CN114461196B - Intelligent auxiliary method and system for software development - Google Patents
Intelligent auxiliary method and system for software development Download PDFInfo
- Publication number
- CN114461196B CN114461196B CN202210157721.8A CN202210157721A CN114461196B CN 114461196 B CN114461196 B CN 114461196B CN 202210157721 A CN202210157721 A CN 202210157721A CN 114461196 B CN114461196 B CN 114461196B
- Authority
- CN
- China
- Prior art keywords
- information
- target
- software development
- sdk
- code
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/30—Creation or generation of source code
- G06F8/33—Intelligent editors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/30—Creation or generation of source code
- G06F8/36—Software reuse
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/40—Transformation of program code
- G06F8/41—Compilation
- G06F8/43—Checking; Contextual analysis
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Stored Programmes (AREA)
Abstract
The invention discloses an intelligent auxiliary method and system for software development, and relates to the technical field of computers. Acquiring software development information of a target account of a logged software development intelligent auxiliary system, and calling a target Software Development Kit (SDK) according to the software development information; when a calling request aiming at a target method is detected, extracting context information of a target code line where the target method is located; acquiring a preset number of methods to be selected with high similarity to the context information from the target SDK; generating a code abstract of the method to be selected aiming at each method to be selected to obtain the method to be displayed; and displaying the method to be displayed on a software development interface. The target SDK can be automatically called through the software development information, and when the method is called, the method to be selected can be automatically matched according to the context information of the target code line where the target method is located, the code abstract of the method to be selected is generated, and the program code compiling efficiency is improved.
Description
Technical Field
The invention relates to the technical field of computers, in particular to an intelligent auxiliary method and system for software development.
Background
Software development is the process of building a software system or software parts in a system according to user requirements, including system engineering of demand capture, demand analysis, design, implementation, and testing. Program code writing is a vital part of the overall software development process.
The developer can use an SDK (Software Development Kit) to assist the writing process during the writing process of the program code, wherein the SDK contains some callable methods (written functional function code) which can be used or referred by the developer. However, developers need to call the SDK and find a needed method in the SDK, which greatly affects the efficiency of writing program codes.
Disclosure of Invention
The present invention is directed to solve the problems of the background art, and provides an intelligent auxiliary method and system for software development.
The purpose of the invention can be realized by the following technical scheme:
in a first aspect, an embodiment of the present invention first provides an intelligent auxiliary method for software development, which is applied to an intelligent auxiliary system for software development, and the method includes:
acquiring software development information of a target account which has logged in the intelligent software development auxiliary system, and calling a target Software Development Kit (SDK) according to the software development information; the software development information comprises developer information and software information to be developed;
when a calling request aiming at a target method is detected, extracting context information of a target code line where the target method is located; the context information is preset character information contained in a preset number of line code lines containing the target code lines;
acquiring a preset number of methods to be selected with high similarity to the context information from the target SDK;
generating a code abstract of the method to be selected aiming at each method to be selected to obtain the method to be displayed; the method comprises the steps of storing written function codes in the target SDK;
and displaying the method to be displayed on a software development interface.
Optionally, the developer information includes software development tool information that the developer used and SDK information that the developer called; the software information to be developed comprises software type information and software configuration items;
acquiring software development information of a target account of a logged-in software development intelligent auxiliary system, and calling a target SDK according to the software development information, wherein the software development information comprises the following steps:
determining a target SDK type according to SDK information called by a developer and the software type information;
determining a target SDK version according to software development tool information used by a developer and the software configuration item;
and calling the target SDK according to the type of the target SDK and the version of the target SDK.
Optionally, the context information comprises row context information and column context information; the line context information is first preset character information contained in the target code line; the column context information is second preset character information contained in a preset number of line code lines before and after the target code line; the first preset character information comprises at least one of a method name, a Java keyword, a class name and an interface name; the second preset character information comprises at least one of a method name, a Java keyword, a class name, an interface name and a value operator.
