Input error correction method, apparatus and device for input error correction

Abstract

This invention provides an input error correction method, apparatus, and device for input error correction. The method specifically includes: determining input stage features; determining a proofreading result based on proofreading rules corresponding to the input stage features; the proofreading rules include: proofreading result acquisition conditions, and / or, the quality of the proofreading result; and displaying the proofreading result. This invention can improve the intelligence of input proofreading and proofreading results, and help users use the proofreading results for error correction, thereby improving input efficiency and enhancing user experience.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer information input, and in particular to an input error correction method and device and a device for input error correction. BACKGROUND

[0002] For users of Chinese, Japanese, Korean and other languages, they generally need to interact with computers through an input method system. For example, a user can input a coded string through a keyboard, and then the input method system converts the coded string into candidate items of the corresponding language according to a preset standard mapping rule and displays the candidate items, and then the user selects a candidate item to be displayed on the screen.

[0003] However, in actual applications, the user may input an incorrect candidate item on the screen due to a wrong key or a wrong screen position, etc. For example, user A is chatting with user B on a mobile device, and user A wants to input "past this period" using the keyboard. However, user A inputs an incorrect candidate item on the screen during the input process, so that the input content in the input box is "past this end time".

[0004] In actual applications, to correct the above error, user A often needs to perform a series of correction operations such as moving the cursor position, deleting the incorrect input content, and re-inputting the correct content. If user A does not find the error of the input content in the input box in time, and sends the incorrect input content to user B; in this case, a series of correction operations such as withdrawing the sent input content and re-inputting the correct content need to be performed. The above correction operations are not only tedious but also easy to cause more editing errors, and affect the input efficiency of the user. SUMMARY

[0005] The input error correction method and device and the device for input error correction provided by the embodiments of the present application can improve the intelligence of input correction and correction results, and help the user to correct errors using the correction results, thereby improving the input efficiency and enhancing the user experience.

[0006] To solve the above problem, the embodiments of the present application disclose an input error correction method, comprising:

[0007] determining an input stage feature;

[0008] determining a correction result according to a correction rule corresponding to the input stage feature; the correction rule comprises: a correction result acquisition condition, and / or a quality of the correction result;

[0009] displaying the correction result.

[0010] On the other hand, the embodiments of the present application disclose an input error correction device, comprising:

[0011] a stage determining module configured to determine an input stage feature;

[0012] a proof result determining module configured to determine a proof result according to a proof rule corresponding to the input stage feature, wherein the proof rule comprises a proof result obtaining condition and / or a quality of the proof result;

[0013] a proof result presenting module configured to present the proof result.

[0014] In still another aspect, an apparatus for input error correction is disclosed, comprising a memory, and one or more programs stored in the memory and configured to be executed by one or more processors, wherein the one or more programs contain instructions for performing the following operations:

[0015] determining an input stage feature;

[0016] determining a proof result according to a proof rule corresponding to the input stage feature, wherein the proof rule comprises a proof result obtaining condition and / or a quality of the proof result;

[0017] presenting the proof result.

[0018] In still another aspect, a machine readable medium having instructions stored thereon, which when executed by one or more processors, cause an apparatus to perform the input error correction method as described in one or more of the preceding aspects.

[0019] Embodiments of the present application have the following advantages:

[0020] Embodiments of the present application preset a proof rule corresponding to an input stage feature, and determine a proof result according to a proof rule corresponding to a real-time input stage feature, so as to match the proof result with the error tolerance degree and proof willingness reflected by the real-time input stage feature. Since embodiments of the present application can provide a proof result matched with the demand willingness of a user, the intelligence of input proof and proof result can be improved, and the user can use the proof result to correct errors, thereby improving input efficiency and enhancing user experience.

[0021] The proof rule of embodiments of the present application can comprise a proof result obtaining condition and / or a quality of the proof result.

[0022] The proof result obtaining condition can represent a condition or threshold that is satisfied by the proof result obtaining. In the case that the user has a high error tolerance and a weak proof willingness, a strict proof result obtaining condition can be used. Alternatively, in the case that the user has a low error tolerance and a strong proof willingness, a loose proof result obtaining condition can be used, or no proof result obtaining condition is set, in which case the proof result obtaining can be directly executed.

[0023] The quality of the proof result can represent the advantages and disadvantages of the proof result. In the case that the user has a high error tolerance and a weak proof willingness, a higher quality proof result and a more convenient interaction form will improve the user's proof willingness. Alternatively, in the case that the user has a low error tolerance and a strong proof willingness, the quality of the proof result can be appropriately reduced, and more proof results can be provided to improve the coverage of the proof results. BRIEF DESCRIPTION OF DRAWINGS

[0024] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the description of the embodiments of the present application. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor under the premise of the drawings.

[0025] Figure 1 is a schematic diagram of an application environment of an input error correction method according to an embodiment of the present application;

[0026] Figure 2 is a step flow chart of an input error correction method according to an embodiment of the present application;

[0027] Figure 3 is a step flow chart of an input error correction method according to an embodiment of the present application;

[0028] Figure 4 is a structural block diagram of an input error correction device according to an embodiment of the present application;

[0029] Figure 5 is a block diagram of an input error correction device 800 according to an embodiment of the present application; and

[0030] Figure 6 is a structural diagram of a server in some embodiments of the present application. DETAILED DESCRIPTION

[0031] With reference to the drawings and embodiments of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of the present application.

[0032] The input error correction scheme provided by the embodiments of the present application can include: determining an input stage feature; determining a proofreading result according to a proofreading rule corresponding to the input stage feature; the proofreading rule specifically includes a proofreading result obtaining condition and / or quality of the proofreading result; and presenting the proofreading result.

[0033] In the embodiments of the present application, the input stage feature can be used to represent the characteristics of the interval paragraph in the input process.

[0034] For example, the input stage feature of the embodiments of the present application can specifically include any one of the following stage features:

[0035] Before sending after on-screen, and detecting the operation of moving the cursor; or

[0036] Before sending after on-screen, and detecting the operation of moving the cursor; or

[0037] After sending, and detecting the operation of continuing to input; or

[0038] After sending, and detecting the operation of continuing to input.

[0039] In the input process, the cursor is used to display the position of the character to be input. The cursor can be presented in the form of a vertical line.

[0040] In the process of implementing the embodiments of the present application, the input stage feature can reflect the error tolerance degree and proofreading willingness of the user; and different input stage features can reflect different error tolerance degrees and proofreading willingness. The error tolerance and proofreading willingness of the user are usually different in different input stages, that is, different input stage features usually correspond to different proofreading rules.

[0041] The embodiments of the present application preset the corresponding proofreading rules for the input stage features, and determine the proofreading result according to the proofreading rules corresponding to the real-time input stage features, so that the proofreading result matches the error tolerance degree and proofreading willingness reflected by the real-time input stage features. Since the embodiments of the present application can provide the proofreading result matched with the demand willingness of the user, the intelligence of the proofreading result can be improved, and the user can use the proofreading result to correct errors, thereby improving the input efficiency and enhancing the user experience.

[0042] The proofreading rule of the embodiment of the present application can include: a proofreading result obtaining condition and / or a quality of the proofreading result.

[0043] The proofreading result obtaining condition can represent a condition or threshold that is satisfied by the obtaining of the proofreading result. In the case that the user has a high error tolerance and a weak proofreading willingness, a more stringent proofreading result obtaining condition can be used. Alternatively, in the case that the user has a low error tolerance and a strong proofreading willingness, a more lenient proofreading result obtaining condition can be used, or no proofreading result obtaining condition is set, in which case the obtaining of the proofreading result can be directly performed.

[0044] The quality of the proofreading result can represent the advantages and disadvantages of the proofreading result. In the case that the user has a high error tolerance and a weak proofreading willingness, a higher quality proofreading result and a more convenient interaction form will improve the proofreading willingness of the user. Alternatively, in the case that the user has a low error tolerance and a strong proofreading willingness, the quality of the proofreading result can be appropriately reduced, and more proofreading results can be provided to improve the coverage of the proofreading result.

[0045] The input error correction method provided by the embodiment of the present application can be applied to Figure 1 The application environment is shown in FIG. 1. Figure 1 The client 100 and the server 200 are located in a wired or wireless network, and the client 100 and the server 200 perform data interaction through the wired or wireless network.

[0046] Optionally, the client 100 can run on a terminal, and the terminal specifically includes but is not limited to: a smart phone, a tablet computer, an e-book reader, an MP3 (Moving Picture Experts Group Audio Layer III) player, an MP4 (Moving Picture Experts Group Audio Layer IV) player, a laptop computer, a vehicle-mounted computer, a desktop computer, a set-top box, a smart television, a wearable device, and the like. The client 100 can correspond to a website or an APP (Application). The client 100 can correspond to an input method APP, an instant messaging APP, and the like.

[0047] The server of the embodiment of the present application can be a cloud server. The cloud server is a kind of computing service that is simple and efficient, safe and reliable, and has elastic processing capacity. The resource information of the cloud server is dynamic, so that the processing capacity of the cloud server is elastic.

