WO2021114928A1 - Error correction word sorting method and apparatus, terminal device and storage medium - Google Patents

Abstract

The embodiments of the present application are applicable to the technical field of input methods. Provided are an error correction word sorting method and apparatus, a terminal device and a storage medium. The method comprises: when a character string input by a user is received, acquiring a plurality of error correction words matching the character string, and determining error correction types of all the error correction words and word order weights corresponding to the error correction types; determining weight values of all the error correction words according to the word order weights of the error correction types; and sorting the plurality of error correction words according to the weight values of all the error correction words. In the method, weight values of error correction words are re-determined according to word order weights of error correction types, such that an error correction word corresponding to an input error that more frequently appears can be preferentially presented to a user, thereby improving the error correction efficiency of an input method; and the method can be applied to the fields of artificial intelligence, natural language processing, etc., and is conducive to improving input efficiency.

Description

Error correction word sorting method, device, terminal equipment and storage medium

This application requires the priority of a Chinese patent application filed with the State Intellectual Property Office, the application number is 201911279538.X, and the application name is "error correction word sequencing method, device, terminal equipment, and storage medium" on December 13, 2019. The entire content is incorporated into this application by reference.

Technical field

This application relates to the technical field of input methods, and in particular to a method, device, terminal device, and storage medium for sorting error correction words.

Background technique

The pinyin input method suitable for Chinese input is that after the user inputs a string of pinyin, the system converts the input pinyin into a string of Chinese characters. Since it does not require special memory and conforms to the way of thinking of people, as long as you know Pinyin, you can input. The Pinyin input method has become the most widely used input method at present.

With the popularization of mobile devices, it is very easy for users to type the pinyin incorrectly when using the pinyin input method on small mobile phones and tablets. For example, if the user wants to input "you", because the letter "i" and the letter "o" on the keyboard are adjacent, it is very easy to make a mistake when inputting, the result is "yiu", which will cause the output Chinese characters are not what users want. The user needs to re-enter or modify the pinyin at a relatively high cost to get the desired words.

Currently, various input method manufacturers provide automatic error correction functions for the Pinyin input method. When the user enters the wrong pinyin, the input method will try to automatically correct the wrong pinyin to the correct pinyin, and then give the corresponding Chinese words according to the corrected pinyin. However, for incorrectly input pinyin, according to different error correction methods, a variety of different error correction results may be obtained. When there are too many error correction results, users also need to go through tedious operations to find out the words they really want.

Summary of the invention

The embodiments of the present application provide a method, device, terminal device, and storage medium for sorting error correction words, which can improve the error correction rate of the Pinyin input method, so that the error correction words finally presented to the user can better match the actual needs of the user.

In the first aspect, an embodiment of the present application provides a method for sorting error correction words, including:

When receiving the character string input by the user, obtain a plurality of error correction words matching the character string, and determine the error correction type to which each error correction word belongs and the word order weight corresponding to the error correction type;

Determine the weight value of each error correction word according to the word order weight of the error correction type;

Sort the plurality of error correction words according to the weight value of each error correction word.

Exemplarily, the weight value of each error correction word may be determined according to the initial weight value of each error correction word and the word order weight of the corresponding error correction type.

Exemplarily, when sorting the error correction words, the number of error correction words corresponding to various error correction types can also be counted separately; the error correction words that exceed the threshold of the number of error correction words are deleted, and then according to the remaining The weight value of each error correction word is used to sort each error correction word.

Exemplarily, for error correction words having a mutually exclusive relationship, the error correction words with a relatively small order weight may be deleted according to the order weight of the error correction type, so as to reduce the number of error correction words.

In the second aspect, an embodiment of the present application provides a device for sorting error correction words, including:

The error correction word acquisition module is used to obtain multiple error correction words matching the character string when receiving the character string input by the user, and determine the error correction type to which each error correction word belongs and the error correction type Corresponding word order weight;

A weight value determining module, configured to determine the weight value of each error correction word according to the word order weight of the error correction type;

The error correction word ordering module is used for ordering the multiple error correction words according to the weight value of each error correction word.

In the third aspect, an embodiment of the present application provides a terminal device, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, The method for sorting error correction words according to any one of the foregoing first aspect is implemented.

In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium that stores a computer program, and when the computer program is executed by a processor of a terminal device, any one of the above-mentioned first aspects is implemented. The method for sorting error correction words described in the item.

In a fifth aspect, the embodiments of the present application provide a computer program product, which when the computer program product runs on a terminal device, causes the terminal device to execute the error correction word ordering method described in any one of the above-mentioned first aspects.

Compared with the prior art, the embodiments of the present application include the following beneficial effects:

In the embodiment of the present application, when a character string input by a user is received, each error correction word can be re-determined by obtaining an error correction word matching the character string, and then according to the word order weight of the error correction type corresponding to the error correction word After sorting each error correction word according to the re-determined weight value, each error correction word can be displayed to the user. Generally, the error correction type with higher word order weight is the error correction for the input errors that occur more frequently when the user is input. The weight value of the error correction word can be re-determined according to the error correction type, and the more common input errors can be corrected. Corresponding error correction words are first displayed to users, which improves the error correction efficiency of the input method, and can be applied to fields such as artificial intelligence and natural language processing, which helps improve input efficiency.

Description of the drawings

FIG. 1 is a schematic diagram of the hardware structure of a mobile phone to which the method for sorting error correction words provided by an embodiment of the present application is applicable;

2 is a schematic diagram of the software structure of a mobile phone to which the method for sorting error correction words provided by an embodiment of the present application is applicable;

FIG. 3 is a schematic step flow chart of a method for sorting error correction words according to an embodiment of the present application;

FIG. 4 is a schematic diagram of an input method architecture provided by an embodiment of the present application;

FIG. 5 is a schematic step flowchart of a method for sorting error correction words provided by another embodiment of the present application;

FIG. 6 is a schematic step flowchart of a method for sorting error correction words according to another embodiment of the present application;

FIG. 7 is a structural block diagram of a device for sorting error correction words according to an embodiment of the present application;

FIG. 8 is a schematic structural diagram of a terminal device provided by an embodiment of the present application.

Detailed ways

In the following description, for the purpose of illustration rather than limitation, specific details such as a specific system structure and technology are proposed for a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from obstructing the description of this application.

