Component search method, system and equipment based on feature vectors and storage medium

Abstract

The invention provides a component searching method, system and device based on feature vectors and a storage medium, and the method comprises the steps: analyzing each component in a front-end component library to obtain names, versions, dependencies and function description information of the components as a remark information set; performing keyword expansion on each remark information set, converting the expanded remark information set into a feature vector, and performing enhanced retrieval based on historical retrieval data; the trained large model is used for processing the feature vectors, and a sorted retrieval result is generated; and feeding back a retrieval result based on the retrieval condition. According to the method, the retrieval speed and accuracy can be improved, the user can quickly position the required component, and through the intelligent analysis and matching technology, repeated development is reduced, and the overall working efficiency is improved.

Description

Background Art

[0002] The current front - end component market faces a key challenge: how to efficiently find the required components. Existing search solutions mainly rely on simple text matching or manual classification and grouping. Although this improves the accuracy of retrieval, there are the following main problems and limitations: Many solutions in the prior art are based on keyword matching. For example, preliminary screening is carried out through information such as titles and brief descriptions. This method is simple and easy to implement, but its effect is not satisfactory when dealing with complex and diverse components.

[0003] The current solutions mainly have the following defects and limitations:

[0004] (1) Relying on manual maintenance: Existing technologies often require manual component classification, grouping, and update maintenance. Although this manual process helps improve accuracy, it is prone to problems such as untimely classification and inaccurate updates.

[0005] (2) Low retrieval efficiency: The simple text - matching - based method lacks sufficient semantic information, resulting in inaccurate retrieval results. In addition, due to the complexity and diversity of components, a single keyword cannot fully describe the characteristics of components, further reducing the retrieval efficiency and accuracy.

[0006] (3) Lack of intelligent support: Traditional search methods mainly rely on manual operations and lack the support of artificial intelligence technology. This makes it difficult for users to efficiently conduct complex component retrievals and limits the practical application effect of the search solution.

[0007] The existence of these problems is mainly due to the following deficiencies in the prior art: First, there is a lack of effective extraction and utilization of component semantic information; second, the inherent relevance between components cannot be fully explored; finally, there is a lack of intelligent support to improve the efficiency and accuracy of retrieval. These defects lead to poor performance of the prior art in component market searches and are difficult to meet the growing needs of users. In summary, the current search solutions in the component market have many problems and defects in design and urgently need a more intelligent and efficient method to improve retrieval effects and meet user needs.

[0008] Therefore, the present invention provides a component search method, system, device, and storage medium based on feature vectors.

[0009] The present invention can combine advanced AI technologies such as large models, and through natural language processing (NLP) and machine learning algorithms, deeply analyze and semantically understand the metadata, dependency relationships, and module structures of components, thereby achieving more efficient and intelligent component retrieval. It can not only solve the limitations of the prior art but also improve the user experience and promote the healthy development of the front - end component market. Summary of the invention

[0010] In response to the problems in the prior art, the purpose of the present invention is to provide a component search method, system, device and storage medium based on feature vectors, which overcomes the difficulties of the prior art, can improve the speed and accuracy of retrieval, allow users to quickly locate the required components, and reduce duplicate development and improve overall work efficiency through intelligent analysis and matching technology.

[0011] An embodiment of the present invention provides a component search method based on a feature vector, comprising the following steps:

[0012] S110, parsing each component in the front-end component library to obtain the component name, version, dependency, and function description information as a remark information set;

[0013] S120, performing keyword expansion on each of the remark information sets, converting the expanded remark information sets into feature vectors, and performing enhanced retrieval based on historical retrieval data;

[0014] S130, using the trained large model to process the feature vector to generate ranked search results;

[0015] S140: Feedback search results based on the search conditions.

[0016] Preferably, the step S110 includes:

[0017] S111, extracting basic information files and usage instruction files for each component in the front-end component library;

[0018] S112. Parse the basic information file and the instruction file to obtain the component name, version, component function, component category, dependency, and function description information to establish a note information set.

[0019] Preferably, the basic information file is a package.json file, and the instruction file is a readme.md file.

