A skill and post matching method and system, computer readable storage medium

Abstract

The application discloses a kind of skill and post matching method and system, computer readable storage medium, receive prediction ability demand;Carry out prediction;According to the test data of ability provided according to prediction result;Receive test feedback information, adjust ability test data according to test feedback information;Whether test is completed is judged, and ability report is dynamically generated;According to ability report, work matching recommendation is carried out.Complete user skill and the system that post is matched, before interview, has formed relatively objective user skill identification by prediction ability demand and test feedback information, and work matching recommendation is carried out according to ability report, also help post avoid screening from countless resume, eliminate blind marriage and the problem of mismatch of ability of use, convenient to use, strong in pertinence, can effectively improve enterprise recruitment efficiency and quality, improve the accuracy and fairness of enterprise employment, also improve the matching degree and success rate of personal job hunting.

Description

Technical Field

[0001] The present invention relates to recruitment and application technology, and in particular to a method and system for matching skills with positions, and a computer-readable storage medium. Background Art

[0002] With the development of technology, recruitment is often conducted online. However, a common problem is that companies receive many irrelevant resumes, making it difficult to assess the degree to which applicants' skills match the required positions, and it is also prone to suspicion. Therefore, existing technologies have shortcomings and need improvement. Summary of the Invention

[0003] The present invention provides a method and system for matching skills and positions, and a computer-readable storage medium. The technical problems to be solved include: how to avoid the problem of mismatch between employment capabilities, how to improve the efficiency and quality of corporate recruitment, how to improve the accuracy and fairness of corporate employment, and how to improve the matching degree and success rate of individual job seekers.

[0004] The technical solutions of the present invention are as follows:

[0005] A method for matching skills and positions, comprising the following steps: S1A, receiving predicted capability requirements; S2A, making a prediction; S3A, providing capability test data based on the prediction result and presenting the capability test data; S4A, receiving test feedback information, adjusting the capability test data based on the test feedback information, and presenting the adjusted capability test data; S5A, judging whether the test is completed, and returning to execute S4A if not, and executing S6A if yes; S6A, dynamically generating a capability report; and S7A, making a job matching recommendation based on the capability report.

[0006] Preferably, in S1A, predicted competency requirements are received by receiving resumes; or in S2A, predictions are made through machine learning. Preferably, in S4A, real-time competency probabilities are analyzed based on test feedback information, and competency test data is adjusted based on the results of the real-time competency probabilities analysis. Preferably, in S7A, job matching recommendations are made based on the competency reports and work preference information; or after S7A, interview notifications are received and online interviews are conducted.

[0007] A method for matching skills and positions includes the following steps: S1B, sending predicted ability requirements; S2B, submitting basic information; S3B, obtaining ability test data; S4B, sending test feedback information and obtaining adjusted ability test data; S5B, judging whether the test is completed, otherwise returning to execute S4B, and if so, executing S6B; S6B, obtaining a dynamically generated ability report; S7B, obtaining a job matching recommendation based on the ability report.

[0008] Preferably, in S1B, the predicted ability requirements are submitted by submitting a resume; or in S2B, basic information is submitted by submitting a resume; or in S1B, the predicted ability requirements are submitted in a question-and-answer format; or in S2B, basic information is submitted in a question-and-answer format. Preferably, in S2B, job preference information is also submitted; or, job preference information is submitted before S7B. Preferably, after S7B, an online interview is also conducted.

[0009] Preferably, a skills and positions matching system comprises: a memory for storing a computer program; and a processor for implementing the steps of any one of the skills and positions matching methods when executing the computer program.

[0010] Preferably, a computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the computer program implements the steps of any one of the methods for matching skills and positions.

