WO2020186778A1

WO2020186778A1 - Error word correction method and device, computer device, and storage medium

Info

Publication number: WO2020186778A1
Application number: PCT/CN2019/117237
Authority: WO
Inventors: 解笑; 徐国强; 邱寒
Original assignee: 平安科技（深圳）有限公司
Priority date: 2019-03-15
Filing date: 2019-11-11
Publication date: 2020-09-24
Also published as: CN110110041B; CN110110041A

Abstract

An error word correction method and device, a computer device, and a storage medium. The error word correction method comprises: obtaining a general natural language data set (101); converting each sentence comprised in the natural language data set into a Pinyin sequence to obtain obtaining Pinyin-sentence pairs of the general natural language data set (102); performing Pinyin replacement on some of the Pinyin-sentence pairs of the general natural language data set to obtain a first sample set (103); pre-training a neural network model using the first sample set to obtain a pre-trained neural network model (104); obtaining a plurality of Pinyin-sentence pairs comprising similar Pinyin and related to a specific field as a second sample set (105); performing fine tuning on the pre-trained neural network model using the second sample set to obtain a fine-tuned neural network model (106); and inputting a Pinyin sequence of a sentence to be corrected into the fine-tuned neural network model for correction to obtain a corrected sentence (107). By means of the method, error correction can be performed on special words identified as common words in language identification.

Description

Wrong word correction method, device, computer device and storage medium

This application claims to be submitted to the Chinese Patent Office on March 15, 2019. The application number is 201910199221.9. The application titled "Wrong word correction method, device, computer device and storage medium" is the priority of the Chinese patent application, the entire content of which is incorporated by reference In this application.

Technical field

This application relates to the technical field of speech recognition, and in particular to a method, device, computer device and non-volatile readable storage medium for correcting wrong words.

Background technique

With the rapid expansion of speech recognition application scenarios, speech recognition technology has become more and more mature, and the market has increasingly strong demand for high-accuracy speech recognition. For some companies that develop products with voice recognition functions, more often they use the voice recognition module of the general system. If they do not recognize specific application scenarios, it is easy to recognize certain proprietary words as common words. For example, "who needs to be insured" is identified as "who needs to Taobao". Since there is no obvious error, the existing wrong word correction system is difficult to find such errors.

Currently, there is no effective solution to how to improve the correction effect of language recognition in actual application scenarios. How to formulate a suitable solution to reduce the deviation of speech recognition and improve user experience is a technical problem that relevant technicians need to solve at present.

Summary of the invention

In view of the above, it is necessary to propose a method, device, computer device, and non-volatile readable storage medium for correcting wrong words, which can correct the errors when the proprietary words are recognized as common words in language recognition.

The first aspect of this application provides a method for correcting a wrong word. The method includes:

Acquiring a universal natural language data set, the universal natural language data set containing a plurality of sentences;

Converting each sentence contained in the universal natural language data set into a pinyin sequence to obtain a pinyin-sentence pair of the universal natural language data set;

Select multiple pinyin-sentence pairs from the pinyin-sentence pairs of the universal natural language data set, replace part of the pinyin of each selected pinyin-sentence pair with similar pinyin, obtain the replaced pinyin-sentence pair, The unselected pinyin-sentence pairs of the general natural language data set and the replaced pinyin-sentence pairs form the first sample set;

Pre-training the neural network model by using the first sample set to obtain a pre-trained neural network model;

Acquire multiple pinyin-sentence pairs with similar pinyin related to a specific field as the second sample set;

Using the second sample set to fine-tune the pre-trained neural network model to obtain a fine-tuned neural network model;

The pinyin sequence of the sentence to be corrected is input into the fine-tuned neural network model for error correction, and the corrected sentence is obtained.

The second aspect of the present application provides a wrong word correction device, the device includes:

The first acquisition module is configured to acquire a universal natural language data set, the universal natural language data set containing multiple sentences;

A conversion module, configured to convert each sentence contained in the universal natural language data set into a pinyin sequence to obtain a pinyin-sentence pair of the universal natural language data set;

The generating module is used to select multiple pinyin-sentence pairs from the pinyin-sentence pairs in the universal natural language data set, and replace part of the pinyin of each selected pinyin-sentence pair with similar pinyin to obtain the replaced pinyin- Sentence pairs, combining the unselected pinyin-sentence pairs of the general natural language data set and the replaced pinyin-sentence pairs into a first sample set;

The pre-training module is used to pre-train the neural network model with the first sample set to obtain the pre-trained neural network model;

The second acquisition module is used to acquire multiple pinyin-sentence pairs containing similar pinyin related to a specific field as a second sample set;

A fine-tuning module, configured to fine-tune the pre-trained neural network model by using the second sample set to obtain a fine-tuned neural network model;

The error correction module is used to input the pinyin sequence of the sentence to be corrected into the fine-tuned neural network model for error correction, and obtain the corrected sentence.

A third aspect of the present application provides a computer device, the computer device includes a processor, and the processor is configured to implement the wrong word correction method when executing computer-readable instructions stored in a memory.

A fourth aspect of the present application provides a non-volatile readable storage medium having computer readable instructions stored thereon, and when the computer readable instructions are executed by a processor, the wrong word correction method is implemented.

This application obtains a universal natural language data set, the universal natural language data set contains multiple sentences; each sentence included in the universal natural language data set is converted into a pinyin sequence to obtain the pinyin of the universal natural language data set- Sentence pairs; select multiple pinyin-sentence pairs from the pinyin-sentence pairs of the universal natural language data set, and replace part of the pinyin of each selected pinyin-sentence pair with similar pinyin to obtain the replaced pinyin-sentence pair , Compose the unselected pinyin-sentence pairs of the general natural language data set and the replaced pinyin-sentence pairs into a first sample set; use the first sample set to pre-train the neural network model, Obtain a pre-trained neural network model; acquire a number of pinyin-sentence pairs related to a specific field containing similar pinyin as the second sample set; use the second sample set to fine-tune the pre-trained neural network model , Obtain the fine-tuned neural network model; input the pinyin sequence of the sentence to be corrected into the fine-tuned neural network model for error correction, and obtain the corrected sentence. This embodiment can solve the problem that the proprietary words cannot be accurately predicted in a specific field due to the versatility of the speech recognition system, and can correct errors in the recognition of the proprietary words as common words in language recognition.

Description of the drawings

Fig. 1 is a flowchart of a method for correcting a wrong word provided by an embodiment of the present application.

Figure 2 is a structural diagram of a wrong word correction device provided by an embodiment of the present application.

Fig. 3 is a schematic diagram of a computer device provided by an embodiment of the present application.

detailed description

In order to be able to understand the above objectives, features and advantages of the application more clearly, the application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that the embodiments of the application and the features in the embodiments can be combined with each other if there is no conflict.

Preferably, the wrong word correction method of this application is applied to one or more computer devices. The computer device is a device that can automatically perform numerical calculation and/or information processing in accordance with pre-set or stored instructions. Its hardware includes, but is not limited to, a microprocessor and an application specific integrated circuit (ASIC) , Field-Programmable Gate Array (FPGA), Digital Processor (Digital Signal Processor, DSP), embedded equipment, etc.

The computer device may be a computing device such as a desktop computer, a notebook, a palmtop computer, and a cloud server. The computer device can interact with the user through a keyboard, a mouse, a remote control, a touch panel, or a voice control device.

Example one

FIG. 1 is a flowchart of a method for correcting a wrong word provided in Embodiment 1 of the present application. The wrong word correction method is applied to a computer device.

The method for correcting wrong words in this application is to correct sentences obtained by language recognition. The method for correcting wrong words can solve the problem of unable to accurately predict proprietary words in a specific field due to the versatility of the speech recognition system, and at the same time enhance the error correction system's ability to find wrong words when the proprietary words are replaced with common words. Improve the user experience.

As shown in Figure 1, the wrong word correction method includes:

Step 101: Obtain a universal natural language data set, the universal natural language data set containing multiple sentences.

The universal natural language data set is a Chinese text containing everyday words.

The universal natural language data set can be collected from data sources such as books, news, web pages (such as Baidu Baike, Wikipedia, etc.). For example, text recognition can be performed on text in a book to obtain the universal natural language data set. For another example, language recognition can be performed on the broadcast news to obtain the universal natural language data set. For another example, text can be captured from a web page to obtain the universal natural language data set.

Alternatively, the universal natural language data set can be read from a preset database. The preset database can store a large amount of Chinese texts in advance.

Alternatively, the Chinese text input by the user may be received, and the Chinese text input by the user may be used as the universal natural language data set.

Step 102: Convert each sentence contained in the universal natural language data set into a pinyin sequence to obtain a pinyin-sentence pair of the universal natural language data set.

In this embodiment, the universal natural language data set may include multiple Chinese texts, and each Chinese text may include multiple sentences (ie, multiple sentences). In this case, each Chinese text can be divided into multiple sentences according to punctuation marks (such as comma, semicolon, period, etc.), and each sentence obtained by the division can be converted into a pinyin sequence to obtain the pinyin corresponding to each sentence -Sentence pairs.

The sentence can be converted into a pinyin sequence according to the ASCII code of the Chinese character. Since Chinese characters are represented by ASCII codes in the computer system, only the correspondence between each pinyin and each ASCII code existing in the computer system or established by the user can be used to convert sentences into pinyin sequences. If the sentence contains polyphonic characters, multiple pinyins of the polyphonic characters can be listed, and the correct pinyin selected by the user can be received.

Alternatively, the sentence can be converted into a pinyin sequence according to the Unicode value of the Chinese character. Specific steps are as follows:

(1) Establish a pinyin-number comparison table, number all the pinyins and add the corresponding numbers of all the pinyins to the pinyin-number comparison table. The pinyin of all Chinese characters does not exceed 512, and the pinyin can be numbered with two bytes. Each pinyin corresponds to a number.

(2) Establish a Unicode value-Pinyin number comparison table, and add the corresponding pinyin number of the Chinese character to the Unicode value-Pinyin number comparison table according to the Unicode value of the Chinese character.

(3) Read the Chinese characters to be converted in the sentence one by one, determine the Unicode value of the Chinese characters to be converted, and obtain the to-be converted from the Unicode value-pinyin number comparison table according to the Unicode value of the Chinese characters to be converted The number of the pinyin corresponding to the Chinese character is obtained from the pinyin-number comparison table according to the number of the pinyin corresponding to the Chinese character to be converted, so that each Chinese character in the sentence is converted into a pinyin.

If the sentence contains polyphonic characters, in the above step (2), the numbers of the multiple pinyin corresponding to the polyphonic characters can be added to the Unicode value-pinyin number comparison table according to the Unicode value of the polyphonic character, In the above (3), the Unicode value of the polysyllabic character is determined, and the number of the multiple pinyin corresponding to the polysyllabic character is obtained from the Unicode value-pinyin number comparison table according to the Unicode value of the polysyllabic character. The numbers of the multiple pinyin corresponding to the polyphonic character are obtained from the pinyin-number comparison table. The correct pinyin selected by the user from the plurality of pinyin can be received, and the pinyin selected by the user can be used as the correct pinyin of the polyphone in the sentence.

Step 103: Select a plurality of pinyin-sentence pairs from the pinyin-sentence pairs of the general natural language data set, and replace part of the pinyin of each selected pinyin-sentence pair with similar pinyin to obtain the replaced pinyin-sentence pair , Compose the unselected pinyin-sentence pair of the universal natural language data set and the replaced pinyin-sentence pair into a first sample set.

The multiple pinyin-sentence pairs may be randomly selected from the pinyin-sentence pairs in the universal natural language data set, and part of the pinyin in each selected pinyin-sentence may be replaced with a similar pinyin.

A plurality of pinyin-sentence pairs can be selected from the pinyin-sentence pairs of the general natural language data set according to a preset ratio. For example, 20% of the pinyin-sentence pairs can be selected from the pinyin-sentence pairs in the universal natural language data set for pinyin replacement. For example, if the universal natural language data set includes 100 sentences (that is, includes 100 pinyin-sentence pairs), then 20 pinyin-sentence pairs are selected for pinyin replacement.

The training samples of the first sample set include unselected pinyin-sentence pairs, that is, correct pinyin-sentence pairs, and also include pinyin-sentence pairs after replacement, that is, partial pinyin is replaced with pinyin-sentence pairs of similar pinyin.

This application is mainly used to correct errors in sentences obtained by language recognition. Most of the sentence errors obtained by speech recognition are that the words in the sentence are meaningful but the sentence is meaningless. For example, "who needs to insure for whom" is sometimes recognized as "who needs to Taobao for". Therefore, not only the correct pinyin-sentence pairs are needed as training samples, but part of the pinyin needs to be replaced with similar pinyin-sentence pairs as training samples for the model.

Step 104: Pre-train the neural network model by using the first sample set to obtain a pre-trained neural network model.

The input of the neural network model is a pinyin sequence, and the output is a corresponding sentence (ie, a sequence of Chinese characters). For each pinyin in the pinyin sequence, the corresponding Chinese character is predicted.

When training the neural network model, each unselected pinyin-sentence pair (ie unreplaced pinyin-sentence pair) and each replaced pinyin-sentence pair are used as training samples. The pinyin sequence in the pinyin-sentence pair is the input of the neural network model, and the sentence in the pinyin-sentence pair is the real result.

In this embodiment, the neural network model may be a transformer model.

The transformer model can accept a string of sequences as input and output a string of sequences at the same time. In this application, the Transformer model uses a Pinyin sequence as input and outputs a sequence of Chinese characters.

The transformer model includes an encoding layer, a self-attention layer, and a decoding layer. The coding layer and the decoding layer correspond to the coding of Pinyin and the decoding of Chinese characters respectively. The self-attention layer is used to predict Chinese characters with repeated Pinyin. Since there are a lot of repetitions of Chinese pinyin, different Chinese characters and words correspond to the same pinyin, for example, "Bangxiao" and "baoxiao" have the same pinyin and tone, so when making predictions for each pinyin, you need to "pay attention" to the entire sentence Pinyin sequence instead of just looking at the pinyin at the current position. The self-attention mechanism can make the pinyin of a certain position obtain the pinyin representations of all other positions, so as to make predictions of Chinese characters more in line with the sentence scenario.

After training with a large number of samples, the Ttransformer model can output the corresponding Chinese character sequence by inputting the Pinyin sequence.

Step 105: Acquire a plurality of pinyin-sentence pairs that contain similar pinyin related to a specific field as a second sample set.

Each training sample in the second sample set is a pinyin-sentence pair related to a specific field, and the pinyin-sentence pair contains similar pinyin related to the specific field.

The specific field is the exclusive field to be applied in this method, such as law, insurance, etc.

The language data set obtained in step 101 is a general natural language data set, which mainly contains some everyday words. The first sample set obtained according to the general natural language data set is a training sample about everyday words. Therefore, the neural network model obtained by pre-training is in When the sentences in daily life have obvious speech recognition errors, they can be corrected well. However, when encountering certain proprietary fields such as law and insurance, the error correction effect of the neural network model is reduced, and many proprietary words will be recognized as everyday words. For example, "Insured" in "Who needs to insure" is identified as "Taobao". Therefore, when it is applied to a specific field for error correction, sample data of the specific field is required.

You can obtain multiple pinyin-sentence pairs with similar pinyin related to a specific field according to the following method:

Acquiring a text data set of the specific field, the text data set containing multiple sentences;

Converting each sentence contained in the text data set into a pinyin sequence to obtain a pinyin-sentence pair of the text data set;

The pinyin of the specific word in the specific field in the pinyin-sentence pair of the text data set is replaced with a similar pinyin to obtain a pinyin-sentence pair containing the similar pinyin related to the specific field. For example, replace the pinyin (tou, ersheng, bao, three tones) of "insurance" in "who needs to insure for" with the pinyin of "taobao" (tao, ersheng, bao, three tones).

Alternatively, a database may be established in advance to store the pinyin-sentence pairs that are incorrectly recognized in the specific field, and a plurality of pinyin-sentence pairs containing similar pinyin related to the specific field can be obtained from the database.

Step 106: Use the second sample set to fine-tune the pre-trained neural network model to obtain a fine-tuned neural network model.

The purpose of fine-tuning the neural network model by using the second sample set is to make the neural network model more suitable for a specific field and improve the error correction accuracy rate in the specific field.

When the pinyin is similar, the model after fine-tuning training is more inclined to predict the exclusive words in the specific field, thereby improving the effect of correcting the wrong words of speech recognition errors.

The weights of the neurons in the first few layers of the neural network model can be fixed, and the weights of the neurons in the subsequent layers of the neural network model can be fine-tuned. This is mainly to avoid over-fitting when the second sample set is too small. The neurons in the first few layers of the neural network model generally contain more general features, which are very important for many tasks, but the characteristics of the neurons in the latter layers Learning pays attention to high-level features, and there are big differences between different data sets.

Step 107: Input the pinyin sequence of the sentence to be corrected into the fine-tuned neural network model for error correction, and obtain the corrected sentence.

The result of language recognition may include multiple Chinese texts, and each Chinese text may include multiple sentences to be corrected (ie, multiple sentences). In this case, the Chinese text obtained by language recognition can be divided into multiple sentences to be corrected according to punctuation (such as comma, semicolon, period, etc.), and each sentence to be corrected is converted into a pinyin sequence.

The sentence to be corrected can be converted into a pinyin sequence according to the ASCII code of the Chinese character. Alternatively, the sentence to be corrected can be converted into a pinyin sequence according to the Unicode value of the Chinese character. Refer to step 102 for the method of converting the sentence to be corrected into a pinyin sequence.

Alternatively, the sentence to be corrected input by the user may be received, and the sentence to be corrected may be converted into a pinyin sequence. For example, a user interface may be generated, and a sentence to be corrected input by the user may be received from the user interface. It is also possible to directly receive the pinyin sequence of the sentence to be corrected input by the user.

The wrong word correction method of the first embodiment obtains a universal natural language data set, the universal natural language data set contains multiple sentences; each sentence included in the universal natural language data set is converted into a pinyin sequence to obtain the universal natural language data set. Pinyin-sentence pairs of the language data set; select multiple pinyin-sentence pairs from the pinyin-sentence pairs of the general natural language data set, and replace part of the pinyin of each selected pinyin-sentence pair with similar pinyin to obtain the replacement After the pinyin-sentence pair, the unselected pinyin-sentence pair of the general natural language data set and the replaced pinyin-sentence pair form the first sample set; use the first sample set to pair the nerve The network model is pre-trained to obtain a pre-trained neural network model; a plurality of pinyin-sentence pairs containing similar pinyin related to a specific field are obtained as the second sample set; the second sample set is used to perform the pre-training The neural network model is fine-tuned to obtain a fine-tuned neural network model; the pinyin sequence of the sentence to be corrected is input into the fine-tuned neural network model for error correction, and the corrected sentence is obtained. This embodiment can solve the problem that the proprietary words cannot be accurately predicted in a specific field due to the versatility of the speech recognition system, and can correct errors in the recognition of the proprietary words as common words in language recognition.

In another embodiment, the method for correcting wrong words may further include: recognizing the input voice to obtain the sentence to be corrected. Various speech recognition technologies can be used, such as Dynamic Time Warping (DTW), Hidden Markov Model (HMM), Vector Quantization (VQ), and Artificial Neural Network (Artificial Neural Network, ANN) and other technologies to recognize the voice.

Example two

Fig. 2 is a structural diagram of a wrong word correction device provided in the second embodiment of the present application. The wrong word correction device 20 is applied to a computer device. As shown in FIG. 2, the wrong word correction device 20 may include a first acquisition module 201, a conversion module 202, a generation module 203, a pre-training module 204, a second acquisition module 205, a fine-tuning module 206, and an error correction module 207.

The first acquisition module 201 is configured to acquire a universal natural language data set, the universal natural language data set containing multiple sentences.

The conversion module 202 is configured to convert each sentence contained in the universal natural language data set into a pinyin sequence to obtain a pinyin-sentence pair of the universal natural language data set.

The generating module 203 is configured to select multiple pinyin-sentence pairs from the pinyin-sentence pairs in the universal natural language data set, and replace part of the pinyin of each selected pinyin-sentence pair with similar pinyin to obtain the replaced pinyin -Sentence pairs, combining the unselected pinyin-sentence pairs of the universal natural language data set and the replaced pinyin-sentence pairs into a first sample set.

A plurality of pinyin-sentence pairs can be selected from the pinyin-sentence pairs of the general natural language data set according to a preset ratio. For example, 20% of the pinyin-sentence pairs can be selected from the pinyin-sentence pairs in the universal natural language data set for pinyin replacement. For example, if the general natural language data set includes 100 sentences (that is, includes 100 pinyin-sentence pairs), then 20 pinyin-sentence pairs are selected for pinyin replacement.

This application is mainly used to correct errors in sentences obtained by language recognition. Most of the sentence errors obtained by speech recognition are that the words in the sentence are meaningful but the sentence is meaningless. For example, "who needs to insure for whom" is sometimes recognized as "who needs to Taobao for". Therefore, not only the correct pinyin-sentence pairs are required as training samples, but also some pinyin-sentence pairs need to be replaced with similar pinyin pinyin-sentence pairs as training samples for the model.

The pre-training module 204 is configured to pre-train the neural network model by using the first sample set to obtain the pre-trained neural network model.

In this embodiment, the neural network model may be a transformer model.

The transformer model includes an encoding layer, a self-attention layer, and a decoding layer. The coding layer and the decoding layer correspond to the coding of Pinyin and the decoding of Chinese characters respectively.

The self-attention layer is used to predict Chinese characters with repeated Pinyin. Because there are a lot of repetitions in Chinese pinyin, different Chinese characters and words correspond to the same pinyin, for example, "Bangxiao" and "baoxiao" have the same pinyin and tone, so when making predictions for each pinyin, you need to "pay attention" to the entire sentence Pinyin sequence instead of just looking at the pinyin at the current position. The self-attention mechanism can make the pinyin of a certain position obtain the pinyin representations of all other positions, so as to make predictions of Chinese characters more in line with the sentence scenario.

The second acquisition module 205 is configured to acquire a plurality of pinyin-sentence pairs containing similar pinyin related to a specific field as a second sample set.

The language data set obtained by the first acquisition module 201 is a general natural language data set, which mainly contains some everyday words. The first sample set obtained according to the general natural language data set is a training sample about everyday words, so the nerves obtained by pre-training The network model can perform a good error correction when there are obvious speech recognition errors in sentences in daily life. However, when encountering certain proprietary fields such as law and insurance, the error correction effect of the neural network model is reduced, and many proprietary words will be recognized as everyday words. For example, "Insured" in "Who needs to insure" is identified as "Taobao". Therefore, when it is applied to a specific field for error correction, sample data of the specific field is required.

The fine-tuning module 206 is configured to use the second sample set to fine-tune the pre-trained neural network model to obtain a fine-tuned neural network model.

The weights of neurons in the first few layers of the neural network model can be fixed, and the weights of neurons in the next few layers of the neural network model can be fine-tuned. This is mainly to avoid over-fitting when the second sample set is too small. The neurons in the first few layers of the neural network model generally contain more general features, which are very important for many tasks, but the characteristics of the neurons in the latter layers Learning focuses on high-level features, and different data sets vary greatly.

The error correction module 207 is configured to input the pinyin sequence of the sentence to be corrected into the fine-tuned neural network model for error correction, and obtain the corrected sentence.

The sentence to be corrected can be converted into a pinyin sequence according to the ASCII code of the Chinese character. Alternatively, the sentence to be corrected can be converted into a pinyin sequence according to the Unicode value of the Chinese character. Refer to the description of the conversion module 202 for the method of converting the sentence to be corrected into a pinyin sequence.

The wrong word correction device 20 of this embodiment obtains a universal natural language data set, the universal natural language data set contains multiple sentences; each sentence included in the universal natural language data set is converted into a pinyin sequence to obtain the universal Pinyin-sentence pairs of the natural language data set; select multiple pinyin-sentence pairs from the pinyin-sentence pairs of the general natural language data set, and replace part of the pinyin of each selected pinyin-sentence pair with similar pinyin to obtain The replaced pinyin-sentence pair, the unselected pinyin-sentence pair of the general natural language data set and the replaced pinyin-sentence pair form a first sample set; the first sample set pair is used The neural network model is pre-trained to obtain the pre-trained neural network model; a plurality of pinyin-sentence pairs containing similar pinyin related to a specific field are obtained as the second sample set; the second sample set is used to perform the pre-training The latter neural network model is fine-tuned to obtain a fine-tuned neural network model; the pinyin sequence of the sentence to be corrected is input into the fine-tuned neural network model for error correction, and the corrected sentence is obtained. This embodiment can solve the problem that the proprietary words cannot be accurately predicted in a specific field due to the versatility of the speech recognition system, and can correct errors in the recognition of the proprietary words as common words in language recognition.

In another embodiment, the wrong word correction device 20 may further include: a recognition module, which recognizes the input voice to obtain the sentence to be corrected. Various speech recognition technologies can be used, such as Dynamic Time Warping (DTW), Hidden Markov Model (HMM), Vector Quantization (VQ), Artificial Neural Network (Artificial Neural Network, ANN) and other technologies to recognize the voice.

Example three

This embodiment provides a non-volatile readable storage medium with computer readable instructions stored on the non-volatile readable storage medium, and when the computer readable instructions are executed by a processor, the above-mentioned wrong word correction method embodiment is implemented Steps in, for example, steps 101-107 shown in Figure 1:

Step 101: Obtain a universal natural language data set, where the universal natural language data set contains multiple sentences;

Step 102: Convert each sentence contained in the universal natural language data set into a pinyin sequence to obtain a pinyin-sentence pair of the universal natural language data set;

Step 103: Select a plurality of pinyin-sentence pairs from the pinyin-sentence pairs of the general natural language data set, and replace part of the pinyin of each selected pinyin-sentence pair with similar pinyin to obtain the replaced pinyin-sentence pair , Compose the unselected pinyin-sentence pair of the universal natural language data set and the replaced pinyin-sentence pair into a first sample set;

Step 104: Pre-train the neural network model by using the first sample set to obtain a pre-trained neural network model;

Step 105: Obtain a plurality of pinyin-sentence pairs containing similar pinyin related to a specific field as a second sample set;

Step 106: Use the second sample set to fine-tune the pre-trained neural network model to obtain a fine-tuned neural network model;

Alternatively, the computer-readable instructions realize the functions of the modules in the above-mentioned device embodiment when executed by the processor, for example, modules 201-207 in Figure 2:

The first acquiring module 201 is configured to acquire a universal natural language data set, the universal natural language data set containing multiple sentences;

The conversion module 202 is configured to convert each sentence contained in the universal natural language data set into a pinyin sequence to obtain a pinyin-sentence pair of the universal natural language data set;

The generating module 203 is configured to select multiple pinyin-sentence pairs from the pinyin-sentence pairs in the universal natural language data set, and replace part of the pinyin of each selected pinyin-sentence pair with similar pinyin to obtain the replaced pinyin -Sentence pairs, combining the unselected pinyin-sentence pairs of the general natural language data set and the replaced pinyin-sentence pairs into a first sample set;

The pre-training module 204 is configured to pre-train the neural network model by using the first sample set to obtain a pre-trained neural network model;

The second acquiring module 205 is configured to acquire a plurality of pinyin-sentence pairs containing similar pinyin related to a specific field as a second sample set;

The fine-tuning module 206 is configured to use the second sample set to fine-tune the pre-trained neural network model to obtain a fine-tuned neural network model;

Example four

FIG. 3 is a schematic diagram of a computer device provided in Embodiment 4 of this application. The computer device 30 includes a memory 301, a processor 302, and computer-readable instructions 303 stored in the memory 301 and running on the processor 302, such as a wrong word correction program. When the processor 302 executes the computer-readable instruction 303, the steps in the embodiment of the above-mentioned wrong word correction method are implemented, for example, steps 101-107 shown in Fig. 1:

Or, when the computer-readable instruction is executed by the processor, the function of each module in the above device embodiment is realized, for example, the modules 201-207 in FIG. 2

Exemplarily, the computer-readable instruction 303 may be divided into one or more modules, and the one or more modules are stored in the memory 301 and executed by the processor 302 to complete the method . For example, the computer-readable instruction 303 can be divided into the first acquisition module 201, the conversion module 202, the generation 203, the pre-training module 204, the second acquisition module 205, the fine-tuning module 206, and the error correction module 207 in FIG. Refer to the second embodiment for the specific functions of each module.

The computer device 30 may be a computing device such as a desktop computer, a notebook, a palmtop computer, and a cloud server. Those skilled in the art can understand that the schematic diagram 3 is only an example of the computer device 30 and does not constitute a limitation on the computer device 30. It may include more or less components than those shown in the figure, or combine certain components, or be different. For example, the computer device 30 may also include input and output devices, network access devices, buses, etc.

The so-called processor 302 may be a central processing unit (Central Processing Unit, CPU), other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor 302 can also be any conventional processor, etc. The processor 302 is the control center of the computer device 30 and connects the entire computer device 30 with various interfaces and lines. Various parts.

The memory 301 may be used to store the computer-readable instructions 303, and the processor 302 executes or executes the computer-readable instructions or modules stored in the memory 301, and calls data stored in the memory 301 to implement Various functions of the computer device 30. The memory 301 may mainly include a program storage area and a data storage area. The program storage area may store an operating system, an application program required by at least one function (such as a sound playback function, an image playback function, etc.), etc.; The data created according to the use of the computer device 30 is stored. In addition, the memory 301 may include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a Secure Digital (SD) card, a flash memory card (Flash Card), At least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device.

If the integrated module of the computer device 30 is implemented in the form of a software function module and sold or used as an independent product, it may be stored in a non-volatile readable storage medium. Based on this understanding, this application implements all or part of the processes in the above-mentioned embodiments and methods, and can also be completed by instructing relevant hardware through computer-readable instructions. The computer-readable instructions can be stored in a non-volatile memory. In the read storage medium, when the computer-readable instructions are executed by the processor, the steps of the foregoing method embodiments can be implemented. Wherein, the computer-readable instructions may be in the form of source code, object code, executable file, or some intermediate forms, etc. The computer-readable medium may include: any entity or device capable of carrying the computer-readable instruction code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, read-only memory (ROM, Read-Only Memory).

In the several embodiments provided in this application, it should be understood that the disclosed system, device, and method may be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the application and not to limit them. Although the application has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the application can be Modifications or equivalent replacements are made without departing from the spirit and scope of the technical solution of this application.

Claims

A method for correcting wrong words, characterized in that the method includes:

Acquiring a universal natural language data set, the universal natural language data set containing a plurality of sentences;

Converting each sentence contained in the universal natural language data set into a pinyin sequence to obtain a pinyin-sentence pair of the universal natural language data set;

Select multiple pinyin-sentence pairs from the pinyin-sentence pairs of the universal natural language data set, replace part of the pinyin of each selected pinyin-sentence pair with similar pinyin, obtain the replaced pinyin-sentence pair, The unselected pinyin-sentence pairs of the general natural language data set and the replaced pinyin-sentence pairs form the first sample set;

Pre-training the neural network model by using the first sample set to obtain a pre-trained neural network model;

Acquire multiple pinyin-sentence pairs with similar pinyin related to a specific field as the second sample set;

Using the second sample set to fine-tune the pre-trained neural network model to obtain a fine-tuned neural network model;

The pinyin sequence of the sentence to be corrected is input into the fine-tuned neural network model for error correction, and the corrected sentence is obtained.
The method according to claim 1, wherein the converting each sentence contained in the universal natural language data set into a pinyin sequence comprises:

Convert the sentence into a Pinyin sequence according to the ASCII code of the Chinese character; or

The sentence is converted into a Pinyin sequence according to the Unicode value of the Chinese character.
3. The method of claim 2, wherein the converting the sentence into a pinyin sequence according to the Unicode value of the Chinese character comprises:

Establish a pinyin-number comparison table, number all the pinyins and add the corresponding numbers of all the pinyins to the pinyin-number comparison table;

Establish a Unicode value-Pinyin number comparison table, and add the number of the Chinese character corresponding to the pinyin to the Unicode value-Pinyin number comparison table according to the Unicode value of the Chinese character;

Read the Chinese characters to be converted in the sentence one by one, determine the Unicode value of the Chinese character to be converted, and obtain the corresponding Chinese character to be converted from the Unicode value-pinyin number comparison table according to the Unicode value of the Chinese character to be converted The pinyin number is obtained from the pinyin-number comparison table according to the pinyin number corresponding to the Chinese character to be converted, so as to convert each Chinese character in the sentence into pinyin.
The method according to claim 1, wherein the selecting a plurality of pinyin-sentence pairs from the pinyin-sentence pairs of the universal natural language data set comprises:

Randomly selecting the plurality of pinyin-sentence pairs from the pinyin-sentence pairs of the universal natural language data set; and/or

The multiple pinyin-sentence pairs are selected from the pinyin-sentence pairs in the universal natural language data set according to a preset ratio.
The method of claim 1, wherein the neural network model is a transformer model.
The method of claim 1, wherein the fine-tuning the neural network model after the pre-training comprises:

Fix the weights of the neurons in the first few layers of the neural network model, and fine-tune the weights of the neurons in the next few layers of the neural network model.
The method according to any one of claims 1-6, wherein the method further comprises:

Recognizing the input voice to obtain the sentence to be corrected.
A wrong word correction device, characterized in that the device includes:

The first acquisition module is configured to acquire a universal natural language data set, the universal natural language data set containing multiple sentences;

A conversion module, configured to convert each sentence contained in the universal natural language data set into a pinyin sequence to obtain a pinyin-sentence pair of the universal natural language data set;

The generating module is used to select multiple pinyin-sentence pairs from the pinyin-sentence pairs in the universal natural language data set, and replace part of the pinyin of each selected pinyin-sentence pair with similar pinyin to obtain the replaced pinyin- Sentence pairs, combining the unselected pinyin-sentence pairs of the general natural language data set and the replaced pinyin-sentence pairs into a first sample set;

The pre-training module is used to pre-train the neural network model with the first sample set to obtain the pre-trained neural network model;

The second acquisition module is used to acquire multiple pinyin-sentence pairs containing similar pinyin related to a specific field as a second sample set;

A fine-tuning module, configured to fine-tune the pre-trained neural network model by using the second sample set to obtain a fine-tuned neural network model;

The error correction module is used to input the pinyin sequence of the sentence to be corrected into the fine-tuned neural network model for error correction, and obtain the corrected sentence.
A computer device, wherein the computer device includes a processor and a memory, and the processor is configured to execute computer-readable instructions stored in the memory to implement the following steps:

Acquiring a universal natural language data set, the universal natural language data set containing a plurality of sentences;

Converting each sentence contained in the universal natural language data set into a pinyin sequence to obtain a pinyin-sentence pair of the universal natural language data set;

Select multiple pinyin-sentence pairs from the pinyin-sentence pairs of the universal natural language data set, replace part of the pinyin of each selected pinyin-sentence pair with similar pinyin, obtain the replaced pinyin-sentence pair, The unselected pinyin-sentence pairs of the general natural language data set and the replaced pinyin-sentence pairs form the first sample set;

Pre-training the neural network model by using the first sample set to obtain a pre-trained neural network model;

Acquire multiple pinyin-sentence pairs with similar pinyin related to a specific field as the second sample set;

Using the second sample set to fine-tune the pre-trained neural network model to obtain a fine-tuned neural network model;

The pinyin sequence of the sentence to be corrected is input into the fine-tuned neural network model for error correction, and the corrected sentence is obtained.
The computer device of claim 9, wherein the processor executes computer-readable instructions stored in the memory to implement the conversion of each sentence contained in the universal natural language data set into a Pinyin sequence When including:

Convert the sentence into a Pinyin sequence according to the ASCII code of the Chinese character; or

