CN115543099A - Input method, device and device for input - Google Patents

Input method, device and device for input Download PDF

Info

Publication number
CN115543099A
CN115543099A CN202110752127.9A CN202110752127A CN115543099A CN 115543099 A CN115543099 A CN 115543099A CN 202110752127 A CN202110752127 A CN 202110752127A CN 115543099 A CN115543099 A CN 115543099A
Authority
CN
China
Prior art keywords
candidate
current
candidate item
server
local
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110752127.9A
Other languages
Chinese (zh)
Inventor
余天照
崔欣
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Sogou Technology Development Co Ltd
Original Assignee
Beijing Sogou Technology Development Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Sogou Technology Development Co Ltd filed Critical Beijing Sogou Technology Development Co Ltd
Priority to CN202110752127.9A priority Critical patent/CN115543099A/en
Publication of CN115543099A publication Critical patent/CN115543099A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/02—Input arrangements using manually operated switches, e.g. using keyboards or dials
    • G06F3/023—Arrangements for converting discrete items of information into a coded form, e.g. arrangements for interpreting keyboard generated codes as alphanumeric codes, operand codes or instruction codes
    • G06F3/0233—Character input methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
    • G06F3/0487—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser
    • G06F3/0488—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning

Abstract

The embodiment of the application discloses an input method, an input device and a device for inputting. An embodiment of the method comprises: extracting feature information from current input data of a user; inputting the characteristic information into a pre-trained candidate item comparison model to obtain a comparison result, wherein the candidate item comparison model is used for comparing the advantages and disadvantages of candidate items from different sources; and determining display positions of the current local candidate item and the current server candidate item based on the comparison result, and displaying the candidate items based on the display positions. The embodiment improves the preferred hit rate of the input method and the input efficiency of the user.

Description

Input method, device and device for input
Technical Field
The embodiment of the application relates to the technical field of computers, in particular to an input method, an input device and a device for inputting.
Background
When a user inputs by using the input method client, the input method can not only select candidate items from the local word stock of the client, but also can obtain the candidate items from the server by sending a request to the server.
In the prior art, usually, a candidate item locally obtained from a client is displayed in a candidate column above a keyboard, and a candidate item delivered by a server is displayed in a fixed secondary position, for example, a cloud candidate position above the right of the keyboard. Due to the fact that the capacity and the computing performance of the local word bank are limited, the candidate items issued by the server side are superior to the local candidate items in many cases, and target words expected by a user can be hit more easily, so that the first-choice hit rate of the input method is low easily caused by the existing mode, and further the input efficiency of the user is low.
Disclosure of Invention
The embodiment of the application provides an input method, an input device and an input device, and aims to solve the technical problems that in the prior art, the input method is low in preferred hit rate and low in user input efficiency.
In a first aspect, an embodiment of the present application provides an input method, where the method includes: extracting feature information from current input data of a user; inputting the characteristic information into a pre-trained candidate item comparison model to obtain a comparison result, wherein the candidate item comparison model is used for comparing the advantages and disadvantages of candidate items from different sources; and determining the display positions of the current local candidate item and the current server candidate item based on the comparison result, and displaying the candidate items based on the display positions.
In some embodiments, the current local candidate and the current server candidate are included in the current input data; and the extracting of feature information from the current input data of the user includes: extracting input characteristics, local candidate item characteristics and server candidate item characteristics from current input data of a user; and summarizing the input features, the local candidate item features and the server candidate item features to obtain feature information.
In some embodiments, the input features include at least one of: current input string length, current above length; the local candidate item features include at least one of: the length and the number of the current local candidate items, the word frequency of the first candidate items and the types of the first candidate items; the server candidate feature comprises at least one of: the length and the number of the candidate items of the current server side, the word frequency of the first candidate items and the types of the first candidate items.
In some embodiments, the determining, based on the comparison result, the display positions of the current local candidate item and the current server candidate item includes: in response to the comparison result indicating that the current server candidate item is superior to the current local candidate item, showing a preference in the current server candidate item at a head of a candidate bar, and showing a preference in the current local candidate item at a next head of the candidate bar; or, in response to the comparison result indicating that the current local candidate item is superior to the current server candidate item, showing the preference in the current local candidate item at the head of the candidate bar, and showing the preference in the current server candidate item at the next head of the candidate bar.
In some embodiments, the candidate item comparison model is obtained by training: acquiring historical input data of a user, wherein the historical input data comprises historical local candidate items and historical server candidate items issued by a server; dividing the historical input data into a positive sample and a negative sample based on the hit conditions of the historical local candidate and the historical server candidate on the user screen candidate; training a classification model based on the positive sample and the negative sample to obtain a candidate item comparison model.
In some embodiments, the dividing the historical input data into positive samples and negative samples based on hits of the historical local candidates and the historical server candidates on screen candidates of the user includes: for each piece of historical input data, if a history server candidate item in the historical input data hits a user screen candidate item and a history local candidate item does not hit the user screen candidate item, taking the historical input data as a positive sample; the historical input data other than the positive samples are taken as negative samples.
In some embodiments, the training a classification model based on the positive sample and the negative sample to obtain a candidate item comparison model includes: summarizing the positive samples and the negative samples into a sample set; extracting characteristic information from the samples in the sample set, taking the characteristic information of the samples as input of a classification model, carrying out supervised training on the classification model based on the sample type corresponding to the input characteristic information, and determining the trained classification model as a candidate item comparison model.
In some embodiments, after candidate item presentation based on the presentation position, the method further comprises: in response to the fact that a user selects the current server candidate item, the current input data is used as a positive sample, and the candidate item comparison model is retrained on the basis of the positive sample so as to update the candidate item comparison model; or in response to the user selecting the current local candidate item, the current input data is used as a negative sample, and the candidate item comparison model is retrained based on the negative sample so as to update the candidate item comparison model.
In a second aspect, an embodiment of the present application provides an input device, including: an extraction unit configured to extract feature information from current input data of a user; the comparison unit is configured to input the characteristic information into a pre-trained candidate item comparison model to obtain a comparison result, and the candidate item comparison model is used for comparing the advantages and the disadvantages of candidate items from different sources; and the display unit is configured to determine the display positions of the current local candidate item and the current server candidate item based on the comparison result, and display the candidate items based on the display positions.
In some embodiments, the current local candidate and the current server candidate are included in the current input data; and the extraction unit is further configured to: extracting input features, local candidate item features and server candidate item features from current input data of a user; and summarizing the input characteristics, the local candidate item characteristics and the server candidate item characteristics to obtain characteristic information.
In some embodiments, the input features include at least one of: current input string length, current above length; the local candidate item features include at least one of: the length and the number of the current local candidate items, the word frequency of the first candidate items and the type of the first candidate items; the server candidate feature comprises at least one of: the length and the number of the candidate items of the current server side, the word frequency of the first candidate items and the types of the first candidate items.
In some embodiments, the presentation unit is further configured to: in response to the comparison result indicating that the current server candidate item is superior to the current local candidate item, showing a preference in the current server candidate item at a head of a candidate bar, and showing a preference in the current local candidate item at a next head of the candidate bar; or, in response to the comparison result indicating that the current local candidate item is superior to the current server candidate item, showing the preference in the current local candidate item at the head of the candidate bar, and showing the preference in the current server candidate item at the next head of the candidate bar.
In some embodiments, the candidate item comparison model is trained by: acquiring historical input data of a user, wherein the historical input data comprises historical local candidate items and historical server candidate items issued by a server; dividing the historical input data into a positive sample and a negative sample based on the hit conditions of the historical local candidate and the historical server candidate on the user screen candidate; and training a classification model based on the positive sample and the negative sample to obtain a candidate item comparison model.
In some embodiments, the dividing the historical input data into positive samples and negative samples based on hits of the historical local candidates and the historical server candidates on screen candidates of the user includes: for each piece of historical input data, if the historical server candidate in the historical input data hits the user on-screen candidate and the historical local candidate does not hit the user on-screen candidate, taking the historical input data as a positive sample; the historical input data other than the positive samples are taken as negative samples.
In some embodiments, the training a classification model based on the positive sample and the negative sample to obtain a candidate item comparison model includes: summarizing the positive sample and the negative sample into a sample set; extracting characteristic information from the samples in the sample set, taking the characteristic information of the samples as input of a classification model, carrying out supervised training on the classification model based on the sample type corresponding to the input characteristic information, and determining the trained classification model as a candidate item comparison model.
In some embodiments, the apparatus further includes an updating unit configured to, in response to the user selecting the current server candidate, treat the current input data as a positive sample, and retrain the candidate comparison model based on the positive sample to update the candidate comparison model; or in response to the user selecting the current local candidate item, the current input data is used as a negative sample, and the candidate item comparison model is retrained based on the negative sample so as to update the candidate item comparison model.
In a third aspect, an embodiment of the present application provides an apparatus for input, comprising a memory, and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs are configured to be executed by the one or more processors and comprise instructions for performing the method as described in the first aspect.
In a fourth aspect, embodiments of the present application provide a computer-readable medium, on which a computer program is stored, which when executed by a processor, implements the method described in the first aspect above.
According to the input method, the input device and the input device provided by the embodiment of the application, the characteristic information is extracted from the current input data of a user and is input into a pre-trained candidate item comparison model to obtain a comparison result, so that the display positions of the current local candidate item and the current server candidate item are determined based on the comparison result, and then the candidate item is displayed based on the display positions. The candidate item comparison model can compare the advantages and disadvantages of candidate items from different sources, so that the candidate item comparison model can judge out a better one of the current local candidate item and the current server candidate item based on the current input data, and the better one is displayed in a better position. Compared with the mode that the candidates from different sources are shown in fixed positions, the probability that the candidates from the better positions hit the user expectation is higher, and therefore the first-choice hit rate of the input method and the input efficiency of the user are improved.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the detailed description of non-limiting embodiments made with reference to the following drawings:
FIG. 1 is a flow diagram of one embodiment of an input method according to the present application;
FIG. 2 is a flow diagram of yet another embodiment of an input method according to the present application;
FIG. 3 is a schematic block diagram of one embodiment of an input device according to the present application;
FIG. 4 is a schematic diagram of a structure of an apparatus for input according to the present application;
fig. 5 is a schematic diagram of a server in some embodiments according to the application.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.
It should be noted that, in the present application, the embodiments and features of the embodiments may be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Referring to FIG. 1, a flow 100 of one embodiment of an input method according to the present application is shown. The input method can be operated in various electronic devices including but not limited to: the mobile terminal comprises a server, a smart phone, a tablet computer, an electronic book reader, an MP3 (moving Picture Experts Group Audio Layer III) player, an MP4 (moving Picture Experts Group Audio Layer IV) player, a laptop portable computer, a vehicle-mounted computer, a desktop computer, a set-top box, a smart television, a wearable device and the like.
The input method application mentioned in the embodiment of the present application may refer to an input method client, which is capable of supporting multiple input methods. The input method may be an encoding method used for inputting various symbols to electronic devices such as computers and mobile phones, and a user may conveniently input a desired character or character string to the electronic devices using the input method application. It should be noted that, in the embodiment of the present application, in addition to the common chinese input method (such as pinyin input method, wubi input method, zhuyin input method, phonetic input method, handwriting input method, etc.), the input method may also support other languages (such as english input method, japanese hiragana input method, korean input method, etc.), and the input method and the language category of the input method are not limited at all.
The input method in this embodiment may include the following steps:
step 101, feature information is extracted from current input data of a user.
In this embodiment, an execution subject of the input method (such as the electronic device described above) may be installed with an input method client. The execution main body can acquire the current input data of the user in the input method client in real time and extract the characteristic information from the current input data.
The input data is data which is generated by a user in the input process and is related to input. For example, the information may include, but is not limited to, input strings, the above information, local candidates obtained locally from the client, server candidates delivered by the server, and the like. The user may use various encoding input modes such as pinyin and wubi, or may use a voice input mode, or may use other input modes such as a handwriting input mode, which is not limited specifically. In addition, the local candidate and the server candidate may include, but are not limited to, text, pictures, expressions, and the like, which is not limited in particular. The current input data is the input data generated in the current input process (i.e., the current input process). Accordingly, the current input data may include, but is not limited to, a current input string, current above information, a candidate currently obtained locally from the client (which may be referred to as a current local candidate), a candidate currently issued by the server (which may be referred to as a current server candidate), and so on.
Here, the feature information may be information for characterizing features of the current input data. In some alternative implementations, the characteristics of the input data may include, but are not limited to, an input characteristic, a local candidate characteristic, and a server candidate characteristic. At this time, the execution subject may extract the input feature, the local candidate feature, and the server candidate feature from the current input data of the user, respectively. And summarizing the extracted input features, the local candidate item features and the server candidate item features to obtain feature information. The local candidate item feature may be specifically extracted from a current local candidate item in the current input data, and the server candidate item feature may be specifically extracted from a current server candidate item.
In some examples, the input features may include, but are not limited to, at least one of: current input string length, current above length. The local candidate features may include, but are not limited to, at least one of: the length and the number of the current local candidate items, the word frequency of the first candidate items and the type of the first candidate items. The server candidate features may include, but are not limited to, at least one of: the length and the number of the candidate items of the current server side, the word frequency of the first candidate items and the types of the first candidate items.
And 102, inputting the characteristic information into a pre-trained candidate item comparison model to obtain a comparison result.
In this embodiment, the execution body may store a pre-trained candidate comparison model. The candidate item comparison model can be used for comparing the advantages and disadvantages of candidate items from different sources. Sources of candidates may include, but are not limited to, client local, server. The server here may be hardware or software. When the server is hardware, the server can be implemented as a distributed server cluster formed by a plurality of servers, or can be implemented as a single server. The server can be a physical server or a cloud server. When the server is software, the server may be implemented as a plurality of software or software modules, or may be implemented as a single software or software module. And is not particularly limited herein.
In this embodiment, the candidate item comparison model may be obtained by pre-training by a machine learning method based on historical input data. The executing body may input the feature information extracted in step 101 to the candidate item comparison model to obtain a comparison result output by the candidate item comparison model. In practice, the alignment result may be a numerical value. For example, if the value is greater than a preset value, it may indicate that the current server candidate is better than the current local candidate; otherwise, if the value is smaller than the preset value, the current local candidate item is indicated to be superior to the current server candidate item.
In this embodiment, the candidate item comparison model may be obtained by training the classification model. The classification model may be various models having a classification function, such as a convolutional neural network using an existing structure (e.g., denseBox, VGGNet, resNet, segNet, etc.), a Support Vector Machine (SVM), various types of decision trees, and the like. The training method can be specifically obtained according to the following steps:
first, historical input data of a user is obtained.
The historical input data is input data generated in the historical input process. Such as, but not limited to, the history input string, the above information of the history input string, the candidate obtained locally from the client during the history input process (may be referred to as a history local candidate), the candidate issued by the server during the history input process (may be referred to as a history server candidate), the candidate displayed on the screen of the user, and so on. Based on the historical input data, whether the historical local candidate and the historical server candidate hit the candidate on the screen of the user can be known.
And secondly, dividing the historical input data into a positive sample and a negative sample based on the hit conditions of the historical local candidate and the historical server candidate to the user screen-on candidate.
Here, each piece of history input data may be taken as one sample. And for each piece of historical input data, if the historical server candidate in the historical input data hits the user on-screen candidate and the historical local candidate does not hit the user on-screen candidate, taking the historical input data as a positive sample. Otherwise (i.e., the rest of the cases other than the above), it may be taken as a negative sample. That is, the historical input data other than the positive samples are all negative samples.
And thirdly, training the classification model based on the positive sample and the negative sample to obtain a candidate item comparison model.
Here, the positive and negative samples may be first summarized into a sample set. Then, feature information can be extracted from each sample in the sample set, respectively. Similar to the feature information extracted from the current input data, the feature information extracted from the sample may also include, but is not limited to, input features, local candidate features, and server candidate features. Input features herein may include, but are not limited to, at least one of: historical input string length, historical above length. The local candidate term features herein may be extracted from historical local candidate terms and may include, but are not limited to, at least one of: the length and the number of the historical local candidate items, the word frequency of the first candidate items and the type of the first candidate items. Similarly, the server candidate feature herein may be extracted from historical server candidates, and may include, but is not limited to, at least one of the following: the length and the number of the candidate items of the history server side, the word frequency of the first candidate items and the types of the first candidate items.
After extracting the feature information, the feature information of the sample can be used as the input of a classification model, the supervised training is performed on the classification model based on the sample type (positive sample or negative sample) corresponding to the input feature information, and the trained classification model is determined as a candidate item comparison model.
In the training process, the characteristic information of the sample can be input into the classification model one by one, and a comparison result (which can be a numerical value) output by the end-to-end model is obtained. Then, a loss value of the classification model may be determined based on a sample type (positive sample or negative sample, for example, a positive sample may be represented by 1 and a negative sample may be represented by 0) of the comparison result corresponding to the input feature information. The loss value is a value of a loss function (loss function), and the loss function is a non-negative real-valued function and can be used for representing the difference between the detection result and the real result. In general, the smaller the loss value, the better the robustness of the model. The loss function may be set according to actual requirements. The parameters of the classification model may then be updated with the loss value. Therefore, the loss value can be obtained once when the characteristic information of the sample is input once, and the parameters of the classification model can be updated once based on the loss value until the training is completed.
In practice, whether training is complete may be determined in a number of ways. As an example, when the accuracy of the comparison result output by the classification model reaches a preset value (e.g., 99%), it may be determined that the training is completed. As yet another example, the training may be determined to be completed if the number of times of training of the classification model is equal to a preset number of times. Here, if the training of the classification model is completed, the trained classification model can be used as a candidate item comparison model for comparing the quality of candidate items from different sources.
The candidate item comparison model is obtained by pre-training based on historical input data, and the historical input data can reflect the hit conditions of the client local candidate items and the server candidate items on the target words expected by the user, so that the candidate item comparison model can automatically learn the characteristics of the server candidate items when the server candidate items are more optimal and the characteristics of the local candidate items when the local candidate items are more optimal according to the hit conditions of the candidate items from different sources on the target words, so that the characteristics of the current input data are analyzed and processed in the real-time input process of the user, and the advantages and disadvantages of the current local candidate items and the current server candidate items are automatically distinguished.
And 103, determining display positions of the current local candidate item and the current server candidate item based on the comparison result, and displaying the candidate items based on the display positions.
In this embodiment, the execution subject may determine, based on the comparison result, a display order of the current local candidate item and the current server candidate item, and then determine, based on the display order, display positions of the display order of the current local candidate item and the current server candidate item in the input method panel, so as to display the candidate items based on the display positions.
In some optional implementation manners, if the comparison result indicates that the current candidate item of the server is better than the current local candidate item, the execution main body may rank some or all of the candidate items of the current candidate item of the server before the current local candidate item. Similarly, if the comparison result indicates that the current local candidate item is better than the current server candidate item, the execution subject may rank some or all of the current local candidate items before the current server candidate item.
In some optional implementation manners, if the comparison result indicates that the current candidate of the server is better than the current local candidate, the execution subject may show a preference in the current candidate of the server in a top position of the candidate bar and show a preference in the current candidate of the local server in a next position of the candidate bar. Similarly, if the comparison result indicates that the current local candidate item is better than the current server candidate item, the execution subject may display the preference in the current local candidate item in the top of the candidate bar and display the preference in the current server candidate item in the next of the candidate bar.
It should be noted that the position after the second order may be used for displaying all the non-preference items in the current local candidate item, or may be used for displaying all the non-preference items in the current server candidate item, or may be used for displaying part of the non-preference items in the current local candidate item, or may be used for displaying part of the non-preference items in the current server candidate item. For example, the non-preference in the current server candidate and the non-preference in the current local candidate may be ordered according to a rule (e.g., ordered according to word frequency), and presented in a position next to the next order according to the ordering result.
In addition, it should be noted that, when the candidate item comparison model is initially trained or updated according to a specific period, historical input data of a specific group or a total number of users may be used as training data. After the candidate item comparison model is deployed at a client of a certain user, the candidate item comparison model can be updated in real time by using input data of the user, so that the candidate item comparison model is adapted to the input habit of the user. Therefore, in some optional implementation manners, after the candidate item is displayed based on the display position, the execution main body may further update the candidate item comparison model based on the candidate item selected by the user and the current input data. Specifically, in response to the user selecting the current server candidate item, the current input data may be used as a positive sample, and the candidate item comparison model is retrained based on the positive sample to update the candidate item comparison model. And in response to the user selecting the current local candidate item, the current input data can be used as a negative sample, and the candidate item comparison model is retrained based on the negative sample so as to update the candidate item comparison model. Therefore, the request decision model can be continuously updated, so that the generalization of the request decision model is improved.
In the method provided by the embodiment of the application, the feature information is extracted from the current input data of the user and is input into the pre-trained candidate item comparison model to obtain the comparison result, so that the display positions of the current local candidate item and the current server candidate item are determined based on the comparison result, and then the candidate item is displayed based on the display positions. Because the candidate item comparison model can compare the advantages and disadvantages of candidate items from different sources, the candidate item comparison model can judge out the better of the current local candidate item and the current server candidate item based on the current input data, thereby showing the better in a better position. Compared with the mode that the candidates from different sources are shown in fixed positions, the probability that the candidates from the better positions hit the user expectation is higher, and therefore the first-choice hit rate of the input method and the input efficiency of the user are improved.
With further reference to fig. 2, a flow 200 of yet another embodiment of an input method is shown. The process 200 of the input method comprises the following steps:
step 201, extracting input characteristics, local candidate characteristics and server candidate characteristics from current input data of a user.
In this embodiment, the input data is data related to input generated by the user in the input process, and may include, but is not limited to, an input string, the above information, a local candidate locally obtained from the client, a server candidate delivered by the server, and the like. The current input data is the input data generated in the current input process (i.e. the current input process), which may include, but is not limited to, the current input string, the current above information, the current local candidate, the current server candidate, and the like.
In this embodiment, the execution subject of the input method may extract the input feature, the local candidate feature, and the server candidate feature from the current input data of the user. The local candidate item feature may be specifically extracted from a current local candidate item in the current input data, and the server candidate item feature may be specifically extracted from a current server candidate item. Wherein the input features may include, but are not limited to, at least one of: current input string length, current above length. The local candidate features may include, but are not limited to, at least one of: the length and the number of the current local candidate items, the word frequency of the first candidate items and the type of the first candidate items. The server candidate feature may include, but is not limited to, at least one of: the length and the number of the candidate items of the current server side, the word frequency of the first candidate items and the types of the first candidate items.
Step 202, summarizing the input features, the local candidate item features and the server candidate item features to obtain feature information.
In the embodiment, the input feature, the local candidate feature and the server candidate feature may all be represented in the form of a feature vector. The execution main body can adopt splicing and other modes to input the features, the local candidate item features and the server candidate item features for gathering to obtain new feature vectors, namely feature information.
Step 203, inputting the characteristic information into a pre-trained candidate item comparison model to obtain a comparison result.
Step 203 in this embodiment can refer to step 101 in the corresponding embodiment of fig. 1, and is not described herein again.
In some optional implementation manners of this embodiment, the candidate item comparison model may be obtained by training through the following steps: acquiring historical input data of a user, wherein the historical input data comprises historical local candidate items and historical server candidate items issued by a server; dividing the historical input data into a positive sample and a negative sample based on the hit condition of the historical local candidate item and the historical server candidate item on the user screen candidate item; and training a classification model based on the positive sample and the negative sample to obtain a candidate item comparison model.
In some optional implementation manners of this embodiment, the dividing the history input data into a positive sample and a negative sample based on hits of the history local candidate and the history server candidate on the user screen candidate may include: for each piece of historical input data, if the historical server candidate in the historical input data hits the user on-screen candidate and the historical local candidate does not hit the user on-screen candidate, taking the historical input data as a positive sample; the historical input data other than the positive samples are taken as negative samples.
In some optional implementation manners of this embodiment, the training the classification model based on the positive sample and the negative sample to obtain a candidate item comparison model may include: summarizing the positive sample and the negative sample into a sample set; extracting characteristic information from the samples in the sample set, taking the characteristic information of the samples as input of a classification model, carrying out supervised training on the classification model based on the sample type corresponding to the input characteristic information, and determining the trained classification model as a candidate item comparison model.
And 204, in response to the comparison result indicating that the current server candidate item is superior to the current local candidate item, showing the preference in the current server candidate item to the top of the candidate bar, and showing the preference in the current local candidate item to the next of the candidate bar.
In this embodiment, if the comparison result indicates that the current candidate of the server is better than the current local candidate, the execution subject may show the preference of the current candidate of the server in the top of the candidate bar and show the preference of the current candidate of the local candidate in the next of the candidate bar. The positions after the second order can be used for displaying the non-preference in the current local candidate item, can also be used for displaying the non-preference in the current server candidate item, and is also used for displaying the non-preference in the current local candidate item and is also used for displaying the non-preference in the current server candidate item. For example, the non-preference in the current server candidate and the non-preference in the current local candidate may be ordered according to a rule (e.g., ordered according to word frequency), and presented in a position next to the next order according to the ordering result.
In step 205, in response to the comparison result indicating that the current local candidate is better than the current server candidate, the preference in the current local candidate is shown in the top of the candidate bar, and the preference in the current server candidate is shown in the next of the candidate bar.
In this embodiment, if the comparison result indicates that the current local candidate is better than the current server candidate, the execution subject may show the preference in the current local candidate in the top of the candidate bar and show the preference in the current server candidate in the next of the candidate bar. The position after the next position can be used for displaying the non-preference in the current local candidate item, or can be used for displaying the non-preference in the current server candidate item, or is used for displaying the non-preference in the current local candidate item, or is used for displaying the non-preference in the current server candidate item. For example, the non-preference in the current server candidate and the non-preference in the current local candidate may be sorted according to a rule (for example, sorted according to word frequency), and displayed in a position after the next place according to the sorting result.
In some optional implementation manners, after the candidate item is displayed based on the display position, the execution main body may further update the candidate item comparison model based on the candidate item selected by the user and the current input data. Specifically, in response to the user selecting the current server candidate item, the current input data may be used as a positive sample, and the candidate item comparison model is retrained based on the positive sample to update the candidate item comparison model. In response to the user selecting the current local candidate item, the current input data may be used as a negative sample, and the candidate item comparison model is retrained based on the negative sample to update the candidate item comparison model. Therefore, the request decision model can be continuously updated, so that the generalization of the request decision model is improved.
As can be seen from fig. 2, compared with the embodiment corresponding to fig. 1, the flow 200 of the input method in this embodiment involves a step of determining the top candidate item according to the comparison result. Because the better candidate is arranged at the head, the probability that the candidate at the head hits the expectation of the user is higher, and the first-choice hit rate of the input method and the input efficiency of the user can be improved.
With further reference to fig. 3, as an implementation of the method shown in the above figures, the present application provides an embodiment of an input device, which corresponds to the embodiment of the method shown in fig. 1, and which can be applied in various electronic devices.
As shown in fig. 3, the input device 300 of the present embodiment includes: an extraction unit 301 configured to extract feature information from current input data of a user; a comparison unit 302 configured to input the feature information into a pre-trained candidate item comparison model for comparing the candidate items from different sources to obtain a comparison result; the presentation unit 303 is configured to determine presentation positions of the current local candidate item and the current server candidate item based on the comparison result, and perform candidate item presentation based on the presentation positions.
In some optional implementations of this embodiment, the current input data includes the current local candidate and the current server candidate; and, the above-mentioned extraction unit 301, is further configured to: extracting input characteristics, local candidate item characteristics and server candidate item characteristics from current input data of a user; and summarizing the input characteristics, the local candidate item characteristics and the server candidate item characteristics to obtain characteristic information.
In some optional implementations of the embodiment, the input feature includes at least one of: current input string length, current above length; the local candidate feature includes at least one of: the length and the number of the current local candidate items, the word frequency of the first candidate items and the types of the first candidate items; the server candidate feature includes at least one of the following: the length and the number of the candidate items of the current server side, the word frequency of the first candidate items and the types of the first candidate items.
In some optional implementations of this embodiment, the display unit 303 is further configured to: responding to the comparison result to indicate that the current server candidate item is superior to the current local candidate item, showing a preference in the current server candidate item to a first position of a candidate bar, and showing a preference in the current local candidate item to a second position of the candidate bar; or, in response to the comparison result indicating that the current local candidate item is better than the current server candidate item, showing the preference in the current local candidate item at the top of the candidate bar, and showing the preference in the current server candidate item at the next top of the candidate bar.
In some optional implementation manners of this embodiment, the candidate item comparison model is obtained by training through the following steps: acquiring historical input data of a user, wherein the historical input data comprises historical local candidate items and historical server candidate items issued by a server; dividing the historical input data into a positive sample and a negative sample based on the hit condition of the historical local candidate item and the historical server candidate item on the user screen candidate item; and training a classification model based on the positive sample and the negative sample to obtain a candidate item comparison model.
In some optional implementation manners of this embodiment, the dividing the history input data into a positive sample and a negative sample based on hits of the history local candidate and the history server candidate on the user screen candidate includes: for each piece of historical input data, if the historical server candidate in the historical input data hits the user on-screen candidate and the historical local candidate does not hit the user on-screen candidate, taking the historical input data as a positive sample; the historical input data other than the positive samples are taken as negative samples.
In some optional implementation manners of this embodiment, the training the classification model based on the positive sample and the negative sample to obtain a candidate item comparison model includes: summarizing the positive samples and the negative samples into a sample set; extracting characteristic information from the samples in the sample set, taking the characteristic information of the samples as input of a classification model, carrying out supervised training on the classification model based on the sample type corresponding to the input characteristic information, and determining the trained classification model as a candidate item comparison model.
In some optional implementation manners of this embodiment, the apparatus further includes an updating unit, configured to, in response to a user selecting the current server candidate item, use the current input data as a positive sample, and retrain the candidate item comparison model based on the positive sample to update the candidate item comparison model; or, in response to the user selecting the current local candidate item, the current input data is used as a negative sample, and the candidate item comparison model is retrained based on the negative sample to update the candidate item comparison model.
In the apparatus provided in the above embodiment of the present application, the feature information is extracted from the current input data of the user, and the feature information is input to the candidate item comparison model trained in advance to obtain the comparison result, so that the display positions of the current local candidate item and the current server candidate item are determined based on the comparison result, and then the candidate item is displayed based on the display positions. The candidate item comparison model can compare the advantages and disadvantages of candidate items from different sources, so that the candidate item comparison model can judge out a better one of the current local candidate item and the current server candidate item based on the current input data, and the better one is displayed in a better position. Compared with a mode of showing the candidates from different sources in a fixed position, the probability that the candidate from a better position hits the expectation of the user is higher, and therefore the first-choice hit rate of the input method and the input efficiency of the user are improved.
Fig. 4 is a block diagram illustrating an apparatus 400 for inputting according to an example embodiment, where the apparatus 400 may be an intelligent terminal or a server. For example, the apparatus 400 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, an exercise device, a personal digital assistant, and the like.
Referring to fig. 4, the apparatus 400 may include one or more of the following components: processing components 402, memory 404, power components 406, multimedia components 408, audio components 410, input/output (I/O) interfaces 412, sensor components 414, and communication components 416.
The processing component 402 generally controls overall operation of the apparatus 400, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing element 402 may include one or more processors 420 to execute instructions to perform all or a portion of the steps of the methods described above. Further, the processing component 402 can include one or more modules that facilitate interaction between the processing component 402 and other components. For example, the processing component 402 may include a multimedia module to facilitate interaction between the multimedia component 408 and the processing component 402.
The memory 404 is configured to store various types of data to support operations at the apparatus 400. Examples of such data include instructions for any application or method operating on the device 400, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 404 may be implemented by any type or combination of volatile or non-volatile 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 disks.
Power supply components 406 provide power to the various components of device 400. The power components 406 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the apparatus 400.
The multimedia component 408 includes a screen that provides an output interface between the device 400 and a user. 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 an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of the touch or slide action but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 408 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 400 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 a focal length and optical zoom capability.
The audio component 410 is configured to output and/or input audio signals. For example, audio component 410 includes a Microphone (MIC) configured to receive external audio signals when apparatus 400 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal may further be stored in the memory 404 or transmitted via the communication component 416. In some embodiments, audio component 410 also includes a speaker for outputting audio signals.
The I/O interface 412 provides an interface between the processing component 402 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.
The sensor component 414 includes one or more sensors for providing various aspects of status assessment for the apparatus 400. For example, the sensor component 414 may detect the open/closed state of the device 400, the relative positioning of components, such as a display and keypad of the apparatus 400, the sensor component 414 may also detect a change in position of the apparatus 400 or a component of the apparatus 400, the presence or absence of user contact with the apparatus 400, orientation or acceleration/deceleration of the apparatus 400, and a change in temperature of the apparatus 400. The sensor assembly 414 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 414 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 414 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
The communication component 416 is configured to facilitate wired or wireless communication between the apparatus 400 and other devices. The apparatus 400 may access a wireless network based on a communication standard, such as WiFi,2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 416 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 416 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 400 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, micro-controllers, microprocessors, or other electronic components for performing the above-described methods.
In an exemplary embodiment, a non-transitory computer-readable storage medium comprising instructions, such as the memory 404 comprising instructions, executable by the processor 420 of the apparatus 400 to perform the above-described method is also provided. For example, the non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
Fig. 5 is a schematic diagram of a server in some embodiments of the present application. The server 500, which may vary significantly depending on configuration or performance, may include one or more Central Processing Units (CPUs) 522 (e.g., one or more processors) and memory 532, one or more storage media 530 (e.g., one or more mass storage devices) that store applications 542 or data 544. Memory 532 and storage media 530 may be, among other things, transient storage or persistent storage. The program stored on the storage medium 530 may include one or more modules (not shown), each of which may include a series of instruction operations for the server. Still further, the central processor 522 may be configured to communicate with the storage medium 530, and execute a series of instruction operations in the storage medium 530 on the server 500.
The server 500 may also include one or more power supplies 526, one or more wired or wireless network interfaces 550, one or more input-output interfaces 558, one or more keyboards 556, and/or one or more operating systems 541, such as Windows Server, mac OS XTM, unixTM, linuxTM, freeBSDTM, etc.
A non-transitory computer readable storage medium having instructions therein which, when executed by a processor of an apparatus (smart terminal or server), enable the apparatus to perform an input method, the method comprising: extracting feature information from current input data of a user; inputting the characteristic information into a pre-trained candidate item comparison model to obtain a comparison result, wherein the candidate item comparison model is used for comparing the advantages and disadvantages of candidate items from different sources; and determining display positions of the current local candidate item and the current server candidate item based on the comparison result, and displaying the candidate items based on the display positions.
Optionally, the current input data includes the current local candidate and the current server candidate; and, the extracting feature information from the current input data of the user includes: extracting input characteristics, local candidate item characteristics and server candidate item characteristics from current input data of a user; and summarizing the input features, the local candidate item features and the server candidate item features to obtain feature information.
Optionally, the input features include at least one of: current input string length, current above length; the local candidate item features include at least one of: the length and the number of the current local candidate items, the word frequency of the first candidate items and the type of the first candidate items; the server candidate feature comprises at least one of: the length and the number of the candidate items of the current server side, the word frequency of the first candidate items and the types of the first candidate items.
Optionally, the determining, based on the comparison result, the display positions of the current local candidate item and the current server candidate item includes: in response to the comparison result indicating that the current server candidate item is superior to the current local candidate item, showing a preference in the current server candidate item to a first position of a candidate bar, and showing a preference in the current local candidate item to a second position of the candidate bar; or, in response to the comparison result indicating that the current local candidate item is superior to the current server candidate item, showing the preference in the current local candidate item at the head of the candidate bar, and showing the preference in the current server candidate item at the next head of the candidate bar.
Optionally, the candidate item comparison model is obtained by training through the following steps: acquiring historical input data of a user, wherein the historical input data comprises historical local candidate items and historical server candidate items issued by a server; dividing the historical input data into a positive sample and a negative sample based on the hit condition of the historical local candidate item and the historical server candidate item on the user screen candidate item; and training a classification model based on the positive sample and the negative sample to obtain a candidate item comparison model.
Optionally, the dividing the history input data into a positive sample and a negative sample based on the hit of the history local candidate and the history server candidate to the user screen-up candidate includes: for each piece of historical input data, if the historical server candidate in the historical input data hits the user on-screen candidate and the historical local candidate does not hit the user on-screen candidate, taking the historical input data as a positive sample; the historical input data other than the positive samples are taken as negative samples.
Optionally, training a classification model based on the positive sample and the negative sample to obtain a candidate item comparison model includes: summarizing the positive samples and the negative samples into a sample set; extracting characteristic information from the samples in the sample set, taking the characteristic information of the samples as input of a classification model, carrying out supervised training on the classification model based on the sample type corresponding to the input characteristic information, and determining the trained classification model as a candidate item comparison model.
Optionally, the device being configured to execute the one or more programs by the one or more processors includes instructions for: responding to the fact that a user selects the current server candidate item, taking the current input data as a positive sample, and retraining the candidate item comparison model based on the positive sample to update the candidate item comparison model; or in response to the user selecting the current local candidate item, the current input data is used as a negative sample, and the candidate item comparison model is retrained based on the negative sample so as to update the candidate item comparison model.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice in 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 application being indicated by the following claims.
It will be understood that the present application is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.
The above description is only a preferred embodiment of the present application and should not be taken as limiting the present application, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present application should be included in the protection scope of the present application.
The input method, the input device and the input device provided by the present application are described in detail above, and specific examples are applied herein to illustrate the principles and embodiments of the present application, and the above description of the embodiments is only used to help understand the method and the core idea of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Claims (15)

1. An input method, characterized in that the method comprises:
extracting feature information from current input data of a user;
inputting the characteristic information into a pre-trained candidate item comparison model to obtain a comparison result, wherein the candidate item comparison model is used for comparing the advantages and disadvantages of candidate items from different sources;
and determining the display positions of the current local candidate item and the current server candidate item based on the comparison result, and displaying the candidate items based on the display positions.
2. The method of claim 1, wherein said current input data includes said current local candidate and said current server candidate; and the number of the first and second groups,
the extracting of feature information from the current input data of the user includes:
extracting input characteristics, local candidate item characteristics and server candidate item characteristics from current input data of a user;
and summarizing the input characteristics, the local candidate item characteristics and the server candidate item characteristics to obtain characteristic information.
3. The method of claim 2, wherein the input features comprise at least one of: current input string length, current above length;
the local candidate item features include at least one of: the length and the number of the current local candidate items, the word frequency of the first candidate items and the type of the first candidate items;
the server candidate feature comprises at least one of: the length and the number of the candidate items of the current server side, the word frequency of the first candidate items and the types of the first candidate items.
4. The method of claim 1, wherein said determining the display positions of the current local candidate and the current server candidate based on the comparison result comprises:
in response to the comparison result indicating that the current server candidate item is superior to the current local candidate item, showing a preference in the current server candidate item to a first position of a candidate bar, and showing a preference in the current local candidate item to a second position of the candidate bar; alternatively, the first and second electrodes may be,
and in response to the comparison result indicating that the current local candidate item is superior to the current server candidate item, showing the preference in the current local candidate item at the head of the candidate bar, and showing the preference in the current server candidate item at the next head of the candidate bar.
5. The method of claim 1, wherein the candidate item comparison model is trained by:
acquiring historical input data of a user, wherein the historical input data comprises historical local candidate items and historical server candidate items issued by a server;
dividing the historical input data into a positive sample and a negative sample based on the hit conditions of the historical local candidate and the historical server candidate on the user screen candidate;
training a classification model based on the positive sample and the negative sample to obtain a candidate item comparison model.
6. The method of claim 5, wherein said dividing the historical input data into positive and negative examples based on hits of the historical local candidates and the historical server candidates on the user's screen candidates comprises:
for each piece of historical input data, if a history server candidate item in the historical input data hits a user screen candidate item and a history local candidate item does not hit the user screen candidate item, taking the historical input data as a positive sample;
the historical input data other than the positive samples are taken as negative samples.
7. The method of claim 5, wherein training a classification model based on the positive samples and the negative samples to obtain a candidate comparison model comprises:
summarizing the positive sample and the negative sample into a sample set;
extracting characteristic information from the samples in the sample set, taking the characteristic information of the samples as input of a classification model, carrying out supervised training on the classification model based on the sample type corresponding to the input characteristic information, and determining the trained classification model as a candidate item comparison model.
8. The method of claim 1, wherein after performing candidate item presentation based on the presentation position, the method further comprises:
responding to the fact that a user selects the current server candidate item, taking the current input data as a positive sample, and retraining the candidate item comparison model based on the positive sample to update the candidate item comparison model; alternatively, the first and second electrodes may be,
and in response to the user selecting the current local candidate item, using the current input data as a negative sample, and retraining the candidate item comparison model based on the negative sample to update the candidate item comparison model.
9. An input device, the device comprising:
an extraction unit configured to extract feature information from current input data of a user;
the comparison unit is configured to input the characteristic information into a pre-trained candidate item comparison model to obtain a comparison result, and the candidate item comparison model is used for comparing the advantages and the disadvantages of candidate items from different sources;
and the display unit is configured to determine the display positions of the current local candidate item and the current server candidate item based on the comparison result, and display the candidate items based on the display positions.
10. The apparatus of claim 9, wherein said current input data includes said current local candidate and said current server candidate; and (c) a second step of,
the extraction unit, further configured to:
extracting input features, local candidate item features and server candidate item features from current input data of a user;
and summarizing the input features, the local candidate item features and the server candidate item features to obtain feature information.
11. The apparatus of claim 10, wherein the input features comprise at least one of: current input string length, current above length;
the local candidate feature comprises at least one of: the length and the number of the current local candidate items, the word frequency of the first candidate items and the types of the first candidate items;
the server candidate feature comprises at least one of: the length and the number of the candidate items of the current server side, the word frequency of the first candidate items and the types of the first candidate items.
12. The apparatus of claim 9, wherein the presentation unit is further configured to:
in response to the comparison result indicating that the current server candidate item is superior to the current local candidate item, showing a preference in the current server candidate item at a head of a candidate bar, and showing a preference in the current local candidate item at a next head of the candidate bar; alternatively, the first and second liquid crystal display panels may be,
and in response to the comparison result indicating that the current local candidate item is superior to the current server candidate item, showing the preference in the current local candidate item at the head of the candidate bar, and showing the preference in the current server candidate item at the next head of the candidate bar.
13. The apparatus of claim 9, wherein the candidate item comparison model is trained by:
acquiring historical input data of a user, wherein the historical input data comprises historical local candidate items and historical server candidate items issued by a server;
dividing the historical input data into a positive sample and a negative sample based on the hit condition of the historical local candidate item and the historical server candidate item on the user screen candidate item;
training a classification model based on the positive sample and the negative sample to obtain a candidate item comparison model.
14. An apparatus for input, comprising a memory, and one or more programs, wherein the one or more programs are stored in the memory, and wherein the programs, when executed by the one or more processors, perform the steps of the method of any of claims 1-8.
15. A computer-readable medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-8.
CN202110752127.9A 2021-06-30 2021-06-30 Input method, device and device for input Pending CN115543099A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110752127.9A CN115543099A (en) 2021-06-30 2021-06-30 Input method, device and device for input

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110752127.9A CN115543099A (en) 2021-06-30 2021-06-30 Input method, device and device for input

Publications (1)

Publication Number Publication Date
CN115543099A true CN115543099A (en) 2022-12-30

Family

ID=84723205

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110752127.9A Pending CN115543099A (en) 2021-06-30 2021-06-30 Input method, device and device for input

Country Status (1)

Country Link
CN (1) CN115543099A (en)

Similar Documents

Publication Publication Date Title
CN107102746B (en) Candidate word generation method and device and candidate word generation device
CN106774970B (en) Method and device for sorting candidate items of input method
CN109961791B (en) Voice information processing method and device and electronic equipment
CN107564526B (en) Processing method, apparatus and machine-readable medium
CN111831806A (en) Semantic integrity determination method and device, electronic equipment and storage medium
CN109901726B (en) Candidate word generation method and device and candidate word generation device
CN110968246A (en) Intelligent Chinese handwriting input recognition method and device
CN110858099B (en) Candidate word generation method and device
CN109426359B (en) Input method, device and machine readable medium
CN115543099A (en) Input method, device and device for input
CN109388252B (en) Input method and device
CN113515618A (en) Voice processing method, apparatus and medium
CN107977089B (en) Input method and device and input device
US20230196001A1 (en) Sentence conversion techniques
CN115494965A (en) Request sending method and device and request sending device
CN111103986A (en) User word stock management method and device and input method and device
CN110716653B (en) Method and device for determining association source
CN112083811B (en) Candidate item display method and device
CN115454259A (en) Input method, input device and input device
CN112445347A (en) Input method, input device and input device
CN113703588A (en) Input method, input device and input device
CN115509371A (en) Key identification method and device for identifying keys
CN115373523A (en) Input method, input device and input device
CN114510154A (en) Input method, input device and input device
CN114442816A (en) Association prefetching method and device for association prefetching

Legal Events

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