[0011] By adopting the above scheme, the present invention establishes a complete system for matching user skills with employment positions. Before the interview, a relatively objective user skill identification is formed by predicting ability requirements and test feedback information, and job matching recommendations are made based on the ability report. This overcomes the existing technology of only submitting a large number of resumes without knowing whether they are suitable. It also helps employers avoid screening from countless resumes and eliminates the problem of blind marriage and dumb marriage type of employment ability mismatch. It is easy to use and highly targeted, which can effectively improve the efficiency and quality of corporate recruitment, improve the accuracy and fairness of corporate employment, and also improve the matching degree and success rate of individual job seekers. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A schematic diagram of a first embodiment of the present invention;

[0013] Figure 2 is a schematic diagram of a second embodiment of the present invention;

[0014] Figure 3 is a schematic diagram of a third embodiment of the present invention;

[0015] Figure 4 is a schematic diagram of a fourth embodiment of the present invention;

[0016] Figure 5 is a schematic diagram of a fifth embodiment of the present invention;

[0017] Figure 6 is a schematic diagram of a sixth embodiment of the present invention;

[0018] Figure 7 is a schematic diagram of a seventh embodiment of the present invention;

[0019] Figure 8 is a schematic diagram of an eighth embodiment of the present invention;

[0020] Figure 9 is a schematic diagram of a ninth embodiment of the present invention;

[0021] Figure 10 is a schematic diagram of a tenth embodiment of the present invention;

[0022] Figure 11 This is a flow chart of the adaptive machine learning prediction capability according to the eleventh embodiment of the present invention;

[0023] Figure 12 is a schematic diagram of a twelfth embodiment of the present invention;

[0024] Figure 13 This is a diagram illustrating the classification of topics according to the thirteenth embodiment of the present invention;

[0025] Figure 14 are three capability response curves of the fourteenth embodiment of the present invention;

[0026] Figure 15 are three capability response curves of the fifteenth embodiment of the present invention;

[0027] Figure 16 are three capability response curves of the sixteenth embodiment of the present invention;

[0028] Figure 17 This is a schematic diagram of a dynamic capability report according to the seventeenth embodiment of the present invention. DETAILED DESCRIPTION

[0029] For ease of understanding of the present invention, the present invention will be described in more detail below in conjunction with the accompanying drawings and specific embodiments. However, the present invention can be implemented in many different forms and is not limited to the embodiments described in this specification. It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected" to another element, it may be directly connected to the other element or there may be a central element at the same time. Unless otherwise defined, all technical and scientific terms used in this specification have the same meaning as those generally understood by those skilled in the art to which the present invention belongs. The terms used in this specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0030] like Figure 1As shown, one embodiment of the present invention is a method for matching skills and positions, which includes the following steps: S1A, receiving predicted capability requirements; S2A, making predictions; S3A, providing capability test data based on the prediction results, and presenting the capability test data; S4A, receiving test feedback information, adjusting the capability test data based on the test feedback information, and presenting the adjusted capability test data; S5A, judging whether the test is completed, otherwise returning to execute S4A, if yes, executing S6A; S6A, dynamically generating a capability report; S7A, making job matching recommendations based on the capability report. By adopting the above scheme, the present invention establishes a complete system for matching user skills with employment positions. Before the interview, a relatively objective user skill identification is formed by predicting ability requirements and test feedback information, and job matching recommendations are made based on the ability report. This overcomes the existing technology of only submitting a large number of resumes without knowing whether they are suitable. It also helps employers avoid screening from countless resumes and eliminates the problem of blind marriage and dumb marriage type of employment ability mismatch. It is easy to use and highly targeted, which can effectively improve the efficiency and quality of corporate recruitment, improve the accuracy and fairness of corporate employment, and also improve the matching degree and success rate of individual job seekers.

