WO2015120713A1 - Procédé et appareil d'acquisition d'une entrée, support de stockage informatique et dispositif associé - Google Patents

Procédé et appareil d'acquisition d'une entrée, support de stockage informatique et dispositif associé Download PDF

Info

Publication number
WO2015120713A1
WO2015120713A1 PCT/CN2014/085481 CN2014085481W WO2015120713A1 WO 2015120713 A1 WO2015120713 A1 WO 2015120713A1 CN 2014085481 W CN2014085481 W CN 2014085481W WO 2015120713 A1 WO2015120713 A1 WO 2015120713A1
Authority
WO
WIPO (PCT)
Prior art keywords
eyeball
area
interest
word
candidate
Prior art date
Application number
PCT/CN2014/085481
Other languages
English (en)
Chinese (zh)
Inventor
陈晓昕
吴先超
肖日新
Original Assignee
百度在线网络技术（北京）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 百度在线网络技术（北京）有限公司 filed Critical 百度在线网络技术（北京）有限公司
Publication of WO2015120713A1 publication Critical patent/WO2015120713A1/fr

Links

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
    • G06F3/0236—Character input methods using selection techniques to select from displayed items
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/31—Indexing; Data structures therefor; Storage structures
    • G06F16/313—Selection or weighting of terms for indexing
    • 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
    • G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
    • G06F3/013—Eye tracking input arrangements

