CN110929122B

CN110929122B - Data processing method and device for data processing

Info

Publication number: CN110929122B
Application number: CN201811101152.5A
Authority: CN
Inventors: 刘文文; 李琳; 潘牧野
Original assignee: Beijing Sogou Technology Development Co Ltd
Current assignee: Beijing Sogou Technology Development Co Ltd
Priority date: 2018-09-20
Filing date: 2018-09-20
Publication date: 2024-02-06
Anticipated expiration: 2038-09-20
Also published as: CN110929122A; WO2020056948A1

Abstract

The embodiment of the invention provides a data processing method, a data processing device and a data processing device. The method specifically comprises the following steps: determining information to be replied from the clipboard information; the information to be replied corresponds to all or part of the clipboard information; determining reply candidates corresponding to the information to be replied; the reply candidates are shown. The embodiment of the invention can improve the reply efficiency and realize intelligent reply in a reply scene crossing the communication window.

Description

Data processing method and device for data processing

Technical Field

The present invention relates to the field of communications technologies, and in particular, to a data processing method and apparatus, and a device for data processing.

Background

With the development of communication technology, communication applications such as short message application and instant messaging application can provide information interaction function for users, so that information interaction between different users can be performed. For example, different users may send messages to each other through a message application. For another example, different users may also send information to each other through instant messaging applications.

In practical application, when receiving the information sent by the opposite communication end, the user needs to cut and grind proper sentences to reply the information, and the reply efficiency is low.

Disclosure of Invention

The embodiment of the invention provides a data processing method, a data processing device and a data processing device, which can improve the reply efficiency and realize intelligent reply in a reply scene crossing a communication window.

In order to solve the above problems, an embodiment of the present invention discloses a data processing method, including:

determining information to be replied from the clipboard information; the information to be replied corresponds to all or part of the clipboard information;

determining reply candidates corresponding to the information to be replied;

the reply candidates are shown.

In another aspect, an embodiment of the present invention discloses a data processing apparatus, including:

the information to be replied determining module is used for determining the information to be replied from the clipboard information; the information to be replied corresponds to all or part of the clipboard information;

a reply candidate determining module, configured to determine a reply candidate corresponding to the information to be replied; and

and the reply candidate display module is used for displaying the reply candidates.

In yet another aspect, an embodiment of the present invention discloses an apparatus for data processing, comprising a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more processors, the one or more programs comprising instructions for:

determining reply candidates corresponding to the information to be replied;

the reply candidates are shown.

In yet another aspect, embodiments of the invention disclose a machine-readable medium having instructions stored thereon that, when executed by one or more processors, cause an apparatus to perform a data processing method as described in one or more of the preceding.

The embodiment of the invention has the following advantages:

the embodiment of the invention supports that the user carries the information to be replied through the clipboard, so that the information to be replied can be determined from the clipboard information, and reply candidates corresponding to the information to be replied are provided, and the reply efficiency can be improved. The embodiment of the invention can be applied to a reply scene crossing communication windows, in particular, a user can copy information in a first communication window and jump to a second communication window, so that the embodiment of the invention can automatically determine information to be replied from clipboard information and provide reply candidates corresponding to the information to be replied, thereby realizing intelligent reply in the reply scene crossing the communication windows and improving the reply efficiency.

The embodiment of the invention can also be applied to the reply scene in the communication window. The reply scene in the communication window specifically comprises: the information received by the user and the information sent are located in the same communication window. For an operating system with strict security requirements, such as an IOS system, it cannot support direct reading of the content of the screen, so that the embodiment of the invention can determine the information to be replied through the clipboard information.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments of the present invention will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic illustration of an application environment for a data processing method of an embodiment of the present invention;

FIG. 2 is a flowchart illustrating steps of a first embodiment of a data processing method according to the present invention;

FIG. 3 is a flowchart illustrating steps of a second embodiment of a data processing method according to the present invention;

FIG. 4 is a schematic representation of an interface according to an embodiment of the present invention;

FIG. 5 is a block diagram of an embodiment of a data processing apparatus of the present invention;

FIG. 6 is a block diagram of an apparatus 800 for data processing according to the present invention; and

Fig. 7 is a schematic diagram of a server in some embodiments of the invention.

Detailed Description

The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

The embodiment of the invention provides a data processing scheme, which can comprise the following steps: determining information to be replied from the clipboard information; the information to be replied can correspond to all or part of the clipboard information; determining reply candidates corresponding to the information to be replied; the reply candidates are shown.

In the embodiment of the invention, the clipboard is an area in the memory and is an insert in a preset program, and a user can transfer and share selected information among various application programs through simple actions such as cutting, copying and pasting through the clipboard. The clipboard temporarily stores the cut and copied information by using the internal resource memory of the terminal, or virtual memory.

The preset program may specifically include: browser programs, instant messaging programs, social networking (e.g., microblog, forum, news, etc.) programs, and the like.

The information in the clipboard is selected by the user. The type of clipboard information may include at least one of the following types: text, picture, audio, video, and page addresses.

In practical applications, the clipboard may include only one piece of information; alternatively, a plurality of pieces of information may be included in the clipboard. For example, 3 pieces of information may be included in the clipboard, where the 1 st piece of information may be a text type, the 2 nd piece of information may be a voice type, the 3 rd piece of information may be a picture type, and so on. It will be appreciated that embodiments of the present invention are not limited in the number of clipboard information, nor in the particular type of clipboard information.

The embodiment of the invention can be suitable for a reply scene crossing the communication window. The cross-communication window may include: different communication windows for different applications, or different communication windows for the same application, etc.

Different windows for different applications may include: a communication window of a short message application and a communication window of an instant messaging application, or a communication window of a first instant messaging application and a communication window of a second instant messaging application, and the like. For example, the user a receives the information a sent by the user B through the short message application, and because the short message sending needs to consume the corresponding short message charge, the embodiment of the invention supports the user a to send the reply corresponding to the information a to the user B through the instant messaging application. Accordingly, the user a can copy the information a and jump to a communication window between the user a and the user B in the instant messaging application, so that the embodiment of the invention can take the clipboard information (i.e. the content of the information a) as the information to be replied and automatically provide reply candidates for the user a to select, so that the user a can realize quick reply under the condition of crossing scenes, and further the reply efficiency can be improved.

