[go: up one dir, main page]

CN106873799A - Input method and device - Google Patents

Input method and device Download PDF

Info

Publication number
CN106873799A
CN106873799A CN201710083643.0A CN201710083643A CN106873799A CN 106873799 A CN106873799 A CN 106873799A CN 201710083643 A CN201710083643 A CN 201710083643A CN 106873799 A CN106873799 A CN 106873799A
Authority
CN
China
Prior art keywords
entry
input
user
word frequency
candidate
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201710083643.0A
Other languages
Chinese (zh)
Other versions
CN106873799B (en
Inventor
张东栋
田野
孟可丰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Baidu Netcom Science and Technology Co Ltd
Original Assignee
Beijing Baidu Netcom Science and Technology Co Ltd
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 Beijing Baidu Netcom Science and Technology Co Ltd filed Critical Beijing Baidu Netcom Science and Technology Co Ltd
Priority to CN201710083643.0A priority Critical patent/CN106873799B/en
Publication of CN106873799A publication Critical patent/CN106873799A/en
Application granted granted Critical
Publication of CN106873799B publication Critical patent/CN106873799B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING OR CALCULATING; 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 OR CALCULATING; 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
    • G06F3/0236Character input methods using selection techniques to select from displayed items

Landscapes

  • Engineering & Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • User Interface Of Digital Computer (AREA)
  • Document Processing Apparatus (AREA)

Abstract

This application discloses input method and device.One specific embodiment of the method includes:Obtain the input information of user;Inquiry and the candidate entry for being input into information matches in the dictionary for pre-building;According to the number of times of user input candidate entry in the history cycle of predetermined quantity, the current word frequency of candidate entry is adjusted;According to the word frequency after adjustment, the order of candidate entry is determined;According to the order, candidate entry is presented.The implementation method realizes the change being accustomed to according to user and adjusts word frequency, there is provided personalized Search Results, so as to improve the efficiency of user input entry.

Description

输入方法和装置Input method and device

技术领域technical field

本申请涉及计算机技术领域,具体涉及输入法技术领域,尤其涉及输入方法和装置。The present application relates to the technical field of computers, in particular to the technical field of input methods, especially to an input method and device.

背景技术Background technique

当用户在信息输入区域中输入信息时,通常通过输入法来完成。输入法作为一种辅助用户输入的装置,目标是能够让用户更方便、更快捷、更准确的输入。When a user enters information in an information input area, it is usually done through an input method. As a device for assisting user input, the input method aims to enable users to input more conveniently, faster and more accurately.

输入法技术中很重要的一部分是对于候选结果的排序,现有的排序通常是通过用户的历史数据,例如词频,对于候选结果的进行排序,然而在用户长时间使用输入法情况下,由于用户历史数据的积累,导致用户在输入习惯变化时,候选结果不能快速的适应新习惯。A very important part of the input method technology is the sorting of candidate results. The existing sorting usually uses the user's historical data, such as word frequency, to sort the candidate results. However, when the user uses the input method for a long time, due to the user The accumulation of historical data causes the candidate results to be unable to quickly adapt to the new habit when the user's input habit changes.

发明内容Contents of the invention

本申请的目的在于提出一种改进的输入方法和装置,来解决以上背景技术部分提到的技术问题。The purpose of this application is to propose an improved input method and device to solve the technical problems mentioned in the background art section above.

第一方面,本申请提供了一种输入方法,该方法包括:获取用户的输入信息;在预先建立的词库中查询与上述输入信息匹配的候选词条;根据预定数量的历史周期内上述用户输入上述候选词条的次数,调整上述候选词条的当前词频;根据调整后的词频,确定上述候选词条的顺序;按照上述顺序,呈现上述候选词条。In a first aspect, the present application provides an input method, which includes: obtaining user input information; searching for candidate entries matching the above input information in a pre-established thesaurus; Input the number of times of the above candidate entries, adjust the current word frequency of the above candidate entries; determine the sequence of the above candidate entries according to the adjusted word frequency; present the above candidate entries according to the above sequence.

在一些实施例中,上述预定数量经由以下步骤确定:统计预定时间段内的每个历史周期结束时用户输入词条种类的总量;基于上述总量,确定上述预定数量。In some embodiments, the above-mentioned predetermined number is determined through the following steps: counting the total amount of entry categories input by users at the end of each historical period within a predetermined time period; and determining the above-mentioned predetermined number based on the above-mentioned total amount.

在一些实施例中,上述基于上述总量确定上述预定数量,包括:从预定时间段内的第二个历史周期起,统计各个历史周期结束时用户输入词条种类的总量相对于前一个历史周期结束时用户输入词条种类的总量的增量得到增量集合;按照统计上述增量的顺序,对上述增量集合中的增量执行以下步骤,直到比较出该增量小于预置阈值:比较该增量是否小于预置阈值;更新比较次数;将上述比较次数确定为上述预定数量。In some embodiments, the above-mentioned determination of the above-mentioned predetermined amount based on the above-mentioned total amount includes: starting from the second historical cycle within the predetermined time period, counting the total amount of the entry type entered by the user at the end of each historical cycle relative to the previous history At the end of the period, the increment of the total amount of entry types entered by the user is obtained as an increment set; according to the order in which the above increments are counted, the following steps are performed on the increments in the above increment set until the increment is found to be less than the preset threshold : comparing whether the increment is smaller than a preset threshold; updating the number of comparisons; determining the number of comparisons as the predetermined number.

在一些实施例中,上述基于上述总量确定上述预定数量,包括:从预定时间段内的第二个历史周期起,统计该历史周期结束时用户输入词条种类的总量相对于前一个历史周期结束时用户输入词条种类的总量的增量,并比较所统计的增量是否小于预置阈值,若是,则停止统计并记录比较次数,若否,则记录比较次数;将上述比较次数确定为上述预定数量。In some embodiments, the above-mentioned determination of the above-mentioned predetermined amount based on the above-mentioned total amount includes: starting from the second historical period within the predetermined period of time, counting the total amount of the entry category entered by the user at the end of the historical period relative to the previous history At the end of the period, the user enters the increment of the total amount of the entry category, and compares whether the statistical increment is less than the preset threshold, if so, stops the statistics and records the number of comparisons, if not, records the number of comparisons; Determined as the above predetermined quantity.

在一些实施例中,上述根据预定数量的历史周期内上述用户输入上述候选词条的次数,调整上述候选词条的当前词频,包括:统计各个上述历史周期内上述用户输入上述候选词条的次数;将所统计的次数中小于预设阈值的候选词条确定为待调整词条;降低上述待调整词条的当前词频。In some embodiments, adjusting the current word frequency of the candidate entry according to the number of times the user inputs the candidate entry within a predetermined number of historical periods includes: counting the number of times the user enters the candidate entry in each of the historical periods ; Determining the candidate entry whose number of counts is less than the preset threshold as the entry to be adjusted; reducing the current word frequency of the entry to be adjusted.

在一些实施例中,上述降低上述待调整词条的当前词频,包括:获取各个上述历史周期内上述用户输入的词条数量;根据上述词条数量,确定用于降低上述当前词频的调整系数;计算上述调整系数与上述当前词频的乘积,并将上述乘积作为降低后的词频。In some embodiments, the above-mentioned reducing the current word frequency of the above-mentioned entry to be adjusted includes: obtaining the number of entries input by the user in each of the above-mentioned historical periods; determining an adjustment coefficient for reducing the above-mentioned current word frequency according to the above-mentioned number of entries; Calculate the product of the above-mentioned adjustment coefficient and the above-mentioned current word frequency, and use the above-mentioned product as the reduced word frequency.

在一些实施例中,上述根据上述词条数量,确定用于降低上述当前词频的调整系数,包括:判断上述词条数量是否大于预定阈值;如果是,则将第一调整系数确定为用于降低上述当前词频的调整系数;如果否,则将第二调整系数确定为用于降低上述当前词频的调整系数,其中,上述第二调整系数大于上述第一调整系数。In some embodiments, the determination of the adjustment coefficient for reducing the frequency of the current word according to the number of entries above includes: judging whether the number of entries is greater than a predetermined threshold; if so, determining the first adjustment coefficient as used for reducing The adjustment coefficient of the above-mentioned current word frequency; if not, the second adjustment coefficient is determined as the adjustment coefficient for reducing the above-mentioned current word frequency, wherein the above-mentioned second adjustment coefficient is greater than the above-mentioned first adjustment coefficient.

在一些实施例中,上述当前词频是由输入策略确定的权重加权上述候选词条的原始词频得到的;以及上述根据预定数量的历史周期内上述用户输入上述候选词条的次数,调整上述候选词条的当前词频,包括:统计各个上述历史周期内上述用户输入上述候选词条的次数;将所统计的次数中小于预设阈值的候选词条确定为待调整词条;降低上述输入策略确定的权重。In some embodiments, the above-mentioned current word frequency is obtained by weighting the original word frequency of the above-mentioned candidate entry according to the weight determined by the input strategy; The current term frequency of the entry, including: counting the number of times that the above-mentioned user inputs the above-mentioned candidate term in each of the above-mentioned historical periods; determining the candidate term that is less than the preset threshold in the counted times as the term to be adjusted; reducing the number of times determined by the above-mentioned input strategy Weights.

在一些实施例中,上述输入策略包括以下至少一项:简拼策略,用于通过输入声母或声母的首字母进行输入;模糊音策略,用于不区分预先设置的易混淆音节进行输入;纠错策略,用于不区分预先设置的易输错音节进行输入;逐词策略,用于将已输入词条作为在前词条,提供出现概率大的在后词条作为候选词条进行输入;个性化策略,用于使用用户账户中对输入法规则的设置进行输入。In some embodiments, the above-mentioned input strategy includes at least one of the following: Jianpin strategy, used for inputting initial consonants or initial letters of initial consonants; fuzzy sound strategy, used for inputting without distinguishing pre-set confusing syllables; correcting The wrong strategy is used to input without distinguishing the pre-set easy-to-enter syllables; the word-by-word strategy is used to use the input entry as the previous entry, and provide the following entry with a high probability of occurrence as the candidate entry; Personalization policy for input using the settings for input method rules in the user account.

第二方面,本申请提供了一种输入装置,该装置包括:获取单元,用于获取用户的输入信息;查询单元,用于在预先建立的词库中查询与上述输入信息匹配的候选词条;调整单元,用于根据预定数量的历史周期内上述用户输入上述候选词条的次数,调整上述候选词条的当前词频;确定单元,用于根据调整后的词频,确定上述候选词条的顺序;呈现单元,用于按照上述顺序,呈现上述候选词条。In a second aspect, the present application provides an input device, which includes: an acquisition unit, configured to acquire user input information; a query unit, configured to query a pre-established thesaurus for candidate entries that match the input information The adjustment unit is used to adjust the current word frequency of the above-mentioned candidate entry according to the number of times the above-mentioned user enters the above-mentioned candidate entry in a predetermined number of historical periods; the determination unit is used to determine the order of the above-mentioned candidate entry according to the adjusted word frequency ; The presenting unit is configured to present the above-mentioned candidate entries according to the above-mentioned order.

在一些实施例中,上述装置还包括预定数量确定单元,上述预定数量确定单元包括:第一统计子单元,用于统计预定时间段内的每个历史周期结束时用户输入词条种类的总量;第一确定子单元,用于基于上述总量,确定上述预定数量。In some embodiments, the above-mentioned device further includes a predetermined number determination unit, and the above-mentioned predetermined number determination unit includes: a first statistical subunit, which is used to count the total amount of the user input entry category at the end of each historical period within a predetermined time period ; A first determining subunit, configured to determine the above-mentioned predetermined quantity based on the above-mentioned total amount.

