WO2019169722A1

WO2019169722A1 - Shortcut key recognition method and apparatus, device, and computer-readable storage medium

Info

Publication number: WO2019169722A1
Application number: PCT/CN2018/085255
Authority: WO
Inventors: 刘万晶; 黄胜彪; 徐钊
Original assignee: 平安科技（深圳）有限公司
Priority date: 2018-03-08
Filing date: 2018-05-02
Publication date: 2019-09-12
Also published as: CN108491379A

Abstract

Disclosed in embodiments of the present application are a shortcut key recognition method and apparatus, a device, and a computer-readable storage medium. The method comprises: reading a configuration file of a system to determine related shortcut keys, wherein a shortcut operation instruction is correspondingly provided for each shortcut key; performing voice recognition on obtained voice information to obtain text information, and performing semantic analysis on the text information to determine corresponding semantic information; and performing text recognition matching on the semantic information according to a preset rule to determine a shortcut key that matches the semantic information.

Description

Shortcut key identification method, device, device and computer readable storage medium

This application claims the priority of the Chinese Patent Application filed on March 8, 2018, the Chinese Patent Office, the application number is CN201810191036.0, and the application name is "the shortcut key identification method, device, device, and computer readable storage medium". The entire contents are incorporated herein by reference.

Technical field

The present application relates to the field of computer technologies, and in particular, to a shortcut key identification method, apparatus, device, and computer readable storage medium.

Background technique

The Integrated Development Environment (IDE) is an application for providing a program development environment. It generally includes tools such as a code editor, compiler, debugger, and graphical user interface. It also integrates code writing functions and analysis functions. Integrated development software service suites such as compilation functions and debugging functions. There are many kinds of development tools in the current IDE. Different IDEs have different combinations of shortcut keys. For programmers, remembering a variety of shortcut keys can be operated quickly and easily, but programmers need to remember in order to be able to program quickly. Living a large number of shortcuts will undoubtedly increase the programmer's workload and may make the shortcuts less fast and accurate.

Summary of the invention

The embodiment of the present application provides a shortcut key identification method, device, device, and computer readable storage medium, which can simplify the identification of shortcut keys to assist in rapid development of programming and improve work efficiency.

In one aspect, the embodiment of the present application provides a shortcut key identification method, where the method includes:

Reading a configuration file of the system to determine related shortcut keys, wherein each shortcut key is correspondingly provided with a corresponding shortcut operation instruction; performing voice recognition on the acquired voice information to obtain text information, and obtaining the text information Performing semantic analysis to determine corresponding semantic information; performing text recognition matching on the semantic information according to a preset rule to determine a shortcut key that matches the semantic information.

On the other hand, the embodiment of the present application further provides a shortcut key identification device, and the device includes:

a reading unit, configured to read a configuration file of the system to determine related shortcut keys, wherein each shortcut key is correspondingly provided with a corresponding shortcut operation instruction; and an analysis unit is configured to perform voice recognition on the acquired voice information Obtaining text information, and performing semantic analysis on the text information to determine corresponding semantic information; and determining unit, configured to perform text recognition matching on the semantic information according to a preset rule to determine that the semantic information is matched Shortcut instructions.

In another aspect, the embodiment of the present application further provides a computer device, including: a memory, configured to store a program for implementing shortcut key identification; and a processor, configured to execute a program for realizing shortcut key identification stored in the memory, To perform the method as described above.

In still another aspect, an embodiment of the present application further provides a computer readable storage medium storing one or more programs, the one or more programs being executable by one or more processors, To achieve the method as described above.

The implementation of the embodiment of the present application not only simplifies the identification of the shortcut keys, but also assists in rapid system development and programming, and improves work efficiency.

DRAWINGS

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings used in the description of the embodiments will be briefly described below. Obviously, the drawings in the following description are some embodiments of the present application, For the ordinary technicians, other drawings can be obtained based on these drawings without any creative work.

1 is a schematic flow chart of a shortcut key identification method provided by an embodiment of the present application;

2 is another schematic flowchart of a shortcut key identification method provided by an embodiment of the present application;

FIG. 3 is another schematic flowchart of a shortcut key identification method according to an embodiment of the present application; FIG.

4 is another schematic flowchart of a shortcut key identification method provided by an embodiment of the present application;

FIG. 5 is another schematic flowchart of a shortcut key identification method according to an embodiment of the present application; FIG.

FIG. 6 is a schematic block diagram of a shortcut key identification apparatus according to an embodiment of the present application; FIG.

FIG. 7 is another schematic block diagram of a shortcut key identification apparatus according to an embodiment of the present application; FIG.

FIG. 8 is another schematic block diagram of a shortcut key identification apparatus according to an embodiment of the present application; FIG.

FIG. 9 is another schematic block diagram of a shortcut key identification apparatus according to an embodiment of the present application; FIG.

FIG. 10 is another schematic block diagram of a shortcut key identification apparatus according to an embodiment of the present application; FIG.

FIG. 11 is a schematic structural diagram of a computer device according to an embodiment of the present application.

Detailed ways

The technical solutions in the embodiments of the present application are clearly and completely described in the following with reference to the drawings in the embodiments of the present application. It is obvious that the described embodiments are a part of the embodiments of the present application, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present application without departing from the inventive scope are the scope of the present application.

Please refer to FIG. 1. FIG. 1 is a schematic flow chart of a method for identifying a shortcut key according to an embodiment of the present application. The method can be run on terminals such as smart phones (such as Android phones, IOS phones, etc.), tablets, laptops, and smart devices. Specifically, the method can be applied to various development tools to assist programming, and can also be applied to office software such as OFFICE, thereby implementing shortcut operations such as creating a class, code formatting, etc., wherein the development tool can be eclipse or intellJ. IDEA, etc. As shown in FIG. 1, the steps of the method include S101 to S104.

S101: Read a configuration file of the system to determine related shortcut keys, wherein each shortcut key is correspondingly set with a corresponding shortcut operation instruction.

In the embodiment of the present application, the configuration file of the system may be a configuration file of the development tool IDE, or a configuration file of an office software such as OFFICE. By reading the configuration file, you can determine the shortcut keys recorded in the configuration file and the shortcut operation instructions that match the shortcut keys. In general, after one of the shortcut keys is called, the shortcut operation instruction corresponding to the shortcut key can be obtained and executed, thereby realizing the recognition and use of the shortcut key. For example, the shortcut key corresponding to “Copy” may be “ctrl+C”, and the “ctrl+C” shortcut key corresponds to a shortcut operation instruction for copying, and the shortcut key corresponding to “Paste” may be “ctrl+V”. The "ctrl+V" shortcut key corresponds to a shortcut operation instruction for pasting.

S102: Perform speech recognition on the acquired voice information to obtain text information, and perform semantic analysis on the text information to determine corresponding semantic information.

In the embodiment of the present application, the voice information corresponding to the voice information can be obtained by performing voice recognition on the voice information sent by the user, and the text information can also be semantically analyzed, thereby corresponding to the text information. Semantic information.

Further, as shown in FIG. 2, the step S102 specifically includes steps S201 to S202.

S201: Perform speech recognition on the acquired voice information to convert the voice information into text information.

In the embodiment of the present application, the obtained voice information may be processed correspondingly through the smart voice API. The smart voice API may be an API for voice recognition.

Further, as shown in FIG. 3, the step S201 specifically includes steps S301 to S303.

S301. Convert the acquired voice information into pure sound wave information by using voice activity detection.

In the embodiment of the present application, in general, before the voice recognition, the voice activity detection (VAD) voice signal processing technology is required to perform mute and cut off the first and last segments of the acquired voice information. Pure acoustic information is obtained to reduce noise interference. Among them, voice activity detection technology is mainly used for speech coding and speech recognition, which can simplify speech processing, and can also be used to remove non-speech segments during an audio session, such as encoding and transmission of mute data packets in IP telephony applications. Saving computation time and bandwidth, voice activity detection technology makes some column-based applications a reality.

S302, using the moving window function to frame the pure sound wave information, and performing acoustic feature extraction on the pure sound wave information after the framed.

In the embodiment of the present application, the moving window function can implement truncation of the signal, thereby realizing framing the pure acoustic wave information. At the same time, the more common acoustic feature extraction method may be to extract the MFCC feature, that is, according to the physiological characteristics of the human ear, turn each frame waveform into a multi-dimensional vector, to simply understand that this vector contains the content information of the frame speech. For example, after pure acoustic wave information is extracted by acoustic features, it can be a 12-line (assuming the acoustic feature is 12-dimensional) and a matrix of N columns, so it is called an observation sequence, where N is the total number of frames.

S303. Construct a state network by using a hidden Markov model, and find a path that best matches the pure sound wave information from the state network to obtain corresponding text information.

In the embodiment of the present application, the built-in state network refers to a state network after being developed into a phoneme network by a word-level network. In general, the speech recognition process is actually searching for an optimal path in the state network. The probability of the best path corresponding to the voice information is the largest, which is called “decoding”. The path search algorithm is a dynamic plan pruning algorithm called Viterbi algorithm for finding the global optimal path. In short, several frame speeches correspond to one state, and each of the three states is combined into one phoneme, and several phonemes are combined into one word, and then the sound wave information is finally converted into text information through the matching of the state network.

S202: Perform semantic analysis on the text information by using a natural language processing algorithm to obtain corresponding semantic information.

In the embodiment of the present application, Natural Language Processing (NLP) is a sub-area of artificial intelligence (AI), which uses the dependency relationship between words and words in a sentence to represent the syntactic structure information of a word (such as The subject-predicate, the verb-object, and the medium-structure relationship), and use the tree structure to represent the structure of the whole sentence (such as the subject-predicate, the fixed complement, etc.). By analyzing the dependency syntax structure information of the user Query, the semantic backbone and related semantic components are extracted to help the intelligent product realize the accurate understanding of the user's intention.

Further, as shown in FIG. 4, the step S202 specifically includes steps S401 to S403.

S401: Perform word segmentation and part-of-speech tagging on the text information to obtain a plurality of words marked with part of speech.

In the embodiment of the present application, the natural language processing is to enable the computer to understand the human language, that is, to understand the meaning behind the text. The word segmentation is the basis of natural language processing, for example, it can help to extract keywords and classify them. Under normal circumstances, the principle of word segmentation uses the conditional random field, and the word segmentation is carried out by the features such as position labeling and part of speech, so that several words are obtained, which can also be called obtaining a number of terms.

S402, calculating a weight value of each word.

In the embodiment of the present application, a weight can be calculated for each term after the word segmentation, and the important term should be given a higher weight. For example, the term weighting result of "what exercise is more helpful for weight loss/" may be: "What 0.1, exercise 0.5, 0.1, weight loss 0.8, help 0.3, larger 0.2". The weighting formula of Term Weighting generally consists of three parts: local, global and normalization. The Term weighting method can include F-IDF, Okapi, MI, LTU, ATC, TF-ICF, etc. Through the combination of various formulas of local, global, and normalization, different term weighting calculation methods can be generated. That is, the weight value corresponding to each word can be obtained by the term weighting calculation method.

S403. Determine that the word whose weight value is greater than or equal to the preset threshold is a keyword, and the keyword is the corresponding semantic information.

In the embodiment of the present application, a threshold is preset, a weight value corresponding to all words is obtained, and a word corresponding to a weight value greater than or equal to a preset threshold is determined as a keyword, and the keyword is a corresponding semantic information. .

S103. Perform text recognition matching on the semantic information according to a preset rule to determine a shortcut key that matches the semantic information.

In the embodiment of the present application, the preset rule may be that the semantic information is subjected to fuzzy search and parsing according to a preset Chinese vocabulary, thereby implementing text recognition of the semantic information. In general, after the specific text recognition is performed, the shortcut key corresponding to the voice information can be determined, and according to the shortcut key, the shortcut operation instruction that the user needs to call can be confirmed, that is, the corresponding voice feedback is realized.

Further, as shown in FIG. 5, the step S103 specifically includes steps S501 to S502.

S501: Obtain a preset Chinese vocabulary.

In the embodiment of the present application, a related professional term vocabulary may be created according to the existing data information, and the existing data information may be a word in a professional field and a popular word in life, and at the same time, the preset Chinese word The library can be created according to the needs of the user. For example, according to the shortcut keys and related shortcut operations configured by the system, a terminology vocabulary corresponding to the shortcut key can be created, and the terminology vocabulary is the preset Chinese vocabulary of the application.

S502: Perform fuzzy matching on the semantic information with the preset Chinese vocabulary to determine a shortcut key that matches the semantic information.

In the embodiment of the present application, by performing fuzzy matching on the semantic information with the preset Chinese vocabulary, text recognition and matching of the semantic information is implemented, thereby determining a shortcut key corresponding to the semantic information, and because Each shortcut key corresponds to a corresponding shortcut operation instruction, and at this time, a shortcut operation instruction matching the semantic information can be determined, thereby implementing a subsequent shortcut operation.

For example, in the traditional system development process, if the developer wants to copy a piece of code, then after selecting the content to be copied, after identifying the voice information including "copy", it is determined that "copy" is a keyword, at this time " "Copy" is the semantic information. By fuzzy matching the "copy" with the preset Chinese vocabulary, it can be determined that "ctrl+C" is the corresponding shortcut key, that is, the shortcut operation instruction corresponding to "ctrl+C" is determined as "Copy" matches the shortcut action instructions so that copying of the selected code is possible. Therefore, any operation that can be simplified by the shortcut key can save the key operation and directly execute the instruction through the natural language. For example, to create a test class, you only need to use the natural language to issue an instruction to create a test class.

Therefore, in general, a related terminology vocabulary can be created according to the existing data information, and then fuzzy matching is performed by synthesizing the semantics of the parsed linguistic information with the professional term vocabulary related to the creation to determine the semantic information. Matching shortcut operation instructions, then feedback to the user to perform the next operation (professional term feedback), perform corresponding operations and language feedback to execute the results, and perform customization with the feedback language to enhance user professionalism. It is convenient for users to operate and learn.

As a further embodiment, the method further comprises the steps of:

S104. Run a shortcut operation instruction corresponding to the shortcut key to implement a corresponding shortcut operation.

In the embodiment of the present application, by running the shortcut operation instruction corresponding to the shortcut key, a shortcut operation corresponding to the input voice information can be implemented. At the same time, as another embodiment, after the running shortcut operation instruction is invoked, a shortcut key corresponding to the shortcut operation instruction may be displayed, thereby facilitating the user to perform a direct operation.

For example, the method provided by the embodiment of the present application can be applied to a common IDE development tool such as Eclipse. The user expresses it through natural language without knowing the shortcut keys of some operations. For example, "I want to create a Java class of Test", the voice recognition API, the semantic recognition API, and the Chinese lexicon can be used. Fuzzy search, etc., the shortcut operation instruction corresponding to the shortcut key "alt+C" of the creation class set in the IDE development tool of Eclipse is called to create a Test.java file. Preferably, the shortcut key “alt+C” is displayed on the display screen of the terminal at the same time, so as to prompt the user to create a shortcut key of the class as “alt+C”, so that the user can directly use the corresponding shortcut key next time. Of course, you can also play the voice to remind the user.

For another example, a call of a shortcut operation instruction may be performed on the selected target by voice recognition to implement an operation process on the target. For example, select a xxx.txt file and send a voice message: “Open File”, then call the shortcut operation command, select the default open file tool to open the file, and also return the voice: “Opened xxx.txt After selecting the text content, the voice message is sent: “Copy”, at this time, it is determined that the corresponding “ctrl+C” shortcut key is copied, so that the shortcut operation instruction corresponding to the shortcut key is called to perform the copying, and the voice feedback: “ The content has been copied." Specify the text position, and send out the voice message: “Paste”. At this time, confirm the corresponding “ctrl+V” shortcut key, and then call the shortcut operation instruction corresponding to the shortcut key and paste the content in the specified position. At the same time, you can voice feedback: “Paste success".

In summary, the embodiment of the present application can not only simplify the identification of shortcut keys, but also assist in rapid system development and programming, and improve work efficiency. At the same time, the shortcut key recognition method mainly utilizes intelligent speech recognition and integrates shortcut keys in different IDEs, so that the developer can complete the corresponding shortcut operation after inputting the natural language to the computer.

Referring to FIG. 6 , corresponding to the above-mentioned shortcut key identification method, the embodiment of the present application further provides a shortcut key identification apparatus, and the apparatus 100 includes: a reading unit 101, an analysis unit 102, and a determination unit 103.

The reading unit 101 is configured to read a configuration file of the system to determine related shortcut keys, wherein each shortcut key is correspondingly provided with a corresponding shortcut operation instruction. In the embodiment of the present application, the configuration file of the system may be a configuration file of the development tool IDE, or a configuration file of an office software such as OFFICE. By reading the configuration file, you can determine the shortcut keys recorded in the configuration file and the shortcut operation instructions that match the shortcut keys. In general, after one of the shortcut keys is called, the shortcut operation instruction corresponding to the shortcut key can be obtained and executed, thereby realizing the recognition and use of the shortcut key. For example, the shortcut key corresponding to “Copy” may be “ctrl+C”, and the “ctrl+C” shortcut key corresponds to a shortcut operation instruction for copying, and the shortcut key corresponding to “Paste” may be “ctrl+V”. The "ctrl+V" shortcut key corresponds to a shortcut operation instruction for pasting.

