 , 将上一次输入的键盘码已选择的字或词语, 与每一个候选 字符关联作为组合关键字到所述预置的词库中进行搜索,并根据搜索结果计算 每一个组合关键字的权重值;
所述计算每一个组合关键字的权重值,是根据每一个搜索并命中数据的组 合关键字的使用频率, 计算得到每一个搜索并命中数据的组合关键字的权重 值,对于搜索但未命中数据的组合关键字的权重值赋值为基本值, 例如赋值为
0。
在步骤 S204, 根据计算得到的每一个组合关键字的权重值更新对应候选 字符的权重值,按照更新后的权重值显示每一个候选字符,以供用户选择确认。
具体可以在已计算得到的每一个候选字符的权重值的基石出上,再加上每一 个候选字符对应的组合关键字的权重值, 得到每一个候选字符的最终权重值, 并可以按照最终权重值,对每一个候选字符进行排序显示,以供用户选择确认。
在步骤 S205 , 输出用户对所述显示的候选字符的选择结果, 并将所述选 择结果存储到所述上下文数据库中以供对下一次输入的键盘码关联的字和 /或 词语进行联想。在用户选择确认某一个候选字符后,将用户选择的候选字符输 出到相应文档的对应位置中。
进一步的, 请参见图 3 , 是本发明实施例的计算每一个组合关键字的权重 值的方法流程示意图,本实施例的计算每一个组合关键字的权重值的方法对应 于上述在输入法中实现智能联想的方法第一实施例中的 S 103 , 或者对应于上 述在输入法中实现智能联想的方法第二实施例中的 S203。 本实施例中的计算 每一个组合关键字的权重值所述方法包括:
在步骤 S301 , 将上一次输入的键盘码已选择的字或词语, 与每一个候选 字符关联作为组合关键字到所述预置的词库中进行搜索。 - - 在步骤 S302, 对于搜索并命中数据的组合关键字, 计算每一个搜索并命 中数据的组合关键字的权重值。
在步骤 S303 , 对于搜索但未命中数据的组合关键字, 将该搜索但未命中 数据的组合关键字的权重值赋值为预设的基本值。
当在词库中搜索到所述组合关键字对应的字或词语时, 即命中数据, 然后 可以根据搜索到的数据确定所述组合关键字的使用频率,来计算对应的组合关 键字的权重值。对于没有命中数据的组合关键字, 可直接将其权重值赋值为预 设的基本值如零。
再请参见图 4, 是本发明实施例的其中一种候选字符显示方法的流程示意 图, 在本发明实施例中, 是根据候选字符更新后的权重值的大小, 来对候选字 符进行排序, 并将排序结果显示给用户, 具体可对应于上述实施例中的 S104, 本实施例的所述方法包括:
在步骤 S401 , 根据计算得到的每一个组合关键字的权重值更新对应候选 字符的权重值。 如可通过将组合关键字的权重值与当前候选字符的权重值相 加, 得到更新后的每一个候选字符的权重值。
在步骤 S402, 按照权重值由大到小的顺序, 对更新权重值后的候选字符 进行排序。
具体可按照由大到小的顺序, 从左至右, 或者从上至下的顺序进行排序。 在步骤 S403 , 显示排序后的候选字符。
下面以一具体实例对本发明实施例的所述在输入法中实现智能联想的方 法进行说明。
用户使用拼音输入法输入了 "zaixian" 的键盘码, 手机等设备接收到此键 盘码后, 确定该键盘码为字符键盘码。
到输入法词库中搜索所述键盘码关联的字和 /或词语, 联想出 "zaixian" 对应的字和词语包括 "1、 在线 [100]; 2、 再现剛; 3、 在先 [60] , 5、 在 [40]" , 其中, 方括号中为根据使用频率计算得到的对应词条的权重值。
此时, 用户选择了 " 1、在线 [100]" , 同时, 上下文数据库中暂存 "在线"。 当用户再次输入 "shipin" 的字符键盘码时, 再到词库中搜索得到 " 1、 食 品 [90]; 2、 视频 [80]; 3、 饰品 [70]; 4、 诗品网; 5、 是 [50],, 作为候选字符。 此时, 手机等设备并不需要将这些候选字符显示给用户, 而是需要继续在后台 - - 执行下述步骤。
将用户上次输入的 "在线" 与上述的每一个候选字符组合, 分别得到 "在 线食品" 、 "在线视频" 、 "在线饰品" 、 "在线诗品" 以及 "在线是" 的组 合关键字;
根据上述的组合关键字到词库中搜索, 可以得到 " 1、 在线食品 [0]; 2、 在线视频 [50]; 3、 在线饰品 [0]; 4、 在线诗品 [0]; 5、 在线是 [0]" 。