[0048] The embodiment of the present application can be applied to an input method program of various input modes such as keyboard symbol, handwriting, voice, etc. Taking the keyboard symbol input mode as an example, a user can input characters by an encoding string, and the input string can refer to the encoding string input by the user. In the input method field, for an input method program of Chinese, Japanese, Korean, or other languages, the input string input by the user can be usually converted into a candidate of the corresponding language. Hereinafter, taking Chinese as an example, other languages such as Japanese and Korean can be referred to each other. It can be understood that the Chinese input method described above can include, but is not limited to, full spelling, simple spelling, stroke, and five-stroke, etc. The embodiment of the present application does not limit the specific input method program corresponding to a certain language.

[0049] Taking the input of Chinese as an example, the type of the encoding string can include a pinyin string and a character string (such as a five-stroke string, etc.). Taking the input of English as an example, the type of the encoding string can include a letter string, etc.

[0050] In actual application, for the input mode of keyboard symbol, the user can input the input string by a physical keyboard or a virtual keyboard, etc. For example, for a terminal with a touch screen, a virtual keyboard can be set in an input interface to input the input string by triggering a virtual key included in the virtual keyboard. Optionally, examples of the virtual keyboard can include a 9-key keyboard and a 26-key keyboard, etc. It can be understood that in addition to the virtual keys corresponding to letters, the input interface can also be provided with symbol keys, number keys, function keys such as Chinese-English switching keys, or tool bar keys, etc. It can be understood that the embodiment of the present application does not limit the specific keys contained in the input interface.

[0051] According to some embodiments, the input string can include, but is not limited to, one key symbol or a combination of multiple key symbols input by the user. The key symbol can specifically include pinyin, stroke, and hiragana, etc.

[0052] In the embodiment of the present application, the candidate can be used to represent one or more characters provided by the input method program to be selected by the user. The candidate can be a character of Chinese, English, Japanese, etc. The candidate can also be a combination of symbols in the form of color text and picture, etc. The color text includes, but is not limited to, a picture composed of lines, symbols, and characters, for example, examples of the color text can include ":P", ":-o", ":-)", etc.

[0053] Method embodiment one

[0054] Reference Figure 2 Fig. 1 shows a step flowchart of an input error correction method embodiment one of the present application, which can specifically include the following steps:

[0055] Step 201, determining an input stage feature;

[0056] Step 202, determining a proofreading result according to a proofreading rule corresponding to the input stage feature; the proofreading rule can include a proofreading result obtaining condition and / or quality of the proofreading result;

[0057] Step 203, presenting the proofreading result.

[0058] Figure 2 The method embodiments can be executed by a client and / or a server, and it can be understood that the embodiments of the present application do not limit the specific execution subject of the method embodiments.

[0059] In step 201, the input stage feature can be used to represent the characteristics of the interval paragraph in the input process.

[0060] For example, the input stage feature of the embodiments of the present application can specifically include any one of the following stage features:

[0061] Input stage feature 1, after onscreen and before sending, and no operation of moving the cursor is detected; or

[0062] Input stage feature 2, after onscreen and before sending, and the operation of moving the cursor is detected; or

[0063] Input stage feature 3, after sending, and no operation of continuing input is detected; or

[0064] Input stage feature 4, after sending, and the operation of continuing input is detected; the operation of continuing input can include receiving the input string of the user, but no onscreen operation of the user for the candidate is received.

[0065] In the embodiments of the present application, optionally, the user operation can be detected, and the input stage feature can be determined according to the detection result.

[0066] According to an embodiment, the operation time of the user operation can be recorded, and the input stage feature can be determined according to the latest user operation (i.e., the most recent user operation) of the operation time. For example, the most recent user operation is the onscreen operation, and the input stage feature is the input stage feature 1. For another example, the most recent user operation is the operation of moving the cursor, and the input stage feature is the input stage feature 2. For another example, the most recent user operation is the sending operation, and the input stage feature is the input stage feature 3.

[0067] According to another embodiment, the input stage feature can be determined according to a subsequent operation of the input operation. For example, if the subsequent operation of the input operation includes a sending operation and a continue input operation, the input stage feature is the input stage feature 4. It can be understood that, between the sending operation and the continue input operation, the user operation can further include a withdrawal operation for the input content.

[0068] In step 202, the corresponding proofreading rule can be determined according to the error tolerance degree and the proofreading intention reflected by the input stage feature.

[0069] The embodiment of the present application can provide the following implementation of the proofreading rule:

[0070] The proofreading rule 1 can include the first proofreading result acquisition condition and the first proofreading result if the input stage feature is before sending after inputting and no operation of moving the cursor is detected; and / or

[0071] The proofreading rule 2 can include the second proofreading result if the input stage feature is before sending after inputting and the operation of moving the cursor is detected; and / or

[0072] The proofreading rule 3 can include the second proofreading result acquisition condition and the third proofreading result if the input stage feature is after sending and no operation of continuing inputting is detected; and / or

[0073] The proofreading rule 4 can include the third proofreading result acquisition condition and the fourth proofreading result if the input stage feature is after sending and the operation of continuing inputting is detected.

[0074] It should be noted that the proofreading rule 2 corresponds to the input stage feature 2. Since the user finds the error in the input content and tries to move the cursor to the position of the error to proofread the error when the input stage feature is the input stage feature 2, it indicates that the user has a low error tolerance degree and a strong proofreading intention. In this case, no proofreading result acquisition condition can be set in the proofreading rule 2, and thus the acquisition of the proofreading result can be directly performed.

[0075] For the input stage feature 1, the input stage feature 3 and the input stage feature 4, since no operation of moving the cursor is detected, it can be considered that the user still has a certain error tolerance degree, and thus the corresponding proofreading result acquisition condition can be set in the corresponding proofreading rule.

[0076] In the embodiment of the present application, at least part of the quality of the second proofreading result is lower than the quality of the third proofreading result or the fourth proofreading result; at least part of the quality of the third proofreading result or the fourth proofreading result is lower than the quality of the first proofreading result.

[0077] From the perspective of quantity, for the same on-screen content, the range or set corresponding to the first proofreading result can be smaller than the range or set corresponding to the third proofreading result or the fourth proofreading result, and the range or set corresponding to the third proofreading result or the fourth proofreading result can be smaller than the range or set corresponding to the second proofreading result.

[0078] From the perspective of quality, assuming that the quality levels of the proofreading results include quality level 3, quality level 2 and quality level 1, wherein the quality represented by quality level 3 is higher than the quality represented by quality level 2, and the quality represented by quality level 2 is higher than the quality represented by quality level 1. The first proofreading result can include the proofreading result corresponding to quality level 3, the second proofreading result can include the proofreading result corresponding to quality level 3 and quality level 2, and the third proofreading result can include the proofreading result corresponding to quality level 3, quality level 2 and quality level 1.

[0079] In the embodiment of the present application, optionally, the quality score of the first proofreading result exceeds the first threshold value, the quality score of the second proofreading result exceeds the second threshold value, the quality score of the third proofreading result exceeds the first threshold value, and the quality score of the fourth proofreading result exceeds the third threshold value; wherein the first threshold value is greater than the third threshold value, and the third threshold value is greater than the second threshold value.

[0080] Optionally, the proofreading result with a quality score exceeding the first threshold value can correspond to quality level 3, the proofreading result with a quality score between the second threshold value and the first threshold value can correspond to quality level 2, and the proofreading result with a quality score between the third threshold value and the second threshold value can correspond to quality level 1.

[0081] The embodiment of the present application can provide the following technical solutions for determining proofreading results:

[0082] Technical solution A1,

[0083] In technical solution A1, if the input stage feature is after on-screen and before sending, and no operation of moving the cursor is detected, the determination of the proofreading result can specifically include: if the first proofreading result acquisition condition is met, requesting the first proofreading result from the server; the quality score of the first proofreading result can exceed the first threshold value.

[0084] Optionally, the first proofreading result acquisition condition specifically includes:

[0085] The number of characters of the on-screen content is within a first preset character range; and

[0086] detecting an input operation for a preset punctuation mark, or detecting an onscreen operation for content from a preset source.

[0087] In an optional embodiment of the present application, the dynamic first preset character range can be determined according to a dynamic cloud resource level.

[0088] Optionally, the greater the value corresponding to the cloud resource level, the more abundant the cloud resource information, and the greater the character range represented by the first preset character range; conversely, the smaller the value corresponding to the cloud resource level, the more lacking the cloud resource information, and the smaller the character range represented by the first preset character range. Examples of the first preset character range can be 2-200, etc.

[0089] In actual application, the server can issue the cloud resource level and the mapping relationship between the cloud resource level and the preset character range to the client. Moreover, the server can update the cloud resource level according to real-time cloud resource information and issue the updated cloud resource level to the client.

[0090] Detecting the input operation for the preset punctuation mark can mean that the onscreen content corresponds to a language unit with high integrity, and the language unit with high integrity can be a sentence, a sentence component such as a subject or a predicate or an object, etc.

[0091] The preset punctuation mark can be determined by those skilled in the art according to actual application requirements. For example, the preset punctuation mark can include a comma “,”, a period “.”, a question mark “?”, an exclamation mark “!”, a sentence point “.”, and a space, etc. It can be understood that the embodiments of the present application do not limit the specific preset punctuation mark.

[0092] Detecting the onscreen operation for the content from the preset source can mean that a preset source is used to complete the input with high integrity.

[0093] In the case where the onscreen content corresponds to a language unit with high integrity or the input with high integrity is completed by using a preset source, the embodiments of the present application request the first proofreading result from the server. Since the server can obtain the first proofreading result according to the content with high integrity, the accuracy of the first proofreading result can be improved.

[0094] Optionally, requesting the proofreading result from the server can specifically include: sending a request to the server and receiving the proofreading result returned by the server according to the request.

[0095] Optionally, the request can include one or more onscreen contents. The request can also include input stage features so that the user determines the proofreading result according to the quality corresponding to the input stage features.

[0096] Optionally, in the embodiment of the present application, after the first proofreading result is requested from the server, the first proofreading result can be saved to the local cache for subsequent use.

[0097] Technical solution A2,

[0098] In technical solution A2, if the input stage feature is after the content is on the screen and before the content is sent, and the operation of moving the cursor is detected, the determination of the proofreading result specifically includes: requesting a second proofreading result from the server; and the quality score of the second proofreading result can exceed a second threshold.

[0099] In the case where the input stage feature is input stage feature 2, the user finds the error in the on-screen content and tries to move the cursor to the position where the error is input to proofread the error. This situation indicates that the user has a low error tolerance and a strong proofreading willingness. In this case, no proofreading result acquisition condition can be set in proofreading rule 2, so the acquisition of the proofreading result can be directly performed, that is, the second proofreading result is directly requested from the server.

[0100] Optionally, in the embodiment of the present application, after the second proofreading result is requested from the server, the second proofreading result can be saved to the local cache for subsequent use.

[0101] Technical solution A3,

[0102] In technical solution A3, if the input stage feature is after the content is sent and the operation of continuing to input is not detected, the determination of the proofreading result specifically includes:

[0103] querying a third proofreading result from the cache; or

[0104] If the cache query fails, the third proofreading result is requested from the server in the case where the second proofreading result acquisition condition is met.

[0105] The quality score of the third proofreading result exceeds the first threshold.

[0106] In the case where the input stage feature is input stage feature 3, the third proofreading result can be provided. Since the quality score of the third proofreading result exceeds the first threshold, the user can be provided with a high-quality proofreading result in the case where the user has a weak proofreading willingness.

[0107] The third proofreading result can come from the cache. The first proofreading result obtained by technical solution A1 can be saved in the cache, and / or the second proofreading result obtained by technical solution A2 can be saved in the cache.

[0108] In actual application, there can be a case that the requested first proofreading result and / or the second proofreading result is not displayed. For example, the sending operation of the input content by the user is received before the first proofreading result returned by the server is received, resulting in that the second proofreading result cannot be displayed.

[0109] In actual application, there can be a case that the display duration of the requested first proofreading result and / or the second proofreading result is less than the duration threshold, resulting in that the first proofreading result and / or the second proofreading result is not viewed by the user. For example, the sending operation of the input content by the user is received within a short time interval after the first proofreading result returned by the server is received, resulting in that the second proofreading result is not viewed by the user. The duration threshold can be determined by those skilled in the art according to actual application requirements, for example, the duration threshold can be a duration value of 3 seconds.

[0110] The technical solution A3 queries the third proofreading result from the cache in priority, which can reduce the pressure of the server and save the resources consumed by the process of requesting the third proofreading result from the server.

[0111] In the embodiment of the application, the cache can include one or more requested proofreading results, and one requested proofreading result can be referred to as a cache item. The embodiment of the application can record the cache time corresponding to the cache item and the quality score of the corresponding proofreading result.

[0112] Optionally, in the process of querying the third proofreading result from the cache, the querying can be performed in the order from the latest cache time to the earliest cache time, for example, one or two cache items with the latest cache time can be queried. In addition, the query result can be filtered according to the quality score. For example, the proofreading results with a quality score less than a first threshold can be filtered out from the query result, so as to retain the proofreading results with a quality score greater than the first threshold.

[0113] Suppose that the user sends the on-screen content without generating a moving cursor operation after generating the on-screen content, in this case, the second proofreading result is not requested from the server, and the first proofreading result needs to meet certain first proofreading result obtaining conditions. Suppose that the on-screen content does not meet the first proofreading result obtaining conditions (for example, the on-screen content input by the keyboard does not contain a preset punctuation symbol), then the first proofreading result is not requested from the server. Therefore, there is no proofreading result corresponding to the on-screen content in the cache, and the cache query fails.

[0114] In the embodiment of the application, in the case of cache query failure, it is determined whether the second proofreading result obtaining conditions are met, if yes, the third proofreading result is requested from the server. The second proofreading result obtaining conditions can be determined by those skilled in the art according to actual application requirements, for example, the number of characters corresponding to the second proofreading result obtaining conditions is within a second character number range.

[0115] The second character quantity range can be a static range. Alternatively, a dynamic second preset character range can be determined according to a dynamic cloud resource level, which is similar to the determination process of the first preset character range and will not be repeated here. Examples of the second character quantity range can include 6-32, etc.

[0116] Technical solution A4,

[0117] In technical solution A4, if the input stage feature is after sending and a continue input operation is detected, the determination of the proofreading result specifically includes: if the input string and the proofreading result in the cache meet a third proofreading result acquisition condition, a fourth proofreading result is acquired from the cache; and the quality score of the fourth proofreading result exceeds a third threshold value.

[0118] The third proofreading result acquisition condition can represent that the input string input after sending is used to proofread the sent on-screen content.

[0119] Optionally, the third proofreading result acquisition condition can be that the encoding corresponding to the proofreading result in the cache includes the encoding corresponding to the input string, in other words, the encoding corresponding to the input string is a superset or subset of the encoding corresponding to the proofreading result in the cache. For example, the proofreading result in the cache includes "past this period of time, thank you for your help", if the input string is "guoqu" or "zheduan", it can be considered to meet the third proofreading result acquisition condition; and if the input string is "zaizheli", it is considered not to meet the third proofreading result acquisition condition.

[0120] In the embodiment of the application, optionally, the number of characters corresponding to the input string can be greater than a fourth threshold value, for example, the fourth threshold value is 2, etc. That is, the input string and the proofreading result in the cache have at least 3 character codes. Of course, the embodiment of the application does not limit the specific fourth threshold value.

[0121] In the embodiment of the application, optionally, the input string can match the first character of the proofreading result in the cache. For example, the proofreading result in the cache includes "past this period of time, thank you for your help", and the input string is "guoqu". Optionally, in this case, the number of characters corresponding to the fourth proofreading result can match the number of characters of the proofreading result in the cache, so as to present the effect of a whole sentence through the fourth proofreading result.

[0122] In this embodiment of the invention, optionally, the input string can be matched with the middle character of the proofreading result in the cache. Optionally, in this case, the fourth proofreading result can start from the first character matched by the input string and end at the character where the error position (proofreading position) is located, or it can end before the punctuation mark closest to the error position. For example, if the proofreading result in the cache includes "Thank you for your help during this period of time", and the input string is "zheduan", then the fourth proofreading result can be "this period" or "this time".

[0123] In step 203, the proofreading results are displayed, which helps users correct errors, thereby improving input efficiency and enhancing user experience.

[0124] In an optional embodiment of the present invention, the proofreading result can be displayed according to the display style information corresponding to the input stage features; the display style information may include: display position, and / or, display content.

[0125] Users typically handle errors differently depending on the characteristics of different stages of input. For example, a user may be typing or about to type if they haven't noticed an error. Conversely, if a user notices an error, they may move the cursor to locate it.

[0126] To address the processing methods for users at different input stages, embodiments of the present invention can provide different display style information to increase the likelihood of the proofreading results being viewed and used by users, and to reduce the conflict between the proofreading results and the user's typing process.

[0127] In this embodiment of the invention, optionally, if the input stage feature is an operation of moving the cursor after being displayed on the screen but before being sent, and the operation of moving the cursor is detected, the display position includes: a candidate position. The operation of moving the cursor is usually performed when the user discovers an error. In this case, the user usually intends to position the cursor to the wrong position and does not intend to type temporarily, so the candidate position is temporarily empty. Therefore, the second proofreading result can be displayed at the candidate position.

[0128] Optionally, the candidate position may include: the input string position and the candidate field. Optionally, the displayed text at the input string position may be: "XX" replaced with "YY", where "XX" is the content that was mistakenly entered and "YY" is the target correction candidate. An example of the displayed text could be: "End" replaced with "Segment".

[0129] Optionally, proofreading results can be displayed in the candidate column. Multiple proofreading results that meet the criteria can be displayed, and the proofreading results can be at the word level, such as "paragraph".

[0130] Optionally, if a trigger operation is received for the proofreading result, the triggered proofreading result can be used to replace the erroneous object.

[0131] In this embodiment of the invention, optionally, if the input stage feature is an operation that occurs after the content is displayed but before it is sent, and a cursor movement is detected, then the user's focus is on the error. Therefore, the granularity of the language unit corresponding to the displayed content (proofreading result) can correspond to the granularity of the language unit corresponding to the error. For example, if the granularity of the language unit corresponding to the error is a character, then the granularity of the language unit corresponding to the proofreading result is a character; or, if the granularity of the language unit corresponding to the error is a word, then the granularity of the language unit corresponding to the proofreading result is a word; or, if the granularity of the language unit corresponding to the error is a phrase, then the granularity of the language unit corresponding to the proofreading result is a phrase; or, if the granularity of the language unit corresponding to the error is a sentence, then the granularity of the language unit corresponding to the proofreading result is a sentence.

[0132] In this embodiment of the invention, optionally, if the input stage feature is not an operation that occurs after the screen is displayed but before the data is sent, and a cursor movement is detected, the display position includes: a non-candidate position. This embodiment of the invention can display the corresponding proofreading result at a non-candidate position.

[0133] In this scenario, the input stage features may include: Input Stage Feature 1, Input Stage Feature 3, or Input Stage Feature 4, etc. In this case, the user is typing or about to type, and during the typing process, candidate positions are displayed to show candidates corresponding to the user's input string. Therefore, to reduce the conflict between the proofreading result and the user's typing process, the display position in this case can be a non-candidate position. Typically, candidate positions are located on the left side of the input interface, so non-candidate positions can be located on the right side of the input interface, etc. It is understood that positions different from candidate positions are all within the protection scope of non-candidate positions in this embodiment of the invention.

[0134] In this embodiment of the invention, optionally, if the input stage feature is not the operation of sending after being displayed on the screen and before the cursor is detected, then the granularity of the language unit corresponding to the displayed content (proofreading result) can be a sentence or a paragraph.

[0135] Since the proofreading result corresponds to a word or phrase at the granularity of the language unit, the user needs to substitute the proofreading result into the original sentence to confirm whether the proofread sentence is fluent and correct. In this embodiment of the invention, the proofreading result corresponds to a clause or sentence at the granularity of the language unit, which can save the user the verification operation of substituting words into the original sentence, thus improving the user's input efficiency and enhancing the user experience.

[0136] In this embodiment of the invention, optionally, during the process of displaying the proofreading results, characters corresponding to input errors in the proofreading results can be marked and displayed to prompt the user with the corresponding correction content. Marking and display can include: highlighting or displaying text in a preset color, etc.

[0137] In this embodiment of the invention, optionally, if the display position cannot fully display the proofreading result, a hiding effect can be used on the left and right ends of the proofreading result to display the correction content corresponding to the input error in the middle of the display position, thereby exposing the correction content corresponding to the input error to the user's view. For example, if the proofreading result is "this period of time in the past", the input error is "this end", and the correction content is "this section", then "this section" can be displayed in the middle of the display position.

[0138] In this embodiment of the invention, the display duration of the calibration results can exceed a duration threshold in order to avoid flickering of the calibration results.

[0139] In summary, the input error correction method of this invention presets corresponding proofreading rules for input stage features and determines the proofreading result based on the proofreading rules corresponding to the real-time input stage features, so that the proofreading result matches the error tolerance and proofreading intention reflected by the real-time input stage features. Since this invention can provide users with proofreading results that match their needs and intentions, it can improve the intelligence of input proofreading and proofreading results, and help users use the proofreading results for error correction, thereby improving input efficiency and enhancing user experience.

[0140] The proofreading rules in this embodiment of the invention may include: proofreading result acquisition conditions and / or the quality of the proofreading results.

[0141] Among them, the proofreading result acquisition conditions can characterize the conditions or thresholds that must be met to acquire the proofreading results. When users have a high tolerance for errors and a weak willingness to proofread, stricter proofreading result acquisition conditions can be adopted. Alternatively, when users have a low tolerance for errors and a strong willingness to proofread, more lenient proofreading result acquisition conditions can be adopted; or no proofreading result acquisition conditions can be set, in which case the proofreading results can be acquired directly.

[0142] The quality of proofreading results can characterize their effectiveness. When users have a high tolerance for errors and a low willingness to proofread, higher quality proofreading results and more convenient interaction methods will increase users' willingness to proofread. Alternatively, when users have a low tolerance for errors and a high willingness to proofread, the quality requirements for proofreading results can be appropriately lowered, and more proofreading results can be provided to increase the coverage of proofreading results.

[0143] Method Example 2

[0144] This embodiment of the invention describes the process by which the server determines the verification result based on the request.

[0145] In this embodiment of the invention, the server can identify erroneously uploaded content, determine the target error correction candidate corresponding to the erroneously uploaded content, and obtain the correction result based on the target error correction candidate.

[0146] It should be noted that the content displayed on the screen may include one or more instances of incorrectly displayed content, and one instance of incorrectly displayed content may correspond to one or more target error correction candidates.

[0147] In this embodiment of the invention, the language unit corresponding to the proofreading result obtained by the server can be matched with the language unit corresponding to the content displayed on the screen in the request.

[0148] For example, if the language unit corresponding to the content displayed in the request is a sentence, then the proofreading result obtained by the server can be a sentence. For example, if the content displayed in the request is "Thank you for your help over this period of time", then the proofreading result can be "Thank you for your help over this period of time".

[0149] For example, if the language unit corresponding to the content displayed in the request is a sentence, then the proofreading result obtained by the server can be the sentence. For instance, if the content displayed in the request is "past time", then the proofreading result can be "past time".

[0150] The embodiments of the present invention can provide the following technical solution for identifying erroneously uploaded content:

[0151] Technical Solution B1

[0152] Recognition scheme B1 can identify erroneously uploaded content from the error correction candidate list, which can specifically include the following sub-steps:

[0153] Sub-step S11: Based on the encoding string corresponding to the term in the content displayed on the screen, search in the error correction candidate list to obtain the error correction candidate that matches the encoding string; wherein, the error correction candidate list may record the mapping relationship between the encoding string and the error correction candidate;

[0154] Sub-step S12: Determine the combination information between the found error correction candidates and the preceding and / or following text of the term;

[0155] Sub-step S13: When the combined information meets the preset combination conditions, the term is determined as the erroneously displayed content in the displayed content.

[0156] For sub-step S11, the mapping relationship between the encoded string and the error correction candidate in the above error correction candidate list may specifically include at least one of the following mapping relationships:

[0157] Mapping Relationship 1: The encoded string of the error correction candidate has the same code as the encoded string in the error correction candidate list;

[0158] The above mapping relationship 1 can be applicable to the situation where the encoded string of the error correction candidate has the same code as the encoded string in the error correction candidate list. The same code here can specifically include: the same code of the pinyin string and the same code of the glyph string, etc.;

[0159] Among them, applicable to the same code situation on a full keyboard (such as a 26-key keyboard), the encoded string of the error correction candidate can be homophonic with the encoded string in the error correction candidate list. For example, the error correction candidates corresponding to the encoded string homophonic with the encoded string "zheduan" in the error correction candidate list can specifically include: "这段", "折断", etc.;

[0160] Applicable to the same code situation on a non-full keyboard (such as a 9-key keyboard), the encoded string of the error correction candidate can also be the encoded string that has the same code as the encoded string in the error correction candidate list on the non-full keyboard. For example, on a nine-grid keyboard, the encoded strings that have the same code as the encoded string "jiehun" in the error correction candidate list can specifically include: "jieguo", "liehuo", "lieguo", "jieguo", "jiehuo", etc.; These error correction candidates corresponding to the encoded strings that have the same code as "jiehun" are all within the application scope of the embodiments of the present invention;

[0161] The glyph string can be applicable to input method systems such as shape codes and Wubi. For example, the error correction candidates corresponding to the encoded string "aw" can specifically include: "茶" and "荼", etc.;

[0162] Mapping relationship 2: There is a preset pairing relationship between the error correction candidate and the entry corresponding to the encoded string in the error correction candidate list;

[0163] The above preset pairing relationship can be the mapping relationship between error-prone words that users are used to typing wrong and correct words, such as "账户" - "帐户", "甘败下风" - "甘拜下风", etc.; It can also be the mapping relationship between dialects and Mandarin, such as "前个" - "前天", "制达" - "这里", etc.

[0164] Mapping relationship 3: The edit distance between the encoded string of the error correction candidate and the encoded string in the error correction candidate list is less than the distance threshold.

[0165] In the embodiments of the present invention, the edit distance can be used to represent the minimum number of edit operations required to convert one encoded string into another between two encoded strings. The above edit operations can specifically include operations such as replacing one character with another character, inserting a character, and deleting a character.

[0166] In one application example 1 of the present invention, the edit distance between "xingfu" and "xinfu" is 1, so they can be each other's error correction candidates. That is, the candidate corresponding to "xingfu" can be used as the error correction candidate for "xinfu" to solve the error correction problem in the case of missing input by the user; or, the candidate corresponding to "xinfu" can be used as the error correction candidate for "xingfu" to solve the error correction problem in the case of multiple inputs.

[0167] In another application example 2 of the present invention, the edit distance between "yingxiong" and "yingxiang" is 2, so they can be each other's error correction candidates to solve the error correction problem in the case of incorrect input.

[0168] In the specific implementation, the words in the sentences corresponding to the above-mentioned content can be scanned in sequence, and the error correction candidate list can be searched according to the corresponding code string of each word to obtain the error correction candidate that matches the corresponding code string of each word.

[0169] For sub-step S12, in a preferred embodiment of the present invention, binary and higher relational data can be used to store the combination information between the above-mentioned at least two words, and the combination information between the found error correction candidate and the preceding and / or following text of the word can be analyzed using binary and higher relational data.

[0170] A binary relation, also known as a 2-gram, can be used to represent the probability of two elements appearing consecutively. In the field of input methods, these elements can be phonemes, syllables, stroke strings, letters, or words. In this embodiment of the invention, the binary relation can specifically include binary relations of words, binary relations of syllables, and binary relations of phonemes and letters. Relations with more than two grams can be used to represent the probability of two or more elements appearing consecutively. For example, a ternary relation can be used to represent the probability of the words "sending you," "marriage," and "gift" appearing consecutively. The following mainly uses binary relations as an example for explanation; relations with more than two grams can be referred to accordingly.

[0171] To ensure the accuracy and representativeness of the binary relation data, in a preferred embodiment of the present invention, the same corpus can be used to statistically analyze the binary relation data of Chinese / English words and / or English / English words and / or Chinese / Chinese words to obtain a binary database. The corpus can be an internet corpus obtained using web crawling technology, or a corpus accumulated by a cloud computing input method; furthermore, the internet can be an internet blog corpus, an internet news corpus, and / or an internet forum corpus, etc. This embodiment of the present invention does not limit the specific corpus used.

[0172] To reflect the probability of two words being used adjacently, in a specific implementation, the binary library can be used to store the collocation relationship and connection parameters between the two words; wherein, the two words may include Chinese words and Chinese words, Chinese words and English words, English words and Chinese words, and English words and English words, etc.

[0173] For sub-step S13, an example of a preset combination condition can be: the found error correction candidate has a matching relationship with the preceding and / or following text of the term, and the corresponding connection parameter is greater than the parameter threshold. The parameter threshold here can be determined by those skilled in the art based on the actual situation, such as 0.8, etc.

[0174] In one application example 3 of the present invention, it is assumed that the content input by the user corresponds to the sentence "the past time" in which the words are "past", "this time" and "time". It is assumed that the error correction candidate "this part" has a collocation relationship with the context of the word and the corresponding connection parameter is greater than the parameter threshold. Therefore, "this time" can be considered as erroneously input content.

[0175] Technical Solution B2

[0176] Technical solution B2 can identify erroneously uploaded content through a user dictionary for error correction. Specifically, it may include the following sub-steps:

[0177] Sub-step S31: Based on the terms in the displayed content, search in the error correction user terminology database to obtain the target term that matches the term; wherein, the error correction user terminology database records the mapping relationship between source terms and target terms, the source terms may specifically include: the term before correction corresponding to the historical error correction behavior and the corresponding preceding and / or following terms; the target terms may specifically include: the term after correction corresponding to the historical error correction behavior and the corresponding preceding and / or following terms;

[0178] Sub-step S32: Based on the term and the preceding and / or following terms in the target term it matches, obtain the corresponding erroneously displayed content.

[0179] In a specific implementation, a mapping relationship between source terms and target terms can be established in the aforementioned error correction user dictionary based on the user's historical error correction behavior. For example, if a user corrects "this end" to "this section" in a certain historical error correction behavior, then this embodiment of the invention can use "this end" as the source term (such as "this end") and "this section" or the corresponding context term as the target term (such as "this period" or "this past period"). Thus, in the user's subsequent input process, the aforementioned error correction user dictionary can be used to identify the erroneously entered content in the input content.

[0180] For example, for the content "past time" corresponding to the application example 3 above, the words in it can be matched with the source words in the error correction user's thesaurus. Among them, "this time" is successfully matched with the source words in the error correction user's thesaurus. Therefore, it can be determined that "this time" is the wrong content displayed on screen, and the target word can be determined as the target error correction candidate corresponding to the wrong content displayed on screen.

[0181] Method Example 3

[0182] Reference Figure 3 The diagram illustrates a flowchart of a third embodiment of the input error correction method of the present invention, which may specifically include the following steps:

[0183] Step 301: The client determines that the input stage is characterized as an operation that occurs after the screen is displayed but before the input is sent, and no cursor movement is detected.

[0184] Step 302: If the content displayed on the screen meets the conditions for obtaining the first proofreading result, the client sends the first request to the server.

[0185] Step 303: The server determines the first verification result of quality level 3 based on the first request;

[0186] Step 304: The client displays and caches the first proofreading result;

[0187] Step 305: The client determines that the input stage feature is an operation that occurs after the screen is displayed but before the input is sent, and that a cursor movement is detected.

[0188] Step 306: The client sends a second request to the server;

[0189] Step 307: The server determines the second verification results of quality level 1, quality level 2 and quality level 3 based on the second request;

[0190] Step 308: The client displays and caches the second proofreading result;

[0191] Step 309: The client determines that the input stage is characterized by sending the input and no further input being detected.

[0192] Step 310: The client queries the cache for the third verification result of quality level 3. If the cache query is successful, proceed to step 312.

[0193] Step 311: If the cache lookup fails, the client sends a third request to the server.

[0194] Step 312: The server determines the third verification result of quality level 3 based on the third request;

[0195] Step 313: The client displays the third proofreading result;

[0196] Step 314: The client determines that the input stage feature is that the input has been sent and the operation of continuing input has been detected;

[0197] Step 315: If the input string and the proofreading results in the cache meet the conditions for obtaining the third proofreading result, then obtain the fourth proofreading results of quality level 2 and quality level 3 from the cache.

[0198] Step 316: The client displays the fourth proofreading result.

[0199] In summary, the input error correction method of this invention, based on big data to construct a sentence association model, can provide users with sentence association candidates that are more relevant to their input content, thus bringing users a more convenient and intelligent input experience.

[0200] The embodiments of the present invention can provide sentence association candidates for the following scenarios: a. after a user completes the input of a language unit and inputs a preset punctuation mark; b. after a user sends input content in a communication scenario.

[0201] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of motion actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the motion actions involved are not necessarily required by the embodiments of the present invention.

[0202] Device Examples

[0203] Reference Figure 4 The diagram illustrates a structural block diagram of an embodiment of the input error correction device of the present invention, which may specifically include:

[0204] The stage determination module 401 is used to determine the input stage features;

[0205] The proofreading result determination module 402 is used to determine the proofreading result based on the proofreading rules corresponding to the input stage features mentioned above; the proofreading rules include: proofreading result acquisition conditions, and / or, the quality of the proofreading result;

[0206] The proofreading result display module 403 is used to display the above proofreading results.

[0207] Optionally, if the above-mentioned input stage features are operations performed after the input is displayed but before it is sent, and no cursor movement is detected, then the above-mentioned verification rules include: the first verification result acquisition conditions and the first verification result; and / or

[0208] If the above-mentioned input stage features are operations performed after the input is displayed on the screen but before it is sent, and cursor movement is detected, then the above-mentioned verification rules include: the second verification result; and / or

[0209] If the aforementioned input stage characteristic is that no further input is detected after the input has been sent, then the aforementioned verification rules include: the second verification result acquisition conditions and the third verification result; and / or

[0210] If the above input stage feature is that after sending, an operation to continue input is detected, then the above verification rules include: the third verification result acquisition condition and the fourth verification result;

[0211] Wherein, at least a portion of the second proofreading result is of lower quality than the third or fourth proofreading result; and at least a portion of the third or fourth proofreading result is of lower quality than the first proofreading result.

[0212] Optionally, if the above-mentioned input stage features are operations performed after the screen is displayed but before the data is sent, and no cursor movement is detected, then the above-mentioned verification result determination module includes:

[0213] The first proofreading result determination module is used to request the first proofreading result from the server if the conditions for obtaining the first proofreading result are met; the quality score of the first proofreading result exceeds the first threshold.

[0214] Optionally, the conditions for obtaining the first proofreading result include:

[0215] The number of characters in the displayed content is within a first preset character range; and

[0216] An input operation targeting a preset punctuation mark was detected, or an operation to display content from a preset source was detected.

[0217] Optionally, if the above-mentioned input stage feature is an operation that occurs after the screen is displayed but before the data is sent, and a cursor movement is detected, then the above-mentioned verification result determination module includes:

[0218] The second proofreading result determination module is used to request a second proofreading result from the server; the quality score of the second proofreading result exceeds the second threshold.

[0219] Optionally, if the above-mentioned input stage characteristic is that after sending the data, no further input is detected, then the above-mentioned verification result determination module includes:

[0220] The third proofreading result determination module is used to retrieve the third proofreading result from the cache; or

[0221] The fourth verification result determination module is used to request the third verification result from the server if the cache query fails and the conditions for obtaining the second verification result are met.

[0222] The quality score of the third proofreading result exceeds the first threshold.

[0223] Optionally, if the above-mentioned input stage feature is that after sending and a continued input operation is detected, then the above-mentioned verification result determination module includes:

[0224] The fifth proofreading result determination module is used to obtain the fourth proofreading result from the cache if the input string and the proofreading result in the cache meet the conditions for obtaining the third proofreading result.

[0225] The quality score of the fourth proofreading result exceeds the third threshold.

[0226] Optionally, the quality score of the first proofreading result exceeds the first threshold, the quality score of the second proofreading result exceeds the second threshold, the quality score of the third proofreading result exceeds the first threshold, and the quality score of the fourth proofreading result exceeds the third threshold.

[0227] The first threshold is greater than the third threshold, and the third threshold is greater than the second threshold.

[0228] Optionally, the above proofreading result display module includes:

[0229] The display module based on the display style is used to display the above-mentioned proofreading results according to the display style information corresponding to the above-mentioned input stage features; the above-mentioned display style information includes: display position, and / or, display content.

[0230] Optionally, the aforementioned input stage features are operations performed after the input is displayed but before it is sent, and where cursor movement is detected. The aforementioned display position includes: candidate position; or

[0231] The above-mentioned input stage features are not operations that occur after the screen is displayed but before the data is sent, and where cursor movement is detected. The above-mentioned display positions include: non-candidate positions.

[0232] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0233] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0234] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0235] This invention provides an apparatus for input error correction, including a memory and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more processors. The one or more programs include instructions for performing the following operations: determining input stage features; determining a correction result based on correction rules corresponding to the input stage features; the correction rules including: correction result acquisition conditions, and / or, the quality of the correction result; and displaying the correction result.

[0236] Figure 5 This is a block diagram illustrating an input error correction device 800 according to an exemplary embodiment. For example, device 800 may be a mobile phone, computer, digital broadcasting terminal, messaging device, game console, tablet device, medical device, fitness equipment, personal digital assistant, etc.

[0237] Reference Figure 5 The device 800 may include one or more of the following components: a processing component 802, a memory 804, a power supply component 806, a multimedia component 808, an audio component 810, an input / output (I / O) interface 812, a sensor component 814, and a communication component 816.

[0238] Processing component 802 typically controls the overall operation of device 800, such as operations associated with display, telephone calls, data communication, camera operation, and recording. Processing component 802 may include one or more processors 820 to execute instructions to perform all or part of the steps of the methods described above. Furthermore, processing component 802 may include one or more modules to facilitate interaction between processing component 802 and other components. For example, processing component 802 may include a multimedia module to facilitate interaction between multimedia component 808 and processing component 802.

[0239] Memory 804 is configured to store various types of data to support the operation of device 800. Examples of such data include instructions for any application or method operating on device 800, contact data, phonebook data, messages, pictures, videos, etc. Memory 804 can 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 storage, flash memory, magnetic disk, or optical disk.

[0240] Power supply component 806 provides power to various components of device 800. Power supply component 806 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power to device 800.

[0241] Multimedia component 808 includes a screen that provides an output interface between the device 800 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 touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of the touch or swipe action but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 808 includes a front-facing camera and / or a rear-facing camera. When the device 800 is in an operating mode, such as a shooting mode or a video mode, the front-facing camera and / or the rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0242] Audio component 810 is configured to output and / or input audio signals. For example, audio component 810 includes a microphone (MIC) configured to receive external audio signals when device 800 is in an operating mode, such as call mode, recording mode, and voice input mode. The received audio signals may be further stored in memory 804 or transmitted via communication component 816. In some embodiments, audio component 810 also includes a speaker for outputting audio signals.

[0243] I / O interface 812 provides an interface between processing component 802 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, power buttons, and lock buttons.

[0244] Sensor assembly 814 includes one or more sensors for providing status assessments of various aspects of device 800. For example, sensor assembly 814 may detect the on / off state of device 800, the relative positioning of components such as the display and keypad of device 800, changes in the position of device 800 or a component of device 800, the presence or absence of user contact with device 800, the orientation or acceleration / deceleration of device 800, and temperature changes of device 800. Sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 814 may also include an accelerometer, a gyroscope, a magnetometer, a pressure sensor, or a temperature sensor.

[0245] Communication component 816 is configured to facilitate wired or wireless communication between device 800 and other devices. Device 800 can access wireless networks based on communication standards, such as WiFi, 2G, or 3G, or combinations thereof. In one exemplary embodiment, communication component 816 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 816 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID), Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0246] In an exemplary embodiment, the apparatus 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the methods described above.

[0247] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 804 including instructions, which can be executed by a processor 820 of the device 800 to perform the above-described method. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0248] Figure 6This is a schematic diagram of the server structure in some embodiments of the present invention. The server 1900 can vary considerably depending on its configuration or performance, and may include one or more central processing units (CPUs) 1922 (e.g., one or more processors) and memory 1932, and one or more storage media 1930 (e.g., one or more mass storage devices) for storing application programs 1942 or data 1944. The memory 1932 and storage media 1930 can be temporary or persistent storage. The program stored in the storage media 1930 may include one or more modules (not shown in the diagram), each module including a series of instruction operations on the server. Furthermore, the CPU 1922 may be configured to communicate with the storage media 1930 and execute the series of instruction operations in the storage media 1930 on the server 1900.

[0249] Server 1900 may also include one or more power supplies 1926, one or more wired or wireless network interfaces 1950, one or more input / output interfaces 1958, one or more keyboards 1956, and / or one or more operating systems 1941, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.

[0250] A non-transitory computer-readable storage medium that, when instructions in the storage medium are executed by a processor of a device (server or terminal), enables the device to perform... Figure 2 or Figure 3 The input error correction method shown.

[0251] A non-transitory computer-readable storage medium, when instructions in the storage medium are executed by a processor of a device (server or terminal), enables the device to perform an input error correction method, the method comprising: determining input stage features; determining a correction result based on correction rules corresponding to the input stage features; the correction rules including: conditions for obtaining the correction result, and / or, the quality of the correction result; and displaying the correction result.

[0252] This invention discloses, A1, an input error correction method, the method comprising:

[0253] Determine the characteristics of the input stage;

[0254] The proofreading result is determined based on the proofreading rules corresponding to the input stage features; the proofreading rules include: proofreading result acquisition conditions, and / or, the quality of the proofreading result;

[0255] The proofreading results are then displayed.

[0256] A2. According to the method described in A1, the feature is that if the input stage characteristic is an operation performed after the screen is displayed but before the data is sent, and no cursor movement is detected, then the calibration rules include: a first calibration result acquisition condition and a first calibration result; and / or

[0257] If the input stage feature is an operation that occurs after the screen is displayed but before the data is sent, and a cursor movement is detected, then the calibration rules include: a second calibration result; and / or

[0258] If the input stage characteristic is that no further input is detected after sending, then the verification rules include: a second verification result acquisition condition and a third verification result; and / or

[0259] If the input stage feature is that after sending, an operation to continue input is detected, then the calibration rules include: a third calibration result acquisition condition and a fourth calibration result;

[0260] Wherein, at least a portion of the quality of the second proofreading result is lower than the quality of the third proofreading result or the fourth proofreading result; and at least a portion of the quality of the third proofreading result or the fourth proofreading result is lower than the quality of the first proofreading result.

[0261] A3. The method according to A1 or A2, characterized in that, if the input stage feature is an operation performed after screen display but before transmission, and no cursor movement is detected, then determining the verification result includes:

[0262] If the conditions for obtaining the first proofreading result are met, then the first proofreading result is requested from the server; the quality score of the first proofreading result exceeds the first threshold.

[0263] A4. The method according to A3, characterized in that the conditions for obtaining the first proofreading result include:

[0264] The number of characters in the displayed content is within a first preset character range; and

[0265] An input operation targeting a preset punctuation mark was detected, or an operation to display content from a preset source was detected.

[0266] A5. The method according to A1 or A2, characterized in that, if the input stage feature is an operation that occurs after the screen is displayed but before the data is sent, and a moving cursor is detected, then determining the verification result includes:

[0267] The server requests a second proofreading result; the quality score of the second proofreading result exceeds the second threshold.

[0268] A6. The method according to A1 or A2, characterized in that, if the input stage feature is that after sending and no further input is detected, then determining the verification result includes:

[0269] Retrieve the third-party proofreading result from the cache; or

[0270] If the cache query fails, then if the conditions for obtaining the second verification result are met, the third verification result will be requested from the server.

[0271] The quality score of the third proofreading result exceeds the first threshold.

[0272] A7. The method according to A1 or A2, characterized in that, if the input stage feature is an operation of sending and detecting continued input, then determining the verification result includes:

[0273] If the input string and the verification result in the cache meet the conditions for obtaining the third verification result, then obtain the fourth verification result from the cache.

[0274] The quality score of the fourth proofreading result exceeds the third threshold.

[0275] A8. The method according to A2, characterized in that the quality score of the first proofreading result exceeds a first threshold, the quality score of the second proofreading result exceeds a second threshold, the quality score of the third proofreading result exceeds the first threshold, and the quality score of the fourth proofreading result exceeds a third threshold;

[0276] The first threshold is greater than the third threshold, and the third threshold is greater than the second threshold.

[0277] A9. The method according to A1 or A2, characterized in that, displaying the proofreading result includes:

[0278] The proofreading results are displayed based on the display style information corresponding to the input stage features; the display style information includes: display position, and / or, display content.

[0279] A10. The method according to A9, characterized in that the input stage feature is an operation that occurs after the screen is displayed but before the data is sent, and a moving cursor is detected; the display position includes: a candidate position; or

[0280] The input stage features are not operations that occur after the screen is displayed but before the cursor is sent, and the display position includes: non-candidate positions.

[0281] This invention discloses B11, an input error correction device, characterized in that it includes:

[0282] The stage determination module is used to determine the characteristics of the input stage;

[0283] The proofreading result determination module is used to determine the proofreading result based on the proofreading rules corresponding to the input stage features; the proofreading rules include: proofreading result acquisition conditions, and / or, the quality of the proofreading result;

[0284] The proofreading result display module is used to display the proofreading results.

[0285] B12. The apparatus according to B11, characterized in that, if the input stage feature is an operation performed after screen display but before transmission, and no cursor movement is detected, then the calibration rules include: a first calibration result acquisition condition and a first calibration result; and / or

[0286] If the input stage feature is an operation that occurs after the screen is displayed but before the data is sent, and a cursor movement is detected, then the calibration rules include: a second calibration result; and / or

[0287] If the input stage characteristic is that no further input is detected after sending, then the verification rules include: a second verification result acquisition condition and a third verification result; and / or

[0288] If the input stage feature is that after sending, an operation to continue input is detected, then the calibration rules include: a third calibration result acquisition condition and a fourth calibration result;

[0289] Wherein, at least a portion of the quality of the second proofreading result is lower than the quality of the third proofreading result or the fourth proofreading result; and at least a portion of the quality of the third proofreading result or the fourth proofreading result is lower than the quality of the first proofreading result.

[0290] B13. The apparatus according to B11 or B12, characterized in that, if the input stage feature is an operation performed after screen display but before transmission, and no cursor movement is detected, then the calibration result determination module includes:

[0291] The first proofreading result determination module is used to request the first proofreading result from the server if the conditions for obtaining the first proofreading result are met; the quality score of the first proofreading result exceeds the first threshold.

[0292] B14. The apparatus according to B13, characterized in that the conditions for obtaining the first calibration result include:

[0293] The number of characters in the displayed content is within a first preset character range; and

[0294] An input operation targeting a preset punctuation mark was detected, or an operation to display content from a preset source was detected.

[0295] B15. The apparatus according to B11 or B12, characterized in that, if the input stage feature is an operation performed after screen display but before transmission, and a moving cursor is detected, then the calibration result determination module includes:

[0296] The second proofreading result determination module is used to request a second proofreading result from the server; the quality score of the second proofreading result exceeds a second threshold.

[0297] B16. The apparatus according to B11 or B12, characterized in that, if the input stage feature is that after transmission and no further input is detected, the calibration result determination module includes:

[0298] The third proofreading result determination module is used to retrieve the third proofreading result from the cache; or

[0299] The fourth verification result determination module is used to request the third verification result from the server if the cache query fails and the conditions for obtaining the second verification result are met.

[0300] The quality score of the third proofreading result exceeds the first threshold.

[0301] B17. The apparatus according to B11 or B12, characterized in that, if the input stage feature is an operation of sending and detecting continued input, then the calibration result determination module includes:

[0302] The fifth proofreading result determination module is used to obtain the fourth proofreading result from the cache if the input string and the proofreading result in the cache meet the conditions for obtaining the third proofreading result.

[0303] The quality score of the fourth proofreading result exceeds the third threshold.

[0304] B18. The apparatus according to B12, characterized in that the quality score of the first calibration result exceeds a first threshold, the quality score of the second calibration result exceeds a second threshold, the quality score of the third calibration result exceeds the first threshold, and the quality score of the fourth calibration result exceeds a third threshold.

[0305] The first threshold is greater than the third threshold, and the third threshold is greater than the second threshold.

[0306] B19. The apparatus according to B11 or B12, characterized in that the proofreading result display module includes:

[0307] The display module based on display style is used to display the proofreading results according to the display style information corresponding to the input stage features; the display style information includes: display position, and / or, display content.

[0308] B20. The apparatus according to B19, characterized in that the input stage is an operation performed after screen display but before data transmission, and upon detection of a moving cursor; the display position includes: a candidate position; or

[0309] The input stage features are not operations that occur after the screen is displayed but before the cursor is sent, and the display position includes: non-candidate positions.

[0310] This invention discloses C21, an apparatus for input error correction, characterized in that it includes a memory and one or more programs, wherein one or more programs are stored in the memory and configured to be executed by one or more processors, and the one or more programs contain instructions for performing the following operations:

[0311] Determine the characteristics of the input stage;

[0312] The proofreading result is determined based on the proofreading rules corresponding to the input stage features; the proofreading rules include: proofreading result acquisition conditions, and / or, the quality of the proofreading result;

[0313] The proofreading results are then displayed.

[0314] C22. The apparatus according to C21, characterized in that, if the input stage feature is an operation performed after screen display but before transmission, and no cursor movement is detected, then the calibration rules include: a first calibration result acquisition condition and a first calibration result; and / or

[0315] If the input stage feature is an operation that occurs after the screen is displayed but before the data is sent, and a cursor movement is detected, then the calibration rules include: a second calibration result; and / or

[0316] If the input stage characteristic is that no further input is detected after sending, then the verification rules include: a second verification result acquisition condition and a third verification result; and / or

[0317] If the input stage feature is that after sending, an operation to continue input is detected, then the calibration rules include: a third calibration result acquisition condition and a fourth calibration result;

[0318] Wherein, at least a portion of the quality of the second proofreading result is lower than the quality of the third proofreading result or the fourth proofreading result; and at least a portion of the quality of the third proofreading result or the fourth proofreading result is lower than the quality of the first proofreading result.

[0319] C23. The apparatus according to C21 or C22, characterized in that, if the input stage feature is an operation performed after the screen is displayed but before the data is sent, and no cursor movement is detected, then determining the verification result includes:

[0320] If the conditions for obtaining the first proofreading result are met, then the first proofreading result is requested from the server; the quality score of the first proofreading result exceeds the first threshold.

[0321] C24. The apparatus according to C23, characterized in that the conditions for obtaining the first calibration result include:

[0322] The number of characters in the displayed content is within a first preset character range; and

[0323] An input operation targeting a preset punctuation mark was detected, or an operation to display content from a preset source was detected.

[0324] C25. The apparatus according to C21 or C22, characterized in that, if the input stage feature is an operation performed after screen display but before transmission, and a moving cursor is detected, then determining the verification result includes:

[0325] The server requests a second proofreading result; the quality score of the second proofreading result exceeds the second threshold.

[0326] C26. The apparatus according to C21 or C22, characterized in that, if the input stage feature is that after transmission and no further input is detected, the determination of the verification result includes:

[0327] Retrieve the third-party proofreading result from the cache; or

[0328] If the cache query fails, then if the conditions for obtaining the second verification result are met, the third verification result will be requested from the server.

[0329] The quality score of the third proofreading result exceeds the first threshold.

[0330] C27. The apparatus according to C21 or C22, characterized in that, if the input stage feature is an operation of sending and detecting continued input, then determining the verification result includes:

[0331] If the input string and the verification result in the cache meet the conditions for obtaining the third verification result, then obtain the fourth verification result from the cache.

[0332] The quality score of the fourth proofreading result exceeds the third threshold.

[0333] C28. The apparatus according to C22, characterized in that the quality score of the first calibration result exceeds a first threshold, the quality score of the second calibration result exceeds a second threshold, the quality score of the third calibration result exceeds the first threshold, and the quality score of the fourth calibration result exceeds a third threshold;

[0334] The first threshold is greater than the third threshold, and the third threshold is greater than the second threshold.

[0335] 29. The apparatus according to C21 or C22, characterized in that displaying the calibration result includes:

[0336] The proofreading results are displayed based on the display style information corresponding to the input stage features; the display style information includes: display position, and / or, display content.

[0337] C30. The apparatus according to C29, characterized in that the input stage is an operation performed after the screen is displayed but before the data is sent, and a moving cursor is detected; the display position includes: a candidate position; or

[0338] The input stage features are not operations that occur after the screen is displayed but before the cursor is sent, and the display position includes: non-candidate positions.

[0339] D31. A machine-readable medium having instructions stored thereon that, when executed by one or more processors, cause a device to perform one or more of the input error correction methods described in A1 to A10.

[0340] Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of the invention are indicated by the following claims.

[0341] It should be understood that the present invention is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

[0342] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

[0343] The above provides a detailed description of an input error correction method, an input error correction device, and an input error correction apparatus provided by the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. An input error correction method, characterized in that, The method includes: Determine the input stage characteristics; the input stage characteristics are used to reflect the user's error tolerance and proofreading willingness, and the input stage characteristics include any of the following stage characteristics: operation before sending after being displayed on the screen and no cursor movement is detected; or operation before sending after being displayed on the screen and cursor movement is detected; or operation after sending and no further input is detected; or operation after sending and further input is detected. Based on the error tolerance and proofreading willingness reflected by the characteristics of the input stage, the corresponding proofreading rules are determined; The proofreading result is determined based on the proofreading rules corresponding to the input stage features; the proofreading rules include: proofreading result acquisition conditions, and / or, proofreading result quality, wherein different input stage features correspond to proofreading rules with different proofreading result acquisition conditions and / or different proofreading result quality; The proofreading results are then displayed. Wherein, if the input stage feature is an operation performed after the screen is displayed but before the data is sent, and no cursor movement is detected, then the calibration rules include: a first calibration result acquisition condition and a first calibration result; and / or If the input stage feature is an operation that occurs after the screen is displayed but before the data is sent, and a cursor movement is detected, then the calibration rules include: a second calibration result; and / or If the input stage characteristic is that no further input is detected after sending, then the verification rules include: a second verification result acquisition condition and a third verification result; and / or If the input stage feature is that after sending, an operation to continue input is detected, then the calibration rules include: a third calibration result acquisition condition and a fourth calibration result; Wherein, at least a portion of the quality of the second proofreading result is lower than the quality of the third proofreading result or the fourth proofreading result; and at least a portion of the quality of the third proofreading result or the fourth proofreading result is lower than the quality of the first proofreading result.

2. The method according to claim 1, characterized in that, If the input stage feature is an operation performed after the screen is displayed but before the data is sent, and no cursor movement is detected, then determining the verification result includes: If the conditions for obtaining the first proofreading result are met, then the first proofreading result is requested from the server; the quality score of the first proofreading result exceeds the first threshold.

3. The method according to claim 2, characterized in that, The conditions for obtaining the first proofreading result include: The number of characters in the displayed content is within a first preset character range; and An input operation targeting a preset punctuation mark was detected, or an operation to display content from a preset source was detected.

4. The method according to claim 1, characterized in that, If the input stage feature is an operation that occurs after the screen is displayed but before the data is sent, and a cursor movement is detected, then determining the verification result includes: The server requests a second proofreading result; the quality score of the second proofreading result exceeds the second threshold.

5. The method according to claim 1, characterized in that, If the input stage characteristic is that after sending, no further input is detected, then determining the verification result includes: Retrieve the third-party proofreading result from the cache; or If the cache query fails, then if the conditions for obtaining the second verification result are met, the third verification result will be requested from the server. The quality score of the third proofreading result exceeds the first threshold.

6. The method according to claim 1, characterized in that, If the input stage feature is that after sending and a continued input operation is detected, then determining the verification result includes: If the input string and the verification result in the cache meet the conditions for obtaining the third verification result, then obtain the fourth verification result from the cache. The quality score of the fourth proofreading result exceeds the third threshold.

7. The method according to claim 1, characterized in that, The quality score of the first proofreading result exceeds the first threshold, the quality score of the second proofreading result exceeds the second threshold, the quality score of the third proofreading result exceeds the first threshold, and the quality score of the fourth proofreading result exceeds the third threshold; The first threshold is greater than the third threshold, and the third threshold is greater than the second threshold.

8. The method according to claim 1, characterized in that, The presentation of the proofreading results includes: The proofreading results are displayed based on the display style information corresponding to the input stage features; the display style information includes: display position, and / or, display content.

9. The method according to claim 8, characterized in that, The input stage is characterized by an operation that occurs after the input is displayed but before it is sent, and a moving cursor is detected. The display position includes: a candidate position; or The input stage features are not operations that occur after the screen is displayed but before the cursor is sent, and the display position includes: non-candidate positions.

10. An input error correction device, characterized in that, include: A stage determination module is used to determine input stage characteristics; the input stage characteristics are used to reflect the user's error tolerance and proofreading willingness, and the input stage characteristics include any of the following stage characteristics: operation before sending after being displayed on the screen and no cursor movement is detected; or operation before sending after being displayed on the screen and cursor movement is detected; or operation after sending and no further input is detected; or operation after sending and further input is detected. The proofreading result determination module is used to determine the corresponding proofreading rules based on the error tolerance and proofreading willingness reflected by the input stage features; and to determine the proofreading result based on the proofreading rules corresponding to the input stage features. The proofreading rules include: proofreading result acquisition conditions, and / or, proofreading result quality, wherein different input stage features correspond to proofreading rules with different proofreading result acquisition conditions and / or different proofreading result quality; The proofreading result display module is used to display the proofreading results; Wherein, if the input stage feature is an operation performed after the screen is displayed but before the data is sent, and no cursor movement is detected, then the calibration rules include: a first calibration result acquisition condition and a first calibration result; and / or If the input stage feature is an operation that occurs after the screen is displayed but before the data is sent, and a cursor movement is detected, then the calibration rules include: a second calibration result; and / or If the input stage characteristic is that no further input is detected after sending, then the verification rules include: a second verification result acquisition condition and a third verification result; and / or If the input stage feature is that after sending, an operation to continue input is detected, then the calibration rules include: a third calibration result acquisition condition and a fourth calibration result; Wherein, at least a portion of the quality of the second proofreading result is lower than the quality of the third proofreading result or the fourth proofreading result; and at least a portion of the quality of the third proofreading result or the fourth proofreading result is lower than the quality of the first proofreading result.

11. The apparatus according to claim 10, characterized in that, If the input stage feature is an operation performed after the screen is displayed but before the data is sent, and no cursor movement is detected, then the calibration result determination module includes: The first proofreading result determination module is used to request the first proofreading result from the server if the conditions for obtaining the first proofreading result are met; the quality score of the first proofreading result exceeds the first threshold.

12. The apparatus according to claim 11, characterized in that, The conditions for obtaining the first proofreading result include: The number of characters in the displayed content is within a first preset character range; and An input operation targeting a preset punctuation mark was detected, or an operation to display content from a preset source was detected.

13. The apparatus according to claim 10, characterized in that, If the input stage feature is an operation that occurs after the screen is displayed but before the data is sent, and a cursor movement is detected, then the calibration result determination module includes: The second proofreading result determination module is used to request a second proofreading result from the server; the quality score of the second proofreading result exceeds a second threshold.

14. The apparatus according to claim 10, characterized in that, If the input stage characteristic is that after sending, no further input is detected, then the verification result determination module includes: The third proofreading result determination module is used to retrieve the third proofreading result from the cache; or The fourth verification result determination module is used to request the third verification result from the server if the cache query fails and the conditions for obtaining the second verification result are met. The quality score of the third proofreading result exceeds the first threshold.

15. The apparatus according to claim 10, characterized in that, If the input stage feature is that after sending and a continued input operation is detected, then the verification result determination module includes: The fifth proofreading result determination module is used to obtain the fourth proofreading result from the cache if the input string and the proofreading result in the cache meet the conditions for obtaining the third proofreading result. The quality score of the fourth proofreading result exceeds the third threshold.

16. The apparatus according to claim 10, characterized in that, The quality score of the first proofreading result exceeds the first threshold, the quality score of the second proofreading result exceeds the second threshold, the quality score of the third proofreading result exceeds the first threshold, and the quality score of the fourth proofreading result exceeds the third threshold; The first threshold is greater than the third threshold, and the third threshold is greater than the second threshold.

17. The apparatus according to claim 10, characterized in that, The proofreading result display module includes: The display module based on display style is used to display the proofreading results according to the display style information corresponding to the input stage features; the display style information includes: display position, and / or, display content.

18. The apparatus according to claim 17, characterized in that, The input stage is characterized by an operation that occurs after the input is displayed but before it is sent, and a moving cursor is detected. The display position includes: a candidate position; or The input stage features are not operations that occur after the screen is displayed but before the cursor is sent, and the display position includes: non-candidate positions.

19. An apparatus for input error correction, characterized in that, It includes a memory and one or more programs, wherein one or more programs are stored in the memory, and when the programs are executed by one or more processors, they implement the steps of the method according to any one of claims 1 to 9.

20. A machine-readable medium having instructions stored thereon that, when executed by one or more processors, cause a device to perform the input error correction method as described in any one of claims 1 to 9.

Images