在一些实施例中,上述第一确定子单元,进一步配置用于:从预定时间段内的第二个历史周期起,统计各个历史周期结束时用户输入词条种类的总量相对于前一个历史周期结束时用户输入词条种类的总量的增量得到增量集合;按照统计上述增量的顺序,对上述增量集合中的增量执行以下步骤,直到比较出该增量小于预置阈值:比较该增量是否小于预置阈值;更新比较次数;将上述比较次数确定为上述预定数量。In some embodiments, the above-mentioned first determining subunit is further configured to: start from the second historical period within a predetermined period of time, and count the total amount of user input entry categories at the end of each historical period relative to the previous history At the end of the period, the increment of the total amount of entry types entered by the user is obtained as an increment set; according to the order in which the above increments are counted, the following steps are performed on the increments in the above increment set until the increment is found to be less than the preset threshold : comparing whether the increment is smaller than a preset threshold; updating the number of comparisons; determining the number of comparisons as the predetermined number.

在一些实施例中,上述第一确定子单元,进一步配置用于:从预定时间段内的第二个历史周期起,统计该历史周期结束时用户输入词条种类的总量相对于前一个历史周期结束时用户输入词条种类的总量的增量,并比较所统计的增量是否小于预置阈值,若是,则停止统计并记录比较次数,若否,则记录比较次数;将上述比较次数确定为上述预定数量。In some embodiments, the above-mentioned first determination subunit is further configured to: start from the second historical period within a predetermined period of time, and count the total amount of entry types entered by the user at the end of the historical period relative to the previous historical period At the end of the period, the user enters the increment of the total amount of the entry category, and compares whether the statistical increment is less than the preset threshold, if so, stops the statistics and records the number of comparisons, if not, records the number of comparisons; Determined as the above predetermined quantity.

在一些实施例中,上述调整单元,包括:第二统计子单元,用于统计各个上述历史周期内上述用户输入上述候选词条的次数;第二确定子单元,用于将所统计的次数中小于预设阈值的候选词条确定为待调整词条;第一降低子单元,用于降低上述待调整词条的当前词频。In some embodiments, the above adjustment unit includes: a second statistics subunit, used to count the number of times the above user enters the above candidate entry in each of the above historical periods; Candidate entries below the preset threshold are determined as entries to be adjusted; the first reducing subunit is configured to reduce the current word frequency of the entries to be adjusted.

在一些实施例中,上述第一降低子单元,进一步配置用于:获取各个上述历史周期内上述用户输入的词条数量;根据上述词条数量,确定用于降低上述当前词频的调整系数;计算上述调整系数与上述当前词频的乘积,并将上述乘积作为降低后的词频。In some embodiments, the above-mentioned first reducing subunit is further configured to: obtain the number of entries input by the user in each of the above-mentioned historical periods; determine an adjustment coefficient for reducing the frequency of the current word according to the number of entries; calculate The product of the above adjustment coefficient and the above current word frequency, and use the above product as the reduced word frequency.

在一些实施例中,上述第一降低子单元,进一步配置用于:判断上述词条数量是否大于预定阈值;如果是,则将第一调整系数确定为用于降低上述待调整词条的当前词频的调整系数;如果否,则将第二调整系数确定为用于降低上述待调整词条的当前词频的调整系数,其中,上述第二调整系数大于上述第一调整系数。In some embodiments, the above-mentioned first reducing subunit is further configured to: determine whether the number of the above-mentioned entries is greater than a predetermined threshold; if yes, determine the first adjustment coefficient as used to reduce the current word frequency of the above-mentioned entry to be adjusted If not, determine the second adjustment coefficient as the adjustment coefficient for reducing the current word frequency of the entry to be adjusted, wherein the second adjustment coefficient is greater than the first adjustment coefficient.

在一些实施例中,上述当前词频是由输入策略确定的权重加权上述候选词条的原始词频得到的;以及上述调整单元,包括:第二统计子单元,用于统计各个上述历史周期内上述用户输入上述候选词条的次数;第二确定子单元,用于将所统计的次数中小于预设阈值的候选词条确定为待调整词条;第二降低子单元,用于降低上述输入策略确定的权重。In some embodiments, the above-mentioned current word frequency is obtained by weighting the original word frequency of the above-mentioned candidate entry according to the weight determined by the input strategy; and the above-mentioned adjustment unit includes: a second statistical subunit for counting the above-mentioned users in each of the above-mentioned historical periods The number of times that the above-mentioned candidate entries are input; the second determination subunit is used to determine the candidate entries less than the preset threshold in the counted times as entries to be adjusted; the second reduction subunit is used to reduce the determination of the above-mentioned input strategy the weight of.

第三方面,本申请提供了一种设备,包括:一个或多个处理器;存储装置,用于存储一个或多个程序,当所述一个或多个程序被所述一个或多个处理器执行,使得所述一个或多个处理器实现如第一方面所述的方法。In a third aspect, the present application provides a device, including: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors Execute, so that the one or more processors implement the method as described in the first aspect.

第四方面,本申请提供了一种计算机可读存储介质,其上存储有计算机程序,其特征在于,该程序被处理器执行时实现如第一方面所述的方法。In a fourth aspect, the present application provides a computer-readable storage medium on which a computer program is stored, wherein, when the program is executed by a processor, the method described in the first aspect is implemented.

本申请提供的输入方法和装置,通过获取用户的输入信息,并在预先建立的词库中查询与上述输入信息匹配的候选词条,而后根据预定数量的历史周期内上述用户输入上述候选词条的次数,调整上述候选词条的当前词频,最后根据调整后的词频,确定上述候选词条的顺序,并按照上述顺序,呈现上述候选词条,实现了根据用户习惯的改变调整词频,提供个性化的搜索结果,从而提高了用户输入词条的效率。The input method and device provided by the present application obtain the input information of the user, and search the candidate entry matching the input information in the pre-established thesaurus, and then input the candidate entry according to the predetermined number of historical periods. adjust the current word frequency of the above candidate entries, and finally determine the order of the above candidate entries according to the adjusted word frequency, and present the above candidate entries according to the above order, realizing the adjustment of word frequency according to the change of user habits, and providing personalized Optimized search results, thereby improving the efficiency of user input terms.

附图说明Description of drawings

通过阅读参照以下附图所作的对非限制性实施例所作的详细描述,本申请的其它特征、目的和优点将会变得更明显:Other characteristics, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

图1是本申请可以应用于其中的示例性系统架构图;FIG. 1 is an exemplary system architecture diagram to which the present application can be applied;

图2是根据本申请的输入方法的一个实施例的示意性流程图;Fig. 2 is a schematic flow chart according to an embodiment of the input method of the present application;

图3是根据本申请的输入方法的应用场景的示意图;FIG. 3 is a schematic diagram of an application scenario of an input method according to the present application;

图4是根据本申请的输入方法的又一个实施例的示意性流程图;FIG. 4 is a schematic flowchart of another embodiment of the input method according to the present application;

图5是根据本申请的输入装置的一个实施例的示例性结构图;FIG. 5 is an exemplary structural diagram of an embodiment of an input device according to the present application;

图6是适于用来实现本申请实施例的终端设备或服务器的计算机系统的结构示意图。Fig. 6 is a schematic structural diagram of a computer system suitable for implementing a terminal device or a server according to an embodiment of the present application.

具体实施方式detailed description

下面结合附图和实施例对本申请作进一步的详细说明。可以理解的是,此处所描述的具体实施例仅仅用于解释相关发明,而非对该发明的限定。另外还需要说明的是,为了便于描述,附图中仅示出了与有关发明相关的部分。The application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain related inventions, rather than to limit the invention. It should also be noted that, for the convenience of description, only the parts related to the related invention are shown in the drawings.

需要说明的是,在不冲突的情况下,本申请中的实施例及实施例中的特征可以相互组合。下面将参考附图并结合实施例来详细说明本申请。It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and embodiments.

图1示出了可以应用本申请的输入方法或输入装置的实施例的示例性系统架构100。FIG. 1 shows an exemplary system architecture 100 to which embodiments of the input method or input device of the present application can be applied.

如图1所示,系统架构100可以包括终端设备101、102、103,网络104和服务器105、106。网络104用以在终端设备101、102、103和服务器105、106之间提供通信链路的介质。网络104可以包括各种连接类型,例如有线、无线通信链路或者光纤电缆等等。As shown in FIG. 1 , the system architecture 100 may include terminal devices 101 , 102 , 103 , a network 104 and servers 105 , 106 . The network 104 serves as a medium for providing communication links between the terminal devices 101 , 102 , 103 and the servers 105 , 106 . Network 104 may include various connection types, such as wires, wireless communication links, or fiber optic cables, among others.

用户110可以使用终端设备101、102、103通过网络104与服务器105、106交互,以接收或发送数据等。终端设备101、102、103上可以安装有各种通讯客户端应用,例如输入法类应用、社交平台软件网页浏览器应用、搜索引擎类应用、购物类应用、即时通信工具、邮箱客户端等。The user 110 can use the terminal device 101 , 102 , 103 to interact with the server 105 , 106 through the network 104 to receive or send data and the like. Various communication client applications can be installed on the terminal devices 101, 102, 103, such as input method applications, social platform software web browser applications, search engine applications, shopping applications, instant messaging tools, email clients, etc.

终端设备101、102、103可以是各种电子设备,包括但不限于智能手机、平板电脑、电子书阅读器、MP3播放器(Moving Picture Experts Group Audio Layer III,动态影像专家压缩标准音频层面3)、MP4(Moving Picture Experts Group Audio Layer IV,动态影像专家压缩标准音频层面4)播放器、膝上型便携计算机和台式计算机等等。终端设备101、102、103在获取到用户的输入信息后,在预先建立的词库中查询与上述输入信息匹配的候选词条,而后根据预定数量的历史周期内上述用户输入上述候选词条的次数,调整上述候选词条的当前词频,最后根据调整后的词频,确定上述候选词条的顺序,并按照所述顺序,呈现上述候选词条。Terminal devices 101, 102, 103 can be various electronic devices, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III, moving picture experts compression standard audio level 3) , MP4 (Moving Picture Experts Group Audio Layer IV, Moving Picture Experts Compression Standard Audio Layer 4) player, laptop portable computer and desktop computer, etc. After obtaining the user's input information, the terminal devices 101, 102, and 103 search the pre-established thesaurus for candidate entries that match the above-mentioned input information, and then according to the number of times the above-mentioned users input the above-mentioned candidate entries within a predetermined number of historical periods, times, adjust the current word frequency of the candidate entry, and finally determine the order of the candidate entry according to the adjusted word frequency, and present the candidate entry according to the order.

服务器105、106可以是提供各种服务的服务器,例如对终端设备101、102、103上所安装的输入法应用提供支持的后台服务器。后台服务器可以接收终端设备的词库更新请求并根据词库更新请求进行数据处理,并将处理结果(例如更新的词库)反馈给终端设备,也可以获取用户使用输入法应用所产生输入记录,例如,预定数量的历史周期内上述用户输入候选词条的次数,并根据输入记录调整该候选词条的当前词频。The servers 105 , 106 may be servers that provide various services, for example, background servers that provide support for input method applications installed on the terminal devices 101 , 102 , 103 . The background server can receive the thesaurus update request of the terminal device and perform data processing according to the thesaurus update request, and feed back the processing result (such as the updated thesaurus) to the terminal device, and can also obtain the input records generated by the user using the input method application, For example, the number of times the user inputs a candidate entry within a predetermined number of historical periods, and adjust the current word frequency of the candidate entry according to the input record.

需要说明的是,本申请实施例所提供的输入方法一般由终端设备101、102、103执行,相应地,输入装置一般设置于终端设备101、102、103中,此外,本申请实施例所提供的输入方法中的一些步骤,如“根据预定数量的历史周期内上述用户输入上述候选词条的次数,调整所述候选词条的当前词频”,也可以由服务器105、106执行。相应地,输入装置中的部分单元如“调整单元”也可以设置于服务器105、106中。It should be noted that the input methods provided in the embodiments of the present application are generally executed by the terminal devices 101, 102, and 103, and correspondingly, the input devices are generally set in the terminal devices 101, 102, and 103. In addition, the input methods provided in the embodiments of the present application Some steps in the input method, such as "adjust the current word frequency of the candidate entry according to the number of times the user inputs the candidate entry within a predetermined number of historical periods", can also be executed by the servers 105 and 106. Correspondingly, some units in the input device such as the "adjustment unit" can also be set in the servers 105 and 106 .