根据各关键字的权重值,对上述的每一个候选字符的权重值进行更新, 将 组合关键字的权重值与该组合关键字对应的候选字符的权重值相加,可以得出 "1、 食品 [90]; 2、 视频 [130]; 3、 饰品 [70]; 4、 诗品 [60]; 5、 是 [50],, 。
根据更新后的各候选字符的权重值, 得到 " 1、 视频 [130]; 2、 食品 [90];
3、 饰品 [70]; 4、 诗品 [60]; 5、 是 [50]" , 此时, 将各候选字符显示给用户。
用户此时就可以直接通过空格键选择得到 "1、视频 [130]" ,从而完成 "在 线视频" 的输入。
本发明实施例能够根据用户上一次输入的字符或者词语作为参考,对本次 输入的键盘码进行对应候选字符的搜索以及各候选字符权重值的更新和确定, 并按照更新后的最终权重值向用户显示各候选字符,可以有效地提高对键盘码 进行字符联想的命中率, 提高用户的字符输入速度。
并且在向用户显示候选字符时,是根据更新后的权重值按照由大到小的顺 序显示, 方便用户查看以及选择。
同时, 能够在用户打断输入时, 自动删除上一次暂存的上一次输入的字或 者词语停止后续的智能联想操作,避免对位于新位置字或词语的输入结果产生 干扰, 进一步地实现了智能化、 自动化。
下面对本发明的在输入法中实现智能联想的装置的结构示意图进行说明。 请参见图 5 , 是本发明的在输入法中实现智能联想的装置的第一实施例结 构示意图。本发明实施例的所述装置可应用于手机、 电脑等能够实现输入法的 设备中, 本发明实施例根据上一次输入的字或词语,对当前输入的键盘码对应 的字或者词语进行联想, 以完成键盘码对应的字或词语的联想。 具体的, 本发 明实施例的所述装置包括:
接收模块 11 , 接收当前输入的键盘码。
当用户需要输入文字时, 可通过硬件键盘、或触摸屏键盘等输入相应的键 - - 盘码, 所述接收模块 11接收相应的键盘码, 例如所述接收模块 11接收用户输 入的 "shipin" 的键盘码。
计算模块 12, 到预置的词库中搜索所述键盘码关联的字和 /或词语作为候 选字符, 并计算每一个候选字符的权重值。
所述词库在该输入法创建的时候已经被设置,并且在用户安装后使用的过 程中, 可以根据用户的输入情况自动学习, 并更新词库, 也就是说, 该词库中 包括基本的字或词语,也包括根据用户习惯得到的常用字或词语。 查找到作为 候选字符的字和 /或词语后, 可通过权重算法对这些候选字符进行计算, 具体 可以根据本机中记录的这些字或词语的使用频率来计算对应的权重值。
例如, 根据所述接收模块 11接收到的 "shipin" 的键盘码, 搜索得到 "1、 食品 [90]; 2、 视频 [80]; 3、 饰品 [70]; 4、 诗品 [60]; 5、 是 [50]" 的候选字符, 其中, 方括号中的数值为所述计算模块 12根据使用频率计算得到的对应候选 字符的权重值。
搜索模块 13 , 将上一次输入的键盘码已选择的字或词语, 与每一个候选 字符关联作为组合关键字到所述预置的词库中进行搜索,并根据搜索结果计算 每一个组合关键字的权重值。
所述搜索模块 13将每一个候选字符和上一次输入的字或词语组合作为一 个关键字到词库中搜索, 确定基本的字和 /或词语、 或者常用字和 /或词语中是 否存在该组合关键字, 并在查询得到即命中数据时,计算相应组合关键字的权 重值。 其中, 对于没有查询命中数据的组合关键字, 可对该组合关键字的权重 值赋值为基本值, 如赋值为零。
例如, 用户上次输入并确定的词语为 "在线" , 那么所述搜索模块 13将 "在线食品" 、 "在线视频" 、 "在线饰品" 、 "在线诗品" 以及 "在线是" 作为组合关键字到词库中搜索相关词语, 在本次搜索中, 所述搜索模块 13仅 搜索到关于 "在线视频" 的词语及其使用频率, 根据该搜索结果得出每一个组 合关键字的权重值 " 1、 在线食品 [0]; 2、 在线视频 [50]; 3、 在线饰品 [0]; 4、 在线诗品 [0]; 5、 在线是 [0]" , 其中, "在线食品" "在线饰品" "在线诗品" "在线是" 由于没有数据库中搜索到其被使用过, 没有命中数据, 因此直接对 "在线食品" "在线饰品" "在线诗品" "在线是" 赋值为 0。
