CN114675816A - Code completion ordering method and system based on user behaviors - Google Patents
Code completion ordering method and system based on user behaviors Download PDFInfo
- Publication number
- CN114675816A CN114675816A CN202210247274.5A CN202210247274A CN114675816A CN 114675816 A CN114675816 A CN 114675816A CN 202210247274 A CN202210247274 A CN 202210247274A CN 114675816 A CN114675816 A CN 114675816A
- Authority
- CN
- China
- Prior art keywords
- code
- codes
- syntax tree
- user
- abstract syntax
- 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.)
- Pending
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
- G06F8/40—Transformation of program code
- G06F8/41—Compilation
- G06F8/42—Syntactic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/60—Software deployment
- G06F8/65—Updates
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Security & Cryptography (AREA)
- Stored Programmes (AREA)
Abstract
The application relates to a code completion sorting method and a system based on user behaviors, wherein the method comprises the steps of analyzing a source code and generating an AST abstract syntax tree; analyzing user behaviors, updating the AST abstract syntax tree and determining an updating node of the AST abstract syntax tree; acquiring alternative codes matched with the characters input by the user in the AST abstract syntax tree by a similarity algorithm; acquiring code content and grammar in a specific range according to user behaviors, and eliminating alternative codes which do not accord with grammar rules; and sequencing the rest candidate codes through a preset sequencing rule, and displaying the rest candidate codes in a candidate list in an editor. According to the method and the device, the code characters input by the user are collected, the standby codes matched with the input code characters are collected from the grammar tree, and the standby codes are sequenced through specific rules, so that the accuracy of completing the codes is improved, and the use experience of programmers is improved.
Description
Technical Field
The application relates to the technical field of computer software, in particular to a code completion ordering method based on user behaviors.
Background
Vscode (visual Studio code) is a free modern lightweight code editor, the software almost supports the functions of syntax highlighting, code automatic completion, code reconstruction, view definition and the like of all mainstream development languages, and the rich and powerful functions and cross-platform support of the software become one of the most popular editors. Among them, code completion (code completion), which is a software automation technology that intuitively reduces the workload of software developers, is a key functional component of Vscode and many Integrated Development Environments (IDEs). The code completion technology predicts class names, variable names, function names, code fragments and the like in codes to be completed in real time based on input of developers and existing project codes and provides suggestion lists for the developers. With the intensive research and the application of tools related to code completion technology, code completion has become one of the most common operations for developers.
Although the intelligent code completion method has made some progress in recent years, especially the introduction of advanced technology in the fields of natural language processing and machine learning, and the accuracy is greatly improved, there still exist many problems, among which the problems affecting the user efficiency are as follows:
1) The research of the intelligent recommendation model and the intelligent recommendation algorithm focuses more on the extraction and similarity comparison of information such as semantic features and structural features in the codes, and the code completion algorithm can give correct completion suggestions under most conditions, but the recommendation list is too long.
2) The recommendation list is often sorted alphabetically, and the desired completion result is often found only after the recommendation list.
These issues affect the time at which developers review the recommendation list and the confidence in accepting the completion suggestions.
Disclosure of Invention
In order to improve the recommendation accuracy in the completion code list and improve the use experience of a user, the application provides a code completion sequencing method and system based on user behaviors.
In a first aspect, the code completion ordering method based on user behavior provided by the present application adopts the following technical scheme:
a code completion ordering method based on user behavior comprises
Analyzing the source code to generate an AST abstract syntax tree;
analyzing user behaviors, updating the AST abstract syntax tree and determining an updating node of the AST abstract syntax tree;
acquiring alternative codes matched with characters input by a user in an AST abstract syntax tree by a similarity algorithm;
Code content and grammar in a specific range are obtained according to user behaviors, and alternative codes which do not accord with grammar rules are eliminated;
and sequencing the rest candidate codes through a preset sequencing rule, and displaying the rest candidate codes in a candidate list in an editor.
Optionally, the similarity algorithm includes: and acquiring the input content of the user, and searching a matching item from the AST abstract syntax tree according to the input content to acquire the alternative code.
Optionally, when the candidate codes that do not comply with the syntax rule are excluded, the method includes:
obtaining a context and a corresponding grammar rule at the update node;
sequentially matching all the alternative codes with the context at the updating node;
and deleting the alternative codes which fail to be matched.
Optionally, the preset ordering rule includes:
judging whether updated content exists in a specific time period;
if so, arranging the sequence of the updated contents according to the priority from low to high; wherein the update content with the highest priority is ranked to the first digit of the recommendation list;
if not, giving high-to-low priority according to the cumulative usage of the recommended contents from large to small, wherein the recommended contents with the highest priority are arranged to the first position of the recommendation list.
In a second aspect, the code completion ordering system based on user behavior provided by the present application adopts the following technical solutions:
a user behavior based code completion ranking system, comprising:
the data analysis unit is used for analyzing the source code and generating an AST abstract syntax tree;
the behavior analysis unit is used for analyzing user behaviors, updating the AST abstract syntax tree and determining an updating node of the AST abstract syntax tree;
the code completion unit is used for acquiring alternative codes matched with the characters input by the user in the AST abstract syntax tree by a similarity algorithm;
the filtering unit is used for acquiring code content and grammar in a specific range according to user behaviors and eliminating alternative codes which do not accord with grammar rules; and
and the sorting unit is used for sorting the rest of the alternative codes according to a preset sorting rule and displaying the alternative codes in an alternative list in the editor.
Optionally, the similarity algorithm includes: and acquiring a cursor position and the input content of the user, and searching a matching item from the AST abstract syntax tree according to the input content to acquire the alternative code.
Optionally, the filter unit further comprises:
the data acquisition subunit is used for acquiring the context at the updated node and the corresponding grammar rule;
The data matching subunit is used for sequentially matching all the candidate codes with the context at the updating node;
and the data deleting subunit is used for deleting the candidate codes which fail to be matched.
Optionally, the sorting unit includes:
a judging subunit, configured to judge whether there is an update content within a specific time period;
the first sequencing subunit is used for sequencing the updated contents according to the sequence from low to high priority; the updated content with the highest priority is used as the recommended content with the first rank;
and the second sorting subunit is used for giving priority to the recommended contents according to the accumulated usage of the recommended contents from large to small, wherein the recommended contents with the highest priority are sorted to the first position of the recommendation list.
In a third aspect, the present application provides an intelligent device that adopts the following technical solution:
an intelligent device comprises
One or more memories for storing instructions; and
one or more processors configured to invoke and execute the instructions from the memory to perform the user behavior based code completion ordering method according to any one of the first aspect.
In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solutions:
A computer-readable storage medium, the computer-readable storage medium comprising:
a program which, when executed by a processor, performs the method of user behavior based code completion ranking according to any of the first aspects.
In summary, the present application includes at least one of the following beneficial technical effects:
1. the user programming behavior is recorded in the document updating event, the user programming behavior data is stored by combining the abstract syntax tree, the information of user operation time, frequency, times and the like is recorded in the corresponding syntax tree nodes, the code completion recommended content is sequenced by using the user programming behavior data, the code completion recommended content is not displayed according to the alphabetic order, the hit rate of the first several alternative codes is increased, and the coding efficiency is improved.
2. And filtering the recommended content by using context grammar check, deleting the recommended content with wrong grammar, reducing the length of a recommendation list and improving the use experience of programmers.
Drawings
FIG. 1 is a schematic flow chart of a method provided by an embodiment of the present application;
fig. 2 is a schematic view of a method subdivision flow provided in an embodiment of the present application.
Detailed Description
The technical solutions in the present application will be described in further detail below with reference to the accompanying drawings.
The specific embodiments are only for explaining the present application and are not limiting to the present application, and those skilled in the art can make modifications to the embodiments without inventive contribution as required after reading the present specification, but all the embodiments are protected by patent law within the scope of the claims of the present application.
The embodiment of the application provides a code completion sorting method based on user behaviors, which comprises the steps of analyzing a source code and generating an AST abstract syntax tree; analyzing user behaviors, updating the AST syntax tree when a file updating event is triggered, and determining AST syntax tree nodes where updating positions are located; acquiring a cursor position and input content of a user, searching a matching item from an AST syntax tree according to the input content to form recommended content, and triggering a completion event; obtaining context information of the cursor position and a grammar rule corresponding to the context, and filtering recommendation contents different from the grammar rule; and sequencing the recommended contents according to a preset sequencing rule.
In the embodiment of the application, code characters input by a user are collected, standby codes matched with the input code characters are collected from a syntax tree, user programming behavior data are stored by combining an abstract syntax tree, information such as user operation time, frequency and times are recorded in corresponding syntax tree nodes, the code completion recommendation contents are sequenced by using the user programming behavior data, the code completion recommendation contents are not displayed according to the alphabetic order, the hit rate of the first candidate codes is increased, and the coding efficiency is improved.
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without making any creative effort belong to the protection scope of the present application.
Embodiments of the present application are described in further detail below with reference to figures 1-2 of the specification.
As shown in fig. 1:
step S100: and analyzing the source code to generate the AST abstract syntax tree.
In computer science, an Abstract Syntax Tree (AST), or simply Syntax Tree (Syntax Tree), is an Abstract representation of a source code Syntax structure. It represents the syntactic structure of the programming language in the form of a tree, each node on the tree representing a structure in the source code.
The syntax is said to be "abstract" in that the syntax does not represent every detail that appears in the true syntax. For example, nesting brackets are implicit in the structure of the tree and are not present in the form of nodes; whereas a conditional jump statement like the if-condition-then may be represented using a node with two branches. As opposed to abstract syntax trees, there are concrete syntax trees (often called parse trees). Generally, during the translation and compilation of source code, a parser creates a parse tree. Once the AST is created, some information is added during subsequent processing, such as the semantic analysis stage.
Step S200: and analyzing the user behavior, updating the AST abstract syntax tree and determining the update node of the AST abstract syntax tree.
Wherein analyzing user behavior comprises monitoring behavior of a user to add, delete, or modify code. In the daily development process, the plug-in records the programming behavior of the user and triggers a code updating event when the programming behavior occurs to the user. And after receiving the document updating event, the plug-in records the position, content and time modified by the user, analyzes the code modified by the user, updates the modified code content to the AST syntax tree and records the user behavior data in the corresponding syntax tree node.
The analyzing the code specifically comprises the following steps:
step S210: the code is read character by character and then lexical and grammatical analysis is performed on the content of the code.
The lexical analysis is to divide the code into fixed formats after removing invalid contents such as comments, blanks and the like, and is used for determining the part of speech of each word; the syntax analysis is used to check whether there is a syntax error.
Step S220: acquiring the definition information and recording the use times and frequency of the user and the operation time corresponding to the use times according to the definition information.
The definition information comprises definition position information and definition content information, wherein the definition content information comprises variables, functions, objects and other information, and the definition position is the node position of the definition information in the AST abstract syntax tree. For example, when the user defines a function fun in the nth line, one node records the information of the fun such as name, line number, file path, etc. in the syntax tree, and then the user inputs the function fun in the m lines, the node of the fun in the AST abstract syntax tree can be found from the syntax tree, and the information of the definition position, etc. can be further acquired.
Step S300: and acquiring alternative codes matched with the characters input by the user in the AST abstract syntax tree by a similarity algorithm.
Wherein the similarity algorithm comprises: and acquiring the codes input by the user, and searching matching items from the AST abstract syntax tree according to the code content to acquire alternative codes.
The completion condition of the Vscode code can be set in plug-in development, and is typically automatically triggered when a user inputs a character such as a letter, "- >".
The acquiring of the alternative code specifically includes: monitoring a code updating event in real time, and acquiring request parameters including a cursor position from the event after receiving the code updating event; and acquiring the character content of the cursor position, taking the input character as a prefix, and searching and matching items from the syntax tree. For example, a variable count and a cmount are defined in the code and are updated into the AST abstract syntax tree, and if the user inputs c, the variable count and the cmount in the code are matched with the characters input by the user, that is, the count and the cmount can be returned to the editor for display as the alternative codes from the AST abstract syntax tree.
Step S400: and acquiring code content and grammar in a specific range according to the user behavior, and excluding alternative codes which do not accord with grammar rules.