Definitions

  • the present invention relates to input method technology, and in particular, to a method and device for acquiring a term, a computer storage medium and a device.
  • Input method refers to the encoding method used to input various characters into the terminal.
  • the client of the input method software can use the loaded dictionary, that is, the vocabulary and the word frequency contained in the dictionary, to display the sorting of various candidate terms to the user, so as to facilitate user input.
  • the frequency of the use of the terms and the terms that is, the word frequency
  • the server is periodically collected by the server to update various professional dictionaries, for example, the newly appearing words are recognized as new words added to the dictionary. Or, for example, identify some words that are frequently used as hot words, and so on.
  • An aspect of the present invention provides a method for obtaining an entry, including:
  • Select at least one candidate term as a new word and/or a hot word further provide an implementation manner, the performing a tracking operation on the eyeball of the user to obtain the region of interest of the user, including: acquiring video information of the eyeball;
  • the region of interest of the eyeball is determined as the region of interest of the user based on the location area of the eyeball and the movable region of the eyeball.
  • the attention condition includes at least one of a attention time and a frequency of interest.
  • the selecting at least one candidate term as a new word and/or a hot word includes:
  • a candidate term that does not appear in the pre-configured input method dictionary is determined as a new word.
  • the aspect as described above and any possible implementation manner further provide an implementation manner, wherein the selecting at least one candidate term as a new word and/or a hot word includes:
  • a candidate term appearing in the pre-configured input method dictionary is determined as a candidate hot word; determining a heat value of the candidate hot word according to a word frequency of the candidate hot word; and setting the heat value to be greater than or equal to the heat threshold
  • the candidate hot words are identified as hot words.
  • a tracking unit configured to perform a tracking operation on a user's eyeball to obtain an interest area of the user
  • An obtaining unit configured to acquire text information in the region of interest
  • a word unit for performing a word-cutting operation on the text information to obtain a candidate term
  • a selecting unit configured to select at least one candidate term as a new word and/or a hot word.
  • the region of interest of the eyeball is determined as the region of interest of the user based on the location area of the eyeball and the movable region of the eyeball.
  • the region of interest of the eyeball satisfies the condition of interest, the region of interest of the eyeball is determined to be the region of interest of the user.
  • the attention condition includes at least one of a attention time and a frequency of interest.
  • the selecting unit is specifically used to
  • a candidate term that does not appear in the pre-configured input method dictionary is determined as a new word.
  • the candidate term appearing in the pre-configured input method dictionary is determined as a candidate hot word; determining the heat value of the selected hot word according to the word frequency of the selected hot word; and the heat A candidate hot word whose value is greater than or equal to the heat threshold is determined as a hot word.
  • a computer storage medium is provided, the computer storage medium being encoded with a computer program, the program, when executed by one or more computers, causing the one or more computers to perform the following operations:
  • the present invention provides an apparatus comprising at least one processor, a memory, and at least one computer program; the at least one computer program being stored in the memory and executed by the at least one processor; Includes instructions to do the following:
  • the embodiment of the present invention performs a tracking operation on a user's eyeball to obtain a region of interest of the user, and then acquires text information in the region of interest, and performs word cutting on the text information. Operation, to obtain candidate terms, enabling selection of at least one candidate term as a new word and/or a hot word, due to the text information of the user extracted by the region of interest of the user's current reading behavior, The acquisition operation of the candidate term, therefore, can recognize the new word and/or the hot word in time based on the text information, thereby improving the timeliness of the term acquisition.
  • FIG. 1 is a schematic flowchart of a method for acquiring an entry according to an embodiment of the present invention
  • FIG. 2 is a schematic structural diagram of an apparatus for acquiring an entry according to another embodiment of the present invention. detailed description
  • terminals involved in the embodiments of the present invention may include, but are not limited to, a mobile phone, a personal digital assistant (PDA), a wireless handheld device, a tablet computer, and a personal computer (PC). ),
  • PDA personal digital assistant
  • PC personal computer
  • MP3 player MP4 player, etc.
  • FIG. 1 is a schematic flowchart of a method for acquiring an entry according to an embodiment of the present invention, as shown in FIG. 1 .
  • the tracking operation of the user's eyeball may be specifically performed on the user interface.
  • the user interface may be a World Wide Web (Web) page displayed by the terminal, or may also be an application document displayed by the terminal, for example, an email, a WORD document, a TXT document, a PDF document, etc., the present invention This is not particularly limited.
  • execution body of 01 ⁇ 1 04 may be an identification device, which may be located in the present In the local client, for offline identification, or can be located in the server on the network side for online identification, or some functions can be located in the client, and some functions are located in the server for offline and online identification. This embodiment does not limit this.
  • the client may be an input method application installed on the terminal, or may be a webpage of the browser, as long as the entry can be implemented to provide an objective for identifying new words and/or hot words.
  • the existence form is acceptable, and this embodiment does not limit this.
