CN111427459B

CN111427459B - Method and related device for optimizing input during user communication

Info

Publication number: CN111427459B
Application number: CN201910016100.6A
Authority: CN
Inventors: 费腾; 崔欣; 张扬
Original assignee: Beijing Sogou Technology Development Co Ltd
Current assignee: Beijing Sogou Technology Development Co Ltd
Priority date: 2019-01-08
Filing date: 2019-01-08
Publication date: 2024-04-02
Anticipated expiration: 2039-01-08
Also published as: CN111427459A

Abstract

The application discloses a method and a related device for optimizing input during user communication, wherein the method comprises the following steps: after input content and a second user identifier are obtained based on the input of a first user to a second user, determining a target text from the input content; and finding a target user language model which is pre-established based on the historical communication input text of the second user through the second user identifier, searching candidate texts with the similarity to the target text being larger than a preset value, and determining the replacement text corresponding to the target text based on the candidate texts and sending the candidate texts to the second user. Therefore, in the communication process of the first user and the second user, after the target text is determined based on the input of the first user, the target user language model corresponding to the second user identifier is adopted, so that the replacement text which accords with the language habit of the second user and is similar to the target text can be obtained and sent to the second user, the condition that the second user is not suitable for, does not understand or misunderstand the communication text is avoided, and the communication between the two communication parties is more consistent.

Description

Method and related device for optimizing input during user communication

Technical Field

The present disclosure relates to the field of communications technologies, and in particular, to a method and an apparatus for input optimization during user communications.

Background

With the rapid development of internet technology, people can communicate with others by utilizing communication channels such as instant messaging application, network interaction platform and the like, and input is mostly carried out by adopting an input method during communication.

When a user inputs by using an input method, candidate texts or screen texts are obtained by using a language model of the user in most cases based on the input operation of the user, and the selected candidate texts are screen-displayed and sent to a communication object or the screen texts are directly sent to the communication object so as to complete communication between the user and the communication object.

However, there may be a large difference in language habits of different users expressing the same content, that is, the language habits of two users communicating with each other are different, for example, "you true" when user a expresses exaggeration and "you very nice" when user B expresses exaggeration, and "you true" is not considered to express exaggeration. Therefore, in the prior art, the communication text sent by the user only accords with the language habit of the user and does not accord with the language habit of the communication object by utilizing the language model of the user to input and complete communication, so that the communication object is not suitable for the communication text at one time, and even the communication text is possibly not understood or misunderstood.

Disclosure of Invention

The technical problem to be solved by the application is to provide a method and a related device for optimizing input during user communication, which can obtain a replacement text which accords with the language habit of a second user and is similar to a target text and send the replacement text to the second user, so as to avoid the condition that the second user is not suitable for, does not understand or misunderstand the communication text, and further enable communication and communication between two parties to be more consistent.

In a first aspect, embodiments of the present application provide a method for input optimization when a user communicates, the method including:

receiving input content and a second user identification in response to input of a first user to a second user, wherein the input content comprises at least one candidate text or on-screen text;

determining a target text from the input content;

searching a text with similarity larger than a preset value with the target text as a candidate text in a target user language model corresponding to the second user identifier, wherein the target user language model is pre-established according to a historical communication input text of the second user;

determining a replacement text corresponding to the target text according to the candidate text;

and sending the replacement text to the second user.

Optionally, the method further comprises:

obtaining the target user language model from a user language model library according to the second user identifier; the user language model library comprises a user language model of each user, user identifiers and corresponding relations among the user language models, and the user language model of each user is pre-established according to historical communication input text of each user.

Optionally, the searching, in the target user language model corresponding to the second user identifier, for a text with a similarity with the target text greater than a preset value as a candidate text specifically includes:

and searching texts with similarity larger than a preset value with the target text as candidate texts according to the similarity of the word vectors in the target user language model.

Optionally, in the target user language model, searching, according to the similarity of the word vector, a text with a similarity greater than a preset value with the target text as a candidate text includes:

according to the target text and the target user language model, obtaining word vectors corresponding to the target text and word vectors corresponding to each text in the target user language model;

and searching texts with the similarity larger than a preset value with the target text as candidate texts based on the similarity of the word vectors corresponding to the target text and the word vectors corresponding to the texts in the target user language model.

Optionally, the determining, according to the candidate text, a replacement text corresponding to the target text includes:

prompting the first user for the candidate text;

in response to a first user selection of the candidate text, determining that the selected candidate text is a replacement text for the target text.

Optionally, the prompting the candidate text to the first user specifically includes:

if the target text is the on-screen text, prompting the candidate text to the first user as a corrected on-screen text; or alternatively, the first and second heat exchangers may be,

and if the target text is one candidate text in the at least one candidate text, prompting the candidate text to the first user as a correction candidate text.