Optionally, obtaining a preset number of candidate methods with high similarity to the context information from the target SDK includes:
matching a preset number of methods in the target SDK as a first method by using the name and the type of the target method as indexes;
generating an identifier unique to each first method, and constructing a first method list of an inverted index structure by taking the identifier of each first method as a value and the context information as a key of the inverted index structure;
calculating hash values of the context information, and calculating hash values of the first methods according to the first method list;
and determining a preset number of first methods with high similarity as candidate methods according to the hash value of each first method and the hash value of the context information.
Optionally, for each candidate method, generating a code abstract of the candidate method to obtain a to-be-displayed method, including:
generating an abstract syntax tree AST and a token ID of each candidate method;
inputting the AST and the token ID into a pre-trained double-encoder code abstract model to generate a code abstract of the candidate method; the dual-encoder code digest model encodes the AST and the token ID through two encoders, respectively, and combines output results of the two encoders to generate a code digest through a decoder.
In a second aspect, an embodiment of the present invention provides an intelligent auxiliary system for software development, including:
the SDK auxiliary module is used for acquiring software development information of a target account of the logged software development intelligent auxiliary system and calling a target SDK according to the software development information; the software development information comprises developer information and software information to be developed;
the context information extraction module is used for extracting context information of a target code line where a target method is located when a calling request for the target method is detected; the context information is preset character information contained in a preset number of line code lines containing the target code lines;
a candidate method matching module, configured to obtain, in the target SDK, a preset number of candidate methods with high similarity to the context information; the method comprises the steps of storing written function codes in the target SDK;
the code abstract generating module is used for generating a code abstract of each method to be selected to obtain the method to be displayed;
and the display module is used for displaying the method to be displayed on a software development interface.
Optionally, the developer information includes software development tool information that the developer used and SDK information that the developer called; the software information to be developed comprises software type information and software configuration items;
an SDK assistance module comprising:
the development information acquisition sub-module is used for acquiring software development information of a target account of the logged software development intelligent auxiliary system;
the SDK type determining sub-module is used for determining a target SDK type according to the SDK information which is called by a developer and the software type information;
the SDK version determining submodule is used for determining a target SDK version according to software development tool information used by a developer and the software configuration item;
and the SDK version calling sub-module is used for calling the target SDK according to the target SDK type and the target SDK version.
Optionally, the context information comprises row context information and column context information; the line context information is first preset character information contained in the target code line; the column context information is second preset character information contained in a preset number of line code lines before and after the target code line; the first preset character information comprises at least one of a method name, a Java keyword, a class name and an interface name; the second preset character information comprises at least one of a method name, a Java keyword, a class name, an interface name and a value operator.
Optionally, the candidate method matching module includes:
a first matching sub-module, configured to match a preset number of methods in the target SDK as a first method using the name and the type of the target method as an index;
a first method list creating submodule for generating, for each first method, an identifier unique to the first method, and creating a first method list of an inverted index structure with the identifier of each first method as a value and the context information as a key of the inverted index structure;
the calculation submodule is used for calculating the hash value of the context information and calculating the hash value of each first method according to the first method list;
and the second matching submodule is used for determining a preset number of first methods with high similarity as the candidate methods according to the hash value of each first method and the hash value of the context information.
Optionally, the code summary generation module includes:
the preprocessing submodule is used for generating AST and token ID of each candidate method;
the coding and decoding submodule inputs the AST and the token ID into a pre-trained double-coder code abstract model to generate a code abstract of the method to be selected; the dual-encoder code digest model encodes the AST and the token ID through two encoders, respectively, and combines output results of the two encoders to generate a code digest through a decoder.
The software development intelligent auxiliary method provided by the embodiment of the invention is applied to a software development intelligent auxiliary system, acquires software development information of a target account of a logged software development intelligent auxiliary system, and calls a target Software Development Kit (SDK) according to the software development information; the software development information comprises developer information and software information to be developed; when a calling request aiming at a target method is detected, extracting context information of a target code line where the target method is located; the context information is preset character information contained in a preset number of line code lines containing target code lines; the method comprises the steps of storing written functional function codes in a target SDK; acquiring a preset number of methods to be selected with high similarity to the context information from the target SDK; generating a code abstract of the method to be selected aiming at each method to be selected to obtain the method to be displayed; and displaying the method to be displayed on a software development interface. The target SDK can be automatically called through the software development information, and when the method is called, the method to be selected can be automatically matched according to the context information of the target code line where the target method is located, the code abstract of the method to be selected is generated, and the program code compiling efficiency is improved.
Drawings
The invention will be further described with reference to the accompanying drawings.
Fig. 1 is a block diagram of an intelligent auxiliary system for software development according to an embodiment of the present invention;
fig. 2 is a flowchart of an intelligent assistance method for software development according to an embodiment of the present invention;
FIG. 3 is a flowchart of another intelligent assistance method for software development according to an embodiment of the present invention;
FIG. 4 is a flowchart of another intelligent assistance method for software development according to an embodiment of the present invention;
fig. 5 is a flowchart of another intelligent assistance method for software development according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention also provides an intelligent auxiliary system for software development. Referring to fig. 1, fig. 1 is a block diagram of an intelligent auxiliary system for software development according to an embodiment of the present invention. The system comprises:
the SDK auxiliary module 101 is used for acquiring software development information of a target account of a logged software development intelligent auxiliary system and calling a target SDK according to the software development information; the software development information comprises developer information and software information to be developed;
the context information extracting module 102 is configured to, when a call request for a target method is detected, extract context information of a target code line where the target method is located; the context information is preset character information contained in a preset number of line code lines containing target code lines; the method comprises the steps of storing written functional function codes in a target SDK;
the candidate method matching module 103 is configured to obtain a preset number of candidate methods with high similarity to the context information from the target SDK;
a code abstract generating module 104, configured to generate a code abstract of each candidate method to obtain a method to be displayed;
and the display module 105 displays the method to be displayed on the software development interface.
Based on the intelligent auxiliary system for software development provided by the embodiment of the invention, the target SDK can be automatically called through the software development information, and when the method is called, the method to be selected can be automatically matched according to the context information of the target code line where the target method is located, so that the code abstract of the method to be selected is generated, and the efficiency of programming the program code is improved.
In one embodiment, the developer information includes software development tool information that the developer used and SDK information that the developer called; the software information to be developed comprises software type information and software configuration items;
the SDK assistance module 101 includes:
the development information acquisition sub-module is used for acquiring software development information of a target account of the logged software development intelligent auxiliary system;
the SDK type determining submodule is used for determining a target SDK type according to the SDK information and the software type information which are called by a developer;
the SDK version determining submodule is used for determining a target SDK version according to software development tool information and software configuration items used by developers;
and the SDK version calling sub-module is used for calling the target SDK according to the target SDK type and the target SDK version.
In one embodiment, the context information includes row context information and column context information; the line context information is first preset character information contained in a target code line; the column context information is second preset character information contained in a preset number of line code lines before and after the target code line; the first preset character information comprises at least one of a method name, a Java keyword, a class name and an interface name; the second preset character information comprises at least one of a method name, a Java keyword, a class name, an interface name and a value operator.
In one embodiment, the candidate method matching module 103 includes:
the first matching submodule is used for matching a preset number of methods in the target SDK as a first method by using the name and the type of the target method as indexes;
a first method list creating submodule for generating, for each first method, an identifier unique to the first method, and creating a first method list of an inverted index structure with the identifier of the respective first method as a value and context information as a key of the inverted index structure;
the calculation submodule is used for calculating the hash value of the context information and calculating the hash value of each first method according to the first method list;
and the second matching submodule is used for determining a preset number of first methods with high similarity as candidate methods according to the hash value of each first method and the hash value of the context information.
In one embodiment, code digest generation module 104 includes:
the preprocessing submodule is used for generating AST and token ID of each candidate method;
the coding and decoding submodule inputs the AST and the token ID into a pre-trained double-encoder code abstract model and generates a code abstract of the candidate method; the dual-encoder code digest model encodes the AST and the token ID by two encoders, respectively, and combines the output results of the two encoders to generate a code digest by a decoder.
Based on the same inventive concept, the embodiment of the invention also provides an intelligent auxiliary method for software development. Referring to fig. 2, fig. 2 is a flowchart of an intelligent assistance method for software development according to an embodiment of the present invention. The method is applied to the software development intelligent auxiliary system (hereinafter referred to as an auxiliary system), and can comprise the following steps:
s201, acquiring software development information of a target account of the logged software development intelligent auxiliary system, and calling a target Software Development Kit (SDK) according to the software development information.
S202, when a call request for the target method is detected, extracting the context information of the target code line where the target method is located.
S203, obtaining a preset number of candidate methods with high similarity to the context information from the target SDK.
S204, generating a code abstract of the method to be selected aiming at each method to be selected to obtain the method to be displayed;
and S205, displaying the method to be displayed on a software development interface.
The software development information comprises developer information and information of software to be developed. The context information is preset character information contained in a preset number of line code lines containing target code lines, wherein the method is a written function code stored in the target SDK.
Based on the intelligent auxiliary method for software development provided by the embodiment of the invention, the auxiliary system can automatically call the target SDK through software development information, and automatically match the method to be selected according to the context information of the target code line where the target method is located when the method is called, so as to generate the code abstract of the method to be selected, thereby improving the efficiency of programming the program code.
In one implementation, the method to be displayed is marked with a code abstract, so that developers can understand the code of the method to be displayed conveniently, and the code compiling efficiency can be improved.
In one implementation, the auxiliary system may determine a plurality of rectangular blank areas of the current software development interface, select a rectangular blank area with the largest area as a to-be-displayed area, and intelligently display a to-be-displayed method in the to-be-displayed area for a developer to view.
In one embodiment, the developer information includes software development tool information that the developer used and SDK information that the developer called; the information of the software to be developed comprises software type information and software configuration items.
Referring to fig. 3, step S201 includes, on the basis of fig. 2:
s2011, the target SDK type is determined according to the SDK information and the software type information that the developer called once.
S2012, determining the target SDK version according to the software development tool information and the software configuration items used by the developer.
S2013, calling the target SDK according to the type and the version of the target SDK.
In one implementation, the SDK is a set of professional services, such as providing an android development tool, or services developed based on hardware, and may also be an SDK for a certain software function, such as a push technology, an image recognition technology, a mobile payment technology, and the like. The auxiliary system can quickly determine the target SDK type required by the developer according to the SDK information called by the developer and the software type information of the software to be developed. Because the same type of SDK may have different versions, the auxiliary system may determine the target SDK version according to the software development tool information currently used by the developer and the software configuration item of the software to be developed. The auxiliary system automatically calls the target SDK according to the type and the version of the target SDK, developers do not need to call the SDK by themselves, and software development efficiency is improved.
In one embodiment, the context information includes row context information and column context information; the line context information is first preset character information contained in a target code line; the column context information is second preset character information contained in a preset number of line code lines before and after the target code line; the first preset character information comprises at least one of a method name, a Java keyword, a class name and an interface name; the second preset character information comprises at least one of a method name, a Java keyword, a class name, an interface name and a value operator.
In one implementation, in step S203, a preset number of candidate methods with high similarity to the row context information and/or the column context information may be obtained in the target SDK.
In one implementation, in step S203, the row context information may be used to perform matching in the target SDK, and if no method is matched, the column context information may be used to perform matching.
In one embodiment, referring to fig. 4, step S203 on the basis of fig. 2 comprises:
s2031, a preset number of methods are matched in the target SDK using the name and type of the target method as an index as a first method.
S2032, for each first method, generating an identifier unique to the first method, and constructing a first method list of the inverted index structure with the identifier of each first method as a value and the context information as a key of the inverted index structure.
S2033, hash values of the context information are calculated, and hash values of the respective first methods are calculated from the first method list.
S2034, determining a preset number of first methods with high similarity as candidate methods according to the hash value of each first method and the hash value of the context information.
In one implementation, the auxiliary system may compose key-value pairs using each preset character in the context information as a key and an identifier of the respective first method as a value. The first method list is arranged in a reverse index mode, and all first methods containing the preset characters are determined aiming at each preset character.
In one implementation, the auxiliary system may combine all the preset characters in the context information, calculate a hash value (a first hash value) of the combined preset characters, and correspondingly calculate a hash value (a second hash value) of each first method according to the first method list. A hamming distance between the first hash value and the second hash value may be calculated to determine a similarity of the context information and each of the first methods.
In one embodiment, referring to fig. 5, step S204 on the basis of fig. 2 comprises:
s2041, aiming at each candidate method, generating an abstract syntax tree AST and a token ID of the candidate method;
s2042, inputting the AST and the token ID into a pre-trained double-encoder code abstract model, and generating a code abstract of the candidate method; the dual-encoder code digest model encodes the AST and the token ID by two encoders, respectively, and combines the output results of the two encoders to generate a code digest by a decoder.
In one implementation, the dual-encoder code digest model may employ a LSTM (Long short-term memory) model, or may employ an RNN (Recurrent Neural Network) model.
While one embodiment of the present invention has been described in detail, the description is only a preferred embodiment of the present invention and should not be taken as limiting the scope of the invention. All equivalent changes and modifications made within the scope of the present invention shall fall within the scope of the present invention.
Claims (8)
1. An intelligent auxiliary method for software development is applied to an intelligent auxiliary system for software development, and comprises the following steps:
acquiring software development information of a target account which has logged in the intelligent software development auxiliary system, and calling a target Software Development Kit (SDK) according to the software development information; the software development information comprises developer information and software information to be developed;
when a calling request aiming at a target method is detected, extracting context information of a target code line where the target method is located; the context information is preset character information contained in a preset number of line code lines, and the preset number of line code lines contain the target code lines;
acquiring a preset number of methods to be selected with high similarity to the context information from the target software development kit SDK;
acquiring a preset number of candidate methods with high similarity to the context information from the target software development kit SDK, wherein the method comprises the following steps:
using the name and the type of the target method as indexes, and matching a preset number of methods in the target software development kit SDK as a first method;
generating an identifier unique to each first method, and constructing a first method list of an inverted index structure by taking the identifier of each first method as a value and the context information as a key of the inverted index structure;
calculating hash values of the context information, and calculating hash values of the first methods according to the first method list;
determining a preset number of first methods with high similarity as candidate methods according to the hash value of each first method and the hash value of the context information;
generating a code abstract of the method to be selected aiming at each method to be selected to obtain the method to be displayed; the method comprises the steps of storing written functional function codes in the target software development kit SDK;
and displaying the method to be displayed on a software development interface.
2. The intelligent auxiliary method for software development according to claim 1, wherein the developer information includes information of software development tools used by the developer and information of SDKs called by the developer; the software information to be developed comprises software type information and software configuration items;
acquiring software development information of a target account of a logged-in software development intelligent auxiliary system, and calling a target Software Development Kit (SDK) according to the software development information, wherein the software development information comprises the following steps:
determining a target SDK type according to SDK information called by a developer and the software type information;
determining a target SDK version according to software development tool information used by a developer and the software configuration item;
and calling a target Software Development Kit (SDK) according to the target SDK type and the target SDK version.
3. The intelligent auxiliary method for software development according to claim 1, wherein the context information comprises row context information and column context information; the line context information is first preset character information contained in the target code line; the column context information is second preset character information contained in a preset number of line code lines before and after the target code line; the first preset character information comprises at least one of a method name, a Java keyword, a class name and an interface name; the second preset character information comprises at least one of a method name, a Java keyword, a class name, an interface name and a value operator.