  • the tracking operation of the user's eyeball is performed to obtain the region of interest of the user, thereby acquiring text information in the region of interest, and performing a word-cutting operation on the text information to obtain candidate terms.
  • Equivalently selecting at least one candidate term as a new word and/or a hot word, and performing the acquisition operation of the candidate term by using the text information of the user's interest extracted by the region of interest of the current reading behavior of the user The ability to identify new words and/or hot words in time based on these textual information, thereby improving the timeliness of term acquisition.
  • the technical solution provided by the present invention it is possible to promptly use the recognized new words and/or hot words to update various professional dictionaries loaded by the input method, that is, the input method dictionary, which can further effectively improve the dictionary of the input method. accuracy.
  • video information of the eyeball may be specifically acquired.
  • the video information of the eyeball may be composed of a plurality of frame images, and may be collected by a camera. Further, based on the video information, a location area of the eyeball is determined. Then, based on the video information, determining a movable path of the eyeball, and determining a movable area of the eyeball according to the movable path. Since the motion arc of the human eye is in a fixed interval, the movable path corresponding to the eyeball can be determined according to the video information.
  • the motion path can be an exact value or a motion interval.
  • the movable path Through the movable path, it can be further calculated based on the movable The reachable area of the road force, which is the movable area of the eyeball. Finally, the region of interest of the eyeball can be determined according to the location area of the eyeball and the movable area of the eyeball as the region of interest of the user.
  • a portion of the eyeball in a movable region of the eyeball may be determined as a region of interest of the eyeball. If the region of interest of the eyeball satisfies the condition of interest, the region of interest of the eyeball is determined to be the region of interest of the user.
  • the attention condition may include, but is not limited to, at least one of attention time and frequency of interest.
  • the staying area of the eyeball in the movable area of the eyeball is greater than or equal to 3 seconds, it may be determined that the attention area of the eyeball is the user's interest area.
  • the area of interest of the eyeball may be determined to be the user's Area of interest.
  • various text recognition methods in the prior art may be used to obtain text information in the region of interest. No particular limitation is imposed.
  • a partial screenshot of the region of interest surrounded by a user interface having text information may be acquired, and then the obtained partial screenshot may be subjected to text recognition to obtain text information in the region of interest.
  • location information of the region of interest may be acquired, and corresponding text information is determined according to the location information as text information in the region of interest.
  • the word-cutting operation of the obtained text information may be specifically performed by using various word-cutting methods in the prior art.
  • the word segmentation method based on string matching or, for example, a word segmentation method based on understanding, or, for example, a statistical word segmentation method, is not particularly limited in the present invention.
  • the word-cutting method refer to related content in the prior art, and details are not described herein again.
  • the candidate term that does not appear in the pre-configured input method dictionary may be specifically determined as a new word.
  • any candidate term in the candidate term obtained by the word-cutting operation may be acquired. If the candidate term does not appear in the pre-configured input method dictionary, the candidate term can be determined as a new word.
  • pre-configured input method dictionary may be configured on the server on the network side, or may be configured on the local client. This embodiment does not specifically limit this.
  • the candidate term appearing in the pre-configured input method dictionary may be specifically determined as a candidate hot word. Further, a heat value of the candidate hot word is determined according to a word frequency in which the candidate hot word appears. Then, the candidate hot words whose heat value is greater than or equal to the heat threshold can be determined as a hot word.
  • any candidate term in the candidate term obtained by the word-cutting operation may be acquired. If the candidate term has appeared in the pre-configured input method dictionary, the candidate term can be marked as a candidate hot word. Then, according to the input method dictionary, the word frequency of the candidate hot words occurring within a specified time range may be obtained, and according to the word frequency, the heat value of the candidate hot words may be determined. Finally, the candidate hot words with the heat value greater than or equal to the heat threshold can be determined. For hot words.
  • the heat value of the candidate hot words (the average score of all candidate hot words * the average word frequency of all candidate hot words + the score of the candidate hot words * the total word frequency of the candidate hot words in the total statistical time) I (the average word frequency of all candidate hot words + the total word frequency of the candidate hot words in the total statistical time), determine the heat value of the candidate hot words. among them,
  • the score of the candidate hot words the frequency of the candidate hot words in the most recent unit statistical time / the total word frequency of the candidate hot words in the total statistical time.
  • H has no four candidate hot words: hot words A, hot words B, hot words C, and hot words D, and unit statistical time. For one day, the total statistical time is two days.
  • the word frequency that appears during the two days of 2013-12-18 and 2013-12-19 is shown in the following table:
  • the scores of the four candidate hot words are 0.74, 0.52, 0.8, and 0.82, respectively, based on the historical data of 2013-12-18 and 2013-12-19.
  • the candidate hot words A have an additional 135 points, and each person gave 0.74 points. According to the calculation formula described above, these four points.
  • the heat values of the candidate hot words can be:
  • the order from big to small is as follows:
  • the candidate hot word D appears the most frequently, so the ranking is also the highest. If the heat value of the candidate hot word is not less than the preset heat threshold, the candidate hot word D can be determined as a hot word.
  • the local input method dictionary can be further updated by using these terms, or the input method dictionary of the cloud (network side) can be further updated by using these terms.
  • This embodiment is not particularly limited.
  • the local input method dictionary or the input method dictionary of the cloud may be updated by using at least one of the statistical Ngram information and/or the Npos information. For details, refer to related content in the prior art, and details are not described herein. .
  • the technical solution provided in this embodiment can not only identify new words and/or hot words for one user, but also effectively organize and analyze the recognition results of multiple users for multiple users. , to get new words and / or hot words for multiple users.
  • the selected new word and/or hot word may be further specifically displayed. For example, icon characters may be added to these new words and/or hot words; or, for example, these new words and/or hot words may be presented at particular candidate locations.
  • the tracking operation of the user's eyeball is performed to obtain the region of interest of the user, and then the text information in the region of interest is acquired, and the text information is subjected to a word-cutting operation to obtain a candidate.
  • the entry enables selection of at least one candidate term as a new word and/or a hot word, and the candidate term is acquired due to the text information of the user's interest extracted by the region of interest of the user's current reading behavior.
  • the operation therefore, can identify new words and/or hot words in time based on the text information, thereby improving the timeliness of the entry of the terms.
  • the technical solution provided by the present invention it is possible to promptly use the recognized new words and/or hot words to update various professional dictionaries loaded by the input method, that is, the input method dictionary, which can further effectively improve the dictionary of the input method. accuracy.
  • the acquiring means of the term of the embodiment may include a tracking unit 21, an obtaining unit 22, a word cutting unit 23, and a selecting unit 24.
  • the tracking unit 21 is configured to perform a tracking operation on the eyeball of the user to obtain a region of interest of the user, and an acquiring unit 22, configured to acquire text information in the region of interest; Performing a word-cutting operation on the text information to obtain a candidate term; the selecting unit 24 is configured to select at least one candidate term as a new word and/or a hot word.
  • the acquiring device of the term provided in this embodiment may be located in a local client for offline identification, or may be located in a server on the network side for online identification, or may be partially located. In the client, some functions are located in the server for offline and online identification. This embodiment does not limit this.
  • the client may be an input method application installed on the terminal, or may be a webpage of the browser, as long as the entry can be implemented to provide an objective for identifying new words and/or hot words.
  • the existence form is acceptable, and this embodiment does not limit this.
  • the tracking operation of the user's eyeball is performed by the tracking unit to obtain the region of interest of the user, and then the text information in the region of interest is acquired by the acquiring unit, and the text information is cut by the word-cutting unit.
  • a word operation to obtain a candidate term such that the selection unit can select at least one candidate term as a new word and/or a hot word, the text of interest of the user extracted by the region of interest of the user's current reading behavior
  • the information is used to perform the acquisition operation of the candidate term, and therefore, the new word and/or the hot word can be recognized in time based on the text information, thereby improving the timeliness of the term acquisition.
  • the tracking unit 21 may specifically perform a tracking operation on the user's eye on the user interface.
  • the user interface may be a World Wide Web (Web) page displayed by the terminal, or may also be an application document displayed by the terminal, for example, an email, a WORD document, a TXT document, a PDF document, etc., the present invention This is not particularly limited.
  • the tracking unit 21 may be specifically configured to acquire video information of the eyeball; and determine, according to the video information, a location area of the eyeball; Video information, determining a movable path of the eyeball, and determining a movable area of the eyeball according to the movable path; and determining the eyeball according to a positional area of the eyeball and a movable area of the eyeball The area of interest, as the area of interest of the user.
  • the video information of the eyeball may be composed of a plurality of frame images, and may be collected by using a camera. Since the motion arc of the human eye is in a fixed interval, the movable path corresponding to the eyeball can be determined based on the video information. The motion path can be an exact value or a motion interval. From the movable path, the reachable area based on the movable path strength can be further calculated, which is the movable area of the eyeball.
  • the tracking unit 21 may specifically determine a portion of the eyeball in a movable region of the eyeball as a region of interest of the eyeball; if the region of interest of the eyeball satisfies a condition of interest, determining The region of interest of the eyeball is the region of interest of the user.
  • the attention condition may include, but is not limited to, at least one of a attention time and a frequency of interest. For example, if the staying area of the eyeball in the movable area of the eyeball is greater than or equal to 3 seconds, the tracking unit 21 may determine that the attention area of the eyeball is the user's area of interest.
  • the tracking unit 21 may determine the region of interest of the eyeball. Is the area of interest of the user.
  • the acquiring unit 22 may obtain the text information in the region of interest by using various text recognition methods in the prior art. This is not particularly limited.