更新模块 14, 根据计算得到的每一个组合关键字的权重值更新每一个候 - - 选字符的权重值。
具体所述更新模块 14可以在已计算得到的每一个候选字符的权重值的基 础上,再加上相应候选字符对应的组合关键字的权重值,得到该候选字符的最 终权重值, 并可以按照最终权重值, 对每一个候选字符进行排序显示, 以供用 户选择确认。
例如,根据各关键字的权重值,对上述的每一个候选字符的权重值进行更 新,将组合关键字的权重值与该组合关键字对应的候选字符的权重值相加, 可 以得出 " 1、 食品 [90]; 2、 视频 [130]; 3、 饰品 [70]; 4、 诗品 [60]; 5、 是 [50],, 。
显示模块 15 , 按照更新后的权重值显示每一个候选字符, 以供用户选择 确认。
所述显示模块 15根据权重值的大小, 对每一个候选字符进行排序, 并将 排序后的候选字符显示给用户, 以便于用户更快地进行选择, 完成本次字符输 入。
例如, 按排列次序显示 " 1、 视频 [130]; 2、 食品 [90]; 3、 饰品 [70]; 4、 诗品 [60]; 5、 是 [50],, 供用户选择。
其中, 所述计算模块 12是根据每一个候选字符的使用频率计算得到每一 个候选字符的权重值。
本发明实施例能够根据用户上一次输入的字符或者词语作为参考,对本次 输入的键盘码进行对应候选字符的搜索以及各候选字符权重值的更新和确定, 并按照更新后的最终权重值向用户显示各候选字符,可以有效地提高对键盘码 进行字符联想的命中率, 提高用户的字符输入速度。
具体的, 再请参见图 6, 是本发明的在输入法中实现智能联想的装置的第 二实施例结构示意图。本发明实施例的所述装置可应用于手机、 电脑等能够实 现输入法的设备中, 本发明实施例根据上一次输入的字或词语,对当前输入的 键盘码对应的字或者词语进行联想, 以完成键盘码对应的字或词语的联想, 本 发明实施例的所述装置包括上述装置第一实施例中的接收模块 11、 计算模块 12、 搜索模块 13、 更新模块 14以及显示模块 15 , 进一步具体的, 在本发明实 施例中的所述装置还包括:
输出模块 16, 输出用户对所述显示的候选字符的选择结果, 并将所述选 择结果存储到所述上下文数据库中以供对下一次输入的键盘码关联的字和 /或 - - 词语进行联想。
在用户对所述显示模块 14中显示的候选字符中选择确认除其中一个候选 字符后, 将用户选择的候选字符输出到相应文档的对应位置中。
进一步可选的, 再请参见图 6, 本发明实施例的所述在输入法中实现智能 联想的装置还包括: 检测模块 17、 通知模块 18以及删除模块 19。 所述装置通 过该三个模块对用户输入的键盘码进行判断,以确定是否通知上述的接收模块 11、 计算模块 12、 搜索模块 13、 更新模块 14以及显示模块 15执行相应的智 能联想操作。 具体的:
所述检测模块 17, 检测所述接收模块 11接收到的当前输入的键盘码的类 型。
通知模块 18, 在检测结果为当前输入的键盘码为字符键盘码时, 则通知 所述计算模块 12执行搜索以及计算操作。
删除模块 19, 在检测结果为所述接收到的键盘码为输入打断控制操作时, 删除上下文数据库中保存的根据上一次输入的键盘码已选择的字或词语。
具体的,在用户输入某一键盘码并选择得到相应的字或词语后, 可以通过 一个上下文数据库暂存用户输入的该字或词语,以便于对紧随其后的输入的键 盘码对应的字或词语进行智能联想。 当然, 在其他实施例中, 也可以智能地扫 描 "光标"前用户已经输入的字或词语, 以便于对紧随其后的输入的键盘码对 应的字或词语进行智能联想。
所述检测模块 17检测得到的打断控制操作可以包括: 用户使用了 "退格 键" 删除了上一次输入的字或词语, 或者用户使用 "方向键" 将 "光标" 移动 到文档中另一个字或词语之后, 此时, 不需要根据上一次输入的字或词语进行 智能联想,需要删除上下文数据库中保存的根据上一次输入的键盘码已选择的 字或词语, 以避免对位于新位置字或词语的输入结果产生干扰。
进一步可选的, 再请参见图 6, 所述在输入法中实现智能联想的装置还包 括:
排序模块 20, 按照权重值由大到小的顺序, 对由所述更新模块更新权重 值后的候选字符进行排序; 所述排序模块 20可根据更新后的候选字符权重值 的大小, 从左至右或者从上至下的顺序对候选字符进行排序。
