Recommendation method, device and electronic device

Abstract

An embodiment of the present invention provides a recommendation method, device and electronic device, wherein the method includes: obtaining an input sequence; determining error correction candidates corresponding to the input sequence, and obtaining error correction benefit information and false correction cost information corresponding to the error correction candidates; recommending the error correction candidates based on the error correction benefit information and false correction cost information corresponding to the error correction candidates; and then recommending the error correction candidates by comprehensively considering the degree to which the recommended error correction candidates improve user input efficiency and the degree to which the recommended error correction candidates reduce user input efficiency, thereby improving the recommendation quality of the error correction candidates and improving user input efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of input methods, and in particular to a recommendation method, device and electronic equipment. Background Art

[0002] With the development of computer technology, electronic devices such as mobile phones and tablet computers are becoming more and more popular, bringing great convenience to people's life, study and work. These electronic devices are usually installed with input method applications (input methods for short), so that users can use the input methods to input information.

[0003] During the input process, users may enter incorrect input sequences due to non-standard pronunciation, incorrect Wubi radicals, false triggering, etc., which results in the input method being unable to provide accurate candidates, requiring the user to re-enter the correct input sequence to obtain the correct candidate, resulting in low input efficiency. Therefore, the input method provides an error correction function, which can correct the input sequence entered by the user, obtain and display error correction candidates, and then the user can select the error correction candidate to be displayed on the screen without having to re-enter, thereby improving the user's input efficiency.

[0004] However, the input method may also make mistakes. When the input method makes a mistake and obtains a mistaken correction candidate and displays it, it will affect the user's ability to display other candidate items on the screen, which will reduce input efficiency. Summary of the invention

[0005] The embodiment of the present invention provides a recommendation method to improve input efficiency.

[0006] Correspondingly, the embodiment of the present invention further provides a recommendation device and an electronic device to ensure the implementation and application of the above method.

[0007] In order to solve the above problems, an embodiment of the present invention discloses a recommendation method, which specifically includes: obtaining an input sequence; determining the error correction candidates corresponding to the input sequence, and obtaining the error correction benefit information and the false correction cost information corresponding to the recommended error correction candidates; and recommending the error correction candidates based on the error correction benefit information and the false correction cost information corresponding to the error correction candidates.

[0008] Optionally, the method further includes: determining other candidates corresponding to the input sequence, the other candidates including candidates other than the error correction candidate; and recommending the error correction candidate based on the error correction benefit information and the false correction cost information corresponding to the error correction candidate, including: recommending the error correction candidate based on the error correction benefit information and the false correction cost information corresponding to the error correction candidate and in combination with the other candidates.

[0009] Optionally, the obtaining of the error correction cost information corresponding to the recommended error correction candidate includes: sorting the error correction candidate and other candidates according to the candidate score corresponding to the error correction candidate and the candidate scores of other candidates; determining a first candidate set to be displayed on the first screen based on the sorting result, the first candidate set including the error correction candidate and / or other candidates; if there is an error correction candidate in the first candidate set, determining a second candidate set to be displayed on the first screen when the error correction candidate does not exist; determining the on-screen cost increment information of the candidates in the second candidate set and the candidates in the first candidate set, and determining the error correction cost information corresponding to the error correction candidate based on the on-screen cost increment information.

[0010] Optionally, the obtaining of error correction benefit information corresponding to the recommended error correction candidate includes: determining position information of the character to be corrected in the input sequence, backspace cost information corresponding to the error correction candidate, and input cost information corresponding to the error correction candidate; and determining the error correction benefit information corresponding to the error correction candidate based on the position information of the character to be corrected, the input cost information and the backspace cost information.

[0011] Optionally, the error correction candidate is recommended based on the error correction benefit information and the false correction cost information corresponding to the error correction candidate and in combination with the other candidates, including: judging whether the error correction benefit information is greater than the false correction cost information; if the error correction benefit information is greater than the false correction cost information, then controlling the error correction candidate to be displayed on the first screen; if the false correction cost information is greater than the error correction benefit information, then controlling not to display the error correction candidate on the first screen and displaying other candidates.

[0012] Optionally, the error correction candidate is recommended based on the error correction benefit information and the false correction cost information corresponding to the error correction candidate and in combination with the other candidates, including: when it is determined that the error correction benefit information is greater than the false correction cost information, judging whether the difference between the error correction benefit information and the false correction cost information is greater than a preset threshold; if the difference between the error correction benefit information and the false correction cost information is greater than the preset threshold, then controlling the error correction candidate to be displayed on the first screen; if the difference between the error correction benefit information and the false correction cost information is less than the preset threshold, then controlling not to display the error correction candidate on the first screen and displaying other candidates.

[0013] Optionally, the obtaining of the error correction cost information corresponding to the recommendation of the error correction candidate includes: determining the upper-screen cost information corresponding to when the error correction candidate is displayed at various positions on the first screen; determining the upper-screen cost information corresponding to when the error correction candidate is displayed at various positions on the first screen as the error correction cost information corresponding to when the error correction candidate is displayed at various positions on the first screen.

[0014] Optionally, the error correction candidate is recommended based on the error correction benefit information and the false correction cost information corresponding to the error correction candidate and in combination with the other candidates, including: sorting the error correction candidate and the other candidates according to the candidate score corresponding to the error correction candidate and the candidate score of the other candidates; determining a third candidate set to be displayed on the first screen according to the sorting result, the third candidate set including the error correction candidate and / or other candidates; if there is an error correction candidate in the third candidate set, selecting a target position where the error correction benefit information is greater than the false correction cost information when the error correction candidate is displayed at each position on the first screen; displaying the error correction candidate in the third candidate set at the target position on the first screen, and displaying other candidates in the third candidate set at other positions on the first screen.

[0015] Optionally, the error correction candidate is recommended based on the error correction benefit information and the false correction cost information corresponding to the error correction candidate and in combination with the other candidates, including: sorting the error correction candidate and the other candidates according to the candidate score corresponding to the error correction candidate and the candidate score of the other candidates; determining a third candidate set to be displayed on the first screen according to the sorting result, the third candidate set including the error correction candidate and / or other candidates; if there is an error correction candidate in the third candidate set, selecting a candidate position where the error correction benefit information of the error correction candidate is greater than the false correction cost information when the error correction candidate is displayed at each position on the first screen; selecting a target position where the difference between the error correction benefit information and the false correction cost information is greater than a preset threshold from each candidate position of the error correction candidate on the first screen; displaying the error correction candidate in the third candidate set at the target position on the first screen, and displaying other candidates in the third candidate set at other positions on the first screen.

[0016] An embodiment of the present invention also discloses a recommendation device, which specifically includes: a first acquisition module, used to acquire an input sequence; a second acquisition module, used to determine the error correction candidates corresponding to the input sequence, and acquire the error correction benefit information and the error correction cost information corresponding to the error correction candidates; a recommendation module, used to recommend the error correction candidates based on the error correction benefit information and the error correction cost information corresponding to the error correction candidates.

[0017] Optionally, the device also includes: a determination module, used to determine other candidates corresponding to the input sequence, the other candidates including candidates other than the error correction candidate; the recommendation module, used to recommend the error correction candidate based on the error correction benefit information and miscorrection cost information corresponding to the error correction candidate, and in combination with the other candidates.

[0018] Optionally, the second acquisition module includes: a first miscorrection cost information acquisition submodule, used to sort the error correction candidates and other candidates according to the candidate scores corresponding to the error correction candidates and the candidate scores of other candidates; determine a first candidate set to be displayed on the first screen based on the sorting result, the first candidate set including error correction candidates and / or other candidates; if there are error correction candidates in the first candidate set, determine a second candidate set to be displayed on the first screen when the error correction candidate does not exist; determine the on-screen cost increment information of the candidates in the second candidate set and the candidates in the first candidate set, and determine the miscorrection cost information corresponding to the error correction candidate based on the on-screen cost increment information.

[0019] Optionally, the second acquisition module includes: an error correction benefit information acquisition sub-module, used to determine the position information of the character to be corrected in the input sequence, the backspace cost information corresponding to the error correction candidate, and the input cost information corresponding to the error correction candidate; based on the position information of the character to be corrected, the input cost information and the backspace cost information, determine the error correction benefit information corresponding to the error correction candidate.

[0020] Optionally, the recommendation module includes: a first display control submodule, used to determine whether the error correction benefit information is greater than the error correction cost information; if the error correction benefit information is greater than the error correction cost information, then controlling the error correction candidate to be displayed on the first screen; if the error correction cost information is greater than the error correction benefit information, then controlling not to display the error correction candidate on the first screen and displaying other candidates.

[0021] Optionally, the recommendation module includes: a second display control submodule, used to determine whether the difference between the error correction benefit information and the error correction cost information is greater than a preset threshold when the error correction benefit information is greater than the error correction cost information; if the difference between the error correction benefit information and the error correction cost information is greater than the preset threshold, then control the display of the error correction candidate on the first screen; if the difference between the error correction benefit information and the error correction cost information is less than the preset threshold, then control not to display the error correction candidate on the first screen and display other candidates.

[0022] Optionally, the second acquisition module includes: a second miscorrection cost information acquisition sub-module, used to determine the upper-screen cost information corresponding to the error correction candidate when it is displayed at various positions on the first screen; the upper-screen cost information corresponding to the error correction candidate when it is displayed at various positions on the first screen is determined as the miscorrection cost information corresponding to the error correction candidate when it is displayed at various positions on the first screen.

[0023] Optionally, the recommendation module includes: a third display control submodule, used to sort the error correction candidates and other candidates according to the candidate scores corresponding to the error correction candidates and the candidate scores of other candidates; based on the sorting result, determine the third candidate set to be displayed on the first screen, the third candidate set including error correction candidates and / or other candidates; if there are error correction candidates in the third candidate set, select the target position where the error correction benefit information is greater than the error correction cost information when the error correction candidate is displayed at each position on the first screen; display the error correction candidates in the third candidate set at the target position on the first screen, and display other candidates in the third candidate set at other positions on the first screen.

[0024] Optionally, the recommendation module includes: a fourth display control submodule, used to sort the error correction candidates and other candidates according to the candidate scores corresponding to the error correction candidates and the candidate scores of other candidates; based on the sorting result, determine a third candidate set to be displayed on the first screen, the third candidate set including error correction candidates and / or other candidates; if there are error correction candidates in the third candidate set, select the candidate position where the error correction benefit information of the error correction candidate is greater than the error correction cost information when it is displayed at each position on the first screen; select the target position where the difference between the error correction benefit information and the error correction cost information is greater than a preset threshold from the candidate positions of the error correction candidate on the first screen; display the error correction candidates in the third candidate set at the target position on the first screen, and display other candidates in the third candidate set at other positions on the first screen.

[0025] An embodiment of the present invention further discloses a readable storage medium. When instructions in the storage medium are executed by a processor of an electronic device, the electronic device can execute a recommendation method as described in any one of the embodiments of the present invention.

[0026] An embodiment of the present invention also discloses an electronic device, comprising a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors, wherein the one or more programs include instructions for performing the following operations: obtaining an input sequence; determining error correction candidates corresponding to the input sequence, and obtaining error correction benefit information and error correction cost information corresponding to the error correction candidates; and recommending the error correction candidates based on the error correction benefit information and error correction cost information corresponding to the error correction candidates.

[0027] Optionally, it also includes instructions for performing the following operations: determining other candidates corresponding to the input sequence, the other candidates including candidates other than the error correction candidate; recommending the error correction candidate based on the error correction benefit information and the error correction cost information corresponding to the error correction candidate, including: recommending the error correction candidate based on the error correction benefit information and the error correction cost information corresponding to the error correction candidate, and in combination with the other candidates.

[0028] Optionally, the obtaining of the error correction cost information corresponding to the recommended error correction candidate includes: sorting the error correction candidate and other candidates according to the candidate score corresponding to the error correction candidate and the candidate scores of other candidates; determining a first candidate set to be displayed on the first screen based on the sorting result, the first candidate set including the error correction candidate and / or other candidates; if there is an error correction candidate in the first candidate set, determining a second candidate set to be displayed on the first screen when the error correction candidate does not exist; determining the on-screen cost increment information of the candidates in the second candidate set and the candidates in the first candidate set, and determining the error correction cost information corresponding to the error correction candidate based on the on-screen cost increment information.

[0029] Optionally, the obtaining of error correction benefit information corresponding to the recommended error correction candidate includes: determining position information of the character to be corrected in the input sequence, backspace cost information corresponding to the error correction candidate, and input cost information corresponding to the error correction candidate; and determining the error correction benefit information corresponding to the error correction candidate based on the position information of the character to be corrected, the input cost information and the backspace cost information.

[0030] Optionally, the error correction candidate is recommended based on the error correction benefit information and the false correction cost information corresponding to the error correction candidate and in combination with the other candidates, including: judging whether the error correction benefit information is greater than the false correction cost information; if the error correction benefit information is greater than the false correction cost information, then controlling the error correction candidate to be displayed on the first screen; if the false correction cost information is greater than the error correction benefit information, then controlling not to display the error correction candidate on the first screen and displaying other candidates.

[0031] Optionally, the error correction candidate is recommended based on the error correction benefit information and the false correction cost information corresponding to the error correction candidate and in combination with the other candidates, including: when it is determined that the error correction benefit information is greater than the false correction cost information, judging whether the difference between the error correction benefit information and the false correction cost information is greater than a preset threshold; if the difference between the error correction benefit information and the false correction cost information is greater than the preset threshold, then controlling the error correction candidate to be displayed on the first screen; if the difference between the error correction benefit information and the false correction cost information is less than the preset threshold, then controlling not to display the error correction candidate on the first screen and displaying other candidates.

[0032] Optionally, the obtaining of the error correction cost information corresponding to the recommendation of the error correction candidate includes: determining the upper-screen cost information corresponding to when the error correction candidate is displayed at various positions on the first screen; determining the upper-screen cost information corresponding to when the error correction candidate is displayed at various positions on the first screen as the error correction cost information corresponding to when the error correction candidate is displayed at various positions on the first screen.

[0033] Optionally, the error correction candidate is recommended based on the error correction benefit information and the false correction cost information corresponding to the error correction candidate and in combination with the other candidates, including: sorting the error correction candidate and the other candidates according to the candidate score corresponding to the error correction candidate and the candidate score of the other candidates; determining a third candidate set to be displayed on the first screen according to the sorting result, the third candidate set including the error correction candidate and / or other candidates; if there is an error correction candidate in the third candidate set, selecting a target position where the error correction benefit information is greater than the false correction cost information when the error correction candidate is displayed at each position on the first screen; displaying the error correction candidate in the third candidate set at the target position on the first screen, and displaying other candidates in the third candidate set at other positions on the first screen.

[0034] Optionally, the error correction candidate is recommended based on the error correction benefit information and the false correction cost information corresponding to the error correction candidate and in combination with the other candidates, including: sorting the error correction candidate and the other candidates according to the candidate score corresponding to the error correction candidate and the candidate score of the other candidates; determining a third candidate set to be displayed on the first screen according to the sorting result, the third candidate set including the error correction candidate and / or other candidates; if there is an error correction candidate in the third candidate set, selecting a candidate position where the error correction benefit information of the error correction candidate is greater than the false correction cost information when the error correction candidate is displayed at each position on the first screen; selecting a target position where the difference between the error correction benefit information and the false correction cost information is greater than a preset threshold from each candidate position of the error correction candidate on the first screen; displaying the error correction candidate in the third candidate set at the target position on the first screen, and displaying other candidates in the third candidate set at other positions on the first screen.

[0035] The embodiments of the present invention include the following advantages:

[0036] In an embodiment of the present invention, an input sequence can be obtained during the user input process; then, the error correction candidates corresponding to the input sequence are determined, and the error correction benefit information and the false correction cost information corresponding to the error correction candidates are obtained; then, based on the error correction benefit information and the false correction cost information corresponding to the error correction candidates, the error correction candidates are recommended; and then, by comprehensively considering the degree to which the recommended error correction candidates improve the user input efficiency and the degree to which the recommended error correction candidates reduce the user input efficiency, the error correction candidates are recommended to improve the recommendation quality of the error correction candidates and thus improve the user input efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 is a flowchart of steps of a recommended method embodiment of the present invention;

[0038] Figure 2 is a flowchart of steps of an optional embodiment of a recommended method of the present invention;

[0039] Figure 3is a flowchart of the steps of another preferred method embodiment of the present invention;

[0040] Figure 4 is a flowchart of the steps of another preferred method alternative embodiment of the present invention;

[0041] Figure 5 is a flowchart of steps of another preferred method embodiment of the present invention;

[0042] Figure 6 is a flowchart of steps of another preferred method optional embodiment of the present invention;

[0043] Figure 7 is a structural block diagram of a recommended device embodiment of the present invention;

[0044] Figure 8 is a structural block diagram of an optional embodiment of a recommended device of the present invention;

[0045] Fig. 9 A structural block diagram of an electronic device for recommendation according to an exemplary embodiment;

[0046] Fig.10 It is a structural schematic diagram of an electronic device for recommendation according to another exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0047] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0048] One of the core concepts of an embodiment of the present invention is to improve the quality of error correction candidate recommendations during the user input process by comprehensively considering the degree to which the recommended error correction candidates improve user input efficiency and the degree to which they reduce user input efficiency, thereby improving user input efficiency.

[0049] Reference Figure 1 , shows a flowchart of a recommended method embodiment of the present invention, which may specifically include the following steps:

[0050] Step 102: Obtain an input sequence.

[0051] In the embodiment of the present invention, when a user uses an input method to input, an input sequence input by the user can be obtained.

[0052] The input sequence is user input content directly received by the input method system. The input method system can convert these input contents into word candidates of the input text according to the input method currently used by the user, and provide them to the user for selection.

[0053] In actual processing, the user can use a variety of input methods, such as pinyin input, stroke input, Wubi input, voice input, and handwriting input. The user can complete the input of the input sequence through any of the above input methods. For input methods such as pinyin input, stroke input, and Wubi input, the input sequence is usually a coded string input by the user through a keyboard, touch screen, etc.; for handwriting input, the input sequence can be a movement trajectory input by the user through a handwriting board, touch screen, etc. The embodiment of the present invention does not limit the user's input method, and the user can use any input method.

[0054] Step 104: determine the error correction candidates corresponding to the input sequence, and obtain error correction benefit information and miscorrection cost information corresponding to the recommended error correction candidates.

[0055] Step 106: Recommend the error correction candidates based on the error correction benefit information and the miscorrection cost information corresponding to the error correction candidates.

[0056] In the embodiment of the present invention, the user may make a mistake in inputting, that is, inputting an incorrect input sequence; therefore, after obtaining the input sequence, the input method can correct the input sequence and determine the corresponding error correction sequence; and then convert the error correction sequence into a corresponding error correction candidate. The error correction candidate may be one or more, and the embodiment of the present invention does not limit this.

[0057] In an embodiment of the present invention, the cost of the user backspacing and re-entering the error correction candidate reduced by recommending the error correction candidate can be used to describe the degree to which the user input efficiency is improved by recommending the error correction candidate; wherein, the cost of the user backspacing and re-entering the error correction candidate reduced by recommending the error correction candidate can be quantified to obtain error correction benefit information. And the cost of the user screen-up other candidates increased by recommending the error correction candidate can be used to describe the degree to which the user input efficiency is reduced by recommending the error correction candidate; wherein, the cost of the user screen-up other candidates increased by recommending the error correction candidate can be quantified to obtain error correction cost information. Then, by comparing the error correction benefit information and error correction cost information corresponding to the error correction candidate, it can be determined whether the error correction candidate needs to be recommended. If it is determined based on the comparison result that the error correction candidate needs to be recommended, the error correction candidate is displayed; if it is determined based on the comparison result that the error correction candidate does not need to be recommended, the error correction candidate may not be displayed.

[0058] In summary, in an embodiment of the present invention, an input sequence can be obtained during the user input process; then, the error correction candidates corresponding to the input sequence are determined, and the error correction benefit information and the false correction cost information corresponding to the recommended error correction candidates are obtained; then, based on the error correction benefit information and the false correction cost information corresponding to the error correction candidates, the error correction candidates are recommended; and then, by comprehensively considering the degree to which the recommended error correction candidates improve the user input efficiency and the degree to which the recommended error correction candidates reduce the user input efficiency, the error correction candidates are recommended to improve the recommendation quality of the error correction candidates and thus improve the user input efficiency.

[0059] Reference Figure 2 , shows a flowchart of an optional embodiment of a recommended method of the present invention, which may specifically include the following steps:

[0060] Step 202: Obtain an input sequence.

[0061] In the embodiment of the present invention, the input method may obtain input association information while obtaining the input sequence input by the user, and further determine the candidate items corresponding to the input sequence based on the input association information.

[0062] The input-related information may include information related to the input, such as input content, location information, time information, weather information, application-related information, etc., which is not limited in the embodiment of the present invention. The input content may include the input content in the current edit box; when the current scene is a chat, the input content may also include interaction information, etc., which is not limited in the embodiment of the present invention. Of course, the input-related information may also include other information, which is not limited in the embodiment of the present invention.

[0063] In the embodiment of the present invention, after the input sequence is obtained, step 204 may be executed to correct the input sequence and determine the corresponding error correction candidate. On the other hand, step 206 may be executed to perform other processing based on the input sequence to determine other candidates corresponding to the input sequence; the other candidates may include candidates other than the error correction candidate.

[0064] Step 204: Determine the error correction candidates corresponding to the input sequence, and obtain error correction benefit information and miscorrection cost information corresponding to the recommended error correction candidates.

[0065] In an embodiment of the present invention, after the input sequence is corrected to obtain the error correction sequence, the error correction sequence can be directly converted to a candidate to obtain the error correction candidate; then the error correction candidate is screened out according to the input association information as the error correction candidate corresponding to the input sequence. Alternatively, after the input sequence is corrected to obtain the error correction sequence, the error correction sequence can be screened according to the input association information; then the screened error correction sequence can be converted to a candidate to obtain the error correction candidate corresponding to the input sequence; the embodiment of the present invention does not limit this. Then, the error correction benefit information and the error correction cost information corresponding to the recommended error correction candidate can be obtained.

[0066] Step 206: Determine other candidates corresponding to the input sequence, where the other candidates include candidates other than the error correction candidate.

[0067] In the embodiment of the present invention, after obtaining the input sequence, in addition to determining the error correction candidates corresponding to the input sequence, other processing can also be performed based on the input sequence. Among them, the manner of performing other processing based on the input sequence can include multiple ways, such as performing word conversion on the input sequence to convert the input sequence into corresponding conventional candidates; for example, prediction can be performed based on input association information and the input sequence to predict the words or sentences corresponding to the input sequence, etc.; the embodiment of the present invention does not limit this; and multiple types of other candidates corresponding to the input sequence can be determined.

[0068] In the embodiment of the present invention, in the process of performing other processing on the input sequence, other candidates corresponding to the input sequence can be determined in combination with the input association information; or after performing other processing on the input sequence to obtain other corresponding candidates, other candidates can be screened according to the input association information; the embodiment of the present invention is not limited to this.

[0069] Step 208: Recommend the error correction candidate based on the error correction benefit information and the miscorrection cost information corresponding to the error correction candidate and in combination with the other candidates.

[0070] In an embodiment of the present invention, the error correction candidate can be recommended based on the error correction benefit information and the false correction cost information corresponding to the error correction candidate and in combination with the other candidates; for example, based on the error correction benefit information and the false correction cost information corresponding to the error correction candidate, it is determined whether to recommend the error correction candidate and the other candidates at the same time, or to only recommend the other candidates without recommending the error correction candidate.

[0071] In summary, in an embodiment of the present invention, during the user input process, an input sequence is obtained; then, on the one hand, the error correction candidates corresponding to the input sequence are determined, and the error correction benefit information and the error correction cost information corresponding to the recommended error correction candidates are obtained; on the other hand, other candidates corresponding to the input sequence are determined; then, based on the error correction benefit information and the error correction cost information corresponding to the error correction candidates, and in combination with the other candidates, the error correction candidates are recommended; thereby, not only the quality of the recommended error correction candidates can be improved, but also other candidates can be recommended when error correction candidates are not recommended, so as to improve the efficiency of the user inputting other candidates.

[0072] In the embodiment of the present invention, other candidates and error correction candidates may be ranked first, and then based on the error correction benefit information and error correction cost information corresponding to the error correction candidates, error correction candidates and other candidates may be recommended. Alternatively, based on the error correction benefit information and error correction cost information corresponding to the error correction candidates, it may be determined whether error correction candidates need to be recommended; when it is determined that error correction candidates need to be recommended, other candidates and error correction candidates are ranked, and then other candidates and error correction candidates are recommended.

[0073] After sorting other candidates and error correction candidates, based on the error correction benefit information and the error correction cost information corresponding to the error correction candidates, error correction candidates and other candidates are recommended for explanation:

[0074] Reference Figure 3 , showing a step flow chart of another recommended method embodiment of the present invention.

[0075] Step 302: Obtain an input sequence.

[0076] Step 302 is similar to the above step 202 and will not be described again.

[0077] Step 304: determine an error correction candidate corresponding to the input sequence and determine other candidates corresponding to the input sequence, wherein the other candidates include candidates other than the error correction candidate.

[0078] The method of determining the error correction candidates corresponding to the input sequence in step 304 is similar to the method of determining the error correction candidates corresponding to the input sequence in step 204; and the method of determining other candidates corresponding to the input sequence in step 304 is similar to the method of determining other candidates corresponding to the input sequence in step 306, which will not be repeated here.

[0079] Wherein, in step 204, the miscorrection cost information corresponding to the recommended error correction candidate is obtained, which can refer to steps 306 to 312:

[0080] Step 306: Sort the error correction candidate and other candidates according to the candidate score corresponding to the error correction candidate and the candidate scores of other candidates.

[0081] In an embodiment of the present invention, when determining an error correction candidate corresponding to an input sequence, a candidate score corresponding to the error correction candidate may be determined; and when determining other candidates corresponding to the input sequence, candidate scores corresponding to other candidates may be determined.

[0082] In an example of the present invention, the error correction candidate and other candidates may be sorted in ascending order or descending order directly based on the candidate score corresponding to the error correction candidate and the candidate scores of other candidates; and a corresponding sorting result may be obtained.

[0083] In another example of the present invention, the error correction candidate and other candidates may be sorted in ascending or descending order based on the candidate score corresponding to the error correction candidate and the candidate scores of other candidates, as well as input association information to obtain corresponding sorting results.

[0084] Step 308: Determine a first candidate set to be displayed on the first screen based on the sorting result, wherein the first candidate set includes error correction candidates and / or other candidates.

[0085] In an embodiment of the present invention, when displaying candidates, the input method can display the top N candidates with the highest candidate scores on the first screen of the candidate area. The N is a positive integer, and N can be determined according to the size of the corresponding display interface of each electronic device, which is not limited by the embodiment of the present invention. Among them, electronic devices with different display interface sizes have different numbers of candidates displayed on the first screen of the candidate area. Furthermore, after sorting the error correction candidates and other candidates, the top N candidates with the highest candidate scores (including error correction candidates and / or other candidates) can be determined as candidates to be displayed on the first screen according to the sorting results.

[0086] In an embodiment of the present invention, the position of the candidate corresponding to the home screen can be determined according to the candidate corresponding to the candidate score; the higher the candidate score, the closer the position to the home screen; that is, the N candidates can be displayed from front to back in the home screen in descending order of the candidate score. In order to facilitate subsequent description, the set consisting of the N candidates can be referred to as the first candidate set; the N candidates in the first candidate set can be arranged in descending order of the candidate score; the sorting position of the N candidates in the first candidate set corresponds to the position displayed on the home screen.

[0087] Step 310: If there are error correction candidates in the first candidate set, then when it is determined that the error correction candidates do not exist, a second candidate set is displayed on the first screen.

[0088] In an embodiment of the present invention, it is possible to determine whether there are error correction candidates in the first candidate set; when there are error correction candidates in the first candidate set, the error correction cost information corresponding to each error correction candidate in the first candidate set can be determined.

[0089] Among them, starting from the first candidate in the first candidate set, it is possible to judge whether each candidate is an error correction candidate one by one. When it is determined that a certain candidate is an error correction candidate, it is possible to determine which N candidates are displayed on the first screen when the error correction candidate does not exist based on the sorting result. Among them, for the convenience of subsequent explanation, the set composed of N candidates displayed on the first screen when the error correction candidate does not exist is called the second candidate set. Among them, the N candidates in the second candidate set can be arranged in descending order according to the candidate score; the sorting position corresponding to the N candidates in the second candidate set corresponds to the position displayed on the first screen.

[0090] When the candidate is displayed at different positions on the first screen, the cost to the user to put the candidate on the screen is different; for example, the cost of the user putting the candidate on the screen at the first position of the first screen is less than the cost of the candidate being displayed at other positions on the first screen. Then, the error correction cost information caused by displaying the error correction candidate can be determined based on the position of each candidate in the first candidate set and the position of each candidate in the second candidate set.

[0091] Step 312: Determine the on-screen cost increment information of the candidates in the second candidate set and the candidates in the first candidate set, and determine the error correction cost information corresponding to the error correction candidate based on the on-screen cost increment information.

[0092] In an embodiment of the present invention, the duration of the candidates displayed at each position of the first screen of the screen for all users of the network can be counted in advance; then, based on the duration of the candidates displayed at each position of the first screen of the screen for all users of the network, the upper screen cost information of the candidates corresponding to each position of the first screen of the screen can be determined. Among them, the duration of each candidate displayed at each position of the first screen of the user's screen can refer to the duration between the display of the candidate at that position of the first screen and the display of the candidate at that position of the user's screen. Among them, for a position of the first screen, the upper screen cost information of the candidate corresponding to that position of the first screen of the screen can be determined based on the average duration of the candidates displayed at that position of the first screen of the screen for all users of the network. The upper screen cost information corresponding to a position of the first screen can be proportional to the average duration of the candidates displayed at that position of the first screen of the screen for all users of the network.

[0093] Of course, after pre-counting the duration of the candidates displayed at various positions on the first screen of all users on the entire network, the on-screen cost information of the candidates corresponding to each position on the first screen may be temporarily determined; instead, when executing step 312, the on-screen cost information of the candidates corresponding to each position on the first screen of all users on the entire network is determined based on the duration of the candidates displayed at various positions on the first screen of all users on the entire network.

[0094] In addition, in addition to counting the time when the candidates are displayed at each position of the first screen of all network users, the time when the candidates are displayed at each position of the kth screen of all network users can also be counted; then, according to the time when the candidates are displayed at each position of the kth screen of each user, the screen cost information corresponding to each position of the kth screen is determined. The k is a positive integer greater than 1; it can be set according to the requirements, and the embodiment of the present invention does not limit this.

[0095] Then, for each candidate in the second candidate set, the position of the candidate displayed on the first screen can be determined based on the position of the candidate in the second candidate set; that is, the position of the candidate displayed on the first screen when the error correction candidate does not exist. Then, based on the upper screen cost information corresponding to the position of the candidate displayed on the first screen when the error correction candidate does not exist, the first upper screen cost information corresponding to the candidate is determined. And based on the position of the candidate in the first candidate set, the position of the candidate displayed on the first screen is determined, that is, the position of the candidate displayed on the first screen when the error correction candidate exists. Then, based on the upper screen cost information corresponding to the position of the candidate displayed on the first screen when the error correction candidate exists, the second upper screen cost information corresponding to the candidate is determined.

[0096] Based on the first on-screen cost information and the second on-screen cost information corresponding to the candidate, determine the on-screen incremental information corresponding to the candidate; then, based on the on-screen cost incremental information corresponding to each candidate in the second candidate set, calculate the miscorrection cost information corresponding to the error correction candidate. In one example, the sum of the on-screen cost incremental information corresponding to each candidate in the second candidate set can be calculated, and the sum value obtained is used as the miscorrection cost information corresponding to the error correction candidate. In another example, a weighted calculation can be performed based on the on-screen cost incremental information corresponding to each candidate in the second candidate set and the candidate score, and the value obtained by the weighted calculation is used as the miscorrection cost information corresponding to the error correction candidate. In yet another example, a weighted calculation can be performed based on the on-screen cost incremental information corresponding to each candidate in the second candidate set, the candidate score and the input association information, and the value obtained by the weighted calculation is used as the miscorrection cost information corresponding to the error correction candidate. Of course, there are other ways to determine the miscorrection cost information corresponding to the error correction candidate, and the embodiments of the present invention are not limited to this.

[0097] When there are multiple error correction candidates in the first candidate set, for each error correction candidate, the corresponding second candidate set can be determined in accordance with the above step 310, and the error correction cost information corresponding to the error correction candidate can be determined in accordance with step 312.

[0098] For example, the first screen can support 5 candidates for display.

[0099] The first candidate set includes the following five candidates: A, B, C, D and E; among them, C and D are error correction candidates, and A, B and E are other candidates. A, B, C, D and E correspond to the first position, the second position, the third position, the fourth position and the fifth position on the first screen. If C does not exist, the second candidate set displayed on the first screen includes the following five candidates: A, B, D, E and F; among them, F is the candidate to be displayed at the first position of the second screen when C is displayed. The positions of these five candidates on the first screen are the first position, the second position, the third position, the fourth position and the fifth position. Among them, the upper screen cost increment information corresponding to A and B is 0, the upper screen cost increment information corresponding to D is d1-d2, the upper screen cost increment information corresponding to E is e1-e2, and the upper screen cost increment information corresponding to F is f1-f2. Assuming that the sum of the on-screen cost increment information corresponding to each candidate in the second candidate set is taken as the miscorrection cost information corresponding to the error correction candidate, the miscorrection cost information corresponding to the error correction candidate C is: (d1-d2)+(e1-e2)+(f1-f2).

[0100] If D does not exist, the second candidate set displayed on the first screen includes the following five candidates: A, B, C, E and F; among which, F is the candidate to be displayed at the first position of the second screen when D is displayed. The positions of these five candidates on the first screen are the first position, the second position, the third position, the fourth position and the fifth position, respectively. Among them, the on-screen cost increment information corresponding to A, B and C is 0, the on-screen cost increment information corresponding to E is e1-e2, and the on-screen cost increment information corresponding to F is f1-f2. Assuming that the sum of the on-screen cost increment information corresponding to each candidate in the second candidate set is taken as the error correction cost information corresponding to the error correction candidate, the error correction cost information corresponding to the error correction candidate D is: (e1-e2)+(f1-f2).

[0101] In step 204, the error correction benefit information corresponding to the error correction candidate recommended is obtained, which can refer to steps 314 to 316:

[0102] Step 314: Determine the position information of the character to be corrected in the input sequence, the backspace cost information corresponding to the error correction candidate, and the input cost information corresponding to the error correction candidate.

[0103] Step 316: Based on the position information of the character to be corrected, input cost information and backspace cost information to determine the error correction benefit information corresponding to the error correction candidate.

[0104] In the embodiment of the present invention, in the process of determining the error correction candidate corresponding to the input sequence, the error correction sequence is first determined, and then the error correction candidate is determined based on the conversion of the error correction sequence. Therefore, for each error correction candidate in the first candidate set, the error correction sequence corresponding to the error correction candidate can be compared with the input sequence to determine the position information of the character to be corrected and the character to be corrected in the input sequence; such as the beginning of the input sequence, the middle of the input sequence, and the end of the input sequence.

[0105] In addition, the embodiment of the present invention can also determine the backspace cost information corresponding to the error correction candidate, and the backspace cost information can be used to describe the cost required for the user to delete part of the characters in the current input sequence through the backspace operation on the basis of the current input sequence to obtain the error correction sequence corresponding to the error correction candidate. And the input cost information corresponding to the error correction candidate can be determined, and the input cost information can be used to describe the cost required to delete all the currently input input sequences and input the input sequence corresponding to the error correction candidate.

[0106] In an embodiment of the present invention, the backspace cost information and input cost information corresponding to each candidate can be determined in advance based on the user's operation. For example, the number and duration of backspaces performed by the user before a candidate is displayed on the screen, the length of the input sequence before the user performs backspaces, and the input sequence when the user displays the candidate can be counted; then the backspace cost information corresponding to the candidate is determined based on the number and duration of backspaces performed by the user, the length of the input sequence before the user performs backspaces, and the input sequence when the user displays the candidate. Among them, classification can be performed based on the number and duration of backspaces performed by the user, and the length of the input sequence before the user performs backspaces; wherein, in each category, the length of the input sequence before the user performs backspaces is different, and / or, the number of times the user performs backspaces is different, and / or, the duration of the user's execution of the recommendation is different. Then the backspace cost information corresponding to the candidate of each category is determined respectively.

[0107] For another example, before a candidate is displayed on the screen, the number of times and duration of backspaces performed by the user, the length of the input sequence before the user performs backspaces, and the length and input duration of the input sequence corresponding to the user when the candidate is displayed on the screen can be obtained; then the number and duration of backspaces performed by the user, the length of the input sequence before the user performs backspaces, and the length and input duration of the input sequence corresponding to the user when the candidate is displayed on the screen can be used to determine the input cost information corresponding to the candidate. Among them, classification can be performed based on the number and duration of backspaces performed by the user, the length of the input sequence before the user performs backspaces, and the length and input duration of the input sequence corresponding to the user when the candidate is displayed on the screen; the number of times the user performs backspaces in each category is different, and / or the duration of backspaces performed by the user is different, and / or the length of the input sequence before the user performs backspaces is different, and / or the length of the input sequence corresponding to the user when the candidate is displayed on the screen is different, and / or the input duration corresponding to the input sequence when the user displays the candidate. Then the input cost information corresponding to the candidate of each category is determined respectively.

[0108] Furthermore, the embodiment of the present invention can determine the length of the current user input sequence and the error correction sequence corresponding to the error correction candidate; then, based on the determination of the length of the current user input sequence and the error correction sequence corresponding to the error correction candidate, determine the number and duration of the backspace operation performed by the user. Then, based on the length of the current user input sequence and the number and duration of the backspace operation performed by the user, the backspace cost information corresponding to each candidate of different categories obtained by pre-classification is searched for the backspace cost information corresponding to the error correction candidate.

[0109] And the length of the current input sequence can be determined, and based on the length of the current input sequence and the input sequence, the number of times and duration of the backspace operation performed by the user can be determined; and the error correction sequence corresponding to the error correction candidate can be determined, and based on the error correction sequence corresponding to the error correction candidate, the length and input duration of the error correction sequence input by the user can be determined. Then, according to the number and duration of the backspace operation performed by the user, the length of the current input sequence, and the length and input duration of the error correction sequence input by the user, the input cost information corresponding to each candidate of different categories obtained by pre-classification can be used to find the input cost information corresponding to the error correction candidate.

[0110] Then, based on the position information of the character to be corrected, the distance between the character to be corrected and the last character in the input sequence can be determined; and then based on the distance between the character to be corrected and the last character in the input sequence, the input cost information and the backspace cost information, the error correction benefit information corresponding to the error correction candidate can be determined.

[0111] Step 318: Determine whether the error correction benefit information is greater than the error correction cost information.

[0112] In the embodiment of the present invention, for each error correction candidate, the error correction benefit information and the error correction cost information corresponding to the error correction candidate can be compared; if the error correction benefit information is greater than the error correction cost information, step 320 can be executed; if the error correction benefit information is less than the error correction cost information, step 322 can be executed. If the error correction benefit information is equal to the error correction cost information, either step 320 or step 322 can be executed, and the embodiment of the present invention does not limit this.

[0113] Step 320: Control the display of the error correction candidates on the first screen.

[0114] In an embodiment of the present invention, if the error correction benefit information of the error correction candidate is greater than the error correction cost information, it means that the improvement degree of the recommended error correction candidate on the user input efficiency is greater than the reduction degree of the user input efficiency; at this time, the error correction candidate can be controlled to be displayed on the first screen. The position of the error correction candidate displayed on the first screen can correspond to the position of the error correction candidate in the first candidate set.

[0115] Step 322: Control not to display the error correction candidate on the first screen and display other candidates.

[0116] In an embodiment of the present invention, if the error correction benefit information of the error correction candidate is less than the miscorrection cost information, it means that the degree to which the recommended error correction candidate improves the user input efficiency is less than the degree to which it reduces the user input efficiency; at this time, the error correction candidate can be controlled not to be displayed on the first screen, and other candidates can be controlled to be displayed on the first screen.

[0117] Among them, the display positions of other candidates can be determined according to the positions of the error correction candidates displayed on the first screen and the positions of the error correction candidates not displayed on the first screen.

[0118] Among them, according to the error correction cost information and error correction benefit information of each error correction candidate in the first candidate set, the error correction candidate with the error correction cost information greater than the error correction benefit information and the error correction candidate with the error correction cost information less than the error correction benefit information can be determined. Then, the error correction candidate with the error correction cost information greater than the error correction benefit information in the first candidate set can be deleted; and the candidates after the deleted error correction candidate in the first candidate set and the candidates after the candidates in the first candidate set determined based on the sorting result can be moved forward; and then the first N candidates are selected for display on the first screen.

[0119] In addition, after the user performs the screen flipping operation, the error correction benefit information and the error correction cost information corresponding to the error correction candidate displayed on the second screen can be determined according to steps 308-316; then, according to the error correction benefit information and the error correction cost information corresponding to the error correction candidate displayed on the second screen, the error correction candidate displayed on the second screen can be recommended on the second screen according to steps 318-322. Similarly, for any screen in the input method candidate display area, the error correction candidates displayed on the screen can be recommended according to steps 308-322.

[0120] In summary, in an embodiment of the present invention, in the process of obtaining the error correction cost information corresponding to the recommended error correction candidate, the error correction candidate and other candidates can be sorted according to the candidate score corresponding to the error correction candidate and the candidate score of other candidates; based on the sorting result, a first candidate set displayed on the first screen is determined, and the first candidate set includes error correction candidates and / or other candidates; if there is an error correction candidate in the first candidate set, then a second candidate set displayed on the first screen when the error correction candidate does not exist is determined; then the on-screen cost increment information of the candidates in the second candidate set and the candidates in the first candidate set is determined, and the error correction cost information corresponding to the error correction candidate is determined based on the on-screen cost increment information; and then by assuming the on-screen cost increment information corresponding to other candidates when the error correction candidate does not exist and exists, the error correction cost information corresponding to the error correction candidate can be accurately determined, thereby further improving the recommendation quality of the error correction candidate; thereby improving the user input efficiency.

[0121] Secondly, in an embodiment of the present invention, if the error correction benefit information is greater than the false correction cost information, the error correction candidate is controlled to be displayed on the first screen; if the false correction cost information is less than the error correction benefit information, the error correction candidate is controlled not to be displayed on the first screen; and then when the effect of displaying the error correction candidate on improving user efficiency is greater than the effect of reducing user input efficiency, the error correction candidate is displayed; the recommendation quality of the error correction candidate can be improved.

[0122] Reference Figure 4 , showing a step flow chart of another recommended method optional embodiment of the present invention.

[0123] Step 402: Obtain an input sequence.

[0124] Step 404: determine an error correction candidate corresponding to the input sequence and determine other candidates corresponding to the input sequence, wherein the other candidates include candidates other than the error correction candidate.

[0125] Step 406: Sort the error correction candidate and other candidates according to the candidate score corresponding to the error correction candidate and the candidate scores of other candidates.

[0126] Step 408: Determine a first candidate set to be displayed on the first screen based on the sorting result, wherein the first candidate set includes error correction candidates and / or other candidates.

[0127] Step 410: If there are error correction candidates in the first candidate set, then when it is determined that the error correction candidates do not exist, a second candidate set is displayed on the first screen.

[0128] Step 412: Determine the on-screen cost increment information of the candidates in the second candidate set and the candidates in the first candidate set, and determine the error correction cost information corresponding to the error correction candidate based on the on-screen cost increment information.

[0129] Step 414: Determine the position information of the character to be corrected in the input sequence, the backspace cost information corresponding to the error correction candidate, and the input cost information corresponding to the error correction candidate.

[0130] Step 416: Based on the position information of the character to be corrected, input cost information and backspace cost information to determine the error correction benefit information corresponding to the error correction candidate.

[0131] Step 402 to step 416 are similar to the above-mentioned steps 302 to step 316, and are not described again here.

[0132] Step 418: Determine whether the error correction benefit information is greater than the error correction cost information.

[0133] In the embodiment of the present invention, if the error correction benefit information is greater than the false correction cost information, step 420 is executed; if the error correction benefit information is less than or equal to the false correction cost information, step 424 is executed.

[0134] Step 420: Determine whether the difference between the error correction benefit information and the error correction cost information is greater than a preset threshold.

[0135] In the embodiment of the present invention, if the error correction benefit information is greater than the error correction cost information, the difference between the error correction benefit information and the error correction cost information can be calculated; then it is determined whether the difference is greater than a preset threshold. If the difference is greater than the preset threshold, step 422 is executed; if the difference is less than or equal to the preset threshold, step 424 is executed. The preset threshold can be set as required, and the embodiment of the present invention does not limit this.

[0136] Step 422: Control the display of the error correction candidates on the first screen.

[0137] In an embodiment of the present invention, when the difference is greater than a preset threshold, it indicates that the degree of improvement in user input efficiency of displaying the error correction candidate pairs is greater than a certain value of the degree of reduction in user input efficiency; at this time, the error correction candidates can be controlled to be displayed on the first screen.

[0138] Step 424: Control not to display the error correction candidate on the first screen and display other candidates.

[0139] In an embodiment of the present invention, when the difference is greater than a preset threshold, it indicates that the degree of improvement in the user input efficiency of displaying the error correction candidate pairs is not greater than a certain value of the degree of reduction in the user input efficiency; at this time, the error correction candidate can be controlled not to be displayed on the first screen, and other candidates can be controlled to be displayed on the first screen.

[0140] In summary, in an embodiment of the present invention, if the difference between the error correction benefit information and the false correction cost information is greater than a preset threshold, then each candidate in the first candidate set is displayed on the first screen; if the difference between the error correction benefit information and the false correction cost information is less than the preset threshold, then each candidate in the second candidate set is displayed on the first screen; relative to the above embodiment, an embodiment of the present invention displays the error correction candidates only when the degree of improvement in the user input efficiency of displaying the error correction candidate pairs is greater than a certain value of the degree of reduction in the user input efficiency, which can further improve the recommendation quality of the error correction candidates.

[0141] The following describes first determining whether to recommend an error correction candidate based on the error correction benefit information and the error correction cost information corresponding to the error correction candidate; and when it is determined that an error correction candidate needs to be recommended, then recommending other candidates and error correction candidates after sorting them.

[0142] Reference Figure 5 , showing a step flow chart of another recommended method embodiment of the present invention.

[0143] Step 502: Obtain an input sequence.

[0144] Step 504: determine an error correction candidate corresponding to the input sequence and determine other candidates corresponding to the input sequence, wherein the other candidates include candidates other than the error correction candidate.

[0145] Step 502 to step 504 are similar to the above-mentioned step 302 to step 304 and will not be described again here.

[0146] Wherein, in step 204, the miscorrection cost information corresponding to the recommended error correction candidate is obtained, which can refer to steps 506 to 508:

[0147] Step 506: Determine the corresponding on-screen cost information when the error correction candidate is displayed at each position on the first screen.

[0148] Step 508: determine the corresponding on-screen cost information when the error correction candidate is displayed at each position on the first screen as the corresponding miscorrection cost information when the error correction candidate is displayed at each position on the first screen.

[0149] In an embodiment of the present invention, the corresponding on-screen cost information of the error correction candidate when displayed at each position of the first screen can be determined based on the predetermined on-screen cost information corresponding to each position of the first screen. Then, the corresponding on-screen cost information of the error correction candidate when displayed at each position of the first screen is determined as the corresponding miscorrection cost information of the error correction candidate when displayed at each position of the first screen.

[0150] Step 510: Determine the position information of the character to be corrected in the input sequence, the backspace cost information corresponding to the error correction candidate, and the input cost information corresponding to the error correction candidate.

[0151] Step 512: Based on the position information of the character to be corrected, input cost information and backspace cost information to determine the error correction benefit information corresponding to the error correction candidate.

[0152] Step 510 to step 512 are similar to the above-mentioned step 314 to step 316 and will not be described in detail here.

[0153] Step 514: Sort the error correction candidate and other candidates according to the candidate score corresponding to the error correction candidate and the candidate scores of other candidates.

[0154] Step 516: Determine a third candidate set to be displayed on the first screen based on the sorting result, wherein the third candidate set includes error correction candidates and / or other candidates.

[0155] Step 514 to step 516 are similar to the above-mentioned step 306 to step 308 and will not be described in detail here.

[0156] Among them, the N candidates in the third candidate set can be arranged in descending order according to the candidate scores; the sorting positions corresponding to the N candidates in the third candidate set correspond to the positions displayed on the first screen.

[0157] Step 518: If there are error correction candidates in the third candidate set, select the target position where the error correction benefit information is greater than the error correction cost information when the error correction candidate is displayed at each position on the first screen.

[0158] In an embodiment of the present invention, if there are error correction candidates in the third candidate set, then for each error correction candidate, when the error correction candidate is displayed at each position on the first screen, it can be determined whether the error correction benefit information of the error correction candidate when displayed at that position on the first screen is greater than the error correction cost information. If the error correction benefit information of the error correction candidate when displayed at that position on the first screen is greater than the error correction cost information, then that position can be determined as the target position. If there are multiple target positions, then the target position with the largest corresponding error correction benefit information can be screened out as the final target position; or the target position with the largest difference between the error correction benefit information and the corresponding error correction cost information can be screened out as the final target position; this is not limited in the embodiment of the present invention.

[0159] Step 520: Display the error correction candidates in the third candidate set at a target position on the first screen, and display other candidates in the third candidate set at other positions on the first screen.

[0160] Then, the error correction candidates in the third candidate set are displayed at the target position of the first screen, and other candidates can be displayed at other positions corresponding to the first screen according to their positions in the third candidate set.

[0161] Of course, when the target position is not selected, the fourth candidate set to be displayed on the first screen when the error correction candidate does not exist is re-determined. The fourth candidate set includes N candidates, which can be arranged in descending order according to the candidate scores; the sorting positions corresponding to the N candidates in the fourth candidate set correspond to the positions displayed on the first screen. Then, according to the corresponding positions of the candidates in the fourth candidate set, the candidates in the fourth candidate set are displayed at the corresponding positions on the first screen.

[0162] In summary, in an embodiment of the present invention, in the process of recommending the error correction candidate based on the error correction benefit information and the false correction cost information corresponding to the error correction candidate and in combination with the other candidates, the error correction candidate and the other candidates can be sorted according to the candidate score corresponding to the error correction candidate and the candidate score of the other candidates, and then based on the sorting result, a third candidate set to be displayed on the first screen is determined, the third candidate set including the error correction candidate and / or other candidates; if there is an error correction candidate in the third candidate set, then based on the false correction cost information when the error correction candidate is displayed at each position on the first screen, the position where the error correction benefit information of the error correction candidate is greater than the false correction cost information when it is displayed at each position on the first screen is selected as the target position; the error correction candidate in the third candidate set is displayed at the target position on the first screen, and the other candidates in the third candidate set are displayed at other positions on the first screen; and then the error correction candidate is displayed at the position where the error correction benefit information is greater than the false correction cost information, so as to reduce the cost of displaying the error correction candidate to the user to go to the screen of other candidates; thereby improving the user input efficiency.

[0163] Reference Figure 6 , showing a step flow chart of another recommended method optional embodiment of the present invention.

[0164] Step 602: Obtain an input sequence.

[0165] Step 604: Determine an error correction candidate corresponding to the input sequence and determine other candidates corresponding to the input sequence, wherein the other candidates include candidates other than the error correction candidate.

[0166] Step 606: Determine the corresponding on-screen cost information when the error correction candidate is displayed at each position on the first screen.

[0167] Step 608: Determine the corresponding on-screen cost information when the error correction candidate is displayed at each position on the first screen as the corresponding miscorrection cost information when the error correction candidate is displayed at each position on the first screen.

[0168] Step 610: Determine the position information of the character to be corrected in the input sequence, the backspace cost information corresponding to the error correction candidate, and the input cost information corresponding to the error correction candidate.

[0169] Step 612: Based on the position information of the character to be corrected, input cost information and backspace cost information to determine the error correction benefit information corresponding to the error correction candidate.

[0170] Step 614: Sort the error correction candidate and other candidates according to the candidate score corresponding to the error correction candidate and the candidate scores of other candidates.

[0171] Step 616: Determine a third candidate set to be displayed on the first screen based on the sorting result, wherein the third candidate set includes error correction candidates and / or other candidates.

[0172] Step 602 to step 616 are similar to the above-mentioned steps 502 to step 516 and will not be described in detail here.

[0173] Step 618: If there are error correction candidates in the third candidate set, select candidate positions where the error correction benefit information is greater than the error correction cost information when the error correction candidate is displayed at each position on the first screen.

[0174] In the embodiment of the present invention, if there are error correction candidates in the third candidate set, for each error correction candidate, when the error correction candidate is displayed at each position on the first screen, it can be determined whether the error correction benefit information of the error correction candidate when displayed at that position on the first screen is greater than the error correction cost information. Then, the position where the error correction benefit information of the error correction candidate is greater than the error correction cost information when the error correction candidate is displayed at each position on the first screen is selected as the candidate position.

[0175] Step 620: Select a target position whose difference between error correction benefit information and miscorrection cost information is greater than a preset threshold from among the candidate positions of the error correction candidates on the first screen.

[0176] Then, for each candidate position of the error correction candidate, the difference between the error correction benefit information and the error correction cost information can be determined when the error correction candidate is displayed at the candidate position on the first screen; if the difference is greater than a preset threshold, the candidate position can be determined as the target position. If there are multiple target positions, the target position with the largest difference can be selected as the final target position.

[0177] Step 622: Display the error correction candidates in the third candidate set at the target position of the first screen, and display other candidates in the third candidate set at other positions of the first screen.

[0178] Step 622 is similar to the above step 520 and will not be described again.

[0179] In summary, in the embodiment of the present invention, in the process of recommending the error correction candidate based on the error correction benefit information and the error correction cost information corresponding to the error correction candidate and in combination with the other candidates, the error correction candidate and the other candidates can be sorted according to the candidate score corresponding to the error correction candidate and the candidate score of the other candidates; then, according to the sorting result, the third candidate set displayed on the first screen is determined, the third candidate set includes the error correction candidate and / or other candidates, if there is an error correction candidate in the third candidate set, then the candidate position where the error correction benefit information is greater than the error correction cost information when the error correction candidate is displayed at each position on the first screen is selected, and the target position where the difference between the error correction benefit information and the error correction cost information is greater than the preset threshold value is selected from the candidate positions of the error correction candidate on the first screen; the error correction candidate in the third candidate set is displayed at the target position on the first screen, and the other candidates in the third candidate set are displayed at other positions on the first screen. Then, the error correction candidate is displayed at a position where the error correction benefit information is greater than the error correction cost information to a certain extent. Compared with the above embodiment, the cost of displaying the error correction candidate for the user to display other candidates can be further reduced; thereby further improving the user input efficiency.

[0180] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0181] Reference Figure 7 , shows a structural block diagram of an embodiment of a recommendation device of the present invention, which may specifically include the following modules:

[0182] A first acquisition module 702, used to acquire an input sequence;

[0183] The second acquisition module 704 is used to determine the error correction candidate corresponding to the input sequence, and obtain the error correction benefit information and the error correction cost information corresponding to the recommended error correction candidate;

[0184] The recommendation module 706 is used to recommend the error correction candidate based on the error correction benefit information and the miscorrection cost information corresponding to the error correction candidate.

[0185] Reference Figure 8 , showing a structural block diagram of an optional embodiment of a recommendation device of the present invention.

[0186] In an optional embodiment of the present invention, the device further comprises:

[0187] A determination module 708, configured to determine other candidates corresponding to the input sequence, wherein the other candidates include candidates other than the error correction candidate;

[0188] The recommendation module 706 is used to recommend the error correction candidate based on the error correction benefit information and the miscorrection cost information corresponding to the error correction candidate and in combination with the other candidates.

[0189] In an optional embodiment of the present invention, the second acquisition module 704 includes:

[0190] The first miscorrection cost information acquisition submodule 7042 is used to sort the error correction candidates and other candidates according to the candidate scores corresponding to the error correction candidates and the candidate scores of other candidates; determine the first candidate set to be displayed on the first screen according to the sorting result, the first candidate set including the error correction candidates and / or other candidates; if there are error correction candidates in the first candidate set, determine the second candidate set to be displayed on the first screen when the error correction candidates do not exist; determine the on-screen cost increment information of the candidates in the second candidate set and the candidates in the first candidate set, and determine the miscorrection cost information corresponding to the error correction candidate according to the on-screen cost increment information.

[0191] In an optional embodiment of the present invention, the second acquisition module 704 includes:

[0192] The error correction benefit information acquisition submodule 7044 is used to determine the position information of the character to be corrected in the input sequence, the backspace cost information corresponding to the error correction candidate and the input cost information corresponding to the error correction candidate; based on the position information of the character to be corrected, the input cost information and the backspace cost information, the error correction benefit information corresponding to the error correction candidate is determined.

[0193] In an optional embodiment of the present invention, the recommendation module 706 includes:

[0194] The first display control submodule 7062 is used to determine whether the error correction benefit information is greater than the error correction cost information; if the error correction benefit information is greater than the error correction cost information, the error correction candidate is controlled to be displayed on the first screen; if the error correction cost information is greater than the error correction benefit information, the error correction candidate is controlled not to be displayed on the first screen and other candidates are displayed.

[0195] In an optional embodiment of the present invention, the recommendation module 706 includes:

[0196] The second display control submodule 7064 is used to determine whether the difference between the error correction benefit information and the error correction cost information is greater than a preset threshold when it is determined that the error correction benefit information is greater than the error correction cost information; if the difference between the error correction benefit information and the error correction cost information is greater than the preset threshold, then control the display of the error correction candidate on the first screen; if the difference between the error correction benefit information and the error correction cost information is less than the preset threshold, then control not to display the error correction candidate on the first screen and display other candidates.

[0197] In an optional embodiment of the present invention, the second acquisition module 704 includes:

[0198] The second error correction cost information acquisition submodule 7046 is used to determine the upper-screen cost information corresponding to the error correction candidate when it is displayed at various positions on the first screen; the upper-screen cost information corresponding to the error correction candidate when it is displayed at various positions on the first screen is determined as the error correction cost information corresponding to the error correction candidate when it is displayed at various positions on the first screen.

[0199] In an optional embodiment of the present invention, the recommendation module 706 includes:

[0200] The third display control submodule 7066 is used to sort the error correction candidates and other candidates according to the candidate scores corresponding to the error correction candidates and the candidate scores of other candidates; determine the third candidate set to be displayed on the first screen according to the sorting result, the third candidate set including the error correction candidates and / or other candidates; if there are error correction candidates in the third candidate set, select the target position where the error correction benefit information is greater than the error correction cost information when the error correction candidate is displayed at each position on the first screen; display the error correction candidates in the third candidate set at the target position on the first screen, and display other candidates in the third candidate set at other positions on the first screen.

[0201] In an optional embodiment of the present invention, the recommendation module 706 includes:

[0202] The fourth display control submodule 7068 is used to sort the error correction candidates and other candidates according to the candidate scores corresponding to the error correction candidates and the candidate scores of other candidates; determine the third candidate set to be displayed on the first screen according to the sorting result, the third candidate set including the error correction candidates and / or other candidates; if there are error correction candidates in the third candidate set, select the candidate position where the error correction benefit information is greater than the error correction cost information when the error correction candidate is displayed at each position on the first screen; select the target position where the difference between the error correction benefit information and the error correction cost information is greater than a preset threshold from the candidate positions of the error correction candidate on the first screen; display the error correction candidates in the third candidate set at the target position on the first screen, and display other candidates in the third candidate set at other positions on the first screen.

[0203] In summary, in an embodiment of the present invention, an input sequence can be obtained during the user input process; then, the error correction candidates corresponding to the input sequence are determined, and the error correction benefit information and the false correction cost information corresponding to the recommended error correction candidates are obtained; then, based on the error correction benefit information and the false correction cost information corresponding to the error correction candidates, the error correction candidates are recommended; and then, by comprehensively considering the degree to which the recommended error correction candidates improve the user input efficiency and the degree to which the recommended error correction candidates reduce the user input efficiency, the error correction candidates are recommended to improve the recommendation quality of the error correction candidates and thus improve the user input efficiency.

[0204] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0205] Fig. 9 1 is a block diagram of an electronic device 900 for recommendation according to an exemplary embodiment. For example, the electronic device 900 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0206] Reference Fig. 9 , the electronic device 900 may include one or more of the following components: a processing component 902 , a memory 904 , a power component 906 , a multimedia component 908 , an audio component 910 , an input / output (I / O) interface 912 , a sensor component 914 , and a communication component 916 .

[0207] The processing component 902 generally controls the overall operation of the electronic device 900, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 902 may include one or more processors 920 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 902 may include one or more modules to facilitate the interaction between the processing component 902 and other components. For example, the processing component 902 may include a multimedia module to facilitate the interaction between the multimedia component 908 and the processing component 902.

[0208] The memory 904 is configured to store various types of data to support operations on the electronic device 900. Examples of such data include instructions for any application or method operating on the electronic device 900, contact data, phone book data, messages, pictures, videos, etc. The memory 904 may be implemented by any type of volatile or non-volatile storage device or a combination thereof, 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 disk or optical disk.

[0209] The power component 906 provides power to the various components of the electronic device 900. The power component 906 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 900.

[0210] The multimedia component 908 includes a screen that provides an output interface between the electronic device 900 and the 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 input signals from the 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 boundaries 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 908 includes a front camera and / or a rear camera. When the electronic device 900 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0211] The audio component 910 is configured to output and / or input audio signals. For example, the audio component 910 includes a microphone (MIC), and when the electronic device 900 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 904 or sent via the communication component 916. In some embodiments, the audio component 910 also includes a speaker for outputting audio signals.

[0212] I / O interface 912 provides an interface between processing component 902 and peripheral interface modules, such as 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.

[0213] The sensor assembly 914 includes one or more sensors for providing various aspects of status assessment for the electronic device 900. For example, the sensor assembly 914 can detect the open / closed state of the electronic device 900, the relative positioning of components, such as the display and keypad of the electronic device 900, and the sensor assembly 914 can also detect the position change of the electronic device 900 or a component of the electronic device 900, the presence or absence of user contact with the electronic device 900, the orientation or acceleration / deceleration of the electronic device 900, and the temperature change of the electronic device 900. The sensor assembly 914 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 914 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 914 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0214] The communication component 916 is configured to facilitate wired or wireless communication between the electronic device 900 and other devices. The electronic device 900 can 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 914 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 914 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0215] In an exemplary embodiment, the electronic device 900 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 to perform the above methods.

[0216] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 904 including instructions, and the instructions can be executed by a processor 920 of an electronic device 900 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0217] A non-temporary computer-readable storage medium, when the instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to perform a recommendation method, the method comprising: obtaining an input sequence; determining an error correction candidate corresponding to the input sequence, and obtaining error correction benefit information and error correction cost information corresponding to the error correction candidate; and recommending the error correction candidate based on the error correction benefit information and error correction cost information corresponding to the error correction candidate.

[0218] Optionally, the method further includes: determining other candidates corresponding to the input sequence, the other candidates including candidates other than the error correction candidate; and recommending the error correction candidate based on the error correction benefit information and the false correction cost information corresponding to the error correction candidate, including: recommending the error correction candidate based on the error correction benefit information and the false correction cost information corresponding to the error correction candidate and in combination with the other candidates.

[0219] Optionally, the obtaining of the error correction cost information corresponding to the recommended error correction candidate includes: sorting the error correction candidate and other candidates according to the candidate score corresponding to the error correction candidate and the candidate scores of other candidates; determining a first candidate set to be displayed on the first screen based on the sorting result, the first candidate set including the error correction candidate and / or other candidates; if there is an error correction candidate in the first candidate set, determining a second candidate set to be displayed on the first screen when the error correction candidate does not exist; determining the on-screen cost increment information of the candidates in the second candidate set and the candidates in the first candidate set, and determining the error correction cost information corresponding to the error correction candidate based on the on-screen cost increment information.

[0220] Optionally, the obtaining of error correction benefit information corresponding to the recommended error correction candidate includes: determining position information of the character to be corrected in the input sequence, backspace cost information corresponding to the error correction candidate, and input cost information corresponding to the error correction candidate; and determining the error correction benefit information corresponding to the error correction candidate based on the position information of the character to be corrected, the input cost information and the backspace cost information.

[0221] Optionally, the error correction candidate is recommended based on the error correction benefit information and the false correction cost information corresponding to the error correction candidate and in combination with the other candidates, including: judging whether the error correction benefit information is greater than the false correction cost information; if the error correction benefit information is greater than the false correction cost information, then controlling the error correction candidate to be displayed on the first screen; if the false correction cost information is greater than the error correction benefit information, then controlling not to display the error correction candidate on the first screen and displaying other candidates.

[0222] Optionally, the error correction candidate is recommended based on the error correction benefit information and the false correction cost information corresponding to the error correction candidate and in combination with the other candidates, including: when it is determined that the error correction benefit information is greater than the false correction cost information, judging whether the difference between the error correction benefit information and the false correction cost information is greater than a preset threshold; if the difference between the error correction benefit information and the false correction cost information is greater than the preset threshold, then controlling the error correction candidate to be displayed on the first screen; if the difference between the error correction benefit information and the false correction cost information is less than the preset threshold, then controlling not to display the error correction candidate on the first screen and displaying other candidates.

[0223] Optionally, the obtaining of the error correction cost information corresponding to the recommendation of the error correction candidate includes: determining the upper-screen cost information corresponding to when the error correction candidate is displayed at various positions on the first screen; determining the upper-screen cost information corresponding to when the error correction candidate is displayed at various positions on the first screen as the error correction cost information corresponding to when the error correction candidate is displayed at various positions on the first screen.

[0224] Optionally, the error correction candidate is recommended based on the error correction benefit information and the false correction cost information corresponding to the error correction candidate and in combination with the other candidates, including: sorting the error correction candidate and the other candidates according to the candidate score corresponding to the error correction candidate and the candidate score of the other candidates; determining a third candidate set to be displayed on the first screen according to the sorting result, the third candidate set including the error correction candidate and / or other candidates; if there is an error correction candidate in the third candidate set, selecting a target position where the error correction benefit information is greater than the false correction cost information when the error correction candidate is displayed at each position on the first screen; displaying the error correction candidate in the third candidate set at the target position on the first screen, and displaying other candidates in the third candidate set at other positions on the first screen.

[0225] Optionally, the error correction candidate is recommended based on the error correction benefit information and the false correction cost information corresponding to the error correction candidate and in combination with the other candidates, including: sorting the error correction candidate and the other candidates according to the candidate score corresponding to the error correction candidate and the candidate score of the other candidates; determining a third candidate set to be displayed on the first screen according to the sorting result, the third candidate set including the error correction candidate and / or other candidates; if there is an error correction candidate in the third candidate set, selecting a candidate position where the error correction benefit information of the error correction candidate is greater than the false correction cost information when the error correction candidate is displayed at each position on the first screen; selecting a target position where the difference between the error correction benefit information and the false correction cost information is greater than a preset threshold from each candidate position of the error correction candidate on the first screen; displaying the error correction candidate in the third candidate set at the target position on the first screen, and displaying other candidates in the third candidate set at other positions on the first screen.

[0226] Fig.101 is a schematic diagram of a structure of an electronic device 1000 for recommendation according to another exemplary embodiment of the present invention. The electronic device 1000 may be a server, which may have relatively large differences due to different configurations or performances, and may include one or more central processing units (CPU) 1022 (for example, one or more processors) and a memory 1032, and one or more storage media 1030 (for example, one or more mass storage devices) storing application programs 1042 or data 1044. Among them, the memory 1032 and the storage medium 1030 may be temporary storage or permanent storage. The program stored in the storage medium 1030 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the server. Furthermore, the central processor 1022 may be configured to communicate with the storage medium 1030 and execute a series of instruction operations in the storage medium 1030 on the server.

[0227] The server may also include one or more power supplies 1026, one or more wired or wireless network interfaces 1090, one or more input and output interfaces 1098, one or more keyboards 1096, and / or, one or more operating systems 1041, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.

[0228] In an exemplary embodiment, the server is configured to execute one or more programs including instructions for performing the following operations by one or more central processors 1022: obtaining an input sequence; determining the error correction candidates corresponding to the input sequence, and obtaining error correction benefit information and error correction cost information corresponding to the error correction candidates; and recommending the error correction candidates based on the error correction benefit information and error correction cost information corresponding to the error correction candidates.

[0229] Optionally, it also includes instructions for performing the following operations: determining other candidates corresponding to the input sequence, the other candidates including candidates other than the error correction candidate; recommending the error correction candidate based on the error correction benefit information and the error correction cost information corresponding to the error correction candidate, including: recommending the error correction candidate based on the error correction benefit information and the error correction cost information corresponding to the error correction candidate, and in combination with the other candidates.

[0230] Optionally, the obtaining of the error correction cost information corresponding to the recommended error correction candidate includes: sorting the error correction candidate and other candidates according to the candidate score corresponding to the error correction candidate and the candidate scores of other candidates; determining a first candidate set to be displayed on the first screen based on the sorting result, the first candidate set including the error correction candidate and / or other candidates; if there is an error correction candidate in the first candidate set, determining a second candidate set to be displayed on the first screen when the error correction candidate does not exist; determining the on-screen cost increment information of the candidates in the second candidate set and the candidates in the first candidate set, and determining the error correction cost information corresponding to the error correction candidate based on the on-screen cost increment information.

[0231] Optionally, the obtaining of error correction benefit information corresponding to the recommended error correction candidate includes: determining position information of the character to be corrected in the input sequence, backspace cost information corresponding to the error correction candidate, and input cost information corresponding to the error correction candidate; and determining the error correction benefit information corresponding to the error correction candidate based on the position information of the character to be corrected, the input cost information and the backspace cost information.

[0232] Optionally, the error correction candidate is recommended based on the error correction benefit information and the false correction cost information corresponding to the error correction candidate and in combination with the other candidates, including: judging whether the error correction benefit information is greater than the false correction cost information; if the error correction benefit information is greater than the false correction cost information, then controlling the error correction candidate to be displayed on the first screen; if the false correction cost information is greater than the error correction benefit information, then controlling not to display the error correction candidate on the first screen and displaying other candidates.

[0233] Optionally, the error correction candidate is recommended based on the error correction benefit information and the false correction cost information corresponding to the error correction candidate and in combination with the other candidates, including: when it is determined that the error correction benefit information is greater than the false correction cost information, judging whether the difference between the error correction benefit information and the false correction cost information is greater than a preset threshold; if the difference between the error correction benefit information and the false correction cost information is greater than the preset threshold, then controlling the error correction candidate to be displayed on the first screen; if the difference between the error correction benefit information and the false correction cost information is less than the preset threshold, then controlling not to display the error correction candidate on the first screen and displaying other candidates.

[0234] Optionally, the obtaining of the error correction cost information corresponding to the recommendation of the error correction candidate includes: determining the upper-screen cost information corresponding to when the error correction candidate is displayed at various positions on the first screen; determining the upper-screen cost information corresponding to when the error correction candidate is displayed at various positions on the first screen as the error correction cost information corresponding to when the error correction candidate is displayed at various positions on the first screen.

[0235] Optionally, the error correction candidate is recommended based on the error correction benefit information and the false correction cost information corresponding to the error correction candidate and in combination with the other candidates, including: sorting the error correction candidate and the other candidates according to the candidate score corresponding to the error correction candidate and the candidate score of the other candidates; determining a third candidate set to be displayed on the first screen according to the sorting result, the third candidate set including the error correction candidate and / or other candidates; if there is an error correction candidate in the third candidate set, selecting a target position where the error correction benefit information is greater than the false correction cost information when the error correction candidate is displayed at each position on the first screen; displaying the error correction candidate in the third candidate set at the target position on the first screen, and displaying other candidates in the third candidate set at other positions on the first screen.

[0236] Optionally, the error correction candidate is recommended based on the error correction benefit information and the false correction cost information corresponding to the error correction candidate and in combination with the other candidates, including: sorting the error correction candidate and the other candidates according to the candidate score corresponding to the error correction candidate and the candidate score of the other candidates; determining a third candidate set to be displayed on the first screen according to the sorting result, the third candidate set including the error correction candidate and / or other candidates; if there is an error correction candidate in the third candidate set, selecting a candidate position where the error correction benefit information of the error correction candidate is greater than the false correction cost information when the error correction candidate is displayed at each position on the first screen; selecting a target position where the difference between the error correction benefit information and the false correction cost information is greater than a preset threshold from each candidate position of the error correction candidate on the first screen; displaying the error correction candidate in the third candidate set at the target position on the first screen, and displaying other candidates in the third candidate set at other positions on the first screen.

[0237] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0238] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0239] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0240] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0241] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0242] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0243] A recommended method, a recommended device and an electronic device provided by the present invention are introduced in detail above. Specific examples are used in this article to illustrate the principle and implementation mode of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation mode and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A recommendation method, characterized in that: include: Get the input sequence; Determine the error correction candidate corresponding to the input sequence, and obtain error correction benefit information and error correction cost information corresponding to the recommended error correction candidate; The error correction benefit information is used to describe the degree to which the recommendation of the error correction candidate improves the user input efficiency, and the miscorrection cost information is used to describe the degree to which the recommendation of the error correction candidate reduces the user input efficiency; Based on the error correction benefit information and the error correction cost information corresponding to the error correction candidate, and in combination with other candidates, recommend the error correction candidate; The step of obtaining the error correction benefit information and the error correction cost information corresponding to the error correction candidate recommended includes: quantifying the cost of backspacing and re-entering by the user to obtain the error correction candidate reduced by recommending the error correction candidate, to obtain the error correction benefit information; The cost of the user displaying the other candidates increased by recommending the error correction candidate is quantified to obtain the error correction cost information.

2. The method according to claim 1, characterized in that The method further comprises: The other candidates corresponding to the input sequence are determined, wherein the other candidates include candidates other than the error correction candidate.

3. The method according to claim 2, characterized in that The obtaining of the miscorrection cost information corresponding to the recommended error correction candidate includes: Sort the error correction candidate and other candidates according to the candidate score corresponding to the error correction candidate and the candidate scores of other candidates; Determine a first candidate set to be displayed on the first screen according to the sorting result, wherein the first candidate set includes error correction candidates and / or other candidates; If there is an error correction candidate in the first candidate set, then when it is determined that the error correction candidate does not exist, the second candidate set is displayed on the first screen; Determine the first on-screen cost information corresponding to the candidate in the second candidate set according to the on-screen cost information corresponding to the position of the candidate in the second candidate set displayed on the first screen when the error correction candidate does not exist; Determine the second on-screen cost information corresponding to the candidate in the second candidate set according to the on-screen cost information corresponding to the position of the candidate in the second candidate set displayed on the first screen when the error correction candidate exists; According to the first on-screen cost information and the second on-screen cost information, the on-screen cost increment information of the candidates in the second candidate set and the candidates in the first candidate set is determined, and the error correction cost information corresponding to the error correction candidate is determined based on the on-screen cost increment information.

4. The method according to claim 1, characterized in that: The obtaining of error correction benefit information corresponding to the recommended error correction candidate includes: Determine the position information of the character to be corrected in the input sequence, the backspace cost information corresponding to the error correction candidate, and the input cost information corresponding to the error correction candidate; the input cost information is used to describe the cost required to delete all the input sequence currently input and input the input sequence corresponding to the error correction candidate; According to the position information of the character to be corrected, input cost information and backspace cost information, the error correction benefit information corresponding to the error correction candidate is determined.

5. The method according to claim 2, characterized in that: The recommending the error correction candidate based on the error correction benefit information and the error correction cost information corresponding to the error correction candidate and in combination with the other candidates includes: Determine whether the error correction benefit information is greater than the error correction cost information; If the error correction benefit information is greater than the error correction cost information, controlling the display of the error correction candidate on the first screen; If the error correction cost information is greater than the error correction benefit information, the error correction candidate is not displayed on the first screen and other candidates are displayed.

6. The method according to claim 2, characterized in that The recommending the error correction candidate based on the error correction benefit information and the error correction cost information corresponding to the error correction candidate and in combination with the other candidates includes: When it is determined that the error correction benefit information is greater than the error correction cost information, determining whether the difference between the error correction benefit information and the error correction cost information is greater than a preset threshold; If the difference between the error correction benefit information and the error correction cost information is greater than a preset threshold, controlling the display of the error correction candidate on the first screen; If the difference between the error correction benefit information and the error correction cost information is less than a preset threshold, the error correction candidate is not displayed on the first screen and other candidates are displayed.

7. The method according to claim 2, characterized in that The obtaining of the miscorrection cost information corresponding to the recommended error correction candidate includes: Determine the corresponding on-screen cost information when the error correction candidate is displayed at each position on the first screen; The upper-screen cost information corresponding to when the error correction candidate is displayed at each position on the first screen is determined as the miscorrection cost information corresponding to when the error correction candidate is displayed at each position on the first screen.

8. A recommendation device, characterized in that: include: A first acquisition module, used for acquiring an input sequence; A second acquisition module is used to determine the error correction candidate corresponding to the input sequence, and obtain error correction benefit information and error correction cost information corresponding to the error correction candidate; the error correction benefit information is used to describe the degree to which the recommendation of the error correction candidate improves the user input efficiency, and the error correction cost information is used to describe the degree to which the recommendation of the error correction candidate reduces the user input efficiency; A recommendation module, configured to recommend the error correction candidate based on the error correction benefit information and the error correction cost information corresponding to the error correction candidate and in combination with other candidates; The step of obtaining the error correction benefit information and the error correction cost information corresponding to the error correction candidate recommended includes: quantifying the cost of backspacing and re-entering by the user to obtain the error correction candidate reduced by recommending the error correction candidate, to obtain the error correction benefit information; The cost of the user displaying the other candidates increased by recommending the error correction candidate is quantified to obtain the error correction cost information.

9. An electronic device, characterized in that: The system comprises a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors, wherein the one or more programs include instructions for performing the following operations: Get the input sequence; Determine the error correction candidate corresponding to the input sequence, and obtain error correction benefit information and error correction cost information corresponding to the error correction candidate; the error correction benefit information is used to describe the degree to which the recommendation of the error correction candidate improves the user input efficiency, and the error correction cost information is used to describe the degree to which the recommendation of the error correction candidate reduces the user input efficiency; Based on the error correction benefit information and the error correction cost information corresponding to the error correction candidate, and in combination with other candidates, recommend the error correction candidate; The step of obtaining the error correction benefit information and the error correction cost information corresponding to the error correction candidate recommended includes: quantifying the cost of backspacing and re-entering by the user to obtain the error correction candidate reduced by recommending the error correction candidate, to obtain the error correction benefit information; The cost of the user displaying the other candidates increased by recommending the error correction candidate is quantified to obtain the error correction cost information.

10. A readable storage medium, characterized in that: When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the recommendation method as described in any one of method claims 1-7.

Images