WO2017071190A1 - 输入数据的处理方法、装置、设备及非易失性计算机存储介质 - Google Patents

输入数据的处理方法、装置、设备及非易失性计算机存储介质 Download PDF

Info

Publication number
WO2017071190A1
WO2017071190A1 PCT/CN2016/083003 CN2016083003W WO2017071190A1 WO 2017071190 A1 WO2017071190 A1 WO 2017071190A1 CN 2016083003 W CN2016083003 W CN 2016083003W WO 2017071190 A1 WO2017071190 A1 WO 2017071190A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
data
input data
input
obtaining
Prior art date
Application number
PCT/CN2016/083003
Other languages
English (en)
French (fr)
Inventor
卜庆晗
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
Priority to JP2017547516A priority Critical patent/JP2018508080A/ja
Priority to EP16858634.5A priority patent/EP3370136A4/en
Priority to US15/743,268 priority patent/US20180210875A1/en
Publication of WO2017071190A1 publication Critical patent/WO2017071190A1/zh

Links

Images

Classifications

    • 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
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00Handling natural language data
    • G06F40/30Semantic analysis
    • 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
    • G06F40/00Handling natural language data
    • G06F40/20Natural language analysis
    • G06F40/205Parsing
    • 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
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00Network arrangements or protocols for supporting network services or applications
    • H04L67/50Network services
    • H04L67/55Push-based network services
    • 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
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00Network arrangements or protocols for supporting network services or applications
    • H04L67/50Network services
    • H04L67/52Network services specially adapted for the location of the user terminal