4. The intelligent auxiliary method for software development according to claim 1, wherein for each candidate method, generating a code abstract of the candidate method to obtain a method to be displayed, comprises:
generating an abstract syntax tree AST and a token ID of each candidate method;
inputting the AST and the token ID into a pre-trained double-encoder code abstract model to generate a code abstract of the candidate method; the dual-encoder code digest model encodes the AST and the token ID through two encoders, respectively, and combines output results of the two encoders to generate a code digest through a decoder.
5. An intelligent assistance system for software development, comprising:
the SDK auxiliary module is used for acquiring software development information of a target account of a logged software development intelligent auxiliary system and calling a target software development kit SDK according to the software development information; the software development information comprises developer information and software information to be developed;
the context information extraction module is used for extracting context information of a target code line where a target method is located when a calling request for the target method is detected; the context information is preset character information contained in a preset number of line code lines, and the preset number of line code lines contain the target code lines;
a candidate method matching module, configured to obtain, in the target software development kit SDK, a preset number of candidate methods with high similarity to the context information; the method comprises the steps of storing written functional function codes in the target software development kit SDK;
the candidate method matching module comprises:
the first matching sub-module is used for matching a preset number of methods in the target software development kit SDK as a first method by using the name and the type of the target method as indexes;
a first method list creating sub-module, configured to generate, for each first method, an identifier unique to the first method, and create a first method list of an inverted index structure by using the identifier of each first method as a value and the context information as a key of the inverted index structure;
the calculation submodule is used for calculating the hash value of the context information and calculating the hash value of each first method according to the first method list;
the second matching submodule is used for determining a preset number of first methods with high similarity according to the hash value of each first method and the hash value of the context information, and the first methods serve as methods to be selected;
the code abstract generating module is used for generating a code abstract of each method to be selected to obtain the method to be displayed;
and the display module is used for displaying the method to be displayed on a software development interface.
6. The intelligent auxiliary system for software development according to claim 5, wherein the developer information includes information of software development tools used by the developer and information of SDKs called by the developer; the software information to be developed comprises software type information and software configuration items;
an SDK assistance module comprising:
the development information acquisition submodule is used for acquiring software development information of a target account of the logged software development intelligent auxiliary system;
the SDK type determining submodule is used for determining a target SDK type according to the SDK information called by a developer and the software type information;
the SDK version determining submodule is used for determining a target SDK version according to software development tool information used by a developer and the software configuration item;
and the SDK version calling sub-module is used for calling the target software development kit SDK according to the target SDK type and the target SDK version.
7. The intelligent assistance system for software development according to claim 5, wherein the context information includes row context information and column context information; the line context information is first preset character information contained in the target code line; the column context information is second preset character information contained in a preset number of line code lines before and after the target code line; the first preset character information comprises at least one of a method name, a Java keyword, a class name and an interface name; the second preset character information comprises at least one of a method name, a Java keyword, a class name, an interface name and a value operator.