所述显示模块 15具体是显示由所述排序模块排序后的候选字符。 - - 进一步的, 请参见图 7 , 是图 6中的搜索模块的结构示意图, 所述搜索模 块 13具体包括:
搜索单元 131 , 将上一次输入的键盘码已选择的字或词语, 与每一个候选 字符关联作为组合关键字到所述预置的词库中进行搜索。
确定单元 132, 计算搜索并命中数据的组合关键字的权重值, 并将搜索但 未命中数据的组合关键字的权重值赋值为零。
当在词库中搜索到所述组合关键字对应的字或词语时, 即命中数据, 然后 可以根据该搜索到的数据对应的组合关键字的使用频率,来计算对应的组合关 键字的权重值。对于没有命中数据的组合关键字, 可直接将其权重值赋值为预 设的基本值如零。
本发明实施例能够根据用户上一次输入的字符或者词语作为参考,对本次 输入的键盘码进行对应候选字符的搜索以及各候选字符权重值的更新和确定, 并按照更新后的最终权重值向用户显示各候选字符,可以有效地提高对键盘码 进行字符联想的命中率, 提高用户的字符输入速度。
并且在向用户显示候选字符时,是根据更新后的权重值按照由大到小的顺 序显示, 方便用户查看以及选择。
同时, 能够在用户打断输入时, 自动删除上一次暂存的上一次输入的字或 者词语停止后续的智能联想操作,避免对位于新位置字或词语的输入结果产生 干扰, 进一步地实现了智能化、 自动化。
根据本发明的一个实施例,根据图 1所示的在输入法中实现智能联想的方 法可以是由图 5 所示的在输入法中实现智能联想的装置中的各个单元来执行 的方法。 例如, 图 1所示的步骤 S101-S105可以由图 5所示的接收模块 11、 计算模块 12、 搜索模块 13及更新模块 14来执行。
根据本发明的另一个实施例,图 5所示的在输入法中实现智能联想的装置 中的各个单元可以分别或全部合并为一个或若干个另外的单元来构成,或者其 中的某个(些)单元还可以再拆分为功能上更小的多个单元来构成。 例如但不 限于,计算模块 12可以与搜索模块 13合并构成一个单独的计算模块, 更新模 块 14可以与显示模块 15合并构成一个单独的更新模块等,这可以实现同样的 操作, 而不影响本发明的实施例的技术效果的实现。
根据本发明的第二个实施例,根据图 2所示的在输入法中实现智能联想的 - - 方法可以是由图 6、 7所示的在输入法中实现智能联想的装置中的各个单元来 执行的方法。 例如, 图 2所示的步骤 S201、 S205、 S301、 S402、 S403可以由 图 6、 7所示的检测模块 17、 输出模块 16、 搜索单元 131、 排序模块 20、 显示 模块 15来执行。
根据本发明的另一个实施例, 图 6、 7所示的在输入法中实现智能联想的 装置中的各个单元可以分别或全部合并为一个或若干个另外的单元来构成,或 者其中的某个(些)单元还可以再拆分为功能上更小的多个单元来构成。 例如 但不限于, 检测模块 17可以与通知模块 18、 删除模块 19合并构成一个单独 的判断模块,搜索单元 131可以与确定单元 132合并构成一个单独的赋值模块 等, 这可以实现同样的操作, 而不影响本发明的实施例的技术效果的实现。
本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步 骤是可以通过程序来指令相关的如图 5、 6、 7中所示的在输入法中实现智能联 想的硬件来完成如图 1、 2中所示的在输入法中实现智能联想的方法, 该程序 可以存储于一计算机可读存储介质中, 存储介质可以包括: 闪存盘、 只读存储 器 ( Read-Only Memory , ROM ) 、 随机存取器 ( Random Access Memory, RAM ) 、 磁盘或光盘等。
综上所述,应用根据本发明的各个实施例的在输入法中实现智能联想的方 法和在输入法中实现智能联想的装置,可以有效地提高对键盘码进行字符联想 的命中率, 提高用户的字符输入速度, 具有很强的实用价值。
以上描述了本发明的各个实施例,但是它们不用以限制本发明的范围, 本 发明的范围由后附的权利要求来定义。 在不脱离本发明的精神和原则的情况 下, 所做的任何修改、 等同替换、 改进等, 均应包含在权利要求的保护范围之 内。