Definitions

  • the present disclosure relates to input method technologies, and in particular, to a method, an apparatus, a device, and a non-volatile computer storage medium for processing input data.
  • the input method refers to the encoding method used to input various characters into the terminal.
  • the client of the input method software can provide a candidate matching the sequence of characters according to the sequence of characters input by the user, so that the user can select the upper screen.
  • the order in which the candidates are provided by the client is related to the number of times the candidate is on the screen.
  • aspects of the present disclosure provide a method, apparatus, device, and non-processing method for input data Volatile computer storage media to increase the flexibility of processing input data.
  • An aspect of the present disclosure provides a method for processing input data, including:
  • the push information is provided to the user.
  • the acquiring at least one input data of the user includes:
  • obtaining the semantic data according to the at least one input data comprises:
  • the semantic data is obtained according to the word bag of each of the input data.
  • a word bag of each of the input data is obtained according to each of the input data, or the each input data and the preset extension data.
  • the input data comprising at least one of the following data:
  • the location data of the user includes at least one of the following data:
  • a processing apparatus for inputting data includes:
  • An obtaining unit configured to acquire at least one input data of the user
  • a parsing unit configured to obtain semantic data according to the at least one input data
  • a matching unit configured to obtain push information according to the semantic data
  • a pushing unit configured to provide the push information to the user.
  • any possible implementation manner further provide an implementation manner, where the acquiring unit is specifically configured to
  • parsing unit is specifically configured to
  • the semantic data is obtained according to the word bag of each of the input data.
  • parsing unit is specifically configured to
  • a word bag of each of the input data is obtained according to each of the input data, or the each input data and the preset extension data.
  • the input data comprising at least one of the following data:
  • the location data of the user includes at least one of the following data:
  • an apparatus comprising:
  • One or more processors are One or more processors;
  • One or more programs the one or more programs being stored in the memory, When executed by the one or more processors:
  • the push information is provided to the user.
  • a non-volatile computer storage medium storing one or more programs when the one or more programs are executed by one device causes The device:
  • the push information is provided to the user.
  • the embodiment of the present disclosure obtains semantic data according to the at least one input data by acquiring at least one input data of the user, so that the push information can be obtained according to the semantic data, and the push information is provided.
  • the user input data is not directly considered when acquiring the push information, but the semantic data obtained according to the user's input data is considered, so that the push information provided to the user can be more in line with the user's intention. This increases the flexibility of the processing of the input data.
  • the obtained according to the input data of the user is considered.
  • the semantic data makes the push information provided to the user more in line with the user's intention. Therefore, the push information can be made more likely to cause additional attention of the user, and the scalability of the processing of the input data can be effectively improved.
  • the semantic data obtained according to the input data of the user is considered, so that the push provided to the user is made.
  • the information can be more consistent with the user's intention, and is directly selected by the user, which can effectively improve the efficiency of the processing of the input data.
  • the semantic data obtained according to the input data of the user is considered, so that the push provided to the user is made.
  • the information can be more in line with the user's intention without the user having to input additional input data to obtain other push information, which can effectively improve the reliability of the processing of the input data.
  • FIG. 1 is a schematic flowchart of a method for processing input data according to an embodiment of the present disclosure
  • FIG. 2 is a schematic structural diagram of an apparatus for processing input data according to another embodiment of the present disclosure.
  • the terminals involved in the embodiments of the present disclosure 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 (Personal Computer, PC). ), MP3 player, MP4 player, wearable device (for example, smart glasses, smart watches, smart bracelets, etc.).
  • PDA personal digital assistant
  • PC Personal Computer
  • MP3 player for example, smart glasses, smart watches, smart bracelets, etc.
  • wearable device for example, smart glasses, smart watches, smart bracelets, etc.
  • FIG. 1 is a schematic flowchart of a method for processing input data according to an embodiment of the present disclosure, as shown in FIG. 1 .
  • execution entities of 101 to 104 may be applications located in a local terminal, for example, an input method application, or the like, or may be a plug-in or a software development kit installed in an application located in the local terminal (
  • the functional unit, such as the software development kit (SDK) may also be a processing engine located in the network side server, or may be a distributed system located on the network side, which is not specifically limited in this embodiment.
  • the input method refers to the encoding method used to input various characters into the terminal.
  • the input method application can display a plurality of candidates corresponding to the character sequence to the user according to the sequence of characters input by the user, so that the user can select a candidate to complete the input operation, for example, the upper screen operation.
  • the application may be a local application (nativeApp) installed on the terminal, or may be a web application (webApp) of the browser on the terminal, which is not specifically limited in this embodiment.
  • the push information can be obtained according to the semantic data, and the push information is provided to the user, because the push information is acquired.
  • the semantic data obtained according to the user's input data is considered, so that the push information provided to the user can be more in line with the user's intention, thereby improving the processing of the input data. flexibility.
  • the acquired input data may include, but is not limited to, at least one of the following data:
  • the so-called user input sequence refers to the sequence in which the user applies the publication (ie, the upper screen) using the input method. It can be understood that the so-called one input sequence may be a single input sequence of one input, or may be a combined data sequence of multiple consecutive inputs, which is not particularly limited in this embodiment.
  • the character sequence input by the user may be correspondingly processed according to the input intention of the user to obtain an input sequence.
  • the sequence of characters of the user may include, but is not limited to, text, which is not specifically limited in this embodiment.
  • the user may input a sequence of characters corresponding to different languages in the input box provided by the application, and the text may be a pinyin sequence, or may be a Roman sequence, or may be a sequence of glyphs, etc., which is not performed in this embodiment. Specially limited.
  • the input intention is to input characters of various languages such as Chinese characters, then, specifically, the sequence of characters such as the collected pinyin sequence, Roman sequence or glyph sequence may be encoded to obtain corresponding numbers.
  • the selection instruction input by the user one candidate is selected from a plurality of candidates to perform the upper screen operation as all or part of the input sequence.
  • the character sequence may be directly processed correspondingly to obtain a processing result.
  • the pair of characters The sequence is encoded to obtain a corresponding plurality of candidates, and then a candidate is selected from a plurality of candidates according to a selection instruction input by the user to perform an upper screen operation as all or a part of the input sequence.
  • the character sequence may be sent to the cloud server, and the character sequence is processed by the cloud server, and the processing result is returned.
  • the cloud server encodes the character sequence to obtain a corresponding plurality of candidates, and then selects one candidate from among the plurality of candidates according to the selection instruction input by the user, as all or part of the input sequence, and The input sequence returns and the upper screen operation is performed.
  • This embodiment is not particularly limited to the above two cases.
  • the so-called location data of the user refers to data capable of identifying the location where the user is located, for example, geographical location data such as longitude and latitude, or text location data such as a POI name, etc., etc. limited.
  • the location data of the user may include, but is not limited to, at least one of the following data:
  • location data than the location data corresponding to the user's input sequence, for example, location data at any time.
  • the user when the user uses the input method to apply an output sequence (ie, on the screen), the user can invoke the interface provided by the terminal to obtain the geographic location data of the location where the terminal is located. Then, the acquired geographic location data is followed by the input sequence published by the user. Send in a pre-defined format. After receiving the input sequence and the position data corresponding to the input sequence, that is, the input data, the input data is stored in the database.
  • the filtering process may include, but is not limited to, at least one of conventional noise cleaning, part of speech classification, and word sequence conversion.
  • each input sequence of the user is processed by the above process. After each input sequence of the user and the position data corresponding to the input sequence, that is, input data, it is determined whether the user has accumulated enough input data in a unit time to satisfy a preset restriction condition, for example, reaching a certain limit. The number of screens, the number of whole sentences, or any combination of the above, and so on. If the constraint is met, then all of the input data stored by the user in the database can be called up as at least one input data of the user acquired in 101.
  • At least one input data of the user that is consecutive in time may be acquired.
  • these input data can be continuous in time.
  • a sentence that the user inputs continuously without interruption can be used as the input data of the user. In this way, it is possible to ensure the consistency and consistency of the input data input by the user in expressing semantics.
  • the word bag of each input data may be obtained according to each input data of the at least one input data, and then, The semantic data is obtained according to the word bag of each of the input data.
  • the so-called semantic data refers to some data used to express the intention of the user's behavior.
  • each word in the text is independent, independent of whether other words appear, or when the author of this article chooses a vocabulary at any position and is independent of the previous sentence.
  • the word bag of each input data is independent of each other. Therefore, in the process of obtaining semantic data, the weights corresponding to the word bags of each input data are different from each other.
  • the text corresponding to each input data for example, the text corresponding to the input sequence, or, for example, the text corresponding to the location data, and the like, may be subjected to word segmentation processing to obtain a word segmentation result.
  • the word segmentation result is then composed into the word bag of the input data.
  • each word obtained after the word segmentation process is filtered, including but not limited to the following filtering process: filtering the preset The words contained in the stop word list; wherein the general vocabulary is a function word, augmentation, pronoun, article, adverb, modal particle, etc., which are pre-existing based on word frequency, and these words usually do not have independent ideographic ability.
  • the words that have reached the preset high frequency condition in the existing resources may be collected.
  • the auxiliary word "has" has a high frequency of occurrence, but it usually has a low ideographic ability, and therefore, Collected into the stop word list.
  • the word bag of each input data may be obtained according to each input data.
  • the word bag of each input data may be obtained according to each of the input data and the preset extended data.
  • the so-called extended data can be an extended pair of input data - extended text, for example, geographic location data - expansion of hot words equal.
  • the semantic analysis model may be specifically established for the user from multiple dimensions, and the semantic analysis model that is established each time is stored in a structure, and is obtained according to the word bag of each input data. Semantic data, in this way, can predict the behavior of users in larger time and space dimensions.
  • the push information is obtained according to the semantic data, and the push information is provided to the user, because
  • the push information is obtained, the input data of the user is not directly considered, but the semantic data obtained according to the input data of the user is considered, so that the push information provided to the user can be more in line with the intention of the user, thereby improving the input data.
  • the flexibility of processing is not only considered, but the semantic data obtained according to the input data of the user is considered, so that the push information provided to the user can be more in line with the intention of the user, thereby improving the input data.
  • the semantic data obtained according to the input data of the user is considered, so that the push provided to the user is made.
  • the information can be more in line with the user's intention, and therefore, the push information can be made more likely to cause additional attention of the user, and the scalability of the processing of the input data can be effectively improved.
  • the semantic data obtained according to the input data of the user is considered, so that the push provided to the user is made.
  • the information can be more consistent with the user's intention, and is directly selected by the user, which can effectively improve the efficiency of the processing of the input data.
  • the semantic data obtained according to the input data of the user is considered, so that the push provided to the user is made.
  • Information can be more in line with the user's intentions The figure can be used to effectively improve the reliability of the processing of the input data without requiring the user to input additional input data to obtain other push information.
  • the processing device for input data of the present embodiment may include an acquisition unit 21, a parsing unit 22, a matching unit 23, and a push unit 24.
  • the obtaining unit 21 is configured to obtain at least one input data of the user;
  • the parsing unit 22 is configured to obtain semantic data according to the at least one input data, and
  • the matching unit 23 is configured to obtain the push information according to the semantic data;
  • the pushing unit 24 is configured to provide the push information to the user.
  • part or all of the processing device for input data provided in this embodiment may be an application located in a local terminal, for example, an input method application, or the like, or may be a plug-in disposed in an application located in the local terminal or Functional units such as the Software Development Kit (SDK), or may be located on the network side server
  • SDK Software Development Kit
  • the processing engine in the process may be a distributed system located on the network side, which is not specifically limited in this embodiment.
  • the input method refers to the encoding method used to input various characters into the terminal.
  • the input method application can display a number of candidates corresponding to the input sequence to the user according to the sequence of characters input by the user, so that the user can select a candidate to complete the input operation, for example, the upper screen operation.
  • the application may be a local application (nativeApp) installed on the terminal, or may be a web application (webApp) of the browser on the terminal, which is not specifically limited in this embodiment.
  • the acquiring unit 21 may be specifically configured to acquire at least one input data of the user that is consecutive in time.
  • the parsing unit 22 may be configured to obtain a word bag of each input data according to each input data in the at least one input data. And obtaining the semantic data according to the word bag of each of the input data.
  • the parsing unit 22 may be specifically configured to obtain a word bag of each input data according to each of the input data, or the each input data and the preset extended data.
  • the input data acquired by the acquiring unit 21 may include, but is not limited to, at least one of the following data:
  • the location data of the user may include, but is not limited to, at least one of the following data:
  • At least one input data of the user is acquired by the obtaining unit, and then the parsing unit obtains the semantic data according to the at least one input data, so that the matching unit can obtain the push information according to the semantic data, and is pushed by the pushing unit.
  • the parsing unit obtains the semantic data according to the at least one input data, so that the matching unit can obtain the push information according to the semantic data, and is pushed by the pushing unit.
  • the semantic data obtained according to the input data of the user is considered, so that the push provided to the user is made.
  • the information can be more in line with the user's intention, and therefore, the push information can be made more likely to cause additional attention of the user, and the scalability of the processing of the input data can be effectively improved.
  • the semantic data obtained according to the input data of the user is considered, so that the push provided to the user is made.
  • Information can be more in line with the user's intentions
  • the figure, which is directly selected by the user can effectively improve the efficiency of the processing of the input data.
  • the semantic data obtained according to the input data of the user is considered, so that the push provided to the user is made.
  • the information can be more in line with the user's intention without the user having to input additional input data to obtain other push information, which can effectively improve the reliability of the processing of the input data.
  • the disclosed system, apparatus, and method may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division.
  • multiple units or components may be combined. Or it can be integrated into another system, or some features can be ignored or not executed.
  • the mutual 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 in an electrical, mechanical or other form.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Can choose according to actual needs Some or all of the units are used to achieve the objectives of the solution of the embodiment.
  • each functional unit in various embodiments of the present disclosure 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 and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor to perform the methods of the various embodiments of the present disclosure. Part of the steps.
  • the foregoing storage medium includes: a U disk, a mobile 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 codes. .