应该理解,图1中的终端设备、网络和服务器的数目仅仅是示意性的。根据实现需要,可以具有任意数目的终端设备、网络和服务器。It should be understood that the numbers of terminal devices, networks and servers in Fig. 1 are only illustrative. According to the implementation needs, there can be any number of terminal devices, networks and servers.

继续参考图2,示出了根据本申请的输入方法的一个实施例的流程200。该输入方法,包括以下步骤:Continuing to refer to FIG. 2 , a flow 200 of an embodiment of the input method according to the present application is shown. The input method includes the following steps:

步骤201,获取用户的输入信息。Step 201, acquire user input information.

在本实施例中,输入方法运行于其上的电子设备(例如图1所示的终端或服务器),可以获取用户的输入信息。用户的输入信息可以是用户输入的字符串。In this embodiment, the electronic device on which the input method runs (such as the terminal or the server shown in FIG. 1 ) can obtain the user's input information. The user input information may be a character string input by the user.

步骤202,在预先建立的词库中查询与输入信息匹配的候选词条。Step 202, searching for candidate entries matching the input information in the pre-established thesaurus.

在本实施例中,上述电子设备可以在预先建立的词库中查询与步骤201中获取的输入信息匹配的候选词条。预先建立的词库可以是预先存储在终端本地的输入法词库,也可以是存储在云端的词库,或二者的结合。词库中的词条可以是在网页中抓取的,也可以是用户历史输入的词条,词库中同时记录有输入信息或处理后的输入信息与词条的匹配规则。用户在输入中文时,可以基于正向最大匹配方式,对用户输入的字符串进行切分,补全切分后的字符串的音节信息,得到音节序列,而后可以根据音节与词条的匹配规则进行匹配,例如,用户输入“wo”,与“wo”匹配的候选词条可以是“我”、“握”。同样的用户在输入日文时,可以根据假名与词条的匹配规则进行匹配。In this embodiment, the electronic device may search a pre-established thesaurus for candidate entries matching the input information obtained in step 201 . The pre-established thesaurus may be an input method thesaurus pre-stored locally in the terminal, or a thesaurus stored in the cloud, or a combination of the two. The entries in the thesaurus may be captured from webpages, or may be entries entered by users in history. The thesaurus also records the matching rules between input information or processed input information and entries. When the user enters Chinese, the character string input by the user can be segmented based on the forward maximum matching method, and the syllable information of the segmented string can be completed to obtain the syllable sequence, and then according to the matching rule between the syllable and the entry For matching, for example, the user inputs "wo", and the candidate entries matching "wo" may be "I" and "hold". When the same user inputs Japanese, they can be matched according to the matching rules of pseudonyms and words.

步骤203,根据预定数量的历史周期内用户输入候选词条的次数,调整候选词条的当前词频。Step 203: Adjust the current word frequency of the candidate entry according to the number of times the user inputs the candidate entry within a predetermined number of historical periods.

在本实施例中,上述电子设备可以根据预定数量的历史周期内用户输入步骤202中查询到的候选词条的次数,调整该候选词条的当前词频。词频可简单理解为词条在词库中的出现频率,从某种程度上可根据词频衡量用户选择该候选词条的概率。调整候选词条的当前词频可以是降低近期低频使用的词条的当前词频,也可以是升高近期高频使用的词条的当前词频,能达到适应用户输入习惯变化的目的即可。预定数量的历史周期可以是获取到用户输入信息之前的多个时间周期,作为示例,候选词条为“谷丙转氨”,预定数量为3,每1天为一个历史周期,第1天用户输入:“吃饭、洗澡、谷丙转氨”三个词条;第2天用户输入:“吃饭、洗澡、晚安”三个词条;第3天用户输入:“吃饭、洗澡、晚安”三个词条;“谷丙转氨”仅在一个历史周期内出现了一次,可认为用户近期低频使用该词条,并对“谷丙转氨”的当前词频进行调整。In this embodiment, the electronic device may adjust the current word frequency of the candidate entry according to the number of times the user inputs the candidate entry found in step 202 within a predetermined number of historical periods. Word frequency can be simply understood as the frequency of occurrence of an entry in the thesaurus, and to some extent, the probability of the user selecting the candidate entry can be measured according to the word frequency. Adjusting the current word frequency of the candidate entry can be to reduce the current word frequency of the recently infrequently used entry, or to increase the current word frequency of the recently frequently used entry, which can achieve the purpose of adapting to the change of the user's input habits. The predetermined number of historical periods can be a plurality of time periods before the information input by the user is obtained. As an example, the candidate entry is "Grain-to-Grain Transammonia", the predetermined number is 3, and every day is a historical period. On the first day, the user Input: three entries of "eating, bathing, glutamic acid transammonia"; user input on the 2nd day: three entries of "eating, bathing, good night"; user input on the third day: three entries of "eating, bathing, good night" Entries; "glutinous aminotransferase" only appeared once in a historical cycle, it can be considered that the user has used this entry infrequently recently, and the current word frequency of "glutinous aminotransferase" is adjusted.

在本实施例的一些可选实现方式中,预定数量经由以下步骤确定:统计预定时间段内的每个历史周期结束时用户输入词条种类的总量;基于总量,确定预定数量。In some optional implementations of this embodiment, the predetermined number is determined through the following steps: counting the total amount of the entry types input by the user at the end of each historical period within the predetermined time period; and determining the predetermined number based on the total amount.

在本实现方式中,预定时间段可以包括若干个历史周期,以预定时间段内用户输入的词条种类的总量作为样本,可以分析出用户输入习惯改变的周期,例如,预定时间段可以是10天或15天。预定数量的确定方法也可以是,绘制用于表征预设时间段内每个历史周期结束时用户输入词条种类的总量的曲线,再根据图形统计规律,确定最优的预定数量,例如,可以根据曲线的曲率确定,因为通常用户词条种类的总量会随时间不断增加,但是新增词条种类数量的趋势会不断趋于平和。需要说明的是,预定数量的确定不限于以上方法,能体现出用户输入习惯改变的周期即可。用户输入习惯的改变可理解为用户输入词条种类的改变,例如,有的用户每天会输入大量新词或输入词条的重复性低,可以认为其输入习惯改变较快。通过统计预定时间段内的每个历史周期结束时用户输入词条种类的总量确定预定数量,一方面用户输入词条种类的总量的变化与用户输入习惯的相关度较大,所确定出的预定数量较为准确,另一方面用户输入词条种类的总量易于统计,通过其确定预定数量的效率较高。In this implementation, the predetermined period of time may include several historical periods. Taking the total amount of entry types input by the user within the predetermined period of time as a sample, the cycle of user input habit change can be analyzed. For example, the predetermined period of time may be 10 days or 15 days. The method for determining the predetermined number may also be to draw a curve representing the total amount of user-input entry types at the end of each historical period within a preset time period, and then determine the optimal predetermined number according to the graphical statistical law, for example, It can be determined according to the curvature of the curve, because usually the total amount of user entry types will continue to increase over time, but the trend of the number of new entry types will continue to be flat. It should be noted that the determination of the predetermined number is not limited to the above methods, and it only needs to reflect the cycle of changing the user's input habits. Changes in user input habits can be understood as changes in the types of entries entered by users. For example, some users input a large number of new words every day or input entries with low repetition, so it can be considered that their input habits change quickly. Determine the predetermined number by counting the total amount of entry types entered by the user at the end of each historical period within the predetermined time period. The predetermined quantity is more accurate. On the other hand, the total amount of entry types input by users is easy to count, and the efficiency of determining the predetermined quantity is relatively high.

在本实施例的一些可选实现方式中,基于总量确定预定数量,包括:从预定时间段内的第二个历史周期起,统计各个历史周期结束时用户输入词条种类的总量相对于前一个历史周期结束时用户输入词条种类的总量的增量得到增量集合;按照统计增量的顺序,对增量集合中的增量执行以下步骤,直到比较出该增量小于预置阈值:比较该增量是否小于预置阈值;更新比较次数;将比较次数确定为预定数量。In some optional implementations of this embodiment, determining the predetermined number based on the total amount includes: starting from the second historical period within the predetermined period of time, counting the total amount of the entry type entered by the user at the end of each historical period relative to At the end of the previous historical period, the increment of the total amount of entry types entered by the user is obtained as an increment set; according to the order of statistical increments, the following steps are performed on the increments in the increment set until it is compared that the increment is less than the preset Threshold: comparing whether the increment is smaller than a preset threshold; updating the number of comparisons; determining the number of comparisons as a predetermined number.

在本实现方式中,预置阈值可以根据需要设置,例如可以设置为用户一个历史周期内输入词条种类的总量的百分之十,作为示例,预置阈值为10,预定时间段为4天,历史周期为1天,从第2天起到第4天,第2天结束时相对于第1天结束时用户输入词条种类的总量增加了18,第3天结束时相对于第2天结束时用户输入词条种类的总量增加了16,第4天结束时相对于第3天结束时用户输入词条种类的总量增加了9,小于上述预置阈值10,确定预定数量为比较所统计的增量与预置阈值的次数,即3。通过统计用户输入词条种类的总量的增量,可以更直观的体现出用户输入习惯的变化,且增量计算简单,通过其确定预定数量的效率较高。In this implementation, the preset threshold can be set as required, for example, it can be set to 10% of the total amount of entry types entered by the user within a historical period. As an example, the preset threshold is 10, and the predetermined time period is 4 day, the historical period is 1 day, from the 2nd day to the 4th day, the total amount of entry types entered by the user at the end of the 2nd day has increased by 18 compared with the end of the 1st day, and at the end of the 3rd day compared with the 1st day At the end of the 2nd day, the total amount of the entry types entered by the user increased by 16, and at the end of the fourth day, the total amount of the entry types entered by the user increased by 9 compared to the end of the third day, which is less than the above preset threshold of 10, and the predetermined number is determined The number of times for comparing the counted increment with the preset threshold, that is, 3. By counting the increment of the total amount of entry types input by the user, the change of the user's input habit can be reflected more intuitively, and the increment calculation is simple, and the efficiency of determining the predetermined number through it is high.

在本实施例的一些可选实现方式中,基于总量确定预定数量,包括:从预定时间段内的第二个历史周期起,统计该历史周期结束时用户输入词条种类的总量相对于前一个历史周期结束时用户输入词条种类的总量的增量,并比较所统计的增量是否小于预置阈值,若是,则停止统计并记录比较次数,若否,则记录比较次数;将上述比较次数确定为上述预定数量。In some optional implementations of this embodiment, determining the predetermined amount based on the total amount includes: starting from the second historical period within the predetermined period of time, counting the total amount of the entry type entered by the user at the end of the historical period relative to At the end of the previous historical period, the increment of the total amount of entry types entered by the user, and compare whether the counted increment is less than the preset threshold, if so, stop the statistics and record the number of comparisons, if not, record the number of comparisons; The above-mentioned number of comparisons is determined to be the above-mentioned predetermined number.

在本实现方式中确定预定数量的方法,与上一种实现方式相比较,上一种实现方式先统计完所有的增量,再依次比较统计的增量和预置阈值直到比较出增量小于预置阈值,本实现方式中是每统计完一个增量就进行一次比较,若增量不小于预置阈值,再统计下一个增量,若增量小于预置阈值则不统计下一个增量,提高了统计效率,相应的也进一步提高了确定预定数量的效率。In the method of determining the predetermined quantity in this implementation, compared with the previous implementation, the previous implementation first counts all the increments, and then compares the statistical increments with the preset threshold in turn until the increment is less than Preset threshold. In this implementation, a comparison is made every time an increment is counted. If the increment is not less than the preset threshold, the next increment will be counted. If the increment is less than the preset threshold, the next increment will not be counted. , which improves the statistical efficiency and correspondingly further improves the efficiency of determining the predetermined quantity.

在本实施例的一些可选实现方式中,根据预定数量的历史周期内用户输入候选词条的次数,调整候选词条的当前词频,包括:统计各个历史周期内用户输入候选词条的次数;将所统计的次数中小于预设阈值的候选词条确定为待调整词条;降低待调整词条的当前词频。In some optional implementations of this embodiment, adjusting the current word frequency of the candidate entry according to the number of times the user inputs the candidate entry within a predetermined number of historical periods includes: counting the number of times the user inputs the candidate entry within each historical period; Determining the candidate entry whose number of counts is smaller than the preset threshold as the entry to be adjusted; reducing the current word frequency of the entry to be adjusted.

