Code review method, system and device, storage medium and program product

Abstract

The invention discloses a code review method, system and device, a storage medium and a program product, and the method comprises the steps: cleaning a to-be-reviewed code snippet, and obtaining an incremental code snippet and position information; vectorizing the incremental code snippets; semantic query is conducted on the vectorized incremental code snippet data based on an ES database according to the cosine law, development rules of similar semantics are obtained and ranked from high to low according to similarity values, and a preset number of first several snippets are obtained; recombining cue words, wherein the recombining cue words comprise incremental code snippets and a preset number of development rules; and sending the recombined cue word to a general generative large model to obtain an examination suggestion. The code snippets to be examined are pushed to the gilab warehouse by a developer, and are cleaned by the gilab warehouse through webhook triggering. According to the review method, the whole process is automatic, the review efficiency is high, review can be conducted according to the development rules in the team, knowledge sharing is achieved, the review result is objective, and the problem that the text exceeds the upper limit is avoided.

Description

Technical Field

[0001] The present invention relates to the field of computer machine learning, and in particular to a code review method, system, device, storage medium and program product. Background Art

[0002] Traditional code review is mostly done manually, relying on communication and cooperation between software developers and code reviewers. The main method is peer review, during which other developers check the quality, security, and compliance with coding standards of the original code. Code review can use GitLab's platform to facilitate this process, allowing other developers to make suggestions or modifications. Sometimes automated tool detection is also used, such as static code analyzers that scan code errors and non-compliant parts through preset rules. Although traditional code review is essential to ensuring code quality, it has the following problems and shortcomings:

[0003] (1) Low review efficiency. Experienced developers need to spend a lot of time manually checking the code, which slows down the project progress, especially when the code base is large and updated frequently.

[0004] (2) Reliance on personal experience. The effectiveness of code review depends largely on the personal experience and ability of the code reviewer. The lack of standardized and automated processes may lead to errors and omissions.

[0005] (3) Limited knowledge sharing. In traditional review, knowledge sharing is limited to developers who participate in the review, and it is difficult for new developers to quickly acquire previous review knowledge.

[0006] (4) Poor objectivity. Manual review is easily influenced by personal preferences and emotions, which may lead to inconsistent review results. Summary of the invention

[0007] In view of this, embodiments of the present invention provide a code review method, system, device, storage medium, and program product, which at least partially solve the problems existing in the prior art.

[0008] In a first aspect, an embodiment of the present invention provides a code review method, comprising the following steps:

[0009] Clean the code snippets to be reviewed and obtain the incremental code snippets and location information;

[0010] Vectorize incremental code snippets;

[0011] Perform semantic query on the vectorized incremental code snippet data based on the ES database according to the cosine theorem to obtain development rules with similar semantics; sort the development rules with similar semantics from high to low according to the similarity value, and obtain the first few of the preset number;

[0012] Reorganize the prompt words, including: incremental code snippets + a preset number of development rules;

[0013] Send the reorganized prompt words to a general generative large model to obtain suggestions for incremental code snippets.

[0014] According to a specific implementation of an embodiment of the present invention, the code snippet to be reviewed is pushed by a developer to a gitlab warehouse, and is cleaned by the gitlab warehouse through a webhook trigger.

[0015] According to a specific implementation manner of an embodiment of the present invention, the location information is line number marking information; and vectorizing the incremental code snippet includes slicing the incremental code snippet and then vectorizing it.

[0016] According to a specific implementation of an embodiment of the present invention, the method for constructing the ES database is as follows:

[0017] Get the development team's development rules prepared in a preset data format;

[0018] Vectorize the code data to get a floating point array;

[0019] The vector data is stored in the ES database, providing semantic query of the code.

[0020] According to a specific implementation of an embodiment of the present invention, after obtaining the suggestion about the incremental code snippet, the method further includes:

[0021] Send the suggestion to gitlab to complete the review of the incremental code snippet;

[0022] And / or, after waiting for all incremental code snippets to give suggestions, the total suggested abbreviation information is pushed to the corresponding developer to complete the closed loop of the entire link.

[0023] In a second aspect, an embodiment of the present invention further provides a code review system, including:

[0024] A cleaning module is configured to clean the code snippets to be reviewed and obtain incremental code snippets and location information;

[0025] A vectorization module, configured to vectorize the incremental code snippet;

[0026] The semantic query sorting module is configured to perform semantic query on the vectorized incremental code snippet data based on the ES database according to the cosine theorem to obtain development rules with similar semantics; sort the development rules with similar semantics from high to low according to the similarity value, and obtain the first few of a preset number;

[0027] The reorganization prompt word module is configured to provide a reorganization prompt word as: incremental code snippet + a preset number of development rules;

[0028] The big model review interface module is configured to send the reorganized prompt words to the general generative big model to obtain suggestions on incremental code snippets.

[0029] According to a specific implementation of an embodiment of the present invention, the system further includes: an automatic triggering module configured to clean the code snippets to be reviewed pushed by the developer to the gitlab warehouse through a webhook triggered by the gitlab warehouse;

[0030] And / or, a suggestion push module is configured to send the suggestions to gitlab to complete the review of the incremental code snippets; and / or, after waiting for all incremental code snippets to give suggestions, the total suggestion summary information is pushed to the corresponding developer to complete the closed loop of the entire link.

[0031] In a third aspect, an embodiment of the present invention provides an electronic device, the electronic device comprising:

[0032] at least one processor; and,

[0033] a memory communicatively connected to the at least one processor; wherein,

[0034] The memory stores instructions that can be executed by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor performs the code review method described in any one of the first aspect or any one of the implementations of the first aspect.

[0035] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, which stores computer instructions, and when the computer instructions are executed by at least one processor, the at least one processor executes the code review method in the aforementioned first aspect or any implementation of the first aspect.

[0036] In a fifth aspect, an embodiment of the present invention further provides a computer program product, which includes computer program instructions, and when the computer program instructions are executed by a processor, the code review method in the aforementioned first aspect or any implementation method of the first aspect is implemented.

[0037] The present invention adopts the RAG (retrieval enhanced generation) technical concept, based on incremental code snippets and development rule vectors, and uses a large model for review. It does not require the intervention of other developers, and the entire process is automated. It uses a large model for code review to achieve the purpose of self-sufficiency, save time, reduce communication costs, and has high review efficiency. After using the present invention for code review, the development efficiency of the entire group is improved by 5%. By building an ES database and using a large model for review, the review can be conducted according to the development rules within the team, without relying on personal experience, to achieve knowledge sharing, and the review results are more objective. By conducting incremental code review, the problem of text exceeding the upper limit is avoided. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The above is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0039] Figure 1 A schematic diagram of a code review method flow chart provided by an embodiment of the present invention;

[0040] Figure 2 A flowchart of an automated AI code review provided by an embodiment of the present invention;

[0041] Figure 3 A schematic diagram of a code review system provided by an embodiment of the present invention;

[0042] Figure 4 A schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0043] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0044] The following describes the embodiments of the present invention through specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work belong to the scope of protection of the present invention.

[0045] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein may be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on the present invention, it should be understood by those skilled in the art that an aspect described herein may be implemented independently of any other aspect, and two or more of these aspects may be combined in various ways. For example, any number of aspects described herein may be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein may be used to implement this device and / or practice this method.

[0046] Additionally, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, it will be understood by those skilled in the art that the aspects described may be practiced without these specific details.

[0047] The embodiment of the present invention provides a code review method, referring to Figure 1 , 2 As shown, Figure 1 A schematic diagram of a code review method flow chart provided by an embodiment of the present invention; Figure 2 A flowchart of an automated AI code review provided in an embodiment of the present invention.

[0048] The code review method mainly includes an intelligent AI service, which can be an http service built by express.js, or other forms. The code review method mainly includes the following steps S110-S150:

[0049] Step S110, clean the code snippets to be reviewed, and obtain incremental code snippets and location information.

[0050] Specifically, after the developer has developed the code snippet, a cleaning step may be performed.

[0051] As a preferred embodiment, refer to Figure 2 As shown in the figure, the first cleaning step in the AI ​​service can be automatically triggered for cleaning. For example, when the developer has developed the code, he can push the code snippet to the gitlab warehouse, and then the gitlab warehouse triggers the AI ​​service through the webhook to start cleaning. Through this setting, fully automatic triggering can be achieved, with a higher degree of automation.

[0052] Since the developed code often has the problem of text exceeding the limit, the embodiment of the present invention selects a method of reviewing incremental code snippets to solve the problem that the text exceeds the limit and cannot be reviewed. Incremental code snippets mainly refer to the changed code part. Through cleaning, the incremental code snippets and location information can be obtained, where the location information can be in the form of line number annotation information.

[0053] Next, go to step S120 to vectorize the incremental code snippet.

[0054] Specifically, the incremental code snippet may be sliced ​​and then vectorized.

[0055] Next, go to step S130, perform semantic query on the vectorized incremental code snippet data based on the ES database according to the cosine theorem to obtain development rules with similar semantics; sort the development rules with similar semantics from high to low according to the similarity value, and obtain the first few of a preset number.

[0056] In this step, the ES database needs to be built in advance. The construction method is as follows: obtain the development rules of the development team prepared in a preset data format; vectorize the code data to obtain a floating-point array; store the vector data in the ES database to provide semantic queries for the code. For example, prepare the development rules within the development team in the following data format, such as: [Question: How to use JSON safely? Answer: Use JSON.safeParse and JSON.safeStringify], then vectorize the data according to 1536 dimensions to obtain a floating-point array such as [-0.019119712, 0.012891223, 0.019819688, -0.016721645, 0.0025050063, 0.012703266, 0.01771976, **], and then store the vector data in the DB database Elasticsearch (ES database) to provide semantic queries for the code.

[0057] The ES database is referenced here. By adopting the RAG (retrieval enhanced generation) technology idea and conducting reviews based on incremental code snippets and development rule vectors, the review can be conducted according to the development rules within the team without relying on personal experience, thus achieving knowledge sharing and making the review results more objective.

[0058] Specifically, when the vectorized incremental code snippet data is semantically queried based on the ES database according to the law of cosines, the internal development rules (development specification data) of the development team and the similarity values ​​can be obtained, and then the development rules are sorted from high to low in similarity (the higher the similarity, the more similar it is to the incremental code snippet). The preferred preset number is 5, which can also be adaptively adjusted.

[0059] Next, go to step S140. On the basis of the above steps, reorganize the prompt words, and the reorganized prompt words include: incremental code snippets + a preset number of development rules; for example, the prompt word template [You are a coding expert, please review the code rule part ``` rule1 rule2````, code part ``` code chunk```] according to the following rules.

[0060] Next, go to step S150 and send the reorganized prompt words to the general generative large model to obtain suggestions on incremental code snippets.

[0061] Specifically, the general generative large model is a model known in the prior art, such as LIama3.1-405B, which can give the corresponding reasoned answer text according to the input content requirements. The suggestions of incremental code snippets generally include: such as hidden bugs, code readability, specifications (rules), etc.

[0062] In summary, the embodiment of the present invention adopts the RAG (retrieval enhanced generation) technical idea through the above-mentioned code review method, based on incremental code snippets and development rule vectors, and the final effect is as follows: when a user pushes a code snippet to the code repository, it will trigger the review of the generative large model and make suggestions for the code snippet.

[0063] As a preferred embodiment, refer to Figure 2 As shown, after getting suggestions for incremental code snippets, it also includes:

[0064] The suggestion is sent to gitlab to complete the review of the incremental code snippet; specifically, the text can be sent to gitlab via http according to the standard number of lines to complete the review of the changed code.

[0065] And, after all incremental code snippets have given suggestions, the total suggested abbreviation information, such as [submission information, number of comments], is pushed to the corresponding developer to complete the closed loop of the entire link. Specifically, it can be pushed to the corresponding developer through WeChat for Enterprise.

[0066] Figure 3 A code review system 400 provided in an embodiment of the present invention includes:

[0067] A cleaning module 410 is configured to clean the code snippets to be reviewed and obtain incremental code snippets and location information;

[0068] A vectorization module 420 configured to vectorize the incremental code snippet;

[0069] The semantic query sorting module 430 is configured to perform semantic query on the vectorized incremental code snippet data based on the ES database according to the cosine theorem to obtain development rules with similar semantics; sort the development rules with similar semantics from high to low according to the similarity value, and obtain the first few rules of a preset number;

[0070] The reorganization prompt word module 440 is configured to provide a reorganization prompt word as: incremental code snippet + a preset number of development rules;

[0071] The big model review interface module 450 is configured to send the reorganized prompt words to the general generative big model to obtain suggestions on incremental code snippets.

[0072] As a preferred embodiment, the system further includes:

[0073] The automatic trigger module is configured to clean the code snippets to be reviewed pushed by developers to the GitLab repository through webhooks;

[0074] The suggestion push module is configured to send the suggestions to gitlab to complete the review of the incremental code snippets; after waiting for all incremental code snippets to give suggestions, the total suggestion summary information is pushed to the corresponding developer to complete the closed loop of the entire link.

[0075] See also Figure 4 The embodiment of the present invention further provides an electronic device 50, the electronic device comprising:

[0076] at least one processor; and,

[0077] a memory communicatively connected to the at least one processor; wherein,

[0078] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the code review method in the aforementioned method embodiment.

[0079] An embodiment of the present invention further provides a computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable the computer to execute the code review method in the aforementioned method embodiment.

[0080] An embodiment of the present invention further provides a computer program product, which includes computer program instructions. When the computer program instructions are executed by a processor, the code review method in the aforementioned method embodiment is implemented.

[0081] The following is a further explanation.