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Artificial Intelligence (AREA)
  • Human Computer Interaction (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • User Interface Of Digital Computer (AREA)
  • Machine Translation (AREA)

Abstract

本公开提供一种输入数据的处理方法、装置、设备及非易失性计算机存储介质。本公开实施例通过获取用户的至少一个输入数据,进而根据所述至少一个输入数据,获得语意数据,使得能够根据所述语意数据,获得推送信息,并将该推送信息提供给用户,由于在获取推送信息时,并不是直接考虑用户的输入数据,而是考虑根据用户的输入数据所获得的语意数据,因此,使得向用户所提供的推送信息能够更加符合用户的意图,从而提高了输入数据的处理的灵活性。

Description

输入数据的处理方法、装置、设备及非易失性计算机存储介质
本申请要求了申请日为2015年10月26日,申请号为201510702341.8发明名称为“输入数据的处理方法及装置”的中国专利申请的优先权。
技术领域
本公开涉及输入法技术,尤其涉及一种输入数据的处理方法、装置、设备及非易失性计算机存储介质。
背景技术
输入法,是指为将各种字符输入终端而采用的编码方法,不同语言、国家、或地区,有多种不同的输入法,例如,搜狗拼音输入法、百度输入法、QQ拼音输入法等。一般来说,输入法软件的客户端可以根据用户输入的字符序列,提供与该字符序列匹配的候选项,以供用户进行上屏选择。其中,客户端所提供的候选项的排列顺序与候选项的上屏次数有关。
然而,现有技术提供的技术方案,只能够提供与该字符序列匹配的候选项,且候选项的排列顺序与候选项的上屏次数有关,从而导致了输入数据的处理的灵活性的降低。
发明内容
本公开的多个方面提供一种输入数据的处理方法、装置、设备及非 易失性计算机存储介质,用以提高输入数据的处理的灵活性。
本公开的一方面,提供一种输入数据的处理方法,包括:
获取用户的至少一个输入数据;
根据所述至少一个输入数据,获得语意数据;
根据所述语意数据,获得推送信息;
向所述用户提供所述推送信息。
如上所述的方面和任一可能的实现方式,进一步提供一种实现方式,所述获取用户的至少一个输入数据,包括:
获取所述用户的在时间上连续的至少一个输入数据。
如上所述的方面和任一可能的实现方式,进一步提供一种实现方式,所述根据所述至少一个输入数据,获得语意数据,包括:
根据所述至少一个输入数据中每个输入数据,获得所述每个输入数据的词袋;
根据所述每个输入数据的词袋,获得所述语意数据。
如上所述的方面和任一可能的实现方式,进一步提供一种实现方式,所述根据所述至少一个输入数据中每个输入数据,获得所述每个输入数据的词袋,包括:
根据所述每个输入数据,或者所述每个输入数据和预先设置的扩展数据,获得所述每个输入数据的词袋。
如上所述的方面和任一可能的实现方式,进一步提供一种实现方式,所述输入数据包括下列数据中的至少一项:
用户的输入序列;以及
用户的位置数据。
如上所述的方面和任一可能的实现方式,进一步提供一种实现方式,所述用户的位置数据包括下列数据中的至少一项:
用户的输入序列所对应的位置数据;以及
除了用户的输入序列所对应的位置数据之外的其他位置数据。
本公开的另一方面,提供一种输入数据的处理装置,包括:
获取单元,用于获取用户的至少一个输入数据;
解析单元,用于根据所述至少一个输入数据,获得语意数据;
匹配单元,用于根据所述语意数据,获得推送信息;
推送单元,用于向所述用户提供所述推送信息。
如上所述的方面和任一可能的实现方式,进一步提供一种实现方式,所述获取单元,具体用于
获取所述用户的在时间上连续的至少一个输入数据。
如上所述的方面和任一可能的实现方式,进一步提供一种实现方式,所述解析单元,具体用于
根据所述至少一个输入数据中每个输入数据,获得所述每个输入数据的词袋;以及
根据所述每个输入数据的词袋,获得所述语意数据。
如上所述的方面和任一可能的实现方式,进一步提供一种实现方式,所述解析单元,具体用于
根据所述每个输入数据,或者所述每个输入数据和预先设置的扩展数据,获得所述每个输入数据的词袋。
如上所述的方面和任一可能的实现方式,进一步提供一种实现方式,所述输入数据包括下列数据中的至少一项:
用户的输入序列;以及
用户的位置数据。
如上所述的方面和任一可能的实现方式,进一步提供一种实现方式,所述用户的位置数据包括下列数据中的至少一项:
用户的输入序列所对应的位置数据;以及
除了用户的输入序列所对应的位置数据之外的其他位置数据。
本公开的另一方面,提供一种设备,包括:
一个或者多个处理器;
存储器;
一个或者多个程序,所述一个或者多个程序存储在所述存储器中, 当被所述一个或者多个处理器执行时:
获取用户的至少一个输入数据;
根据所述至少一个输入数据,获得语意数据;
根据所述语意数据,获得推送信息;
向所述用户提供所述推送信息。
本公开的另一方面,提供一种非易失性计算机存储介质,所述非易失性计算机存储介质存储有一个或者多个程序,当所述一个或者多个程序被一个设备执行时,使得所述设备:
获取用户的至少一个输入数据;
根据所述至少一个输入数据,获得语意数据;
根据所述语意数据,获得推送信息;
向所述用户提供所述推送信息。
由上述技术方案可知,本公开实施例通过获取用户的至少一个输入数据,进而根据所述至少一个输入数据,获得语意数据,使得能够根据所述语意数据,获得推送信息,并将该推送信息提供给用户,由于在获取推送信息时,并不是直接考虑用户的输入数据,而是考虑根据用户的输入数据所获得的语意数据,因此,使得向用户所提供的推送信息能够更加符合用户的意图,从而提高了输入数据的处理的灵活性。
另外,采用本公开所提供的技术方案,由于在获取推送信息时,并不是直接考虑用户的输入数据,而是考虑根据用户的输入数据所获得的 语意数据,因此,使得向用户所提供的推送信息能够更加符合用户的意图,因此,能够使得推送信息更容易引起用户额外的关注,能够有效地提高输入数据的处理的可扩展性。
另外,采用本公开所提供的技术方案,由于在获取推送信息时,并不是直接考虑用户的输入数据,而是考虑根据用户的输入数据所获得的语意数据,因此,使得向用户所提供的推送信息能够更加符合用户的意图,而被用户直接选中,能够有效地提高输入数据的处理的效率。
另外,采用本公开所提供的技术方案,由于在获取推送信息时,并不是直接考虑用户的输入数据,而是考虑根据用户的输入数据所获得的语意数据,因此,使得向用户所提供的推送信息能够更加符合用户的意图,而无需用户再输入额外的输入数据以获取其他推送信息,能够有效地提高输入数据的处理的可靠性。
另外,采用本公开所提供的技术方案,在提供基本的信息输入功能的同时,还可以进一步提供与输入行为相关的其他推送信息,例如,广告、游戏或应用程序等,能够有效地提高用户的体验。
附图说明
为了更清楚地说明本公开实施例中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作一简单地介绍,显而易见地,下面描述中的附图是本公开的一些实施例,对于本领域普通技术人员来讲, 在不付出创造性劳动性的前提下,还可以根据这些附图获得其他的附图。
图1为本公开一实施例提供的输入数据的处理方法的流程示意图;
图2为本公开另一实施例提供的输入数据的处理装置的结构示意图。
具体实施方式
为使本公开实施例的目的、技术方案和优点更加清楚,下面将结合本公开实施例中的附图,对本公开实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例是本公开一部分实施例,而不是全部的实施例。基于本公开中的实施例,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全部其他实施例,都属于本公开保护的范围。
需要说明的是,本公开实施例中所涉及的终端可以包括但不限于手机、个人数字助理(Personal Digital Assistant,PDA)、无线手持设备、平板电脑(Tablet Computer)、个人电脑(Personal Computer,PC)、MP3播放器、MP4播放器、可穿戴设备(例如,智能眼镜、智能手表、智能手环等)等。
另外,本文中术语“和/或”,仅仅是一种描述关联对象的关联关系,表示可以存在三种关系,例如,A和/或B,可以表示:单独存在A,同时存在A和B,单独存在B这三种情况。另外,本文中字符“/”,一般表示前后关联对象是一种“或”的关系。
图1为本公开一实施例提供的输入数据的处理方法的流程示意图,如图1所示。
101、获取用户的至少一个输入数据。
102、根据所述至少一个输入数据,获得语意数据。
103、根据所述语意数据,获得推送信息。
104、向所述用户提供所述推送信息。
需要说明的是,101~104的执行主体的部分或全部可以为位于本地终端的应用,例如,输入法应用等,或者还可以为设置在位于本地终端的应用中的插件或软件开发工具包(Software Development Kit,SDK)等功能单元,或者还可以为位于网络侧服务器中的处理引擎,或者还可以为位于网络侧的分布式系统,本实施例对此不进行特别限定。
输入法,是指为将各种字符输入终端而采用的编码方法,不同语言、国家、或地区,有多种不同的输入法,例如,搜狗拼音输入法、百度输入法、QQ拼音输入法等。一般来说,输入法应用可以根据用户输入的字符序列,向用户展现与该字符序列对应的若干个候选项,以供用户选择一个候选项完成输入操作,例如,上屏操作。
可以理解的是,所述应用可以是安装在终端上的本地程序(nativeApp),或者还可以是终端上的浏览器的一个网页程序(webApp),本实施例对此不进行特别限定。
这样,通过获取用户的至少一个输入数据,进而根据所述至少一个输入数据,获得语意数据,使得能够根据所述语意数据,获得推送信息,并将该推送信息提供给用户,由于在获取推送信息时,并不是直接考虑用户的输入数据,而是考虑根据用户的输入数据所获得的语意数据,因此,使得向用户所提供的推送信息能够更加符合用户的意图,从而提高了输入数据的处理的灵活性。
可选地,在本实施例的一个可能的实现方式中,在101中,所获取的所述输入数据可以包括但不限于下列数据中的至少一项:
用户的输入序列;以及
用户的位置数据。
所谓的用户的输入序列,是指用户使用输入法应用发布(即上屏)的序列。可以理解的是,所谓的一个输入序列,可以是一次输入的单独输入序列,或者还可以是多次连续输入的组合数据序列,本实施例对此不进行特别限定。
具体地,具体可以根据用户的输入意图,对用户输入的字符序列进行相应的处理,以获得输入序列。
在一个具体的实现过程中,所述用户的字符序列可以包括但不限于文本,本实施例对此不进行特别限定。例如,用户可以在应用所提供的输入框中输入不同语言所对应的字符序列,该文本可以为拼音序列,或者还可以为罗马序列,或者还可以为字形序列等,本实施例对此不进行特别限定。
在另一个具体的实现过程中,输入意图为输入汉字等各种语言的字符,那么,则具体可以对所采集的拼音序列、罗马序列或字形序列等字符序列进行编码处理,以获得对应的若干个候选项,进而根据用户输入的选择指令,从若干个候选项中选择一个候选项,以作为输入序列的全部或者一部分,执行上屏操作。
需要说明的是,在101中,针对执行主体为输入法应用的情况,还需要分为本地输入法应用和云输入法应用两种情况分别进行如下特别说明。
情况一,当输入法应用为本地输入法应用时,在101中,具体可以直接对所述字符序列进行相应的处理,以获得处理结果。例如,对字符 序列进行编码处理,以获得对应的若干个候选项,进而根据用户输入的选择指令,从若干个候选项中选择一个候选项,以作为输入序列的全部或者一部分,执行上屏操作。
情况二,当输入法应用为云输入法应用时,在101中,具体可以将字符序列发送给云服务器,由云服务器对所述字符序列进行相应的处理,进而将处理结果返回。例如,云服务器对字符序列进行编码处理,以获得对应的若干个候选项,进而根据用户输入的选择指令,从若干个候选项中选择一个候选项,以作为输入序列的全部或者一部分,并将输入序列返回,执行上屏操作。
本实施例对上述两种情况并没有进行特别限定。
所谓的用户的位置数据,是指能够标识用户所在的位置的数据,例如,经度和纬度等地理位置数据,或者再例如,POI名称等文本位置数据,等等,本实施例对此不进行特别限定。
其中,所述用户的位置数据可以包括但不限于下列数据中的至少一项:
用户的输入序列所对应的位置数据;以及
除了用户的输入序列所对应的位置数据之外的其他位置数据,例如,任意时刻的位置数据。
以用户的输入序列所对应的位置数据作为举例,下面详细说明如何获取输入数据。
在一个具体的实现过程中,用户使用输入法应用发布(即上屏)一个输入序列时,可以调用终端所提供的接口获取该终端所在的位置的地理位置数据。然后,将所获取的地理位置数据随用户所发布的输入序列, 以预先定义好的格式,进行发送。接收到输入序列和该输入序列所对应的位置数据即输入数据之后,再将这些输入数据存储到数据库。
在将上述输入数据存储到数据库之前,还可以进一步执行一个过滤流程,来过滤输入序列。该过滤流程可以包括但不限于常规噪音清理、词性分类、词序列转换中的至少一项。
用户的每个输入数列的操作,均由上述过程,进行处理。在每个接收到用户的输入序列和该输入序列所对应的位置数据即输入数据之后,都会判断该用户是否已经在单位时间内累计足够的输入数据满足预先设置的限制条件,例如,达到一定的上屏次数、达到一定的整句数目、或以上的任意组合,等等。如果满足限制条件,那么,则可以将该用户在数据库中所存储的全部输入数据调出,以作为101中所获取的用户的至少一个输入数据。
可选地,在本实施例的一个可能的实现方式中,在101中,具体地,具体可以获取所述用户的在时间上连续的至少一个输入数据。在该实现过程中,这些输入数据,可以在时间上是连续的。例如,用户连续不间断地所输入的一句话,可以作为该用户的这些输入数据。这样,能够保证用户所输入的输入数据在表达语意上的连贯性与一致性。
可选地,在本实施例的一个可能的实现方式中,在102中,具体可以根据所述至少一个输入数据中每个输入数据,获得所述每个输入数据的词袋,进而,则可以根据所述每个输入数据的词袋,获得所述语意数据。所谓的语意数据,是指用于表达用户行为意图的一些数据。
在信息检索中,假定对于一个文本即输入序列,忽略其词序、语法和句法,将其仅仅看做是一个词集合,或者说是词的一个组合。所谓的 词集合或者词的组合,可以称之为词袋(Bag of words)。
文本中每个词的出现都是独立的,不依赖于其他词是否出现,或者说当这篇文章的作者在任意一个位置选择一个词汇都不受前面句子的影响而独立选择的。
可以理解的是,每个输入数据的词袋,都是相互独立的。因此,在获得语意数据的过程中,每个输入数据的词袋所对应的权重是互不相同的。
具体地,具体可以对每个输入数据所对应的文本,例如,输入序列所对应的文本,或者再例如,位置数据所对应的文本,等等,进行分词处理,以获得分词结果。然后,将分词结果组成该输入数据的词袋。
在对输入数据所对应的文本进行分词处理后,为了提高后续处理的效率和减小噪音,对分词处理后得到的各词语进行过滤处理,包括但不限于以下所列过滤处理:过滤掉预设的停用词表所包含的词语;其中,通用词表是预先基于词频统计出的虚词、助词、代词、冠词、副词、语气词等,这些词语通常不具备独立表意能力。具体可以通过对已有资源中出现频率达到预设的高频条件的词语进行收集得到,例如,助词“的”具有很高的出现频率,但其通常具有很低的表意能力,因此,将其收集到停用词表中。
在一个具体的实现过程中,具体可以根据所述每个输入数据,获得所述每个输入数据的词袋。
在另一个具体的实现过程中,具体可以根据所述每个输入数据和预先设置的扩展数据,获得所述每个输入数据的词袋。所谓的扩展数据,可以为输入数据-扩展文本的扩展对,例如,地理位置数据-热词的扩展 对等。
在本实现方式中,具体可以从多个维度为用户建立语意解析模型,将每次所建立的语义解析模型存储在一个结构中,用以根据所述每个输入数据的词袋,获得所述语意数据,这样,能够预估用户在更大的时间和空间维度的行为。