The terms used in the following embodiments are only for the purpose of describing specific embodiments, and are not intended to limit the application. As used in the specification and appended claims of this application, the singular expressions "a", "an", "said", "above", "the" and "this" are intended to also This includes expressions such as "one or more" unless the context clearly indicates to the contrary. It should also be understood that in the embodiments of the present application, "one or more" refers to one, two, or more than two; "and/or" describes the association relationship of associated objects, indicating that there may be three relationships; for example, A and/or B can mean the situation where A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character "/" generally indicates that the associated objects before and after are in an "or" relationship.

Currently, input methods of various brands provide corresponding error correction functions. Take the Pinyin input method as an example. The basic principle is to preset some fixed error correction lists or strategies. When it is detected that the pinyin character string input by the user matches the above error correction lists or strategies, it is searched from the system lexicon. The error correction character string corresponding to the input pinyin character string is output, and then candidate words that match the error correction character string are displayed to the user.

For example, if the user enters the pinyin string "lng", the automatic error correction function of the input method will add it to "lang", "leng" or "ling" according to the preset error correction strategy, and then find the corresponding Chinese characters are provided to users.

For another example, if the user enters the pinyin string "yiu", the input method will search for other adjacent letters around the letter "i" to form the string "you", and then provide the Chinese characters corresponding to the string "you" to the user .

However, the error correction words provided by the input method after automatic error correction are not necessarily the words that the user really wants. There are situations where the correcting words are incorrect, or there are too many correcting words, which affects the normal use of users.

For example, if the input method detects the user input string "daohng", the string cannot directly match the corresponding Chinese character. At this time, the input method will correct the errors, get "daohang", "daohong" and "daoheng", and give the corresponding error correction words. In fact, the user may just want to enter "daohang-navigation", according to the above error correction will lead to too many error correction words. When the input method provides all the correcting words to the user, it will take some time for the user to find the word they really want to input.

Therefore, in response to the above problems, the embodiments of the present application provide a method for sorting error correction words. By scientifically and reasonably sorting each error correction word obtained by error correction, the error correction rate of the pinyin input method is improved, and the final presentation is The error correction words given to the user can better match the actual needs of the user, and reduce the operation event that the user chooses the word that he really wants to input from the excessive error correction words.

The following describes the error correction word ordering method provided in the embodiments of the present application in combination with specific technical solutions.

The method for sorting error correction words provided by the embodiments of this application can be applied to mobile phones, tablet computers, wearable devices, vehicle-mounted devices, augmented reality (AR)/virtual reality (VR) devices, notebook computers, and super mobiles. For terminal devices such as ultra-mobile personal computers (UMPC), netbooks, and personal digital assistants (personal digital assistants, PDAs), the embodiments of this application do not impose any restrictions on the specific types of terminal devices.

Take the terminal device as a mobile phone as an example. Fig. 1 shows a block diagram of a part of the structure of a mobile phone provided in an embodiment of the present application. 1, the mobile phone includes: a radio frequency (RF) circuit 110, a memory 120, an input unit 130, a display unit 140, a sensor 150, an audio circuit 160, a wireless fidelity (Wi-Fi) module 170, a processing Adapter 180, power supply 190 and other components. Those skilled in the art can understand that the structure of the mobile phone shown in FIG. 1 does not constitute a limitation on the mobile phone, and may include more or fewer components than those shown in the figure, or a combination of some components, or different component arrangements.

The following describes the components of the mobile phone in detail with reference to Figure 1:

The RF circuit 110 can be used for receiving and sending signals during information transmission or communication. In particular, after receiving the downlink information of the base station, it is processed by the processor 180; in addition, the designed uplink data is sent to the base station. Generally, the RF circuit includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier (LNA), a duplexer, and the like. In addition, the RF circuit 110 can also communicate with the network and other devices through wireless communication. The above-mentioned wireless communication can use any communication standard or protocol, including but not limited to Global System of Mobile Communication (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (Code Division) Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), Email, Short Messaging Service (SMS), etc.

The memory 120 may be used to store software programs and modules. The processor 180 executes various functional applications and data processing of the mobile phone by running the software programs and modules stored in the memory 120. The memory 120 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.; Data created by the use of mobile phones (such as audio data, phone book, etc.), etc. In addition, the memory 120 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

The input unit 130 may be used to receive inputted numeric or character information, and generate key signal input related to user settings and function control of the mobile phone 100. Specifically, the input unit 130 may include a touch panel 131 and other input devices 132. The touch panel 131, also known as a touch screen, can collect user touch operations on or near it (for example, the user uses any suitable objects or accessories such as fingers, stylus, etc.) on the touch panel 131 or near the touch panel 131. Operation), and drive the corresponding connection device according to the preset program. Optionally, the touch panel 131 may include two parts: a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch position, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into contact coordinates, and then sends it To the processor 180, and can receive and execute the commands sent by the processor 180. In addition, the touch panel 131 can be implemented in multiple types such as resistive, capacitive, infrared, and surface acoustic wave. In addition to the touch panel 131, the input unit 130 may also include other input devices 132. Specifically, the other input device 132 may include, but is not limited to, one or more of a physical keyboard, function keys (such as volume control buttons, switch buttons, etc.), trackball, mouse, and joystick.

The display unit 140 may be used to display information input by the user or information provided to the user and various menus of the mobile phone. The display unit 140 may include a display panel 141. Optionally, the display panel 141 may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), etc. Further, the touch panel 131 can cover the display panel 141. When the touch panel 131 detects a touch operation on or near it, it transmits it to the processor 180 to determine the type of the touch event, and then the processor 180 responds to the touch event. The type provides corresponding visual output on the display panel 141. Although in FIG. 1, the touch panel 131 and the display panel 141 are used as two independent components to realize the input and input functions of the mobile phone, but in some embodiments, the touch panel 131 and the display panel 141 can be integrated. Realize the input and output functions of the mobile phone.

The mobile phone 100 may also include at least one sensor 150, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor. The ambient light sensor can adjust the brightness of the display panel 141 according to the brightness of the ambient light. The proximity sensor can close the display panel 141 and/or when the mobile phone is moved to the ear. Or backlight. As a kind of motion sensor, the accelerometer sensor can detect the magnitude of acceleration in various directions (usually three-axis), and can detect the magnitude and direction of gravity when it is stationary. It can be used to identify mobile phone posture applications (such as horizontal and vertical screen switching, related Games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, percussion), etc.; as for other sensors such as gyroscopes, barometers, hygrometers, thermometers, infrared sensors, etc., which can also be configured in mobile phones, I will not here Go into details.