[0031] Preferably, S1A receives the predicted ability requirements; for example, in S1A, the predicted ability requirements are received in the form of questions and answers; preferably, in S1A, the predicted ability requirements are received in the form of resumes; the predicted ability requirements can help improve the matching degree and accuracy of the ability test. For example, the predicted ability requirements are obtained through certificates and some supporting documents. Figure 2 As shown, one embodiment of the present invention is a method for matching skills with positions, comprising the following steps: S1A, receiving predicted ability requirements by receiving a resume; S2A, performing a prediction; S3A, providing ability test data based on the prediction result and presenting the ability test data; S4A, receiving test feedback information, adjusting the ability test data based on the test feedback information, and presenting the adjusted ability test data; S5A, determining whether the test is completed; if not, returning to S4A; if so, executing S6A; S6A, dynamically generating an ability report; S7A, performing a job matching recommendation based on the ability report. This facilitates the reception of predicted ability requirements and enables interaction with predicted ability requirements.

[0032] Preferably, S2A performs prediction; preferably, in S2A, prediction is performed by machine learning; for example, prediction is performed by machine learning, including the steps of: setting the priority of test items and / or test questions according to the prediction capability requirements, outputting the test items and their test questions according to the priority, verifying the response effect to the test questions, updating the priority of the test items and / or test questions in combination with the response curve, and judging whether the test is completed, otherwise continue to output the test items and their test questions according to the priority, and if so, score or evaluate this prediction, output the prediction result, and adjust the system model of machine learning at the same time, and set or adjust the priority of the test items and / or test questions according to the prediction capability requirements. For example, big data is used to obtain the preference information of the current predicted object and perform prediction; the purpose of prediction mainly includes conducting appropriate capability tests for the current predicted object. For example, big data is used to obtain the preference information of the current predicted object and perform prediction by machine learning; for example, the priority of test items and / or test questions is set according to the preference information and prediction capability requirements, and the design of preference information is conducive to improving the accuracy and effectiveness of test items and / or test questions. As Figure 3 As shown, one embodiment of the present invention is a method for matching skills with positions, which includes the following steps: S1A, receiving predicted capability requirements; S2A, making predictions through machine learning; S3A, providing capability test data based on the prediction results and presenting the capability test data; S4A, receiving test feedback information, adjusting the capability test data based on the test feedback information, and presenting the adjusted capability test data; S5A, determining whether the test is completed; if not, returning to S4A; if yes, executing S6A; S6A, dynamically generating a capability report; S7A, making job matching recommendations based on the capability report. Machine learning and big data analysis can both be optimized using existing technologies. This can improve prediction accuracy and avoid having middle school students take university exams, or having liberal arts students take science and engineering exams. While improving test efficiency, it also increases test comfort, thereby enhancing the user experience.

[0033] Preferably, S3A provides ability test data based on the prediction results and presents the ability test data; for example, in S3A, the prediction results include the job requirements of a specific enterprise, or the ability test data is targeted at the job requirements of a specific enterprise, or the prediction results include specific types of job requirements, or the ability test data is targeted at specific types of job requirements. In S2A, predictions are made for specific job requirements, such as predictions for specific job requirements through machine learning. This allows for customized job tests for job seekers or hiring positions, and also for providing suitable predictions or ability test data for a large class of positions with the same or similar ability requirements. In conjunction with the dynamic generation of ability reports, job matching analysis for specific enterprises or specific positions can be achieved, thereby improving the effective matching effect for specific positions in certain specific enterprises. For example, at least two sets of ability test data are provided based on the prediction results and their themes are presented, that is, the themes of at least two sets of ability test data are presented to the current predicted object, and then the current predicted object's choice of the theme is received, and then the ability test data corresponding to the theme is presented, that is, the ability test data corresponding to the theme is presented to the current predicted object. This allows the current predicted object to be determined by multiple sets of themes. Personal preferences and ability range. Preferably, in S4A, the ability probability is analyzed in real time according to the test feedback information, and the ability test data is adjusted according to the results of the real-time analysis of the ability probability. For example, the ability test data is adjusted in real time according to the preference information and the real-time analysis results of the ability probability, that is, the ability test data is adjusted dynamically while the test is being conducted. In this way, not only the ability report is dynamically generated, but also the ability test data is dynamically adjusted. Therefore, compared with the existing sets of test questions, the skill and position matching method of the present invention is more accurate and efficient, and more importantly, the test questions are more in line with the ability level of the current predicted object, the time for answering the questions is shorter, and the test efficiency of the current predicted object is improved. Figure 4 As shown, one embodiment of the present invention is a method for matching skills to positions, comprising the following steps: S1A, receiving predicted ability requirements; S2A, performing a prediction; S3A, providing ability test data based on the prediction results and presenting the ability test data; S4A, receiving test feedback information, performing real-time ability probability analysis based on the test feedback information, adjusting the ability test data based on the results of the real-time ability probability analysis, and presenting the adjusted ability test data; S5A, determining whether the test is complete; if not, returning to S4A; if yes, executing S6A; S6A, dynamically generating an ability report; S7A, making job matching recommendations based on the ability report. This process of testing and adjusting results in increased accuracy over time, thereby improving the test rate of the current predicted subject and reducing the number of questions, saving the test time of the current predicted subject.

[0034] Preferably, S4A receives test feedback information, adjusts the ability test data according to the test feedback information, and presents the adjusted ability test data; for example, in adjusting the ability test data according to the test feedback information, the ability test data is adjusted according to the timeliness and accuracy of the test feedback information, one indicator is the completion time, and the other indicator is the completion quality. The combination of the two indicators can accurately present the true level of the current predicted object. For example, the ability test data is adjusted in real time according to the test feedback information; because the time and accuracy provided by the test feedback information can reflect the actual ability of the current predicted object and the degree of familiarity with the test content, the ability test data is adjusted in real time according to the test feedback information, which can help make the ability test data closer and closer to the true level of the current predicted object in the next ability test. For example, while receiving the test feedback information, the surrounding environment information of the current predicted object is also obtained, which can help improve the authenticity of the test feedback information and ensure that it is completed independently by himself.

[0035] Preferably, S5A determines whether the test is complete. If not, the process returns to S4A, and if so, executes S6A. That is, S4A is executed in a loop. If the test is not complete, it continues to receive test feedback, adjusts the capability test data based on the test feedback, and presents the adjusted capability test data. Alternatively, if the remote user abandons the process and the connection is lost, the process is terminated directly. In other words, any step from S1A to S7A, and even S8A, can be interrupted, and interruptions should not cause system crashes.

[0036] Preferably, S6A generates a capability report; preferably, S6A dynamically generates a capability report; for example, the capability report includes general capability analysis, professional capability analysis, and specific skill analysis, etc., and may also include a job matching analysis for a specific enterprise, thereby improving the effective matching effect for specific positions in certain specific enterprises. For example, the capability report is dynamically generated, and what is presented is the current capability of the current predicted object. The next test can be performed directly on the previous capability report. For example, S1A receives predicted capability requirements, including: judging whether a capability report exists, and if so, using the capability report as at least a part of the predicted capability requirement. For example, a temporary capability report is generated each time test feedback information is received, and the two adjacent temporary capability reports are compared to judge whether the current capability test of the current predicted object is normal. If so, a completed version capability report is generated when the test is completed, otherwise an evaluation version capability report is generated when the test is completed. Since the ability of the current predicted object should be stable, without external assistance, it should show a smooth and expected result that is consistent with the ability test data adjusted according to the test feedback information. Even if there is a deviation, it should not be too much. Therefore, through two different versions of the ability report, some references can be provided for different job requirements of different companies.