在本实现方式中,通过比较各个历史周期内用户输入候选词条的次数与预设阈值,可以更加准确的确定出用户近期是否低频使用该候选词条,以降低其当前词频,进一步提高了用户输入词条的效率。同样也可以判断各个历史周期中,用户未输入候选词条的历史周期的数量是否大于预设数量阈值,如果是,则将该候选词条确定为待调整词条,例如,一个历史周期为1天,预定数量为3,预设数量阈值为1,候选词条为“谷丙转氨”,用户第一天输入了“谷丙转氨”,但是第二天,第三天均未输入“谷丙转氨”未输入“谷丙转氨”的历史周期的数量为2,大于预设数量阈值1,将“谷丙转氨”确定为待调整词条。In this implementation, by comparing the number of times the user enters a candidate entry in each historical period with the preset threshold, it can be more accurately determined whether the user has recently used the candidate entry infrequently, so as to reduce the current word frequency and further improve user input. Efficiency of input terms. It can also be judged whether the number of historical periods in which the user does not input a candidate term is greater than the preset quantity threshold in each historical period, and if so, then the candidate term is determined as the term to be adjusted, for example, a historical period is 1 day, the predetermined quantity is 3, the preset quantity threshold is 1, and the candidate entry is "glutinous aminotransferase", the user entered "glutinous aminotransferase" on the first day, but neither " The number of historical periods in which "GMP" has not been entered into "GLT" is 2, which is greater than the preset quantity threshold 1, and "GLT" is determined as an entry to be adjusted.

在本实施例的一些可选实现方式中,降低待调整词条的当前词频,包括:获取各个历史周期内用户输入的词条数量;根据词条数量,确定用于降低当前词频的调整系数;计算调整系数与当前词频的乘积,并将乘积作为降低后的词频。In some optional implementations of this embodiment, reducing the current word frequency of the entry to be adjusted includes: obtaining the number of entries input by the user in each historical period; determining an adjustment coefficient for reducing the current word frequency according to the number of entries; Calculate the product of the adjustment factor and the current word frequency, and use the product as the reduced word frequency.

在本实现方式中,因为词频之间差异较大,较高的词频与较低的词频减去同一个值对其产生的影响也存在较大差异,所以,通过调整系数的对词频进行调整,对词频的调整更加合理,进一步提高了用户输入词条的效率。In this implementation, because there is a large difference between the word frequencies, there is also a big difference in the impact of the higher word frequency and the lower word frequency minus the same value. Therefore, the word frequency is adjusted by adjusting the coefficient. The adjustment of word frequency is more reasonable, which further improves the efficiency of user input entries.

在本实施例的一些可选实现方式中,根据词条数量,确定用于降低当前词频的调整系数,包括:判断词条数量是否大于预定阈值;如果是,则将第一调整系数确定为用于降低当前词频的调整系数;如果否,则将第二调整系数确定为用于降低当前词频的调整系数,其中,第二调整系数大于第一调整系数。In some optional implementations of this embodiment, according to the number of entries, determining an adjustment coefficient for reducing the frequency of the current word includes: judging whether the number of entries is greater than a predetermined threshold; if so, determining the first adjustment coefficient as is used to reduce the adjustment coefficient of the current word frequency; if not, then determine the second adjustment coefficient as the adjustment coefficient used to reduce the current word frequency, wherein the second adjustment coefficient is greater than the first adjustment coefficient.

在本实现方式中,用户输入的词条数量多,其输入的词条包括待调整词条的可能性更大,用户输入的词条数量少,其输入的词条包括待调整词条的可能性更小。例如,用户输入的词条数量较多,但在各个历史周期内,其一直未输入候选词条,由此可以推断出其近期内低频使用该候选词条的原因是输入习惯的改变的可能性更大,是输入词条数量少的可能性更小,所以对与其关联的待调整词条的当前词频的调整的幅度也就更大。通过用户输入的词条数量确定的调整系数对词频进行的调整更加准确,呈现的候选词条顺序更加合理,进一步提高了用户输入词条的效率。In this implementation mode, the number of entries entered by the user is large, and the possibility of the entry to be adjusted is greater, and the number of entries entered by the user is small, and the possibility of the entry to be adjusted includes the entry to be adjusted. less sexual. For example, the user has entered a large number of entries, but in each historical period, he has not entered a candidate entry, so it can be inferred that the reason for his low frequency of using this candidate entry in the near future is the possibility of a change in input habits Larger means that it is less likely that the number of input entries is small, so the adjustment range of the current word frequency of the associated entry to be adjusted is also greater. The adjustment coefficient determined by the number of entries input by the user can adjust the word frequency more accurately, and the order of the candidate entries presented is more reasonable, further improving the efficiency of the user input entries.

在本实施例的一些可选实现方式中,当前词频是由输入策略确定的权重加权候选词条的原始词频得到的;以及根据预定数量的历史周期内用户输入候选词条的次数,调整候选词条的当前词频,包括:统计各个历史周期内用户输入候选词条的次数;将所统计的次数中小于预设阈值的候选词条确定为待调整词条;降低输入策略确定的权重。In some optional implementations of this embodiment, the current word frequency is obtained by weighting the original word frequency of the candidate entry according to the weight determined by the input strategy; The current word frequency of an entry includes: counting the number of times that users input candidate entries in each historical period; determining the candidate entries that are smaller than the preset threshold in the counted times as entries to be adjusted; reducing the weight determined by the input strategy.

在本实现方式中,体现了对输入策略确定的权重的调整,由于用户习惯的改变不仅仅是输入内容的改变,其对于模糊音的区分等也可能发生变化,因此通过对输入策略确定的权重的调整,进一步完善了词频调整的机制,使得所呈现的候选词条顺序更加合理,进一步提高了用户输入词条的效率。In this implementation, it reflects the adjustment of the weight determined by the input strategy. Since the change of user habits is not only the change of the input content, but also the distinction of fuzzy sounds, etc., the weight determined by the input strategy The adjustment further improves the word frequency adjustment mechanism, makes the sequence of candidate entries presented more reasonable, and further improves the efficiency of user input entries.

在本实施例的一些可选实现方式中,输入策略包括以下至少一项:简拼策略,用于通过输入声母或声母的首字母进行输入;模糊音策略,用于不区分预先设置的易混淆音节进行输入;纠错策略,用于不区分预先设置的易输错音节进行输入;逐词策略,用于将已输入词条作为在前词条,提供出现概率大的在后词条作为候选词条进行输入;个性化策略,用于使用用户账户中对输入法规则的设置进行输入。In some optional implementations of this embodiment, the input strategy includes at least one of the following: Jianpin strategy, used to input by inputting the initial consonant or the first letter of the initial consonant; fuzzy sound strategy, used to not distinguish the pre-set confusing Syllable input; error correction strategy, used to input without distinguishing pre-set error-prone syllables; word-by-word strategy, used to use the input entry as the previous entry, and provide the following entry with a high probability of occurrence as a candidate Entries for input; personalization policy, used for input using the settings of the input method rules in the user account.

在本实现方式中,易混淆音节可以是平翘舌音,前后鼻音等,易输错音节可以是由于键盘等输入工具中位置接近的按键误触所导致的容易输入错误的音节。In this implementation, the easily confused syllables may be flat tongue, front and back nasal sounds, etc., and the easily mistyped syllables may be the easily mistyped syllables caused by mistakenly touching keys in close positions in input tools such as keyboards.

步骤204,根据调整后的词频,确定候选词条的顺序。Step 204, according to the adjusted word frequency, determine the order of the candidate entries.

在本实施例中,上述电子设备可以根据步骤203中调整后的词频,确定候选词条的顺序。可以按照词频由大到小的顺序对候选词条进行排序以确定候选词条的顺序。In this embodiment, the above-mentioned electronic device may determine the sequence of the candidate entries according to the word frequency adjusted in step 203 . The candidate entries may be sorted in descending order of word frequency to determine the order of the candidate entries.

步骤205,按照顺序,呈现候选词条。Step 205, present candidate entries in order.

在本实施例中,上述电子设备可以按照步骤204中确定的顺序,在用户利用其进行信息输入的终端设备上呈现候选词条。In this embodiment, the above-mentioned electronic device may present the candidate entries on the terminal device through which the user inputs information according to the sequence determined in step 204 .

继续参考图3,其示出了根据本申请的输入方法呈现的候选词集合的一个效果示意图。在图3的应用场景中,用户在输入法应用的输入框中输入“gubingzhuanan”,词库中与用户输入信息匹配的候选词条可能有“骨病转案”和“谷丙转氨”,进一步地,用户可能一个月前进行了肝功能检查,发现谷丙转氨酶偏高,因此用户某天内多次输入了“谷丙转氨”一词,以进行相关资料的查询,导致“谷丙转氨”的词条在词库中的词频激增,但是在用户已经了解谷丙转氨酶的相关知识,或者康复之后,其输入习惯也会发生改变,用户再次输入“谷丙转氨”的概率很小。根据预定数量的历史周期内用户输入“谷丙转氨”的次数即可得知,“谷丙转氨”并不是该用户常用的词条,所以可以降低“谷丙转氨”的当前词频,降低后的词频小于“骨病转案”的词频,所以将“骨病转案”排在“谷丙转氨”之前呈现。Continue to refer to FIG. 3 , which shows a schematic diagram of the effect of the candidate word set presented according to the input method of the present application. In the application scenario in Figure 3, the user enters "gubingzhuanan" in the input box of the input method application, and the candidate entries in the thesaurus that match the user input information may include "bone disease transfer case" and "glutinate transfer ammonia". Furthermore, the user may have performed a liver function test a month ago and found that the glutamic acid aminotransferase was too high, so the user entered the word "glutinous aminotransferase" several times in a day to search for relevant information, resulting in "glutinyl aminotransferase". The word frequency of the entry "ammonia" in the dictionary has increased sharply, but after the user has learned the relevant knowledge of GPT or recovered, his input habits will also change, and the probability of the user entering "GLT" again is very small . According to the number of times the user enters "Guanjiao" in a predetermined number of historical periods, it can be known that "Guanjiao" is not a commonly used entry for the user, so the current word frequency of "Guanjiao" can be reduced. The reduced word frequency is less than the word frequency of "bone disease transfer case", so "bone disease transfer case" is presented before "glutamine transfer case".

本申请的上述实施例提供的方法通过获取用户的输入信息,并在预先建立的词库中查询与上述输入信息匹配的候选词条,而后根据预定数量的历史周期内上述用户输入上述候选词条的次数,调整上述候选词条的当前词频,最后根据调整后的词频,确定上述候选词条的顺序,并按照顺序,呈现上述候选词条,实现了根据用户习惯的改变调整词频,提供个性化的搜索结果,从而提高了用户输入词条的效率。The method provided by the above-mentioned embodiments of the present application obtains the input information of the user, and queries the candidate entries matching the above-mentioned input information in the pre-established thesaurus, and then according to the above-mentioned user inputting the above-mentioned candidate entries within a predetermined number of historical periods Adjust the current word frequency of the above candidate entries, and finally determine the order of the above candidate entries according to the adjusted word frequency, and present the above candidate entries according to the order, realizing the adjustment of word frequency according to the change of user habits, and providing personalized search results, thereby improving the efficiency of user input terms.

请参考图4,图4是根据本实施例的输入方法的又一个实施例的流程示意图。Please refer to FIG. 4 , which is a schematic flowchart of another embodiment of the input method according to this embodiment.

在图4中,该输入方法400,包括以下步骤:In FIG. 4, the input method 400 includes the following steps:

步骤401,获取用户的输入信息。Step 401, acquiring user input information.

在本实施例中,输入方法运行于其上的电子设备(例如图1所示的终端),可以获取用户的输入信息。用户在输入中文时输入信息可以是对用户输入的字符串进行处理得到音节序列,用户在输入日文时输入信息也可以是假名。In this embodiment, the electronic device on which the input method runs (such as the terminal shown in FIG. 1 ) can acquire user input information. The information input by the user when inputting Chinese may be a sequence of syllables obtained by processing the character string input by the user, and the information input by the user when inputting Japanese may also be kana.

步骤402,在预先建立的词库中查询与输入信息匹配的候选词条。Step 402, searching for candidate entries matching the input information in the pre-established thesaurus.

在本实施例中,上述电子设备可以在预先建立的词库中查询与步骤401中获取的输入信息匹配的候选词条。预先建立的词库中同时记录有输入信息或处理后的输入信息与词条的匹配规则,例如,可以是音节与词条的匹配规则。In this embodiment, the electronic device may search a pre-established thesaurus for candidate entries matching the input information obtained in step 401 . Matching rules between input information or processed input information and entries are also recorded in the pre-established thesaurus, for example, matching rules between syllables and entries.

步骤403,统计各个历史周期内用户输入候选词条的次数。Step 403, counting the number of times the user enters the candidate entry in each historical period.

在本实施例中,上述电子设备可以统计预定数量的历史周期内用户输入步骤402中查询到的候选词条的次数。In this embodiment, the electronic device may count the number of times the user inputs the candidate entry found in step 402 within a predetermined number of historical periods.

步骤404,将所统计的次数中小于预设阈值的候选词条确定为待调整词条。Step 404 , determining candidate entries whose counted times are smaller than a preset threshold as entries to be adjusted.

在本实施例中,上述电子设备可以将步骤403统计的次数中小于预设阈值的候选词条确定为待调整词条。预设阈值可以是根据用户输入的词条数量确定的,用户输入的词条数量多,预设阈值可以相应大一些。例如,每日输入1000词条的用户,预设阈值可以为1,每日输入3000词条的用户,预设阈值可以为2。以预设阈值是1为例,候选词条为“谷丙转氨”,预订数量为3,每1天为一个历史周期,第1天用户输入:“吃饭、洗澡、谷丙转氨”三个词条;第2天用户输入:“吃饭、洗澡、晚安”三个词条;第3天用户输入:“吃饭、洗澡、晚安”三个词条,“谷丙转氨”仅在第3天内出现了一次,其他历史周期内输入次数为0,可认为用户近期低频使用该词条,将“谷丙转氨”确定为待调整词条。In this embodiment, the above-mentioned electronic device may determine a candidate entry whose number of counts in step 403 is smaller than a preset threshold as an entry to be adjusted. The preset threshold may be determined according to the number of entries entered by the user. If the number of entries entered by the user is large, the preset threshold may be correspondingly larger. For example, for a user who inputs 1000 entries per day, the preset threshold may be 1, and for a user who inputs 3000 entries per day, the preset threshold may be 2. Taking the preset threshold value as 1 as an example, the candidate entry is "glutinate to ammonia", and the number of reservations is 3. Every day is a historical cycle. entry; the user input on the 2nd day: three entries of "eat, bath, good night"; the user input on the 3rd day: three entries of "eat, bath, good night", and "glutinous transammonia" only in the third Appeared once in a day, and the number of inputs in other historical periods is 0. It can be considered that the user has used this entry infrequently recently, and "Gluan-Gran-transaminization" is determined as the entry to be adjusted.

步骤405,降低待调整词条的当前词频。Step 405, reducing the current word frequency of the entry to be adjusted.

在本实施例中,上述电子设备可以降低步骤404中确定的待调整词条的当前词频。上述电子设备可以首先获取各个历史周期内用户输入的词条数量,而后根据词条数量,确定用于降低当前词频的调整系数。历史周期内用户输入的词条数量即用户输入的所有词条的数量,例如,历史周期为1天,用户在这1天内输入了“吃饭”3次,“洗澡”1次,“谷丙转氨”1次,则用户在此历史周期内输入的词条数量为5。根据词条数量,确定用于降低当前词频的调整系数可以通过预先建立不同词条数量的范围与调整系数的对应关系来实现,例如,各个历史周期内用户输入的词条数量平均为150,预先建立的对应关系包括词条数量在100到200之间,调整系数为0.9。最后计算调整系数与当前词频的乘积,并将乘积作为降低后的词频。In this embodiment, the electronic device may reduce the current word frequency of the entry to be adjusted determined in step 404 . The above-mentioned electronic device may first obtain the number of entries input by the user in each historical period, and then determine an adjustment coefficient for reducing the frequency of the current word according to the number of entries. The number of entries entered by the user in the historical period is the number of all entries entered by the user. For example, the historical period is 1 day, and the user entered "eat" 3 times, "bath" 1 time, and "Gu Bingzhuan" within 1 day. Ammonia" once, the number of entries entered by the user in this historical period is 5. According to the number of entries, determining the adjustment coefficient used to reduce the frequency of the current word can be realized by pre-establishing the corresponding relationship between the range of the number of different entries and the adjustment coefficient. For example, the average number of entries entered by the user in each historical period is 150. The established correspondence includes the number of entries between 100 and 200, and the adjustment factor is 0.9. Finally, calculate the product of the adjustment coefficient and the current word frequency, and use the product as the reduced word frequency.

步骤406,若当前词频是由输入策略确定的权重加权候选词条的原始词频得到的,则降低输入策略确定的权重。Step 406, if the current word frequency is obtained by weighting the original word frequency of the candidate entry with the weight determined by the input strategy, then reduce the weight determined by the input strategy.

在本实施例中,若步骤404中确定的待调整词条的当前词频是由输入策略确定的权重加权候选词条的原始词频得到的,上述电子设备可以降低输入策略确定的权重。以模糊音策略为例,输入法判断用户为模糊音用户,无法区分“shen”和“sen”,用户输入“shenhua”时,假设模糊音策略确定的权重加权候选词条“森华”、“神话”的原始词频得到的二者的当前词频一致,当“森华”被确定为待调整词条时,则对模糊音策略确定的权重进行降低,认为用户输错“sh”、“s”的概率降低,相应的森华的加权后的词频也会降低,“神话”的当前词频将会大于“森华”。同时,后续再由模糊音策略确定的权重加权其他词条时,其他词条加权后的词频也会降低。需要说明的是,步骤405和步骤406可以同时进行也可以单独执行步骤405或步骤406。也可以进一步分析待调整词条近期被用户选中频率较低的原因,例如,用户输入“shenhua”时,“森华”被确定为待调整词条时,则可以通过对其他模糊音的分析确定用户是否已经可以区分了平舌音和翘舌音,如果是则对模糊音策略确定的权重进行降低,如果否则简单通过调整系数降低“森华”的当前词频即可。In this embodiment, if the current word frequency of the entry to be adjusted determined in step 404 is obtained by weighting the original word frequency of the candidate entry with the weight determined by the input strategy, the electronic device may reduce the weight determined by the input strategy. Taking the fuzzy sound strategy as an example, the input method judges that the user is a fuzzy sound user and cannot distinguish between "shen" and "sen". The current word frequency of the two obtained from the original word frequency of "Mythology" is consistent. When "Senhua" is determined to be an entry to be adjusted, the weight determined by the fuzzy sound strategy will be reduced, and it will be considered that the user has mistyped "sh" and "s". The probability decreases, and the corresponding weighted word frequency of Senhua will also decrease, and the current word frequency of "myth" will be greater than that of "Senhua". At the same time, when other entries are subsequently weighted by the weight determined by the fuzzy sound strategy, the weighted word frequency of other entries will also decrease. It should be noted that step 405 and step 406 may be performed simultaneously, or step 405 or step 406 may be performed separately. It is also possible to further analyze the reason why the entry to be adjusted has been selected by the user recently. For example, when the user inputs "shenhua" and "森华" is determined to be the entry to be adjusted, it can be determined by analyzing other fuzzy sounds. Whether the user can already distinguish the flat tongue sound from the warped tongue sound, if so, reduce the weight determined by the fuzzy sound strategy, if not, simply reduce the current word frequency of "Senhua" by adjusting the coefficient.

步骤407,根据调整后的词频,确定候选词条的顺序。Step 407, according to the adjusted word frequency, determine the order of the candidate entries.

在本实施例中,上述电子设备可以根据步骤405或步骤406中调整后的词频,确定候选词条的顺序。可以按照词频由大到小的顺序对候选词条进行排序以确定候选词条的顺序。In this embodiment, the above-mentioned electronic device may determine the sequence of the candidate entries according to the word frequency adjusted in step 405 or step 406 . The candidate entries may be sorted in descending order of word frequency to determine the order of the candidate entries.

步骤408,按照顺序,呈现候选词条。Step 408, present the candidate entries in order.

在本实施例中,上述电子设备可以按照步骤407中顺序,在用户利用其进行信息输入的终端设备上呈现候选词条。In this embodiment, the above-mentioned electronic device may present the candidate entry on the terminal device through which the user inputs information according to the sequence in step 407 .

本申请的上述实施例提供的方法通过降低待调整词条的当前词频和/或在当前词频是由输入策略确定的权重加权候选词条的原始词频得到的时,降低输入策略确定的权重,进一步优化了候选词条的排序结果,提高了信息输入效率。The method provided by the above-mentioned embodiments of the present application further reduces the weight determined by the input strategy by reducing the current word frequency of the entry to be adjusted and/or when the current word frequency is obtained by weighting the original word frequency of the candidate entry with the weight determined by the input strategy. Optimized the sorting results of candidate entries and improved the efficiency of information input.

进一步参考图5,作为对上述方法的实现,本申请提供了一种输入装置的一个实施例,该装置实施例与图2所示的方法实施例相对应,该装置具体可以应用于各种电子设备中。Further referring to FIG. 5, as an implementation of the above method, the present application provides an embodiment of an input device, which corresponds to the method embodiment shown in FIG. 2, and this device can be specifically applied to various electronic in the device.

如图5所示,本实施例的输入装置500包括:获取单元510、查询单元520、调整单元530、确定单元540、呈现单元550,其中,获取单元510,用于获取用户的输入信息;查询单元520,用于在预先建立的词库中查询与上述输入信息匹配的候选词条;调整单元530,用于根据预定数量的历史周期内上述用户输入上述候选词条的次数,调整上述候选词条的当前词频;确定单元540,用于根据调整后的词频,确定上述候选词条的顺序;呈现单元550,用于按照顺序,呈现上述候选词条。As shown in Figure 5, the input device 500 of this embodiment includes: an acquisition unit 510, a query unit 520, an adjustment unit 530, a determination unit 540, and a presentation unit 550, wherein the acquisition unit 510 is used to acquire user input information; query The unit 520 is configured to search the pre-established thesaurus for candidate entries matching the above-mentioned input information; the adjustment unit 530 is used to adjust the above-mentioned candidate words according to the number of times the above-mentioned user inputs the above-mentioned candidate entries within a predetermined number of historical periods The current word frequency of the entry; the determination unit 540 is configured to determine the order of the candidate entries according to the adjusted word frequency; the presentation unit 550 is configured to present the candidate entries in order.

在本实施例中,获取单元510、查询单元520、调整单元530、确定单元540、呈现单元550的具体处理可以参考图2对应实施例步骤201、步骤202、步骤203、步骤204和步骤205的详细描述,在此不再赘述。In this embodiment, the specific processing of the acquisition unit 510, the query unit 520, the adjustment unit 530, the determination unit 540, and the presentation unit 550 can refer to the steps 201, 202, 203, 204, and 205 of the corresponding embodiment in FIG. Detailed description will not be repeated here.

在本实施例的一些可选实现方式中,上述装置还包括预定数量确定单元560,上述预定数量确定单元560包括:第一统计子单元561,用于统计预定时间段内的每个历史周期结束时用户输入词条种类的总量;第一确定子单元562,用于基于总量,确定上述预定数量。In some optional implementations of this embodiment, the above-mentioned device further includes a predetermined number determination unit 560, and the above-mentioned predetermined number determination unit 560 includes: a first statistical subunit 561, configured to count the end of each historical period within a predetermined time period When the user inputs the total amount of the entry category; the first determining subunit 562 is configured to determine the above-mentioned predetermined amount based on the total amount.

在本实施例的一些可选实现方式中,上述第一确定子单元562,进一步配置用于:从预定时间段内的第二个历史周期起,统计各个历史周期结束时用户输入词条种类的总量相对于前一个历史周期结束时用户输入词条种类的总量的增量得到增量集合;按照统计增量的顺序,对增量集合中的增量执行以下步骤,直到比较出该增量小于预置阈值:比较该增量是否小于预置阈值;更新比较次数;将比较次数确定为预定数量。In some optional implementations of this embodiment, the above-mentioned first determining subunit 562 is further configured to: start from the second historical period within a predetermined period of time, and count the number of entries entered by the user at the end of each historical period The increment of the total amount relative to the total amount of the entry type entered by the user at the end of the previous historical period is obtained as an increment set; according to the order of statistical increments, the following steps are performed on the increments in the increment set until the increment is compared. The amount is less than a preset threshold: compare whether the increment is less than a preset threshold; update the number of comparisons; determine the number of comparisons as a predetermined number.

在本实施例的一些可选实现方式中,上述第一确定子单元562,进一步配置用于:从预定时间段内的第二个历史周期起,统计该历史周期结束时用户输入词条种类的总量相对于前一个历史周期结束时用户输入词条种类的总量的增量,并比较所统计的增量是否小于预置阈值,若是,则停止统计并记录比较次数,若否,则记录比较次数;将上述比较次数确定为上述预定数量。In some optional implementations of this embodiment, the above-mentioned first determination subunit 562 is further configured to: start from the second historical period within a predetermined period of time, and count the number of entries entered by the user at the end of the historical period. The increment of the total amount relative to the total amount of the entry type entered by the user at the end of the previous historical period, and compare whether the counted increment is less than the preset threshold, if so, stop the statistics and record the number of comparisons, if not, record The number of comparisons; the above-mentioned number of comparisons is determined as the above-mentioned predetermined number.

在本实施例的一些可选实现方式中,上述调整单元530,包括:第二统计子单元531,用于统计各个历史周期内用户输入候选词条的次数;第二确定子单元534,用于将所统计的次数中小于预设阈值的候选词条确定为待调整词条;第一降低子单元532,用于降低上述待调整词条的当前词频。In some optional implementations of this embodiment, the adjustment unit 530 includes: a second statistics subunit 531, configured to count the number of times the user enters a candidate entry in each historical period; a second determination subunit 534, configured to Determining a candidate entry whose number of counts is less than a preset threshold as an entry to be adjusted; the first reducing subunit 532 is configured to reduce the current word frequency of the entry to be adjusted.

在本实施例的一些可选实现方式中,上述第一降低子单元532,进一步配置用于:获取各个历史周期内上述用户输入的词条数量;根据词条数量,确定用于降低上述当前词频的调整系数;计算调整系数与上述当前词频的乘积,并将乘积作为降低后的词频。In some optional implementations of this embodiment, the first reducing subunit 532 is further configured to: obtain the number of entries input by the user in each historical period; The adjustment coefficient; calculate the product of the adjustment coefficient and the above-mentioned current word frequency, and use the product as the reduced word frequency.

在本实施例的一些可选实现方式中,上述第一降低子单元532,进一步配置用于:判断上述词条数量是否大于预定阈值;如果是,则将第一调整系数确定为用于降低上述待调整词条的当前词频的调整系数;如果否,则将第二调整系数确定为用于降低上述待调整词条的当前词频的调整系数,其中,上述第二调整系数大于上述第一调整系数。In some optional implementations of this embodiment, the above-mentioned first reducing subunit 532 is further configured to: judge whether the above-mentioned number of entries is greater than a predetermined threshold; The adjustment coefficient of the current word frequency of the entry to be adjusted; if not, the second adjustment coefficient is determined as the adjustment coefficient for reducing the current word frequency of the above-mentioned entry to be adjusted, wherein the second adjustment coefficient is greater than the first adjustment coefficient .

在本实施例的一些可选实现方式中,上述当前词频是由输入策略确定的权重加权候选词条的原始词频得到的;以及调整单元530,包括:第二统计子单元531,用于统计各个历史周期内用户输入候选词条的次数;第二确定子单元534,用于将所统计的次数中小于预设阈值的候选词条确定为待调整词条;第二降低子单元533,用于降低输入策略确定的权重。In some optional implementations of this embodiment, the above-mentioned current word frequency is obtained by the original word frequency of the weighted candidate entry determined by the input strategy; The number of times the user enters the candidate entry in the historical period; the second determination subunit 534 is used to determine the candidate entry less than the preset threshold in the counted times as the entry to be adjusted; the second reduction subunit 533 is used to Decreases the weight of the input policy determination.

从图5中可以看出,本实施例中输入装置500通过获取用户的输入信息,并在预先建立的词库中查询与上述输入信息匹配的候选词条,而后根据预定数量的历史周期内上述用户输入上述候选词条的次数,调整上述候选词条的当前词频,最后根据调整后的词频,确定上述候选词条的顺序,并按照顺序,呈现上述候选词条。由此,本实施例实现了根据用户习惯的改变调整词频,提供个性化的搜索结果,从而提高了用户输入词条的效率。It can be seen from FIG. 5 that in this embodiment, the input device 500 obtains the user's input information, and searches the pre-established thesaurus for candidate entries matching the above input information, and then according to the above-mentioned The number of times the user inputs the candidate entry, adjusts the current word frequency of the candidate entry, and finally determines the order of the candidate entry according to the adjusted word frequency, and presents the candidate entry according to the order. Thus, in this embodiment, word frequency is adjusted according to changes in user habits, and personalized search results are provided, thereby improving the efficiency of user input of terms.

下面参考图6,其示出了适于用来实现本申请实施例的终端设备或服务器的计算机系统600的结构示意图。图6示出的终端设备/服务器仅仅是一个示例,不应对本申请实施例的功能和使用范围带来任何限制。Referring now to FIG. 6 , it shows a schematic structural diagram of a computer system 600 suitable for implementing a terminal device or a server according to an embodiment of the present application. The terminal device/server shown in FIG. 6 is only an example, and should not limit the functions and scope of use of this embodiment of the present application.

如图6所示,计算机系统600包括中央处理单元(CPU)601,其可以根据存储在只读存储器(ROM)602中的As shown in FIG. 6 , a computer system 600 includes a central processing unit (CPU) 601 that can

程序或者从存储部分608加载到随机访问存储器(RAM)603中的程序而执行各种适当的动作和处理。在RAM 603中,还存储有系统600操作所需的各种程序和数据。CPU 601、ROM 602以及RAM 603通过总线604彼此相连。输入/输出(I/O)接口605也连接至总线604。Various appropriate actions and processes are executed by a program or a program loaded from the storage unit 608 into the random access memory (RAM) 603 . In the RAM 603, various programs and data necessary for the operation of the system 600 are also stored. The CPU 601 , ROM 602 , and RAM 603 are connected to each other via a bus 604 . An input/output (I/O) interface 605 is also connected to the bus 604 .

以下部件连接至I/O接口605:包括键盘、鼠标等的输入部分606;包括诸如阴极射线管(CRT)、液晶显示器(LCD)等以及扬声器等的输出部分607;包括硬盘等的存储部分608;以及包括诸如LAN卡、调制解调器等的网络接口卡的通信部分609。通信部分609经由诸如因特网的网络执行通信处理。驱动器610也根据需要连接至I/O接口606。可拆卸介质611,诸如磁盘、光盘、磁光盘、半导体存储器等等,根据需要安装在驱动器610上,以便于从其上读出的计算机程序根据需要被安装入存储部分608。The following components are connected to the I/O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage section 608 including a hard disk, etc. and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I/O interface 606 as needed. A removable medium 611 such as a magnetic disk, optical disk, magneto-optical disk, semiconductor memory, etc. is mounted on the drive 610 as necessary so that a computer program read therefrom is installed into the storage section 608 as necessary.

特别地,根据本公开的实施例,上文参考流程图描述的过程可以被实现为计算机软件程序。例如,本公开的实施例包括一种计算机程序产品,其包括承载在计算机可读介质上的计算机程序,该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中,该计算机程序可以通过通信部分609从网络上被下载和安装,和/或从可拆卸介质611被安装。在该计算机程序被中央处理单元(CPU)601执行时,执行本申请的方法中限定的上述功能。需要说明的是,本申请所述的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件,或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于:具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本申请中,计算机可读存储介质可以是任何包含或存储程序的有形介质,该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本申请中,计算机可读的信号介质可以包括在基带中或者作为载波一部分传播的数据信号,其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式,包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读的信号介质还可以是计算机可读存储介质以外的任何计算机可读介质,该计算机可读介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输,包括但不限于:无线、电线、光缆、RF等等,或者上述的任意合适的组合。In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, where the computer program includes program codes for executing the methods shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network via communication portion 609 and/or installed from removable media 611 . When the computer program is executed by the central processing unit (CPU) 601, the above-mentioned functions defined in the method of the present application are performed. It should be noted that the computer-readable medium described in this application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable Programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, however, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, in which computer-readable program codes are carried. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. . Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

附图中的流程图和框图,图示了按照本申请各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上,流程图或框图中的每个方框可以代表一个单元、程序段、或代码的一部分,所述单元、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意,在有些作为替换的实现中,方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如,两个接连地表示的方框实际上可以基本并行地执行,它们有时也可以按相反的顺序执行,这依所涉及的功能而定。也要注意的是,框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合,可以用执行规定的功能或操作的专用的基于硬件的系统来实现,或者可以用专用硬件与计算机指令的组合来实现。The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in a flowchart or block diagram may represent a unit, program segment, or portion of code that contains one or more logic devices for implementing the specified Executable instructions for a function. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved. It should also be noted that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented by a dedicated hardware-based system that performs the specified functions or operations , or may be implemented by a combination of dedicated hardware and computer instructions.

描述于本申请实施例中所涉及到的单元可以通过软件的方式实现,也可以通过硬件的方式来实现。所描述的单元也可以设置在处理器中,例如,可以描述为:一种处理器包括获取单元、查询单元、调整单元、确定单元、呈现单元。其中,这些单元的名称在某种情况下并不构成对该单元本身的限定,例如,获取单元还可以被描述为“获取用户的输入信息的单元”。The units involved in the embodiments described in the present application may be implemented by means of software, or may be implemented by means of hardware. The described units may also be set in a processor, for example, it may be described as: a processor includes an acquisition unit, a query unit, an adjustment unit, a determination unit, and a presentation unit. Wherein, the names of these units do not constitute a limitation on the unit itself in some cases, for example, the obtaining unit may also be described as "a unit for obtaining user input information".

作为另一方面,本申请还提供了一种非易失性计算机存储介质,该非易失性计算机存储介质可以是上述实施例中所述装置中所包含的非易失性计算机存储介质;也可以是单独存在,未装配入终端中的非易失性计算机存储介质。上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:获取用户的输入信息;在预先建立的词库中查询与输入信息匹配的候选词条;根据预定数量的历史周期内用户输入候选词条的次数,调整候选词条的当前词频;根据调整后的词频,确定候选词条的顺序;按照上述顺序,呈现候选词条。As another aspect, the present application also provides a non-volatile computer storage medium, which may be the non-volatile computer storage medium contained in the device described in the above embodiments; It may be a non-volatile computer storage medium that exists independently and is not assembled into the terminal. The above-mentioned non-volatile computer storage medium stores one or more programs, and when the one or more programs are executed by a device, the device: obtains user input information; queries and Input information matching candidate entries; adjust the current word frequency of the candidate entries according to the number of times the user enters the candidate entries within a predetermined number of historical periods; determine the order of the candidate entries according to the adjusted word frequency; present the candidates according to the above order entry.

以上描述仅为本申请的较佳实施例以及对所运用技术原理的说明。本领域技术人员应当理解,本申请中所涉及的发明范围,并不限于上述技术特征的特定组合而成的技术方案,同时也应涵盖在不脱离所述发明构思的情况下,由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本申请中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。The above description is only a preferred embodiment of the present application and an illustration of the applied technical principles. Those skilled in the art should understand that the scope of the invention involved in this application is not limited to the technical solution formed by the specific combination of the above-mentioned technical features, but should also cover the technical solution formed by the above-mentioned technical features without departing from the inventive concept. Other technical solutions formed by any combination of or equivalent features thereof. For example, a technical solution formed by replacing the above-mentioned features with technical features with similar functions disclosed in (but not limited to) this application.

Claims (19)

1.一种输入方法,其特征在于,所述方法包括:1. An input method, characterized in that the method comprises: 获取用户的输入信息;Obtain user input information; 在预先建立的词库中查询与所述输入信息匹配的候选词条;Searching for candidate entries matching the input information in a pre-established thesaurus; 根据预定数量的历史周期内所述用户输入所述候选词条的次数,调整所述候选词条的当前词频;adjusting the current word frequency of the candidate entry according to the number of times the user has input the candidate entry within a predetermined number of historical periods; 根据调整后的词频,确定所述候选词条的顺序;Determine the order of the candidate entries according to the adjusted word frequency; 按照所述顺序,呈现所述候选词条。According to the sequence, the candidate entries are presented. 2.根据权利要求1所述的方法,其特征在于,所述预定数量经由以下步骤确定:2. The method according to claim 1, wherein the predetermined number is determined via the following steps: 统计预定时间段内的每个历史周期结束时用户输入词条种类的总量;Count the total amount of entry types entered by the user at the end of each historical period within the predetermined time period; 基于所述总量,确定所述预定数量。Based on the total amount, the predetermined amount is determined. 3.根据权利要求2所述的方法,其特征在于,所述基于所述总量确定所述预定数量,包括:3. The method according to claim 2, wherein said determining said predetermined amount based on said total amount comprises: 从预定时间段内的第二个历史周期起,统计各个历史周期结束时用户输入词条种类的总量相对于前一个历史周期结束时用户输入词条种类的总量的增量得到增量集合;From the second historical cycle in the predetermined period of time, the increment of the total amount of user-input entry types at the end of each historical cycle relative to the total amount of user-input entry types at the end of the previous historical cycle is counted to obtain an incremental set ; 按照统计所述增量的顺序,对所述增量集合中的增量执行以下步骤,直到比较出该增量小于预置阈值:比较该增量是否小于预置阈值;更新比较次数;Perform the following steps on the increments in the increment set according to the order in which the increments are counted until the increments are found to be smaller than a preset threshold: compare whether the increments are smaller than a preset threshold; update the number of comparisons; 将所述比较次数确定为所述预定数量。The number of comparisons is determined as the predetermined number. 4.根据权利要求2所述的方法,其特征在于,所述基于所述总量确定所述预定数量,包括:4. The method according to claim 2, wherein said determining said predetermined amount based on said total amount comprises: 从预定时间段内的第二个历史周期起,统计该历史周期结束时用户输入词条种类的总量相对于前一个历史周期结束时用户输入词条种类的总量的增量,并比较所统计的增量是否小于预置阈值,若是,则停止统计并记录比较次数,若否,则记录比较次数;From the second historical cycle in the predetermined period of time, the increment of the total amount of the user input entry type at the end of the historical cycle relative to the total amount of the user input entry type at the end of the previous historical cycle is counted, and the comparison is made Whether the statistical increment is less than the preset threshold, if so, stop the statistics and record the number of comparisons, if not, record the number of comparisons; 将所述比较次数确定为所述预定数量。The number of comparisons is determined as the predetermined number. 5.根据权利要求1所述的方法,其特征在于,所述根据预定数量的历史周期内所述用户输入所述候选词条的次数,调整所述候选词条的当前词频,包括:5. The method according to claim 1, wherein the adjusting the current word frequency of the candidate entry according to the number of times the user inputs the candidate entry within a predetermined number of historical periods comprises: 统计各个所述历史周期内所述用户输入所述候选词条的次数;Counting the number of times the user inputs the candidate entry in each of the historical periods; 将所统计的次数中小于预设阈值的候选词条确定为待调整词条;Determining candidate entries smaller than a preset threshold in the counted times as entries to be adjusted; 降低所述待调整词条的当前词频。Reduce the current word frequency of the entry to be adjusted. 6.根据权利要求5所述的方法,其特征在于,所述降低所述待调整词条的当前词频,包括:6. The method according to claim 5, wherein the reducing the current word frequency of the entry to be adjusted comprises: 获取各个所述历史周期内所述用户输入的词条数量;Acquiring the number of entries input by the user in each of the historical periods; 根据所述词条数量,确定用于降低所述当前词频的调整系数;Determine an adjustment coefficient for reducing the current word frequency according to the number of terms; 计算所述调整系数与所述当前词频的乘积,并将所述乘积作为降低后的词频。Calculate the product of the adjustment coefficient and the current word frequency, and use the product as the reduced word frequency. 7.根据权利要求6所述的方法,其特征在于,所述根据所述词条数量,确定用于降低所述当前词频的调整系数,包括:7. The method according to claim 6, wherein said determining an adjustment coefficient for reducing said current word frequency according to said entry quantity comprises: 判断所述词条数量是否大于预定阈值;Judging whether the number of entries is greater than a predetermined threshold; 如果是,则将第一调整系数确定为用于降低所述当前词频的调整系数;If yes, then the first adjustment coefficient is determined as the adjustment coefficient for reducing the current word frequency; 如果否,则将第二调整系数确定为用于降低所述当前词频的调整系数,其中,所述第二调整系数大于所述第一调整系数。If not, the second adjustment coefficient is determined as the adjustment coefficient for reducing the frequency of the current word, wherein the second adjustment coefficient is greater than the first adjustment coefficient. 8.根据权利要求1-7中任一项所述的方法,其特征在于,所述当前词频是由输入策略确定的权重加权所述候选词条的原始词频得到的;以及8. The method according to any one of claims 1-7, wherein the current word frequency is obtained by weighting the original word frequency of the candidate entry by the weight determined by the input strategy; and 所述根据预定数量的历史周期内所述用户输入所述候选词条的次数,调整所述候选词条的当前词频,包括:The adjusting the current word frequency of the candidate entry according to the number of times the user inputs the candidate entry within a predetermined number of historical periods includes: 统计各个所述历史周期内所述用户输入所述候选词条的次数;Counting the number of times the user inputs the candidate entry in each of the historical periods; 将所统计的次数中小于预设阈值的候选词条确定为待调整词条;Determining candidate entries smaller than a preset threshold in the counted times as entries to be adjusted; 降低所述输入策略确定的权重。Decreases the weight of the input policy determination. 9.根据权利要求8所述的方法,其特征在于,所述输入策略包括以下至少一项:9. The method according to claim 8, wherein the input strategy comprises at least one of the following: 简拼策略,用于通过输入声母或声母的首字母进行输入;Jianpin strategy, which is used to input by inputting the initial consonant or the first letter of the initial consonant; 模糊音策略,用于不区分预先设置的易混淆音节进行输入;Fuzzy sound strategy, which is used to input without distinguishing the pre-set confusing syllables; 纠错策略,用于不区分预先设置的易输错音节进行输入;Error correction strategy, which is used to input without distinguishing pre-set error-prone syllables; 逐词策略,用于将已输入词条作为在前词条,提供出现概率大的在后词条作为候选词条进行输入;The word-by-word strategy is used to use the entered entry as the previous entry, and provide the following entry with a high probability of occurrence as the candidate entry for input; 个性化策略,用于使用用户账户中对输入法规则的设置进行输入。Personalization policy for input using the settings for input method rules in the user account. 10.一种输入装置,其特征在于,所述装置包括:10. An input device, characterized in that the device comprises: 获取单元,用于获取用户的输入信息;An acquisition unit, configured to acquire user input information; 查询单元,用于在预先建立的词库中查询与所述输入信息匹配的候选词条;a query unit, configured to query a pre-established thesaurus for candidate entries matching the input information; 调整单元,用于根据预定数量的历史周期内所述用户输入所述候选词条的次数,调整所述候选词条的当前词频;An adjustment unit, configured to adjust the current word frequency of the candidate entry according to the number of times the user inputs the candidate entry within a predetermined number of historical periods; 确定单元,用于根据调整后的词频,确定所述候选词条的顺序;A determining unit, configured to determine the order of the candidate entries according to the adjusted word frequency; 呈现单元,用于按照所述顺序,呈现所述候选词条。The presenting unit is configured to present the candidate entries in the sequence. 11.根据权利要求10所述的装置,其特征在于,所述装置还包括预定数量确定单元,所述预定数量确定单元包括:11. The device according to claim 10, characterized in that the device further comprises a predetermined number determination unit, and the predetermined number determination unit comprises: 第一统计子单元,用于统计预定时间段内的每个历史周期结束时用户输入词条种类的总量;The first statistical subunit is used to count the total amount of entry types entered by the user at the end of each historical period within a predetermined time period; 第一确定子单元,用于基于所述总量,确定所述预定数量。A first determining subunit, configured to determine the predetermined amount based on the total amount. 12.根据权利要求11所述的装置,其特征在于,所述第一确定子单元,进一步配置用于:12. The device according to claim 11, wherein the first determining subunit is further configured to: 从预定时间段内的第二个历史周期起,统计各个历史周期结束时用户输入词条种类的总量相对于前一个历史周期结束时用户输入词条种类的总量的增量得到增量集合;From the second historical cycle in the predetermined period of time, the increment of the total amount of user-input entry types at the end of each historical cycle relative to the total amount of user-input entry types at the end of the previous historical cycle is counted to obtain an incremental set ; 按照统计所述增量的顺序,对所述增量集合中的增量执行以下步骤,直到比较出该增量小于预置阈值:比较该增量是否小于预置阈值;更新比较次数;Perform the following steps on the increments in the increment set according to the order in which the increments are counted until the increments are found to be smaller than a preset threshold: compare whether the increments are smaller than a preset threshold; update the number of comparisons; 将所述比较次数确定为所述预定数量。The number of comparisons is determined as the predetermined number. 13.根据权利要求11所述的装置,其特征在于,所述第一确定子单元,进一步配置用于:13. The device according to claim 11, wherein the first determining subunit is further configured to: 从预定时间段内的第二个历史周期起,统计该历史周期结束时用户输入词条种类的总量相对于前一个历史周期结束时用户输入词条种类的总量的增量,并比较所统计的增量是否小于预置阈值,若是,则停止统计并记录比较次数,若否,则记录比较次数;From the second historical cycle in the predetermined period of time, the increment of the total amount of the user input entry type at the end of the historical cycle relative to the total amount of the user input entry type at the end of the previous historical cycle is counted, and the comparison is made Whether the statistical increment is less than the preset threshold, if so, stop the statistics and record the number of comparisons, if not, record the number of comparisons; 将所述比较次数确定为所述预定数量。The number of comparisons is determined as the predetermined number. 14.根据权利要求10所述的装置,其特征在于,所述调整单元,包括:14. The device according to claim 10, wherein the adjustment unit comprises: 第二统计子单元,用于统计各个所述历史周期内所述用户输入所述候选词条的次数;The second statistical subunit is used to count the number of times the user inputs the candidate entry in each of the historical periods; 第二确定子单元,用于将所统计的次数中小于预设阈值的候选词条确定为待调整词条;The second determining subunit is used to determine the candidate entries whose counted times are smaller than the preset threshold as the entries to be adjusted; 第一降低子单元,用于降低所述待调整词条的当前词频。The first reducing subunit is used to reduce the current word frequency of the entry to be adjusted. 15.根据权利要求14所述的装置,其特征在于,所述第一降低子单元,进一步配置用于:15. The device according to claim 14, wherein the first lowering subunit is further configured to: 获取各个所述历史周期内所述用户输入的词条数量;Acquiring the number of entries input by the user in each of the historical periods; 根据所述词条数量,确定用于降低所述当前词频的调整系数;Determine an adjustment coefficient for reducing the current word frequency according to the number of terms; 计算所述调整系数与所述当前词频的乘积,并将所述乘积作为降低后的词频。Calculate the product of the adjustment coefficient and the current word frequency, and use the product as the reduced word frequency. 16.根据权利要求15所述的装置,其特征在于,所述第一降低子单元,进一步配置用于:16. The device according to claim 15, wherein the first lowering subunit is further configured to: 判断所述词条数量是否大于预定阈值;Judging whether the number of entries is greater than a predetermined threshold; 如果是,则将第一调整系数确定为用于降低所述待调整词条的当前词频的调整系数;If yes, then the first adjustment coefficient is determined as the adjustment coefficient for reducing the current word frequency of the entry to be adjusted; 如果否,则将第二调整系数确定为用于降低所述待调整词条的当前词频的调整系数,其中,所述第二调整系数大于所述第一调整系数。If not, the second adjustment coefficient is determined as the adjustment coefficient for reducing the current word frequency of the entry to be adjusted, wherein the second adjustment coefficient is greater than the first adjustment coefficient. 17.根据权利要求10-16中任一项所述的装置,其特征在于,所述当前词频是由输入策略确定的权重加权所述候选词条的原始词频得到的;以及17. The device according to any one of claims 10-16, wherein the current word frequency is obtained by weighting the original word frequency of the candidate entry with a weight determined by an input strategy; and 所述调整单元,包括:The adjustment unit includes: 第二统计子单元,用于统计各个所述历史周期内所述用户输入所述候选词条的次数;The second statistical subunit is used to count the number of times the user inputs the candidate entry in each of the historical periods; 第二确定子单元,用于将所统计的次数中小于预设阈值的候选词条确定为待调整词条;The second determining subunit is used to determine the candidate entries whose counted times are smaller than the preset threshold as the entries to be adjusted; 第二降低子单元,用于降低所述输入策略确定的权重。The second reducing subunit is configured to reduce the weight determined by the input strategy. 18.一种设备,其特征在于,包括:18. A device, characterized in that it comprises: 一个或多个处理器;one or more processors; 存储装置,用于存储一个或多个程序,storage means for storing one or more programs, 当所述一个或多个程序被所述一个或多个处理器执行,使得所述一个或多个处理器实现如权利要求1-9中任一所述的方法。When the one or more programs are executed by the one or more processors, the one or more processors are made to implement the method according to any one of claims 1-9. 19.一种计算机可读存储介质,其上存储有计算机程序,其特征在于,该程序被处理器执行时实现如权利要求1-9中任一所述的方法。19. A computer-readable storage medium, on which a computer program is stored, wherein, when the program is executed by a processor, the method according to any one of claims 1-9 is implemented.
CN201710083643.0A 2017-02-16 2017-02-16 Input method and device Active CN106873799B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710083643.0A CN106873799B (en) 2017-02-16 2017-02-16 Input method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710083643.0A CN106873799B (en) 2017-02-16 2017-02-16 Input method and device