The audio circuit 160, the speaker 161, and the microphone 162 can provide an audio interface between the user and the mobile phone. The audio circuit 160 can transmit the electrical signal converted from the received audio data to the speaker 161, which is converted into a sound signal for output by the speaker 161; on the other hand, the microphone 162 converts the collected sound signal into an electrical signal, and the audio circuit 160 After being received, it is converted into audio data, and then processed by the audio data output processor 180, and sent to, for example, another mobile phone via the RF circuit 110, or the audio data is output to the memory 120 for further processing.

Wi-Fi is a short-distance wireless transmission technology. The mobile phone can help users send and receive emails, browse web pages, and access streaming media through the Wi-Fi module 170. It provides users with wireless broadband Internet access. Although FIG. 1 shows the Wi-Fi module 170, it is understandable that it is not a necessary component of the mobile phone 100, and can be omitted as needed without changing the essence of the invention.

The processor 180 is the control center of the mobile phone. It uses various interfaces and lines to connect various parts of the entire mobile phone. It executes by running or executing software programs and/or modules stored in the memory 120 and calling data stored in the memory 120. Various functions and processing data of the mobile phone can be used to monitor the mobile phone as a whole. Optionally, the processor 180 may include one or more processing units; preferably, the processor 180 may integrate an application processor and a modem processor, where the application processor mainly processes the operating system, user interface, application programs, etc. , The modem processor mainly deals with wireless communication. It can be understood that the foregoing modem processor may not be integrated into the processor 180.

The mobile phone 100 also includes a power source 190 (such as a battery) for supplying power to various components. Preferably, the power source can be logically connected to the processor 180 through a power management system, so that functions such as charging, discharging, and power consumption management can be managed through the power management system.

Although not shown, the mobile phone 100 may also include a camera. Optionally, the position of the camera on the mobile phone 100 may be front-mounted or rear-mounted, which is not limited in the embodiment of the present application.

Optionally, the mobile phone 100 may include a single camera, a dual camera, or a triple camera, etc., which is not limited in the embodiment of the present application.

For example, the mobile phone 100 may include three cameras, of which one is a main camera, one is a wide-angle camera, and one is a telephoto camera.

Optionally, when the mobile phone 100 includes multiple cameras, the multiple cameras may be all front-mounted, or all rear-mounted, or partly front-mounted and some rear-mounted, which is not limited in the embodiment of the present application.

In addition, although not shown, the mobile phone 100 may also include a Bluetooth module, etc., which will not be repeated here.

FIG. 2 is a schematic diagram of the software structure of the mobile phone 100 according to an embodiment of the present application. Taking the mobile phone 100 operating system as the Android system as an example, in some embodiments, the Android system is divided into four layers, namely the application layer, the application framework layer (framework, FWK), the system layer, and the hardware abstraction layer. Communication between the layers through software interface.

As shown in Figure 2, the application layer may include a series of application packages, which may include applications such as short message, calendar, camera, video, navigation, gallery, and call.

The application framework layer provides an application programming interface (application programming interface, API) and a programming framework for applications in the application layer. The application framework layer may include some predefined functions, such as functions for receiving events sent by the application framework layer.

As shown in Figure 2, the application framework layer can include a window manager, a resource manager, and a notification manager.

The window manager is used to manage window programs. The window manager can obtain the size of the display screen, determine whether there is a status bar, lock the screen, take a screenshot, etc. The content provider is used to store and retrieve data and make these data accessible to applications. The data may include videos, images, audios, phone calls made and received, browsing history and bookmarks, phone book, etc.

The resource manager provides various resources for the application, such as localized strings, icons, pictures, layout files, video files, and so on.

The notification manager enables the application to display notification information in the status bar, which can be used to convey notification-type messages, and it can automatically disappear after a short stay without user interaction. For example, the notification manager is used to notify download completion, message reminders, etc. The notification manager can also be a notification that appears in the status bar at the top of the system in the form of a chart or a scroll bar text, such as a notification of an application running in the background, or a notification that appears on the screen in the form of a dialog window. For example, text messages are prompted in the status bar, prompt sounds, electronic devices vibrate, and indicator lights flash.

The application framework layer can also include:

A view system, which includes visual controls, such as controls that display text, controls that display pictures, and so on. The view system can be used to build applications. The display interface can be composed of one or more views. For example, a display interface that includes a short message notification icon may include a view that displays text and a view that displays pictures.

The phone manager is used to provide the communication function of the mobile phone 100. For example, the management of the call status (including connecting, hanging up, etc.).

The system layer can include multiple functional modules. For example: sensor service module, physical state recognition module, 3D graphics processing library (for example: OpenGL ES), etc.

The sensor service module is used to monitor the sensor data uploaded by various sensors at the hardware layer and determine the physical state of the mobile phone 100;

Physical state recognition module, used to analyze and recognize user gestures, faces, etc.;

The 3D graphics processing library is used to implement 3D graphics drawing, image rendering, synthesis, and layer processing.

The system layer can also include:

The surface manager is used to manage the display subsystem and provides a combination of 2D and 3D layers for multiple applications.

The media library supports playback and recording of a variety of commonly used audio and video formats, as well as still image files. The media library can support multiple audio and video encoding formats, such as: MPEG4, H.264, MP3, AAC, AMR, JPG, PNG, etc.

The hardware abstraction layer is the layer between hardware and software. The hardware abstraction layer can include display drivers, camera drivers, sensor drivers, etc., used to drive related hardware at the hardware layer, such as display screens, cameras, sensors, and so on.

The following embodiments can be implemented on the mobile phone 100 having the above hardware structure/software structure. The following embodiment will take the mobile phone 100 as an example to describe the error correction word ordering method provided in the embodiment of the present application.

Referring to FIG. 3, a schematic step flow chart of a method for sorting error correction words provided by an embodiment of the present application is shown. As an example and not a limitation, the method may be applied to the above-mentioned mobile phone 100, and the method may specifically include the following steps:

S301: When a character string input by a user is received, obtain a plurality of error correction words matching the character string, and determine the error correction type to which each error correction word belongs and the word order weight corresponding to the error correction type;

In this embodiment, the character string input by the user may be a pinyin character string. That is, the user inputs a pinyin character string when using the pinyin input method, and then outputs corresponding Chinese characters through matching and searching of the input method.

As shown in FIG. 4, it is a schematic diagram of the input method architecture of this embodiment. The method for sorting error correction words provided in this embodiment can be implemented in the input method architecture shown in FIG. 4. The input method architecture shown in Figure 4 mainly includes four core units: input, engine, thesaurus, and display. The input unit can provide the user with keyboard input input methods, including pinyin full key, pinyin nine keys, etc. The core processing of the input unit is to prevent accidental touch, so that the user can input the correct character string as much as possible. Of course, the input unit can also provide users with input methods in other languages, as well as various types of input methods such as strokes, handwriting, and voice.

For the engine unit, for the pinyin input method, it mainly provides the N-gram language model and Viterbi pinyin decoding, which can be combined with the vocabulary to achieve specific word generation, association and error correction functions. The vocabulary in the input method includes basic vocabulary, internet hot words, user-defined phrases, etc., and each vocabulary can be updated at a certain frequency.

The display unit of the input method can be presented to the user through the display interface of the terminal device. In addition to the basic candidate word output, it can also include other information or service recommendation information.

In this embodiment, based on the aforementioned input method architecture, the candidate word ranking process is improved, and a new error correction word ranking method is proposed. The following is a specific introduction.

Generally, when a user enters a pinyin character string, an input error may occur. At this time, the input method can automatically correct the wrong character string. For example, if the user enters the string "yiu", the input method automatically corrects it to the string "you".

After the input method corrects the incorrectly input pinyin character string, it can output an error correction word that matches the corrected character string. For example, for the character string "yiu" input by the user, the input method can output error-correcting words such as "有", "又", and "由" that match the corrected character string "you".

The above-mentioned error correction words can all be regarded as obtained after correcting an erroneous character string according to a certain type of error correction. Also take the string "yiu" as an example. After the input method corrects its errors, the outputted error correction words such as "有", "又", "由" can be regarded as correcting the "yiu" according to the adjacent key. The result of error correction. That is, the letter "i" in the character string "yiu" that has been entered incorrectly is replaced with the letter "o" adjacent to it.

Of course, the adjacent key error correction provided above is only an example, and the error correction methods provided by the input method may include many kinds, which are not limited in this embodiment.

In this embodiment, for any error correction type, a corresponding word order weight can be configured for it, so that after error correction is performed on the pinyin character string, the error correction words can be sorted according to the above word order weight.

The word order weights of various error correction types in this embodiment may be calculated based on a large amount of statistical data and error correction cases. In this embodiment, the word order weights of various error correction types are calculated by analyzing the correspondence between a large number of input wrong character strings and the Chinese characters finally input by the user, which can reflect the most common input error types of the user. Therefore, the word order weight of the error correction type corresponding to the most common input error of the user is usually larger. For example, ambiguous tone error correction, less input character error correction at the end, and so on.

It should be noted that the pinyin character string entered by the user may not be an incorrect character string. For example, when the user inputs the character string "zai", it may indicate that the user really wants to input "zai" and obtain Chinese characters that match the character string. On the other hand, the input method can also correct the error to "zhai" according to the corresponding error correction method, and provide the user with the Chinese characters matching the string "zhai" at the same time. At this time, each Chinese character matching the character string "zai" is a non-error correcting word, and the Chinese character matching the character string "zhai" is an error correcting word.

S302: Determine the weight value of each error correction word according to the word order weight of the error correction type;

In this embodiment, various error correction types can be divided into different error correction classes in advance, and for any error correction class, a word order weight is set for each error correction class.

As an example of this embodiment, multiple types of error correction can be divided into four categories: one type of error correction, two types of error correction, three types of error correction, and four types of error correction, and then set each type separately A word order weight. For example, you can set the word order weight of the error correction type 1 to be equal to the word order weight of the error correction type 2, set the word order weight of the error correction type 2 to be greater than the word order weight of the error correction category 3, and set the word order weight of the error correction category 3 to be greater than Correct the four types of word order weights, and so on.

When the weight value of each error correction word is determined according to the word order weight of the error correction type, the word order weight of the error correction type can be directly assigned to the corresponding error correction word. That is, the word order weight of the error correction class is directly used as the weight value of the error correction word obtained after the error correction is performed according to the error correction class. It is also possible to use the word order weight of the error correction class as an additional value, and add the word order weight to the original weight value of the error correction word. For example, if the word order weight of a certain error correction type is 60%, the original weight value of a certain error correction word obtained by the error correction according to the error correction type can be multiplied by 60%, as the new error correction word The weight value of is not limited in this embodiment.

S303. Sort the multiple error correction words according to the weight value of each error correction word.

After the weight value of each error correction word is determined, the error correction words can be sorted according to the size of the weight value. Generally, the larger the weight value, the higher the ranking; otherwise, the lower the ranking.

In the embodiment of the present application, when a character string input by a user is received, each error correction word can be re-determined by obtaining an error correction word that matches the character string, and then according to the word order weight of the error correction type corresponding to the error correction word. The weight value of the wrong word can be displayed to the user after sorting the error correction words according to the re-determined weight value. Generally, the error correction type with higher word order weight is the error correction for the input errors that occur more frequently when the user is input. The weight value of the error correction word can be re-determined according to the error correction type, and the more common input errors can be corrected. The corresponding error correction words are first displayed to users, which improves the error correction efficiency of the input method, and can be widely used in artificial intelligence (AI) and natural language processing fields, which helps improve input efficiency.

Referring to FIG. 5, there is shown a schematic step flowchart of a method for sorting error correction words according to another embodiment of the present application. The method may specifically include the following steps:

S501: When a character string input by a user is received, error correction is performed on the character string according to multiple preset error correction types, and the word order weights corresponding to the various error correction types are determined;

It should be noted that this method can be applied to terminal devices, such as mobile phones, tablet computers, and so on. That is, the execution subject of this embodiment is the terminal device. Taking the terminal device as a mobile phone as an example, when the user uses the pinyin input method on the mobile phone, if the pinyin character string input by the user is a wrong character string, the wrong character string can be corrected and corrected according to the method provided in this embodiment. Reorder the error-corrected words obtained after error correction, so that the error-corrected words ranked higher have a greater probability that they belong to the words that the user really wants to input.