Claims

权 利 要 求
1、 一种在输入法中实现智能联想的方法, 包括以下步骤:
接收当前输入的键盘码;
到预置的词库中搜索所述当前输入的键盘码关联的字和 /或词语作为候选 字符, 并计算每一个候选字符的权重值;
将上一次输入的键盘码已选择的字或词语,与每一个候选字符关联作为组 合关键字到所述预置的词库中进行搜索,并根据搜索结果计算每一个组合关键 字的权重值;
根据计算得到的每一个组合关键字的权重值更新对应候选字符的权重值, 按照更新后的权重值显示每一个候选字符, 以供用户选择确认。
2、 如权利要求 1所述的方法, 在所述将上一次输入的键盘码已选择的字 或词语, 与每一个候选字符关联作为组合关键字到所述预置的词库中进行搜 索, 并根据搜索结果计算每一个组合关键字的权重值中, 进一步包括步骤: 将上一次输入的键盘码已选择的字或词语,与所述每一个候选字符关联作 为组合关键字到所述预置的词库中进行搜索;
计算搜索并命中数据的组合关键字的权重值;
将搜索但未命中数据的组合关键字的权重值赋值为预设的基本值。
3、 如权利要求 2所述的方法,
所述计算每一个候选字符的权重值,是根据每一个候选字符的使用频率计 算得到每一个候选字符的权重值;
所述计算每一个组合关键字的权重值,是根据每一个搜索并命中数据的组 合关键字的使用频率, 计算得到每一个搜索并命中数据的组合关键字的权重 值。
4、 如权利要求 1-3任一项所述的方法, 在所述根据计算得到的每一个组 合关键字的权重值更新对应候选字符的权重值,按照更新后的权重值显示每一 个候选字符中, 还包括步骤:
根据计算得到的每一个组合关键字的权重值更新对应候选字符的权重值; 按照权重值由大到小的顺序, 对更新权重值后的候选字符进行排序; 显示排序后的候选字符。
5、 如权利要求 4所述的方法, 还包括步骤:
输出用户对所述显示的候选字符的选择结果 ,并将所述选择结果存储到上 下文数据库中以供对下一次输入的键盘码关联的字和 /或词语进行联想。
6、 如权利要求 5所述的方法, 在所述接收当前输入的键盘码中, 进一步 包括步骤:
检测接收到的当前输入的键盘码的类型;
若检测结果为当前输入的键盘码为字符键盘码,则执行所述到预置的词库 中搜索所述键盘码关联的字和 /或词语作为候选字符, 并计算每一个候选字符 的权重值;
若检测结果为所述接收到的键盘码为输入打断控制操作,则删除所述上下 文数据库中保存的根据上一次输入的键盘码已选择的字或词语。
7、 如权利要求 6所述的方法, 在所述接收当前输入的键盘码中, 进一步 包括步骤: 用户输入某一键盘码并选择得到相应的字或词语后,通过所述上下 文数据库暂存用户输入的该字或词语。
8、 如权利要求 6所述的方法, 在所述接收当前输入的键盘码中, 进一步 包括步骤: 扫描 "光标" 前用户已经输入的字或词语。
9、 一种在输入法中实现智能联想的装置, 包括:
接收模块, 被配置为接收当前输入的键盘码;
计算模块, 被配置为到预置的词库中搜索所述键盘码关联的字和 /或词语 作为候选字符, 并计算每一个候选字符的权重值; 搜索模块,被配置为将上一次输入的键盘码已选择的字或词语, 与每一个 候选字符关联作为组合关键字到所述预置的词库中进行搜索,并根据搜索结果 计算每一个组合关键字的权重值;
