CN114489439A

CN114489439A - Article correcting method and related equipment thereof

Info

Publication number: CN114489439A
Application number: CN202210067368.4A
Authority: CN
Inventors: 储德宝; 王帆; 王晓斐
Original assignee: Anhui Toycloud Technology Co Ltd
Current assignee: Anhui Toycloud Technology Co Ltd
Priority date: 2022-01-20
Filing date: 2022-01-20
Publication date: 2022-05-13

Abstract

The application discloses an article correction method and related equipment thereof, wherein the method comprises the following steps: after an article to be corrected input by a user is obtained, firstly, article correcting processing is carried out on the article to be corrected to obtain correcting data to be displayed, so that the correcting data to be displayed can show correcting results aiming at the article to be corrected, and the correcting data to be displayed can show the article writing level of the user; and displaying the correction data to be displayed to a user so that the user can know the writing level of the article based on the correction data to be displayed, so that the user can subsequently improve learning based on the correction data to be displayed, and thus the purpose of automatically correcting the article can be realized, the defects in the manual correction process can be effectively overcome, the article correction effect can be improved, and the language learning experience of students can be improved.

Description

Article correcting method and related equipment thereof

Technical Field

The present application relates to the field of data processing technologies, and in particular, to an article modification method and related devices.

Background

For a language learning class (e.g., english, etc.), the language learning class may generally involve multiple aspects of learning content such as "listen", "speak", "read", "write", and so on. Among them, the written article belongs to the learning content of the aspect of "writing" described above.

At present, after a student writes an article (e.g., an english composition, etc.), a teacher in a language teaching usually performs manual correction on the article to obtain a manual correction result of the article, so that the student can perform improved learning based on the manual correction result to improve the writing level of the student's article.

However, the manual correction process has defects, so that the article correction effect is poor.

Disclosure of Invention

The embodiment of the application mainly aims to provide an article correction method and related equipment thereof, which can improve the article correction effect and are beneficial to improving the language learning experience of students.

The embodiment of the application provides an article correction method, which comprises the following steps: acquiring an article to be corrected input by a user; carrying out article correction processing on the article to be corrected to obtain correction data to be displayed; and displaying the correction data to be displayed to the user.

An embodiment of the present application further provides an article correction device, including: the article acquisition unit is used for acquiring an article to be corrected input by a user; the article correcting unit is used for carrying out article correcting processing on the article to be corrected to obtain correcting data to be displayed; and the correction display unit is used for displaying the correction data to be displayed to the user.

An embodiment of the present application further provides an apparatus, including: a processor, a memory, a system bus; the processor and the memory are connected through the system bus; the memory is used for storing one or more programs, and the one or more programs comprise instructions which, when executed by the processor, cause the processor to execute any implementation of the article correction method provided by the embodiment of the application.

The embodiment of the present application further provides a computer-readable storage medium, where instructions are stored in the computer-readable storage medium, and when the instructions are run on a terminal device, the terminal device is enabled to execute any implementation of the article approval method provided in the embodiment of the present application.

The embodiment of the present application further provides a computer program product, and when the computer program product runs on a terminal device, the terminal device is enabled to execute any implementation manner of the article correction method provided in the embodiment of the present application.

Based on the technical scheme, the method has the following beneficial effects:

according to the technical scheme, after the article to be corrected input by the user is obtained, the article to be corrected is corrected to obtain correction data to be displayed, so that the correction data to be displayed can show the correction result of the article to be corrected, and the correction data to be displayed can show the article writing level of the user; and displaying the correction data to be displayed to a user so that the user can know the writing level of the article based on the correction data to be displayed, so that the user can subsequently improve learning based on the correction data to be displayed, and thus the purpose of automatically correcting the article can be realized, the defects in the manual correction process can be effectively overcome, the article correction effect can be improved, and the language learning experience of students can be improved.

In addition, the to-be-displayed correction data not only comprise correction text display data displayed by means of characters, but also comprise correction virtual comment data displayed by means of teacher comment simulation, so that the user can experience the teacher comment process of the to-be-corrected article through the display process of the correction virtual comment data, the learning effect of the user is further improved, and language learning experience of students is improved.

In addition, the to-be-displayed correcting data not only comprises an error analysis result aiming at the to-be-corrected article, but also comprises a highlight analysis result aiming at the to-be-corrected article, so that the user can know the advantages and disadvantages of the writing of the article from the to-be-displayed correcting data, the learning effect of the user is favorably improved, and the language learning experience of students is favorably improved.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a flowchart of an article correction method provided in an embodiment of the present application;

fig. 2 is a schematic diagram of an article correction result display page provided in an embodiment of the present application;

fig. 3 is a schematic diagram of another article correction result display page provided in the embodiment of the present application;

fig. 4 is a schematic diagram of an abnormal character use reminding page according to an embodiment of the present application;

fig. 5 is a schematic diagram of another abnormal character use reminding page provided in the embodiment of the present application;

FIG. 6 is a diagram illustrating a spelling error displayed page according to an embodiment of the present application;

fig. 7 is a schematic structural diagram of an article correction device according to an embodiment of the present application.

Detailed Description

The inventor finds that the work load of the language teaching teacher is greatly increased due to the long time consumption of the manual correction process in the research aiming at the manual correction process, so that the language teaching teacher is easy to make errors in the manual correction process, and the manual correction result is easy to be inaccurate; moreover, because the energy of the language teacher is limited, the language teacher cannot strictly control the details of each article, so that the language teacher usually gives a scoring value for the whole article, and thus the manual correction result given by the language teacher is too simple, and the learning effect of the student based on the manual correction result is poor.

Based on the above findings, in order to solve the technical problems shown in the background section, an embodiment of the present application provides an article modification method, including: after an article to be corrected input by a user is obtained, firstly, article correcting processing is carried out on the article to be corrected to obtain correcting data to be displayed, so that the correcting data to be displayed can show correcting results aiming at the article to be corrected, and the correcting data to be displayed can show the article writing level of the user; and displaying the correction data to be displayed to a user so that the user can know the writing level of the article based on the correction data to be displayed, so that the user can subsequently improve learning based on the correction data to be displayed, and thus the purpose of automatically correcting the article can be realized, the defects in the manual correction process can be effectively overcome, the article correction effect can be improved, and the language learning experience of students can be improved.

In addition, the embodiment of the present application does not limit the execution subject of the article correction method provided in the embodiment of the present application, and for example, the article correction method provided in the embodiment of the present application may be applied to a display device or a server. For another example, the article correction method provided in the embodiment of the present application may also be implemented by means of a data interaction process between the display device and the server. The display equipment refers to terminal equipment with an information display function; the display device is not limited to the embodiment of the present application, and for example, the display device may be a smart phone, a computer, a Personal Digital Assistant (PDA), a tablet computer, a wand with a display screen, or a learning assistance device (e.g., a dictionary pen) with a display screen. The server may be a stand-alone server, a cluster server, or a cloud server.

In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

Method embodiment one

Referring to fig. 1, the figure is a flowchart of an article modification method provided in an embodiment of the present application.

The article correction method provided by the embodiment of the application comprises the following steps of S1-S3:

s1: and acquiring the article to be corrected input by the user.

The user is used for representing a trigger of an article correction request; the "user" is not limited to this embodiment, and may be a user of a dictionary pen having an article batch correction function, for example.

The article correction request is used for requesting correction processing on the article to be corrected; the embodiment of the present application does not limit the triggering manner of the "article approval request", and for example, it may be implemented by any request triggering manner (for example, clicking a button, etc.) that is present or appears in the future.

The article to be corrected is an article which needs to be corrected; furthermore, the "article to be amended" is not limited in the embodiments of the present application, and for example, it may refer to a composition in a certain language (e.g., english, chinese, etc.).

In addition, the data type of the above "article to be corrected" is not limited in the embodiment of the present application, and for example, it may belong to text data.

In addition, the embodiment of the present application does not limit the acquiring process of the article to be checked and modified, for example, the acquiring process may specifically include the following two steps:

the method comprises the following steps: and receiving article acquisition data sent by the article acquisition equipment.

The article acquisition equipment is used for carrying out character acquisition processing on an article; and the article collecting equipment and the execution main body of the article correcting method provided by the embodiment of the application can be in data communication.

In addition, the embodiment of the present application is not limited to the above-mentioned "article collecting device", and for example, it may specifically be a scanning device (for example, a dictionary pen, a scanning pen, and other electronic devices with a scanning function, etc.). As another example, the "article capture device" can also be an image capture device (e.g., a camera, a webcam, an Artificial Intelligence (AI) webcam, a camcorder, etc.). Also for example, an "article capture device" may also be a character input device (e.g., keyboard, mouse, stylus, etc.).

The article acquisition data refers to a character acquisition result for one article; the "article acquisition data" is not limited to this "article acquisition data", and may be image data (for example, a scanned image obtained by scanning an article or a photographed image obtained by photographing an article) when the above-described "article acquisition device" is a scanning device.

Step two: and determining the article to be corrected according to the article acquisition data.

It should be noted that the embodiment of the present application is not limited to the implementation of the second step, for example, when the "article collected data" is image data and the "article to be corrected" belongs to text data, the second step may specifically be: and carrying out image recognition processing on the article collected data to obtain an article to be corrected, so that the article to be corrected is used for recording character information carried in the article collected data.

Based on the above-mentioned related content of S1, when a user (e.g., a learner in a certain language) wants to perform an automatic correction process on an article written by the user, the user can input the article to be corrected by means of the article collecting device, so that the automatic correction process can be performed on the article to be corrected later.

S2: and carrying out article correction processing on the article to be corrected to obtain correction data to be displayed.

The "to-be-presented correction data" is used to indicate a correction result for the to-be-presented correction article, so that the "to-be-presented correction data" can indicate the writing level of the to-be-corrected article (for example, can indicate advantages and disadvantages existing in the to-be-presented correction article).

In addition, the embodiment of the present application does not limit the "approval data to be displayed" described above, and for example, the "approval data to be displayed" may include at least one of approval text display data and approval virtual comment data.

The "correction text presentation data" refers to text data indicating a correction result for the article to be corrected, so that the "correction text presentation data" can present the correction result for the article to be corrected in a text form (e.g., the text presentation form shown in fig. 2).

The "modifying virtual comment data" refers to multimedia data that is spoken by a virtual teacher with respect to a modifying result of an article to be modified, so that the modifying virtual comment data can show the modifying result of the article to be modified in a manner that the virtual teacher modifies the comment data (e.g., the virtual teacher modifying manner shown in fig. 3).

In addition, the embodiment of the present application is not limited to the above-mentioned "correction virtual comment data", and for example, it may include a mimic character and correction description audio data so that the "correction virtual comment data" can play the correction description audio data by means of the mimic character, thus implementing the virtual teacher's comment process.

The above-mentioned "anthropomorphic character image" is used to represent a virtual teacher; and the mimicry character image can realize the comment process of the virtual teacher aiming at the article to be corrected by broadcasting the correction description audio data. It should be noted that the embodiment of the present application is not limited to the "anthropomorphic character," and for example, the anthropomorphic character may be a preset virtual character (such as the virtual character shown in fig. 3), a preset virtual cartoon character, or the like.

The "correction description audio data" refers to audio data for indicating a correction result for an article to be corrected; and there is an intersection between the semantic information carried by the "correction description audio data" and the semantic information carried by the "correction text presentation data" above (for example, the semantic information carried by the "correction description audio data" may include the semantic information carried by the "correction text presentation data" and the like).

It should be noted that the "intersection" is not limited in the embodiment of the present application, and for example, the "intersection" may include all the modifying contents for the article to be modified (for example, the "scoring result to be shown", the "error resolution result of the article to be modified", the "bright point resolution result of the article to be modified", and the "abnormal character recognition result" below).

In addition, the present examples do not limit the implementation of S2, and for example, the following may be adoptedMethod example fourAny of the embodiments of S2 shown are performed.

S3: and displaying the correction data to be displayed to the user.

The present application example does not limit the implementation manner of S3, and for example, it may specifically be: and directly displaying the correction data to be displayed to the user. As another example, it may employ the followingMethod example fiveAny of the illustrated embodiments of the process of displaying the wholesale data to be displayed is implemented.

Based on the relevant contents of S1 to S3, for the article correction method provided in the embodiment of the present application, after the article to be corrected input by the user is obtained, the article correction processing is performed on the article to be corrected first to obtain the correction data to be displayed, so that the correction data to be displayed can show the correction result for the article to be corrected, and thus the correction data to be displayed can show the article writing level of the user; and displaying the correction data to be displayed to the user so that the user can know the writing level of the article based on the correction data to be displayed, so that the user can subsequently improve and learn based on the correction data to be displayed, and the purpose of automatically correcting the article can be realized, thereby effectively overcoming the defects in the manual correction process, improving the correction effect of the article and being beneficial to improving the language learning experience of students.

Method embodiment two

The inventors discovered in studies of articles written by students that some students may have some bad writing habits (e.g., chinese characters used in writing english compositions, continuous punctuation marks in articles, etc.).

Based on the above findings, in order to further improve the article correction effect, in this embodiment, another possible implementation manner of the article correction method is further provided, and in this implementation manner, the article correction method may further include not only the foregoing S1 to S3, but also S4 to S8:

s4: and carrying out abnormal character recognition processing on the article to be corrected to obtain an abnormal recognition result.

The abnormal character recognition processing is used for recognizing abnormal characters in the article to be corrected.

The abnormal character refers to a character which should not appear in the article to be corrected; the embodiment of the present application does not limit the "abnormal character". For example, when the "article to be falsified" refers to a composition (e.g., english composition) in the target language, the "abnormal character" may include: characters in any language other than the target language (e.g., chinese characters), and at least one of a pure symbol character string. Where a "pure symbol string" is used to represent a plurality of symbols occurring in succession (e.g., a plurality of punctuation symbols occurring in succession similar to a "zero" ", etc.).

The embodiment of the present invention is not limited to the method for recognizing the "abnormal character", and for example, the abnormal character may be recognized by utf (unicode Transformation format) coding.

The embodiment of the present application is not limited to the above-described embodiment of the "abnormal character recognition processing", and may be implemented, for example, by a machine learning model having an abnormal character recognition function that is constructed in advance.

The "abnormal recognition result" is used to indicate whether abnormal characters exist in the article to be corrected.

S5: judging whether the abnormal recognition result meets a preset abnormal condition, if so, executing S6; if not, then S2 above is performed (or S10 below is performed).

The "preset abnormal condition" may be preset, and for example, it may specifically be: and the abnormal recognition result indicates that abnormal characters exist in the article to be corrected.

As can be seen, after the abnormal recognition result is obtained, if the abnormal recognition result indicates that there are no abnormal characters in the article to be corrected, it may be determined that the abnormal recognition result does not satisfy the preset abnormal condition, so that it may be determined that there is no preset bad article writing habit (for example, mixed writing of chinese and english, etc.) for the user, and therefore, the subsequent processing procedure (for example, performing S2-S3, or performing S10 and subsequent steps) for the article to be corrected may be continuously performed; however, if the abnormal recognition result indicates that abnormal characters exist in the article to be corrected, it may be determined that the abnormal recognition result satisfies a preset abnormal condition, so that it may be determined that the user has a bad article writing habit, and thus the user may be presented with the following "first presentation data", so that the user may know the bad article writing habit from the "first presentation data", which is beneficial to improving the learning effect of the user.

S6: first presentation data is generated.

The first display data is used for describing bad writing habits of the user presented by the article to be corrected; the embodiment of the present application does not limit the generation process of the "first presentation data", and for the convenience of understanding, the following description will be made with reference to two examples.

Example 1, S6 may specifically be: and determining the first prompt information as first display data.

The first prompt message is used for reminding a user that abnormal characters exist in the article to be corrected; the first prompt message is not limited in the embodiment of the present application, and for example, when the article to be modified is an english composition, the first prompt message may be a prompt message shown in fig. 4. For another example, when the article to be corrected is an english composition, the "first prompt message" may specifically be a warning message that "the article to be corrected has other abnormal characters (for example, chinese characters, pure symbol character strings, etc.) except for english characters, please check the article to be corrected, and re-input the modified article".

The "first presentation information" may be set in advance.

Based on the related content of the above "example 1", if the abnormal recognition result indicates that abnormal characters exist in the article to be modified, the preset first prompt information may be directly determined as the first display data, so that the user can know that the abnormal characters exist in the article to be modified based on the first display data, and thus after the user modifies the original of the article to be modified, the user performs the article input operation again on the modified original.

It should be noted that the "original document of the article to be falsified" refers to a text collection object of the "article collection device" above; furthermore, the embodiment of the present application does not limit the "original of the article to be approved", and for example, the original may be a paper document (e.g., a paper book, a paper test paper, etc.).

Example 2, to prompt the user to quickly know that those characters in the article to be endorsed are recognized as abnormal characters, S6 may specifically include S61-S62:

s61: and according to the abnormal recognition result, performing abnormal character labeling processing on the article to be corrected to obtain an abnormal labeled article.

The abnormal character marking processing is used for marking the abnormal characters in the article to be corrected according to a first character marking mode. It should be noted that the "first character labeling manner" may be preset, and for example, may specifically include: the character color is updated to red. For another example, the "first character labeling method" may be implemented by using the abnormal character labeling method shown in fig. 5.

Based on the related content of S61, after the abnormal recognition result is obtained, the abnormal character labeling processing may be performed on the article to be corrected by referring to the position of each abnormal character recorded in the abnormal recognition result in the article to be corrected, so as to obtain an abnormal labeled article, so that each abnormal character in the "abnormal labeled article" is labeled according to the first character labeling manner, and thus each abnormal character in the "abnormal labeled article" can be highlighted for the user, and the user can quickly know the abnormal character in the article to be corrected from the "abnormal labeled article".

S62: and determining first display data according to the abnormal labeled article.

It should be noted that the examples of the present application do not limit the implementation manner of S62, and for example, the examples may specifically include: the abnormal labeled article is directly determined as the first display data (the display content shown in fig. 5). For another example, S62 may specifically be: firstly, according to the first prompt message and the abnormal labeled article, at least one third display page (for example, two display pages shown in fig. 4 and 5) is constructed, so that the "at least one third display page" is used for displaying the first prompt message and the abnormal labeled article; and determining the 'at least one third display page' as the first display data.

Based on the related content of S6, after the abnormal recognition result is obtained, if the abnormal recognition result indicates that abnormal characters exist in the article to be corrected, first display data may be generated, so that the first display data is used for displaying bad writing habits of the user presented by the article to be corrected.

S7: the first presentation data is presented to the user.

In the embodiment of the application, after the first display data is acquired, the first display data can be directly displayed to the user, so that the user can know the bad writing habit of the user from the first display data, and the user can overcome the bad writing habit.

S8: after first feedback data input by a user for the first display data are acquired, updating the article to be corrected according to the first feedback data.

The first feedback data is used for representing the manual modification result of the user for the abnormal characters in the article to be corrected; also, the "first feedback data" is not limited by the embodiment of the present application, and may be, for example, a complete article (i.e., a modified article re-entered by the user). As another example, the "first feedback data" may be a set of results of manual modifications for each abnormal character in the article to be corrected.

It should be noted that, the embodiment of the present application does not limit the above "manual modification result", for example, it may be: the manual modification is to a normal character (e.g., english character, etc.). For another example, the "manual modification result" may also be: the abnormal character is manually deleted.

In addition, the embodiment of the present application does not limit the acquiring process of the "first feedback data", and for example, the acquiring process may specifically be: after the abnormal labeling article is displayed to a user, the user can manually modify the labeled abnormal characters to generate manual modification results for the abnormal characters, so that after the user triggers and submits a modification request, the abnormal characters and the manual modification results for the abnormal characters are subjected to collective processing to obtain first feedback data.

In addition, the embodiment of the present application is not limited to the implementation of "updating the article to be corrected according to the first feedback data" in S8, for example, when the "first feedback data" is a complete article, the first feedback data may be directly determined as the updated article to be corrected. For another example, when the "first feedback data" is a set of manual modification results for each abnormal character in the article to be corrected, each abnormal character in the article to be corrected may be replaced by directly using the manual modification result for each abnormal character in the first feedback data, so as to obtain an updated article to be corrected, so that the "updated article to be corrected" includes at least one manual modification result for the abnormal character.

Based on the relevant contents of S4 to S8, after the article to be corrected is obtained, it may be determined whether the article to be corrected has abnormal characters, so that after the article to be corrected is determined to have abnormal characters, a modification process for the abnormal characters in the article to be corrected is implemented by means of a human-computer interaction process with a user, thereby effectively avoiding adverse effects of the abnormal characters on the article correction process, and further improving the article correction effect.

It should be noted that the execution time of S4-S8 is not limited in the embodiment of the present application, and may be between the execution time of S1 and the execution time of S2, for example. For example, in one possible implementation, S1 may be performed first, then S4-S8 may be performed, and finally S2-S3 may be performed.

In fact, in some cases (for example, when the user overlooks some abnormal characters, or the user accidentally clicks the modification result submission button before all the abnormal characters have not been modified), it is easy to cause some abnormal characters still existing in the updated article to be approved, so in order to avoid the adverse effect of the overlooked abnormal characters on the article approval process, the embodiment of the present application also provides another possible implementation manner of the article approval method, and in this implementation manner, the article approval method not only includes the above-mentioned S1-S8, but also includes S9:

s9: determining whether a first stop condition is reached, if so, performing S2 (or S10, below); if not, the process returns to the step of S4 and the following steps.

The "first stop condition" may be preset, and for example, it may specifically be: and abnormal characters do not exist in the updated article to be corrected. For another example, the "first stop condition" may specifically be: the number of cycles for S4-S8 reaches a preset number threshold. Also, for example, the "first stop condition" may be specifically: and receiving an abnormal recognition forced ending request triggered by a user. Here, the "abnormal recognition forced end request" is used to request forced end of the abnormal recognition process for the article to be corrected (that is, forced end of the loop execution process for S4-S8).

The execution time of S9 is later than the execution time of S8. For example, in one possible implementation, S1 may be performed first, then S4-S9 may be performed, and finally S2-S3 may be performed.

Based on the related content in S9, after the update process for the article to be corrected is completed, it may be determined whether a first stop condition is reached, and if the first stop condition is reached, it may be determined that the abnormality recognition processing for the article to be corrected does not need to be continued, so that the subsequent processing process for the article to be corrected may be continued (for example, S2-S3 is performed, or S10 and the subsequent steps thereof are performed); however, if the first stop condition is not reached, it may be determined that the anomaly identification processing needs to be performed on the article to be corrected, so that the process may return to continue to perform S4 and the subsequent steps to implement the next round of anomaly identification process for the article to be corrected. Therefore, the bad influence of the missed abnormal characters on the article correction process can be effectively avoided, and the article correction effect can be further improved.

Method embodiment three

The inventor finds in research on an article input process that, under some conditions (for example, improper operation is taken by a user during the input process of an article to be corrected (for example, the original of the article to be corrected is not properly placed, etc.), a problem occurs in the article collecting device itself (for example, lens is not clean, etc.), … …), a large number of spelling errors occur in the article to be corrected input by the user, and the large number of spelling errors do not exist in the original of the article to be corrected, so that the spelling error rate of the article to be corrected is greatly increased.

Based on the above findings, in order to further improve the article correction effect, the present application example also provides another possible implementation manner of the article correction method, in which the article correction method includes not only the above partial or all steps (e.g., S1-S3, or S1-S8, or S1-S9), but also S10-S14:

s10: and determining the spelling error rate of the article to be corrected.

The spelling error rate of the article to be corrected is used for representing the word spelling error rate of the article to be corrected; moreover, the embodiment of the present application does not limit the determination process of the spelling error rate of the article to be corrected, and for example, the determination process may specifically include S101 to S103:

s101: and counting the total number of words in the article to be corrected, and determining the total number of words.

The word total amount is used for representing the number of words in the article to be corrected; and the embodiment of the present application does not limit the determination process of the "total word amount".

S102: and counting the number of the words with misspelling in the article to be corrected, and determining the number of the words with misspelling.

The word quantity with misspelling is used for representing the number of words with misspelling in the article to be corrected; the embodiment of the present application does not limit the determination process of the misspelled word amount.

S103: and determining the ratio of the misspelled word quantity to the word total quantity as the misspelled rate of the article to be corrected.

Based on the related content of S10, after the article to be corrected is obtained, the total number of words in the article to be corrected and the number of words with misspelling may be counted respectively; and determining the ratio of the number of the words with spelling errors to the total number of the words as the spelling error rate of the article to be corrected, so that the spelling error rate of the article to be corrected can show the occurrence probability of the spelling errors in the article to be corrected.

S11: judging whether the spelling error rate of the article to be corrected reaches a preset error rate threshold value, if so, executing S12; if not, go to S2 above.

The "preset error rate threshold" may be preset; the embodiment of the present application does not limit the "preset error rate threshold".

Based on the related content of S11, after obtaining the spelling error rate of the article to be corrected, it can be determined whether the spelling error rate of the article to be corrected reaches a preset error rate threshold; if the preset error rate threshold value is not reached, it can be determined that the occurrence probability of the spelling errors in the article to be corrected is relatively low, so that it can be determined that the input process of the article to be corrected is almost impossible to cause problems, and the subsequent processing process for the article to be corrected can be continuously executed (i.e., executing S2-S3); however, if the preset error rate threshold is reached, it may be determined that the occurrence probability of the spelling error in the article to be corrected is relatively high, so that it may be determined that there is a high possibility that a problem may occur in the input process of the article to be corrected (for example, scanning and recognition are inaccurate, etc.), so that the following "second display data" may be displayed to the user, so that the user may manually confirm whether the problem actually occurs in the input process of the article to be corrected based on the "second display data".

S12: second presentation data is generated.

The second display data is used for indicating that the occurrence probability of spelling errors in the article to be corrected is higher; in addition, the embodiment of the present application does not limit the generation process of the "second presentation data", and for the convenience of understanding, the following description is made with reference to two examples.

In an example, S12 may specifically be: and determining the second prompt information as second display data.

The second prompt message is used for reminding the user to manually confirm whether the input process of the article to be corrected has a problem; in addition, the second prompt information is not limited in the embodiment of the application, and for example, it may be specifically that "a large number of spelling errors occur in the article to be corrected, and please confirm whether the following problem occurs in the input process of the article to be corrected: firstly, whether the placing position of the article to be corrected is proper or not; secondly, whether the lens of the article acquisition equipment is clean or not is judged; … … "this warning message.

The "second presentation information" may be set in advance.

Based on the related content of the example one, after it is determined that the spelling error rate of the article to be corrected reaches the preset error rate threshold, the second prompt information may be determined as the second display data, so that the user can know from the second display data that the article to be corrected input by the user may have defects, and thus the user can be prompted to manually confirm whether the input process of the article to be corrected really has a problem.

Example two, to prompt the user to quickly learn that spelling errors occurred for those words, S12 may specifically include S121-S122:

s121: and performing spelling error labeling processing on the article to be corrected by using the spelling error word recognition result of the article to be corrected to obtain the spelling error labeled article.

The 'misspelled word recognition result' is used for indicating which words in the article to be corrected have misspellings; the embodiment of the present application does not limit the process of obtaining the "misspelled word recognition result", and may be implemented, for example, by using an existing or future misspelled word recognition method.

The spelling error labeling processing is used for labeling the spelling error words in the article to be corrected according to a second character labeling mode. It should be noted that the "second character labeling manner" may be preset, and for example, may specifically include: the word color is updated to blue. As another example, the "second character tagging approach" can be implemented using the misspelled word tagging approach shown in FIG. 6.

Based on the relevant content in S121, after it is determined that the spelling error rate of the article to be corrected reaches the preset error rate threshold, the spelling error word recognition result of the article to be corrected may be obtained first; and then, performing misspelling labeling processing on the article to be corrected by utilizing the position of each misspelling word recorded in the misspelling word recognition result in the article to be corrected to obtain a misspelling labeled article, so that each misspelling word in the misspelling labeled article is labeled according to a second character labeling mode, and each misspelling word in the misspelling labeled article can be highlighted for a user, so that the user can quickly know the misspelling word in the article to be corrected from the misspelling labeled article.

S122: and determining second display data according to the misspelled labeled article.

It should be noted that the present embodiment is not limited to the implementation of S122, and for example, the implementation may specifically include: the misspelled tagged article is directly determined as the second presentation data (the presentation shown in fig. 6). For another example, S122 may specifically be: firstly, according to the second prompt information and the spelling error labeled article, at least one fourth display page (for example, including the display page shown in fig. 6) is constructed, so that the "at least one fourth display page" is used for displaying the second prompt information and the spelling error labeled article; and determining the 'at least one fourth display page' as the first display data.

Based on the above-mentioned related content of S12, after it is determined that the spelling error rate of the article to be corrected reaches the preset error rate threshold, second display data may be generated, so that the second display data can indicate that the occurrence probability of the spelling error in the article to be corrected is relatively high, so that the user can manually confirm whether the input process of the article to be corrected actually causes a problem.

S13: and acquiring second feedback data input by the user aiming at the second display data.

The above-mentioned "second feedback data" is used to indicate whether a problem actually occurs in the input process of the article to be corrected (i.e., the manual proofreading result for the article to be corrected).

In addition, the embodiment of the present application does not limit the acquiring process of the "second feedback data", and for example, the acquiring process may specifically be: after the second display data are displayed to the user, the user can manually check whether the difference exists between the original of the article to be corrected and the article to be corrected; if the user determines that the original of the article to be corrected is different from the article to be corrected, the user can trigger a request for re-inputting the article so that the 'request for re-inputting the article' can indicate that the input process of the article to be corrected is really problematic, and the 'request for re-inputting the article' is determined as second feedback data; however, if the user determines that there is no difference between the original of the article to be corrected and the article to be corrected, the user may trigger execution of the next request, so that the "execute next request" can indicate that no problem occurs in the input process of the article to be corrected, and the "execute next request" is determined as the second feedback data. The article re-input request is used for requesting to re-input article data. "execute next request" is used to request to continue the subsequent processing procedure for the article to be approved (i.e., execute S2-S3).

S14: judging whether the second feedback data meet preset updating conditions, if so, executing S15; if not, S2 is executed.

The "preset update condition" may be preset, and for example, it may specifically be: the second feedback data indicates that a problem actually occurs in the input process of the article to be corrected (for example, the second feedback data carries a request for re-inputting the article).

Based on the related content of S14, after the second feedback data is obtained, if the second feedback data does not satisfy the preset update condition, it may be determined that the problem does not occur in the input process of the article to be corrected, so that the subsequent processing process for the article to be corrected may be continuously performed (i.e., S2-S3 is performed); however, if the second feedback data meets the preset updating condition, it can be determined that a problem does occur in the input process of the article to be corrected, so that new article data input again by the user can be waited for, and then relevant processing can be performed on the new article data.

S15: and updating the article to be corrected.

It should be noted that the examples of the present application do not limit the implementation manner of S15, and for example, the examples may specifically include: and determining the new article data input by the user as the updated article to be corrected.

It should be noted that the execution time of S10-S15 is earlier than the execution time of S2. In one possible embodiment, S1 may be executed first, then S4-S15 may be executed, and finally S2-S3 may be executed; in this embodiment, S5 may be specifically "determine whether the abnormality recognition result satisfies the preset abnormality condition, if yes, execute S6; if not, execute the above S10 ", and S9 may specifically be" determine whether the first stop condition is reached, if so, execute the above S10; if not, the process returns to step S4 and the subsequent steps ".

Based on the relevant contents of S10 to S15, after the article to be corrected is obtained, it can be determined whether the problem actually occurs in the input process of the article to be corrected by means of the spelling error rate of the article to be corrected, so that after the problem actually occurs in the input process of the article to be corrected is determined, the article to be corrected is updated by using the new article data re-input by the user, so that the updated article to be corrected can accurately represent the character information recorded in the original of the article to be corrected as much as possible, and thus the article correcting effect can be effectively improved.

In fact, the user cannot guarantee that the new article data re-entered by the user does not have some of the drawbacks described above (e.g., abnormal characters are present, or problems occur during the article entry process, etc.). Based on this, in order to further improve the article correction effect, the embodiment of the present application also provides another possible implementation manner of the article correction method, in which the article correction method may include not only part or all of the steps (e.g., S1-S13; or S1-S3, and S10-S13; or S1-S8, and S10-S13), but also S16:

s16: judging whether the second feedback data meet preset updating conditions or not, if so, returning to execute S1 and the subsequent steps; if not, S2 is executed.

In the embodiment of the application, after the second feedback data is acquired, if the second feedback data does not satisfy the preset updating condition, it may be determined that no problem occurs in the input process of the article to be corrected, so that the subsequent processing process for the article to be corrected may be continuously performed (i.e., S2-S3 is performed); however, if the second feedback data satisfies the preset updating condition, it can be determined that the input process of the article to be modified does have a problem, so the process can return to perform S1 and the subsequent steps (e.g., S1-S13, etc.) to implement the next round of article input and the processing process thereof, and the process is circulated in this way until the subsequent processing process for the article to be modified (i.e., S2-S3) can continue to be performed after the second stopping condition is determined to be reached. Therefore, the problem that the article correction effect is poor due to the fact that the new article data input again by the user has the defects introduced above (for example, abnormal characters exist or the article input process is in a problem and the like) can be effectively avoided, and the article correction effect can be effectively improved.

The "second stop condition" may be set in advance, and may be, for example: the spelling error rate of the article to be corrected does not reach a preset error rate threshold value; or the second feedback data does not meet the preset updating condition. As can be seen, for the article to be corrected which needs to be detected in each round, if the spelling error rate of the article to be corrected does not reach the preset error rate threshold, it can be determined that the second stop condition has been reached, so that the subsequent processing procedure for the article to be corrected can be continuously performed (i.e., S2-S3 is performed); also, if the second feedback data fed back for the article to be corrected does not satisfy the preset update condition, it may be determined that the second stop condition has been reached, so that the subsequent processing procedure for the article to be corrected may be continuously performed (i.e., S2-S3 is performed).

It should be noted that, the contents of the above two conditions refer to the contents of S11 and S16, respectively.

It is further noted that the execution time of the above S16 is later than the execution time of the above S13, and the execution time of S16 is earlier than the execution time of S2.

Method example four

In order to further improve the article correction effect, the embodiment of the present application further provides a possible implementation manner of S2, which may specifically include S21-S22:

s21: and determining an evaluation result to be displayed according to the article to be corrected.

The evaluation result to be displayed is used for representing the correction content of the article to be corrected; the evaluation result to be displayed is not limited in the embodiment of the application, and for example, the evaluation result to be displayed may specifically include at least one of a scoring result to be displayed, a full text correction result to be displayed, an error correction result of an article to be displayed, a highlight analysis result of the article to be displayed, and a use result of an abnormal character to be displayed.

The "scoring result to be presented" refers to a scoring result (e.g., 89 points shown in fig. 2) for the content of the article to be modified, so that the "scoring result to be presented" is used to indicate the writing level of the article to be modified.

In addition, the embodiment of the present application does not limit the determination process of the "scoring result to be shown," and for example, any existing or future occurrence method that can score an article may be used for implementation. For another example, in order to improve the article correction effect, the process of determining the "score to be displayed" may specifically include steps 11 to 12:

step 11: and grading the article to be corrected to obtain a grading result under at least one evaluation reference angle.

The 'at least one evaluation reference angle' is used for representing a scoring factor referred to when the article to be corrected is scored; also, the embodiment of the present application does not limit the "at least one evaluation reference angle", for example, it may include: at least one of an overall article evaluation angle, a word use evaluation angle, a sentence use evaluation angle, a punctuation evaluation angle, a scroll look and feel evaluation angle, and a writing habit evaluation angle.

As can be seen, the "at least one evaluation reference angle scoring result" may specifically include: at least one of the scoring result under the overall evaluation angle of the article, the scoring result under the word use evaluation angle, the scoring result under the sentence use evaluation angle, the scoring result under the punctuation evaluation angle, the scoring result under the scroll look and feel evaluation angle and the scoring result under the writing habit evaluation angle. For ease of understanding, these scoring results are described separately below.

The "scoring result under the overall evaluation angle of the article" is used for representing the scoring value of the article to be corrected when the article to be corrected is considered from the overall angle of the article to be corrected; in addition, the embodiment of the present application does not limit the determination process of the "scoring result under the overall evaluation angle of the article", and for example, the determination process may specifically include: and determining the scoring result under the integral evaluation angle of the article according to at least one of the integrity scoring result of the article to be corrected, the continuity scoring result of the article to be corrected and the point coverage scoring result of the article to be corrected. For ease of understanding, the following description is made with reference to examples.

As an example, the process of determining the "scoring result under the overall evaluation angle of the article" may specifically include steps 21 to 24:

step 21: and carrying out integrity scoring processing on the article to be corrected to obtain an integrity scoring result of the article to be corrected.

The integrity scoring result of the article to be corrected is used for representing the scoring value of the article to be corrected when the integrity of the article to be corrected is considered; the embodiment of the present application does not limit the determination process of the "integrity scoring result of the article to be approved", and for example, the determination process may be implemented by using any existing or future article integrity scoring method. In another example, the method can be implemented by means of a pre-constructed machine learning model with an article integrity scoring function.

Step 22: and carrying out consistency scoring processing on the article to be corrected to obtain a consistency scoring result of the article to be corrected.

The 'consistency scoring result of the article to be corrected' is used for representing the scoring value of the article to be corrected when the integral consistency of the article to be corrected is considered; the embodiment of the present application does not limit the determination process of the "consistency scoring result of the article to be approved", and for example, the determination process may be implemented by any article consistency scoring method that is currently used or appears in the future. In another example, the method can be implemented by means of a pre-constructed machine learning model with article consistency scoring function.

Step 23: and performing point coverage scoring processing on the article to be corrected to obtain a point coverage scoring result of the article to be corrected.

The key point coverage scoring result is used for representing the scoring value of the article to be corrected when the key point coverage of the whole content of the article to be corrected is considered; the embodiment of the present application does not limit the determination process of the "gist coverage scoring result of the article to be approved", and for example, the determination process may be implemented by using any existing or future appearing method for scoring the gist coverage of the article. In another example, the method can be implemented by means of a pre-constructed machine learning model with an article main point coverage scoring function.

Step 24: and carrying out weighted summation on the integrity scoring result of the article to be corrected, the continuity scoring result of the article to be corrected and the point coverage scoring result of the article to be corrected to obtain a scoring result under the integral evaluation angle of the article.

It should be noted that the weighting weight corresponding to the "integrity score result of the article to be modified", the weighting weight corresponding to the "continuity score result of the article to be modified", and the weighting weight corresponding to the "main point coverage score result of the article to be modified" may be preset.

Based on the related content of the "scoring result under the overall article evaluation angle", after the article to be corrected is obtained, the article to be corrected may be scored from the overall angle of the article to be corrected (for example, the aspects of overall integrity, overall continuity, and point coverage of the overall content, etc.), so as to obtain the scoring result under the overall article evaluation angle of the article to be corrected, so that the "scoring result under the overall article evaluation angle" may indicate the scoring value of the article to be corrected when considered from the overall angle of the article to be corrected.

The above-mentioned "score result under the word use evaluation angle" is used to indicate the score value of the article to be corrected when considered from the perspective of the word elements formed by the article to be corrected; the determination process of the word use evaluation angle scoring result is not limited in the embodiments of the present application, and for example, the determination process may specifically include: and determining the word scoring result under the evaluation angle according to at least one of the word quantity scoring result of the article to be corrected, the wrong word quantity scoring result of the article to be corrected and the high-grade word quantity scoring result of the article to be corrected. For ease of understanding, the following description is made with reference to examples.

As an example, the determination process of "the word uses the scoring result under the evaluation angle" may specifically include steps 31 to 34:

step 31: and performing word use quantity grading processing on the article to be corrected to obtain a word use quantity grading result of the article to be corrected.

The word quantity scoring result of the article to be corrected is used for representing the scoring value of the article to be corrected when the word quantity of the article to be corrected is considered; the embodiment of the present application does not limit the determination process of the term usage scoring result of the article to be corrected, and for example, the determination process may be implemented by any existing or future article term usage scoring method. For another example, the method can be implemented by means of a pre-constructed machine learning model with an article volume scoring function.

Step 32: and performing word error quantity grading processing on the article to be corrected to obtain the word error quantity grading result of the article to be corrected.

The "wrong word quantity scoring result of the article to be corrected" is used for indicating the scoring value of the article to be corrected when the wrong word quantity of the article to be corrected is considered; the embodiment of the present application does not limit the determination process of the wrong-word quantity scoring result of the article to be corrected, and for example, the determination process may be implemented by any one of the existing or future wrong-word quantity scoring methods for the article. For another example, the method can be implemented by means of a machine learning model which is constructed in advance and has an article wrong word quantity scoring function.

Step 33: and performing high-level word use quantity grading processing on the article to be corrected to obtain a high-level word quantity grading result of the article to be corrected.

The "high-level word quantity scoring result of the article to be corrected" is used for representing the scoring value of the article to be corrected when the high-level word application condition of the article to be corrected is considered; the embodiment of the present application does not limit the determination process of the "high-level word quantity scoring result of the article to be approved", and for example, the determination process may be implemented by using any existing or future high-level word quantity scoring method for the article. In another example, the method can be implemented by means of a machine learning model which is constructed in advance and has the function of article high-level word quantity scoring.

Step 34: and carrying out weighted summation processing on the word quantity scoring result of the article to be corrected, the wrong word quantity scoring result of the article to be corrected and the high-grade word quantity scoring result of the article to be corrected to obtain a scoring result under the word use evaluation angle.

It should be noted that the weighting weight corresponding to the word quantity scoring result of the article to be modified, the weighting weight corresponding to the wrong word quantity scoring result of the article to be modified, and the weighting weight corresponding to the high-level word quantity scoring result of the article to be modified may be preset.

Based on the relevant content of the "scoring result under the word use evaluation angle", after the article to be corrected is obtained, the article to be corrected can be scored from the word use angles (for example, the number of used words, the number of misspellings, the number of used high-level words, and the like) of the article to be corrected, so that the scoring result under the word use evaluation angle of the article to be corrected can be obtained, and the "scoring result under the word use evaluation angle" can show the scoring value of the article to be corrected when considered from the perspective of the word elements formed by the article to be corrected.

The sentence use evaluation result is used for representing the score value of the article to be corrected when the sentence element angle formed by the article to be corrected is considered; the embodiment of the present application does not limit the determination process of the "score result under the sentence use evaluation angle", and for example, the determination process may specifically include: and determining the 'sentence evaluation result under the evaluation angle' according to at least one of the sentence structure evaluation result of the article to be corrected, the sentence human scale evaluation result of the article to be corrected, the sentence tense evaluation result of the article to be corrected and the sentence morpheme evaluation result of the article to be corrected. For ease of understanding, the following description is made with reference to examples.

As an example, the determination process of "using the score result under the evaluation angle in the sentence" may specifically include steps 41 to 45:

step 41: and performing sentence structure application scoring processing on the article to be corrected to obtain a sentence structure scoring result of the article to be corrected.

The sentence structure scoring result of the article to be corrected is used for representing the scoring value of the article to be corrected when the sentence structure application condition of the article to be corrected is considered; the embodiment of the present application does not limit the determination process of the sentence structure scoring result of the article to be falsified, and for example, the determination process may be implemented by using any existing or future sentence structure scoring method of the article. In another example, the method can be implemented by means of a pre-constructed machine learning model with an article sentence structure scoring function.

Step 42: and carrying out sentence personal name application scoring processing on the article to be corrected to obtain a sentence personal name scoring result of the article to be corrected.

The sentence title scoring result of the article to be corrected is used for representing the scoring value of the article to be corrected when the sentence title application condition of the article to be corrected is considered; the embodiment of the present application does not limit the determination process of the "sentence popularity scoring result of the article to be revised", and for example, the determination process may be implemented by using any existing or future sentence popularity scoring method for the article. In another example, the method can be implemented by means of a machine learning model which is constructed in advance and has the function of scoring the sentence names of the articles.

Step 43: and carrying out sentence temporal application scoring processing on the article to be corrected to obtain a sentence temporal scoring result of the article to be corrected.

The sentence temporal scoring result of the article to be corrected is used for representing the scoring value of the article to be corrected when the sentence temporal application condition of the article to be corrected is considered; the embodiment of the present application does not limit the determination process of the sentence temporal scoring result of the article to be revised, and for example, the determination process may be implemented by using any one of the sentence temporal scoring methods of the article, which is currently available or will appear in the future. In another example, the method can be implemented by means of a machine learning model which is constructed in advance and has an article sentence tense scoring function.

Step 44: and carrying out sentence morphological application grading processing on the article to be corrected to obtain a sentence morphological grading result of the article to be corrected.

The sentence morphological scoring result of the article to be corrected is used for representing the scoring value of the article to be corrected when the sentence morphological application condition of the article to be corrected is considered; the embodiment of the present application does not limit the determination process of the "sentence morphological scoring result of the article to be revised", and for example, the determination process may be implemented by using any existing or future sentence morphological scoring method of the article. For another example, the method can be implemented by means of a machine learning model which is constructed in advance and has an article sentence morphological scoring function.

Step 45: and weighting and summing the sentence structure scoring result of the article to be corrected, the sentence human scale scoring result of the article to be corrected, the sentence tense scoring result of the article to be corrected and the sentence tense scoring result of the article to be corrected to obtain a scoring result of the sentence under the evaluation angle.

It should be noted that the weighting weight corresponding to the sentence structure scoring result of the article to be revised, the weighting weight corresponding to the sentence personality scoring result of the article to be revised, the weighting weight corresponding to the sentence temporal scoring result of the article to be revised, and the weighting weight corresponding to the sentence morphological scoring result of the article to be revised may be preset.

Based on the relevant content of the "score result under the sentence use evaluation angle", after the article to be modified is obtained, the article to be modified may be scored from the sentence element angle of the article to be modified (for example, the sentence structure application condition, the sentence name application condition, the sentence tense application condition, the sentence morphism application condition, and the like), so as to obtain the score result under the sentence use evaluation angle of the article to be modified, so that the "score result under the sentence use evaluation angle" can represent the score value of the article to be modified when considered from the sentence element angle of the article to be modified.

The scoring result under the punctuation evaluation angle is used for representing the scoring value of the article to be corrected when the punctuation application condition formed by the article to be corrected is considered; the determination process of the "scoring result under the punctuation mark evaluation angle" is not limited in the embodiment of the application, and for example, the punctuation mark of any existing or future article can be implemented by using a scoring method. For another example, the method can be implemented by means of a pre-constructed machine learning model with an article punctuation mark scoring function.

The "scoring result in the view of evaluation of the roll-to-roll look and feel" is used to indicate a score value of the article to be corrected when the roll-to-roll look and feel (for example, neatness of a written roll, handwriting, etc.) formed by the article to be corrected is considered; the determination process of the "scoring result under the scroll look and feel evaluation angle" is not limited in the embodiment of the present application, and for example, the determination process may be implemented by any existing or future article scroll look and feel scoring method. For another example, the method can be implemented by means of a machine learning model which is constructed in advance and has the function of grading the scroll look and feel of the article.

The "scoring result in the writing habit evaluation angle" is used to indicate a scoring value of the article to be corrected when the writing habits (for example, mixed writing of Chinese and English, continuous adjacent appearance of punctuations, etc.) of the user exposed by the article to be corrected are considered; in addition, the embodiment of the present application does not limit the determination process of the "scoring result under the writing habit evaluation angle", for example, the determination process specifically includes: after acquiring the writing habit description data of the user, inputting the writing habit description data of the user into a pre-constructed machine learning model with an article writing habit evaluation function to obtain a scoring result output by the machine learning model from the writing habit evaluation angle.

The "user writing habit description data" is used for representing the writing habits of the user exposed by the article to be corrected; in addition, the embodiment of the present application does not limit the acquisition process of the "user writing habit description data", for example, it may specifically be: the above "abnormal recognition result" is determined as the user writing habit description data.

Based on the related content in the step 11, after the article to be corrected is obtained, the article to be corrected may be scored from at least one evaluation reference angle of the article to be corrected, so as to obtain scoring results under the at least one evaluation reference angle, so that the scoring results can more comprehensively show the writing level of the article to be corrected.

Step 12: and determining a grading result to be displayed according to the grading result under at least one evaluation reference angle.

The present application example does not limit the implementation manner of step 12, and for example, it may specifically be: and directly summarizing the scoring results under at least one evaluation reference angle to obtain scoring results to be displayed, so that the scoring results to be displayed comprise the scoring results under all the evaluation reference angles, and the scoring results to be displayed can show the writing level of the article to be corrected under at least one evaluation reference angle.

In fact, in order to better show the user writing level, the embodiment of the present application further provides an implementation of step 12, which may specifically include steps 121 to 122:

step 121: and weighting and summing the scoring results under at least one evaluation reference angle to obtain a comprehensive scoring result.

The comprehensive scoring result is used for representing the comprehensive scoring value of the article to be corrected. For the convenience of understanding the "composite score result", the following description is made with reference to an example.

As an example, when the "at least one evaluation reference angle scoring result" includes an article overall evaluation angle scoring result, a word use evaluation angle scoring result, a sentence use evaluation angle scoring result, a punctuation mark evaluation angle scoring result, a scroll look and feel evaluation angle scoring result, and a writing habit evaluation angle scoring result, step 121 may specifically include: and weighting and summing the scoring result under the overall evaluation angle of the article, the scoring result under the word use evaluation angle, the scoring result under the sentence use evaluation angle, the scoring result under the punctuation evaluation angle, the scoring result under the scroll look and feel evaluation angle and the scoring result under the writing habit evaluation angle to obtain a comprehensive scoring result, so that the comprehensive scoring result can more accurately represent the writing level of the article to be corrected.

Note that, a weighting weight corresponding to the "score result under the overall evaluation angle of the article", a weighting weight corresponding to the "score result under the word use evaluation angle", a weighting weight corresponding to the "score result under the sentence use evaluation angle", a weighting weight corresponding to the "score result under the punctuation mark evaluation angle", a weighting weight corresponding to the "score result under the scroll look and feel evaluation angle", and a weighting weight corresponding to the "score result under the writing habit evaluation angle" may be set in advance.

Step 122: and determining a grading result to be displayed according to the comprehensive grading result.

It should be noted that the embodiment of the present application is not limited to the implementation of step 122, for example, step 122 may specifically include: and determining the comprehensive grading result as a grading result to be displayed so that the grading result to be displayed can show the comprehensive writing level of the article to be corrected. As another example, step 122 may specifically include: and performing set processing on the comprehensive grading result and the grading result under at least one evaluation reference angle to obtain a grading result to be displayed, so that the grading result to be displayed can not only show the writing level of the article to be corrected under at least one evaluation reference angle, but also show the comprehensive writing level of the article to be corrected.

Based on the related content of the "scoring result to be displayed", after the article to be corrected is obtained, content scoring processing can be performed on the article to be corrected to obtain the scoring result to be displayed of the article to be corrected, so that the "scoring result to be displayed" can show the writing level of the article to be corrected.

The above "to-be-displayed full-text correction result" refers to a full-text correction result for the to-be-displayed article, so that the "to-be-displayed full-text correction result" is used to indicate the advantages and disadvantages of the to-be-corrected article.

In addition, the embodiment of the present application does not limit the above "to-be-displayed full text modification result", for example, it may specifically include: at least one of an error analysis result of the article to be corrected and a highlight analysis result of the article to be corrected.

The above "error parsing result of the article to be corrected" is used to indicate the relevant content of the error point existing in the article to be corrected (e.g., what the error point is, what the modification suggestion for the error point is, etc.); moreover, the embodiment of the present application does not limit the determination process of the "error parsing result of the article to be corrected", for example, the determination process may specifically include steps 51 to 52:

step 51: and carrying out error identification processing on the article to be corrected to obtain an error identification result.

The error recognition processing is used for recognizing error points (such as phrase collocation errors, irregular writing, article errors, part of speech errors and the like) existing in the article to be corrected; the embodiment of the present application is not limited to the implementation of the "error recognition processing", and may be implemented by a machine learning model having a document error recognition function, which is constructed in advance, for example.

The error recognition result is used for representing at least one error point existing in the article to be corrected.

Step 52: and determining an error analysis result of the article to be corrected according to the error identification result.

The embodiment of the present application is not limited to the implementation of step 52, and for example, it may specifically include: and determining the error identification result as an error analysis result of the article to be corrected. For another example, step 52 may specifically include steps 521-522:

step 521: and determining at least one error semantic unit according to the error recognition result.

The error semantic unit is used for representing an error point existing in the article to be corrected; the "error semantic unit" is not limited in the embodiments of the present application, and may be, for example, a word in which an error occurs, a phrase in which an error occurs, or a sentence in which an error occurs.

Based on the related content of step 521, after the error recognition result is obtained, the semantic units (e.g., words, phrases, or sentences) corresponding to the error points can be extracted from the article to be corrected by referring to the error recognition result, and the semantic units are determined as the error semantic units, respectively.

Step 522: and determining an error analysis result of the article to be corrected according to at least one error semantic unit.

The embodiment of the present application is not limited to the implementation of step 522, and for example, it may specifically include: at least one error semantic unit is processed in a set mode to obtain an error analysis result of the article to be corrected, so that the error analysis result of the article to be corrected comprises the error semantic units, and the error analysis result of the article to be corrected can better show errors in the article to be corrected.

As another example, in order to promote the user to better understand the shortcomings of the writing of his article, the embodiment of the present application further provides another possible implementation manner of step 522, which may specifically be: the method comprises the steps of performing set processing on at least one error semantic unit and error modification suggestions corresponding to the at least one error semantic unit to obtain an error analysis result of an article to be corrected, so that the error analysis result of the article to be corrected comprises the error semantic units and the error modification suggestions (such as the suggestions shown in fig. 2), and therefore the error analysis result of the article to be corrected can not only show which errors occur in the article to be corrected, but also show how the errors should be modified.

Based on the related content of the error analysis result of the article to be corrected, after the article to be corrected is obtained, each error point appearing in the article to be corrected can be identified; and generating an error analysis result of the article to be corrected based on the error points, so that the "error analysis result of the article to be corrected" can better show the analysis content for the error points (for example, why the error occurs or how the error should be modified), which is beneficial to improving the learning effect of the user.

The "highlight analysis result of the article to be falsified" is used to indicate the content related to the highlight appearing in the article to be falsified (for example, what the highlight is, the content to be appreciated by the highlight, and the like). Wherein "highlight" refers to a point that is advocated (i.e., a point that can produce an bonus effect on the article to be wholesale).

In addition, the embodiment of the present application does not limit the determination process of the "bright spot analysis result of the article to be falsified", and for example, the determination process may specifically include steps 61 to 62:

step 61: and carrying out bright spot identification processing on the article to be corrected to obtain a bright spot identification result.

The above-described "bright point recognition processing" is used to recognize bright points that occur in the article to be falsified (for example, using high-level words, using high-level sentence structures, etc.); the embodiment of the present application is not limited to the implementation of the "bright spot recognition processing", and may be implemented by a machine learning model having a text bright spot recognition function, which is constructed in advance, for example.

The "bright point recognition result" is used to indicate at least one bright point appearing in the article to be falsified.

Step 62: and determining the bright spot analysis result of the article to be corrected according to the bright spot identification result.

The embodiment of the present application is not limited to the implementation of step 62, and for example, it may specifically include: and determining the bright spot identification result as a bright spot analysis result of the article to be corrected. For another example, step 62 may specifically include steps 621 to 622:

step 621: and determining at least one bright point semantic unit according to the bright point identification result.

The bright spot semantic unit is used for representing a bright spot appearing in the article to be corrected; the embodiment of the present application is not limited to the "bright point semantic unit," and for example, the "bright point semantic unit" may be a bright point word, a bright point phrase, or a bright point sentence.

Based on the related content in step 621, after the bright point identification result is obtained, the semantic units (e.g., words, phrases, or sentences) corresponding to the bright points may be extracted from the article to be modified by referring to the bright point identification result, and the semantic units are determined as the bright point semantic units, respectively.

Step 622: and determining a bright spot analysis result of the article to be corrected according to at least one bright spot semantic unit.

The embodiment of the present application is not limited to the implementation of step 622, and for example, it may specifically include: at least one bright spot semantic unit is processed in a set mode to obtain a bright spot analysis result of the article to be corrected, so that the bright spot analysis result of the article to be corrected comprises the bright spot semantic units, and the bright spot analysis result of the article to be corrected can indicate bright spots in the article to be corrected.

As another example, to facilitate users to better understand the advantages of their article writing, the present application embodiment further provides another possible implementation manner of step 622, which may specifically be: the method comprises the steps of carrying out set processing on at least one highlight semantic unit and highlight appreciation contents corresponding to the at least one highlight semantic unit to obtain a highlight analysis result of an article to be corrected, so that the highlight analysis result of the article to be corrected comprises the highlight semantic units and the highlight appreciation contents corresponding to the highlight semantic units, and therefore the highlight analysis result of the article to be corrected can not only show bright spots in the article to be corrected, but also show the scoring effect of the bright spots on the article to be corrected.

The "bright spot review content corresponding to the d-th bright spot semantic unit" is used to describe the usage advantage of the d-th bright spot semantic unit (i.e. the scoring effect of the d-th bright spot semantic unit on the article to be falsified). D is a positive integer, D is less than or equal to D, and D is a positive integer.

Based on the related content of the bright point analysis result of the article to be corrected, after the article to be corrected is obtained, each bright point appearing in the article to be corrected can be recognized firstly; based on the bright spots, a bright spot analysis result of the article to be corrected is generated, so that the "bright spot analysis result of the article to be corrected" can better show the analysis content for the bright spots (for example, the semantic units are the bright spots, or the bright spots can bring about the benefits for the article to be corrected), which is beneficial to improving the learning effect of the user.

In addition, the embodiment of the present application also does not limit the determination process of the "to-be-displayed full text correction result", for example, in order to improve the comprehensiveness of the "to-be-displayed full text correction result", the determination process of the "to-be-displayed full text correction result" may specifically be: and performing set processing on the error analysis result of the article to be corrected and the highlight analysis result of the article to be corrected to obtain the full-text correction result to be displayed.

In addition, in order to promote the user to better understand the advantages and disadvantages of the article to be corrected, the determination process of the "full-text correction result to be shown" may specifically include steps (1) - (2):

step (1): and acquiring full text labeling information to be used.

The full text annotation information to be used is used for representing the content required to be used when full text batch annotation is carried out on the article to be batch annotated; and the "full text annotation information to be used" may include at least one of an error parsing result of the article to be corrected and a highlight parsing result of the article to be corrected.

Please refer to the above for the embodiment of step (1).

Step (2): and carrying out data annotation processing on the article to be batched and corrected by using the full text annotation information to be used to obtain a full text batched and corrected result to be displayed.

It should be noted that the embodiment of the present application is not limited to the implementation manner of the step (2), for example, when the "full text annotation information to be used" includes an error analysis result of the article to be corrected and a highlight analysis result of the article to be corrected, the step (2) may specifically be: and performing data labeling processing on the to-be-displayed article by utilizing the error analysis result and the highlight analysis result to obtain a to-be-displayed full-text correction result, so that the to-be-displayed full-text correction result not only comprises the to-be-displayed article, but also comprises the error analysis result and the highlight analysis result which are highlighted on the to-be-displayed article, and therefore after the to-be-displayed full-text correction result is displayed to a user, the user can better know the advantages and the disadvantages of the written article.

It should be further noted that, when the data labeling processing is performed on the article to be corrected by using the two items of information, i.e., the error analysis result of the article to be corrected and the highlight analysis result of the article to be corrected, in order to facilitate the user to better understand the advantages and disadvantages of the article written by the user, the two items of information may be subjected to the data labeling processing by using different labeling modes (e.g., color labeling, underline labeling, thick text labeling, etc.), so that the finally obtained full-text correction result to be displayed can respectively highlight the error analysis result and the highlight analysis result by using different display characteristics.

Based on the relevant content of the full text correction result to be displayed, after the article to be corrected is obtained, full text high-and-low analysis can be performed on the article to be corrected, so that a full text high-and-low analysis result (namely, an error analysis result and a bright spot analysis result) is obtained; and then, performing quality marking processing on the article to be corrected by utilizing the full-text quality and defect analysis result to obtain a full-text correction result to be displayed, so that the full-text correction result to be displayed can perform quality and defect display on the basis of the full-text content of the article to be corrected, and the user can better know the quality and defect of the written article.

The error correction result of the article to be displayed is used for representing error points existing in the article to be corrected and corresponding error correction contents; moreover, the embodiment of the present application does not limit the "error correction result of the article to be presented", for example, as shown in fig. 2, the "error correction result of the article to be presented" may include: at least one error semantic unit in the article to be corrected and an error modification suggestion corresponding to the at least one error semantic unit. It should be noted that the relevant content of the "semantic unit error" is referred to above.

It can be seen that, for the article to be corrected, after at least one error semantic unit is extracted from the article to be corrected, the error semantic units and the error correction suggestions corresponding to the error semantic units can be processed in a set to obtain an error correction result of the article to be displayed, so that the error correction result of the article to be displayed is dedicated to indicating the defects of the article to be corrected, and thus, after the error correction result of the article to be displayed is displayed to a user, the user can view the defects of the article written by the user in a centralized manner.

The 'bright spot appreciation result of the article to be displayed' is used for showing the bright spots appearing in the article to be corrected and appreciation contents corresponding to the bright spots; moreover, the embodiment of the present application does not limit the "highlight appreciation result of the article to be displayed", for example, the highlight appreciation result may specifically include: at least one bright spot semantic unit in the article to be corrected and bright spot appreciation content corresponding to the at least one bright spot semantic unit. It should be noted that the relevant content of the "highlight semantic unit" is referred to above.

It can be seen that, for the article to be corrected, after at least one highlight semantic unit is extracted from the article to be corrected, the highlight semantic units and the highlight appreciation content corresponding to the highlight semantic units can be aggregated to obtain a highlight appreciation result of the article to be displayed, so that the highlight appreciation result of the article to be displayed is dedicated to representing the advantage of the article to be corrected, and thus after the highlight appreciation result of the article to be displayed is displayed to a user, the user can intensively view the advantage of the article written by the user.

The above "abnormal character use result to be shown" is used to indicate the use habit of the user character (for example, mixed writing of Chinese and English, continuous adjacent appearance of punctuation marks, etc.) presented by the article to be corrected; in addition, the determination process of the "abnormal character use result to be displayed" is not limited in the embodiment of the present application, and for example, the determination process may specifically be: after the modification process for the abnormal characters of the article to be corrected is completed (for example, after it is determined that the above-mentioned "first stop condition" is reached), the abnormal character usage result to be presented may be determined according to the data information generated in the modification process for the abnormal characters of the article to be corrected (for example, S4-S9), so that the "abnormal character usage result to be presented" can represent the user character usage habit, thereby enabling the "abnormal character usage result to be presented" to better represent the bad writing habit of the user.

Based on the related content of S21, after the article to be corrected is obtained, some correction processing (for example, scoring processing, error recognition processing, highlight recognition processing, information labeling processing, abnormal character recognition processing, and the like) may be performed on the article to be corrected to obtain the evaluation result to be presented, so that the evaluation result to be presented can show the writing level of the article to be corrected from different directions.

S22: and determining the correction data to be displayed according to the evaluation result to be displayed.

The present example is not limited to the embodiment of S22, and for the sake of easy understanding, the following description will be made in conjunction with both cases.

In case 1, if the user only wants to view the text interpretation content of the article to be corrected, step S22 may specifically include steps 71 to 72:

step 71: and determining at least one piece of evaluation text data according to the evaluation result to be displayed, so that the 'at least one piece of evaluation text data' is used for representing semantic information carried by the evaluation result to be displayed.

As an example, when the "evaluation result to be displayed" includes a scoring result to be displayed, a full text correction result to be displayed, an article error correction result to be displayed, an article highlight appreciation result to be displayed, and an abnormal character using result to be displayed, the step 71 may specifically include: determining the scoring result to be displayed as the 1 st evaluation text data; determining a full text correction result to be displayed as the 2 nd evaluation text data; determining the error correction result of the article to be displayed as the 3 rd evaluation text data; determining the highlight appreciation result of the article to be displayed as the 4 th evaluation text data; and determining the abnormal character using result to be displayed as the 5 th evaluation text data.

Step 72: and performing set processing on at least one evaluation text data to obtain the correction data to be displayed, so that the correction data to be displayed comprises the evaluation text data.

Based on the related contents in the above steps 71 to 72, in some cases, after the evaluation result to be displayed is obtained, the semantic information recorded in the evaluation result to be displayed may be processed in a set to obtain the modification data to be displayed, so that the modification data to be displayed can represent the semantic information carried by the evaluation result to be displayed.

In case 2, if the user desires to not only view the text interpretation contents of the article to be modified, but also obtain the voice interpretation of the article to be modified by the virtual teacher, the S22 may specifically include steps 81-82:

step 81: and determining at least one evaluation text data and evaluation explanation audio data corresponding to the at least one evaluation text data according to the evaluation result to be displayed.

As an example, step 81 may specifically include steps 811-813:

step 811: and determining at least one piece of evaluation text data according to the evaluation result to be displayed, so that the 'at least one piece of evaluation text data' is used for representing semantic information carried by the evaluation result to be displayed.

It should be noted that, for the relevant content of step 811, refer to step 71 above.

Step 812: and determining the voice text content of each evaluation text data according to each evaluation text data.

The "speech text content of the nth comment text data" is used to indicate the speech content spoken by the virtual teacher when the teacher makes a speech comment interpretation with respect to the nth comment text data. Wherein N is a positive integer, N is not more than N, N is a positive integer, and N represents the number of evaluation text data.

In addition, the embodiment of the present application is not limited to the "voice text content of the nth comment text data" described above, and for example, semantic information (particularly, semantic information about article modification) carried by the "voice text content of the nth comment text data" includes semantic information carried by the nth comment text data.

In addition, the embodiment of the present application does not limit the determination process of the "voice text content of the nth evaluation text data", and for example, the determination process may specifically be: and directly determining the nth evaluation text data as the voice text content of the nth evaluation text data. As another example, it may specifically be: extracting core semantic information from the nth evaluation text data, and determining the core semantic information as the voice text content of the nth evaluation text data. For example, it may specifically be: and inputting the nth evaluation text data into a pre-constructed voice content extraction model to obtain the voice text content of the nth evaluation text data output by the voice content extraction model. The "voice content extraction model" is used to perform a voice content extraction process on input data of the voice content extraction model.

Step 813: and determining the evaluation explanation audio data corresponding to each evaluation text data according to the voice text content of each evaluation text data.

The present application example does not limit the implementation manner of step 813, and for example, it may specifically be: and performing audio data conversion processing on the voice text content of the nth evaluation text data to obtain evaluation explanation audio data corresponding to the nth evaluation text data, so that the voice information carried by the evaluation explanation audio data corresponding to the nth evaluation text data comprises the voice text content of the nth evaluation text data.

Based on the related content in step 81, after the evaluation result to be displayed is obtained, at least one piece of evaluation text data and evaluation explanation audio data corresponding to the evaluation text data may be determined according to the evaluation result to be displayed, so that the correction data to be displayed may be determined based on the evaluation text data and the evaluation explanation audio data corresponding to the evaluation text data, so that the correction data to be displayed may better represent the evaluation result to be displayed.

Step 82: and determining correction data to be displayed according to at least one piece of evaluation text data and evaluation explanation audio data corresponding to the at least one piece of evaluation text data.

As an example, step 82 may specifically include steps 821-822:

step 821: and determining at least one binary group according to the at least one evaluation text data and the evaluation explanation audio data corresponding to the at least one evaluation text data.

The present application example does not limit the implementation manner of step 821, and for example, it may specifically be: the nth tuple is constructed by using the nth comment text data and the comment explanation audio data corresponding to the nth comment text data (for example, the nth tuple may be represented as (the nth comment text data, the comment explanation audio data corresponding to the nth comment text data), or the like). Wherein N is a positive integer, N is not more than N, N is a positive integer, and N represents the number of the evaluation text data.

Step 822: and performing set processing on at least one binary group to obtain the correction data to be displayed, so that the correction data to be displayed comprises the binary groups.

Based on the related contents of the above steps 81 to 82, in some cases, after the evaluation result to be displayed is obtained, the semantic information recorded in the evaluation result to be displayed and the audio data corresponding to the semantic information may be processed in a set manner to obtain the modification data to be displayed, so that the modification data to be displayed can show the semantic information carried by the evaluation result to be displayed by means of two manners, namely, text and audio.

Based on the related contents of S21 to S22, after the article to be corrected is obtained, some correction processing (for example, scoring processing, error recognition processing, highlight recognition processing, information labeling processing, abnormal character recognition processing, and the like) may be performed on the article to be corrected first to obtain an evaluation result to be displayed, so that the evaluation result to be displayed can show the writing level of the article to be corrected from different directions; and then referring to the evaluation result to be displayed, and determining the correction data to be displayed so that the correction data to be displayed can better show semantic information (particularly semantic information about article correction) carried by the evaluation result to be displayed, so that after the correction data to be displayed is displayed to a user, the user can better know the advantages and disadvantages of the article written by the user, and the learning effect of the user is improved.

Method example five

In fact, in order to better show the correction data to be shown, the correction data to be shown can be presented by means of a plurality of pages. Based on this, the embodiment of the present application further provides a possible implementation manner of displaying the correction data to be displayed, and for facilitating understanding, the following description is made in combination with two cases.

In case 1, if the to-be-displayed correction data includes N evaluation text data, the display process of the to-be-displayed correction data may specifically include steps 91 to 92:

step 91: and determining at least one first display page according to the N evaluation text data, so that each first display page is used for displaying at least one evaluation text data in the N evaluation text data, and the N evaluation text data can be displayed by the first display pages.

The "at least one first presentation page" is used to present the "N evaluation text data"; and there is a difference between contents presented on the respective first presentation pages in the "at least one first presentation page". For ease of understanding, the following description is made with reference to examples.

As an example, when N is 5, the 1 st evaluation text data includes a scoring result to be displayed, the 2 nd evaluation text data includes a full text correction result to be displayed, the 3 rd evaluation text data includes an error correction result of an article to be displayed, the 4 th evaluation text data includes a highlight analysis result of the article to be displayed, and the 5 th evaluation text data includes an abnormal character use result to be displayed, the number of the first display pages may be 4; moreover, the 1 st first presentation page may be used to present the 1 st comment text data and the 2 nd comment text data in parallel, the 2 nd first presentation page may be used to present the 1 st comment text data and the 3 rd comment text data in parallel (such as the page shown in fig. 2), the 3 rd first presentation page may be used to present the 1 st comment text data and the 4 th comment text data in parallel, and the 4 th first presentation page may be used to present the 1 st comment text data and the 5 th comment text data in parallel.

And step 92: at least one first presentation page is presented to the user.

The present application example does not limit the implementation manner of step 92, and for example, it may specifically be: and directly displaying at least one first display page to the user according to a preset display sequence. As another example, step 92 may specifically be: firstly, combining at least one first display page according to a preset mode to obtain a combined page (such as the combined page shown in fig. 2); and displaying the combined page to a user so that the user can view different first display pages by executing different trigger operations on the combined page.

Based on the related contents of the above steps 91 to 92, in some cases, when the modification data to be displayed only includes some text data, at least one first display page may be generated by using the text data, so that the first display pages can combine and display the text data; and then, the first display pages are displayed to the user according to a certain display mode (for example, the display mode shown in fig. 2), so that the user can obtain the evaluation result to be displayed from the first display pages.

It should be noted that, in order to improve user experience, different touch components (e.g., buttons and the like) may be arranged on each first display page, so that the user can jump to different first display pages for access by triggering different touch components, which is beneficial to improving the flexibility of the user in accessing page data. For example, for the 2 nd first display page shown in fig. 2, the user may jump to the 1 st first display page for access by clicking "view full text" so that the user can view the full text approval result to be displayed on the 1 st first display page.

In case 2, if the to-be-displayed correction data includes N evaluation text data and evaluation explanation audio data corresponding to the N evaluation text data, the display process of the to-be-displayed correction data may specifically include steps 101 to 102:

step 101: and determining the display sequence of at least one second display page and the at least one second display page according to the mimicry character image, the N evaluation text data and the evaluation explanation audio data corresponding to the N evaluation text data, so that each second display page is used for displaying the mimicry character image, at least one evaluation text data in the N evaluation text data and the evaluation explanation audio data corresponding to the at least one evaluation text data.

The related content of the "mimic character" can be referred to as the related content in S2 above.

The at least one second display page is used for displaying the simulated character image, the N evaluation text data and the evaluation explanation audio data corresponding to the N evaluation text data; and there is a difference between contents presented on the respective first presentation pages in the "at least one second presentation page". For ease of understanding, the following description is made with reference to examples.

As an example, when N is 5, the 1 st evaluation text data includes a scoring result to be displayed, the 2 nd evaluation text data includes a full text correction result to be displayed, the 3 rd evaluation text data includes an error correction result of an article to be displayed, the 4 th evaluation text data includes a highlight appreciation result of the article to be displayed, and the 5 th evaluation text data includes an abnormal character use result to be displayed, the number of the second display pages may be 4; and the related contents of the 4 second display pages are as follows:

(1) the display content of the 1 st second display page may include a mimic character, 1 st evaluation text data, evaluation explanation audio data corresponding to the 1 st evaluation text data, 2 nd evaluation text data, and evaluation explanation audio data corresponding to the 2 nd evaluation text data.

In addition, the content presentation process presented by the 1 st second presentation page may be: sequentially broadcasting evaluation explanation audio data corresponding to the 1 st evaluation text data and evaluation explanation audio data corresponding to the 2 nd evaluation text data by the mimicry figure according to a preset broadcasting sequence; moreover, when the mimicry character broadcasts the evaluation explanation audio data corresponding to the 1 st evaluation text data, the 1 st evaluation text data should be displayed on the 1 st second display page; when the anthropomorphic character broadcasts the evaluation explanation audio data corresponding to the 2 nd evaluation text data, the 2 nd evaluation text data should be displayed on the 1 st second display page.

(2) The presentation contents (as shown in fig. 3) of the 2 nd second presentation page may include a mimetic character, 3 rd comment text data, and comment explanation audio data corresponding to the 3 rd comment text data.

In addition, the content presentation process presented by the 2 nd second presentation page may be: broadcasting evaluation explanation audio data corresponding to the 3 rd evaluation text data by the mimicry person; moreover, when the mimicry character broadcasts the evaluation explanation audio data corresponding to the 3 rd evaluation text data, the 3 rd evaluation text data should be displayed on the 2 nd second display page.

(3) The presentation content of the 3 rd second presentation page may include a mimetic character, 4 th evaluation text data, and evaluation interpretation audio data corresponding to the 4 th evaluation text data.

In addition, the content presentation process presented by the 3 rd second presentation page may be: broadcasting evaluation explanation audio data corresponding to the 4 th evaluation text data by the mimicry person; moreover, when the mimicry character broadcasts the evaluation explanation audio data corresponding to the 4 th evaluation text data, the 4 th evaluation text data should be displayed on the 3 rd second display page.

(4) The presentation content of the 4 th second presentation page may include a mimetic character, 5 th evaluation text data, and evaluation interpretation audio data corresponding to the 5 th evaluation text data.

In addition, the content presentation process presented by the 4 th second presentation page may be: broadcasting evaluation explanation audio data corresponding to the 5 th evaluation text data by the mimicry person; moreover, when the mimicry character broadcasts the evaluation explanation audio data corresponding to the 5 th evaluation text data, the 5 th evaluation text data should be displayed on the 4 th second display page.

The above-mentioned "presentation order of at least one second presentation page" is used to indicate an arrangement order in which the second presentation pages are presented to the user. For ease of understanding, the following description is made with reference to examples.

As an example, based on the relevant contents of the "1 st second display page" to the "4 th second display page", the "display order of at least one second display page" may specifically be: firstly, displaying a 1 st second display page; after the 1 st second display page is displayed, automatically jumping to display a 2 nd second display page; after the 2 nd second display page is displayed, automatically jumping to display the 3 rd second display page; and after the 3 rd second display page is displayed, automatically jumping to display the 4 th second display page.

In addition, the embodiment of the present application does not limit the determination process of the "display order of at least one second display page" described above, for example, the "display order of at least one second display page" may be determined by referring to a preset page display rule.

The above-mentioned "preset page display rule" is used to define the display priority among different pages. For example, the "preset page display rule" may specifically be: the scoring result to be displayed has the highest priority; the display priority of the full text correction result to be displayed is higher than that of other evaluation results except the grading result to be displayed; the display priority of the error correction result of the article to be displayed is higher than that of the highlight appreciation result of the article to be displayed; the display priority of the highlight appreciation result of the article to be displayed is higher than that of the abnormal character use result to be displayed.

Step 102: and displaying the at least one second display page to the user according to the display sequence of the at least one second display page.

In the embodiment of the application, after the at least one second display page and the display sequence thereof are obtained, the at least one second display page can be displayed to the user according to the display sequence, so that the user can sequentially obtain the display text and the voice broadcast corresponding to the scoring result to be displayed, the display text and the voice broadcast corresponding to the full text correction result to be displayed, the display text and the voice broadcast corresponding to the error correction result of the article to be displayed, the display text and the voice broadcast corresponding to the highlight analysis result of the article to be displayed, and the display text and the voice broadcast corresponding to the abnormal character use result to be displayed.

Based on the related contents of the above steps 101 to 102, in some cases, when the modification data to be displayed includes some text data and evaluation interpretation audio data corresponding to the text data, at least one second display page may be generated by using the text data, the evaluation interpretation audio data corresponding to the text data, and the preset mimicry character image, so that the second display pages may simulate the interpretation process of the virtual teacher for the evaluation results to be displayed; and then the second display pages are displayed to the user, so that the user can experience the detailed comment process of the teacher for the written article from the second display pages, and the user experience is improved.

Based on the article correction method provided by the above method embodiment, the embodiment of the present application further provides an article correction device, which is explained and explained below with reference to the accompanying drawings.

Device embodiment

The embodiment of the apparatus introduces the article correction apparatus, and for related contents, please refer to the embodiment of the method described above.

Referring to fig. 7, the figure is a schematic structural diagram of an article modification apparatus provided in the embodiment of the present application.

The article correction device 700 provided in the embodiment of the present application includes:

an article obtaining unit 701, configured to obtain an article to be corrected, input by a user;

an article correction unit 702, configured to perform article correction processing on the article to be corrected, so as to obtain correction data to be displayed;

the correction display unit 703 is configured to display the correction data to be displayed to the user.

In a possible embodiment, the wholesale data to be displayed comprises at least one of wholesale text display data and wholesale virtual comment data; the correction virtual comment data comprise a mimic character image and correction description audio data; and the correction description audio data carries semantic information which is matched with the correction text display data, wherein the semantic information carried by the correction description audio data and the semantic information carried by the correction text display data have intersection.

In one possible embodiment, the article modification unit 702 includes:

the first determining subunit is used for determining an evaluation result to be displayed according to the article to be corrected;

and the second determining subunit is used for determining the correction data to be displayed according to the evaluation result to be displayed.

In a possible implementation manner, the evaluation result to be displayed includes at least one of a scoring result to be displayed, a full text correction result to be displayed, an article error correction result to be displayed, an article highlight analysis result to be displayed, and an abnormal character using result to be displayed.

In one possible embodiment, the first determining subunit includes:

the scoring determining subunit is used for scoring the article to be corrected to obtain a scoring result under at least one evaluation reference angle; and determining the scoring result to be displayed according to the scoring result under the at least one evaluation reference angle.

In one possible embodiment, the at least one evaluation reference angle includes at least one of an article overall evaluation angle, a word use evaluation angle, a sentence use evaluation angle, a punctuation evaluation angle, a scroll look and feel evaluation angle, and a writing habit evaluation angle.

In a possible implementation manner, the scoring result under the overall evaluation angle of the article is determined according to at least one of the integrity scoring result of the article to be modified, the continuity scoring result of the article to be modified, and the point coverage scoring result of the article to be modified.

In a possible implementation manner, the word usage evaluation angle scoring result is determined according to at least one of a word usage scoring result of the article to be modified, a wrong word amount scoring result of the article to be modified, and a high-level word amount scoring result of the article to be modified.

In a possible implementation manner, the scoring result under the sentence use evaluation angle is determined according to at least one of a sentence structure scoring result of the article to be revised, a sentence popularity scoring result of the article to be revised, a sentence tense scoring result of the article to be revised, and a sentence tense scoring result of the article to be revised.

In a possible implementation manner, the full-text correction result to be displayed includes at least one of an error resolution result of the article to be corrected and a highlight resolution result of the article to be corrected.

In one possible embodiment, the first determining subunit includes:

the error identification subunit is used for carrying out error identification processing on the article to be corrected to obtain an error identification result;

and the error analysis subunit is used for determining the error analysis result of the article to be corrected according to the error identification result.

In a possible implementation manner, the error resolution subunit is specifically configured to: determining at least one error semantic unit according to the error recognition result; and performing set processing on the at least one error semantic unit and the error modification suggestions corresponding to the at least one error semantic unit to obtain an error analysis result of the article to be corrected.

In one possible embodiment, the first determining subunit includes:

the bright spot determining subunit is used for carrying out bright spot identification processing on the article to be corrected to obtain a bright spot identification result;

and the bright spot analysis subunit is used for determining the bright spot analysis result of the article to be corrected according to the bright spot identification result.

In a possible embodiment, the bright point analyzing subunit is specifically configured to: determining at least one bright spot semantic unit according to the bright spot identification result; and performing set processing on the at least one bright spot semantic unit and the bright spot review content corresponding to the at least one bright spot semantic unit to obtain a bright spot analysis result of the article to be corrected.

In one possible embodiment, the first determining subunit includes:

the full-text correction determining subunit is used for acquiring full-text labeling information to be used; the full text annotation information to be used comprises at least one of an error analysis result of the article to be corrected and a highlight analysis result of the article to be corrected; and carrying out data annotation processing on the article to be corrected by utilizing the full text annotation information to be used to obtain the full text correction result to be displayed.

In a possible implementation manner, the error correction result of the article to be displayed includes at least one error semantic unit in the article to be corrected and an error modification suggestion corresponding to the at least one error semantic unit;

and/or the presence of a gas in the gas,

the highlight appreciation result of the article to be displayed comprises at least one highlight semantic unit in the article to be corrected and highlight appreciation content corresponding to the at least one highlight semantic unit.

In a possible implementation manner, the second determining subunit is specifically configured to: determining at least one evaluation text data and evaluation explanation audio data corresponding to the at least one evaluation text data according to the evaluation result to be displayed; and determining the correction data to be displayed according to the at least one evaluation text data and the evaluation explanation audio data corresponding to the at least one evaluation text data.

In one possible embodiment, the article modification apparatus 700 further comprises:

the abnormal recognition subunit is used for performing abnormal character recognition processing on the article to be corrected to obtain an abnormal recognition result;

the first generation subunit is used for generating first display data if the abnormal recognition result meets a preset abnormal condition;

a first presentation subunit, configured to present the first presentation data to the user;

and the first updating subunit is used for updating the article to be corrected according to the first feedback data after the first feedback data input by the user for the first display data is obtained.

In a possible implementation manner, the first generating subunit is specifically configured to: according to the abnormal recognition result, performing abnormal character marking processing on the article to be corrected to obtain an abnormal marked article; and determining the first display data according to the abnormal labeling article.

In a possible implementation manner, the first generating subunit is specifically configured to: and determining the first prompt information as the first display data.

In a possible implementation manner, the first updating subunit is specifically configured to: after first feedback data input by the user for the first display data is acquired, updating the article to be corrected according to the first feedback data, and returning to the abnormal recognition subunit to continue executing the step of performing abnormal character recognition processing on the article to be corrected to obtain an abnormal recognition result;

the article correction unit 702 is specifically configured to: and after the first stopping condition is determined to be reached, carrying out article correction processing on the article to be corrected to obtain correction data to be displayed.

the error rate determining subunit is used for determining the spelling error rate of the article to be corrected;

the second generation subunit is used for generating second display data if the spelling error rate of the article to be corrected reaches a preset error rate threshold;

a feedback obtaining subunit, configured to obtain second feedback data input by the user for the second presentation data;

and the second updating subunit is used for updating the article to be corrected when the second feedback data is determined to meet the preset updating condition.

In a possible implementation manner, the second updating subunit is specifically configured to: when it is determined that the second feedback data meets a preset updating condition, returning to the article obtaining unit 701 to continue executing the step of obtaining the article to be corrected input by the user;

the article correction unit 702 is specifically configured to: and after the second stopping condition is determined to be reached, carrying out article correction processing on the article to be corrected to obtain correction data to be displayed.

In a possible implementation manner, the correction data to be displayed comprises N evaluation text data; wherein N is a positive integer;

the article modification apparatus 700 further comprises:

a first determining unit, configured to determine at least one first display page according to the N evaluation text data, so that the at least one first display page is used for displaying the N evaluation text data;

the correction display unit 703 is specifically configured to: and displaying the at least one first display page to the user.

In a possible implementation manner, the to-be-displayed correction data includes N evaluation text data and evaluation explanation audio data corresponding to the N evaluation text data;

the article modification apparatus 700 further comprises:

the second determining unit is used for determining at least one second display page and the display sequence of the at least one second display page according to the mimicry character image, the N evaluation text data and the evaluation explanation audio data corresponding to the N evaluation text data; each second display page is used for displaying the mimicry character image, at least one evaluation text data in the N evaluation text data and evaluation explanation audio data corresponding to the at least one evaluation text data;

the correction display unit 703 is specifically configured to: and displaying the at least one second display page to the user according to the display sequence of the at least one second display page.

Further, an embodiment of the present application further provides an apparatus, including: a processor, a memory, a system bus;

the processor and the memory are connected through the system bus;

the memory is configured to store one or more programs, the one or more programs including instructions, which when executed by the processor, cause the processor to perform any of the implementations of the article endorsement method described above.

Further, an embodiment of the present application further provides a computer-readable storage medium, where instructions are stored in the computer-readable storage medium, and when the instructions are run on a terminal device, the instructions cause the terminal device to execute any implementation method of the article approval method.

Further, an embodiment of the present application further provides a computer program product, which, when running on a terminal device, causes the terminal device to execute any one of the implementation methods of the article correction method.

As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that all or part of the steps in the above embodiment methods can be implemented by software plus a necessary general hardware platform. Based on such understanding, the technical solution of the present application may be essentially or partially implemented in the form of a software product, which may be stored in a storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network communication device such as a media gateway, etc.) to execute the method according to the embodiments or some parts of the embodiments of the present application.

It should be noted that, in the present specification, the embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments may be referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.

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

The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for article approval, the method comprising:

acquiring an article to be corrected input by a user;

carrying out article correction processing on the article to be corrected to obtain correction data to be displayed;

and displaying the correction data to be displayed to the user.

2. The method according to claim 1, wherein the wholesale data to be displayed comprises at least one of wholesale text display data and wholesale virtual comment data; the correction virtual comment data comprise a mimic character image and correction description audio data; and the intersection exists between the semantic information carried by the correction description audio data and the semantic information carried by the correction text display data.

3. The method according to claim 1 or 2, wherein the performing article correction processing on the article to be corrected to obtain correction data to be displayed comprises:

determining an evaluation result to be displayed according to the article to be corrected;

and determining the correction data to be displayed according to the evaluation result to be displayed.

4. The method according to claim 3, wherein the evaluation result to be displayed comprises at least one of a scoring result to be displayed, a full text correction result to be displayed, an error correction result of the article to be displayed, a highlight appreciation result of the article to be displayed, and an abnormal character use result to be displayed.

5. The method according to claim 4, wherein the determination process of the scoring result to be shown comprises:

grading the article to be corrected to obtain a grading result under at least one evaluation reference angle;

and determining the scoring result to be displayed according to the scoring result under the at least one evaluation reference angle.

6. The method of claim 5, wherein the at least one evaluation reference angle comprises at least one of an overall article evaluation angle, a word use evaluation angle, a sentence use evaluation angle, a punctuation evaluation angle, a scroll look and feel evaluation angle, and a writing habit evaluation angle.

7. The method of claim 6, wherein the scoring result from the overall evaluation angle of the article is determined according to at least one of an integrity scoring result of the article to be modified, a continuity scoring result of the article to be modified, and a gist coverage scoring result of the article to be modified.

8. The method of claim 6, wherein the word usage evaluation angle score is determined according to at least one of a word usage score of the article to be modified, a wrong word usage score of the article to be modified, and a high-level word usage score of the article to be modified.

9. The method of claim 6, wherein the sentence use evaluation angle score result is determined according to at least one of a sentence structure score result of the article to be revised, a sentence popularity score result of the article to be revised, a sentence tense score result of the article to be revised, and a sentence tense score result of the article to be revised.

10. The method according to claim 4, wherein the full text correction result to be displayed comprises at least one of an error resolution result of the article to be corrected and a highlight resolution result of the article to be corrected.

11. The method of claim 10, wherein the determining of the misinterpretation result of the article to be falsified comprises:

carrying out error identification processing on the article to be corrected to obtain an error identification result;

and determining the error analysis result of the article to be corrected according to the error identification result.

12. The method of claim 11, wherein the determining the misinterpretation result of the article to be endorsed according to the misidentification result comprises:

determining at least one error semantic unit according to the error recognition result;

and performing set processing on the at least one error semantic unit and the error modification suggestions corresponding to the at least one error semantic unit to obtain an error analysis result of the article to be corrected.

13. The method according to claim 10, wherein the determining of the highlight parsing result of the article to be falsified comprises:

performing bright spot identification processing on the article to be corrected to obtain a bright spot identification result;

and determining a bright spot analysis result of the article to be corrected according to the bright spot identification result.

14. The method of claim 13, wherein determining the bright spot resolution result of the article to be endorsed according to the bright spot identification result comprises:

determining at least one bright spot semantic unit according to the bright spot identification result;

and performing set processing on the at least one bright spot semantic unit and the bright spot appreciation content corresponding to the at least one bright spot semantic unit to obtain a bright spot analysis result of the article to be corrected.

15. The method according to claim 4, wherein the determining process of the full text correction result to be displayed comprises:

acquiring full-text labeling information to be used; the full text annotation information to be used comprises at least one of an error analysis result of the article to be corrected and a highlight analysis result of the article to be corrected;

and carrying out data annotation processing on the article to be corrected by utilizing the full text annotation information to be used to obtain the full text correction result to be displayed.

16. The method according to claim 4, wherein the error correction result of the article to be displayed comprises at least one error semantic unit in the article to be corrected and an error modification suggestion corresponding to the at least one error semantic unit;

and/or the presence of a gas in the gas,

17. The method according to claim 3, wherein the determining the wholesale data to be displayed according to the evaluation result to be displayed comprises:

determining at least one evaluation text data and evaluation explanation audio data corresponding to the at least one evaluation text data according to the evaluation result to be displayed;

and determining the correction data to be displayed according to the at least one evaluation text data and the evaluation explanation audio data corresponding to the at least one evaluation text data.

18. The method of claim 1, wherein before the article correction processing is performed on the article to be corrected to obtain the correction data to be displayed, the method further comprises:

carrying out abnormal character recognition processing on the article to be corrected to obtain an abnormal recognition result;

if the abnormal recognition result meets a preset abnormal condition, generating first display data;

presenting the first presentation data to the user;

and after first feedback data input by the user for the first display data are acquired, updating the article to be corrected according to the first feedback data.

19. The method of claim 18, wherein generating the first presentation data comprises:

according to the abnormal recognition result, performing abnormal character marking processing on the article to be corrected to obtain an abnormal marked article; determining the first display data according to the abnormal labeling article;

alternatively, the first and second electrodes may be,

the generating of the first presentation data comprises:

and determining the first prompt information as the first display data.

20. The method of claim 18, wherein after updating the article to be endorsed according to the first feedback data, the method further comprises:

continuing to execute the step of performing abnormal character recognition processing on the article to be corrected to obtain an abnormal recognition result;

the article correction processing is performed on the article to be corrected to obtain correction data to be displayed, and the method comprises the following steps:

and after the first stopping condition is determined to be reached, carrying out article correction processing on the article to be corrected to obtain correction data to be displayed.

21. The method according to claim 1, 18 or 20, wherein before the article modification processing is performed on the article to be modified to obtain modification data to be displayed, the method further comprises:

determining the spelling error rate of the article to be corrected;

if the spelling error rate of the article to be corrected reaches a preset error rate threshold value, generating second display data;

acquiring second feedback data input by the user aiming at the second display data;

and updating the article to be corrected when the second feedback data is determined to meet the preset updating condition.

22. The method of claim 21, wherein updating the article to be endorsed upon determining that the second feedback data meets a preset update condition comprises:

when the second feedback data is determined to meet the preset updating condition, continuing to execute the step of acquiring the article to be corrected input by the user;

and after the second stopping condition is determined to be reached, carrying out article correction processing on the article to be corrected to obtain correction data to be displayed.

23. The method according to claim 1, wherein the wholesale data to be presented comprises N evaluation text data; wherein N is a positive integer;

the method further comprises the following steps:

determining at least one first display page according to the N evaluation text data, so that the at least one first display page is used for displaying the N evaluation text data;

the displaying the to-be-displayed correction data to the user includes:

and displaying the at least one first display page to the user.

24. The method according to claim 1, wherein the correction data to be displayed comprises N evaluation text data and evaluation explanation audio data corresponding to the N evaluation text data;

the method further comprises the following steps:

determining at least one second display page and the display sequence of the at least one second display page according to the mimicry character, the N evaluation text data and the evaluation explanation audio data corresponding to the N evaluation text data; each second display page is used for displaying the mimicry character image, at least one evaluation text data in the N evaluation text data and evaluation explanation audio data corresponding to the at least one evaluation text data;

the displaying the to-be-displayed correction data to the user includes:

and displaying the at least one second display page to the user according to the display sequence of the at least one second display page.

25. An article correction device, comprising:

the article acquisition unit is used for acquiring an article to be corrected input by a user;

the article correcting unit is used for carrying out article correcting processing on the article to be corrected to obtain correcting data to be displayed;

and the correction display unit is used for displaying the correction data to be displayed to the user.

26. An apparatus, characterized in that the apparatus comprises: a processor, a memory, a system bus;

the processor and the memory are connected through the system bus;

the memory is to store one or more programs, the one or more programs comprising instructions, which when executed by the processor, cause the processor to perform the method of any of claims 1 to 24.

27. A computer-readable storage medium having stored therein instructions which, when run on a terminal device, cause the terminal device to perform the method of any one of claims 1 to 24.

28. A computer program product, characterized in that it, when run on a terminal device, causes the terminal device to perform the method of any one of claims 1 to 24.