Different windows for the same application are described herein. For example, the user C receives the information B sent by the user D through the communication window a of the instant messaging application, and because the communication window a is a group window, the reply corresponding to the information B may relate to privacy. Accordingly, the user C can copy the information B and jump to the communication window B between the user C and the user D in the instant messaging application, so that the embodiment of the invention can take the clipboard information (i.e. the content of the information B) as the information to be replied and automatically provide reply candidates for the user C to select, so that the user C can realize quick reply under the condition of crossing scenes, and further the reply efficiency can be improved. For example, user D is the leader of user C, communication window a is the communication window of the workgroup, and communication window B is the communication window between user C and user D, and since replies generated in the communication window of the workgroup may be seen by users other than user C and user D, it is inconvenient to reply to information B in the communication window of the workgroup.

It should be noted that, the foregoing user jumps to the second communication window, which is just an optional embodiment, in practice, the scheme of the embodiment of the present invention may not depend on the jump of the communication window, and even if the user does not jump of the communication window, the embodiment of the present invention may still automatically determine the information to be replied from the clipboard information, and provide the reply candidate corresponding to the information to be replied.

The data processing method provided by the embodiment of the invention can be applied to Application environments such as websites and/or Application (Application) so as to improve the reply efficiency. For example, the APP may be a communication application, the website may be a web page for providing communication services, or the like.

The data processing method provided by the embodiment of the invention can be applied to the application environment shown in fig. 1, and as shown in fig. 1, the client 100 and the server 200 are located in a wired or wireless network, and the client 100 and the server 200 interact data through the wired or wireless network.

Alternatively, client 100 may operate on terminals including, but not limited to: smart phones, tablet computers, e-book readers, MP3 (dynamic video expert compression standard audio plane 3,Moving Picture Experts Group Audio Layer III) players, MP4 (dynamic video expert compression standard audio plane 4,Moving Picture Experts Group Audio Layer IV) players, laptop portable computers, car computers, desktop computers, set-top boxes, smart televisions, wearable devices, and the like.

The client 100 may be an APP running on a device, such as an instant communication APP, a short message APP, an input method APP, or an APP carried by an operating system, which is not limited by the specific APP corresponding to the client in the embodiment of the present application.

Method embodiment one

Referring to fig. 2, a flowchart illustrating steps of a first embodiment of a data processing method according to the present invention may specifically include the following steps:

Step 201, determining information to be replied from clipboard information; the information to be replied can correspond to all or part of the clipboard information;

step 202, determining reply candidates corresponding to the information to be replied;

step 203, displaying the reply candidates.

At least one step of the method embodiment shown in fig. 2 may be performed by a server and/or a client, although embodiments of the present invention are not limited by the specific implementation of each step.

The method embodiment of fig. 2 may correspond to a triggered condition.

According to one embodiment, the trigger condition may include: the input method keyboard is called up. The keyboard of the input method is called up to indicate that the user wants to reply through input, so that the method of the embodiment of the invention can be triggered.

According to another embodiment, the triggering condition may include: clipboard information is updated. The update of the clipboard information may indicate that the user has generated new clipboard information, indicating that the user has a reply request, and thus may trigger the method of embodiments of the present invention.

According to a further embodiment, the triggering condition may include: clipboard information is updated and the input method keyboard is called up. In this case, the user is required to reply by input, so the method of the embodiment of the invention can be triggered.

According to a further embodiment, the triggering condition may include: after the clipboard information is updated, jump to the communication window. The jump to the communication window may refer to the jump from the interface before the clipboard operation to the communication window, in this case, it may be indicated that the user wants to reply through the communication window after the jump, so that the method of the embodiment of the present invention may be triggered. The interface prior to clipboard operation may be a communication window or a non-communication window.

According to a further embodiment, the triggering condition may include: after the clipboard information is updated, jump to the communication window and the input method keyboard is invoked.

It will be appreciated that the above-mentioned triggering conditions are merely alternative embodiments, and in fact, those skilled in the art may determine the above-mentioned triggering conditions according to actual application requirements, for example, the above-mentioned triggering conditions may also be preset gestures of a user, etc., and the embodiments of the present invention are not limited to specific triggering conditions.

In step 201, clipboard information may be obtained by accessing a clipboard. The clipboard information may include: one piece of content, or a plurality of pieces of content. For example, in response to a long press operation by a user, a selection interface corresponding to each piece of information is displayed in the communication window for the user to select at least one piece of information required for copying

Step 201 may determine information to be replied from clipboard information, where the information to be replied may correspond to all or part of the clipboard information. For example, clipboard information may include: the sender identification of the information and the sender identification of the information can be filtered from the clipboard information, and the information can be reserved as the information to be replied.

In the embodiment of the present invention, optionally, the type of clipboard information may include at least one of the following types: text, picture, audio, video, and page addresses. The embodiment of the invention can determine at least one type of information to be replied, and determine corresponding reply candidates aiming at the at least one type of information to be replied.

The embodiment of the invention can provide the following technical scheme for determining the reply candidates corresponding to the information to be replied:

in the technical solution 1, step 202 of determining the reply candidate corresponding to the information to be replied may specifically include: determining a theme corresponding to the information to be replied; and determining reply candidates corresponding to the information to be replied according to the theme.

A topic may refer to the central idea represented by the information to be replied to. The embodiment of the invention can characterize the theme through the theme keywords, and the theme keywords can refer to keywords which can embody the theme of the information to be replied.

Optionally, the determining the theme corresponding to the information to be replied may specifically include:

determining a mode A1, and determining a theme corresponding to a page address according to the content of a page corresponding to the page address; and/or

Determining a mode A2, carrying out first identification on a video stream and/or an audio stream corresponding to a video, and determining a theme corresponding to the video according to an obtained first identification result; and/or

Determining a mode A3, performing second identification on the picture, and determining a theme corresponding to the picture according to an obtained second identification result; and/or

And determining a mode A4, performing voice recognition on the audio, and determining a theme corresponding to the information to be replied according to the obtained voice recognition result.

Video is typically composed of still pictures, which are referred to as video frames. The video corresponding video stream may be used to represent successive video frames. The audio stream corresponding to the video can be used for representing continuous audio signals, and the audio stream and the continuous video frames have synchronism so as to realize synchronous playing effect of video pictures and audio.