In this embodiment, the multiple error correction types provided by the input method can be classified first. For example, the various error correction types are divided into error correction type 1, error correction type two, error correction type three, or error correction type four, etc., so that each error correction type includes at least one specific error correction type.

Generally, the types of error correction provided by input methods include user-configured fuzzy sound error correction, end-of-character error correction, adjacent key error correction, default fuzzy sound error correction, multi-input character error correction, and middle character error correction and exchange Character error correction and so on. The user-configured fuzzy tone error correction may refer to the type of error correction manually configured by the user. For the errors that occur frequently in the input process of the user, the input method can provide the user with the function of manually configuring the error correction. For example, if the user often confuses the letters "f" and "h" during the input process, he can manually choose to configure the above two letters as an error correction pair, and subsequently, when inputting, it can firstly detect whether the above two letters are entered incorrectly Case.

The error correction of fewer input characters at the end can mean that the pinyin has not been input completely. By automatically filling in all possible legal pinyins at the end, the corresponding error correction word can be obtained. For example, for the input string "pe", by adding other letters at the end, legal pinyin such as "pei", "pen" or "peng" can be obtained.

The adjacent key error correction can refer to the letters pressed to the adjacent key position during input. When the adjacent key error correction is performed, the offset letter needs to be corrected back. Under normal circumstances, adjacent key error correction should be limited to not more than one key position.

The default fuzzy sound error correction may refer to some fuzzy sound error correction supported by the input method by default when the user does not configure the fuzzy sound error correction by himself. The difference between default fuzzy sound correction and manual fuzzy sound is that the number of error correction words is limited, and the word order weight is relatively small.

Error correction for multiple input characters can mean that the user has an extra letter in the input pinyin string. The multiple input character can be a repeated letter.

The error correction of missing characters in the middle can mean that a letter is missed in the middle of the pinyin string. It should be noted that the error correction for missing characters in the middle is only for the case where a letter is missed in the middle of the character string, not for the case where a letter is missed before or after the character string.

Swap character error correction can mean that in the string, the adjacent letter sequence has an exchange error, and the error correction can be completed by just turning the order of the two letters.

As shown in Table 1, it is the definition, scope and corresponding description of various error correction types in this embodiment.

Table I:

For the above-mentioned various error correction types, they can be divided into multiple error correction classes, and a corresponding error correction word number threshold and word order weight can be set for each error correction class.

In this embodiment, the threshold for the number of error correction words may be the maximum number of error correction words of this type that are allowed to be displayed to the user when performing error correction according to a certain error correction type. For example, if the threshold of the number of error correction words corresponding to a certain error correction type is 5, it means that when the pinyin field string is corrected according to the type, the maximum number of error correction words provided to the user is not more than 5.

As an example of this embodiment, when the error correction types are divided into four error correction types, the number threshold of the number of error correction words of the first type of error correction can be set to be greater than the first number threshold, and the second type of error correction can be set The threshold for the number of error correction words is less than or equal to the second number threshold, the threshold for the number of error correction words for the three types of error correction is less than or equal to the third number threshold, and the threshold for the number of error correction words for the four types of error correction is less than or equal to the third number threshold. Equal to the fourth number threshold, the first number threshold can be greater than the second number threshold, the second number threshold can be greater than the third number threshold, and the third number threshold can be greater than the fourth number threshold.

For example, the first number threshold can be set to infinity, which means that when performing error correction according to the error correction type belonging to the error correction category, it is not limited by the number of error correction words, and all error correction words are displayed to the user. The second number threshold can be set to 5, the third number threshold can be set to 2, the fourth number threshold can be set to 1, and so on. Of course, the above is only an example of this embodiment, and those skilled in the art can specifically select the threshold for the number of error correction words according to actual needs, which is not limited in this embodiment.

The word order weight in this embodiment may refer to a discount value that discounts the weight value of the error correction word. For example, if the word order weight is 1, it means that the weight value of the error correction words obtained by this error correction type is not discounted; if the word order weight of a certain error correction type is 80%, it means that the error correction type obtained according to the error correction type is 80%. The weight value of the wrong word needs to be discounted by 20%, thereby reducing the weight value of the error-correcting word.

As shown in Table 2, it is an example of classification of error correction types in this embodiment.

Table II:

S502: If the error correction of the character string according to the target error correction type is successful, a target character string corresponding to the target error correction type is generated, and the target error correction type is any of the multiple error correction types. One kind

In this embodiment, when the pinyin character string input by the user is received, it can be corrected first according to the above-mentioned various error correction types. If the error correction is successful, the target character corresponding to the error correction type can be obtained. string.

For example, for the character string "png" input by the user, the target character strings "pang", "peng" and "ping" corresponding to this error correction type can be obtained by performing error correction according to the above-mentioned various error correction types. ",and many more.

It should be noted that there may be more than one type of error correction for any character string input by the user. That is, the input method can perform error correction on the character string according to multiple different error correction types, which is not limited in this embodiment.

S503. Obtain multiple error correction words that match the target character string.

For the obtained target character string, the input method can provide error correction words matching each target character string according to the existing word output method.

When there are multiple error correction types, there may be multiple error correction words corresponding to each error correction type.

S504. Obtain the initial weight value of each error correction word, and determine the weight of each error correction word according to the initial weight value of each error correction word and the word order weight of the error correction type corresponding to each error correction word value;

The initial weight value of each error correction word is the weight value of each word obtained according to the existing sorting strategy of the input method, and the initial weight value reflects the sort position of each error correction word before processing.

In this embodiment, when the initial weight value of each error correction word is obtained, and the word order weight of the error correction type corresponding to the error correction word is obtained, the initial weight value may be compared with the word order weight of the corresponding error correction type. Multiply to get the final weight value of each error correction word.

For example, if a certain error correction word is given according to the error correction of the adjacent key, when calculating the final weight value of the error correction word, the initial weight value can be multiplied by 60%, so that after processing, its final weight value will be Will be less than the initial weight value. Correspondingly, the ranking position of the error correction word among all candidate words may move backward.

After the weight value of each error correction word is determined, the error correction words can be sorted according to the size of the weight value. Generally, the larger the weight value, the higher the ranking.

S505: Count the number of error correction words corresponding to the various error correction types respectively;

In this embodiment, because different error correction types may give multiple error correction words, in order to reduce some unnecessary error correction words from appearing in the candidate word list, statistics can also be made for each error correction type according to the The number of error-corrected words obtained by type of error correction.