[0037] Preferably, in S7A, job matching recommendations are made based on the capability report. Preferably, in S7A, job matching recommendations are made based on the capability report and the job preference information; for example, the job preference information includes time requirements, location requirements, salary requirements, and accommodation requirements. Figure 5 As shown, one embodiment of the present invention is a method for matching skills and positions, which includes the following steps: S1A, receiving predicted ability requirements; S2A, making predictions; S3A, providing ability test data based on the prediction results, and presenting the ability test data; S4A, receiving test feedback information, adjusting the ability test data based on the test feedback information, and presenting the adjusted ability test data; S5A, judging whether the test is completed, otherwise returning to execute S4A, if yes, executing S6A; S6A, dynamically generating an ability report; S7A, making job matching recommendations based on the ability report and work tendency information. Through the above description and analysis, it can be seen that the ability report and work tendency information after the ability test are combined, and the recommended position after job matching is not limited to the work location and salary requirements of the existing recruitment method. It is more in line with the ability of the current predicted object, which greatly improves the accuracy of job recruitment and can truly achieve the goal of calling on people and making them capable.

[0038] Preferably, after S7A, the interview notification is received and an online interview is conducted. For example, for a specific position of remote work, only voice communication can be used as an online interview; for a general position, video chat can be used as an online interview. Figure 6 As shown, one embodiment of the present invention is a method for matching skills with positions, which includes the following steps: S1A, receiving predicted ability requirements; S2A, making a prediction; S3A, providing ability test data based on the prediction results and presenting the ability test data; S4A, receiving test feedback information, adjusting the ability test data based on the test feedback information, and presenting the adjusted ability test data; S5A, determining whether the test is completed, if not, returning to execute S4A, if yes, executing S6A; S6A, dynamically generating an ability report; S7A, making a job matching recommendation based on the ability report and work preference information; S8A, receiving an interview notification and conducting an online interview. The specific online interview can be conducted in a conventional manner.

[0039] The previous embodiments are all system-related and can be implemented through servers, software systems or mobile phone apps; the user-side skills and job matching method can be implemented based on the system-side skills and job matching method, as described below. Figure 7As shown, one embodiment of the present invention is a method for matching skills with positions, which includes the following steps: S1B, sending predicted ability requirements; S2B, submitting basic information; S3B, obtaining ability test data; S4B, sending test feedback information and obtaining adjusted ability test data; S5B, determining whether the test is completed, if not, returning to execute S4B, if yes, executing S6B; S6B, obtaining a dynamically generated ability report; S7B, obtaining job matching recommendations based on the ability report. The technical effects of this embodiment are similar to those of the previous system embodiment. The present invention establishes a complete system for matching user skills with job positions. Before the interview, a relatively objective user skill identification is formed through predicted ability requirements and test feedback information, and job matching recommendations are made based on the ability report. This overcomes the existing technology of only knowing how to submit a large number of resumes without knowing whether they are suitable. It also helps employers avoid screening from countless resumes, eliminating the problem of blind marriage and dumb marriage of employment ability mismatch. It is easy to use and highly targeted, and can effectively improve the efficiency and quality of corporate recruitment, enhance the accuracy and fairness of corporate employment, and also improve the matching degree and success rate of individual job seekers. That is, a method for matching skills with positions is implemented based on the various embodiments of the skill matching method with steps S1A to S7A described above, and includes the following steps: S1B, sending predicted capability requirements; S2B, submitting basic information; S3B, obtaining capability test data; S4B, sending test feedback information and obtaining adjusted capability test data; S5B, determining whether the test is complete; if not, returning to S4B; if yes, executing S6B; S6B, obtaining a dynamically generated capability report; S7B, obtaining job matching recommendations based on the capability report. Other embodiments may be similarly implemented.

[0040] Preferably, S1B sends the forecast capability requirement; preferably, in S1B, the forecast capability requirement is sent by submitting a resume; preferably, in S2B, the basic information is submitted by submitting a resume; Figure 8 As shown, one embodiment of the present invention is a method for matching skills with positions, which includes the following steps: S1B, sending predicted ability requirements; S2B, submitting basic information in the form of a resume; S3B, obtaining ability test data; S4B, sending test feedback information, and obtaining the adjusted ability test data; S5B, judging whether the test is completed, otherwise returning to execute S4B, if yes, executing S6B; S6B, obtaining a dynamically generated ability report; S7B, obtaining a job matching recommendation based on the ability report. Preferably, in S1B, the predicted ability requirements are sent in a question-and-answer manner; preferably, in S2B, the basic information is submitted in a question-and-answer manner. The specific implementation method, such as submitting by filling in blanks on a mobile phone, is not particularly limited in the various embodiments of the present invention.