The specific scope refers to the scope of the code, and is located in the context of the cursor position, which may be the whole sentence block, the whole class in the "{ }" or the whole line of the cursor position.
When the candidate codes which do not conform to the grammar rule are excluded, the method specifically includes the following steps, please refer to fig. 2:
step S410: acquiring a context and a corresponding grammar rule at a code updating node;
step S420: matching all the alternative codes with the contexts and the corresponding grammar rules at the code updating nodes in sequence;
step S430: and deleting the alternative codes which fail to be matched.
The matching process, for example, checks whether the left and right types of the assignment operation equal sign match, checks whether the function return value type matches, checks whether the variable type and the parameter type match, and deletes the variable that does not meet the syntax rule from the recommendation list.
Step S500: and sequencing the rest candidate codes through a preset sequencing rule, and displaying the rest candidate codes in a candidate list in an editor.
The sequencing rule comprises the following steps:
Step S510: judging whether updated content exists in a specific time period;
step S511: if so, arranging the sequence of the updated contents according to the priority from low to high; wherein the update content with the highest priority is ranked to the first digit of the recommendation list;
step S512: if not, giving high-to-low priority according to the cumulative usage of the recommended contents from large to small, wherein the recommended contents with the highest priority are arranged to the first position of the recommendation list.
The specific time period is a time period between the current code editing time point and the last code editing time point, and is a self-defined fixed value. The time of use of alternative codes is more recent, such as newly added or modified, with a greater chance of use, followed by a ranking by frequency of use. Since the programming time and the programming habit of each programmer are different, different sorting modes within and outside a specific time period have higher recommendation accuracy.
Based on the same inventive concept, the application also discloses a code completion ordering system based on user behavior, which comprises:
the data analysis unit is used for analyzing the source code and generating an AST abstract syntax tree;
The behavior analysis unit is used for analyzing the user behavior, updating the AST abstract syntax tree and determining an update node of the AST abstract syntax tree;
the code completion unit is used for acquiring an alternative code with higher similarity with the characters input by the user in the AST abstract syntax tree through a similarity algorithm;
the filtering unit is used for acquiring code content and grammar in a specific range according to user behaviors and eliminating alternative codes which do not accord with grammar rules; and
and the sorting unit is used for sorting the rest of the alternative codes according to a preset sorting rule and displaying the alternative codes in an alternative list in the editor.
Optionally, the similarity algorithm includes: and acquiring a cursor position and the input content of the user, and searching a matching item from the AST abstract syntax tree according to the input content to acquire the alternative code.
Optionally, the filtering unit further comprises:
the data acquisition subunit is used for acquiring the context at the updated node and the corresponding grammar rule;
the data matching subunit is used for sequentially matching all the candidate codes with the context at the updating node;
and the data deleting subunit is used for deleting the candidate codes which fail to be matched.
Optionally, the sorting unit includes:
A judging subunit, configured to judge whether there is an update content within a specific time period;
the first ordering subunit is used for ordering according to the priority of the updated contents from low to high; wherein the updated content with the highest priority is used as the recommended content with the first rank;
and the second sorting subunit is used for giving priority to the recommended contents according to the accumulated usage of the recommended contents from large to small, wherein the recommended contents with the highest priority are sorted to the first position of the recommendation list.
The embodiment of the application also discloses an intelligent terminal, which comprises one or more memories used for storing instructions; and one or more processors configured to retrieve and execute the instructions from the memory, and to execute any of the computer programs in the preceding method steps.
The embodiment of the application also discloses a computer readable storage medium, which comprises: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk. The computer-readable storage medium stores a program that when executed by a processor, performs any of the aforementioned document approval methods.
In the embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The above embodiments are only used to describe the technical solutions of the present application in detail, but the above embodiments are only used to help understanding the method and the core idea of the present application, and should not be construed as limiting the present application. Those skilled in the art should also appreciate that various modifications and substitutions can be made without departing from the scope of the present disclosure.