The sentence is converted into a Pinyin sequence according to the Unicode value of the Chinese character.
10. The computer device according to claim 10, wherein when the processor executes the computer-readable instructions stored in the memory to implement the conversion of the sentence into a Pinyin sequence according to the Unicode value of the Chinese character, it comprises:

Establish a pinyin-number comparison table, number all the pinyins and add the corresponding numbers of all the pinyins to the pinyin-number comparison table;

Establish a Unicode value-Pinyin number comparison table, and add the number of the Chinese character corresponding to the pinyin to the Unicode value-Pinyin number comparison table according to the Unicode value of the Chinese character;

Read the Chinese characters to be converted in the sentence one by one, determine the Unicode value of the Chinese character to be converted, and obtain the corresponding Chinese character to be converted from the Unicode value-pinyin number comparison table according to the Unicode value of the Chinese character to be converted The number of the pinyin is obtained from the pinyin-number comparison table according to the number of the pinyin corresponding to the Chinese character to be converted, so as to convert each Chinese character in the sentence into pinyin.
The computer device of claim 9, wherein the processor executes computer-readable instructions stored in the memory to implement the selection of a plurality of pinyin-sentence pairs from the general natural language data set Pinyin-sentence pairs include:

Randomly selecting the plurality of pinyin-sentence pairs from the pinyin-sentence pairs of the universal natural language data set; and/or

The multiple pinyin-sentence pairs are selected from the pinyin-sentence pairs in the universal natural language data set according to a preset ratio.
9. The computer device according to claim 9, wherein when the processor executes the computer-readable instructions stored in the memory to implement the fine-tuning of the pre-trained neural network model, it comprises:

Fix the weights of the neurons in the first few layers of the neural network model, and fine-tune the weights of the neurons in the next few layers of the neural network model.
The computer device according to any one of claims 9-13, wherein the processor executing the computer-readable instructions stored in the memory is further used to implement the following steps:

Recognizing the input voice to obtain the sentence to be corrected.
A non-volatile readable storage medium having computer readable instructions stored on the non-volatile readable storage medium, characterized in that, when the computer readable instructions are executed by a processor, the following steps are implemented:

Acquiring a universal natural language data set, the universal natural language data set containing a plurality of sentences;

Converting each sentence contained in the universal natural language data set into a pinyin sequence to obtain a pinyin-sentence pair of the universal natural language data set;

Select multiple pinyin-sentence pairs from the pinyin-sentence pairs of the universal natural language data set, replace part of the pinyin of each selected pinyin-sentence pair with similar pinyin, obtain the replaced pinyin-sentence pair, The unselected pinyin-sentence pairs of the general natural language data set and the replaced pinyin-sentence pairs form the first sample set;

Pre-training the neural network model by using the first sample set to obtain a pre-trained neural network model;

Acquire multiple pinyin-sentence pairs with similar pinyin related to a specific field as the second sample set;

Using the second sample set to fine-tune the pre-trained neural network model to obtain a fine-tuned neural network model;

The pinyin sequence of the sentence to be corrected is input into the fine-tuned neural network model for error correction, and the corrected sentence is obtained.
The storage medium of claim 15, wherein the computer-readable instructions are executed by the processor to implement the conversion of each sentence contained in the universal natural language data set into a pinyin sequence, comprising: :

Convert the sentence into a Pinyin sequence according to the ASCII code of the Chinese character; or

The sentence is converted into a Pinyin sequence according to the Unicode value of the Chinese character.
16. The storage medium of claim 16, wherein the computer-readable instructions are executed by the processor to implement the conversion of the sentence into a Pinyin sequence according to the Unicode value of the Chinese character, comprising:

Establish a pinyin-number comparison table, number all the pinyins and add the corresponding numbers of all the pinyins to the pinyin-number comparison table;

Establish a Unicode value-Pinyin number comparison table, and add the number of the Chinese character corresponding to the pinyin to the Unicode value-Pinyin number comparison table according to the Unicode value of the Chinese character;

Read the Chinese characters to be converted in the sentence one by one, determine the Unicode value of the Chinese character to be converted, and obtain the corresponding Chinese character to be converted from the Unicode value-pinyin number comparison table according to the Unicode value of the Chinese character to be converted The pinyin number is obtained from the pinyin-number comparison table according to the pinyin number corresponding to the Chinese character to be converted, so as to convert each Chinese character in the sentence into pinyin.
The storage medium of claim 15, wherein the computer-readable instructions are executed by the processor to implement the selection of a plurality of pinyin-sentences from the pinyin-sentence pairs in the universal natural language data set Right, including:

Randomly selecting the plurality of pinyin-sentence pairs from the pinyin-sentence pairs of the universal natural language data set; and/or

The multiple pinyin-sentence pairs are selected from the pinyin-sentence pairs in the universal natural language data set according to a preset ratio.
15. The storage medium of claim 15, wherein when the computer-readable instructions are executed by the processor to implement the fine-tuning of the pre-trained neural network model, the method comprises:

Fix the weights of the neurons in the first few layers of the neural network model, and fine-tune the weights of the neurons in the next few layers of the neural network model.
18. The storage medium according to any one of claims 15-18, wherein the computer-readable instructions are executed by the processor to further implement the following steps:

Recognizing the input voice to obtain the sentence to be corrected.