[0041] Preferably, in S2B, basic information is submitted; preferably, in S2B, work preference information is also submitted; Figure 9 As shown, one embodiment of the present invention is a method for matching skills with positions, comprising the following steps: S1B, sending predicted capability requirements; S2B, submitting basic information and work preference information; S3B, obtaining capability test data; S4B, sending test feedback information and obtaining adjusted capability test data; S5B, determining whether the test is complete; if not, returning to S4B; if so, executing S6B; S6B, obtaining a dynamically generated capability report; S7B, obtaining job matching recommendations based on the capability report. As data volumes increase, work preference information can be further refined, for example, to include requirements for non-Huawei Africa positions, or requirements for Tencent's Shenzhen headquarters, such as "Don't ask me to take this test if my annual salary is less than seven figures," or "996 is fine, 007 is better," and so on.

[0042] Preferably, S3B obtains the ability test data; for example, the ability test data is obtained from a remote server or cloud via a mobile phone. For example, the specific ability test data is constantly adjusted, so S3B only obtains a portion or the first ability test data.

[0043] Preferably, S4B sends test feedback information to obtain the adjusted ability test data; the test feedback information can include options for multiple-choice questions, text for fill-in-the-blank questions, text for simple questions, simple diagrams and explanations for various question types, etc. Sending the test feedback information can be done via a mobile phone, such as through voice input or text input, or by taking a hand-drawn picture, or by uploading a program.

[0044] Preferably, S5B determines whether the test is completed, otherwise returns to execute S4B, and if so, executes S6B; this is actually the same as the previous one, which is a loop execution. It can be roughly understood as doing a question, system evaluation and analysis, then generating a question, and then doing another question, and looping in sequence until the test is completed.

[0045] Preferably, S6B, obtain a dynamically generated capability report; the dynamically generated capability report is mainly for this test, and the next test may require another dynamically generated capability report.

[0046] Preferably, S7B obtains job matching recommendations based on the capability report. Preferably, job preference information is submitted before S7B. For example, job preference information is submitted in S2B or S4B. In this case, the job matching recommendations obtained by the current user are the recommended jobs.

[0047] Preferably, after S7B, an online interview will be conducted. Figure 10As shown, one embodiment of the present invention is a method for matching skills and positions, which includes the following steps: S1B, sending predicted ability requirements; S2B, submitting basic information and work tendency information; S3B, obtaining ability test data; S4B, sending test feedback information, and obtaining adjusted ability test data; S5B, judging whether the test is completed, otherwise returning to execute S4B, if yes, executing S6B; S6B, obtaining a dynamically generated ability report; S7B, obtaining job matching recommendations based on the ability report; S8B, conducting an online interview.

[0048] Preferably, a skills-to-position matching system includes: a memory for storing a computer program; and a processor for implementing the steps of any one of the skills-to-position matching methods described above when executing the computer program. Preferably, a skills-to-position matching system includes relevant structures or functional modules for implementing the skills-to-position matching methods described in various embodiments, or the skills-to-position matching methods described in various embodiments are implemented using the skills-to-position matching system.

[0049] The following is an example of a specific operation from the system perspective. Figure 11 As shown, one embodiment of the present invention is a method for matching skills with positions, wherein the adaptive machine learning prediction process includes the following steps: starting a test, setting priorities, selecting questions, verifying the effectiveness of the answers, updating priorities based on the response curve, determining whether the test is complete, and returning to set questions. If yes, scoring is performed, publishing recruitment results based on the scores, adding the scores to the system model, and returning to set priorities. In other words, predictions through machine learning include the above steps and may also include other steps.

[0050] The following takes IT as an example, but is not limited to IT. To solve the problem of mismatch between the capabilities of IT engineers and those employed by enterprises, IT engineers include students and social users, etc., and a method for matching skills with positions is proposed. It can be called an adaptive artificial intelligence method or system that prioritizes IT skills and solves the mismatch between people and positions. For example, a skill and position matching system is used to implement the skill and position matching methods of each embodiment, or has functional modules corresponding to the skill and position matching methods of each embodiment. For example, a skill and position matching system includes: a receiving module that receives predicted capability requirements; a prediction module that makes predictions; an analysis module that provides capability test data based on the prediction results and presents the capability test data; an intelligent module that receives test feedback information, adjusts the capability test data based on the test feedback information, and presents the adjusted capability test data; a judgment module that determines whether the test is completed, otherwise the intelligent module continues to work, and if so, dynamically generates a capability report; a matching module that makes job matching recommendations based on the capability report. And so on.

[0051] From another perspective, a skills-job matching system includes a predictive competency module, a dynamic reporting module, a corporate job recommendation module, and a competency analysis module. Within the predictive competency module, users select a corresponding competency test module. Machine learning then uses the data from the test module to generate a prediction for the user. Then, based on the user's performance during the test, adaptive data is provided to perform real-time competency probability analysis. After the test, a competency report is dynamically generated, and job matching recommendations are made based on the user's competency report. This system, while supporting the upload of traditional resumes, generates a new type of personal electronic resume, primarily based on competency reports. This makes the job search process more fair, accurate, and efficient for users and facilitates companies in finding the most suitable talent. Furthermore, the system's well-designed architecture, centered around machine learning models and integrated with common PC or mobile software, makes it easy to use and highly targeted, effectively improving the efficiency, quality, and fairness of corporate recruitment.

[0052] The following is an example of a specific operation in combination with the system and user aspects. Figure 12 As shown, one embodiment of the present invention is a method for matching skills with positions, comprising the following steps: Initially, after logging in, a user can choose to search for a job or take a quiz based on their registration and previous information. Searching for a job involves answering questions, which then lead to job recommendations; the questions require selecting a position, a work location, and other related questions. The system then recommends a model or a matching model, allowing the user to view the recommended results and then apply for the position with the selected position. The user can then optionally access the position tracking manager to view the results of the job application, including whether the application has been accepted, is pending, or has been rejected.

[0053] When taking the test, users select an assessment library, either automatically or by themselves. The test then begins. Considering test efficiency and user experience, the number of questions should be minimal, with easy-to-answer questions and a short duration. For example, consider 15 multiple-choice questions, with a time limit of 5 to 15 minutes per question, or 1 to 10 minutes per question. Examples include IRT (Item Response Theory) models, time series models, anti-deception models, and evaluation models. A competency report, or test assessment report, is then dynamically generated, which allows for job matching recommendations, including system-recommended models or matching models. When accessing the job tracking manager, users can view the results of their job application, including acceptance, pending processing, or rejection. If an interview opportunity is available, users can accept it. This will initially involve an online interview, such as video or voice chat, or a competency assessment. Afterward, the application can be finalized, or an in-person interview can be conducted. If the candidate is hired, the system or company will send a notification. This continues in a similar fashion.

[0054] In the test, for IT engineers, the questions should include basic skills and programming languages ​​and frameworks that he should master, such as Figure 13 As shown, for example, basic skills include general coding logic, algorithms and data structures, and languages ​​and frameworks include Python, Java, Javascript, Go, Rust and C++. This is just an example and should not be considered exhaustive. Different positions have different requirements. You can use a capability curve to reflect the current user's capabilities and then compare it with the capability curve set for the position in the system. The capability curve or capability response curve is shown below. Figure 14 、 15 As shown in Figure 16, this can simplify the system evaluation and make it easier for recruiters to use it. Figure 14 、 15 The capability curves shown in FIG16 can be presented in the same graph or can be dispersed to form nine graphs. For example, in various embodiments, the dynamically generated capability report is displayed graphically to highlight strengths and weaknesses. The dynamic capability report graph of one embodiment of the present invention is shown in FIG16. Figure 17 shown for example reference.

[0055] In some embodiments, an example of some items of a capability report is given below. The capability assessment results of an IT engineer are shown in the following table:

[0056]

[0057] This makes it easy to determine whether he meets the requirements of a certain position, greatly simplifying the company's workload in selecting people and improving recruitment efficiency.

[0058] Preferably, a computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the computer program implements the steps of any one of the methods for matching skills and positions.

[0059] Furthermore, embodiments of the present invention also include a method and system for matching skills and positions, and a computer-readable storage medium formed by combining the technical features of the above embodiments.

[0060] The reader should understand that, in the description of this specification, the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" and the like mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are mutually inconsistent. In the several embodiments provided in this specification, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the method embodiments described above are merely schematic. For example, the division of steps is only a logical function division. In actual implementation, there may be other division methods, such as multiple steps can be combined or integrated into another step, or some features can be ignored or not executed.

[0061] If the above method is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program code.

[0062] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and such modifications or substitutions are intended to be within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A method for matching skills with positions, characterized in that: The following steps are involved: S1A, receiving a predicted capacity requirement, including: determining whether a capacity report exists, and if so, using the capacity report as at least a portion of the predicted capacity requirement; S2A uses big data to obtain the preference information of the current predicted object and makes predictions through machine learning; S3A, providing ability test data according to the prediction result, and presenting the ability test data; S4A, receiving test feedback information, adjusting the ability test data according to the test feedback information, and presenting the adjusted ability test data; wherein, each time test feedback information is received, a temporary ability report is generated, and two adjacent temporary ability reports are compared to determine whether the current ability test of the current predicted object is normal. If yes, a completed version ability report is generated when the test is completed; otherwise, an evaluation version ability report is generated when the test is completed; S5A, determines whether the test is completed, if not, returns to execute S4A, if yes, executes S6A; S6A, dynamically generate capability reports; S7A, making job matching recommendations based on the ability report and work preference information; In S2A, prediction is performed through machine learning, including the following steps: Prioritize test items and / or test questions based on the preference information and predicted capacity needs, Output test items and their test issues according to priority, Verify the effectiveness of responses to test questions, Update the priority of test items and / or test questions based on the response curve, Determine whether the test is completed. If not, continue to output the test items and their test questions according to priority. If yes, score or evaluate this prediction, output the prediction results, adjust the machine learning system model, and set or adjust the priority of the test items and / or test questions according to the prediction capability requirements.

2. The method for matching skills and positions according to claim 1, characterized in that: In S1A, the predicted capability requirements are received by receiving resumes.

3. The method for matching skills and positions according to claim 1, characterized in that: In S2A, at least two sets of ability test data are provided based on the prediction results, and the themes of the at least two sets of ability test data are presented to the current predicted object. Then, the current predicted object's choice of the theme is received, and the ability test data corresponding to the theme is presented to the current predicted object to determine the current predicted object's personal preferences and ability range; in S4A, real-time analysis of ability probability is performed based on the test feedback information, and the ability test data is adjusted in real time based on the preference information and the real-time analysis results of ability probability.

4. The method for matching skills and positions according to claim 1, characterized in that: In S7A, job matching recommendations are made based on the ability report and work preference information; or after S7A, interview notifications are received and online interviews are conducted.

5. A skills and job matching system, characterized by: include: Memory for storing computer programs; A processor, configured to implement the steps of the method for matching skills and positions as described in any one of claims 1 to 4 when executing the computer program.

6. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method for matching skills and positions according to any one of claims 1 to 4.

Images