Claims (10)
1. A code completion ordering method based on user behavior is characterized in that: comprises that
Analyzing the source code to generate an AST abstract syntax tree;
analyzing user behaviors, updating the AST abstract syntax tree and determining an updating node of the AST abstract syntax tree;
acquiring alternative codes matched with characters input by a user in an AST abstract syntax tree by a similarity algorithm;
code content and grammar in a specific range are obtained according to user behaviors, and alternative codes which do not accord with grammar rules are eliminated;
and sequencing the rest candidate codes through a preset sequencing rule, and displaying the rest candidate codes in a candidate list in an editor.
2. The method of claim 1, wherein the similarity algorithm comprises: and acquiring the input content of the user, and searching a matching item from the AST abstract syntax tree according to the input content to acquire the alternative code.
3. The code completion ranking method based on user behavior according to claim 1, characterized in that: when the alternative codes which do not accord with the grammar rule are excluded, the method comprises the following steps:
obtaining a context and a corresponding grammar rule at the update node;
Sequentially matching all the alternative codes with the context at the updating node;
and deleting the alternative codes which fail to be matched.
4. The code completion ranking method based on user behavior according to claim 1, characterized in that: the preset sequencing rule comprises the following steps:
judging whether updated content exists in a specific time period;
if so, arranging the sequence of the updated contents according to the priority from low to high; wherein the update content with the highest priority is ranked to the first digit of the recommendation list;
if not, giving high-to-low priority according to the cumulative usage of the recommended contents from large to small, wherein the recommended contents with the highest priority are arranged to the first position of the recommendation list.
5. A system for code completion ranking based on user behavior, comprising:
the data analysis unit is used for analyzing the source code and generating an AST abstract syntax tree;
the behavior analysis unit is used for analyzing user behaviors, updating the AST abstract syntax tree and determining an updating node of the AST abstract syntax tree;
the code completion unit is used for acquiring alternative codes matched with the characters input by the user in the AST abstract syntax tree by a similarity algorithm;
The filtering unit is used for acquiring code content and grammar in a specific range according to user behaviors and eliminating alternative codes which do not accord with grammar rules; and
and the sorting unit is used for sorting the rest candidate codes according to a preset sorting rule and displaying the rest candidate codes in a candidate list in the editor.
6. The system of claim 5, wherein the similarity algorithm comprises: and acquiring a cursor position and the input content of the user, and searching a matching item from the AST abstract syntax tree according to the input content to acquire the alternative code.
7. The system of claim 5, wherein the filter unit further comprises:
the data acquisition subunit is used for acquiring the context at the updated node and the corresponding grammar rule;
a data matching subunit, configured to match all candidate codes with the context at the update node in sequence;
and the data deleting subunit is used for deleting the candidate codes which fail to be matched.
8. The system of claim 5, wherein the code completion ranking system based on user behavior comprises: the sorting unit includes:
A judging subunit, configured to judge whether there is an update content within a specific time period;
the first ordering subunit is used for ordering according to the priority of the updated contents from low to high; wherein the updated content with the highest priority is used as the recommended content with the first rank;
and the second sequencing subunit is used for giving priorities according to the cumulative usage of the recommended contents from large to small, wherein the recommended contents with the highest priority are ranked to the first position of the recommendation list.
9. A smart device, characterized by: the above-mentioned
One or more memories for storing instructions; and
one or more processors configured to invoke and execute the instructions from the memory to perform the user behavior based code completion ordering method of any of claims 1 to 4.
10. A computer-readable storage medium characterized by: the computer-readable storage medium includes:
program which, when executed by a processor, performs the user behavior based code completion ranking method of any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210247274.5A CN114675816A (en) | 2022-03-14 | 2022-03-14 | Code completion ordering method and system based on user behaviors |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210247274.5A CN114675816A (en) | 2022-03-14 | 2022-03-14 | Code completion ordering method and system based on user behaviors |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114675816A true CN114675816A (en) | 2022-06-28 |
Family
ID=82074176
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210247274.5A Pending CN114675816A (en) | 2022-03-14 | 2022-03-14 | Code completion ordering method and system based on user behaviors |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114675816A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115562679A (en) * | 2022-12-05 | 2023-01-03 | 广州市保伦电子有限公司 | Method and server for automatically generating codes based on Java language |
| CN115562649A (en) * | 2022-10-27 | 2023-01-03 | 新疆品宣生物科技有限责任公司 | Computer mixed program language source code auxiliary compiling method and system |
| CN117289919A (en) * | 2023-11-24 | 2023-12-26 | 浙江口碑网络技术有限公司 | Data processing method and device and electronic equipment |
| CN117289929A (en) * | 2023-11-24 | 2023-12-26 | 浙江口碑网络技术有限公司 | Plug-in frame, plug-in and data processing method and device and electronic equipment |
| CN117632106A (en) * | 2023-11-21 | 2024-03-01 | 广州致远电子股份有限公司 | Code complement method, device, equipment and storage medium |
-
2022
- 2022-03-14 CN CN202210247274.5A patent/CN114675816A/en active Pending
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115562649A (en) * | 2022-10-27 | 2023-01-03 | 新疆品宣生物科技有限责任公司 | Computer mixed program language source code auxiliary compiling method and system |
| CN115562679A (en) * | 2022-12-05 | 2023-01-03 | 广州市保伦电子有限公司 | Method and server for automatically generating codes based on Java language |
| CN115562679B (en) * | 2022-12-05 | 2023-06-30 | 广东保伦电子股份有限公司 | Java language-based automatic code generation method and server |
| CN117632106A (en) * | 2023-11-21 | 2024-03-01 | 广州致远电子股份有限公司 | Code complement method, device, equipment and storage medium |
| CN117289919A (en) * | 2023-11-24 | 2023-12-26 | 浙江口碑网络技术有限公司 | Data processing method and device and electronic equipment |
| CN117289929A (en) * | 2023-11-24 | 2023-12-26 | 浙江口碑网络技术有限公司 | Plug-in frame, plug-in and data processing method and device and electronic equipment |
| CN117289919B (en) * | 2023-11-24 | 2024-02-20 | 浙江口碑网络技术有限公司 | Data processing method and device and electronic equipment |
| CN117289929B (en) * | 2023-11-24 | 2024-03-19 | 浙江口碑网络技术有限公司 | Plug-in frame, plug-in and data processing method and device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114675816A (en) | Code completion ordering method and system based on user behaviors | |
| US11776533B2 (en) | Building a natural language understanding application using a received electronic record containing programming code including an interpret-block, an interpret-statement, a pattern expression and an action statement | |
| KR100650427B1 (en) | Integrated development tool for building a natural language understanding application | |
| CN110502227B (en) | Code complement method and device, storage medium and electronic equipment | |
| CN109344230B (en) | Code library file generation, code search, coupling, optimization and migration method | |
| CN110309289B (en) | Sentence generation method, sentence generation device and intelligent equipment | |
| CN106570180B (en) | Voice search method and device based on artificial intelligence | |
| JPS6375835A (en) | Apparatus for generating intended code, program, list and design document | |
| CN109614329B (en) | Software test case aided design method based on interface control file | |
| CN113987405A (en) | AST-based mathematical expression calculation algorithm | |
| JP3794716B2 (en) | Method for changing word form and data processing apparatus for executing the method | |
| CN108563561B (en) | Program implicit constraint extraction method and system | |
| CN110716953B (en) | SQL sentence automatic generation method, device, equipment and readable storage medium | |
| CN112862334A (en) | Index system construction method and device based on syntax analysis tree and computer equipment | |
| CN117435230A (en) | Code annotation processing method and device based on neural network | |
| CN112905232B (en) | Program code parallel corpus mining method and system based on syntax analysis tree | |
| CN116400910A (en) | Code performance optimization method based on API substitution | |
| KR102614967B1 (en) | Automation system and method for extracting intermediate representation based semantics of javascript | |
| CN115796194A (en) | English translation system based on machine learning | |
| CN114676155A (en) | Code prompt information determining method, data set determining method and electronic equipment | |
| CN114925179A (en) | Information query method, device, storage medium and terminal | |
| CN114089980A (en) | Programming processing method, device, interpreter and nonvolatile storage medium | |
| CN113051925A (en) | Time identification method, device, equipment and computer storage medium | |
| CN116306391B (en) | Character string processing system and method for integrated circuit design | |
| CN113408597B (en) | Java method name recommendation method based on two-stage framework |
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 |