Optionally, the determining, according to the candidate text, a replacement text corresponding to the target text specifically includes:

and directly determining the replacement text corresponding to the target text according to the candidate text.

Optionally, if a plurality of candidate texts are searched, the directly determining, according to the candidate texts, a replacement text corresponding to the target text specifically includes:

and selecting one candidate text from the plurality of candidate texts according to a preset rule, and determining the candidate text as a replacement text corresponding to the target text.

Optionally, the selecting a candidate text from the plurality of candidate texts according to a preset rule determines that the candidate text is a replacement text corresponding to the target text, specifically:

and determining the candidate text with the maximum similarity with the target text from the plurality of candidate texts as a replacement text corresponding to the target text.

Optionally, the method further comprises:

and updating a user language model corresponding to the first user identifier according to the replacement text.

In a second aspect, embodiments of the present application provide an apparatus for input optimization in user communication, the apparatus comprising:

a receiving unit, configured to receive input content and a second user identifier in response to an input from a first user to a second user, where the input content includes at least one candidate text or an on-screen text;

a first determining unit configured to determine a target text from the input content;

the searching unit is used for searching texts with similarity larger than a preset value with the target texts in target user language models corresponding to the second user identifications as candidate texts, and the target user language models are pre-established according to the historical communication input texts of the second user;

A second determining unit, configured to determine a replacement text corresponding to the target text according to the candidate text;

and the sending unit is used for sending the replacement text to the second user.

Optionally, the method further comprises an obtaining unit;

the obtaining unit is used for obtaining the target user language model from a user language model library according to the second user identifier; the user language model library comprises a user language model of each user, user identifiers and corresponding relations among the user language models, and the user language model of each user is pre-established according to historical communication input text of each user.

Optionally, the search unit is specifically configured to:

Optionally, the search unit includes an acquisition subunit and a search subunit;

the obtaining subunit is configured to obtain, according to the target text and the target user language model, a word vector corresponding to the target text and a word vector corresponding to each text in the target user language model;

the searching subunit is configured to search, based on the word vector corresponding to the target text and the similarity of the word vector corresponding to each text in the target user language model, for a text with a similarity greater than a preset value as a candidate text.

Optionally, the second determining unit includes a prompt subunit and a determining subunit;

the prompting subunit is configured to prompt the first user for the candidate text;

the determining subunit is configured to determine, in response to a selection operation of the candidate text by the first user, that the selected candidate text is a substitute text for the target text.

Optionally, the first prompting subunit is specifically configured to:

Optionally, the second determining unit is specifically configured to:

Optionally, if a plurality of candidate texts are searched, the second determining unit is specifically configured to:

Optionally, the second determining unit is specifically configured to:

Optionally, the device further comprises an updating unit;

and the updating unit is used for updating the user language model corresponding to the first user identifier according to the replacement text.

In a third aspect, embodiments of the present application provide an apparatus for input optimization when a user communicates, the apparatus 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 a target text from the input content;

and sending the replacement text to the second user.

In a fourth aspect, embodiments of the present application provide a machine-readable medium having instructions stored thereon, which when executed by one or more processors, cause an apparatus to perform one or more of the methods of input optimization at user communication described in the first aspect above.

Compared with the prior art, the application has at least the following advantages:

according to the technical scheme, after input content and a second user identifier are obtained based on input of a first user to a second user, firstly, a target text is determined from the input content, then, a target user language model which is built in advance based on historical communication input text of the second user is found through the second user identifier, candidate texts with similarity to the target text being larger than a preset value are searched, and replacement texts corresponding to the target text are determined based on the candidate texts and are sent to the second user. Therefore, in the communication process of the first user and the second user, after the target text is determined based on the input of the first user, a target user language model corresponding to the second user identifier is adopted, and the replacement text which accords with the language habit of the second user and is similar to the target text can be obtained and sent to the second user, so that the condition that the second user is not suitable for, does not understand or misunderstand the communication text is avoided, and communication between two communication parties are more consistent.

Drawings

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

Fig. 1 is a schematic diagram of a system frame related to an application scenario in an embodiment of the present application;

FIG. 2 is a flowchart of a method for input optimization during user communication according to an embodiment of the present application;

FIG. 3 is an exemplary diagram of a modification candidate text prompt interface according to an embodiment of the present application;

FIG. 4 is a diagram illustrating an example of a modified on-screen text prompt interface provided in an embodiment of the present application;

FIG. 5 is a flowchart of another method for input optimization during user communication according to an embodiment of the present application;

FIG. 6 is a schematic structural diagram of an apparatus for input optimization in user communication according to an embodiment of the present application;

FIG. 7 is a block diagram of an apparatus for input optimization in user communication provided by an embodiment of the present application;

Fig. 8 is a schematic structural diagram of a server according to an embodiment of the present application.