8. The intelligent auxiliary system for software development according to claim 5, wherein the code summary generation module comprises:
the preprocessing submodule is used for generating AST and token ID of each candidate method;
the coding and decoding submodule inputs the AST and the token ID into a pre-trained double-coder code abstract model to generate a code abstract of the method to be selected; the dual-encoder code digest model encodes the AST and the token ID through two encoders, respectively, and combines output results of the two encoders to generate a code digest through a decoder.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210157721.8A CN114461196B (en) | 2022-02-21 | 2022-02-21 | Intelligent auxiliary method and system for software development |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210157721.8A CN114461196B (en) | 2022-02-21 | 2022-02-21 | Intelligent auxiliary method and system for software development |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114461196A CN114461196A (en) | 2022-05-10 |
| CN114461196B true CN114461196B (en) | 2022-09-27 |
Family
ID=81414936
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210157721.8A Active CN114461196B (en) | 2022-02-21 | 2022-02-21 | Intelligent auxiliary method and system for software development |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114461196B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115358642B (en) * | 2022-10-20 | 2023-01-03 | 深圳市诚王创硕科技有限公司 | Intelligent auxiliary method and system for software development |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103336890A (en) * | 2013-06-08 | 2013-10-02 | 东南大学 | Method for quickly computing similarity of software |
| CN109918127A (en) * | 2019-03-07 | 2019-06-21 | 扬州大学 | A kind of defect error correction method based on code revision pattern differentials |
| CN111459491A (en) * | 2020-03-17 | 2020-07-28 | 南京航空航天大学 | Code recommendation method based on tree neural network |
| CN112835560A (en) * | 2021-03-04 | 2021-05-25 | 广州图创计算机软件开发有限公司 | WEB multi-terminal low-code intelligent software development platform |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11954462B2 (en) * | 2021-10-12 | 2024-04-09 | Intel Corporation | Dual bayesian encoding-decoding technique for text to code transformations |
-
2022
- 2022-02-21 CN CN202210157721.8A patent/CN114461196B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103336890A (en) * | 2013-06-08 | 2013-10-02 | 东南大学 | Method for quickly computing similarity of software |
| CN109918127A (en) * | 2019-03-07 | 2019-06-21 | 扬州大学 | A kind of defect error correction method based on code revision pattern differentials |
| CN111459491A (en) * | 2020-03-17 | 2020-07-28 | 南京航空航天大学 | Code recommendation method based on tree neural network |
| CN112835560A (en) * | 2021-03-04 | 2021-05-25 | 广州图创计算机软件开发有限公司 | WEB multi-terminal low-code intelligent software development platform |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114461196A (en) | 2022-05-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111625635B (en) | Question-answering processing method, device, equipment and storage medium | |
| CN108334487B (en) | Missing semantic information completion method and device, computer equipment and storage medium | |
| CN109325040B (en) | FAQ question-answer library generalization method, device and equipment | |
| CN109299471B (en) | Text matching method, device and terminal | |
| CN111352907A (en) | Method and device for analyzing pipeline file, computer equipment and storage medium | |
| CN109344242B (en) | Dialogue question-answering method, device, equipment and storage medium | |
| CN114461196B (en) | Intelligent auxiliary method and system for software development | |
| CN108304387B (en) | Method, device, server group and storage medium for recognizing noise words in text | |
| CN111026857A (en) | Conversation state tracking method, man-machine conversation method and system | |
| CN112925898B (en) | Question-answering method and device based on artificial intelligence, server and storage medium | |
| CN113435196B (en) | Intention recognition method, device, equipment and storage medium | |
| CN113821605A (en) | Event extraction method | |
| CN114490953A (en) | Training event extraction model, event extraction method and target event extraction model | |
| CN111708800A (en) | Query method and device and electronic equipment | |
| CN113343692B (en) | Search intention recognition method, model training method, device, medium and equipment | |
| CN112836019B (en) | Public medical health named entity identification and entity linking method and device, electronic equipment and storage medium | |
| CN113918467A (en) | Financial system testing method, device, equipment and storage medium | |
| CN117149996A (en) | Man-machine interface digital conversation mining method and AI system for artificial intelligence application | |
| US20060085414A1 (en) | System and methods for reference resolution | |
| CN115617975A (en) | Intention identification method and device for few-sample and multi-turn conversations | |
| CN113987202A (en) | Knowledge graph-based interactive telephone calling method and device | |
| CN115048102A (en) | Code generation method, device, equipment and storage medium | |
| CN113468306A (en) | Voice conversation method, device, electronic equipment and storage medium | |
| CN112307181A (en) | Corpus-specific-corpus-based corpus extraction method and corpus extractor | |
| CN112182177A (en) | User problem processing method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |