WO2022143454A1

WO2022143454A1 - Information correction method and apparatus, and electronic device

Info

Publication number: WO2022143454A1
Application number: PCT/CN2021/141161
Authority: WO
Inventors: 王林林
Original assignee: 维沃移动通信有限公司
Priority date: 2020-12-30
Filing date: 2021-12-24
Publication date: 2022-07-07
Also published as: CN112684913A; CN112684913B

Abstract

The present application relates to the technical field of communications, and discloses an information correction method and apparatus, and an electronic device. The information correction method comprises: displaying, in a target area of an information editing interface, first text information converted and generated according to first voice information; according to a received first input, displaying corresponding candidate words in a candidate information area of the information editing interface; obtaining first indication information according to an operation by a user in the candidate information area, the first indication information being used for indicating a target candidate word among the candidate words; and correcting the first text information in the target area according to the target candidate word.

Description

Information correction method, device and electronic equipment

CROSS-REFERENCE TO RELATED APPLICATIONS

This application claims priority to Chinese Patent Application No. 202011608156.X filed in China on December 30, 2020, the entire contents of which are incorporated herein by reference.

technical field

The present application belongs to the field of communication technologies, and specifically relates to an information correction method, device and electronic device.

Background technique

At present, in the process of using an input method on a mobile terminal to express one's own thoughts, the pinyin input method and the voice input method are often used.

As the accuracy of speech recognition continues to improve, the voice input method is favored by more users. However, although the voice input method has the advantages of being fast and easy to use, it also has a serious disadvantage: when the user speaks a long sentence, there are often misrecognized words in the sentence after speech recognition, resulting in the recognition of wrong words. The accuracy of text information is low, requiring users to modify and identify wrong words.

In the prior art, in the process of modifying the text information obtained by the voice recognition, the user can only correct the wrong words by inputting the text through the keyboard input method, which reduces the input efficiency.

SUMMARY OF THE INVENTION

The purpose of the embodiments of the present application is to provide an information correction method, device and electronic device, which can solve the problem that the input efficiency of the voice input method in the prior art needs to be improved.

In order to solve the above technical problems, this application is implemented as follows:

In a first aspect, an embodiment of the present application provides an information correction method, the method comprising:

The first text information that is converted and generated according to the first voice information is displayed in the target area in the information editing interface;

According to the received first input, the corresponding candidate word is displayed in the candidate information area in the information editing interface;

Obtain first indication information according to the user's operation in the candidate information area, where the first indication information is used to indicate the target candidate word in the candidate word;

According to the target candidate word, the first text information in the target area is modified.

In a second aspect, an embodiment of the present application provides an information correction device, including:

a display module, used for displaying the first text information converted and generated according to the first voice information in the target area in the information editing interface;

a processing module, configured to display corresponding candidate words in the candidate information area in the information editing interface according to the received first input;

a target determination module, configured to obtain first indication information according to a user's operation in the candidate information area, where the first indication information is used to indicate a target candidate word in the candidate word;

An information modification module, configured to modify the first text information in the target area according to the target candidate word.

In a third aspect, embodiments of the present application provide an electronic device, the electronic device includes a processor, a memory, and a program or instruction stored on the memory and executable on the processor, the program or instruction being The processor implements the steps of the method according to the first aspect when executed.

In a fourth aspect, an embodiment of the present application provides a readable storage medium, where a program or an instruction is stored on the readable storage medium, and when the program or instruction is executed by a processor, the steps of the method according to the first aspect are implemented .

In a fifth aspect, an embodiment of the present application provides a chip, the chip includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is configured to run a program or an instruction, and implement the first aspect the method described.

In a sixth aspect, an embodiment of the present application provides a computer program product, the computer program product is stored in a non-volatile storage medium, and the computer program product is executed by at least one processor to implement the first aspect. method described.

In a seventh aspect, an embodiment of the present application provides an electronic device, where the electronic device is configured to execute the method described in the first aspect.

In the embodiment of the present application, by converting the user's input into the corresponding pinyin information, and developing candidate words for the pinyin, the user can easily correct the recognition errors that occur during voice input, and quickly and accurately obtain the desired input. content, improve the efficiency of voice input, and improve the user experience.

Description of drawings

Fig. 1 is one of the flow charts of the information correction method of the embodiment of the present application;

Fig. 2 is one of the schematic diagrams of the voice input interface of the embodiment of the present application;

3 is one of the schematic diagrams of the information editing interface under the correction mode of the embodiment of the present application;

4 is one of the schematic diagrams of the deletion operation of the information editing interface under the correction mode of the embodiment of the present application;

5 is one of the schematic diagrams of the process of determining target candidate words in the correction mode of the embodiment of the present application;

6 is the second schematic diagram of the process of determining target candidate words in the correction mode according to the embodiment of the present application;

7 is one of the schematic diagrams of the completion of the correction in the correction mode of the embodiment of the present application;

FIG. 8 is the second flow chart of the information correction method according to the embodiment of the present application;

9 is the second schematic diagram of the voice input interface according to the embodiment of the present application;

10 is the second schematic diagram of the information editing interface in the correction mode of the embodiment of the present application;

11 is the second schematic diagram of the deletion operation of the information editing interface in the correction mode according to the embodiment of the present application;

12 is the third schematic diagram of the process of determining the target candidate word in the correction mode according to the embodiment of the present application;

13 is the second schematic diagram of the completion of the correction in the correction mode of the embodiment of the present application;

FIG. 14 is the third flowchart of the information correction method according to the embodiment of the present application;

15 is a block diagram of a display device according to an embodiment of the present application;

16 is a block diagram of an electronic device according to an embodiment of the present application;

FIG. 17 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present application.

Detailed ways

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application.

The terms "first", "second" and the like in the description and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It is to be understood that the data so used are interchangeable under appropriate circumstances so that the embodiments of the present application can be practiced in sequences other than those illustrated or described herein, and distinguish between "first", "second", etc. The objects are usually of one type, and the number of objects is not limited. For example, the first object may be one or more than one. In addition, "and/or" in the description and claims indicates at least one of the connected objects, and the character "/" generally indicates that the associated objects are in an "or" relationship.

In order to enable those skilled in the art to better understand the embodiments of the present application, the following description is first provided.

Multi-level candidate: The user inputs a series of correct pinyin, but the desired sentence is not in the candidate list, and needs to select lower-level words one by one to form the desired sentence. This step-by-step selection process is called multi-level selection. level candidate.

Multi-order words (n-gram): We call a word with a more complete meaning a unigram or a first-order word. Such as "beauty", "Hangzhou", "Gongchen Bridge" and so on. A word composed of N single-order words is called a multi-order word. For example, "Hangzhou Gongchen Bridge" consists of two single-order words, which is the second-order word (bigram) in the multi-order word.

Higher-order words and second-order words: This is a related concept. If a multi-order word A is composed of other multi-order words or single-order words, then A is the higher-order word of these other words, other These words are the second-order words of A, also called the lower-order words of A. For example, "Hangzhou Gongchen Bridge" is a higher-order word of "Hangzhou", and "Hangzhou" and "Gongchen Bridge" are both secondary words of "Hangzhou Gongchen Bridge".

Weighted Finite State Transducer (WFST): It is an efficient white-box model. The built model can automatically select a path that meets each input condition according to a series of inputs, from the initial state to the end state, and output the sequences on these paths in turn. It can be used to realize the functions of pinyin characters to vocabulary, vocabulary to sentences and so on. In addition, multiple models can also be combined into one to efficiently achieve the effect of cascading multiple models, such as the direct translation of Pinyin characters into sentences.

The information correction method, apparatus, and electronic device provided by the embodiments of the present application will be described in detail below with reference to the accompanying drawings through specific embodiments and application scenarios thereof.

As shown in FIG. 1 , an embodiment of the present application provides an information correction method, including:

Step 11: Display the first text information converted and generated according to the first voice information in the target area in the information editing interface.

Here, after the user uses the voice input method to input a whole sentence of voice, the text recognized according to the voice is directly displayed on the screen and displayed in the target area, which can give full play to the advantage of fewer voice input buttons.

Step 12: Display the corresponding candidate words in the candidate information area in the information editing interface according to the received first input.

Here, when the user finds that the text recognized by the voice is different from the text that he wants to input and needs to be corrected, the correction mode can be triggered by the user's operation, such as triggering by the user clicking or long-pressing the text in the target area. In the correction mode, the recognized characters can be corrected according to the received first input.

For example, when the first input is a voice, the user can perform a correction operation according to the voice. According to the voice input by the user at this time (ie, the second voice information), candidate words are converted and generated for the user to select. Specifically, in the correction mode, the voice recognition of the desired word input by the user by using the voice can be converted into pinyin, and then multi-level candidate words can be expanded according to the pinyin for the user to select the correct target candidate word in multiple levels.

For another example, if the first input is second text information selected by the user in the target area, pinyin recognition may be performed according to the second text information, and candidate words corresponding to the second target pinyin are displayed for the user to select.

Step 13: Obtain first indication information according to the user's operation in the candidate information area, where the first indication information is used to indicate a target candidate word in the candidate words.

In this step, the first indication information may be obtained according to operations such as a single click or a long press of the user. For example, the first indication information is obtained when the user clicks a candidate word, and the candidate word selected by the user's click is used as the target candidate word.

Step 14: Modify the first text information in the target area according to the target candidate word.

It should be noted that since there are about 407 Chinese pinyin, even if the tones are counted, it is much less than the more than 30,000 Chinese characters. Therefore, the accuracy of phonetic conversion is relatively high.

The embodiments of the present application take advantage of the above features, when the user inputs the desired text using the voice input method, the voice input by the user is converted into text and directly displayed on the screen, which can give full play to the advantage of fewer voice input buttons. When the user needs to modify the text after the screen is displayed, the correction mode can be turned on. In this mode, the user can still input the pronunciation of the desired word or sentence by voice. At this time, the present embodiment will not convert the speech recognition into Chinese characters and directly display it on the screen, but first adopts the speech recognition mode to identify the corresponding pinyin of the speech, and then expands multi-level candidate words for the user to select according to these pinyin. In this way, by converting the speech information into candidate words, the user can select the target candidate word through a multi-level candidate method, without having to press many keys to correct the text through pinyin input, avoid interrupting the rhythm of the speech input, and improve the speech input efficiency.

Optionally, the information modification method further includes: determining that the first target position is located between the text information displayed in the target area, or the first target position in the target area, according to the user's operation in the information editing interface. When the second text information is selected, the correction mode is enabled; wherein, the first text information in the target area includes the second text information.

For example, when the user moves the cursor to a position that needs to be corrected in the target area, or when the user presses the text in the target area for a long time, the correction mode can be turned on.

Optionally, the displaying the corresponding candidate words in the candidate information area in the information editing interface according to the received first input includes: obtaining the first target pinyin according to the received second voice information; The first target pinyin is described, and the candidate words corresponding to the second phonetic information are displayed in the candidate information area.

Specifically, since the language model module included in WFST can make pinyin-to-phrase conversion to a better level, this embodiment of the present application can use WFST to convert pinyin to vocabulary and then convert to phrases to provide candidate words for users, and according to the weight (for example, rank order) order, probability, etc.) to rank candidate words from high to low. It should be noted that these candidate words not only include high-order words that match all pinyin, but also high-frequency and low-order words that match part of pinyin. In this way, the user can avoid the tediousness of inputting the pinyin of each low-level word by pressing the keyboard step by step, and also avoid the problem that the selection cost increases due to the large ambiguity of short words. Therefore, the words desired by the user can be obtained more quickly to correct the erroneous text.

In this embodiment, fewer user operations are required for input, and it is suitable for correcting relatively long input phrases (such as between 2nd and 4th order), and relatively short words with high frequency (usually 1, 2 order, a few words of order 3). The user can select the target candidate word that he wants to input from the candidate words of each order, and this process may require multi-level consumption of pinyin to complete.

It should be noted that, in the process of determining the first target pinyin according to the second speech information, the user can confirm whether the pinyin converted by speech recognition is correct. Optionally, the received second voice information is converted into corresponding pinyin information, and displayed in the pinyin information area in the information editing interface. That is to say, the pinyin recognized and converted according to the second voice information can be displayed in a certain area (such as the pinyin information area) in the information editing interface, and the user can edit and modify the pinyin in this area. At this time, the pinyin displayed in this area can be used as the first target pinyin, and the candidate words corresponding to the first target pinyin are displayed in the candidate information area. In this way, in the process of confirming pinyin, if the user finds that the pinyin recognition is wrong, he can modify it through the keyboard; if he finds that the pinyin recognition is correct, he can directly confirm the target candidate word in the candidate information area.

In this embodiment, the confirmation operation for the target candidate word may be that when the user clicks on the candidate word, the candidate word replaces the pinyin information corresponding to the candidate word and displays it in the pinyin information area until the pinyin information is displayed in the pinyin information area. When all the pinyin information in the information area is replaced, the candidate word in the pinyin information area is used as the target candidate word.

For example, in the correction mode, after identifying and transforming the pronunciation of the user's voice input of "epidemic prevention materials", the string of pinyin fang'yi'wu'zi is displayed in the "pinyin information area", and the "Put a room" is displayed in the candidate information area. ", "epidemic prevention" and "overflow prevention" and other candidate words, after the user clicks "epidemic prevention", the pinyin "fang'yi" is consumed, and the "pinyin information area" is displayed as epidemic prevention wu'zi, and enters the secondary selection. The candidate information area displays the candidate words corresponding to "wu'zi" such as "house" and "materials". After the user clicks on "materials", all the pinyin strings of fang'yi'wu'zi are consumed, and "epidemic prevention" and "" The word composed of "materials" is confirmed as the target candidate word, and it is directly displayed on the screen at the target position.

Optionally, the displaying the corresponding candidate words in the candidate information area in the information editing interface according to the received first input includes: according to the received second voice information and preset rules, in the The candidate information area displays candidate words corresponding to the second voice information;

Wherein, the preset rule includes: when the candidate word is a phrase, displaying the higher-order word in the candidate word before the lower-order word, and displaying the second-order word of the higher-order word Before the same-order words of the second-order words; the number of words contained in the higher-order words is greater than the number of words contained in the lower-order words, the number of words contained in the two same-order words is the same, and the second-order words of the higher-order words contain the same number of words. The first-order word is the word contained in the higher-order word; the second voice information is the phonetic information corresponding to the higher-order word including the target candidate word; the first indication information is obtained according to the long-press operation Instructions.

For example, when the user needs to input the word "dominant", instead of directly inputting the "dominant" voice, it is better to input the voice of "dominant gene", which makes it easier to obtain the candidate word "dominant". In this embodiment, the first indication information is obtained according to the user's long-pressing on the candidate word, and the candidate word selected by the user's long-pressing is used as the target candidate word.

It should be noted that, in the case where the words that the user needs to input are less common and shorter, according to the theory of the language model, the more words that constitute a sentence, the lower the ambiguity, and the number of high-level candidate words that need to be selected is will be less. That is, the longer and more commonly used phrases are entered, the lower the cost of the selection operation.

Therefore, for a first-order one-character word or two-character word, if the word is not commonly used, you can use voice to input a longer common word containing this word, and the common word is a high-level word containing the word you want to input. Then the user can select the second-order word corresponding to the higher-order word (that is, the word that the user wants) from the multi-order candidate words and directly display it on the screen. This second-order word can be obtained accurately and quickly with the help of the input longer word.

Specifically, in this embodiment, the language model in the correction mode will give a greater weight to the more common combination, so that it ranks at the top of the candidate words. According to the preset rules, the same-order words are not completely sorted by probability, but the second-order words contained in the higher-order words can appear in front of the words of the same order as this second-order word. For example, the single-order word "epidemic prevention" is part of the higher-order word "epidemic prevention measures", so among many first-order words, "epidemic prevention" is guaranteed to come before words such as "put one" or "overflow prevention".

Optionally, the information correction method further includes: converting the received second voice information into corresponding pinyin information, and displaying the information in the pinyin information area in the information editing interface.

For example, after inputting the voice of "dominant gene", the user can identify and convert the pinyin "xian'xing'ji'yin" according to the "dominant gene", and display the pinyin in the pinyin information area, and the pinyin corresponds to The candidate words of are displayed in the candidate information area.

For example, after the user enters the voice of "dominant gene", in the candidate words, after finding the low-order word "dominant" and long-pressing, "dominant" is directly displayed on the screen and displayed at the target position, and the redundant pinyin "ji" 'yin' can be discarded. In this way, multiple pressing of the keyboard to input pinyin can be avoided, and the desired word can be obtained more quickly, thereby improving the input efficiency.

Optionally, the displaying the corresponding candidate words in the candidate information area in the information editing interface according to the received first input includes: when the second text information in the target area is selected, According to the second text information, determine the second target pinyin; according to the second target pinyin, display the candidate words corresponding to the second target pinyin in the candidate information area; wherein, the first target in the target area A text message includes the second text message.

For example, after a user enters a sentence with voice, he finds that the "house" in the text "now the house is full" converted by voice recognition is incorrectly recognized. The correct text should be "materials", and the user can long press " house". According to the user's long-press operation, the selected word "house" is identified and converted into its pinyin "wu'zi", and the candidate words corresponding to "wu'zi" such as "house" and "materials" are displayed in the candidate information area. After selecting "Material", the word "Material" will replace the word "House" selected by the user in the target area.

Optionally, the modifying the first text information in the target area according to the target candidate word includes: deleting the text information corresponding to the second indication information in the target area through the deletion control; For the second indication information, a second target position is determined, and target candidate words are displayed at the second target position; wherein, the second indication information is obtained according to the user's operation in the target area.

For example, the second indication information can be obtained according to the user's operation of clicking "delete control k2 forward" or "delete control k3 backward" on the candidate information area, and delete the text in the target area with a recognition error. Specifically, the character in at least one adjacent position of the target position in the information editing interface can be deleted through the delete control.

Optionally, the information correction method further includes: according to the third indication information, locating to the end of the sentence of the text information in the target area, and exiting the correction mode.

Here, the third indication information may be obtained according to the operation of the user clicking the "correction completion confirmation control k1" on the candidate information area. The user can conveniently move the cursor to the end of the paragraph by using the "correction completion confirmation control k1" to exit the correction mode.

Optionally, before correcting the first text information in the target area according to the target candidate word, the information correction method further includes: displaying a deletion control and a correction completion confirmation control k1 on the candidate information area, The deletion control includes at least one of forward deletion control k2 and backward deletion control k3;

Wherein, the forward deletion control k2 is used to receive an instruction to delete the character at the left adjacent position of the first target position in the information editing interface;

The backward deletion control k3 is used to receive an instruction to delete the character at the adjacent position on the right side of the first target position in the information editing interface;

The correction completion confirmation control k1 is used to receive an instruction to move the cursor to the end of the sentence of the text information in the target area;

The first target position is determined according to the user's operation in the information editing interface.

In this embodiment, the characters at the left adjacent position of the target position in the information editing interface can be deleted by forwardly deleting the control k2; the characters at the right adjacent position of the target position in the information editing interface can be deleted by backward deleting the control k3 ;The cursor can be moved to the end of the text message in the target area by modifying the completion confirmation control k1.

That is to say, in the correction mode, in addition to the pinyin keyboard and the voice keys, a backward deletion control k3 is also provided. When the user needs to delete the wrong word segment on the upper screen (that is, the characters adjacent to the target position in the information editing interface), in addition to forward deletion, the text adjacent to the target position can also be deleted backward.

The correction mode also provides a "correction completion confirmation control k1", which can exit the correction mode and return to the normal mode with one key. For example, after the user has corrected all the wrong words, press the "correction completion confirmation control k1" to move the cursor to the end of the sentence in the target area, ready to start a new input. This type of shortcut keys can effectively improve input efficiency.

In order to facilitate intuitive understanding of the embodiments of the present application, the embodiments of the present application are explained below in a graphical manner.

Example 1:

As shown in Figures 2 to 7, the user wants to input a sentence: "Now the home is full of anti-epidemic materials".

As shown in Figure 2, the user uses the voice input method to read a whole sentence of speech, and then the speech is mistakenly recognized as "the house is full now", and the recognized text is directly displayed on the screen. At this time, the user finds that "put in a room" is different from the text he wants to enter, and needs to be corrected.

As shown in Figure 3, the cursor can be moved to the error position, and the correction mode is triggered at this time. In this mode, you can press "delete control k2 forward" or "delete control k3 backward" as shown in Figure 3 to delete the text that has a recognition error. In this way, at least one adjacent character at the target position can be easily deleted.

As shown in Figure 4, after deleting the wrong text, the target area in the information editing interface is displayed as "now the house is full". At this time, in order to correctly input the words "epidemic prevention materials", users can click the voice recognition button below and still use voice to input "epidemic prevention materials".

As shown in FIG. 5 , the speech recognition engine at this time may share most of the modules with the speech recognition engine in the normal mode, or may be two independent engines. For example, the engine of the correction mode is specially optimized for the phonetic-to-pinyin conversion, which can ensure a higher accuracy rate when the engine converts the phonetic to pinyin. For the string of pinyin fang'yi'wu'zi, this application can use the WFST model to convert the string of pinyin into many multi-level words, for example, "put a room" is a bigram, which consists of two words "put one" and "room" composed of single-order words. At the same time, it will also be transformed into some low-level words, such as the single-level words "epidemic prevention" and "overflow prevention". At this time, since there is no "epidemic prevention material" but only "epidemic prevention" in the interface shown in Figure 5, the user can first select the word "epidemic prevention" at this level (for example, by clicking on the word to select), and consume the corresponding pinyin After "fang'yi", the pinyin "wu'zi" remains.

As shown in Figure 6, after selecting "epidemic prevention", enter the second-level selection interface. At this time, you can select the word "materials" to consume the corresponding pinyin "wu'zi", because "fang'yi'wu'zi" This string of pinyin has been used up, and the "epidemic prevention" and "materials" selected by the user can be displayed on the screen. It should be noted that the more common the phrase entered through the voice, the higher the probability that the language model will rank the multi-order word or single-order word corresponding to the phrase in the front. If the user thinks that all the words have been corrected at this time, he can press the "correction completion confirmation control k1" shown in Figure 6, and the cursor can be conveniently moved to the end of the paragraph to automatically exit the correction mode.

As shown in Figure 7, after exiting the correction mode, press the voice recognition key again to start a new voice input.

In this embodiment, a multi-level candidate function is added to the voice input method, and when correcting a small inaccurate segment of a sentence (or a sentence input through the Pinyin input method) recognized by the voice, the voice input method is used After inputting the voice of the desired word, the voice recognition is converted into pinyin, and then multi-level candidate words are expanded according to the pinyin, so that the user can select the correct target candidate word in multiple levels.

The flow chart of the above embodiment is shown in Figure 8, which specifically includes the following steps:

Step 801 : the voice input by the user (usually a sentence) is recognized by voice, and the recognition is converted into text and then directly displayed on the screen, which can give full play to the advantage of fewer keys for voice input.

Step 802: Check whether there is any wrong word in the text on the upper screen; if there is no error, go to Step 803; if there is an error, go to Step 804.

Step 803: Continue to input the next sentence by voice.

Step 804: Locate (by moving the cursor) the target position, that is, one of the wrong words. When the cursor is moved to the wrong word, the correction mode is activated. In this mode, in addition to the "forward delete control k2", a button that can delete the text backward (ie "backward delete control k3") is provided, This makes it easier to remove erroneous text.

Step 805: Input the voice corresponding to the text to be input by voice.

Step 806: The optimized speech recognition engine in the embodiment of the present application mainly converts phrases rather than long sentences, and instead of directly converting the speech into Chinese characters, it first converts the speech into Pinyin. The reason for adopting this conversion method is that there are only about 407 different Chinese pinyin, even if the tones are counted, it is much less than the more than 30,000 Chinese characters. Therefore, the accuracy rate of converting the phonetic into a pinyin string is relatively high. It is easier than converting to a Chinese character string.

Step 807: The user can confirm whether the pinyin converted by speech recognition is correct; if it is correct, go to Step 809, otherwise, go to Step 808;

Step 808: If the pinyin recognition is wrong, the user can still modify it through the keyboard. Of course, this should be avoided as much as possible, as it will increase the number of keystrokes.

Step 809: For the correct pinyin (ie, the first target pinyin), the trained WFST can convert the pinyin into multi-order candidate words, and arrange them according to the weight (such as order, probability, etc.) from high to low. This WFST can be a composite of two models: the pinyin-to-first-order vocabulary, and the WFST language model of the vocabulary.

Step 810: According to the candidate words, the user can select a word as long as possible that is consistent with the target word by clicking the candidate word, and consume the corresponding pinyin until all the pinyin is consumed, and the desired word is displayed on the screen.

Step 811: Determine whether all the pinyin has been consumed; if yes, go to step 812; if not, go to step 810, that is, continue to select candidate words and consume the corresponding pinyin.

Step 812: When all the pinyin is exhausted, complete the screen of the word or phrase you want to input.

Step 813: The user can continue to confirm whether the text in the target area in the information editing interface is correct or not, and check whether there are other incorrect segments in the sentence. If yes, go to step 804; if not, go to step 814. That is to say, when there are multiple errors in the sentence, steps 804 to 813 can be executed repeatedly until all the error segments of the sentence are corrected.

Step 814: When the user confirms that the sentence has been corrected, he can press the "correction completion confirmation control k1", at this time, the cursor will automatically move to the end of the text in the target area, ready to start the input of the next sentence, so as to avoid moving the cursor. Positioning operation.

In the above embodiment, if there is one error in total, it is necessary to move the cursor once, enter the voice once, and press the key seven times. Among them, the 7 key operations include 4 deletions of the wrong word (respectively delete "put", "one", "house", "zi"), 1 voice button and 2 two-level word selection. Relatively speaking, if you use the Pinyin input method to input a string of text input by the above voice, even using Jianpin will require a lot of keystrokes; if you use the traditional phonetic input method, you need to move the cursor to the wrong word, and then use the keyboard to input Pinyin to Correction, also requires a lot of keystrokes and interrupts the rhythm of voice input. In the embodiment, most of the operations are used in voice and word selection, and the number of keystrokes is reduced to a lower number, so that a correct sentence input can be obtained with less positioning and keystrokes, thereby making the voice input more efficient. promote. The user can quickly correct the wrong words in the text through the information correction method provided in this application, so as to achieve the purpose of quickly and accurately inputting large pieces of text.

Embodiment 2:

As shown in Figures 7 and 9 to 13, it is assumed that the user still wants to input: "Now the home is full of anti-epidemic materials".

As shown in Figure 9, the user uses the voice input method to input a piece of speech. Suppose it is mistakenly recognized as "now the house is full of translation materials", and the recognized text is directly displayed on the screen. At this time, the user finds that the "translation" is different from the desired text and needs to be corrected.

As shown in Figure 10, the cursor can be moved to the error position, and the correction mode is triggered at this time. The user can delete the word "translation" through the "delete control k2 forward".

As shown in Figure 11, after deleting the wrong text, the interface is displayed as shown in Figure 11, and the target area in the information editing interface is displayed as "Now the house is full of supplies". In order to correctly enter the word "epidemic prevention", users can click the voice recognition button below to re-enter the voice. At this time, in order to improve the probability of the word "epidemic prevention", users can choose to input "epidemic prevention measures" by voice instead of directly inputting the voice of "epidemic prevention".

As shown in Figure 12, after the user enters the voice of "epidemic prevention measures", for the identified string of pinyin fang'yi'cuo'shi, the WFST model can be used to convert the string of pinyin into many multi-level words, such as "epidemic prevention measures". "Measures" is a bigram consisting of "epidemic prevention" and "measures", and at the same time, it will also be transformed into some low-level words, such as "epidemic prevention" and "put one" are single-level words. Usually, high-order words are always arranged in front of low-order words; and in words of the same order, the sorting is mainly based on the probability of the WFST model. However, in this embodiment, according to the preset rules, the same-order words are not completely sorted by probability, but the second-order words contained in the higher-order words can appear in front of the words of the same order as this second-order word. For example, the single-order word "epidemic prevention" is part of the higher-order word "epidemic prevention measures", so among many first-order words, "epidemic prevention" will be guaranteed to be ranked in words such as "put one" or "overflow prevention" in front of.

As shown in Figure 13, the user long presses the target candidate word "epidemic prevention", the purpose is to make the word "epidemic prevention" directly on the screen to complete the input of the correct word. During this process, the unconsumed pinyin "cuo'shi" will be automatically ignored. It should be noted that the more common the phrase entered by the voice, the higher the probability that the language model will ensure that the word and its subordinate words appear. If the user thinks that all the words have been corrected at this time, he can press the "correction completion confirmation control k1" shown in Figure 13, and the cursor can be conveniently moved to the end of the paragraph to automatically exit the correction mode.

The flow chart of the above embodiment is shown in Figure 14, which specifically includes the following steps:

Step 1401: Voice recognition of the voice input by the user (usually a sentence), and the recognition is converted into text and directly displayed on the screen.

Step 1402: Check whether there is any wrong word in the text on the upper screen; if there is no error, go to Step 1403; if there is an error, go to Step 1404.

Step 1403: Continue to input the next sentence by voice.

Step 1404: Move the cursor to locate the target position, that is, one of the wrong words. When the cursor is moved to the wrong word, the correction mode is activated, and in this mode, the wrong word can be deleted forward or backward at the target position (ie, adjacent to the target position).

Step 1405: When inputting an uncommon low-order word (usually 1st-order or 2nd-order), in order to improve the word probability of the word, the user can choose to input a high-order word (the more Commonly used as possible) speech instead of directly entering the low-order word. The language model will give more weight to the more common combinations, ranking them higher in the candidate words.

Step 1406: The optimized speech engine converts the speech input by the user into corresponding pinyin.

Step 1407: For the identified correct pinyin, the WFST model will convert it into many multi-level words. For example, "epidemic prevention measures" is a second-order word consisting of "epidemic prevention" and "measures", "put one" and "epidemic prevention". " is a single-order word. Usually, high-order words always appear in front of low-order words. In words of the same order, the sorting is mainly based on the probability of the WFST model. In the embodiment of the present application, according to a preset rule, the second-order words included in the higher-order words in the candidate words are arranged in front of other candidate words of the same order as this second-order word. Here, it is precisely with the help of high-order words that there is a high probability of ranking in the front, so that the second-order words of the high-order word have the opportunity to appear in a higher position in the candidate words with the help of the correct probability of the high-order word. Of course, it is understandable that the second-order word is only ranked at the top of its same-order words, and it is still ranked at the back of other high-order words.

Step 1408: Determine whether there is a word that the user wants in the second-order words in the candidate words; if yes, go to Step 1410; if not, the user can choose to modify the pinyin, that is, go to Step 1409, or can use voice to re-input other words. Step 1405 is executed to include the speech corresponding to the commonly used higher-order words of the words to be input.

Step 1409: The user can modify the pinyin through the keyboard.

Step 1410: Since the user has found the desired word from the candidate words, although there are still redundant pinyin not consumed at this time, the mission of these redundant pinyin (ie, helping to find the word that the user needs) has been completed. Therefore, the user can press and hold the target candidate word to make it appear on the screen directly, and the pinyin that is not consumed will be ignored, so that the input of the correct word can be completed.

Step 1411: The user can continue to confirm whether the text in the target area in the information editing interface is correct or not, and check whether there are other incorrect segments in the sentence. If yes, go to step 1404; if not, go to step 1412.

Step 1412: When the user confirms that the sentence has been corrected, he can press the "correction completion confirmation control k1", at this time, the cursor will automatically move to the end of the text in the target area, ready to start the input of the next sentence, so as to avoid moving the cursor. Positioning operation.

The information correction method provided in this embodiment is more suitable for correcting the input of less common shorter words (usually 1st-order or 2nd-order words, and may also be a few 3rd-order words). For uncommon words, in extreme cases, users even need to rely on the pinyin of each word to find the words they need one by one, which is very laborious. The present application can prevent the user from searching for the desired word at a very late position in the candidate word list, thereby improving the input efficiency.

Through a large number of tonal pinyin and the corresponding speech data, the speech recognition engine of the correction mode is optimized. The engine can be simpler than the normal mode, but it can be optimized for the conversion of phonetic pinyin, so that the accuracy rate of pinyin conversion is higher. Level. Therefore, it can also be considered that the corresponding voice information input by the user is attached beside the text after voice recognition and correction. In this way, on the one hand, the information receiver can confirm the accuracy of the text, and on the other hand, it can also provide a very good parallel corpus, and the parallel corpus can be used to improve the accuracy of the user's speech engine.

In the embodiment of the present application, the pinyin of the word or short sentence to be input is obtained through voice input, and the Chinese character corresponding to the pinyin is selected by using multi-level candidates and high-level word auxiliary candidates, which is easy to operate.

It should be noted that, in the information correction method provided by the embodiments of the present application, the execution body may be an information correction device, or a control module in the information correction device for executing the information correction method. In the embodiment of the present application, the information correction device provided by the embodiment of the present application is described by taking the information correction device executing the information correction method as an example.

As shown in FIG. 15 , an embodiment of the present application further provides an information correction apparatus 1500, including:

The display module 1501 is used to display the first text information converted and generated according to the first voice information in the target area in the information editing interface;

The processing module 1502 is configured to display the corresponding candidate words in the candidate information area in the information editing interface according to the received first input;

A target determination module 1503, configured to obtain first indication information according to the user's operation in the candidate information area, where the first indication information is used to indicate the target candidate word in the candidate word;

The information modification module 1504 is configured to modify the first text information in the target area according to the target candidate word.

Optionally, the processing module 1502 includes:

a first processing unit, configured to obtain the first target pinyin according to the received second voice information;

The second processing unit is configured to display the candidate words corresponding to the second voice information in the candidate information area according to the first target pinyin.

Optionally, the processing module 1502 includes:

a third processing unit, configured to display the candidate words corresponding to the second voice information in the candidate information area according to the received second voice information and a preset rule;

Wherein, the preset rule includes: when the candidate word is a phrase, displaying the higher-order word in the candidate word before the lower-order word, and displaying the second-order word of the higher-order word Before the same-order words of the second-order words; the number of words contained in the higher-order words is greater than the number of words contained in the lower-order words, the number of words contained in the two same-order words is the same, and the second-order words of the higher-order words contain the same number of words. An order word is a word contained in the higher order word;

The second voice information is the voice information corresponding to the higher-order words including the target candidate words;

The first indication information is indication information obtained according to a long-press operation.

Optionally, the processing module 1502 includes:

a fourth processing unit, configured to determine a second target pinyin according to the second text information when the second text information in the target area is selected;

a fifth processing unit, configured to display candidate words corresponding to the second target pinyin in the candidate information area according to the second target pinyin;

Wherein, the first text information in the target area includes the second text information.

Optionally, the information correction apparatus 1500 further includes:

a control display module, configured to display a deletion control and a correction completion confirmation control on the candidate information area, the deletion control includes at least one of a forward deletion control and a backward deletion control;

Wherein, the forward deletion control is used to receive an instruction to delete the character at the left adjacent position of the first target position in the information editing interface;

The backward deletion control is used to receive an instruction to delete the character at the right adjacent position of the first target position in the information editing interface;

The correction completion confirmation control is used to receive an instruction to move the cursor to the end of the sentence of the text information in the target area;

Optionally, the information correction module 1504 includes:

a first correction unit, configured to delete the text information corresponding to the second indication information in the target area through the deletion control;

a second correction unit, configured to determine a second target position according to the second indication information, and display the target candidate word at the second target position;

Wherein, the second indication information is obtained according to the user's operation in the target area.

The information correction device in this embodiment of the present application may be a device, or may be a component, an integrated circuit, or a chip in a terminal. The apparatus may be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device may be a mobile phone, a tablet computer, a notebook computer, a palmtop computer, an in-vehicle electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (personal digital assistant). assistant, PDA), etc., non-mobile electronic devices can be servers, network attached storage (Network Attached Storage, NAS), personal computer (personal computer, PC), television (television, TV), teller machine or self-service machine, etc., this application Examples are not specifically limited.

The information correction device in the embodiment of the present application may be a device with an operating system. The operating system may be an Android (Android) operating system, an ios operating system, or other possible operating systems, which are not specifically limited in the embodiments of the present application.

The information correction apparatus provided in this embodiment of the present application can implement each process implemented by the method embodiments in FIG. 1 to FIG. 14 , and to avoid repetition, details are not repeated here.

Optionally, as shown in FIG. 16, an embodiment of the present application further provides an electronic device 1600, including a processor 1602, a memory 1601, a program or instruction stored in the memory 1601 and executable on the processor 1602, When the program or instruction is executed by the processor 1602, each process of the above-mentioned information correction method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, details are not described here.

It should be noted that the electronic devices in the embodiments of the present application include the aforementioned mobile electronic devices and non-mobile electronic devices.

FIG. 17 is a schematic diagram of a hardware structure of an electronic device implementing an embodiment of the present application.

The electronic device 1700 includes but is not limited to: a radio frequency unit 1701, a network module 1702, an audio output unit 1703, an input unit 1704, a sensor 1705, a display unit 1706, a user input unit 1707, an interface unit 1708, a memory 1709, and a processor 1710, etc. part.

Those skilled in the art can understand that the electronic device 1700 may also include a power source (such as a battery) for supplying power to various components, and the power source may be logically connected to the processor 1710 through a power management system, so as to manage charging, discharging, and power consumption through the power management system. consumption management and other functions. The structure of the electronic device shown in FIG. 17 does not constitute a limitation on the electronic device. The electronic device may include more or less components than those shown in the figure, or combine some components, or arrange different components, which will not be repeated here. .

The processor 1710 is configured to display the first text information converted and generated according to the first voice information in the target area in the information editing interface; according to the received first input, display in the candidate information area in the information editing interface corresponding candidate words; first indication information is obtained according to the user's operation in the candidate information area, and the first indication information is used to indicate the target candidate words in the candidate words; The first text information in the target area is modified.

Optionally, when displaying the corresponding candidate words in the candidate information area in the information editing interface according to the received first input, the processor 1710 is further configured to: obtain the first voice information according to the received second voice information target pinyin; according to the first target pinyin, display the candidate words corresponding to the second voice information in the candidate information area.

Optionally, when displaying the corresponding candidate words in the candidate information area in the information editing interface according to the received first input, the processor 1710 is further configured to: according to the received second voice information and preset rules , displaying the candidate words corresponding to the second voice information in the candidate information area;

Optionally, when displaying the corresponding candidate words in the candidate information area in the information editing interface according to the received first input, the processor 1710 is further configured to: the second text information in the target area is In the case of selection, according to the second text information, determine the second target pinyin;

According to the second target pinyin, the candidate words corresponding to the second target pinyin are displayed in the candidate information area;

Optionally, before correcting the first text information in the target area according to the target candidate word, the processor 1710 is further configured to: display a delete control and a correction completion confirmation control on the candidate information area, so that The deletion control includes at least one of forward deletion control and backward deletion control;

Optionally, when the processor 1710 corrects the first text information in the target area according to the target candidate words, the processor 1710 is further configured to: use the delete control to modify the text corresponding to the second indication information in the target area information is deleted; according to the second indication information, a second target position is determined, and target candidate words are displayed in the second target position; wherein, the second indication information is obtained according to the user's operation in the target area.

It should be understood that, in this embodiment of the present application, the input unit 1704 may include a graphics processor (Graphics Processing Unit, GPU) 17041 and a microphone 17042. Such as camera) to obtain still pictures or video image data for processing. The display unit 1706 may include a display panel 17061, which may be configured in the form of a liquid crystal display, an organic light emitting diode, or the like. The user input unit 1707 includes a touch panel 17071 and other input devices 17072 . The touch panel 17071 is also called a touch screen. The touch panel 17071 may include two parts, a touch detection device and a touch controller. Other input devices 17072 may include, but are not limited to, physical keyboards, function keys (such as volume control keys, switch keys, etc.), trackballs, mice, and joysticks, which will not be repeated here. Memory 1709 may be used to store software programs as well as various data including, but not limited to, application programs and operating systems. The processor 1710 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and application programs, and the like, and the modem processor mainly handles wireless communication. It can be understood that, the above-mentioned modulation and demodulation processor may not be integrated into the processor 1710.

Embodiments of the present application further provide a readable storage medium, where a program or an instruction is stored on the readable storage medium, and when the program or instruction is executed by a processor, each process of the above information modification method embodiment can be achieved, and the same can be achieved. In order to avoid repetition, the technical effect will not be repeated here.

Wherein, the processor is the processor in the electronic device described in the foregoing embodiments. The readable storage medium includes a computer-readable storage medium, such as a computer read-only memory (Read-Only Memory, ROM), a random access memory (Random Access Memory, RAM), a magnetic disk or an optical disk, and the like.

An embodiment of the present application further provides a chip, where the chip includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is configured to run a program or an instruction to implement the information modification method embodiments described above. Each process can achieve the same technical effect. In order to avoid repetition, it will not be repeated here.

It should be understood that the chip mentioned in the embodiments of the present application may also be referred to as a system-on-chip, a system-on-chip, a system-on-a-chip, or a system-on-a-chip, or the like.

An embodiment of the present application further provides a computer program product, where the computer program product is stored in a non-volatile storage medium, and the computer program product is executed by at least one processor to implement each of the foregoing information correction method embodiments process, and can achieve the same technical effect, in order to avoid repetition, it will not be repeated here.

The embodiment of the present application further provides an electronic device, which is configured to execute each process of the above-mentioned information correction method embodiment, and can achieve the same technical effect. To avoid repetition, details are not described here.

It should be noted that, herein, the terms "comprising", "comprising" or any other variation thereof are intended to encompass non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements, It also includes other elements not expressly listed or inherent to such a process, method, article or apparatus. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in a process, method, article or apparatus that includes the element. Furthermore, it should be noted that the scope of the methods and apparatus in the embodiments of the present application is not limited to performing the functions in the order shown or discussed, but may also include performing the functions in a substantially simultaneous manner or in the reverse order depending on the functions involved. To perform functions, for example, the described methods may be performed in an order different from that described, and various steps may also be added, omitted, or combined. Additionally, features described with reference to some examples may be combined in other examples.

From the description of the above embodiments, those skilled in the art can clearly understand that the method of the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is better implementation. Based on this understanding, the technical solution of the present application can be embodied in the form of a software product in essence or in a part that contributes to the prior art, and the computer software product is stored in a storage medium (such as ROM/RAM, magnetic disk, CD-ROM), including several instructions to make a terminal (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) execute the methods described in the various embodiments of this application.

The embodiments of the present application have been described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific embodiments, which are merely illustrative rather than restrictive. Under the inspiration of this application, without departing from the scope of protection of the purpose of this application and the claims, many forms can be made, which all fall within the protection of this application.

Claims

An information correction method comprising:

The first text information that is converted and generated according to the first voice information is displayed in the target area in the information editing interface;

According to the received first input, the corresponding candidate word is displayed in the candidate information area in the information editing interface;

Obtain first indication information according to the user's operation in the candidate information area, where the first indication information is used to indicate the target candidate word in the candidate word;

According to the target candidate word, the first text information in the target area is modified.
The information correction method according to claim 1, wherein, according to the received first input, the corresponding candidate words are displayed in the candidate information area in the information editing interface, comprising:

Obtain the first target pinyin according to the received second voice information;

According to the first target pinyin, the candidate words corresponding to the second voice information are displayed in the candidate information area.
The information correction method according to claim 1, wherein, according to the received first input, the corresponding candidate words are displayed in the candidate information area in the information editing interface, comprising:

Display the candidate words corresponding to the second voice information in the candidate information area according to the received second voice information and preset rules;

Wherein, the preset rule includes: when the candidate word is a phrase, displaying the higher-order word in the candidate word before the lower-order word, and displaying the second-order word of the higher-order word Before the same-order words of the second-order words; the number of words contained in the higher-order words is greater than the number of words contained in the lower-order words, the number of words contained in the two same-order words is the same, and the second-order words of the higher-order words contain the same number of words. An order word is a word contained in the higher order word;

The second voice information is the voice information corresponding to the higher-order words including the target candidate words;

The first indication information is indication information obtained according to a long-press operation.
The information correction method according to claim 1, wherein, according to the received first input, the corresponding candidate words are displayed in the candidate information area in the information editing interface, comprising:

In the case that the second text information in the target area is selected, determine the second target pinyin according to the second text information;

According to the second target pinyin, the candidate words corresponding to the second target pinyin are displayed in the candidate information area;

Wherein, the first text information in the target area includes the second text information.
The information modification method according to claim 1, wherein, before modifying the first text information in the target area according to the target candidate word, the information modification method further comprises:

Displaying a deletion control and a correction completion confirmation control on the candidate information area, the deletion control includes at least one of a forward deletion control and a backward deletion control;

Wherein, the forward delete control is used to receive an instruction to delete the character at the left adjacent position of the first target position in the information editing interface;

The backward deletion control is used to receive an instruction to delete the character at the right adjacent position of the first target position in the information editing interface;

The correction completion confirmation control is used to receive an instruction to move the cursor to the end of the sentence of the text information in the target area;

The first target position is determined according to the user's operation in the information editing interface.
The information modification method according to claim 5, wherein the modifying the first text information in the target area according to the target candidate word comprises:

Delete the text information corresponding to the second indication information in the target area through the delete control;

determining a second target position according to the second indication information, and displaying the target candidate word at the second target position;

Wherein, the second indication information is obtained according to the user's operation in the target area.
An information correction device, comprising:

A display module, for displaying the first text information generated according to the first voice information conversion in the target area in the information editing interface;

a processing module, configured to display corresponding candidate words in the candidate information area in the information editing interface according to the received first input;

a target determination module, configured to obtain first indication information according to a user's operation in the candidate information area, where the first indication information is used to indicate a target candidate word in the candidate word;

An information modification module, configured to modify the first text information in the target area according to the target candidate word.
The information correction device according to claim 7, wherein the processing module comprises:

a first processing unit, configured to obtain the first target pinyin according to the received second voice information;

The second processing unit is configured to display the candidate words corresponding to the second voice information in the candidate information area according to the first target pinyin.
The information correction device according to claim 7, wherein the processing module comprises:

a third processing unit, configured to display the candidate words corresponding to the second voice information in the candidate information area according to the received second voice information and a preset rule;

Wherein, the preset rule includes: when the candidate word is a phrase, displaying the higher-order word in the candidate word before the lower-order word, and displaying the second-order word of the higher-order word Before the same-order words of the second-order words; the number of words contained in the higher-order words is greater than the number of words contained in the lower-order words, the number of words contained in the two same-order words is the same, and the second-order words of the higher-order words contain the same number of words. An order word is a word contained in the higher order word;

The second voice information is the voice information corresponding to the higher-order words including the target candidate words;

The first indication information is indication information obtained according to a long-press operation.
The information correction device according to claim 7, wherein the processing module comprises:

a fourth processing unit, configured to determine a second target pinyin according to the second text information when the second text information in the target area is selected;

a fifth processing unit, configured to display the candidate words corresponding to the second target pinyin in the candidate information area according to the second target pinyin;

Wherein, the first text information in the target area includes the second text information.
The information correction device according to claim 7, wherein the information correction device further comprises:

a control display module, configured to display a deletion control and a correction completion confirmation control on the candidate information area, the deletion control includes at least one of a forward deletion control and a backward deletion control;

Wherein, the forward delete control is used to receive an instruction to delete the character at the left adjacent position of the first target position in the information editing interface;

The backward deletion control is used to receive an instruction to delete a character adjacent to the right side of the first target position in the information editing interface;

The correction completion confirmation control is used to receive an instruction to move the cursor to the end of the sentence of the text information in the target area;

The first target position is determined according to the user's operation in the information editing interface.
The information correction device according to claim 11, wherein the information correction module comprises:

a first correction unit, configured to delete the text information corresponding to the second indication information in the target area through the deletion control;

a second correction unit, configured to determine a second target position according to the second indication information, and display the target candidate word at the second target position;

Wherein, the second indication information is obtained according to the user's operation in the target area.
An electronic device, comprising a processor, a memory, and a program or instruction stored on the memory and executable on the processor, wherein the program or instruction is executed by the processor to achieve as claimed in claim 1 Steps of the information correction method described in any one of to 6.
A readable storage medium storing programs or instructions on the readable storage medium, wherein when the programs or instructions are executed by a processor, the steps of the information modification method according to any one of claims 1 to 6 are implemented.
A chip, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or an instruction to implement the information modification method according to any one of claims 1 to 6 .
A computer program product, wherein the program product is stored in a non-volatile storage medium, and the program product is executed by at least one processor to implement the information correction method according to any one of claims 1 to 6 .
An electronic device, wherein the electronic device is configured to perform the information correction method according to any one of claims 1 to 6.