Detailed Description

In order to make the present application solution better understood by those skilled in the art, the following description will clearly and completely describe the technical solution in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.

In general, a user performs communication input by using an input method to complete communication, specifically, based on input operation of the user, a candidate text or an on-screen text is obtained by using a language model of the user, for example, a candidate text "you true line" is obtained by inputting a pinyin string "nizhenxing" through a user keyboard, or an on-screen text "you true line" is obtained by inputting "you true line" through user voice; the follow-up user selects a candidate text 'you true line' to be displayed on the screen and sent to a communication object, or the display text 'you true line' is directly sent to the communication object, namely 'you true line' is used as the communication text to complete communication between the user and the communication object.

However, the inventor finds that, for both communication parties communicating with each other, there may be a difference in language habits expressing the same content, for example, user a and user B are both communication parties, user a uses "you true line" when expressing exaction, and user B uses "you very nice" when expressing exaction, and does not consider "you true line" to be used for expressing exaction, so, in the manner of the prior art, user a uses a language model of the user itself to perform communication input "you true line" to send to user B, and the communication text "you true line" does not conform to the language habits of user B, so that user B is not adapted to the communication text at one time, and even does not understand or misunderstand the communication text, resulting in uncomfortable communication between user a and user B of both communication parties.

In order to solve the problem, in the embodiment of the application, based on the input of the first user to the second user, after the input content and the second user identifier are obtained first; then, determining a target text from the input content; secondly, a target user language model which is built in advance based on the historical communication input text of the second user is found through the second user identification, and candidate texts with similarity to the target text larger than a preset value are searched in the target user language model; and finally, determining the replacement text corresponding to the target text based on the candidate text and sending the replacement text to the second user. Therefore, in the communication process of the first user and the second user, the target text is determined based on the input content obtained by the input of the first user to the second user, and the replacement text which is similar to the target text and can replace the target text is found in the target user language model which corresponds to the second user identification and accords with the language habit of the second user and is sent to the second user, so that the second user is easy to adapt to and understand the communication text, and the communication between the two communication parties is more consistent.

For example, one of the scenarios of the embodiments of the present application may be applied to the scenario shown in fig. 1, where the scenario includes a server 101, a first user terminal 102, and a second user terminal 103, and the first user uses the first user terminal 102 to communicate with the second user having the second user terminal 103. First, a first user performs a communication input operation to a second user at a first user terminal 102, and the server 101 receives input content and a second user identification in response to the operation; then, the server 101 determines a target text from the input content; secondly, the server 101 searches candidate texts with similarity to the target text being larger than a preset value in a target user language model which corresponds to the second user identifier and is pre-established according to the historical communication input text of the second user; next, the server 101 determines a replacement text corresponding to the target text based on the candidate text, and finally, the server 101 transmits the replacement text to the second user terminal 103 so that the second user terminal 103 displays the replacement text to the second user.

It is to be understood that, in the above application scenario, although the actions of the embodiments of the present application are described as being performed by the server 101, part of the actions may be performed by the first user terminal 102 and part of the actions may be performed by the server 101. That is, the present application is not limited in terms of execution subject, and the operations disclosed in the embodiments of the present application may be executed.

Specific implementation manners of the method and the related device for optimizing input during user communication in the embodiments of the present application are described in detail below by way of embodiments with reference to the accompanying drawings.

Exemplary method

Referring to fig. 2, a flow chart of a method for input optimization in user communication in an embodiment of the present application is shown. In this embodiment, the method may include, for example, the steps of:

step 201: in response to input by the first user to the second user, input content including at least one candidate text or on-screen text and a second user identification are received.

It can be understood that the embodiment of the application is applied to a scenario in which the user a and the user B are used as communication parties to communicate, for example, the user a is used as a first user, the user B is used as a second user, or the user B is used as a first user, the user a is used as a second user, and when the first user performs an input operation to the second user, in order to solve the problem in the prior art that a candidate text or an on-screen text is obtained by using a language model of the first user and is directly sent to the second user as a communication text, there is a situation that the second user is not suitable for, does not understand or misunderstand the communication text, and the server should first receive the input content obtained by the input operation of the first user to the second user and needs to determine the identification of the second user as the communication object of the first user.

The input content is obtained based on the input of the first user to the second user, and is transmitted to the server by the corresponding first user terminal, and when the input modes are different, the input content forms are different. For example, when a first user performs keyboard pinyin input to a second user, candidate text may be used as input content; for another example, when the first user performs voice input or handwriting input to the second user, the candidate text may be used as the input content, and the on-screen text may also be used as the input content.

Step 202: and determining target text from the input content.

It is to be understood that the target text is a text determined based on the input content to be subjected to correction replacement, and therefore, when the input content is a candidate text, a candidate text is determined based on the candidate text as the target text; when the input content is the on-screen text, the on-screen text is directly used as the target text. In summary, in some implementations of the present embodiment, the target text is one of candidate texts obtained based on the input of the first user to the second user or an on-screen text obtained based on the input of the first user to the second user.

As an example, in response to the first user entering "nizhenxing" into the second user keyboard, each candidate text "you true line", "you true want", "you true" … … may be used as input, and the server determines the first candidate text "you true line" from each candidate text "you true line", "you true want", "you true" … … as the target text. As another example, in response to the first user entering "ni zhenxing" into the second user keyboard, the server may directly determine the first candidate text "you true line" as the target text with the first candidate text "you true line" as the input content. As yet another example, in response to a first user entering or handwriting "you true line" into a second user, the server may take the on-screen text "you true line" as input content and directly determine the on-screen text "you true line" as the target text.

Step 203: searching a text with similarity larger than a preset value with the target text as a candidate text in a target user language model corresponding to the second user identifier, wherein the target user language model is pre-established according to the historical communication input text of the second user.

It should be noted that, in order to implement the embodiment of the present application, before the implementation of the embodiment of the present application, the server should determine the language habit of each user, and since the historical communication input text of each user can embody the language habit of each user, the user language model of each user may be obtained and stored based on the historical communication input text of each user. And in order to facilitate the subsequent searching of the user language model corresponding to each user, for each user, the corresponding relation between the unique user identifier and the user language model should be set and stored, so that the corresponding user language model can be quickly found based on the unique user identifier. Thus, in some implementations of the present embodiment, further comprising:

step A: a user language model of each user is built in advance according to the historical communication input text of each user;

and (B) step (B): and constructing a user language model library according to the user identification of each user, the user language model and the corresponding relation between the user language model.

On the premise of obtaining a user language model library in advance, after the second user identifier is obtained in step 201, a target user language model capable of expressing the language habit of the second user is found in the user language model library based on the second user identifier, so that a text with higher similarity with the target text determined in step 202 is searched in the target user language model, and the searched text is similar to the expression content of the target text, so that the target text can be used for replacing the target text and accords with the language habit of the second user. Thus, in some implementations of the present embodiment, prior to step 203, step C may be further included, for example: and obtaining the target user language model from a user language model library according to the second user identification.

It should be further noted that, since each text in the target text and the target user language model is formed by terms, and each term has a corresponding specific term vector, the similarity of the term vectors of the two texts including the term may represent the similarity of the two texts, and therefore, the text in the target user language model having a similarity with the target text greater than the preset value may be searched as the candidate text based on the similarity of the term vectors of each text in the target text and the target user language model. Thus, in some implementations of the present embodiment, a word vector similarity technique may be used when performing step 203, i.e., the step 203 may be, for example, specifically: and searching texts with similarity larger than a preset value with the target text as candidate texts according to the similarity of the word vectors in the target user language model.

When the method is specifically implemented, the similarity between the word vector corresponding to the target text and the word vector corresponding to each text in the target user language model is calculated, and the word vector corresponding to the target text and the word vector corresponding to each text in the target user language model are needed to be obtained; and then calculating the similarity of word vectors between the target text and each text, so that the text with the similarity larger than a preset value with the target text in the target user language model can be searched as the candidate text. Thus, in some implementations of the present example, the step 203 may include, for example, the steps of:

Step D: according to the target text and the target user language model, obtaining word vectors corresponding to the target text and word vectors corresponding to each text in the target user language model;

step E: and searching texts with the similarity larger than a preset value with the target text as candidate texts based on the similarity of the word vectors corresponding to the target text and the word vectors corresponding to the texts in the target user language model.

As an example, if the second user identifier received in step 201 is the user B identifier, the target text determined in step 202 is "you true", and first, a corresponding target user language model is obtained in the user language model library according to the user B identifier as a user B language model, where the user B language model includes the text "you very nice", "you very stick", "you very severe" … …; then, word vectors corresponding to the target text 'you really line' and word vectors corresponding to the texts in the user B language model are obtained, the similarity between the word vectors corresponding to the target text 'you really line' and the word vectors corresponding to the texts in the user B language model is calculated, and according to the similarity, texts with the similarity of the target text 'you really line' larger than a preset value are searched as candidate texts, wherein the candidate texts are 'you very nice', 'you very stick' and 'you very bad'.

Step 204: and determining a replacement text corresponding to the target text according to the candidate text.

It should be noted that, in the embodiment of the present application, after searching for a candidate text with a similarity to the target text greater than a preset value in step 203, the following two ways may be at least used to determine the replacement text corresponding to the target text according to the candidate text:

in the first optional implementation manner of step 204, for the candidate text that has a similarity with the target text that is greater than the preset value and is searched in step 203, the candidate text has a higher similarity with the target text and accords with the language habit of the second user, and considering user humanized selection, the server may send the candidate text to the first user terminal to prompt the first user, so that the first user may select the prompted candidate text, and based on the user selection operation, the server may determine that the selected candidate text is the replacement text of the target text. Thus, in some implementations of this embodiment, the step of determining, in step 204, a replacement text corresponding to the target text according to the candidate text may include, for example, the steps of:

step F: the candidate text is prompted to the first user.

It should be noted that, since the target text is one candidate text among the candidate texts obtained based on the input of the first user to the second user or the on-screen text obtained based on the input of the first user to the second user. That is, there are two types of target texts, the types of target texts are different, and the prompting modes of the corresponding candidate texts are also different. Specifically, the prompting of the candidate text to the first user may employ two prompting modes as follows:

in the first prompting mode, when the target text is one candidate text in the candidate texts obtained based on the input of the first user to the second user, the text to be replaced is the candidate text, and the candidate text is used as the correction candidate text to prompt the first user, so that the user can select the prompted correction candidate text.

For example, as shown in fig. 3, a correction candidate text prompt interface exemplary diagram is shown, in which, the target text shown in the left graph is "your true line" of the candidate texts obtained by the input of the first user to the second user, after searching that the candidate text with the similarity to the target text "your true line" being greater than the preset value is "you very nice", the candidate text "you very nice" can be used as the correction candidate text to prompt the first user in a candidate text correction box near the candidate text "you true line" as shown in the right graph.

In the second prompting mode, when the target text is the screen text obtained based on the input of the first user to the second user, the text to be replaced is the screen text, and the candidate text is used as the corrected screen text to prompt the first user, so that the user can select the prompted corrected screen text.

For example, as shown in fig. 4, a diagram of an example of a corrected on-screen text prompt interface is shown, in which, the target text is "your true line" of the on-screen text obtained based on the input of the first user to the second user, and after the candidate text having a similarity greater than the preset value with the target text "your true line" is searched for as "you very nice", the candidate text "you very nice" may be prompted to the first user as the corrected on-screen text in an on-screen text correction box near the on-screen text "you true line" as shown in the right diagram.

Step G: in response to a first user selection of the candidate text, determining that the selected candidate text is a replacement text for the target text.

It should be noted that, in the target user language model, there may be one or more texts with similarity to the target text greater than a preset value, and step 203 may search for one or more texts with similarity to the target text greater than the preset value as candidate texts. When only one candidate text with similarity to the target text greater than the preset value is searched, for the first alternative implementation mode adopted in step 204, only one candidate text is prompted to the first user in step F, so that the result of the selection operation of the candidate text by the first user in step G can only be the only candidate text prompted in step F, and the candidate text is the replacement text of the corresponding target text. When a plurality of candidate texts with similarity to the target text being greater than the preset value are searched, for the first alternative implementation mode adopted in the step 204, the step F prompts the first user that the plurality of candidate texts are adopted, so that the step G determines that the selected candidate text is the alternative text of the target text based on the selection operation of the first user on the plurality of candidate texts.

As an example, if step 203 searches for a candidate text "your very nice" having a similarity to the target text "your very nice" greater than the preset value, prompts the text "you very nice" to the first user as a unique candidate text, and determines the first candidate text "you very nice" as a substitute text corresponding to the target text "your very nice" in response to the first user selecting the unique candidate text "you very nice".

As another example, if step 203 searches for a plurality of candidate texts "very nice", "very excellent" and "very severe" having a similarity with the target text "very little" greater than the preset value, the text "very nice" may be used as the first candidate text, the text "very excellent" may be used as the second candidate text, the text "very severe" may be used as the third candidate text to prompt the first user, and in response to the first user selecting the candidate text "very nice", "very excellent" and "very severe" from the first candidate texts "very little", the selected first candidate text "very little" is determined as the replacement text of the target text "very little".

In the second optional implementation manner of step 204, for the candidate text that has a similarity with the target text that is greater than the preset value and is searched in step 203, because the candidate text has a high similarity with the target text and accords with the language habit of the second user, the server may directly determine the alternative text corresponding to the target text based on the candidate text. Thus, in some implementations of this embodiment, the step of determining, in step 204, a replacement text corresponding to the target text according to the candidate text may be, for example, specifically: and directly determining the replacement text corresponding to the target text according to the candidate text.

Similarly, it should be noted that, in the target user language model, there may be one or more texts with similarity to the target text greater than a preset value, and step 203 may search for one or more texts with similarity to the target text greater than the preset value as candidate texts. When only one candidate text having a similarity to the target text greater than the preset value is searched, for the second alternative embodiment, the unique candidate text is directly determined as the alternative text of the corresponding target text for step 204. When a plurality of candidate texts with similarity to the target text being greater than the preset value are searched, for the step 204, a second alternative implementation mode is adopted, and one candidate text is selected from the plurality of candidate texts according to a preset rule to be determined as a replacement text of the corresponding target text.

It should be noted that, for selecting one candidate text from the plurality of candidate texts according to the preset rule, determining the candidate text as the replacement text of the corresponding target text may be implemented in the following two ways:

in the first mode, each candidate text in the plurality of candidate texts with the similarity larger than the preset value is different from the target text in similarity, and only the candidate text with the maximum similarity with the target text can be used for replacing the target text accurately compared with other candidate texts, so that the candidate text can be determined to be the replacement text of the corresponding target text. Therefore, in some implementations of the present embodiment, the candidate text having the greatest similarity to the target text among the plurality of candidate texts is determined as the substitute text corresponding to the target text.

In the second mode, although the similarity between each candidate text and the target text in the plurality of candidate texts with the similarity between the candidate text and the target text being larger than the preset value is different, the candidate texts can be used for replacing the target text more accurately based on the fact that the similarity between each candidate text and the target text is larger than the preset value, and one candidate text can be randomly determined to be the replacement text corresponding to the target text in consideration of the randomness and diversity of the replacement text. Thus, in some implementations of the present embodiments, one candidate text is randomly determined from a plurality of candidate texts as a replacement text for the corresponding target text.

As an example, if step 203 searches for a plurality of candidate texts "very nice", "very excellent" and "very powerful" with the similarity to the target text "very excellent" being greater than the similarity to the target text "very true" and the similarity to the target text "very excellent" being greater than the similarity to the target text "very powerful" and the similarity to the target text "very true" in the candidate text "very excellent" being greater than the similarity to the target text "very powerful" and the target text "true". Then the candidate text 'you very nice' with the greatest similarity with the target text 'you true line' can be determined as the replacement text corresponding to the target text 'you true line'; a candidate text may also be randomly determined from among the candidate texts "you very nice", "you very excellent" and "you very severe" as a replacement text for the target text "you true line".

Step 205: and sending the replacement text to the second user.

It will be appreciated that after determining the replacement text corresponding to the target text in step 204, the replacement text that accords with the language habit of the second user and is similar to the target text needs to be sent to the second user, so as to avoid the situation that the second user does not adapt, does not understand or misunderstand the communication text, and thus the communication between the two communication parties is more consistent.

After the second user sends the replacement text, the similarity between the replacement text and the target text is larger than the preset value, which indicates that the similarity between the replacement text and the target text is higher, and the replacement text is derived from the target user language model corresponding to the second user identifier, which indicates that the replacement text accords with the language habit of the second user. Thus, in some implementations of the present embodiment, further comprising: and updating a user language model corresponding to the first user identifier according to the replacement text.

With the various embodiments provided in this embodiment, after obtaining the input content and the second user identifier based on the input of the first user to the second user, first, a target text is determined from the input content, then, a target user language model previously established based on the history communication input text of the second user is found through the second user identifier, candidate texts having a similarity with the target text greater than a preset value are searched for, and a substitute text corresponding to the target text is determined based on the candidate texts and sent to the second user. Therefore, in the communication process of the first user and the second user, after the target text is determined based on the input of the first user, a target user language model corresponding to the second user identifier is adopted, and the replacement text which accords with the language habit of the second user and is similar to the target text can be obtained and sent to the second user, so that the condition that the second user is not suitable for, does not understand or misunderstand the communication text is avoided, and communication between two communication parties are more consistent.

Taking a first user as a user a and a second user as a user B for example to communicate with a second user by pinyin input "ni zhenxing", taking humanized setting of the user's independently selected alternative text as an example, a specific implementation manner of another prompting method for communication input text in the embodiment of the present application is described in detail by a further embodiment with reference to fig. 5.

Referring to fig. 5, a flow chart of another method for input optimization in user communication in an embodiment of the present application is shown. In this embodiment, the method may include, for example, the steps of:

step 501: in response to user a entering "nizhenxing" into user B keyboard pinyin, the input content is received as a first candidate text "you true line", a second candidate text "you true want" and a third candidate text "you true" … …, and the second user identification is user B identification.

Step 502: the first candidate text "your true line" is determined as the target text from the first candidate text "your true line", the second candidate text "your true want" and the third candidate text "your true" … ….

Step 503: and obtaining a user B language model from a user language model library according to the user B identification, wherein the user language model library comprises a user language model of each user, the user identification and a corresponding relation among the user language model, and the user language model of each user is pre-established according to the historical communication input text of each user.

Step 504: and obtaining word vectors corresponding to the target text 'you true line' and word vectors corresponding to the texts in the user B language model according to the target text 'you true line' and the user B language model.

Step 505: searching texts with the similarity of the target text 'you true line' greater than a preset value 'you very nice', 'you very stick' and 'you very bad' as candidate texts based on the similarity of word vectors corresponding to the target text 'you true line' and word vectors corresponding to the texts in the user B language model.

Step 506: the candidate texts of "you very nice", "you very excellent" and "you very severe" are prompted to the user a as correction candidate texts of the first candidate text "you true line".

Step 507: in response to user a's selection of the candidate text "you very nice", it is determined that "you very nice" is the replacement text for the target text "you true line".

Step 508: the replacement text "you very nice" corresponding to the target text "you true line" is sent to user B.

Exemplary apparatus

Referring to fig. 6, a schematic structural diagram of an apparatus for input optimization in user communication in an embodiment of the present application is shown. In this embodiment, the apparatus may specifically include, for example:

a receiving unit 601, configured to receive input content and a second user identifier in response to an input from a first user to a second user, where the input content includes at least one candidate text or on-screen text;

a first determining unit 602, configured to determine a target text from the input content;

a searching unit 603, configured to search, in a target user language model corresponding to the second user identifier, for a text having a similarity with the target text that is greater than a preset value as a candidate text, where the target user language model is pre-established according to a history communication input text of the second user;

a second determining unit 604, configured to determine, according to the candidate text, a replacement text corresponding to the target text;

and a sending unit 605 configured to send the replacement text to the second user.

Optionally, the apparatus further comprises an obtaining unit;

Optionally, the searching unit 603 is specifically configured to:

Optionally, the search unit 603 includes an obtaining subunit and a search subunit;

Optionally, the second determining unit 604 includes a prompt subunit and a determining subunit;

Optionally, the first prompting subunit is specifically configured to:

Optionally, the second determining unit 604 is specifically configured to:

Optionally, if a plurality of candidate texts are searched, the second determining unit 604 is specifically configured to:

Optionally, the second determining unit 604 is specifically configured to:

Optionally, the apparatus further comprises an updating unit;

Fig. 7 is a block diagram illustrating an apparatus 700 for input optimization when a user communicates, according to an exemplary embodiment. For example, apparatus 700 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. 7, an apparatus 700 may include one or more of the following components: a processing component 702, a memory 704, a power component 706, a multimedia component 708, an audio component 710, an input/output (I/O) interface 712, a sensor component 714, and a communication component 716.

The processing component 702 generally controls overall operation of the apparatus 700, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 702 may include one or more processors 720 to execute instructions to perform all or part of the steps of the methods described above. Further, the processing component 702 can include one or more modules that facilitate interaction between the processing component 702 and other components. For example, the processing component 702 may include a multimedia module to facilitate interaction between the multimedia component 708 and the processing component 702.

Memory 704 is configured to store various types of data to support operations at device 700. Examples of such data include instructions for any application or method operating on the apparatus 700, contact data, phonebook data, messages, pictures, videos, and the like. The memory 704 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 706 provides power to the various components of the device 700. The power components 706 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the device 700.

The multimedia component 708 includes a screen between the device 700 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 708 includes a front-facing camera and/or a rear-facing camera. The front-facing camera and/or the rear-facing camera may receive external multimedia data when the device 700 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 710 is configured to output and/or input audio signals. For example, the audio component 710 includes a Microphone (MIC) configured to receive external audio signals when the device 700 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may be further stored in the memory 704 or transmitted via the communication component 716. In some embodiments, the audio component 710 further includes a speaker for outputting audio signals.

The I/O interface 712 provides an interface between the processing component 702 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 714 includes one or more sensors for providing status assessment of various aspects of the apparatus 700. For example, the sensor assembly 714 may detect an on/off state of the device 700, a relative positioning of the components, such as a display and keypad of the apparatus 700, a change in position of the apparatus 700 or one component of the apparatus 700, the presence or absence of user contact with the apparatus 700, an orientation or acceleration/deceleration of the apparatus 700, and a change in temperature of the apparatus 700. The sensor assembly 714 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 714 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 714 may also include an acceleration sensor, a gyroscopic sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 716 is configured to facilitate communication between the apparatus 700 and other devices in a wired or wireless manner. The apparatus 700 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 part 716 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 716 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 Identification (RFID) technology, infrared data association (IrDA) technology, ultra Wideband (UWB) technology, bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the apparatus 700 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 components for executing the methods described above.

In an exemplary embodiment, a non-transitory computer readable storage medium is also provided, such as memory 704, including instructions executable by processor 720 of apparatus 700 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.

A non-transitory computer readable storage medium, which when executed by a processor of a mobile terminal, causes the mobile terminal to perform a method of input optimization in user communication, the method comprising:

determining a target text from the input content;

and sending the replacement text to the second user.

Fig. 8 is a schematic structural diagram of a server in an embodiment of the present application. The server 800 may vary considerably in configuration or performance and may include one or more central processing units (central processing units, CPUs) 822 (e.g., one or more processors) and memory 832, one or more storage media 830 (e.g., one or more mass storage devices) storing applications 842 or data 844. Wherein the memory 832 and the storage medium 830 may be transitory or persistent. The program stored in the storage medium 830 may include one or more modules (not shown), each of which may include a series of instruction operations on a server. Still further, the central processor 822 may be configured to communicate with the storage medium 830 to execute a series of instruction operations in the storage medium 830 on the server 800.

The server 800 may also include one or more power supplies 826, one or more wired or wireless network interfaces 850, one or more input/output interfaces 858, one or more keyboards 856, and/or one or more operating systems 841, such as Windows ServerTM, mac OS XTM, unixTM, linuxTM, freeBSDTM, and the like.

In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.

Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of functionality in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

The foregoing description is only of the preferred embodiments of the present application and is not intended to limit the present application in any way. While the present application has been described with reference to the preferred embodiments, it is not intended to limit the present application. Any person skilled in the art may make many possible variations and modifications to the technical solution of the present application, or modify equivalent embodiments, using the methods and technical contents disclosed above, without departing from the scope of the technical solution of the present application. Therefore, any simple modification, equivalent variation and modification of the above embodiments according to the technical substance of the present application, which do not depart from the content of the technical solution of the present application, still fall within the scope of protection of the technical solution of the present application.

Claims

1. A method of input optimization in user communication, comprising:

determining a target text from the input content;

according to the target text and the target user language model corresponding to the second user identifier, obtaining word vectors corresponding to the target text and word vectors corresponding to each text in the target user language model;

searching texts with the similarity larger than a preset value as candidate texts based on the similarity of word vectors corresponding to the target texts and word vectors corresponding to each text in the target user language model, wherein the target user language model is pre-established according to the historical communication input texts of the second user;

determining a replacement text corresponding to the target text according to the candidate text; the candidate text is similar to the target text and accords with the language habit of the second user;

and sending the replacement text to the second user.

2. The method as recited in claim 1, further comprising:

3. The method of claim 1, wherein the determining the alternate text corresponding to the target text from the candidate text comprises:

prompting the first user for the candidate text;

4. A method according to claim 3, characterized in that said prompting said first user for said candidate text, in particular:

5. The method according to claim 1, wherein the determining, from the candidate text, a replacement text corresponding to the target text is specifically:

6. The method according to claim 5, wherein if a plurality of candidate texts are searched, the directly determining the alternative text corresponding to the target text according to the candidate texts is specifically:

7. The method according to claim 6, wherein selecting one candidate text from the plurality of candidate texts according to a preset rule is determined as a replacement text corresponding to the target text, specifically:

8. The method as recited in claim 1, further comprising:

9. An apparatus for input optimization in user communication, comprising:

the obtaining subunit is used for obtaining word vectors corresponding to the target text and word vectors corresponding to each text in the target user language model according to the target text and the target user language model corresponding to the second user identifier;

a searching subunit, configured to search, in the target user language model, for a text with a similarity to the target text being greater than a preset value as a candidate text based on a word vector corresponding to the target text and a similarity of word vectors corresponding to respective texts in the target user language model, where the target user language model is pre-established according to a history communication input text of the second user;

a second determining unit, configured to determine a replacement text corresponding to the target text according to the candidate text; the candidate text is similar to the target text and accords with the language habit of the second user;

10. The apparatus of claim 9, further comprising an obtaining unit;

11. The apparatus of claim 9, wherein the second determination unit comprises a hint subunit and a determination subunit;

12. The apparatus of claim 11, wherein the hint subunit is specifically configured to:

13. The apparatus according to claim 9, wherein the second determining unit is specifically configured to:

14. The apparatus of claim 13, wherein if a plurality of candidate texts are searched, the second determining unit is specifically configured to:

15. The apparatus according to claim 14, wherein the second determining unit is specifically configured to:

16. The apparatus of claim 9, further comprising an updating unit;

17. An apparatus for input optimization at user communication 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 to perform the method of input optimization at user communication of one or more of claims 1-8.

18. A machine readable medium having instructions stored thereon, which when executed by one or more processors, cause an apparatus to perform the method of input optimization at user communication of one or more of the above claims 1 to 8.