In practical applications, the audio stream corresponding to the video may correspond to the video content such as a speech, a score, etc. of the video, where the score may include: theme song, episode, tail song, background music corresponding to the speech, etc. It will be appreciated that embodiments of the present application are not limited to specific video content corresponding to an audio stream.

In practical applications, the video stream and the audio stream corresponding to the video may be located in the same file, in which case the audio may be extracted from the video file, specifically, the video file may be converted into an audio file, for example, the video file in MP4 (moving picture experts compression standard audio layer 4,Moving Picture Experts Group Audio Layer 4) format may be converted into an audio file in MP3 (moving picture experts compression standard audio layer 3,Moving Picture Experts Group Audio Layer III) format, and so on. Alternatively, the video stream and the audio stream corresponding to the video may be located in separate files, that is, the video file and the audio file may be separate, in which case the audio file may be directly acquired. The audio file may include an audio stream corresponding to a video, so that the audio stream corresponding to the video may be read from the audio file.

In practical application, a plurality of video frames can be extracted from the video according to preset time intervals, and the extracted video frames can be used as objects for image recognition. It can be appreciated by those skilled in the art that the preset time interval may be determined according to actual application requirements, for example, the preset time interval may be a play duration corresponding to N video frames, where N is a positive integer, and it can be appreciated that the embodiment of the present application is not limited to specific N and preset time intervals.

The embodiment of the application can identify the video stream and/or the audio stream corresponding to the video by adopting the following identification mode:

the method comprises the steps of 1, performing image recognition on a video stream corresponding to video to obtain corresponding image target information; and/or

The identification mode 2 is used for carrying out text identification on the video stream corresponding to the video so as to obtain corresponding text information; and/or

And 3, performing voice recognition on the audio stream corresponding to the video to obtain corresponding text information.

In the recognition method 1, image recognition is a technique of recognizing image objects in various modes by processing, analyzing, and understanding images by a machine. In particular to embodiments of the present application, techniques for processing, analyzing, and understanding video frames with a machine to identify image objects in various different modes may be utilized. Wherein, generally, the image target in the video frame may correspond to a certain image area in the video frame, and the image target in the video frame may include: items, figures, spaces, etc. For example, the person may be a person in a video frame, the object may be an object worn by the person in the video frame, and the space may be an environmental space where the person in the video frame is located, such as an outdoor environment, an indoor environment, etc., for example, the indoor environment may include information such as a wall, a ground, etc., and it is understood that the embodiment of the present application does not limit a specific image target in the video frame.

In an alternative embodiment of the present application, the process of performing image recognition on the video frames corresponding to the video stream and/or the audio stream may include: detecting an image target in a video frame, and analyzing the acquired image target by using a deep learning method to obtain corresponding image target information, so that the recognition result in the embodiment of the application may include: image target information corresponding to the video frame. The image target information may include: the image of the image target (that is, the image of the image target in the video frame, the image target usually corresponds to a certain closed area in the video frame), and the recognition result of the image target (such as the name, the category and other information of the recognized image target). For example, a face in a video frame may be detected by using a face detection technique, and analyzed by using a deep learning method to obtain information on the sex, age, etc. of a person, and even the source of the person, such as from which movie, etc., and even which celebrity the person is. Further, items worn by the person, such as clothing, shoes, watches worn, jewelry, etc., may also be detected. Alternatively, spatial information or the like where the person is located may also be detected.

The text information in the video frame may include: text information included in the image, and/or text information in the subtitle.

For recognition mode 2, text recognition technology may be used to perform text recognition on video frames corresponding to the video stream and/or the audio stream. The text recognition technique may include: OCR (optical character recognition ) technology, etc., the OCR technology may segment characters in an image after preprocessing such as noise reduction on the image to obtain a single character image, and recognize characters corresponding to the single character image. It will be appreciated that embodiments of the present application are not limited to a particular text recognition technique.

For the recognition mode 2, a subtitle file corresponding to the subtitle of the video frame can be obtained, and text information in the subtitle is obtained from the subtitle file; or, a screen can be shot on a picture corresponding to the video frame, and text recognition can be performed on the shot image so as to obtain text information in the subtitle. It can be appreciated that the embodiment of the present application does not limit the specific manner of acquiring text information in subtitles.

For recognition mode 3, voice recognition techniques may be used to convert the audio stream corresponding to the video into text information. If the audio stream corresponding to the video is denoted as S, a series of processing is performed on S to obtain a corresponding speech feature sequence O, and the speech feature sequence O is denoted as o= { O1, O2, …, oi, …, OT }, where Oi is the ith speech feature, and T is the total number of speech features. The sentence corresponding to the audio stream S can be regarded as a word string composed of a number of words, and is denoted as w= { W1, W2, …, wn }, n being a natural number. The speech recognition process is to find the most probable word string W from the known speech feature sequence O.

Specifically, the speech recognition is a model matching process, in which a speech model can be first established according to the characteristics of human speech, and a template required for speech recognition can be established by analyzing an input speech signal and extracting required characteristics; the process of recognizing the voice input by the user is a process of comparing the characteristics of the voice input by the user with the templates, and finally determining the best template matched with the voice input by the user, thereby obtaining the voice recognition result. The specific voice recognition algorithm can adopt a training and recognition algorithm based on a hidden Markov model based on statistics, can also adopt a training and recognition algorithm based on a neural network, a recognition algorithm based on dynamic time alignment matching and other algorithms, and the specific voice recognition process is not limited by the embodiment of the application.

In an application example of the present invention, a user G receives a website a sent by a user H and duplicates the website a, so that the embodiment of the present invention may automatically analyze the page content of the website a to obtain a topic a corresponding to the website a, where the topic a may be related to the eight diagrams of entertainment, the folk life of the country, etc., and automatically provide a reply candidate corresponding to the topic a, for example, "i also see the web page" or "i also like the content corresponding to the topic a".

In another application example of the present invention, when the user I receives the video a sent by the user J and duplicates the video a, the embodiment of the present invention may automatically identify the video a to obtain the theme B corresponding to the video a, where the theme B may be related to the life of the child in the kindergarten, etc., and automatically give the reply candidate corresponding to the theme B, such as "look very happy to the child in the kindergarten" etc.