更新模块,被配置为根据计算得到的每一个组合关键字的权重值更新每一 个候选字符的权重值; 和
显示模块,被配置为按照更新后的权重值显示每一个候选字符, 以供用户 选择确认。
10、 如权利要求 9所述的装置, 所述搜索模块包括:
搜索单元,被配置为将上一次输入的键盘码已选择的字或词语, 与每一个 候选字符关联作为组合关键字到所述预置的词库中进行搜索;
确定单元,被配置为计算搜索并命中数据的组合关键字的权重值, 并对于 搜索但未命中数据的组合关键字的权重值赋值为零。
11、 如权利要求 10所述的装置,
所述计算模块是根据每一个候选字符的使用频率计算得到每一个候选字 符的权重值;
所述确定单元是根据每一个搜索并命中数据的组合关键字的使用频率,计 算得到每一个搜索并命中数据的组合关键字的权重值。
12、 如权利要求 11所述的装置, 还包括:
排序模块,被配置为按照权重值由大到小的顺序,对由所述更新模块更新 权重值后的候选字符进行排序;
所述显示模块用于显示由所述排序模块排序后的候选字符。
13、 如权利要求 12所述的装置, 还包括:
输出模块,被配置为输出用户对所述显示的候选字符的选择结果, 并将所 述选择结果存储到上下文数据库中以供对下一次输入的键盘码关联的字和 /或 词语进行联想。
14、 如权利要求 13所述的装置, 还包括:
检测模块, 被配置为检测所述接收模块接收到的当前输入的键盘码的类 型;
通知模块,被配置为在检测结果为当前输入的键盘码为字符键盘码时, 则 通知所述计算模块执行搜索以及计算操作;
删除模块,被配置为在检测结果为所述接收到的键盘码为输入打断控制操 作时,删除所述上下文数据库中保存的根据上一次输入的键盘码已选择的字或 词语。
15、 一种带输入法的终端设备, 包括上述 9-14任一项所述的在输入法中 实现智能联想的装置。
16、 如权利要求 15所述的终端设备, 所述接收模块接收硬件键盘输入的 键盘码。
17、 如权利要求 15所述的终端设备, 所述接收模块接收触摸屏键盘输入 的键盘码。
18、 如权利要求 15所述的终端设备, 所述预置的词库在该输入法创建的 时候已经被设置,且在用户安装后使用的过程中,根据用户的输入情况自动学 习, 并更新词库。
19、 如权利要求 15所述的终端设备, 所述终端设备扫描 "光标" 前用户 已经输入的字或词语。
20、一种包括程序代码的计算机程序, 当所述计算机程序运行在计算机上 时,所述程序代码执行根据权利要求 1所述的在输入法中实现智能联想的方法 的各步骤。
PCT/CN2013/082911 2012-09-12 2013-09-04 在输入法中实现智能联想的方法、装置及终端设备 WO2014040510A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US14/427,346 US10049091B2 (en) 2012-09-12 2013-09-04 Method, device, and terminal equipment for enabling intelligent association in input method

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201210337043.XA CN103677299A (zh) 2012-09-12 2012-09-12 一种在输入法中实现智能联想的方法、装置及终端设备
CN201210337043.X 2012-09-12

Publications (1)

Publication Number Publication Date
WO2014040510A1 true WO2014040510A1 (zh) 2014-03-20

Family

ID=50277611

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2013/082911 WO2014040510A1 (zh) 2012-09-12 2013-09-04 在输入法中实现智能联想的方法、装置及终端设备

Country Status (4)

Country Link
US (1) US10049091B2 (zh)
CN (1) CN103677299A (zh)
TW (1) TWI505139B (zh)
WO (1) WO2014040510A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105511642A (zh) * 2016-01-07 2016-04-20 珠海市魅族科技有限公司 一种输入方法及装置
WO2016082096A1 (en) * 2014-11-25 2016-06-02 Nuance Communications, Inc. System and method for predictive text entry using n-gram language model
CN105653064A (zh) * 2016-01-07 2016-06-08 珠海市魅族科技有限公司 一种输入方法及装置
CN107368479A (zh) * 2016-05-11 2017-11-21 江苏食品药品职业技术学院 一种利用计算机应用的信息检索方法

Families Citing this family (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104111738A (zh) * 2014-06-06 2014-10-22 珠海市魅族科技有限公司 一种字符关联方法及终端
CN104021201B (zh) * 2014-06-16 2017-06-16 辛玲 一种数据转换方法及装置
TWI587179B (zh) * 2016-05-20 2017-06-11 zheng-hong Lin Associated ad input method
CN106020505B (zh) * 2016-05-27 2018-10-16 维沃移动通信有限公司 一种输入法候选项的排序方法及移动终端
GB2551525A (en) * 2016-06-20 2017-12-27 Austin Consultants Ltd A system for automated code calculation and an automated code calculation method
CN106468960A (zh) * 2016-09-07 2017-03-01 北京新美互通科技有限公司 一种输入法候选项排序的方法和系统
CN108073303B (zh) * 2016-11-17 2021-11-30 北京搜狗科技发展有限公司 一种输入方法、装置及电子设备
CN106959766A (zh) * 2017-03-16 2017-07-18 努比亚技术有限公司 输入法联想方法及联想装置
TWI710926B (zh) * 2018-03-23 2020-11-21 宏碁股份有限公司 鍵盤投影裝置及智慧選字方法
CN109491498A (zh) * 2018-10-31 2019-03-19 广州致远电子有限公司 人机交互方法、系统、终端设备及计算机可读存储介质
CN112989148A (zh) * 2019-12-13 2021-06-18 华为技术有限公司 纠错词排序方法、装置、终端设备和存储介质
CN111782060A (zh) * 2020-06-18 2020-10-16 维沃移动通信有限公司 对象显示方法、装置和电子设备

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101122901A (zh) * 2007-09-25 2008-02-13 腾讯科技(深圳)有限公司 中文整句生成方法及装置
CN101248407A (zh) * 2005-05-27 2008-08-20 索尼爱立信移动通讯股份有限公司 对消息上下文中文本输入的自动语言选择
CN101515205A (zh) * 2008-02-18 2009-08-26 普天信息技术研究院有限公司 中文动态联想输入方法

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7293231B1 (en) * 1999-03-18 2007-11-06 British Columbia Ltd. Data entry for personal computing devices
US7030863B2 (en) * 2000-05-26 2006-04-18 America Online, Incorporated Virtual keyboard system with automatic correction
US7382358B2 (en) * 2003-01-16 2008-06-03 Forword Input, Inc. System and method for continuous stroke word-based text input
US7706616B2 (en) * 2004-02-27 2010-04-27 International Business Machines Corporation System and method for recognizing word patterns in a very large vocabulary based on a virtual keyboard layout
US9471566B1 (en) * 2005-04-14 2016-10-18 Oracle America, Inc. Method and apparatus for converting phonetic language input to written language output
EP1969456A4 (en) * 2005-12-12 2015-11-04 Tegic Comm Llc APPARATUS FOR SEARCHING AND NAVIGATING A MOBILE DEVICE
US20080103772A1 (en) * 2006-10-31 2008-05-01 Duncan Bates Character Prediction System
US20080126075A1 (en) * 2006-11-27 2008-05-29 Sony Ericsson Mobile Communications Ab Input prediction
KR101477530B1 (ko) * 2010-03-12 2014-12-30 뉘앙스 커뮤니케이션즈, 인코포레이티드 이동 전화의 터치 스크린과 함께 사용하기 위한 다중 모드 문자 입력 시스템
TWI564736B (zh) * 2010-07-27 2017-01-01 Iq Tech Inc Method of merging single word and multiple words
US8805095B2 (en) * 2010-12-03 2014-08-12 International Business Machines Corporation Analysing character strings
CN105431809B (zh) * 2013-03-15 2018-12-18 谷歌有限责任公司 用于国际语言的虚拟键盘输入

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101248407A (zh) * 2005-05-27 2008-08-20 索尼爱立信移动通讯股份有限公司 对消息上下文中文本输入的自动语言选择
CN101122901A (zh) * 2007-09-25 2008-02-13 腾讯科技(深圳)有限公司 中文整句生成方法及装置
CN101515205A (zh) * 2008-02-18 2009-08-26 普天信息技术研究院有限公司 中文动态联想输入方法

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2016082096A1 (en) * 2014-11-25 2016-06-02 Nuance Communications, Inc. System and method for predictive text entry using n-gram language model
CN105511642A (zh) * 2016-01-07 2016-04-20 珠海市魅族科技有限公司 一种输入方法及装置
CN105653064A (zh) * 2016-01-07 2016-06-08 珠海市魅族科技有限公司 一种输入方法及装置
CN107368479A (zh) * 2016-05-11 2017-11-21 江苏食品药品职业技术学院 一种利用计算机应用的信息检索方法

Also Published As

Publication number Publication date
US20150248386A1 (en) 2015-09-03
CN103677299A (zh) 2014-03-26
TW201411418A (zh) 2014-03-16
US10049091B2 (en) 2018-08-14
TWI505139B (zh) 2015-10-21

Similar Documents

Publication Publication Date Title
WO2014040510A1 (zh) 在输入法中实现智能联想的方法、装置及终端设备
US9684446B2 (en) Text suggestion output using past interaction data
US9542385B2 (en) Incremental multi-word recognition
US20170091335A1 (en) Search method, server and client
US8825694B2 (en) Mobile device retrieval and navigation
KR101750968B1 (ko) 일관된 텍스트 제안 출력
JP5316158B2 (ja) 情報処理装置、全文検索方法、全文検索プログラム、及び記録媒体
WO2016008452A1 (zh) 高效输入的预测方法和装置
CN110019840B (zh) 一种知识图谱中实体更新的方法、装置和服务器
CN108920649B (zh) 一种信息推荐方法、装置、设备和介质
CN104281275B (zh) 一种英文的输入方法和装置
CN105550217B (zh) 场景音乐搜索方法及场景音乐搜索装置
WO2016034066A1 (zh) 一种汉字识别方法、装置及终端
WO2016037465A1 (zh) 基于手持设备端的用于代码设计的智能化输入系统与方法
JP2001075981A (ja) 検索システム、検索条件受付方法及び記録媒体
JP2012141681A (ja) クエリセグメント位置決定装置
WO2016107611A1 (zh) 一种用于移动终端的文本查找方法和装置
JPH11154164A (ja) 全文検索処理における適合度算出方法および該方法に係るプログラムを格納した記憶媒体
US20100100821A1 (en) Window detection system and method for operating the same
WO2024036616A1 (zh) 一种基于终端的问答方法及装置
WO2010124509A1 (zh) 一种基于关键词输入的智能操作系统及方法
KR102351264B1 (ko) 사용자 맞춤형 신간 도서 정보의 제공 방법 및 그 시스템
EP3709137A1 (en) Character input device, character input method, and character input program
WO2023138047A1 (zh) 网络威胁信息提取方法、设备、存储介质及装置
WO2022174749A1 (zh) 一种联想词展示方法、终端设备及计算机存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 13836714

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 14427346

Country of ref document: US

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 13836714

Country of ref document: EP

Kind code of ref document: A1