The analyzing unit 102 is configured to perform text recognition on the acquired voice information to obtain text information, and perform semantic analysis on the text information to determine corresponding semantic information. In the embodiment of the present application, the voice information corresponding to the voice information can be obtained by performing voice recognition on the voice information sent by the user, and the text information can also be semantically analyzed, thereby corresponding to the text information. Semantic information.

Further, as shown in FIG. 7 , the analyzing unit 102 specifically includes: a voice recognition unit 201 and a semantic analysis unit 202.

The voice recognition unit 201 is configured to perform voice recognition on the acquired voice information to convert the voice information into text information. In the embodiment of the present application, the obtained voice information may be processed correspondingly through the smart voice API. The smart voice API may be an API for voice recognition.

Further, as shown in FIG. 8 , the voice recognition unit 201 specifically includes: a conversion unit 301 , a feature extraction unit 302 , and a construction unit 303 .

The converting unit 301 is configured to convert the acquired voice information into pure sound wave information through voice activity detection. In the embodiment of the present application, in general, before the voice recognition, the voice activity detection (VAD) voice signal processing technology is required to perform mute and cut off the first and last segments of the acquired voice information. Pure acoustic information is obtained to reduce noise interference. Among them, voice activity detection technology is mainly used for speech coding and speech recognition, which can simplify speech processing, and can also be used to remove non-speech segments during an audio session, such as encoding and transmission of mute data packets in IP telephony applications. Saving computation time and bandwidth, voice activity detection technology makes some column-based applications a reality.

The feature extraction unit 302 is configured to frame the pure sound wave information by using a moving window function, and perform acoustic feature extraction on the pure sound wave information after the framed. In the embodiment of the present application, the moving window function can implement truncation of the signal, thereby realizing framing the pure acoustic wave information. At the same time, the more common acoustic feature extraction method may be to extract the MFCC feature, that is, according to the physiological characteristics of the human ear, turn each frame waveform into a multi-dimensional vector, to simply understand that this vector contains the content information of the frame speech. For example, pure acoustic information can be a 12-line (assuming the acoustic feature is 12-dimensional) and a matrix of N columns, so it is called the observation sequence, where N is the total number of frames.

The constructing unit 303 is configured to construct a state network by using a hidden Markov model, and find a path that best matches the pure sound wave information from the state network to obtain corresponding text information. In the embodiment of the present application, the built-in state network refers to a state network after being developed into a phoneme network by a word-level network. In general, the speech recognition process is actually searching for an optimal path in the state network. The probability of the best path corresponding to the voice information is the largest, which is called “decoding”. The path search algorithm is a dynamic plan pruning algorithm called Viterbi algorithm for finding the global optimal path. In short, several frame speeches correspond to one state, and each of the three states is combined into one phoneme, and several phonemes are combined into one word, and then the sound wave information is finally converted into text information through the matching of the state network.

The semantic analysis unit 202 is configured to perform semantic analysis on the text information by using a natural language processing algorithm to obtain corresponding semantic information. In the embodiment of the present application, Natural Language Processing (NLP) is a sub-area of artificial intelligence (AI), which uses the dependency relationship between words and words in a sentence to represent the syntactic structure information of a word (such as The subject-predicate, the verb-object, and the medium-structure relationship), and use the tree structure to represent the structure of the whole sentence (such as the subject-predicate, the fixed complement, etc.). By analyzing the dependency syntax structure information of the user Query, the semantic backbone and related semantic components are extracted to help the intelligent product realize the accurate understanding of the user's intention.

Further, as shown in FIG. 9 , the semantic analysis unit 202 specifically includes: a word segmentation unit 401 , a calculation unit 402 , and an adjustment unit 403 .

The word segmentation unit 401 is configured to perform segmentation and part-of-speech tagging on the text information to obtain a plurality of words marked with part of speech. In the embodiment of the present application, the natural language processing is to enable the computer to understand the human language, that is, to understand the meaning behind the text. The word segmentation is the basis of natural language processing, for example, it can help to extract keywords and classify them. Under normal circumstances, the principle of word segmentation uses the conditional random field, and the word segmentation is carried out by the features such as position labeling and part of speech, so that several words are obtained, which can also be called obtaining a number of terms.

The calculating unit 402 is configured to calculate a weight value of each word. In the embodiment of the present application, a weight can be calculated for each term after the word segmentation, and the important term should be given a higher weight. For example, the term weighting result of "what exercise is more helpful for weight loss/" may be: "What 0.1, exercise 0.5, 0.1, weight loss 0.8, help 0.3, larger 0.2". The weighting formula of Term Weighting generally consists of three parts: local, global and normalization. The Term weighting method can include F-IDF, Okapi, MI, LTU, ATC, TF-ICF, etc. Through the combination of various formulas of local, global, and normalization, different term weighting calculation methods can be generated. That is, the weight value corresponding to each word can be obtained by the term weighting calculation method.

The adjusting unit 403 is configured to determine that a word whose weight value is greater than or equal to a preset threshold is a keyword, and the keyword is a corresponding semantic information. In the embodiment of the present application, a threshold is preset, a weight value corresponding to all words is obtained, and a word corresponding to a weight value greater than or equal to a preset threshold is determined as a keyword, and the keyword is a corresponding semantic information. .

The determining unit 103 is configured to perform text recognition matching on the semantic information according to a preset rule to determine a shortcut operation instruction that matches the semantic information.

Further, as shown in FIG. 10, the determining unit 103 specifically includes: an obtaining unit 501 and a matching unit 502.

The obtaining unit 501 is configured to acquire a preset Chinese vocabulary. In the embodiment of the present application, a related professional term vocabulary may be created according to the existing data information, and the existing data information may be a word in a professional field and a popular word in life, and at the same time, the preset Chinese word The library can be created according to the needs of the user. For example, according to the shortcut keys and related shortcut operations configured by the system, a terminology vocabulary corresponding to the shortcut key can be created, and the terminology vocabulary is the preset Chinese vocabulary of the application.

The matching unit 502 is configured to perform fuzzy matching on the semantic information with the preset Chinese vocabulary to determine a shortcut key that matches the semantic information. In the embodiment of the present application, by performing fuzzy matching on the semantic information with the preset Chinese vocabulary, text recognition and matching of the semantic information is implemented, thereby determining a shortcut key corresponding to the semantic information, and because Each shortcut key corresponds to a corresponding shortcut operation instruction, and at this time, a shortcut operation instruction matching the semantic information can be determined, thereby implementing a subsequent shortcut operation.

As a further embodiment, the apparatus may further comprise the following units:

The running unit 104 is configured to run a shortcut operation instruction corresponding to the shortcut key to implement a corresponding shortcut operation. In the embodiment of the present application, by running the shortcut operation instruction corresponding to the shortcut key, a shortcut operation corresponding to the input voice information can be implemented. Meanwhile, as another further embodiment, the apparatus may further include a display unit, configured to display a shortcut key corresponding to the shortcut operation instruction after the operation shortcut operation instruction is invoked, thereby facilitating the user to perform a direct operation.

The above shortcut key recognition means can be implemented in the form of a computer program which can be run on a computer device as shown in FIG. FIG. 11 is a schematic structural diagram of a computer device according to the present application. The device may be a terminal or a server, wherein the terminal may be a communication-enabled electronic device such as a smart phone, a tablet computer, a notebook computer, a desktop computer, a personal digital assistant, and a wearable device. The server can be a standalone server or a server cluster consisting of multiple servers. Referring to FIG. 11, the computer device 600 includes a processor 602, a non-volatile storage medium 603, an internal memory 604, and a network interface 605 connected by a system bus 601. The non-volatile storage medium 603 of the computer device 600 can store an operating system 6031 and a computer program 6032. When the computer program 6032 is executed, the processor 602 can be caused to execute a shortcut key identification method. The processor 602 of the computer device 600 is used to provide computing and control capabilities to support the operation of the entire computer device 600. The internal memory 604 provides an environment for the operation of a computer program in a non-volatile storage medium that, when executed by the processor, causes the processor 602 to perform the shortcut key identification method of the above-described embodiments. The network interface 605 of the computer device 600 is used to perform network communications, such as sending assigned tasks and the like. It will be understood by those skilled in the art that the embodiment of the computer device shown in FIG. 11 does not constitute a limitation on the specific configuration of the computer device. In other embodiments, the computer device may include more or fewer components than illustrated. Or combine some parts, or different parts. For example, in some embodiments, the computer device may include only a memory and a processor. In such an embodiment, the structure and function of the memory and the processor are the same as those of the embodiment shown in FIG. 11, and details are not described herein again.

The application provides a computer readable storage medium storing one or more programs, the one or more programs being executable by one or more processors to implement the above-described embodiments Key identification method.

The foregoing storage medium of the present application includes: a magnetic disk, an optical disk, a read-only memory (ROM), and the like, which can store various program codes. The units in all the embodiments of the present application may be implemented by a general-purpose integrated circuit, such as a CPU (Central Processing Unit), or by an ASIC (Application Specific Integrated Circuit). The steps in the shortcut key identification method in the embodiment of the present application may be sequentially adjusted, merged, and deleted according to actual needs. In the embodiment of the present application, the units in the shortcut key identification terminal may be combined, divided, and deleted according to actual needs.

The foregoing is only a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto, and any equivalents can be easily conceived by those skilled in the art within the technical scope disclosed in the present application. Modifications or substitutions are intended to be included within the scope of the present application. Therefore, the scope of protection of this application should be determined by the scope of protection of the claims.

Claims

A shortcut key identification method, characterized in that the method comprises:

Read the configuration file of the system to determine related shortcut keys, wherein each shortcut key is correspondingly set with a corresponding shortcut operation instruction;

Performing voice recognition on the acquired voice information to obtain text information, and performing semantic analysis on the text information to determine corresponding semantic information;

The semantic information is subjected to text recognition matching according to a preset rule to determine a shortcut key that matches the semantic information.
The method according to claim 1, wherein the speech information is obtained by performing speech recognition on the acquired speech information, and semantic analysis of the text information is performed to determine corresponding semantic information, including:

Performing voice recognition on the acquired voice information to convert the voice information into text information;

The semantic analysis of the text information is performed by a natural language processing algorithm to obtain corresponding semantic information.
The method according to claim 2, wherein the performing voice recognition on the acquired voice information to convert the voice information into text information comprises:

Converting the acquired voice information into pure sound wave information through voice activity detection;

The moving sound window function is used to frame the pure sound wave information, and the acoustic feature extraction is performed on the pure sound wave information after the framed;

Using the hidden Markov model, a state network is constructed, and the path that best matches the pure sound wave information is found from the state network to obtain the corresponding text information.
The method according to claim 2, wherein the semantic analysis of the text information by the natural language processing algorithm to obtain corresponding semantic information comprises:

Performing word segmentation and part-of-speech tagging on the text information to obtain a plurality of words marked with part of speech;

Calculate the weight value of each word;

The words whose weight value is greater than or equal to the preset threshold are determined as keywords, and the keywords are corresponding semantic information.
The method according to claim 1, wherein the text recognition matching of the semantic information according to a preset rule to determine a shortcut key that matches the semantic information comprises:

Obtain a preset Chinese vocabulary;

The semantic information is fuzzy matched with the preset Chinese vocabulary to determine a shortcut key that matches the semantic information.
A shortcut key recognition device, characterized in that the device comprises:

a reading unit, configured to read a configuration file of the system to determine related shortcut keys, wherein each shortcut key is correspondingly provided with a corresponding shortcut operation instruction;

An analyzing unit, configured to perform text recognition on the acquired voice information to obtain text information, and perform semantic analysis on the text information to determine corresponding semantic information;

And a determining unit, configured to perform text recognition matching on the semantic information according to a preset rule to determine a shortcut operation instruction that matches the semantic information.
The device according to claim 6, wherein the analyzing unit comprises:

a voice recognition unit, configured to perform voice recognition on the acquired voice information, to convert the voice information into text information;

The semantic analysis unit is configured to perform semantic analysis on the text information through a natural language processing algorithm to obtain corresponding semantic information.
The device of claim 7, wherein the speech recognition unit comprises:

a converting unit, configured to convert the acquired voice information into pure sound wave information through voice activity detection;

a feature extraction unit, configured to frame the pure sound wave information by using a moving window function, and perform acoustic feature extraction on the pure sound wave information after the framed;

The building unit is configured to construct a state network by using the hidden Markov model, and find a path that best matches the pure sound wave information from the state network to obtain corresponding text information.
The device according to claim 7, wherein the semantic analysis unit comprises:

a word segmentation unit, configured to perform segmentation and part-of-speech tagging on the text information to obtain a plurality of words marked with part of speech;

a calculation unit for calculating a weight value of each word;

The adjusting unit is configured to determine that the word whose weight value is greater than or equal to the preset threshold is a keyword, and the keyword is the corresponding semantic information.
The device of claim 6, wherein the determining unit comprises:

The obtaining unit is configured to obtain a preset Chinese vocabulary;

And a matching unit, configured to perform fuzzy matching on the semantic information with the preset Chinese vocabulary to determine a shortcut key that matches the semantic information.
A computer device, comprising:

a memory for storing a program that implements shortcut key recognition;

a processor, configured to run a program stored in the memory for implementing shortcut key identification to perform the following operations:

Read the configuration file of the system to determine related shortcut keys, wherein each shortcut key is correspondingly set with a corresponding shortcut operation instruction;

Performing voice recognition on the acquired voice information to obtain text information, and performing semantic analysis on the text information to determine corresponding semantic information;

The semantic information is subjected to text recognition matching according to a preset rule to determine a shortcut key that matches the semantic information.
The device according to claim 11, wherein the voice information is obtained by performing voice recognition on the acquired voice information, and performing semantic analysis on the text information to determine corresponding semantic information, including:

Performing voice recognition on the acquired voice information to convert the voice information into text information;

The semantic analysis of the text information is performed by a natural language processing algorithm to obtain corresponding semantic information.
The device according to claim 12, wherein the performing voice recognition on the acquired voice information to convert the voice information into text information comprises:

Converting the acquired voice information into pure sound wave information through voice activity detection;

The moving sound window function is used to frame the pure sound wave information, and the acoustic feature extraction is performed on the pure sound wave information after the framed;

Using the hidden Markov model, a state network is constructed, and the path that best matches the pure sound wave information is found from the state network to obtain the corresponding text information.
The device according to claim 12, wherein the semantic analysis of the text information by the natural language processing algorithm to obtain corresponding semantic information comprises:

Performing word segmentation and part-of-speech tagging on the text information to obtain a plurality of words marked with part of speech;

Calculate the weight value of each word;

The words whose weight value is greater than or equal to the preset threshold are determined as keywords, and the keywords are corresponding semantic information.
The device according to claim 11, wherein the text identification matching of the semantic information according to a preset rule to determine a shortcut key that matches the semantic information comprises:

Obtain a preset Chinese vocabulary;

The semantic information is fuzzy matched with the preset Chinese vocabulary to determine a shortcut key that matches the semantic information.
A computer readable storage medium, characterized in that the computer readable storage medium stores one or more programs, the one or more programs being executable by one or more processors to implement the steps of:

Read the configuration file of the system to determine related shortcut keys, wherein each shortcut key is correspondingly set with a corresponding shortcut operation instruction;

Performing voice recognition on the acquired voice information to obtain text information, and performing semantic analysis on the text information to determine corresponding semantic information;

The semantic information is subjected to text recognition matching according to a preset rule to determine a shortcut key that matches the semantic information.
The computer readable storage medium according to claim 16, wherein the speech information is obtained by performing speech recognition on the acquired speech information, and the text information is semantically analyzed to determine corresponding semantic information. include:

Performing voice recognition on the acquired voice information to convert the voice information into text information;

The semantic analysis of the text information is performed by a natural language processing algorithm to obtain corresponding semantic information.
The computer readable storage medium according to claim 17, wherein the performing voice recognition on the acquired voice information to convert the voice information into text information comprises:

Converting the acquired voice information into pure sound wave information through voice activity detection;

The moving sound window function is used to frame the pure sound wave information, and the acoustic feature extraction is performed on the pure sound wave information after the framed;

Using the hidden Markov model, a state network is constructed, and the path that best matches the pure sound wave information is found from the state network to obtain the corresponding text information.
The computer readable storage medium according to claim 17, wherein the semantic analysis of the text information by the natural language processing algorithm to obtain corresponding semantic information comprises:

Performing word segmentation and part-of-speech tagging on the text information to obtain a plurality of words marked with part of speech;

Calculate the weight value of each word;

The words whose weight value is greater than or equal to the preset threshold are determined as keywords, and the keywords are corresponding semantic information.
The computer readable storage medium according to claim 16, wherein the performing text recognition matching on the semantic information according to a preset rule to determine a shortcut key that matches the semantic information comprises:

Obtain a preset Chinese vocabulary;

The semantic information is fuzzy matched with the preset Chinese vocabulary to determine a shortcut key that matches the semantic information.