[0082] refer to Figure 4 , which shows a schematic diagram of the structure of an electronic device 50 suitable for implementing an embodiment of the present invention. The electronic device in the embodiment of the present invention may include, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 4 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0083] like Figure 4 As shown, the electronic device 50 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 50 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0084] Typically, the following devices may be connected to the I / O interface 505: input devices 506 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 508 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 509. The communication device 509 may allow the electronic device 50 to communicate with other devices wirelessly or by wire to exchange data. Although the electronic device 50 with various devices is shown in the figure, it should be understood that it is not required to implement or have all the devices shown. More or fewer devices may be implemented or have alternatively.

[0085] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 509, or installed from the storage device 508, or installed from the ROM 502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the method of the embodiment of the present invention are executed.

[0086] It should be noted that the computer-readable medium of the present invention can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal can take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0087] The computer-readable medium may be included in the electronic device, or may exist independently without being installed in the electronic device.

[0088] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: obtains at least two Internet Protocol addresses; sends a node evaluation request including the at least two Internet Protocol addresses to a node evaluation device, wherein the node evaluation device selects an Internet Protocol address from the at least two Internet Protocol addresses and returns it; receives the Internet Protocol address returned by the node evaluation device; wherein the obtained Internet Protocol address indicates an edge node in a content distribution network.

[0089] Alternatively, the computer-readable medium carries one or more programs, and when the one or more programs are executed by the electronic device, the electronic device: receives a node evaluation request including at least two Internet Protocol addresses; selects an Internet Protocol address from the at least two Internet Protocol addresses; and returns the selected Internet Protocol address; wherein the received Internet Protocol address indicates an edge node in a content distribution network.

[0090] Computer program code for performing the operations of the present invention may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0091] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0092] The units involved in the embodiments of the present invention may be implemented by software or hardware. The name of a unit does not limit the unit itself in some cases. For example, the first acquisition unit may also be described as a "unit for acquiring at least two Internet Protocol addresses".

[0093] It should be understood that various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof.

[0094] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A code review method, characterized in that: The following steps are involved: Clean the code snippets to be reviewed and obtain the incremental code snippets and location information; Vectorize incremental code snippets; Perform semantic query on the vectorized incremental code snippet data based on the ES database according to the cosine theorem to obtain development rules with similar semantics; sort the development rules with similar semantics from high to low according to the similarity value, and obtain the first few of the preset number; Reorganize the prompt words, including: incremental code snippets + a preset number of development rules; Send the reorganized prompt words to a general generative large model to obtain suggestions for incremental code snippets.

2. The code review method according to claim 1, characterized in that: The code snippets to be reviewed are pushed by developers to the gitlab repository, and are cleaned by the gitlab repository through webhook triggering.

3. The code review method according to claim 1, characterized in that: The location information is line number marking information; and vectorizing the incremental code snippet includes slicing the incremental code snippet and then vectorizing it.

4. The code review method according to claim 1, characterized in that: The construction method of the ES database is as follows: Get the development team's development rules prepared in a preset data format; Vectorize the code data to get a floating point array; The vector data is stored in the ES database, providing semantic query of the code.

5. The code review method according to any one of claims 1 to 4, characterized in that: After getting suggestions for incremental code snippets, also include: Send the suggestion to gitlab to complete the review of the incremental code snippet; And / or, after waiting for all incremental code snippets to give suggestions, the total suggested abbreviation information is pushed to the corresponding developer to complete the closed loop of the entire link.

6. A code review system, characterized in that: include: A cleaning module is configured to clean the code snippets to be reviewed and obtain incremental code snippets and location information; A vectorization module, configured to vectorize the incremental code snippet; The semantic query sorting module is configured to perform semantic query on the vectorized incremental code snippet data based on the ES database according to the cosine theorem to obtain development rules with similar semantics; sort the development rules with similar semantics from high to low according to the similarity value, and obtain the first few of a preset number; The reorganization prompt word module is configured to provide a reorganization prompt word including: an incremental code snippet + a preset number of development rules; The big model review interface module is configured to send the reorganized prompt words to the general generative big model to obtain suggestions on incremental code snippets.

7. The code review system according to claim 6, characterized in that: include: The automatic trigger module is configured to clean the code snippets to be reviewed pushed by developers to the GitLab repository through webhooks; And / or, a suggestion push module is configured to send the suggestions to gitlab to complete the review of the incremental code snippets; and / or, after waiting for all incremental code snippets to give suggestions, the total suggestion summary information is pushed to the corresponding developer to complete the closed loop of the entire link.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is caused to perform the code review method according to any one of claims 1 to 5.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, which, when executed by at least one processor, cause the at least one processor to perform the code review method according to any one of claims 1 to 5.

10. A computer program product, characterized in that The computer program product comprises computer program instructions, and when the computer program instructions are executed by a processor, the code review method according to any one of claims 1 to 5 is implemented.

Images