In another application example of the present invention, when the user K receives the picture a sent by the user L and duplicates the picture a, the embodiment of the present invention may automatically identify the picture a to obtain the theme C corresponding to the picture a, where the theme C may relate to a piece of clothing, such as a piece of overcoat, a piece of down jackets, a piece of skirt, etc., and automatically provide reply candidates corresponding to the theme C, such as "the theme C is good in view, worth buying", "the theme C is a bit old and a bit, the theme C is fat, etc.

The embodiment of the invention can provide the following determination modes for determining the theme corresponding to the information to be replied:

and determining a mode B1, and determining a topic keyword corresponding to the information to be replied by adopting a TF-IDF (word frequency-inverse document frequency algorithm) method.

The main ideas of TF-IDF are: if a word or phrase appears frequently TF in a document or a piece of text and rarely in other documents or text, the word or phrase is considered to have good class discrimination and is suitable for classification.

And determining a mode B2, and determining a theme keyword corresponding to the information to be replied by adopting an LDA (latent dirichlet allocation ) model.

The LDA model is a document generation model and is an unsupervised machine learning technology. It considers a document or a piece of text to have multiple topics, each topic corresponding to a different topic keyword. In the construction process of a document or a text, a certain topic is selected with a certain probability, and then a certain topic keyword is selected with a certain probability under the topic, so that a first topic keyword of the document is generated. This process is repeated continuously to generate a document or a piece of text. The LDA is used as the inverse of the document generation process, i.e. searching out the topic of a document or a text according to the document or the text, and the topic keywords corresponding to the topic.

And B3, determining a category corresponding to the information to be replied by adopting a classification model, and obtaining the topic keyword according to the information of the category. The classification model may include: fasttext model. The fastText model may output probabilities that a word sequence belongs to different categories for an input word sequence (a piece of text or a sentence). The fastttext model can form feature vectors from words and phrases in the word sequence, the feature vectors are mapped to middle layers through linear transformation, and the middle layers are remapped to corresponding preset categories. Alternatively, fastttext may use a nonlinear activation function in mapping to the corresponding preset category. fastttext has the advantages of high speed and high accuracy, and the embodiment of the invention is not limited to a specific classification model.

It can be appreciated that, according to the actual application requirements, any one or a combination of the above determining modes B1 to B3 may be adopted by a person skilled in the art, and the specific process of determining the topic corresponding to the information to be replied is not limited in the embodiment of the present invention.

According to the embodiment of the invention, the reply candidates corresponding to the information to be replied can be determined according to the theme. Optionally, the information to be replied is notification type information, in which case the reply candidates may be "received", "good", etc. The corresponding theme of the information to be replied "coming to the meeting room" can be "place notification", and the corresponding theme of the information to be replied "your planning scheme has a place to be modified" can be "work modification notification".

Alternatively, the information to be replied to may be query class information, in which case the reply candidate may be a positive class candidate, a negative class candidate, one of a plurality of options, or an answer to a question. For example, if the information to be replied is "tomorrow goes to place a to eat or place B to eat", the corresponding reply candidates may include: site a, or site B. For another example, if the information to be replied is "do you get off duty", the corresponding reply candidates may include: with or without the presence of a drop. For another example, if the information to be replied is "you are in a futilely, the corresponding reply candidates may include: at meals, at watching video, etc.

Technical proposal 2,

In the technical solution 2, step 202 of determining a reply candidate corresponding to the information to be replied may specifically include: searching in a mapping relation between the data to be replied and the reply data according to the information to be replied to obtain reply candidates corresponding to the information to be replied; the mapping relationship may be obtained according to historical communication data corresponding to at least one user, where the historical communication data may include: historical data to be replied and corresponding historical reply data.

In a specific implementation process, the mapping relationship can be determined by the following manner: obtaining historical communication data of at least one user; the historical communication data may include: historical data to be replied and corresponding historical reply data; extracting corresponding historical reply content of each piece of historical data to be replied; and taking the historical reply content meeting the preset condition corresponding to the historical data to be replied as reply data corresponding to the historical data to be replied, thereby determining the mapping relation according to the historical data to be replied and the corresponding reply data thereof.

The user may be a user of the current terminal, or may be at least one sampling user in the whole network, and further, the obtained historical communication data is different, for example:

(1) at least one set of historical communication data generated by a user of a current terminal is obtained. For example, reply data of the user for communication content may be acquired; extracting at least one set of question-answer pairs from the reply data, each set of question-answer pairs may include: the at least one set of question-answer pairs are the at least one set of historical communication data generated by the user.

Such as: the terminal may often receive a short message "how many points are going to work? The terminal sometimes replies to "9 points" and sometimes replies to "8 points", so "is a point off duty? "and" 9 points "form a set of question-answer pairs," are points off duty? "and" 8 points "form a set of question-answer pairs, based on which personalized cache data can be formed: "is a point off duty? (1) 9 points (2)8 points). When the terminal receives the same short message again, two reply candidates are directly given: (1) 9 points (2)8 points), the user can directly click the reply short message without inputting.

(2) Determining at least one sampling user; the at least one set of historical communication data generated by the at least one sampling user is acquired, wherein the at least one sampling user is all users in the system, part of users in the system and the like, and the historical communication data of each user do not need to be analyzed independently according to the scheme, so that the acquisition efficiency of the historical communication data can be improved.

After obtaining at least one set of historical communication data, firstly obtaining historical to-be-replied data in each set of historical communication data, and then combining the same historical to-be-replied data to obtain all the historical to-be-replied data contained in the historical communication data, wherein the historical to-be-replied data in one set of historical communication data refers to communication context, and the historical reply data refers to reply content generated by the communication context; alternatively, the historical data to be replied in the set of historical communication data refers to network questioning data, and the historical reply data refers to answers generated for the network questioning data, and the like.

After all the historical reply data contained in the historical communication data are obtained, the corresponding historical reply data can be obtained for each piece of the historical reply data, and the occurrence times of each piece of the historical reply data are obtained.

Further, after each piece of historical reply data and the corresponding historical reply data are obtained, the historical reply data with the occurrence times larger than the preset times (such as 20, 30 and the like) can be obtained as the corresponding reply data aiming at each piece of historical reply data; the historical reply data can be ranked according to the occurrence times from high to low, and then the historical reply data ranked in the first few bits (such as 4, 5 and the like) are obtained as reply data and the like, so that the mapping relation between the data to be recovered and the reply data can be obtained.