For example, counting the number of error-corrected words obtained by error correction according to manual fuzzy sound, counting the number of error-corrected words obtained by error correction according to neighbor keys, and so on.

S506: If the number of error correction words is more than the threshold value of the number of error correction words corresponding to the error correction type, delete error correction words that are more than the threshold value of the number of error correction words;

In this embodiment, after statistics of various types of error correction words are obtained according to error correction types, the more error correction words can be processed according to the threshold value of the number of error correction words as shown in Table 2.

In the specific implementation, it can be seen from Table 2 that the number of error-corrected words obtained by manual fuzzy tone error correction is not limited, and all the error-corrected words obtained according to this type of error correction can be kept in the candidate words; for less input, this For one type of error correction, only 5 error correction words are allowed to be retained. If 7 error correction words are obtained for error correction according to less input, the more than 2 error correction words need to be deleted; for other types of error correction Word processing can also be performed in the above-mentioned manner, which will not be repeated in this embodiment.

S507: Sort the remaining error correction words according to the weight values of the remaining error correction words.

Taking the 7 error correction words obtained by performing error correction according to the above-mentioned less input as an example, since it exceeds the maximum number of error correction words allowed by the error correction type of the less input one, two of the error correction words should be deleted.

In a specific implementation, two error-correcting words with a relatively small weight value can be deleted, and the remaining five error-correcting words with a relatively large weight value are retained.

In the embodiment of this application, by classifying various error correction types, and setting the number of error correction word thresholds and word order weights corresponding to each error correction type, the input pinyin character string can be compared according to various error correction types. After error correction, the weight value of each error correction word is re-determined according to the word order weight, and the error correction words exceeding the number threshold are deleted to obtain the candidate error correction words that are finally presented to the user. By subdividing the error correction types, this embodiment solves the problems of error correction, error correction failure, and excessive error correction during the input method error correction, and can present the user with the most likely words that the user really wants to input, and reduce The negative influence brought by the automatic error correction function of the input method is improved, and the error correction efficiency of the Pinyin input method is improved.

Referring to FIG. 6, there is shown a schematic step flow chart of a method for sorting error correction words according to another embodiment of the present application. The method may specifically include the following steps:

S601: When a character string input by a user is received, obtain multiple error correction words matching the character string, and determine the error correction type to which each error correction word belongs and the word order weight corresponding to the error correction type;

S602: Determine the weight value of each error correction word according to the word order weight of the error correction type;

S603: Sort the multiple error correction words according to the weight value of each error correction word.

Since steps S601-S603 in this embodiment are similar to steps S301-S303 and S501-S507 in the foregoing embodiment, reference may be made to the description of the foregoing embodiment, which will not be repeated in this embodiment.

S604: Determine whether the error correction types corresponding to any two error correction words have a mutually exclusive relationship;

In this embodiment, when sorting each error correction word, it can also be judged whether the error correction types corresponding to any two error correction words have a mutually exclusive relationship. The above-mentioned mutually exclusive relationship may refer to certain two mutually exclusive relationships. The error correction words of two types of error correction cannot appear at the same time, but only one of them can appear.

In a specific implementation, based on a large amount of statistical data analysis, it can be set that the three types of error correction and the four types of error correction in the foregoing embodiment have a mutually exclusive relationship. That is, the error correction words obtained by performing error correction according to the three types of error correction will reject the error correction words obtained by performing the error correction according to the four types of error correction.

S605: If the error correction types corresponding to any two error correction words have a mutually exclusive relationship, determine the error correction type to be deleted;

In this embodiment, when the error correction types corresponding to two error correction words have a mutually exclusive relationship, one of the error correction words needs to be deleted.

As an example of this embodiment, when there are error-correcting words that have a mutually exclusive relationship, the error-correcting words contained in the error correction types with relatively small word order weights can be deleted.

Therefore, if the error correction types corresponding to any two error correction words have a mutually exclusive relationship, the word order weights of the error correction types with the mutually exclusive relationship can be compared first, and then the error correction types with the mutually exclusive relationship are determined The error correction type corresponding to the minimum word order weight is the error correction type to be deleted.

S606. Delete each error correction word matching the error correction type to be deleted.

In this embodiment, the word order weights of the four types of error correction are smaller than the word order weights of the three types of error correction. Therefore, when there are error correction words that are obtained by performing error correction according to the error correction types belonging to the three types of error correction and the four types of error correction, each error correction word corresponding to the four types of error correction needs to be deleted.

Of course, the foregoing mutually exclusive relationship belongs to a supplementary restriction when sorting error correction words in this embodiment. As shown in Table 3, other supplementary restrictions such as error correction of the preferred word can also be set.

Table Three:

Of course, the above supplementary limitation is only an example, and those skilled in the art can add other limitation content according to actual needs to optimize the sorting order of the error correction words.

As shown in Table 4, according to the error-correcting word sorting method provided in this embodiment, part of the error-corrected words are displayed after error correction is performed on part of the input pinyin character string.

Table Four:

Input pinyin	Error correction words and sorting
eili	Eh, calendar, Hitachi
daxue	University, Daxue, Daxue, capital, law
napi	That batch, where, there, that horse
zian	Zi'an, Zi'an, Xian
zianzai	Now, first
szn	Tenth anniversary, archaeopteryx, three, crossbow
aan	A'an, press
wanan	Good night, ten thousand
iy	One, to
vl	Green, Lu
liag	Two
bingkui	Combined loss, ice cube
hngda	Evergrande
qinren	Relatives, lovers, Qin people
sanghai	Sanghai, Shanghai, hurt

From the above example, it can be seen that the candidate words obtained after error correction and sorting according to the error correction word ordering method provided in this embodiment are not only accurate in error correction, but the number of candidate words obtained is also relatively moderate, which conforms to the user's requirements. Actual use requirements.

By randomly selecting tens of thousands of incorrect pinyin cases and applying the error correction word sorting method provided in this embodiment for error correction and sorting, the error correction rate has increased by 40%, and the error correction rate has dropped by 30%. In terms of error correction, sorting, and the number of words, relatively balanced results were obtained. The method for sorting error correction words provided in this embodiment can be applied to the field of artificial intelligence, especially in the sub-field of natural language processing corresponding to the field of artificial intelligence. By applying the method for sorting error correction words provided by this embodiment, it can effectively improve Input efficiency and error correction efficiency.

It should be understood that the size of the sequence number of each step in the foregoing embodiment does not mean the order of execution, and the execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiment of the present application.

Corresponding to the error correction word ordering method described in the above embodiment, FIG. 7 shows a structural block diagram of an error correction word ordering device provided by an embodiment of the present application. part.

Referring to Figure 7, the device can be applied to terminal equipment, and specifically can include the following modules:

The error correction word acquisition module 701 is configured to, when a character string input by the user is received, obtain multiple error correction words matching the character string, and determine the error correction type to which each error correction word belongs and the error correction The word order weight corresponding to the type;

The weight value determining module 702 is configured to determine the weight value of each error correction word according to the word order weight of the error correction type;

The error correction word ranking module 703 is configured to rank the multiple error correction words according to the weight value of each error correction word.

In the embodiment of the present application, the error correction word acquisition module 701 may specifically include the following sub-modules:

The character string error correction sub-module is used to perform error correction on the character string according to multiple preset error correction types when the character string input by the user is received;

The target character string generation sub-module is configured to generate a target character string corresponding to the target error correction type if the error correction of the character string according to the target error correction type is successful, and the target error correction type is the multiple Any one of the types of error correction;

The error correction word acquisition sub-module is used to acquire multiple error correction words that match the target character string.

In the embodiment of the present application, the weight value determining module 702 may specifically include the following sub-modules:

The initial weight value acquisition sub-module is used to acquire the initial weight value of each error correction word;

The weight value determining sub-module is configured to determine the weight value of each error correction word according to the initial weight value of each error correction word and the word order weight of the error correction type corresponding to each error correction word.

In the embodiment of the present application, the various error correction types also have corresponding thresholds for the number of error correction words, and the error correction word ranking module 703 may specifically include the following sub-modules:

An error correction word count statistics sub-module, which is used to separately count the number of error correction words corresponding to the various error correction types;

The error correction word deletion submodule is configured to delete error correction words that are more than the error correction word number threshold if the number of error correction words is more than the threshold value of the number of error correction words corresponding to the error correction type;

The error-correcting word ordering sub-module is used to order the remaining error-correcting words according to the weight value of each of the remaining error-correcting words.

In the embodiment of the present application, the device may further include the following modules:

Mutually exclusive relationship judgment module, used to judge whether the error correction types corresponding to any two error correction words have a mutually exclusive relationship;

A type determination module to be deleted, configured to determine the error correction type to be deleted if the error correction types corresponding to any two error correction words have a mutually exclusive relationship;

The error correction word deletion module is used to delete each error correction word matching the error correction type to be deleted.

In the embodiment of the present application, the module for determining the type to be deleted may specifically include the following submodules:

The order weight comparison sub-module is used to compare the word order weights of the error correction types with the mutually exclusive relationship if the error correction types corresponding to any two error correction words have a mutually exclusive relationship;

The to-be-deleted type determining sub-module is configured to determine that the error correction type corresponding to the minimum word order weight is the error correction type to be deleted among the error correction types having a mutually exclusive relationship.

In the embodiment of the present application, the error correction type may include at least one of the first type of error correction, the second type of error correction, the third type of error correction, and the four types of error correction. The word order weights of the two types of error correction are equal, the word order weights of the two types of error correction are greater than the word order weights of the three types of error correction, and the word order weights of the three types of error correction are greater than the word order weights of the four types of error correction.

In the embodiment of the present application, the threshold of the number of error correction words of the first type of error correction is greater than the first number threshold, and the threshold of the number of error correction words of the second type of error correction is less than or equal to the second number threshold, The error correction word count threshold of the three types of error correction is less than or equal to the third number threshold, the error correction word number threshold of the four types of error correction is less than or equal to the fourth number threshold, and the first number threshold is greater than the A second number threshold, the second number threshold is greater than the third number threshold, and the third number threshold is greater than the fourth number threshold.

In the embodiment of the present application, the three types of error correction and the four types of error correction have a mutually exclusive relationship.

In the embodiment of the present application, the first type of error correction may include user-configured fuzzy tone error correction, the second type of error correction may include end-of-input character error correction, and the third type of error correction may include adjacent key error correction and At least one of the default fuzzy sound error correction, the four types of error correction may include at least one of error correction for multiple input characters, error correction for fewer input characters in the middle, and error correction for exchange characters.

As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for related parts, please refer to the description of the method embodiment.

Referring to FIG. 8, a schematic diagram of a terminal device according to an embodiment of the present application is shown. As shown in FIG. 8, the terminal device 800 of this embodiment includes a processor 810, a memory 820, and a computer program 821 that is stored in the memory 820 and can run on the processor 810. When the processor 810 executes the computer program 821, the steps in each embodiment of the above-mentioned error correction word ordering method are implemented, for example, steps S301 to S303 shown in FIG. 3. Alternatively, when the processor 810 executes the computer program 821, the functions of the modules/units in the foregoing device embodiments, for example, the functions of the modules 701 to 703 shown in FIG. 7 are realized.

Exemplarily, the computer program 821 may be divided into one or more modules/units, and the one or more modules/units are stored in the memory 820 and executed by the processor 810 to complete This application. The one or more modules/units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments may be used to describe the execution process of the computer program 821 in the terminal device 800. For example, the computer program 821 can be divided into an error correction word acquisition module, a weight value determination module, and an error correction word ranking module. The specific functions of each module are as follows:

The error correction word acquisition module is used to obtain multiple error correction words matching the character string when receiving the character string input by the user, and determine the error correction type to which each error correction word belongs and the error correction type Corresponding word order weight;

A weight value determining module, configured to determine the weight value of each error correction word according to the word order weight of the error correction type;

The error correction word ordering module is used for ordering the multiple error correction words according to the weight value of each error correction word.

The terminal device 800 may be a computing device such as a desktop computer, a notebook, or a palmtop computer. The terminal device 800 may include, but is not limited to, a processor 810 and a memory 820. Those skilled in the art can understand that FIG. 8 is only an example of the terminal device 800, and does not constitute a limitation on the terminal device 800. It may include more or less components than shown in the figure, or combine certain components, or different components. For example, the terminal device 800 may also include input and output devices, network access devices, buses, and so on.

The processor 810 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 (Application Specific Integrated Circuit, ASIC), Ready-made programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor or the like.

The memory 820 may be an internal storage unit of the terminal device 800, such as a hard disk or memory of the terminal device 800. The memory 820 may also be an external storage device of the terminal device 800, such as a plug-in hard disk equipped on the terminal device 800, a smart memory card (Smart Media Card, SMC), and a Secure Digital (SD) Card, Flash Card, etc. Further, the memory 820 may also include both an internal storage unit of the terminal device 800 and an external storage device. The memory 820 is used to store the computer program 821 and other programs and data required by the terminal device 800. The memory 820 can also be used to temporarily store data that has been output or will be output.

In the above-mentioned embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail or recorded in an embodiment, reference may be made to related descriptions of other embodiments.

A person of ordinary skill in the art may realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software depends on the specific application and design constraint conditions of the technical solution. Professionals and technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered beyond the scope of this application.

In the embodiments provided in this application, it should be understood that the disclosed error correction word ordering method, device, terminal device, and storage medium may be implemented in other ways. For example, the division of the modules or units is only a logical function division, and there may be other divisions in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored. Or not. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.

In addition, the functional units in the various embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or software functional unit.

If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the implementation of all or part of the processes in the above-mentioned embodiment methods in the present application can be accomplished by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When executed by the processor, the steps of the foregoing method embodiments can be implemented. Wherein, the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file, or some intermediate forms. The computer-readable medium may at least include: any entity or device capable of carrying computer program code to the error correction word sorting device, terminal equipment, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random Access memory (RAM, Random Access Memory), electric carrier signal, telecommunications signal, and software distribution medium. For example, U disk, mobile hard disk, floppy disk or CD-ROM, etc. In some jurisdictions, according to legislation and patent practices, computer-readable media cannot be electrical carrier signals and telecommunication signals.

Finally, it should be noted that the above are only specific implementations of this application, but the scope of protection of this application is not limited to this. Any changes or substitutions within the technical scope disclosed in this application shall be covered by this application. Within the scope of protection applied for. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

Claims (13)

1. A method for sorting error correction words, which is characterized in that it includes:

   When receiving the character string input by the user, obtain a plurality of error correction words matching the character string, and determine the error correction type to which each error correction word belongs and the word order weight corresponding to the error correction type;

   Determine the weight value of each error correction word according to the word order weight of the error correction type;

   Sort the plurality of error correction words according to the weight value of each error correction word.
2. The method according to claim 1, wherein when a character string input by a user is received, obtaining a plurality of error correction words matching the character string comprises:

   When a character string input by the user is received, error correction is performed on the character string according to a plurality of preset error correction types;

   If the error correction of the character string is successful according to the target error correction type, a target character string corresponding to the target error correction type is generated, and the target error correction type is any one of the multiple error correction types ；

   Acquire multiple error correction words matching the target character string.
3. The method according to claim 1, wherein the determining the weight value of each error correction word according to the word order weight of the error correction type comprises:

   Acquiring the initial weight value of each error correction word;

   The weight value of each error correction word is determined according to the initial weight value of each error correction word and the word order weight of the error correction type corresponding to each error correction word.
4. The method according to claim 3, wherein the various error correction types also have corresponding thresholds for the number of error correction words, and the plurality of error correction words are evaluated according to the weight value of each error correction word. Correction words are sorted, including:

   Respectively count the number of error correction words corresponding to the various error correction types;

   If the number of error correction words is more than the threshold value of the number of error correction words corresponding to the error correction type, delete the error correction words that are more than the threshold value of the number of error correction words;

   Sort the remaining error correction words according to the weight values of the remaining error correction words.
5. The method according to claim 1, further comprising:

   Determine whether the error correction types corresponding to any two error correction words have a mutually exclusive relationship;

   If the error correction types corresponding to any two error correction words have a mutually exclusive relationship, determine the error correction type to be deleted;

   Delete each error correction word that matches the error correction type to be deleted.
6. The method according to claim 5, wherein if the error correction types corresponding to any two error correction words have a mutually exclusive relationship, determining the error correction type to be deleted comprises:

   If the error correction types corresponding to any two error correction words have a mutually exclusive relationship, then compare the word order weights of the error correction types that have a mutually exclusive relationship;

   Among the error correction types having a mutually exclusive relationship, it is determined that the error correction type corresponding to the minimum word order weight is the error correction type to be deleted.
7. The method according to any one of claims 1-6, wherein the error correction type includes at least one of the first type of error correction, the second type of error correction, the third type of error correction, and the four types of error correction. The word order weight of the first type of error correction is equal to the word order weight of the second type of error correction, the word order weight of the second type of error correction is greater than the word order weight of the third type of error correction, and the word order weight of the third type of error correction is greater than The four types of word order weights for error correction.
8. The method according to claim 7, wherein the threshold of the number of error correction words of the first type of error correction is greater than the first number threshold, and the threshold of the number of error correction words of the second type of error correction is less than or equal to the second The number threshold of the three types of error correction words is less than or equal to the third number threshold, the number of error correction words of the four types of error correction thresholds is less than or equal to the fourth number threshold, and the first The number threshold is greater than the second number threshold, the second number threshold is greater than the third number threshold, and the third number threshold is greater than the fourth number threshold.
9. The method according to claim 7, wherein the three types of error correction and the four types of error correction have a mutually exclusive relationship.
10. The method according to claim 7, wherein the first type of error correction includes user-configured fuzzy tone error correction, the second type of error correction includes end-of-input character error correction, and the third type of error correction includes adjacent key At least one of error correction and default ambiguous tone error correction, and the four types of error correction include at least one of error correction for multiple input characters, error correction for middle characters and exchange characters.
11. A sorting device for error correction words, which is characterized in that it comprises:

    The error correction word acquisition module is used to obtain multiple error correction words matching the character string when receiving the character string input by the user, and determine the error correction type to which each error correction word belongs and the error correction type Corresponding word order weight;

    A weight value determining module, configured to determine the weight value of each error correction word according to the word order weight of the error correction type;

    The error correction word ordering module is used for ordering the multiple error correction words according to the weight value of each error correction word.
12. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the computer program as claimed in claims 1 to 10. The method for sorting error correction words according to any one of them.
13. A computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program is executed by a processor to implement the error correction word sorting according to any one of claims 1 to 10 method.

Images