[0020] Preferably, the step S112 further includes: performing deep semantic analysis on the function description information to mine the intrinsic correlation between components.

[0021] Preferably, the step S120 includes:

[0022] S121, performing keyword expansion on each of the remark information sets, and converting the expanded remark information sets into feature vectors respectively by using natural language processing;

[0023] S122. Input the feature vector into the big data platform for enhanced retrieval based on historical retrieval data and user behavior data.

[0024] Preferably, step S140 further includes:

[0025] S141. Identify the retrieval conditions based on natural language processing to obtain at least the component functions and component categories corresponding to the retrieval intent;

[0026] S142. Screen the retrieval results according to the component functions and component categories, and feedback the screened retrieval results.

[0027] Preferably, step S140 further includes:

[0028] S143. Collect the context information of the user's retrieval, where the context information includes the current project type and development environment;

[0029] S144. Reorder the retrieval results according to the context information.

[0030] An embodiment of the present invention further provides a component search system based on feature vectors for implementing the above-mentioned component search method based on feature vectors. The component search system based on feature vectors includes:

[0031] An analysis information module that analyzes each component in the front-end component library to obtain the name, version, dependency relationship, and function description information of the component as a set of note information;

[0032] A feature vector module that expands keywords for each set of note information, converts the expanded set of note information into a feature vector, and performs enhanced retrieval based on historical retrieval data;

[0033] A model sorting module that processes the feature vector using a trained large model to generate a sorted retrieval result;

[0034] A result feedback module that feedbacks the retrieval result based on the retrieval conditions.

[0035] An embodiment of the present invention further provides a component search device based on feature vectors, including:

[0036] A processor;

[0037] A memory that stores executable instructions of the processor;

[0038] Wherein, the processor is configured to execute the steps of the above-mentioned component search method based on feature vectors by executing the executable instructions.

[0039] An embodiment of the present invention also provides a computer-readable storage medium for storing a program, which when executed implements the steps of the above-mentioned component search method based on feature vectors.

[0040] The object of the present invention is to provide a component search method, system, device and storage medium based on feature vectors, which can improve the speed and accuracy of retrieval, enable users to quickly locate the required components, and reduce duplicate development and improve the overall work efficiency through intelligent analysis and matching technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] By reading the detailed description of the non-restrictive embodiments with reference to the following drawings, other features, objects and advantages of the present invention will become more obvious.

[0042] Figure 1 is a flowchart of the component search method based on feature vectors of the present invention.

[0043] Figure 2 is a schematic structural diagram of the component search system based on feature vectors of the present invention.

[0044] Figure 3 is a schematic structural diagram of the component search device based on feature vectors of the present invention.

[0045] Figure 4 is a schematic structural diagram of the computer-readable storage medium according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0046] The following uses specific specific examples to illustrate the implementation manners of the present application. Those skilled in the art can easily understand other advantages and effects of the present application from the content disclosed in the present application. The present application can also be implemented or applied through other different specific implementation manners. Various details in the present application can also be modified or changed according to different viewpoints and application systems without departing from the spirit of the present application. It should be noted that, without conflict, the embodiments and features in the embodiments of the present application can be combined with each other.

[0047] The following takes the drawings as a reference and details the embodiments of the present application so that those skilled in the technical field to which the present application belongs can easily implement it. The present application can be embodied in many different forms and is not limited to the embodiments described herein.

[0048] In the descriptions of the present application, the descriptions referring to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc., mean that the specific features, structures, materials, or characteristics represented in connection with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials, or characteristics represented can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples represented in the present application and the features of different embodiments or examples.

[0049] In addition, the terms "first" and "second" are only used for illustrative purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" can explicitly or implicitly include at least one of such features. In the descriptions of the present application, the meaning of "a plurality of" is two or more, unless otherwise specifically defined.

[0050] To clearly illustrate the present application, devices irrelevant to the description are omitted, and the same or similar components throughout the specification are given the same reference numerals.

[0051] Throughout the specification, when it is said that a device is "connected" to another device, this includes not only the case of "direct connection", but also the case of "indirect connection" with other elements placed therebetween. In addition, when it is said that a certain device "includes" a certain component, unless there is a particularly contrary record, it does not exclude other components, but means that other components can also be included.

[0052] When it is said that a device is "on" another device, this can be directly on the other device, but there can also be other devices therebetween. When it is said that a device is "directly" "on" another device, there are no other devices therebetween.

[0053] Although in some instances the terms first, second, etc. are used herein to denote various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first interface and a second interface, etc. are indicated. Furthermore, as used herein, the singular forms "a", "an", and "the" are also intended to include the plural forms unless the context indicates otherwise. It should be further understood that the terms "comprising", "including" indicate the presence of the features, steps, operations, elements, components, items, kinds, and / or groups, but do not preclude the presence, occurrence, or addition of one or more other features, steps, operations, elements, components, items, kinds, and / or groups. The terms "or" and "and / or" used herein are interpreted as inclusive, or meaning any one or any combination. Thus, "A, B or C" or "A, B and / or C" means "any one of the following: A; B; C; A and B; A and C; B and C; A, B and C". An exception to this definition only occurs when the combination of elements, functions, steps, or operations is inherently mutually exclusive in some way.

[0054] The technical terms used herein are only for referring to specific embodiments and are not intended to limit the present application. The singular forms used herein also include the plural forms as long as the statements do not clearly indicate the contrary meaning. The meaning of "including" used in the specification is to embody specific characteristics, regions, integers, steps, operations, elements, and / or components, and does not exclude the existence or addition of other characteristics, regions, integers, steps, operations, elements, and / or components.

[0055] Although not defined differently, including the technical terms and scientific terms used herein, all terms have the same meaning as generally understood by those skilled in the technical field to which the present application belongs. Terms defined in commonly used dictionaries are additionally interpreted to have a meaning consistent with the relevant technical literature and the content currently presented. As long as they are not defined, they should not be over-interpreted as ideal or very formulaic meanings.

[0056] Figure 1 is a flowchart of the component search method based on feature vectors of the present invention. As Figure 1 shown, the component search method based on feature vectors of the present invention includes:

[0057] S110. Analyze each component in the front-end component library to obtain the name, version, dependency relationship, and function description information of the component as a set of note information;

[0058] S120. Perform keyword expansion on each set of note information, convert the expanded set of note information into a feature vector, and perform enhanced retrieval based on historical retrieval data;

[0059] S130, using the trained large model to process the feature vector to generate ranked retrieval results;

[0060] S140: Feedback search results based on the search conditions.

[0061] The present invention aims to solve the problem that it is difficult to obtain target components through conventional retrieval schemes in the component market. Specifically, the present invention proposes a large model search scheme based on feature vectors, which enables users to find the required components more accurately and efficiently. In traditional component retrieval, it mainly relies on simple text information (such as title) matching, which makes the retrieval results often not accurate enough, and it is easy for users to encounter inefficiency or even fail to find the target when looking for the required components. The present invention uses the reasoning logic of the large model to provide an improved search method that can sort and retrieve components more accurately, so as to better meet the actual needs of users. At the same time, some retrieval systems also rely on manual maintenance and classification operations. This dependence not only increases the user's development cost, but also may lead to a large maintenance workload and low efficiency. In addition, the traditional retrieval method lacks the ability to deeply analyze the semantic information of the component, and it is difficult to explore the intrinsic correlation between components, which further affects the efficiency and accuracy of the retrieval. The existence of these problems seriously affects the user experience and increases the workload of users when using component management tools. Therefore, in order to meet users' needs for efficient, intelligent and convenient component retrieval, the present invention proposes a large model component search solution based on feature vectors, which aims to solve the above technical problems and improve users' development efficiency and service experience by expanding the retrieval scope, improving retrieval accuracy and automation.

[0062] In a preferred embodiment, step S110 includes:

[0063] S111, extracting basic information files and usage instruction files for each component in the front-end component library;

[0064] S112. Parse the basic information file and the instruction file to obtain the component name, version, component function, component category, dependency, and function description information to establish a note information set, but not limited to this.

[0065] In a preferred embodiment, the basic information file is a package.json file, and the instruction file is a readme.md file, but is not limited thereto.

[0066] The basic information file, the package.json file (also known as the manifest file), is a crucial file in the Node.js ecosystem. Its core functions and roles can be summarized as follows: Project metadata management. As a manifest file in JSON format, it records the basic information of the project, including metadata such as project name, version number, author, license, description, etc. This information is particularly important for open-source projects when publishing to the npm repository. Dependency control. It clearly declares the third-party libraries required by the project and their version ranges through the dependencies and devDependencies fields, supporting semantic versioning rules. Together with package-lock.json, it can lock specific versions to ensure environmental consistency. Script task automation. Define commands such as start, build, and test in the scripts field and execute them through npm run, which becomes the basis for the integration of modern front-end toolchains (such as Vite / Webpack). Detailed explanation of the key components of package.json: Required fields, name and version are mandatory fields that form the unique identifier of the project. Other common fields such as description (project description), main (entry file), etc. Dependency management mechanism. Distinguish between production dependencies (dependencies) and development dependencies (devDependencies), and support multiple package managers such as npm, yarn, and pnpm. Advanced configuration. repository declares the code repository address, and engines specifies the Node version requirements. private: true can prevent accidental publishing to npm. As the "instruction manual" of a Node.js project, the design of package.json integrates three core functions: dependency management, task orchestration, and metadata description, and is an indispensable cornerstone for modern JavaScript development.

[0067] The README.md file is a document file used to describe project information. It is usually located in the root directory of the project and is used to provide users with detailed information about the project, including project introduction, installation steps, usage methods, project structure, etc. The suffix of the README.md file is ".md", which is the abbreviation of Markdown markup language. Markdown is a lightweight markup language used to format text. The main content and structure of the README.md file: Project title and description: Usually marked with a first-level heading (#), briefly describing the purpose, functions, and uses of the project. Installation and usage instructions: Provide detailed installation steps and instructions on how users can use the project. Contribution guidelines and license: Guide developers on how to contribute to the project, including the process of submitting issues, suggestions, or code changes, as well as the open-source license used by the project. Project structure and file organization: Explain the file and directory structure of the project to help users understand the code layout. Changelog: List the project's plans and function descriptions. Contact information: Provide the contact information of the project author and maintainer. How to use the README.md file in GitHub: On GitHub, the README.md file can be directly edited online. After opening a GitHub project, the README.md file can be found or added in the file directory. When editing, the GitHub Flavored Markdown (GFM) syntax can be used, which is an extension of the standard Markdown syntax. After editing, the file content can be updated by submitting the changes.

[0068] In a preferred embodiment, step S112 further includes: performing in-depth semantic analysis on the function description information to mine the internal relevance between components, but not limited thereto.

[0069] In a preferred embodiment, step S120 includes:

[0070] S121. Perform keyword expansion on each set of note information, and respectively convert the expanded set of note information into feature vectors by using natural language processing;

[0071] S122. Input the feature vectors into the big data platform for enhanced retrieval based on historical retrieval data and user behavior data, but not limited thereto.

[0072] In a preferred embodiment, step S140 further includes:

[0073] S141. Identify the retrieval conditions based on natural language processing to obtain at least the component functions and component categories corresponding to the retrieval intent;

[0074] S142. Screen the retrieval results according to component functions and component categories, and feedback the screened retrieval results, but not limited thereto.

[0075] In a preferred embodiment, step S140 further includes:

[0076] S143. Collect the context information of the user's retrieval. The context information includes the current project type and development environment.

[0077] S144. Reorder the retrieval results according to the context information, but not limited thereto.

[0078] The present invention proposes a component market search engine solution based on feature vectors. The search scope of keywords is extended by identifying two core files (package.json and readme.md) of components. The relevant extended information is converted into feature vectors, and big data technology is used for enhanced retrieval. The feature vector search scheme of the large model is adopted to retrieve the expected target component content. Preferably, this solution is not only applicable to the component market, but also can be extended to other retrieval scenarios to improve its application scope. Preferably, in addition to using feature vectors, this solution can also adopt other enhancement technologies to further improve the retrieval effect, such as semantic analysis or context understanding, etc. Preferably, a classification filter can be introduced to classify the retrieved keywords to achieve faster and more accurate retrieval. This method can optimize the organization and display of search results and enhance the user experience.

[0079] The process of component search based on feature vectors through the present invention is generally as follows:

[0080] First, extract the basic information file package.json and the usage instruction file readme.md for each component in the front-end component library; parse the basic information file and the usage instruction file to obtain the name, version, component functions, component categories, dependency relationships, and function description information of the components to establish a note information set. Moreover, perform in-depth semantic analysis on the function description information to mine the internal relevance between components.

[0081] Next, perform keyword expansion on each note information set, and respectively convert the expanded note information sets into feature vectors by using natural language processing; input the feature vectors into the big data platform for enhanced retrieval based on historical retrieval data and user behavior data, but not limited thereto.

[0082] Then, use the trained large model to process the feature vectors to generate the sorted retrieval results.

[0083] Finally, based on natural language processing, the search conditions are identified to obtain at least the component functions and component categories corresponding to the search intent; the search results are filtered according to the component functions and component categories, and the filtered search results are fed back. In addition, the context information of the user's search is collected, and the context information includes the current project type and development environment; the search results are re-sorted according to the context information

[0084] The purpose of the present invention is to solve the following problems existing in the prior art:

[0085] (1) The front-end component market lacks efficient and intelligent search methods, resulting in inaccurate and time-consuming retrieval results, making it difficult for users to quickly find the components they need.

[0086] (2) Existing technologies often rely on manual maintenance to classify and group components, which not only increases maintenance costs but also easily leads to problems such as untimely classification or inaccurate updates.

[0087] (3) Traditional retrieval methods lack intelligent support and are unable to fully explore the intrinsic correlation and semantic information between components, resulting in low retrieval efficiency and poor accuracy.

[0088] In order to achieve the above objectives, the present invention provides an intelligent component retrieval method and system based on a large model, which can efficiently perform content analysis and semantic understanding of components and achieve accurate retrieval results. By reducing the phenomenon of reinventing the wheel (that is, front-end technicians need to repeatedly develop components for similar functions), R&D efficiency is improved and R&D working hours are shortened; at the same time, the target component can be used directly after being retrieved, avoiding redundant development work; in addition, after retrieving similar components, component content can be co-built according to demand, further expanding the availability of the component and enriching its application scenarios. By solving the above problems, the present invention aims to promote the healthy development of the front-end component market and improve user experience and work efficiency.

[0089] The specific implementation methods of the present invention are as follows:

[0090] First, identify the core files of the component. In the front-end component market, each component usually contains two core files: package.json and readme.md. These files contain basic information and instructions for use of the component. By parsing these files, key information such as the component name, version, dependencies, and function description can be extracted.

[0091] Then, the search scope of keywords is expanded, and relevant keywords are extracted by analyzing the contents of package.json and readme.md. These keywords include not only the name and description of the component, but also functional features, usage scenarios, and other information. The expanded keyword set will be used for subsequent feature vector generation.

[0092] Next, convert the extended information into feature vectors. Using natural language processing techniques, convert the extracted keywords and description information into feature vectors. Feature vectors are the mathematical representations of information and can capture the semantic and functional characteristics of components. This step is a key technical feature that differentiates the present invention from traditional retrieval methods.

[0093] Use big data technology for enhanced retrieval. Input the generated feature vectors into a big data platform, and combine historical retrieval data and user behavior data for enhanced retrieval. Big data technology can analyze a large amount of historical data, optimize retrieval algorithms, and improve the accuracy and efficiency of retrieval.

[0094] Adopt the feature vector search scheme of a large model. Use the trained large model to process the feature vectors and generate sorted retrieval results. The large model can understand the deep semantic information in the feature vectors, thereby more accurately matching the user's retrieval needs.

[0095] Finally, optimize the retrieval results. After the retrieval results are processed by the large model, they are presented to the user. If the user fails to find the expected target component, they can re - perform the retrieval by adjusting search parameters (such as keywords, filtering conditions, etc.).

[0096] In the above process, in order to further improve the retrieval effect, the present invention can also introduce the following optional enhancement technologies: (a) Semantic analysis: Conduct in - depth semantic analysis on component descriptions to explore the internal correlations between components. (b) Context understanding: Optimize the retrieval results by combining the user's context information (such as the current project type, development environment, etc.). (c) Classification filter: Classify components according to their functions, categories, etc. to help users quickly locate the target components. Through the above steps, the present invention can achieve efficient and accurate component retrieval in the front - end component market, significantly improving the development efficiency and experience of users.

[0097] The present invention provides an innovative component search engine solution based on extended description content and feature vectors. This solution significantly improves the speed and accuracy of retrieval, enabling users to quickly locate the required components. Through intelligent analysis and matching techniques, the possibility of duplicate development by R & D personnel is greatly reduced, thus significantly improving the overall work efficiency. It has the following significant beneficial effects compared with the prior art:

[0098] 1. Greatly improved retrieval accuracy: By utilizing the semantic information of component core files (package.json and readme.md), combining feature vectors and large model analysis, the present invention can more accurately understand and match user needs, significantly improving the relevance and accuracy of retrieval results.

[0099] 2. Significantly improved retrieval efficiency: By expanding the retrieval scope and adopting advanced large model technology, the retrieval process becomes more efficient, greatly reducing the time for users to find target components.

[0100] 3. Effectively reduce duplicate development: By providing more accurate component search results, R & D personnel can quickly locate and reuse existing components, greatly reducing the possibility of duplicate development and saving valuable development time and resources.

[0101] 4. Significantly enhanced automation level: The present invention reduces the dependence on manual classification and maintenance. Through automated feature extraction, semantic analysis, and retrieval ranking, the overall work efficiency is greatly improved, and the risk of human errors is reduced.

[0102] 5. Obviously improved user experience: It provides a more intuitive and user-friendly interface and functions, such as intelligent screening and multi-dimensional sorting, making the component retrieval process more convenient and efficient, and significantly improving user satisfaction.

[0103] 6. Enhanced adaptability and scalability: This solution is not only applicable to the front-end component market, but can also be flexibly extended to retrieval scenarios in other technical fields, with broad application prospects.

[0104] 7. Continuous optimization ability: By introducing large model technology, the system can continuously learn and optimize. With the accumulation of usage data, the retrieval effect will continue to improve, providing users with more and more accurate search results.

[0105] In summary, through the innovative technical solution, the present invention effectively solves the problems existing in the existing component search, provides developers with an efficient, accurate, and easy-to-use component retrieval tool, significantly improves the R & D efficiency, and promotes component reuse and technological innovation.

[0106] Figure 2 It is a schematic structural diagram of the component search system based on feature vectors of the present invention. As Figure 2 shown, the embodiment of the present invention also provides a component search system based on feature vectors for implementing the above-mentioned component search method based on feature vectors. The component search system 5 based on feature vectors includes:

[0107] An information parsing module 51 that parses each component in the front-end component library to obtain the name, version, dependency relationship, and function description information of the component as a set of note information;

[0108] A feature vector module 52 that expands keywords for each set of note information, converts the expanded set of note information into feature vectors, and performs enhanced retrieval based on historical retrieval data;

[0109] The model sorting module 53 processes the feature vectors using the trained large model to generate sorted retrieval results;

[0110] The result feedback module 54 feeds back the retrieval results based on the retrieval conditions.

[0111] In a preferred embodiment, the parsing information module 51 is configured to extract the basic information file and the usage instruction file for each component in the front - end component library; parse the basic information file and the usage instruction file to obtain the name, version, component function, component category, dependency relationship, function description information of the component to establish a set of note information, but not limited thereto.

[0112] In a preferred embodiment, the basic information file is a package.json file, and the usage instruction file is a readme.md file, but not limited thereto.

[0113] In a preferred embodiment, the parsing information module 51 is configured to perform in - depth semantic analysis on the function description information to mine the internal relevance between components, but not limited thereto.

[0114] In a preferred embodiment, the feature vector module 52 is configured to perform keyword expansion on each set of note information, and respectively convert the expanded set of note information into feature vectors by using natural language processing; input the feature vectors into the big data platform for enhanced retrieval based on historical retrieval data and user behavior data, but not limited thereto.

[0115] In a preferred embodiment, the result feedback module 54 is configured to identify the retrieval conditions based on natural language processing, and at least obtain the component function and component category corresponding to the retrieval intention; screen the retrieval results according to the component function and component category, and feed back the screened retrieval results, but not limited thereto.

[0116] In a preferred embodiment, the result feedback module 54 is further configured to collect the context information of the user's retrieval, and the context information includes the current project type and development environment; re - sort the retrieval results according to the context information.

[0117] The component search system based on feature vectors of the present invention can improve the speed and accuracy of retrieval, enable users to quickly locate the required components, reduce duplicate development through intelligent analysis and matching technologies, and improve the overall work efficiency.

[0118] An embodiment of the present invention further provides a component search device based on feature vectors, including a processor and a memory, in which executable instructions of the processor are stored. Wherein, the processor is configured to execute the steps of the component search method based on feature vectors via executing the executable instructions.

[0119] As shown above, the component search device based on feature vectors of the present invention can improve the retrieval speed and accuracy, enabling users to quickly locate the required components. Through intelligent analysis and matching technologies, it reduces duplicate development and improves the overall work efficiency.

[0120] Those skilled in the art can understand that various aspects of the present invention can be implemented as a system, method, or program product. Therefore, various aspects of the present invention can be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software aspects, which can be collectively referred to herein as "circuit", "module", or "platform".

[0121] Figure 3 is a schematic structural diagram of the component search device based on feature vectors of the present invention. The following refers to Figure 3 to describe the electronic device 600 according to this embodiment of the present invention. Figure 3 The electronic device 600 shown is merely an example and should not impose any limitations on the functions and usage scope of the embodiments of the present invention.

[0122] As Figure 3 shown, the electronic device 600 is presented in the form of a general-purpose computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different platform components (including the storage unit 620 and the processing unit 610), a display unit 640, etc.

[0123] Among them, the storage unit stores program code, and the program code can be executed by the processing unit 610, enabling the processing unit 610 to execute the steps according to various exemplary embodiments of the present invention described in the method part of this specification above. For example, the processing unit 610 can execute the steps as Figure 1 shown.

[0124] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 6201 and / or a cache storage unit 6202, and may further include a read-only storage unit (ROM) 6203.

[0125] The storage unit 620 may also include a program / utilities 6204 having a set (at least one) of program modules 6205. Such program modules 6205 include, but are not limited to: an operating system, one or more application programs, other program modules, and program data. The implementation of a network environment may be included in each or some combination of these examples.

[0126] The bus 630 can represent one or more of several types of bus structures, including a memory unit bus or a memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any one of the multiple bus structures.

[0127] The electronic device 600 can also communicate with one or more external devices 700 (such as a keyboard, a pointing device, a Bluetooth device, etc.), and can also communicate with one or more devices that enable a user to interact with the electronic device 600, and / or communicate with any device that enables the electronic device 600 to communicate with one or more other computing devices (such as a router, a modem, etc.). Such communication can be carried out through the input / output (I / O) interface 650. Moreover, the electronic device 600 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through the network adapter 660. The network adapter 660 can communicate with other modules of the electronic device 600 through the bus 630. It should be understood that although not shown in the figure, other hardware and / or software modules can be used in combination with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms, etc.

[0128] An embodiment of the present invention also provides a computer-readable storage medium for storing a program, and the steps of a component search method based on feature vectors are implemented when the program is executed. In some possible implementation manners, various aspects of the present invention can also be implemented in the form of a program product, which includes program code. When the program product runs on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary embodiments of the present invention described in the above method part of this specification.

[0129] As shown above, the component search system based on feature vectors of the embodiment of the present invention can improve the retrieval speed and accuracy, enable users to quickly locate the required components, and reduce duplicate development and improve the overall work efficiency through intelligent analysis and matching technologies.

[0130] Figure 4 is a schematic structural diagram of the computer-readable storage medium of the present invention. Refer to Figure 4 As shown, a program product 800 for implementing the above method according to an embodiment of the present invention is described. It can adopt a portable compact disc read-only memory (CD-ROM) and include program code, and can run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, the readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, device, or device.

[0131] The program product may adopt any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable 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.

[0132] The computer-readable storage medium may include a data signal propagated in a baseband or as part of a carrier wave, in which the readable program code is carried. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable storage medium may also be any readable medium other than the readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical fiber cable, RF, etc., or any suitable combination of the above.

[0133] The program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and also including conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computing device, partially on the user's device, executed as a stand-alone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (for example, by using an Internet service provider to connect through the Internet).

[0134] In summary, the object of the present invention is to provide a component search method, system, device, and storage medium based on feature vectors, which can improve the speed and accuracy of retrieval, enable users to quickly locate the required components, reduce duplicate development through intelligent analysis and matching technologies, and improve the overall work efficiency.

[0135] The above content is a further detailed description of the present invention in combination with specific preferred embodiments. It cannot be determined that the specific implementation of the present invention is only limited to these descriptions. For those of ordinary skill in the technical field to which the present invention pertains, without departing from the concept of the present invention, several simple deductions or substitutions can still be made, and all should be regarded as falling within the protection scope of the present invention.

Claims

1. A component search method based on feature vectors, characterized in that, Including the following steps: S110. Parse each component in the front-end component library to obtain the name, version, dependencies, and function description information of the component as a set of note information; S120. Expand keywords for each set of note information, convert the expanded set of note information into feature vectors, and perform enhanced retrieval based on historical retrieval data; S130. Use the trained large model to process the feature vectors to generate a sorted retrieval result; S140. Feedback the retrieval result based on the retrieval condition.

2. The method for component search based on feature vectors according to claim 1, wherein The step S110 includes: S111. Extract the basic information file and the usage instruction file for each component in the front-end component library; S112. Parse the basic information file and the usage instruction file to obtain the name, version, component function, component category, dependencies, and function description information of the component to establish a set of note information.

3. The method for component search based on feature vectors according to claim 2, wherein The basic information file is the package.json file, and the usage instruction file is the readme.md file.

4. The method for component search based on feature vectors according to claim 2, wherein The step S112 further includes: performing in-depth semantic analysis on the function description information to mine the internal relevance between components.

5. The method for component search based on feature vectors according to claim 2, wherein The step S120 includes: S121. Expand keywords for each set of note information, and convert the expanded set of note information into feature vectors respectively by using natural language processing; S122. Input the feature vectors into the big data platform and perform enhanced retrieval based on historical retrieval data and user behavior data.

6. The method for component search based on feature vectors according to claim 2, wherein The step S140 further includes: S141. Identify the retrieval condition based on natural language processing, and at least obtain the component function and component category corresponding to the retrieval intention; S142. Screen the retrieval result according to the component function and component category, and feedback the screened retrieval result.

7. The method for component search based on feature vectors according to claim 2, wherein The step S140 further includes: S143. Collect the context information of the user's retrieval, and the context information includes the current project type and development environment; S144. Re-sort the retrieval result according to the context information.

8. A component search system based on feature vectors, for implementing the component search method based on feature vectors described in claim 1, characterized in that, Including: An information parsing module that parses each component in the front-end component library to obtain the name, version, dependencies, and function description information of the component as a set of note information; A feature vector module that expands keywords for each set of note information, converts the expanded set of note information into feature vectors, and performs enhanced retrieval based on historical retrieval data; A model sorting module that uses the trained large model to process the feature vectors to generate a sorted retrieval result; A result feedback module that feedbacks the retrieval result based on the retrieval condition.

9. A component search device based on feature vectors, characterized in that, Including: A processor; A memory that stores executable instructions of the processor; Wherein, the processor is configured to execute the steps of the component search method based on feature vectors according to any one of claims 1 to 7 by executing the executable instructions.

10. A computer-readable storage medium for storing a program, characterized in that, When the program is executed by the processor, it implements the steps of the component search method based on feature vectors according to any one of claims 1 to 7.

Images