Taking the example that the number of occurrences is greater than the preset number (e.g., 20), the data to be replied is "how many points are going to work? "comprising two pieces of reply data, respectively: (1) 8 points (2)9 points; data to be replied to "do you eat rice? "comprising six pieces of reply data, respectively: (1) after eating (2) none (3) has been eaten yet (4) has been eaten, (5) has been eaten and (6) has no woolen cloth; the data to be replied "breakfast rest, evening" contains one piece of replied data, specifically: (1) evening. It can be appreciated that embodiments of the present invention are directed to specific mappings.

Technical proposal 3,

In the technical solution 3, step 202 of determining a reply candidate corresponding to the information to be replied may specifically include: extracting first characteristic information of the information to be replied; determining a first reply rule corresponding to the first characteristic information based on a corresponding relation between the pre-established characteristic information and the reply rule; at least one reply candidate is determined by the first reply rule.

For example, the feature information is, for example: preset sentences, preset sentence formats, etc., the preset sentences are, for example: "has eaten", "has sleeping in several points", "has good, etc., the preset sentence format is, for example: "you go to XX for meal today or to XX for meal", "you eat XX today or XX" (where XX is the default word), etc. In a specific implementation process, a corresponding reply rule may be respectively constructed for each feature information, for example: the reply rule is constructed for "having eaten" as follows: (1) has been eaten (2) has not yet been eaten (3) is ready to be eaten; the reply rule is constructed aiming at 'eating the mixed flour of the peas in the state of ten thousand per se or eating the rice with fragrance per se' today as follows: (1) the wan zhou pea surfaces (2) emit fragrance, and the like, and other recovery rules can be constructed, so that the embodiment of the invention is not limited.

As an optional embodiment, said determining said at least one reply candidate by said first reply rule comprises: extracting at least one specific keyword in the information to be replied; the at least one specific keyword is combined with the first reply rule, thereby obtaining the at least one reply candidate.

For example, assuming that the preset sentence format is "you want to go to XX to eat or to XX to eat" the reply rule constructed for it is: i go to XX for a meal today, where XX represents a default item in the message to be replied to, for example: the first data to be replied is "you want to go home to eat or go to the day to eat" and the default words (i.e. specific keywords) include: home, richlet, whereby the at least one reply candidate constructed includes: (1) i go to restaurant A to eat today; (2) i go to restaurant B today to eat. In addition, since the user may not necessarily eat in both places, other reply candidates may also be added, such as: (3) random, etc. The method comprises the steps of carrying out a first treatment on the surface of the Also for example, for "today's dumpling or noodle", a reply rule is constructed for it: by eating XX today, the default words "dumpling", "noodle" are combined with the reply rule, whereby the at least one reply candidate constructed comprises: (1) the dumplings are eaten today; (2) noodles are eaten today, etc. According to the scheme, at least one reply candidate can be determined based on the specific keywords contained in the information to be replied, so that the determined reply candidate has higher relevance and is more accurate with the information to be replied.

Technical proposal 4,

In the technical solution 4, step 202 of determining a reply candidate corresponding to the information to be replied may specifically include: determining user state information through an application program of the terminal in an operating state; and determining reply candidates corresponding to the information to be replied according to the user state information.

In the technical solution 4, user state information is used in the process of generating a reply candidate, and the user state information obtained by an application in a running state can reflect the use situation of the user for the application, for example, when the user receives information from a communication opposite terminal through a terminal or when the user replies to the information from the communication opposite terminal through the terminal, the use situation of the user for the application may specifically include: the user generates a series of user actions such as setting, browsing, purchasing, watching and the like through the APP in the running state, so that the reply candidates generated according to the user state information can carry deep information except judgment replies, the reply candidates can be matched with the accurate reply intention of the user, and the accuracy and the richness of the quick reply candidates are improved. Under the condition that the reply candidates meet the accurate reply intention of the user, the user can directly reply the information by using the reply candidates, and the input cost of the user in reply of the information can be further reduced, so that the reply efficiency can be improved.

For example, when the user M receives a short message, the user M is watching a video through the video APP, so that corresponding user state information can be obtained through the video APP, and when the content of the short message is a problem such as "in the main prayer", "watching a video", "watching a television play", and other reply candidates can be generated according to the user state information; or, when the content of the short message is, for example, "eat is not done," reply candidates such as "no-go" may be generated based on the user status information, and "watch video", "not yet watch drama", "watch drama while eating" and the like.

The above description of the process of determining the reply candidate corresponding to the information to be replied by using the technical solutions 1 to 4 is described in detail, and it can be understood that, according to actual application requirements, one skilled in the art may adopt any one or a combination of the technical solutions 1 to 4, or may also adopt other technical solutions, and the embodiment of the present invention does not limit the specific process of determining the reply candidate corresponding to the information to be replied.

Step 203 may present the reply candidates for selection by the user. Optionally, in response to a triggering operation of a user on any reply candidate, a target reply candidate corresponding to the triggering operation may be displayed on a screen, where the screen may be: and outputting the target reply candidate to an input box of a communication window.

According to an embodiment, the displaying the reply candidate may specifically include: and displaying the reply candidates above the input method keyboard. After the input method keyboard is called up, at least one reply candidate may be presented above the input method keyboard if the user does not generate any input strings, or generates any input strings. According to another embodiment, the reply candidates may be displayed by means of a pop-up window or a cover. It will be appreciated that the embodiments of the present invention are not limited to the specific manner of presenting the reply candidates described above.

In an alternative embodiment of the present invention, step 203 displays the reply candidate, which may specifically include: sorting the plurality of reply candidates according to the social relationship between the home terminal user and the opposite terminal user; and displaying the sorted multiple reply candidates.

In practical application, the social relationship between the local end user and the opposite end user can be determined by the following modes: acquiring communication content between the opposite terminal user and the local terminal user; extracting a first predetermined keyword contained in the communication content; and determining the social relationship between the local end user and the opposite end user based on the first preset keyword.

For example, a database may be preset, where the database includes at least one social relationship and keywords corresponding to each social relationship. Keywords such as "lover relationship" may include: keywords for "Si Mida", "honey", "loved", "couple" relationship may include: keywords for "wife", "boss", "colleague" may include: "project", "worker", "Leader", "Madam", etc.

And further, after the communication content between the opposite terminal user and the local terminal user is obtained, whether the communication content contains any keywords can be judged, if the communication content contains any keywords, the communication content is extracted to be used as first preset keywords, and then the social relationship is determined through the first preset keywords.

Alternatively, for each reply candidate, a probability that it belongs to a social relationship may be determined, and then a plurality of reply candidates are output after being ranked according to the probability, for example: if the social relationship is a lover relationship, the reply candidates include: (1) evening (2) and evening (3), loving, the probabilities of the three reply candidates belonging to lovers are respectively: 0.1, 0.6, 0.9, three reply candidates may be output in the following order: (1) evening, loving (2) ease (3) evening. In the above scheme, the plurality of reply candidates can be ranked according to the social relationship, so that the rationality of the ranking result can be improved.

In summary, the data processing method of the embodiment of the invention supports that the user carries the information to be replied through the clipboard, so that the information to be replied can be determined from the clipboard information, and reply candidates corresponding to the information to be replied are provided, and therefore, the reply efficiency can be improved. The embodiment of the invention can be applied to a reply scene crossing communication windows, in particular, a user can copy information in a first communication window and jump to a second communication window, so that the embodiment of the invention can automatically determine information to be replied from clipboard information and provide reply candidates corresponding to the information to be replied, thereby realizing intelligent reply in the reply scene crossing the communication windows and improving the reply efficiency.

Method embodiment II

Referring to fig. 3, a flowchart illustrating steps of a second embodiment of a data processing method according to the present invention may specifically include the following steps:

step 301, determining information to be replied from clipboard information; the information to be replied can correspond to all or part of the clipboard information;

step 302, determining reply candidates corresponding to the information to be replied;

and step 303, displaying the reply candidates and the clipboard information.

The embodiment of the invention can display the reply candidates and the clipboard information at the same time, so that the comparison display effect between the clipboard information and the reply candidates can be realized, and a user can know that the reply candidates reply aiming at the clipboard information.

Referring to FIG. 4, a schematic of an interface of an embodiment of the present invention is shown, which may specifically include: a communication window 401 and an input method interface 402;

wherein the communication window 401 may include: communication content and an input box. Taking the communication window between the user a and the user B as an example, the communication content may include: communication content 1 transmitted by user B and communication content 2 transmitted by user a, and the like.

The input method interface 402 may include: the input method keyboard 421, the clipboard information area 422 and the reply candidate area 423, wherein the clipboard information area 422 may be located above the input method keyboard 421, and the clipboard information area 422 may cover part or all of the input method tools; the reply candidates 423 may be located in the clipboard information area 423.

Clipboard information area 422 may include: clipboard information, and prompt information corresponding to the clipboard information, such as "from clipboard" and the like.

The reply candidate area 423 may include: n (n is a natural number) reply candidates, and corresponding prompt information, such as "intelligent reply".

If a click operation of the user on one reply candidate is received, the target reply candidate corresponding to the click operation can be output to the input box.

In an optional embodiment of the present invention, it may be determined whether the communication content of the communication window includes the clipboard information, if yes, the clipboard information is not displayed, and if not, the clipboard information is displayed. The judgment can avoid the repetition of clipboard information.

It should be noted that, for simplicity of description, the method embodiments are shown as a series of acts, but it should be understood by those skilled in the art that the embodiments are not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the embodiments. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred embodiments, and that the acts are not necessarily required by the embodiments of the invention.

Device embodiment

Referring to fig. 5, there is shown a block diagram of an embodiment of a data processing apparatus according to the present invention, which may specifically include:

the to-be-replied information determining module 501 is configured to determine to-be-replied information from clipboard information; the information to be replied can correspond to all or part of the clipboard information;

A reply candidate determining module 502, configured to determine a reply candidate corresponding to the information to be replied; and

and a reply candidate display module 503, configured to display the reply candidate.

Optionally, the apparatus may further include:

and the clipboard information display module is used for displaying the clipboard information.

Optionally, the reply candidate display module 503 is specifically configured to display the reply candidate above the input method keyboard.

Optionally, the type of clipboard information may include at least one of the following types: text, picture, audio, video, and page addresses.

Optionally, the reply candidate determination module 502 may include:

the theme determining module is used for determining a theme corresponding to the information to be replied;

and the candidate determining module is used for determining reply candidates corresponding to the information to be replied according to the theme.

Optionally, the theme determination module may include:

the first theme determining module is used for determining a theme corresponding to the page address according to the content of the page corresponding to the page address; and/or

The second theme determining module is used for carrying out first identification on the video stream and/or the audio stream corresponding to the video and determining a theme corresponding to the video according to the obtained first identification result; and/or

The third theme determining module is used for carrying out second recognition on the picture and determining a theme corresponding to the picture according to the obtained second recognition result; and/or

And the fourth theme determining module is used for carrying out voice recognition on the audio and determining the theme corresponding to the information to be replied according to the obtained voice recognition result.

Optionally, the reply candidate determination module 502 may include:

the searching module is used for searching in the mapping relation between the data to be replied and the reply data according to the information to be replied so as to obtain reply candidates corresponding to the information to be replied;

the mapping relationship is obtained according to historical communication data corresponding to at least one user, and the historical communication data may include: historical data to be replied and corresponding historical reply data.

Optionally, the reply candidate display module 503 may include:

the ordering module is used for ordering the plurality of reply candidates according to the social relationship between the local end user and the opposite end user;

the ordering display module is used for displaying the ordered multiple reply candidates.

For the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points.

In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described by differences from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other.

The specific manner in which the various modules perform the operations in the apparatus of the above embodiments have been described in detail in connection with the embodiments of the method, and will not be described in detail herein.

An embodiment of the present invention provides an apparatus for data processing, including a memory, and one or more programs, wherein the one or more programs are stored in the memory, and configured to be executed by one or more processors, the one or more programs comprising instructions for: determining information to be replied from the clipboard information; the information to be replied corresponds to all or part of the clipboard information; determining reply candidates corresponding to the information to be replied; the reply candidates are shown.

Fig. 6 is a block diagram illustrating an apparatus 800 for data processing according to an example embodiment. For example, apparatus 800 may be a mobile phone, computer, digital broadcast terminal, messaging device, game console, tablet device, medical device, exercise device, personal digital assistant, or the like.

Referring to fig. 6, apparatus 800 may include one or more of the following components: a processing component 802, a memory 804, a power component 806, a multimedia component 808, an audio component 810, an input/output (I/O) interface 812, a sensor component 814, and a communication component 816.

The processing component 802 generally controls overall operation of the apparatus 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. Processing element 802 may include one or more processors 820 to execute instructions to perform all or part of the steps of the methods described above. Further, the processing component 802 can include one or more modules that facilitate interactions between the processing component 802 and other components. For example, the processing component 802 can include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.

The memory 804 is configured to store various types of data to support operations at the device 800. Examples of such data include instructions for any application or method operating on the device 800, contact data, phonebook data, messages, pictures, videos, and the like. The memory 804 may be implemented by any type or combination of volatile or nonvolatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk.

The power supply component 806 provides power to the various components of the device 800. The power components 806 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the device 800.

The multimedia component 808 includes a screen between the device 800 and the user that provides an output interface. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may sense not only the boundary of a touch or slide action, but also the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and/or a rear camera. The front camera and/or the rear camera may receive external multimedia data when the device 800 is in an operational mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 includes a Microphone (MIC) configured to receive external audio signals when the device 800 is in an operational mode, such as a call mode, a recording mode, and a voice data processing mode. The received audio signals may be further stored in the memory 804 or transmitted via the communication component 816. In some embodiments, audio component 810 further includes a speaker for outputting audio signals.

The I/O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which may be a keyboard, click wheel, buttons, etc. These buttons may include, but are not limited to: homepage button, volume button, start button, and lock button.

The sensor assembly 814 includes one or more sensors for providing status assessment of various aspects of the apparatus 800. For example, the sensor assembly 814 may detect an on/off state of the device 800, a relative positioning of the components, such as a display and keypad of the apparatus 800, the sensor assembly 814 may also detect a change in position of the apparatus 800 or one component of the apparatus 800, the presence or absence of user contact with the apparatus 800, an orientation or acceleration/deceleration of the apparatus 800, and a change in temperature of the apparatus 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscopic sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 816 is configured to facilitate communication between the apparatus 800 and other devices, either in a wired or wireless manner. The device 800 may access a wireless network based on a communication standard, such as WiFi,2G or 3G, or a combination thereof. In one exemplary embodiment, the communication component 816 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, the communication component 816 further includes a Near Field Communication (NFC) module to facilitate short range communications. For example, the NFC module may be implemented based on radio frequency data processing (RFID) technology, infrared data association (IrDA) technology, ultra Wideband (UWB) technology, bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the apparatus 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic elements for executing the methods described above.

In an exemplary embodiment, a non-transitory computer readable storage medium is also provided, such as memory 804 including instructions executable by processor 820 of apparatus 800 to perform the above-described method. For example, the non-transitory computer readable storage medium may be ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

Fig. 7 is a schematic diagram of a server in some embodiments of the invention. The server 1900 may vary considerably in configuration or performance and may include one or more central processing units (central processing units, CPU) 1922 (e.g., one or more processors) and memory 1932, one or more storage media 1930 (e.g., one or more mass storage devices) that store applications 1942 or data 1944. Wherein the memory 1932 and storage medium 1930 may be transitory or persistent. The program stored in the storage medium 1930 may include one or more modules (not shown), each of which may include a series of instruction operations on a server. Still further, a central processor 1922 may be provided in communication with a storage medium 1930 to execute a series of instruction operations in the storage medium 1930 on the server 1900.

The server 1900 may also include one or more power supplies 1926, one or more wired or wireless network interfaces 1950, one or more input/output interfaces 1958, one or more keyboards 1956, and/or one or more operating systems 1941, such as Windows Server, mac OS XTM, unixTM, linuxTM, freeBSDTM, and the like.

A non-transitory computer readable storage medium, which when executed by a processor of an apparatus (server or terminal) enables the apparatus to perform the data processing method shown in fig. 2 or 3.

A non-transitory computer readable storage medium, which when executed by a processor of an apparatus (server or terminal), causes the apparatus to perform a data processing method, the method comprising: determining information to be replied from the clipboard information; the information to be replied corresponds to all or part of the clipboard information; determining reply candidates corresponding to the information to be replied; the reply candidates are shown.

The embodiment of the invention discloses A1, a data processing method, which comprises the following steps:

determining reply candidates corresponding to the information to be replied;

the reply candidates are shown.

A2, the method of A1, the method further comprising:

and displaying the clipboard information.

A3, the method of A1 or A2, the displaying the reply candidate, comprising:

And displaying the reply candidates above the input method keyboard.

A4, the method according to A1 or A2, wherein the type of clipboard information includes at least one of the following types: text, picture, audio, video, and page addresses.

A5, determining a reply candidate corresponding to the information to be replied according to the method of A1 or A2, including:

determining a theme corresponding to the information to be replied;

and determining reply candidates corresponding to the information to be replied according to the theme.

A6, according to the method of A5, the determining the theme corresponding to the information to be replied includes:

determining a theme corresponding to a page address according to the content of the page corresponding to the page address; and/or

Performing first identification on a video stream and/or an audio stream corresponding to a video, and determining a theme corresponding to the video according to an obtained first identification result; and/or

Performing second identification on the picture, and determining a theme corresponding to the picture according to an obtained second identification result; and/or

And carrying out voice recognition on the audio, and determining the theme corresponding to the information to be replied according to the obtained voice recognition result.

A7, determining a reply candidate corresponding to the information to be replied according to the method of A1 or A2, including:

Searching in a mapping relation between the data to be replied and the reply data according to the information to be replied to obtain reply candidates corresponding to the information to be replied;

the mapping relationship is obtained according to historical communication data corresponding to at least one user, and the historical communication data comprises: historical data to be replied and corresponding historical reply data.

A8, the method of A1 or A2, the displaying the reply candidate, comprising:

sorting the plurality of reply candidates according to the social relationship between the home terminal user and the opposite terminal user;

and displaying the sorted multiple reply candidates.