  • the acquiring unit 22 may acquire a partial screenshot of the region of interest surrounded by a user interface having text information, and then, may perform text recognition on the obtained partial screenshot to obtain the interested Text information within the area.
  • the acquiring unit 22 may acquire location information of the region of interest, and determine corresponding text information as text information in the region of interest according to the location information.
  • the word-cutting unit 23 may perform a word-cutting operation on the obtained text information by using various word-cutting methods in the prior art.
  • the word segmentation method based on string matching, or, for example, a word segmentation method based on understanding, or, for example, a statistical word segmentation method is not particularly limited in the present invention.
  • the selecting unit 24 may be specifically configured to determine a candidate term that does not appear in the pre-configured input method dictionary as a new word.
  • the selecting unit 24 may acquire any candidate term in the candidate term obtained by the word-cutting operation; if the candidate term does not appear in the pre-configured input method dictionary, the candidate term may be Determined to be a new word.
  • pre-configured input method dictionary may be configured on the server on the network side, or may be configured on the local client. This embodiment does not specifically limit this.
  • the selecting unit 24 may be specifically configured to determine a candidate term that appears in a pre-configured input method dictionary as a candidate hot word; The word frequency of the selected hot word is determined, and the heat value of the hot word is determined; and the candidate hot word whose heat value is greater than or equal to the heat value is determined as a hot word.
  • the selecting unit 24 may obtain any candidate term in the candidate term obtained by the word-cutting operation; if the candidate term has appeared in the pre-configured input method dictionary, the candidate term may be Marking as a candidate hot word; then, according to the input method dictionary, obtaining a word frequency of the candidate hot word within a specified time range, and determining a heat value of the candidate hot word according to the word frequency; finally, A candidate hot word whose heat value is greater than or equal to the heat threshold is determined as a hot word.
  • the heat value of the candidate hot words (the average score of all candidate hot words * the average word frequency of all candidate hot words + the score of the candidate hot words * the total word frequency of the candidate hot words in the total statistical time) I (the average word frequency of all candidate hot words + the total word frequency of the candidate hot words in the total statistical time), determine the heat value of the candidate hot words. among them,
  • Score of candidate hot words word frequency/candidate of candidate hot words in the most recent unit statistical time The total word frequency of the hot words in the total statistical time.
  • the acquiring device of the term provided by the embodiment may further use the term to update the local input method dictionary, or may further utilize the terms.
  • the input method dictionary of the cloud (network side) is updated, which is not particularly limited in this embodiment.
  • the local input method dictionary or the input method dictionary of the cloud may be updated by using at least one of the statistical Ngram information and/or the Npos information.
  • the technical solution provided in this embodiment can not only identify new words and/or hot words for one user, but also effectively organize and analyze the recognition results of multiple users for multiple users. , to get new words and / or hot words for multiple users.
  • the acquiring device of the term provided by the embodiment may further perform special presentation on the selected new word and/or hot word.
  • icon characters may be added to these new words and/or hot words; or, for example, these new words and/or hot words may be presented at particular candidate locations.
  • the tracking operation of the user's eyeball is performed by the tracking unit to obtain the region of interest of the user, and then the text information in the region of interest is acquired by the acquiring unit, and the text is read by the word-cutting unit.
  • the information is subjected to a word-cutting operation to obtain a candidate term, so that the selecting unit can select at least one candidate term as a new word and/or a hot word, and the user sense extracted by the region of interest of the user's current reading behavior
  • the text information of interest is used to perform the acquisition operation of the candidate term. Therefore, new words and/or hot words can be recognized in time based on the text information, thereby improving the timeliness of the term acquisition.
  • the newly identified new one can be utilized in time. Words and/or hot words update the various professional dictionaries loaded by the input method, that is, the input method dictionary, which can further effectively improve the accuracy of the input method dictionary.
  • the disclosed system, apparatus and method may be implemented in other ways.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division.
  • there may be another division manner for example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored, or not executed.
  • the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be electrical, mechanical or otherwise.
  • the components displayed as units may or may not be physical units, i.e., may be located in one place, or may be distributed over multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solution of the embodiment.
  • each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of hardware plus software functional units.
  • the above-described integrated unit implemented in the form of a software functional unit can be stored in a computer readable storage medium.
  • the above software functional unit is stored in a storage medium, package A number of instructions are included to cause a computer device (which may be a personal computer, server, or network device, etc.) or a processor to perform some of the steps of the methods described in various embodiments of the present invention.
  • the foregoing storage medium includes: a U disk, a removable hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like, which can store program code. .

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • Software Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

La présente invention concerne un procédé et un appareil d'acquisition d'une entrée. Une opération de suivi est réalisée sur les globes oculaires d'un utilisateur afin d'obtenir une région d'intérêt de l'utilisateur. Des informations de texte dans la région d'intérêt sont alors obtenues. Une opération de segmentation de mots est ensuite réalisée sur les informations de texte pour obtenir les entrées candidates, de sorte qu'au moins une entrée candidate peut être sélectionnée pour servir de mot nouveau et/ou de mot actif. Les informations de texte qui intéressent l'utilisateur sont extraites d'une région observée par l'utilisateur au cours de son comportement de lecture actuel. Une opération d'acquisition d'une entrée candidate est réalisée au moyen des informations de texte, de sorte qu'un mot nouveau et/ou un mot actif peut être identifié dans le temps sur la base des informations de texte, ce qui permet de développer l'opportunité d'acquisition de l'entrée.
PCT/CN2014/085481 2014-02-11 2014-08-29 Procédé et appareil d'acquisition d'une entrée, support de stockage informatique et dispositif associé WO2015120713A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201410047094.8 2014-02-11
CN201410047094.8A CN103823849A (zh) 2014-02-11 2014-02-11 词条的获取方法及装置

Publications (1)

Publication Number Publication Date
WO2015120713A1 true WO2015120713A1 (fr) 2015-08-20

Family

ID=50758913

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2014/085481 WO2015120713A1 (fr) 2014-02-11 2014-08-29 Procédé et appareil d'acquisition d'une entrée, support de stockage informatique et dispositif associé

Country Status (2)

Country Link
CN (1) CN103823849A (fr)
WO (1) WO2015120713A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180107359A1 (en) * 2016-10-18 2018-04-19 Smartisan Digital Co., Ltd. Text processing method and device

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103823849A (zh) * 2014-02-11 2014-05-28 百度在线网络技术（北京）有限公司 词条的获取方法及装置
CN105335416B (zh) * 2014-08-05 2018-11-02 佳能株式会社 内容提取方法、内容提取装置和用于内容提取的系统
CN104484453B (zh) * 2014-12-30 2018-01-26 北京元心科技有限公司 确定网页页面热点区域的方法及装置
CN106257378A (zh) * 2016-07-19 2016-12-28 北京新美互通科技有限公司 一种表情符号输入方法及装置
CN105677018A (zh) * 2015-12-28 2016-06-15 宇龙计算机通信科技(深圳)有限公司 一种屏幕截图方法、装置和电子设备
CN108108017B (zh) * 2017-12-11 2021-03-23 维沃移动通信有限公司 一种搜索信息处理方法及移动终端
CN109325223B (zh) * 2018-07-24 2023-08-25 阿里巴巴（中国）有限公司 文章推荐方法、装置及电子设备
CN110377701B (zh) * 2019-07-02 2022-02-11 北京奇艺世纪科技有限公司 一种热词处理方法、装置、电子设备及存储介质
CN112748809A (zh) * 2019-10-16 2021-05-04 北京搜狗科技发展有限公司 输入法词条的展现方法及装置
CN111626035B (zh) * 2020-04-08 2022-09-02 华为技术有限公司 一种版面分析方法及电子设备
CN114201031A (zh) * 2020-09-17 2022-03-18 北京七鑫易维信息技术有限公司 针对眼动跟踪的时间统计方法及装置

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101364220A (zh) * 2007-11-21 2009-02-11 上海埃帕信息科技有限公司 基于用户特性的词频库的生成方法
CN101567004A (zh) * 2009-02-06 2009-10-28 浙江大学 基于眼球跟踪的英文文本自动摘要方法
CN102163377A (zh) * 2010-02-24 2011-08-24 英特尔公司 面部追踪电子阅读器
CN103336576A (zh) * 2013-06-28 2013-10-02 优视科技有限公司 一种基于眼动追踪进行浏览器操作的方法及装置
CN103345305A (zh) * 2013-07-22 2013-10-09 百度在线网络技术（北京）有限公司 用于移动终端输入法的候选词控制方法、装置和移动终端
CN103823849A (zh) * 2014-02-11 2014-05-28 百度在线网络技术（北京）有限公司 词条的获取方法及装置

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101119334A (zh) * 2007-09-21 2008-02-06 腾讯科技（深圳）有限公司 一种获取新词的方法、系统及设备
CN103300815B (zh) * 2012-03-15 2015-05-13 凹凸电子（武汉）有限公司 眼球关注点确定方法、装置和系统
CN103440038B (zh) * 2013-08-28 2016-06-15 中国人民大学 一种基于眼部识别的信息采集系统及其应用

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101364220A (zh) * 2007-11-21 2009-02-11 上海埃帕信息科技有限公司 基于用户特性的词频库的生成方法
CN101567004A (zh) * 2009-02-06 2009-10-28 浙江大学 基于眼球跟踪的英文文本自动摘要方法
CN102163377A (zh) * 2010-02-24 2011-08-24 英特尔公司 面部追踪电子阅读器
CN103336576A (zh) * 2013-06-28 2013-10-02 优视科技有限公司 一种基于眼动追踪进行浏览器操作的方法及装置
CN103345305A (zh) * 2013-07-22 2013-10-09 百度在线网络技术（北京）有限公司 用于移动终端输入法的候选词控制方法、装置和移动终端
CN103823849A (zh) * 2014-02-11 2014-05-28 百度在线网络技术（北京）有限公司 词条的获取方法及装置

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180107359A1 (en) * 2016-10-18 2018-04-19 Smartisan Digital Co., Ltd. Text processing method and device
US10489047B2 (en) * 2016-10-18 2019-11-26 Beijing Bytedance Network Technology Co Ltd. Text processing method and device

Also Published As

Publication number Publication date
CN103823849A (zh) 2014-05-28

Similar Documents

Publication Publication Date Title
WO2015120713A1 (fr) Procédé et appareil d'acquisition d'une entrée, support de stockage informatique et dispositif associé
JP6114403B2 (ja) 入力文字列に対応する入力候補アイテムを提供する方法及び装置
US9230035B2 (en) Pushing specific content to a predetermined webpage
US9965569B2 (en) Truncated autosuggest on a touchscreen computing device
EP3872652B1 (fr) Procédé et appareil de traitement vidéo, dispositif électronique, support et produit
CN105183761B (zh) 敏感词替换方法和装置
KR101911999B1 (ko) 피처 기반 후보 선택 기법
CN106095845B (zh) 文本分类方法和装置
US20160140136A1 (en) Search Recommendation Method and Apparatus
KR20210000326A (ko) 모바일 비디오 서치 기법
JP2015179497A (ja) 入力方法及びシステム
CN109325223B (zh) 文章推荐方法、装置及电子设备
US20140184514A1 (en) Input processing method and apparatus
US10002610B2 (en) Presentation supporting device, presentation supporting method, and computer-readable recording medium
WO2022042401A1 (fr) Procédé et appareil de publication de contenu multimédia, dispositif électronique et support de stockage
EP2828769A1 (fr) Procédé et système de prédiction de mots dans un message
US11080348B2 (en) System and method for user-oriented topic selection and browsing
JP6419969B2 (ja) 画像の提示情報を提供するための方法及び機器
WO2015131510A1 (fr) Procédé et système de poussée de ressource d'entrée, support d'informations et dispositif
CN103678460B (zh) 用于识别适于在多语言环境中进行通信的非文本元素的方法和系统
US20150154287A1 (en) Method for providing recommend information for mobile terminal browser and system using the same
JP2024064941A (ja) 表示方法、装置、ペン型電子辞書、電子機器及び記憶媒体
CN114244795B (zh) 一种信息的推送方法、装置、设备及介质
CN115248890B (zh) 用户兴趣画像的生成方法、装置、电子设备以及存储介质
JP6457058B1 (ja) 知的財産システム、知的財産支援方法および知的財産支援プログラム

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: 14882332

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 14882332

Country of ref document: EP

Kind code of ref document: A1