Availability intelligent search method and system based on real-time calculation

Abstract

The invention is suitable for the technical field of resume intelligent search, and provides an availability intelligent search method and system based on real-time calculation. The method comprises the following steps: according to a preset rule and frequency, performing data capture on a plurality of data sources and performing data synchronization on an internal database of an enterprise by adopting a web crawler technology to obtain preliminary talent data; performing real-time calculation processing on the preliminary talent data to generate standard talent data; analyzing the standard talent data, extracting key information of a plurality of talents, and constructing a plurality of talent portraits; identifying a plurality of key demand factors and related weights, performing demand matching on the plurality of talent portraits, determining a plurality of candidates, and performing candidate sorting; and collecting user interaction data, adjusting related weights according to the user interaction data, generating an optimization adjustment result, and feeding back the optimization adjustment result. The real-time computing technology can be fully utilized to ensure the timeliness and accuracy of the search result, so that available talents meeting requirements can be quickly and accurately found for enterprises.

Description

Technical Field

[0001] The present invention belongs to the technical field of resume intelligent search, and in particular to an availability intelligent search method and system based on real-time calculation. Background Art

[0002] During the recruitment process, companies need to process a large number of resumes. Traditional resume search methods usually rely on keyword matching and template matching, which are inefficient and prone to errors. They have the following main defects: (1) Insufficient real-time processing capabilities for large-scale data; (2) Inaccurate extraction of key information; and (3) Inability to effectively handle multi-source data fusion. Summary of the invention

[0003] The purpose of the embodiments of the present invention is to provide a method and system for intelligent search of availability based on real-time calculation, aiming to solve the technical problems existing in the prior art mentioned in the background technology.

[0004] The embodiment of the present invention is implemented as follows:

[0005] A method for intelligent search of availability based on real-time calculation, the method specifically comprising the following steps:

[0006] According to the preset rules and frequency, we use web crawler technology to capture data from multiple data sources, synchronize data with the company's internal database, and clean and verify it to obtain preliminary talent data;

[0007] Select a distributed stream processing framework to perform real-time computing on the preliminary talent data to generate standard talent data;

[0008] Based on natural language processing technology, the standard talent data is analyzed to extract multiple key talent information and construct multiple talent portraits;

[0009] Receive the recruitment needs of enterprises, identify multiple key demand factors and related weights, match the needs with multiple talent portraits, determine multiple candidates and rank the candidates;

[0010] Collect user interaction data, adjust the relevant weights according to the user interaction data, generate optimization adjustment results and provide feedback.

[0011] As a further limitation of the technical solution of the embodiment of the present invention, the method of using web crawler technology to crawl data from multiple data sources according to preset rules and frequencies, synchronize data with the internal database of the enterprise, and clean and verify the data to obtain preliminary talent data specifically includes the following steps:

[0012] Identify multiple data sources;

[0013] According to the preset rules and frequency, web crawler technology is used to crawl data from multiple data sources to obtain crawled talent data;

[0014] Synchronize the internal database of the enterprise to obtain synchronized talent data;

[0015] The captured talent data and the synchronized talent data are cleaned and verified to obtain preliminary talent data.

[0016] As a further limitation of the technical solution of the embodiment of the present invention, the multiple data sources include multiple recruitment websites and multiple social platforms.

[0017] As a further limitation of the technical solution of the embodiment of the present invention, the selecting of a distributed stream processing framework to perform real-time computing processing on the preliminary talent data to generate standard talent data specifically includes the following steps:

[0018] Choose a distributed stream processing framework;

[0019] The distributed stream processing framework is used to convert the preliminary talent data into a standard format, filter the required data, and perform real-time aggregate calculation processing to generate standard talent data.

[0020] As a further limitation of the technical solution of the embodiment of the present invention, the distributed stream processing framework is Apache Flink.

[0021] As a further limitation of the technical solution of the embodiment of the present invention, the analyzing of the standard talent data based on natural language processing technology, extracting multiple key information of talents, and constructing multiple talent portraits specifically include the following steps:

[0022] Based on natural language processing technology, the standard talent data is analyzed to extract multiple key talent information;

[0023] Identify multiple talent profile dimensions;

[0024] According to the multiple talent portrait dimensions, multiple talent key information is filled in to construct multiple talent portraits.

[0025] As a further limitation of the technical solution of the embodiment of the present invention, the multiple talent portrait dimensions include: basic personal information, educational background, work experience, skill list, project experience and career development intention.

[0026] As a further limitation of the technical solution of the embodiment of the present invention, the receiving of the enterprise recruitment demand, identifying multiple key demand factors and related weights, matching the demand with multiple talent portraits, determining multiple candidates and ranking the candidates specifically includes the following steps:

[0027] Receive recruitment needs from enterprises;

[0028] Analyze the recruitment needs of the enterprise and select multiple key demand factors from multiple talent portrait dimensions;

[0029] Determining relevant weights corresponding to a plurality of the key demand factors;

[0030] According to the multiple key demand factors and the corresponding relevant weights, the multiple talent portraits are matched with the demand, and multiple candidates are determined and ranked.

[0031] As a further limitation of the technical solution of the embodiment of the present invention, the user interaction data includes: click data, browsing data, collection data and resume submission behavior data.

[0032] A usability intelligent search system based on real-time computing, the system includes a data collection module, a real-time computing module, a talent profile building module, a demand matching module and a real-time feedback optimization module, wherein:

[0033] The data collection module is used to capture data from multiple data sources according to preset rules and frequencies, use web crawler technology, synchronize data with the company's internal database, and perform cleaning and verification to obtain preliminary talent data;

[0034] A real-time computing module is used to select a distributed stream processing framework to perform real-time computing processing on the preliminary talent data to generate standard talent data;

[0035] A talent portrait construction module is used to analyze the standard talent data based on natural language processing technology, extract multiple key talent information, and construct multiple talent portraits;

[0036] The demand matching module is used to receive the recruitment needs of enterprises, identify multiple key demand factors and related weights, match the needs with multiple talent portraits, determine multiple candidates and rank the candidates;

[0037] The real-time feedback optimization module is used to collect user interaction data, adjust the relevant weights according to the user interaction data, generate optimization adjustment results and provide feedback.

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] (1) Ability to obtain and process the latest talent information in a timely manner, ensure that search results reflect the real-time dynamics of the talent market, and improve the timeliness and availability of searches;

[0040] (2) The intelligent search algorithm with multi-dimensional weights, combined with talent profiling and real-time feedback optimization, can accurately match the recruitment needs of enterprises with the actual situation of candidates, thus improving the accuracy and practicality of search results;

[0041] (3) Ability to make real-time adjustments based on market dynamics and changes in corporate needs to adapt to talent search needs in different industries, positions and business scenarios;

[0042] (4) By providing real-time, accurate search results and personalized recommendation services, we can improve users’ search efficiency and satisfaction, and help companies find talents that meet their needs faster and better. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 A flow chart of an availability intelligent search method based on real-time calculation provided by an embodiment of the present invention is shown;

[0044] Figure 2 The application architecture diagram of the availability intelligent search system based on real-time computing provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0046] It is understandable that companies need to process a large number of resumes during the recruitment process. Traditional resume search methods usually rely on keyword matching and template matching, which are inefficient and prone to errors. They have the following main defects: (1) Insufficient real-time processing capabilities for large-scale data; (2) Inaccurate extraction of key information; and (3) Inability to effectively handle multi-source data fusion.

[0047] To solve the above problems, the embodiment of the present invention discloses an availability intelligent search method and system based on real-time computing, which uses web crawler technology to crawl data from multiple data sources according to preset rules and frequencies, synchronize data with the internal database of the enterprise, and clean and verify to obtain preliminary talent data; selects a distributed stream processing framework to perform real-time computing processing on the preliminary talent data to generate standard talent data; based on natural language processing technology, analyzes the standard talent data, extracts multiple talent key information, and constructs multiple talent portraits; receives corporate recruitment needs, identifies multiple key demand factors and related weights, matches multiple talent portraits with needs, determines multiple candidates and sorts them; collects user interaction data, adjusts related weights according to the user interaction data, generates optimization adjustment results and provides feedback. It can make full use of real-time computing technology to ensure the timeliness and accuracy of search results, so as to quickly and accurately find available talents that meet the needs for enterprises.

[0048] Specifically, Figure 1 The flowchart of the intelligent search method for availability based on real-time calculation provided by an embodiment of the present invention is shown.

[0049] In a preferred embodiment of the present invention, a method for intelligent search of availability based on real-time calculation is provided, and the method specifically comprises the following steps:

[0050] Step S101: According to preset rules and frequencies, web crawler technology is used to capture data from multiple data sources, synchronize data with the internal database of the enterprise, and perform cleaning and verification to obtain preliminary talent data.

[0051] In an embodiment of the present invention, data sources including multiple recruitment websites and multiple social platforms are determined, and according to preset rules and frequencies, web crawler technology is used to crawl data from multiple data sources to obtain crawled talent data, and data is synchronized with the internal database of the enterprise to obtain synchronized talent data. The crawled talent data and the synchronized talent data are then cleaned and verified to remove obvious errors, duplications, and incomplete data to obtain preliminary talent data.

[0052] Step S102: Select a distributed stream processing framework to perform real-time computation on the preliminary talent data to generate standard talent data.

[0053] In an embodiment of the present invention, a distributed stream processing framework is selected, which may be Apache Flink. Through the distributed stream processing framework, the preliminary talent data is converted to a standard format (data in different formats are uniformly converted into a standard format), filtered according to requirements (data that does not meet the requirements are filtered out according to specific conditions), and real-time aggregate calculations are performed (real-time aggregate calculations are performed on key indicators). The data changes are monitored in real time, and once new data enters, it is processed immediately to ensure that the latest talent market conditions can be reflected and standard talent data can be generated.

[0054] Step S103: Based on natural language processing technology, the standard talent data is analyzed to extract multiple key talent information and construct multiple talent portraits.

[0055] In an embodiment of the present invention, based on natural language processing technology, standard talent data is analyzed to extract multiple key talent information, and multiple talent portrait dimensions (including: basic personal information, educational background, work experience, skill list, project experience and career development intention, etc.) are determined. According to the multiple talent portrait dimensions, the multiple key talent information is filled in, multiple talent portraits are constructed, and the talent portraits are continuously updated and improved. According to new data and user feedback, the portrait content is dynamically adjusted to more accurately reflect the actual situation of the resume personnel.

[0056] Step S104: receiving the recruitment needs of the enterprise, identifying multiple key demand factors and related weights, matching the needs with the multiple talent portraits, determining multiple candidates and ranking the candidates.

[0057] In an embodiment of the present invention, by receiving the recruitment needs of an enterprise, analyzing the recruitment needs of the enterprise, selecting multiple key demand factors from multiple talent portrait dimensions, and determining the relevant weights corresponding to the multiple key demand factors, and then matching the needs of multiple talent portraits according to the multiple key demand factors and the corresponding relevant weights, determining multiple candidates and ranking the candidates, and fully considering the mutual influence and importance of different dimensions, providing flexible settings, allowing enterprises to adjust search conditions and weights according to actual conditions to meet talent search needs in different business scenarios.

[0058] Step S105: collect user interaction data, adjust the relevant weights according to the user interaction data, generate an optimization adjustment result and provide feedback.

[0059] In an embodiment of the present invention, by collecting user interaction data such as click data, browsing data, collection data, and resume submission behavior data, it is possible to reflect the user's satisfaction and preference for search results, use a real-time computing engine for analysis, adjust relevant weights in a timely manner, generate optimized adjustment results and provide feedback, thereby continuously improving the user experience, while also further improving the accuracy and practicality of the search.

[0060] Furthermore, Figure 2 The application architecture diagram of the availability intelligent search system based on real-time computing provided by an embodiment of the present invention is shown.

[0061] In another preferred embodiment of the present invention, an availability intelligent search system based on real-time calculation includes:

[0062] The data collection module 101 is used to capture data from multiple data sources according to preset rules and frequencies, use web crawler technology, synchronize data with the internal database of the enterprise, and perform cleaning and verification to obtain preliminary talent data.

[0063] In an embodiment of the present invention, the data collection module 101 determines the data sources including multiple recruitment websites and multiple social platforms, and uses web crawler technology to crawl data from multiple data sources according to preset rules and frequencies to obtain crawled talent data, and synchronizes data with the internal database of the enterprise to obtain synchronized talent data, and then cleans and verifies the crawled talent data and the synchronized talent data to remove obvious errors, duplications and incomplete data to obtain preliminary talent data.

[0064] The real-time computing module 102 is used to select a distributed stream processing framework to perform real-time computing processing on the preliminary talent data to generate standard talent data.

[0065] In an embodiment of the present invention, the real-time computing module 102 selects a distributed stream processing framework, which may be Apache Flink. Through the distributed stream processing framework, the preliminary talent data is converted to a standard format (data in different formats are uniformly converted into a standard format), filtered according to requirements (data that does not meet the requirements are filtered out according to specific conditions), and real-time aggregate calculations (real-time aggregate calculations of key indicators) are processed, and changes in data are monitored in real time. Once new data enters, it is processed immediately to ensure that the latest talent market conditions can be reflected and standard talent data can be generated.

[0066] The talent portrait construction module 103 is used to analyze the standard talent data based on natural language processing technology, extract multiple talent key information, and construct multiple talent portraits.

[0067] In an embodiment of the present invention, the talent portrait construction module 103 analyzes standard talent data based on natural language processing technology, extracts multiple key talent information, and determines multiple talent portrait dimensions (including: personal basic information, educational background, work experience, skill list, project experience and career development intention, etc.), fills in multiple talent key information according to multiple talent portrait dimensions, constructs multiple talent portraits, and continuously updates and improves talent portraits. According to new data and user feedback, the portrait content is dynamically adjusted to more accurately reflect the actual situation of the resume personnel.

[0068] The demand matching module 104 is used to receive the recruitment needs of the enterprise, identify multiple key demand factors and related weights, match the needs with the multiple talent portraits, determine multiple candidates and rank the candidates.

[0069] In an embodiment of the present invention, the demand matching module 104 receives the recruitment needs of the enterprise, analyzes the recruitment needs of the enterprise, selects multiple key demand factors from multiple talent portrait dimensions, and determines the relevant weights corresponding to the multiple key demand factors, and then matches the needs of multiple talent portraits according to the multiple key demand factors and the corresponding relevant weights, determines multiple candidates and sorts the candidates, and needs to fully consider the mutual influence and importance of different dimensions, provide flexible settings, and allow enterprises to adjust search conditions and weights according to actual conditions to meet talent search needs in different business scenarios.

[0070] The real-time feedback optimization module 105 is used to collect user interaction data, adjust the relevant weights according to the user interaction data, generate optimization adjustment results and provide feedback.

[0071] In an embodiment of the present invention, the real-time feedback optimization module 105 can reflect the user's satisfaction and preference for search results by collecting user interaction data such as click data, browsing data, collection data, and resume submission behavior data, and uses a real-time computing engine to perform analysis, timely adjust relevant weights, generate optimization adjustment results and provide feedback, thereby continuously improving the user experience, while also further improving the accuracy and practicality of the search.

[0072] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0073] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0074] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A method for intelligent availability search based on real-time computing, characterized in that: The method specifically comprises the following steps: According to the preset rules and frequency, we use web crawler technology to capture data from multiple data sources, synchronize data with the company's internal database, and clean and verify it to obtain preliminary talent data; Select a distributed stream processing framework to perform real-time computing on the preliminary talent data to generate standard talent data; Based on natural language processing technology, the standard talent data is analyzed to extract multiple key talent information and construct multiple talent portraits; Receive the recruitment needs of enterprises, identify multiple key demand factors and related weights, match the needs with multiple talent portraits, determine multiple candidates and rank the candidates; Collect user interaction data, adjust the relevant weights according to the user interaction data, generate optimization adjustment results and provide feedback.

2. The availability intelligent search method based on real-time calculation according to claim 1 is characterized in that: The method of using web crawler technology to crawl data from multiple data sources according to preset rules and frequencies, synchronize data with the internal database of the enterprise, and perform cleaning and verification to obtain preliminary talent data specifically includes the following steps: Identify multiple data sources; According to the preset rules and frequency, web crawler technology is used to crawl data from multiple data sources to obtain crawled talent data; Synchronize the internal database of the enterprise to obtain synchronized talent data; The captured talent data and the synchronized talent data are cleaned and verified to obtain preliminary talent data.

3. The availability intelligent search method based on real-time calculation according to claim 2 is characterized in that: The multiple data sources include multiple recruitment websites and multiple social platforms.

4. The availability intelligent search method based on real-time calculation according to claim 1 is characterized in that: The step of selecting a distributed stream processing framework to perform real-time computation on the preliminary talent data to generate standard talent data specifically includes the following steps: Choose a distributed stream processing framework; The distributed stream processing framework is used to convert the preliminary talent data into a standard format, filter the required data, and perform real-time aggregate calculation processing to generate standard talent data.

5. The availability intelligent search method based on real-time calculation according to claim 4 is characterized in that: The distributed stream processing framework is Apache Flink.

6. The availability intelligent search method based on real-time calculation according to claim 1 is characterized in that: The method of analyzing the standard talent data based on natural language processing technology, extracting multiple key talent information, and constructing multiple talent portraits specifically includes the following steps: Based on natural language processing technology, the standard talent data is analyzed to extract multiple key talent information; Identify multiple talent profile dimensions; According to the multiple talent portrait dimensions, multiple talent key information is filled in to construct multiple talent portraits.

7. The availability intelligent search method based on real-time calculation according to claim 6 is characterized in that: The multiple dimensions of the talent portrait include: basic personal information, educational background, work experience, skill list, project experience and career development intention.

8. The availability intelligent search method based on real-time calculation according to claim 7 is characterized in that: The receiving of the enterprise recruitment demand, identifying multiple key demand factors and related weights, matching the demand with multiple talent portraits, determining multiple candidates and ranking the candidates specifically includes the following steps: Receive recruitment needs from enterprises; Analyze the recruitment needs of the enterprise and select multiple key demand factors from multiple talent portrait dimensions; Determining relevant weights corresponding to a plurality of the key demand factors; According to the multiple key demand factors and the corresponding relevant weights, the multiple talent portraits are matched with the demand, and multiple candidates are determined and ranked.

9. The availability intelligent search method based on real-time calculation according to claim 1, characterized in that: The user interaction data includes: click data, browsing data, collection data and resume submission behavior data.

10. An availability intelligent search system based on real-time computing, characterized in that: The system includes a data collection module, a real-time calculation module, a talent profile building module, a demand matching module and a real-time feedback optimization module, wherein: The data collection module is used to capture data from multiple data sources according to preset rules and frequencies, use web crawler technology, synchronize data with the company's internal database, and perform cleaning and verification to obtain preliminary talent data; A real-time computing module is used to select a distributed stream processing framework to perform real-time computing processing on the preliminary talent data to generate standard talent data; A talent portrait construction module is used to analyze the standard talent data based on natural language processing technology, extract multiple key talent information, and construct multiple talent portraits; The demand matching module is used to receive the recruitment needs of enterprises, identify multiple key demand factors and related weights, match the needs with multiple talent portraits, determine multiple candidates and rank the candidates; The real-time feedback optimization module is used to collect user interaction data, adjust the relevant weights according to the user interaction data, generate optimization adjustment results and provide feedback.

Images