本实施例中,通过获取用户的至少一个输入数据,进而根据所述至少一个输入数据,获得语意数据,使得能够根据所述语意数据,获得推送信息,并将该推送信息提供给用户,由于在获取推送信息时,并不是直接考虑用户的输入数据,而是考虑根据用户的输入数据所获得的语意数据,因此,使得向用户所提供的推送信息能够更加符合用户的意图,从而提高了输入数据的处理的灵活性。
另外,采用本公开所提供的技术方案,由于在获取推送信息时,并不是直接考虑用户的输入数据,而是考虑根据用户的输入数据所获得的语意数据,因此,使得向用户所提供的推送信息能够更加符合用户的意图,因此,能够使得推送信息更容易引起用户额外的关注,能够有效地提高输入数据的处理的可扩展性。
另外,采用本公开所提供的技术方案,由于在获取推送信息时,并不是直接考虑用户的输入数据,而是考虑根据用户的输入数据所获得的语意数据,因此,使得向用户所提供的推送信息能够更加符合用户的意图,而被用户直接选中,能够有效地提高输入数据的处理的效率。
另外,采用本公开所提供的技术方案,由于在获取推送信息时,并不是直接考虑用户的输入数据,而是考虑根据用户的输入数据所获得的语意数据,因此,使得向用户所提供的推送信息能够更加符合用户的意 图,而无需用户再输入额外的输入数据以获取其他推送信息,能够有效地提高输入数据的处理的可靠性。
另外,采用本公开所提供的技术方案,在提供基本的信息输入功能的同时,还可以进一步提供与输入行为相关的其他推送信息,例如,广告、游戏或应用程序等,能够有效地提高用户的体验。
需要说明的是,对于前述的各方法实施例,为了简单描述,故将其都表述为一系列的动作组合,但是本领域技术人员应该知悉,本公开并不受所描述的动作顺序的限制,因为依据本公开,某些步骤可以采用其他顺序或者同时进行。其次,本领域技术人员也应该知悉,说明书中所描述的实施例均属于优选实施例,所涉及的动作和模块并不一定是本公开所必须的。
在上述实施例中,对各个实施例的描述都各有侧重,某个实施例中没有详述的部分,可以参见其他实施例的相关描述。
图2为本公开另一实施例提供的输入数据的处理装置的结构示意图,如图2所示。本实施例的输入数据的处理装置可以包括获取单元21、解析单元22、匹配单元23和推送单元24。其中,获取单元21,用于获取用户的至少一个输入数据;解析单元22,用于根据所述至少一个输入数据,获得语意数据;匹配单元23,用于根据所述语意数据,获得推送信息;推送单元24,用于向所述用户提供所述推送信息。
需要说明的是,本实施例所提供的输入数据的处理装置的部分或全部可以为位于本地终端的应用,例如,输入法应用等,或者还可以为设置在位于本地终端的应用中的插件或软件开发工具包(Software Development Kit,SDK)等功能单元,或者还可以为位于网络侧服务器 中的处理引擎,或者还可以为位于网络侧的分布式系统,本实施例对此不进行特别限定。
输入法,是指为将各种字符输入终端而采用的编码方法,不同语言、国家、或地区,有多种不同的输入法,例如,搜狗拼音输入法、百度输入法、QQ拼音输入法等。一般来说,输入法应用可以根据用户输入的字符序列,向用户展现与该输入序列对应的若干个候选项,以供用户选择一个候选项完成输入操作,例如,上屏操作。
可以理解的是,所述应用可以是安装在终端上的本地程序(nativeApp),或者还可以是终端上的浏览器的一个网页程序(webApp),本实施例对此不进行特别限定。
可选地,在本实施例的一个可能的实现方式中,所述获取单元21,具体可以用于获取所述用户的在时间上连续的至少一个输入数据。
可选地,在本实施例的一个可能的实现方式中,所述解析单元22,具体可以用于根据所述至少一个输入数据中每个输入数据,获得所述每个输入数据的词袋;以及根据所述每个输入数据的词袋,获得所述语意数据。
具体地,所述解析单元22,具体可以用于根据所述每个输入数据,或者所述每个输入数据和预先设置的扩展数据,获得所述每个输入数据的词袋。
可选地,在本实施例的一个可能的实现方式中,所述获取单元21所获取的所述输入数据可以包括但不限于下列数据中的至少一项:
用户的输入序列;以及
用户的位置数据。
其中,所述用户的位置数据可以包括但不限于下列数据中的至少一项:
用户的输入序列所对应的位置数据;以及
除了用户的输入序列所对应的位置数据之外的其他位置数据。
需要说明的是,图1对应的实施例中方法,可以由本实施例提供的输入数据的处理装置实现。详细描述可以参见图1对应的实施例中的相关内容,此处不再赘述。
本实施例中,通过获取单元获取用户的至少一个输入数据,进而由解析单元根据所述至少一个输入数据,获得语意数据,使得匹配单元能够根据所述语意数据,获得推送信息,并由推送单元将该推送信息提供给用户,由于在获取推送信息时,并不是直接考虑用户的输入数据,而是考虑根据用户的输入数据所获得的语意数据,因此,使得向用户所提供的推送信息能够更加符合用户的意图,从而提高了输入数据的处理的灵活性。
另外,采用本公开所提供的技术方案,由于在获取推送信息时,并不是直接考虑用户的输入数据,而是考虑根据用户的输入数据所获得的语意数据,因此,使得向用户所提供的推送信息能够更加符合用户的意图,因此,能够使得推送信息更容易引起用户额外的关注,能够有效地提高输入数据的处理的可扩展性。
另外,采用本公开所提供的技术方案,由于在获取推送信息时,并不是直接考虑用户的输入数据,而是考虑根据用户的输入数据所获得的语意数据,因此,使得向用户所提供的推送信息能够更加符合用户的意 图,而被用户直接选中,能够有效地提高输入数据的处理的效率。
另外,采用本公开所提供的技术方案,由于在获取推送信息时,并不是直接考虑用户的输入数据,而是考虑根据用户的输入数据所获得的语意数据,因此,使得向用户所提供的推送信息能够更加符合用户的意图,而无需用户再输入额外的输入数据以获取其他推送信息,能够有效地提高输入数据的处理的可靠性。
另外,采用本公开所提供的技术方案,在提供基本的信息输入功能的同时,还可以进一步提供与输入行为相关的其他推送信息,例如,广告、游戏或应用程序等,能够有效地提高用户的体验。
所属领域的技术人员可以清楚地了解到,为描述的方便和简洁,上述描述的系统,装置和单元的具体工作过程,可以参考前述方法实施例中的对应过程,在此不再赘述。
在本公开所提供的几个实施例中,应该理解到,所揭露的系统,装置和方法,可以通过其它的方式实现。例如,以上所描述的装置实施例仅仅是示意性的,例如,所述单元的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式,例如,多个单元或组件可以结合或者可以集成到另一个系统,或一些特征可以忽略,或不执行。另一点,所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口,装置或单元的间接耦合或通信连接,可以是电性,机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其 中的部分或者全部单元来实现本实施例方案的目的。
另外,在本公开各个实施例中的各功能单元可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现,也可以采用硬件加软件功能单元的形式实现。
上述以软件功能单元的形式实现的集成的单元,可以存储在一个计算机可读取存储介质中。上述软件功能单元存储在一个存储介质中,包括若干指令用以使得一台计算机装置(可以是个人计算机,服务器,或者网络装置等)或处理器(processor)执行本公开各个实施例所述方法的部分步骤。而前述的存储介质包括:U盘、移动硬盘、只读存储器(Read-Only Memory,ROM)、随机存取存储器(Random Access Memory,RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
最后应说明的是:以上实施例仅用以说明本公开的技术方案,而非对其限制;尽管参照前述实施例对本公开进行了详细的说明,本领域的普通技术人员应当理解:其依然可以对前述各实施例所记载的技术方案进行修改,或者对其中部分技术特征进行等同替换;而这些修改或者替换,并不使相应技术方案的本质脱离本公开各实施例技术方案的精神和范围。

Claims (14)

  1. 一种输入数据的处理方法,其特征在于,包括:
    获取用户的至少一个输入数据;
    根据所述至少一个输入数据,获得语意数据;
    根据所述语意数据,获得推送信息;
    向所述用户提供所述推送信息。
  2. 根据权利要求1所述的方法,其特征在于,所述获取用户的至少一个输入数据,包括:
    获取所述用户的在时间上连续的至少一个输入数据。
  3. 根据权利要求1或2所述的方法,其特征在于,所述根据所述至少一个输入数据,获得语意数据,包括:
    根据所述至少一个输入数据中每个输入数据,获得所述每个输入数据的词袋;
    根据所述每个输入数据的词袋,获得所述语意数据。
  4. 根据权利要求3所述的方法,其特征在于,所述根据所述至少一个输入数据中每个输入数据,获得所述每个输入数据的词袋,包括:
    根据所述每个输入数据,或者所述每个输入数据和预先设置的扩展数据,获得所述每个输入数据的词袋。
  5. 根据权利要求1~4任一权利要求所述的方法,其特征在于,所述输入数据包括下列数据中的至少一项:
    用户的输入序列;以及
    用户的位置数据。
  6. 根据权利要求5所述的方法,其特征在于,所述用户的位置数据 包括下列数据中的至少一项:
    用户的输入序列所对应的位置数据;以及
    除了用户的输入序列所对应的位置数据之外的其他位置数据。
  7. 一种输入数据的处理装置,其特征在于,包括:
    获取单元,用于获取用户的至少一个输入数据;
    解析单元,用于根据所述至少一个输入数据,获得语意数据;
    匹配单元,用于根据所述语意数据,获得推送信息;
    推送单元,用于向所述用户提供所述推送信息。
  8. 根据权利要求7所述的装置,其特征在于,所述获取单元,具体用于
    获取所述用户的在时间上连续的至少一个输入数据。
  9. 根据权利要求7或8所述的装置,其特征在于,所述解析单元,具体用于
    根据所述至少一个输入数据中每个输入数据,获得所述每个输入数据的词袋;以及
    根据所述每个输入数据的词袋,获得所述语意数据。
  10. 根据权利要求9所述的装置,其特征在于,所述解析单元,具体用于
    根据所述每个输入数据,或者所述每个输入数据和预先设置的扩展数据,获得所述每个输入数据的词袋。
  11. 根据权利要求7~10任一权利要求所述的装置,其特征在于,所述输入数据包括下列数据中的至少一项:
    用户的输入序列;以及
    用户的位置数据。
  12. 根据权利要求11所述的装置,其特征在于,所述用户的位置数据包括下列数据中的至少一项:
    用户的输入序列所对应的位置数据;以及
    除了用户的输入序列所对应的位置数据之外的其他位置数据。
  13. 一种设备,包括:
    一个或者多个处理器;
    存储器;
    一个或者多个程序,所述一个或者多个程序存储在所述存储器中,当被所述一个或者多个处理器执行时:
    获取用户的至少一个输入数据;
    根据所述至少一个输入数据,获得语意数据;
    根据所述语意数据,获得推送信息;
    向所述用户提供所述推送信息。
  14. 一种非易失性计算机存储介质,所述非易失性计算机存储介质存储有一个或者多个程序,当所述一个或者多个程序被一个设备执行时,使得所述设备:
    获取用户的至少一个输入数据;
    根据所述至少一个输入数据,获得语意数据;
    根据所述语意数据,获得推送信息;
    向所述用户提供所述推送信息。
PCT/CN2016/083003 2015-10-26 2016-05-23 输入数据的处理方法、装置、设备及非易失性计算机存储介质 WO2017071190A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
JP2017547516A JP2018508080A (ja) 2015-10-26 2016-05-23 入力データの処理方法、装置、デバイス及び不発揮性コンピュータ記憶媒体
EP16858634.5A EP3370136A4 (en) 2015-10-26 2016-05-23 Input data processing method, apparatus and device, and non-volatile computer storage medium
US15/743,268 US20180210875A1 (en) 2015-10-26 2016-05-23 Method and apparatus for processing input data, apparatus and non-volatile computer storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510702341.8 2015-10-26
CN201510702341.8A CN105425978A (zh) 2015-10-26 2015-10-26 输入数据的处理方法及装置

Publications (1)

Publication Number Publication Date
WO2017071190A1 true WO2017071190A1 (zh) 2017-05-04

Family

ID=55504234

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/083003 WO2017071190A1 (zh) 2015-10-26 2016-05-23 输入数据的处理方法、装置、设备及非易失性计算机存储介质

Country Status (5)

Country Link
US (1) US20180210875A1 (zh)
EP (1) EP3370136A4 (zh)
JP (1) JP2018508080A (zh)
CN (1) CN105425978A (zh)
WO (1) WO2017071190A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106776852A (zh) * 2016-11-28 2017-05-31 百度(中国)有限公司 资源处理方法及装置
CN107292396B (zh) * 2017-08-14 2020-05-05 南宁学院 一种水电设备报修消息处理方法
CN109918681B (zh) * 2019-03-29 2023-01-31 哈尔滨理工大学 一种基于汉字-拼音的融合问题语义匹配方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101751202A (zh) * 2008-12-17 2010-06-23 爱思开电讯投资(中国)有限公司 一种基于环境信息进行文字关联输入的方法和装置
CN102236421A (zh) * 2010-04-20 2011-11-09 腾讯科技(深圳)有限公司 用于移动终端的输入法及输入装置
CN102567433A (zh) * 2010-12-07 2012-07-11 中国电信股份有限公司 基于输入法的处理方法、装置和移动终端
CN104298429A (zh) * 2014-09-25 2015-01-21 北京搜狗科技发展有限公司 一种基于输入的信息展示方法和输入法系统
CN104933028A (zh) * 2015-06-23 2015-09-23 百度在线网络技术(北京)有限公司 信息推送方法和装置

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9318108B2 (en) * 2010-01-18 2016-04-19 Apple Inc. Intelligent automated assistant
KR101042515B1 (ko) * 2008-12-11 2011-06-17 주식회사 네오패드 사용자의 의도에 기반한 정보 검색방법 및 정보 제공방법
CN102314222A (zh) * 2010-06-30 2012-01-11 百度在线网络技术(北京)有限公司 一种自适应输入方法、设备及系统
US20130159919A1 (en) * 2011-12-19 2013-06-20 Gabriel Leydon Systems and Methods for Identifying and Suggesting Emoticons
CN102722558B (zh) * 2012-05-29 2016-08-03 百度在线网络技术(北京)有限公司 一种为用户推荐提问的方法和装置
EP2972944A4 (en) * 2013-03-11 2016-11-02 Keypoint Technologies India Pvt Ltd CONTEXTUAL DISCOVERY
CN103714141A (zh) * 2013-12-24 2014-04-09 百度国际科技(深圳)有限公司 信息推送方法及装置
CN104462325B (zh) * 2014-12-02 2019-05-03 百度在线网络技术(北京)有限公司 搜索推荐方法及装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101751202A (zh) * 2008-12-17 2010-06-23 爱思开电讯投资(中国)有限公司 一种基于环境信息进行文字关联输入的方法和装置
CN102236421A (zh) * 2010-04-20 2011-11-09 腾讯科技(深圳)有限公司 用于移动终端的输入法及输入装置
CN102567433A (zh) * 2010-12-07 2012-07-11 中国电信股份有限公司 基于输入法的处理方法、装置和移动终端
CN104298429A (zh) * 2014-09-25 2015-01-21 北京搜狗科技发展有限公司 一种基于输入的信息展示方法和输入法系统
CN104933028A (zh) * 2015-06-23 2015-09-23 百度在线网络技术(北京)有限公司 信息推送方法和装置

Also Published As

Publication number Publication date
EP3370136A4 (en) 2018-10-10
EP3370136A1 (en) 2018-09-05
JP2018508080A (ja) 2018-03-22
CN105425978A (zh) 2016-03-23
US20180210875A1 (en) 2018-07-26

Similar Documents

Publication Publication Date Title
TWI729472B (zh) 特徵詞的確定方法、裝置和伺服器
US10678824B2 (en) Method of searching for relevant node, and computer therefor and computer program
US10122839B1 (en) Techniques for enhancing content on a mobile device
US10552539B2 (en) Dynamic highlighting of text in electronic documents
US10558701B2 (en) Method and system to recommend images in a social application
US10372716B2 (en) Automatic discovery and presentation of topic summaries related to a selection of text
KR20160058587A (ko) 문서 요약을 위한 디스플레이 장치 및 방법
CN107491477B (zh) 一种表情符号搜索方法及装置
US20170249934A1 (en) Electronic device and method for operating the same
US20140040741A1 (en) Smart Auto-Completion
CN104765750B (zh) 一种输入法应用中的输入语言切换方法及装置
US11762926B2 (en) Recommending web API's and associated endpoints
KR20210038467A (ko) 이벤트 테마 생성 방법, 장치, 기기 및 저장 매체
CN110737768A (zh) 基于深度学习的文本摘要自动生成方法及装置、存储介质
US20140379328A1 (en) Apparatus and method for outputting image according to text input in real time
WO2013142823A1 (en) Method and system for predicting words in a message
JP6776310B2 (ja) ユーザ−入力コンテンツと連関するリアルタイムフィードバック情報提供方法およびシステム
CN114861889B (zh) 深度学习模型的训练方法、目标对象检测方法和装置
EP4310695A1 (en) Data processing method and apparatus, computer device, and storage medium
CN111428025A (zh) 文本摘要方法、装置、电子设备和存储介质
WO2017071190A1 (zh) 输入数据的处理方法、装置、设备及非易失性计算机存储介质
JP7309811B2 (ja) データ注釈方法、装置、電子機器および記憶媒体
WO2017075974A1 (zh) 输入序列的处理方法、装置、设备及非易失性计算机存储介质
CN103970865A (zh) 基于种子词的微博文本层次主题发现方法及系统
CN111353070A (zh) 视频标题的处理方法、装置、电子设备及可读存储介质

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: 16858634

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2017547516

Country of ref document: JP

Kind code of ref document: A

REEP Request for entry into the european phase

Ref document number: 2016858634

Country of ref document: EP

WWE Wipo information: entry into national phase

Ref document number: 15743268

Country of ref document: US

NENP Non-entry into the national phase

Ref country code: DE