The embodiment of the invention discloses a B9 data processing device, which comprises:

B10, the apparatus of B9, the apparatus further comprising:

B11, the device according to B9 or B10, wherein the reply candidate display module is specifically configured to display the reply candidate above the input method keyboard.

B12, the device of B9 or B10, wherein the type of clipboard information comprises at least one of the following types: text, picture, audio, video, and page addresses.

B13, the apparatus of B9 or B10, the reply candidate determination module comprising:

B14, the apparatus of B13, the topic determination module comprising:

B15, the apparatus of B9 or B10, the reply candidate determination module comprising:

B16, the apparatus of B9 or B10, the reply candidate display module comprising:

The embodiment of the invention discloses a C17, a device for data processing, which comprises a memory and one or more programs, wherein the one or more programs are stored in the memory, and are configured to be executed by one or more processors, and the one or more programs comprise instructions for:

determining reply candidates corresponding to the information to be replied;

the reply candidates are shown.

C18, the device of C17, the device further configured to be executed by one or more processors the one or more programs including instructions for:

and displaying the clipboard information.

C19, the device of C17 or C18, the displaying the reply candidate comprising:

and displaying the reply candidates above the input method keyboard.

C20, the apparatus of C17 or C18, the type of clipboard information comprising at least one of: text, picture, audio, video, and page addresses.

C21, the apparatus according to C17 or C18, the determining the reply candidate corresponding to the information to be replied includes:

determining a theme corresponding to the information to be replied;

C22, according to the apparatus of C21, the determining the theme corresponding to the information to be replied includes:

C23, the device according to C17 or C18, the determining the reply candidate corresponding to the information to be replied includes:

C24, the device of C17 or C18, the displaying the reply candidate comprising:

And displaying the sorted multiple reply candidates.

Embodiments of the invention disclose D25, a machine-readable medium having instructions stored thereon, which when executed by one or more processors, cause an apparatus to perform a data processing method as described in one or more of A1 to A8.

Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.

It is to be understood that the invention is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the invention is limited only by the appended claims.

The foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the invention are intended to be included within the scope of the invention.

The foregoing has outlined a data processing method, a data processing device and a device for data processing in detail, wherein specific examples are provided herein to illustrate the principles and embodiments of the present invention, and the above examples are provided to assist in understanding the method and core idea of the present invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.

Claims

1. A method of data processing, the method comprising:

determining reply candidates corresponding to the information to be replied;

displaying the reply candidates;

wherein, the clipboard information includes: information, and a sender identification of the information; the determining the information to be replied from the clipboard information comprises the following steps: filtering the sender identification from the clipboard information, only reserving the information, and determining the information as information to be replied;

The determining the reply candidate corresponding to the information to be replied comprises the following steps: extracting first characteristic information and at least one specific keyword of the information to be replied; determining a first reply rule corresponding to the first characteristic information based on a corresponding relation between the pre-established characteristic information and the reply rule; and combining the at least one specific keyword with the first reply rule to determine at least one reply candidate.

2. The method according to claim 1, wherein the method further comprises:

and displaying the clipboard information.

3. The method of claim 1 or 2, wherein the presenting the reply candidate comprises:

and displaying the reply candidates above the input method keyboard.

4. The method according to claim 1 or 2, wherein the type of clipboard information comprises at least one of the following types: text, picture, audio, video, and page addresses.

5. The method according to claim 1 or 2, wherein the determining a reply candidate corresponding to the information to be replied includes:

determining a theme corresponding to the information to be replied;

6. The method of claim 5, wherein the determining the topic corresponding to the information to be replied comprises:

7. The method according to claim 1 or 2, wherein the determining a reply candidate corresponding to the information to be replied includes:

8. The method of claim 1 or 2, wherein the presenting the reply candidate comprises:

and displaying the sorted multiple reply candidates.

9. A data processing apparatus, comprising:

the reply candidate display module is used for displaying the reply candidates;

wherein, the clipboard information includes: information, and a sender identification of the information; the to-be-replied information determining module comprises: filtering the sender identification from the clipboard information, only reserving the information, and determining the information as information to be replied;

the reply candidate determination module includes: extracting first characteristic information and at least one specific keyword of the information to be replied; determining a first reply rule corresponding to the first characteristic information based on a corresponding relation between the pre-established characteristic information and the reply rule; and combining the at least one specific keyword with the first reply rule to determine at least one reply candidate.

10. The apparatus of claim 9, wherein the apparatus further comprises:

11. The apparatus according to claim 9 or 10, wherein the reply candidate display module is specifically configured to display the reply candidate above an input method keyboard.

12. The apparatus of claim 9 or 10, wherein the type of clipboard information comprises at least one of the following types: text, picture, audio, video, and page addresses.

13. The apparatus according to claim 9 or 10, wherein the reply candidate determination module comprises:

14. The apparatus of claim 13, wherein the topic determination module comprises:

15. The apparatus according to claim 9 or 10, wherein the reply candidate determination module comprises:

16. The apparatus of claim 9 or 10, wherein the reply candidate display module comprises:

17. An apparatus for data processing comprising a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more processors, the one or more programs comprising instructions for:

determining reply candidates corresponding to the information to be replied;

displaying the reply candidates;

18. The device of claim 17, wherein the device is further configured to be executed by one or more processors the one or more programs include instructions for:

and displaying the clipboard information.

19. The apparatus of claim 17 or 18, wherein the presenting the reply candidate comprises:

and displaying the reply candidates above the input method keyboard.

20. The apparatus of claim 17 or 18, wherein the type of clipboard information comprises at least one of the following types: text, picture, audio, video, and page addresses.

21. The apparatus according to claim 17 or 18, wherein the determining a reply candidate corresponding to the information to be replied comprises:

determining a theme corresponding to the information to be replied;

22. The apparatus of claim 21, wherein the determining the topic corresponding to the information to be replied to comprises:

23. The apparatus according to claim 17 or 18, wherein the determining a reply candidate corresponding to the information to be replied comprises:

24. The apparatus of claim 17 or 18, wherein the presenting the reply candidate comprises:

And displaying the sorted multiple reply candidates.

25. A machine readable medium having instructions stored thereon, which when executed by one or more processors, cause an apparatus to perform the data processing method of one or more of claims 1 to 8.