Publications (2)

Publication Number Publication Date
CN106873799A true CN106873799A (en) 2017-06-20
CN106873799B CN106873799B (en) 2020-10-09

Family

ID=59166848

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710083643.0A Active CN106873799B (en) 2017-02-16 2017-02-16 Input method and device

Country Status (1)

Country Link
CN (1) CN106873799B (en)

Cited By (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107885348A (en) * 2017-11-27 2018-04-06 牡丹江师范学院 The Japanese input device and method of a kind of mobile communication terminal device
CN108932069A (en) * 2018-07-11 2018-12-04 科大讯飞股份有限公司 Input method candidate entry determines method, apparatus, equipment and readable storage medium storing program for executing
CN109426354A (en) * 2017-08-25 2019-03-05 北京搜狗科技发展有限公司 A kind of input method, device and the device for input
CN109521888A (en) * 2017-09-19 2019-03-26 北京搜狗科技发展有限公司 A kind of input method, device and medium
CN109597495A (en) * 2017-09-30 2019-04-09 北京金山安全软件有限公司 Information prediction method, device and equipment
CN109725737A (en) * 2017-10-31 2019-05-07 北京金山安全软件有限公司 Information display method, device and system
CN109783244A (en) * 2017-11-10 2019-05-21 北京搜狗科技发展有限公司 Treating method and apparatus, the device for processing
CN109917927A (en) * 2017-12-13 2019-06-21 北京搜狗科技发展有限公司 A candidate determination method and device
CN110502126A (en) * 2019-05-28 2019-11-26 华为技术有限公司 Input method and electronic equipment
CN111382242A (en) * 2018-12-28 2020-07-07 北京搜狗科技发展有限公司 Information providing method, device and readable medium
CN111460795A (en) * 2020-03-26 2020-07-28 云知声智能科技股份有限公司 Text error correction method and system
CN111796690A (en) * 2019-03-21 2020-10-20 北京搜狗科技发展有限公司 Data processing method and device and electronic equipment
CN111984132A (en) * 2020-07-07 2020-11-24 北京语言大学 Method and system for inputting information according to context environment
CN112395044A (en) * 2020-11-10 2021-02-23 新华三技术有限公司合肥分公司 Command line keyword filling method and device and network equipment
CN113515618A (en) * 2020-04-09 2021-10-19 北京搜狗科技发展有限公司 Speech processing method, device and medium
CN114995662A (en) * 2021-03-02 2022-09-02 北京搜狗科技发展有限公司 Word frequency adjusting and information recommending method and device and electronic equipment
CN115061583A (en) * 2022-07-26 2022-09-16 维沃移动通信有限公司 Display method, device, electronic device and storage medium for candidate words
CN115454261A (en) * 2022-09-23 2022-12-09 北京百度网讯科技有限公司 Input method candidate word generation method and device, electronic equipment and readable storage medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101071334A (en) * 2006-12-29 2007-11-14 腾讯科技(深圳)有限公司 Method and system for restoring candidat word order for Chinese input method
CN102346560A (en) * 2010-07-29 2012-02-08 腾讯科技(深圳)有限公司 Method and device for adjusting candidate word sequence in input method
US8463598B2 (en) * 2007-08-23 2013-06-11 Google Inc. Word detection
CN105094368A (en) * 2015-07-24 2015-11-25 上海二三四五网络科技有限公司 Control method and control device for frequency modulation ordering of input method candidate item
CN105955495A (en) * 2016-04-29 2016-09-21 百度在线网络技术(北京)有限公司 Information input method and device

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101071334A (en) * 2006-12-29 2007-11-14 腾讯科技(深圳)有限公司 Method and system for restoring candidat word order for Chinese input method
US8463598B2 (en) * 2007-08-23 2013-06-11 Google Inc. Word detection
CN102346560A (en) * 2010-07-29 2012-02-08 腾讯科技(深圳)有限公司 Method and device for adjusting candidate word sequence in input method
CN105094368A (en) * 2015-07-24 2015-11-25 上海二三四五网络科技有限公司 Control method and control device for frequency modulation ordering of input method candidate item
CN105955495A (en) * 2016-04-29 2016-09-21 百度在线网络技术(北京)有限公司 Information input method and device

Cited By (27)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109426354B (en) * 2017-08-25 2022-07-12 北京搜狗科技发展有限公司 Input method, device and device for input
CN109426354A (en) * 2017-08-25 2019-03-05 北京搜狗科技发展有限公司 A kind of input method, device and the device for input
CN109521888B (en) * 2017-09-19 2022-11-01 北京搜狗科技发展有限公司 Input method, device and medium
CN109521888A (en) * 2017-09-19 2019-03-26 北京搜狗科技发展有限公司 A kind of input method, device and medium
CN109597495A (en) * 2017-09-30 2019-04-09 北京金山安全软件有限公司 Information prediction method, device and equipment
CN109725737A (en) * 2017-10-31 2019-05-07 北京金山安全软件有限公司 Information display method, device and system
CN109783244A (en) * 2017-11-10 2019-05-21 北京搜狗科技发展有限公司 Treating method and apparatus, the device for processing
CN109783244B (en) * 2017-11-10 2021-06-22 北京搜狗科技发展有限公司 Processing method and device for processing
CN107885348A (en) * 2017-11-27 2018-04-06 牡丹江师范学院 The Japanese input device and method of a kind of mobile communication terminal device
CN109917927A (en) * 2017-12-13 2019-06-21 北京搜狗科技发展有限公司 A candidate determination method and device
CN108932069A (en) * 2018-07-11 2018-12-04 科大讯飞股份有限公司 Input method candidate entry determines method, apparatus, equipment and readable storage medium storing program for executing
CN111382242A (en) * 2018-12-28 2020-07-07 北京搜狗科技发展有限公司 Information providing method, device and readable medium
CN111796690A (en) * 2019-03-21 2020-10-20 北京搜狗科技发展有限公司 Data processing method and device and electronic equipment
CN110502126A (en) * 2019-05-28 2019-11-26 华为技术有限公司 Input method and electronic equipment
CN110502126B (en) * 2019-05-28 2023-12-29 华为技术有限公司 Input method and electronic equipment
CN111460795A (en) * 2020-03-26 2020-07-28 云知声智能科技股份有限公司 Text error correction method and system
CN111460795B (en) * 2020-03-26 2023-05-26 云知声智能科技股份有限公司 Text error correction method and system
CN113515618A (en) * 2020-04-09 2021-10-19 北京搜狗科技发展有限公司 Speech processing method, device and medium
CN111984132A (en) * 2020-07-07 2020-11-24 北京语言大学 Method and system for inputting information according to context environment
CN111984132B (en) * 2020-07-07 2021-07-27 北京语言大学 A method and system for inputting information according to context
CN112395044B (en) * 2020-11-10 2023-04-28 新华三技术有限公司合肥分公司 Command line keyword filling method and device and network equipment
CN112395044A (en) * 2020-11-10 2021-02-23 新华三技术有限公司合肥分公司 Command line keyword filling method and device and network equipment
CN114995662A (en) * 2021-03-02 2022-09-02 北京搜狗科技发展有限公司 Word frequency adjusting and information recommending method and device and electronic equipment
CN115061583A (en) * 2022-07-26 2022-09-16 维沃移动通信有限公司 Display method, device, electronic device and storage medium for candidate words
CN115061583B (en) * 2022-07-26 2025-05-16 维沃移动通信有限公司 Method, device, electronic device and storage medium for displaying candidate words
CN115454261A (en) * 2022-09-23 2022-12-09 北京百度网讯科技有限公司 Input method candidate word generation method and device, electronic equipment and readable storage medium
CN115454261B (en) * 2022-09-23 2025-05-02 北京百度网讯科技有限公司 Input method candidate word generation method, device, electronic device and readable storage medium

Also Published As

Publication number Publication date
CN106873799B (en) 2020-10-09

Similar Documents

Publication Publication Date Title
CN106873799B (en) Input method and device
JP5926378B2 (en) Text input method, apparatus, and system
US11093854B2 (en) Emoji recommendation method and device thereof
US10885076B2 (en) Computerized system and method for search query auto-completion
TWI512502B (en) Method and system for generating custom language models and related computer program product
US11568860B2 (en) System and method for federated, context-sensitive, acoustic model refinement
US9997157B2 (en) Knowledge source personalization to improve language models
WO2021128880A1 (en) Speech recognition method, device, and device for speech recognition
CN106575503B (en) Method and system for session context modeling for dialog understanding systems
CN106649780B (en) Artificial intelligence-based information providing method and device
CN112313680A (en) Autocomplete for gesture input in assistant system
US10282469B2 (en) System and method for summarizing a multimedia content item
WO2017140221A1 (en) Text information processing method and device
WO2023000491A1 (en) Application recommendation method, apparatus and device, and computer-readable storage medium
CN104750705A (en) Information returning method and device
WO2017197806A1 (en) Method for providing intelligent service, intelligent service system and intelligent terminal based on artificial intelligence
US10175883B2 (en) Techniques for predicting user input on touch screen devices
CN111862961B (en) Method and device for recognizing speech
US10073828B2 (en) Updating language databases using crowd-sourced input
CN110069769B (en) Application label generation method and device and storage device
WO2020151548A1 (en) Method and device for sorting followed pages
CN111538830B (en) French searching method, device, computer equipment and storage medium
WO2021051587A1 (en) Search result sorting method and apparatus based on semantic recognition, electronic device, and storage medium
CN116204624A (en) Response method, device, electronic device and storage medium
CN111381685B (en) A sentence association method and device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant