Enterprise shortage talent recommendation method based on multi-party co-construction and sharing

Abstract

The invention relates to the technical field of talent recommendation management, in particular to an enterprise shortage talent recommendation party based on multi-party co-construction and sharing, and the method comprises the following steps: S1, obtaining talent information from multiple channels, and constructing an international talent pool based on the talent information; s2, according to talent information and talent type requirements in an international talent pool, establishing different types of talent individual DIKWP models; s3, obtaining detailed information of working posts, and constructing a post DIKWP model according to the detailed information of the working posts; s4, on the basis of the post DIKWP model and different types of talent individual DIKWP models, calculating cognitive deviation conditions of the talent individuals and post intentions to obtain a first initial recommendation result; and S5, performing weight assignment on the first initial recommendation result according to a constraint condition of the job application demand, and performing sorting based on an assignment result to obtain a final talent recommendation result.

Description

Technical Field

[0001] The present invention relates to the technical field of talent recommendation management, and in particular to a method for recommending scarce talents for enterprises based on multi-party co-construction and sharing. Background Art

[0002] With the acceleration of globalization and the development of information technology, enterprises have an increasing demand for international talents. In the fierce market competition environment, enterprises not only need to attract and retain excellent talents, but also need to efficiently and accurately match talents with job requirements, especially when looking for scarce talents with specific skills and backgrounds. This challenge is particularly obvious.

[0003] At present, enterprises mainly rely on traditional recruitment channels to find scarce talents, such as recruitment websites, headhunting services, campus recruitment, etc. Although these channels can provide a certain amount of talent information, they have obvious shortcomings in the following aspects: 1. Information fragmentation: The information provided by traditional recruitment channels is often scattered and lacks systematic integration, which requires enterprises to invest a lot of time and energy in screening candidates; 2. Low matching accuracy: Most of the existing talent recommendation algorithms are based on keyword matching and simple resume screening, which makes it difficult to comprehensively and accurately evaluate the matching degree between the comprehensive ability of talents and job requirements; 3. Difficulty in matching international talents: For enterprises that need international talents, the existing recruitment channels and recommendation systems often cannot effectively cover high-quality talent resources around the world, especially for high-end talents with special skills and backgrounds; 4. It is difficult to meet personalized needs: Different enterprises have different needs for talents. The existing recommendation systems often lack in-depth understanding and analysis of job intentions and individual intentions of talents, and it is difficult to meet the personalized needs of enterprises. Therefore, a method for recommending scarce talents that can meet the needs of enterprises is needed. Summary of the invention

[0004] In view of the above-mentioned prior art, the present invention provides a method for recommending scarce talents for enterprises based on multi-party co-construction and sharing, mainly to solve the technical problems existing in the above-mentioned background technology.

[0005] To achieve the above object, the technical solution of the embodiment of the present invention is implemented as follows:

[0006] The first aspect of the present invention discloses a method for recommending scarce talents for enterprises based on multi-party co-construction and sharing, and the method comprises the following steps:

[0007] S1. Obtain talent information from multiple channels and build an international talent pool based on the talent information;

[0008] S2. Establish DIKWP models for different types of talents based on the talent information and talent type requirements in the international talent pool;

[0009] S3, obtaining detailed information of the job position, and constructing a job DIKWP model based on the detailed information of the job position;

[0010] S4. Calculate the cognitive deviation between individual talents and job intentions based on the job DIKWP model and different types of individual talent DIKWP models to obtain the first initial recommendation result;

[0011] S5. According to the constraints of job-seeking needs, weights are assigned to the first initial recommendation results, and they are sorted based on the assigned results to obtain the final talent recommendation results.

[0012] Optionally, talent information is obtained from multiple channels, specifically including: obtaining talent information from internal channels and external channels, the external channels further include recruitment websites, social media, headhunting companies, campus recruitment, industry associations and other channels, the talent information includes basic information, educational background, work experience, work history, skill certificates, and project experience.

[0013] Optionally, the talent type demand includes business talent demand, management talent demand, and professional talent demand, and different types of individual DIKWP models of talents include an individual DIKWP model for business talents, an individual DIKWP model for management talents, and an individual DIKWP model for professional talents.

[0014] Optionally, the individual DIKWP model for business talents, the individual DIKWP model for management talents, the individual DIKWP model for professional talents, and the position DIKWP model all include a data model, an information model, a knowledge model, a value system model, and an intention model.

[0015] Optionally, establish individual DIKWP models for business talents, individual DIKWP models for management talents, and individual DIKWP models for professional talents, including:

[0016] S201, mapping the individual information of business talents / management talents / professional talents into the first type of resources;

[0017] S202, obtaining information on social media and online footprints of individual information of business talents / individual information of management talents / individual information of professional talents, and mapping the information on social media and online footprints as the first intention resource;

[0018] S203. Construct an individual DIKWP model for business talents, an individual DIKWP model for management talents, and an individual DIKWP model for professional talents based on the first type of resources and the first intention resources.

[0019] Optionally, obtain detailed information about the job position and build a job DIKWP model based on the detailed information about the job position, including:

[0020] S301, mapping detailed information of company information, industry information, and job positions into second type resources;

[0021] S302, mapping the recruitment preference of the demand company into the second intended resource;

[0022] S303: construct a position DIKWP model according to the second type of resources and the second intended resources.

[0023] Optionally, the cognitive deviation between individual talents and job intentions is calculated based on the job DIKWP model and different types of individual talent DIKWP models to obtain a first initial recommendation result, which specifically includes:

[0024] According to the recruitment needs of the demand company, select one of the individual DIKWP model of business talents, the individual DIKWP model of management talents and the individual DIKWP model of professional talents to compare and match with the position DIKWP model, and by traversing the intention model nodes of the position DIKWP model, judge whether the talent individual corresponding to the individual DIKWP model of business talents / the individual DIKWP model of management talents / the individual DIKWP model of professional talents meets the intention content corresponding to the intention model node in the position DIKWP model;

[0025] When multiple talent individuals corresponding to the individual DIKWP model for business talent / the individual DIKWP model for management talent / the individual DIKWP model for professional talent meet the job intention corresponding to the intention model node in the job DIKWP model, the multiple talent individuals corresponding to the individual DIKWP model for business talent / the individual DIKWP model for management talent / the individual DIKWP model for professional talent will traverse the value system model nodes in the job DIKWP model, quantify the value of the talent individuals in the value system model in the job DIKWP model, and output the quantitative score of each talent individual relative to the job. The quantitative scores of the multiple talent individuals will be used as the first initial recommendation results.

[0026] Optionally, the first initial recommendation result is weighted according to the constraints of job search needs, specifically including setting whether the talent individual has job search needs as the constraints of job search needs; if the talent individual has job search needs, the first weight is assigned to the talent individual; if the talent individual does not have job search needs, the second weight is assigned to the talent individual.

[0027] Optionally, a total talent score is calculated according to the quantitative scores and weights of the individual talents, and multiple total scores are sorted. Based on the sorting results, the top n individual talents are selected as the final talent recommendation results.

[0028] The second aspect of the present invention discloses a talent recommendation system, which is used to implement the talent recommendation method applied to the talent recommendation system, and the talent recommendation system includes:

[0029] A talent pool building module, configured to obtain talent information from multiple channels and build an international talent pool based on the talent information;

[0030] A job information building module is configured to build a job DIKWP model based on detailed information of the job;

[0031] The talent information building module is configured to build different types of talent individual DIKWP models based on the talent information in the international talent pool and talent type requirements;

[0032] The recommendation module is configured to calculate the cognitive deviation between individual talents and job intentions based on the job DIKWP model and the DIKWP models of different types of individual talents, obtain a first initial recommendation result, and assign weights to the first initial recommendation results according to the constraints of job search needs, and sort based on the assigned results to obtain the final talent recommendation results.

[0033] The beneficial effects of the present invention are as follows: by acquiring talent information from multiple channels and building an international talent pool, the systematic integration of talent information is achieved, and the integrity and reliability of information are improved. By establishing different types of individual DIKWP models and job DIKWP models for talents, the matching degree between the comprehensive quality of talents and job requirements is comprehensively evaluated, and the accuracy of talent recommendation is significantly improved. In addition, the present invention obtains international talent information through multiple channels, expands the coverage of talent resources, and provides effective support in finding high-end talents with special skills and backgrounds. The recommended talents obtained are not only talents who have submitted resumes, but also talents who have been employed in other places but meet the requirements of the demander, which expands the scope of talent recommendation, and meets the diversified needs of different companies through in-depth analysis of job intentions and individual talent intentions. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 A flowchart of a method for recommending scarce talents for enterprises based on multi-party co-construction and sharing in an embodiment of the present application;

[0035] Figure 2 A schematic diagram of a process for establishing DIKWP models for different types of talent individuals in an embodiment of the present application;

[0036] Figure 3 It is a flowchart of constructing a position DIKWP model in an embodiment of the present application. DETAILED DESCRIPTION

[0037] The technical solution of the present invention is further elaborated in detail below in conjunction with the drawings and specific embodiments of the specification. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention. In the following description, the expression "some embodiments" is related to a subset of all possible embodiments, but it should be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict.

[0038] In the following description, a large number of specific details are provided to provide a more thorough understanding of the present invention. However, it is apparent to those skilled in the art that the present invention can be implemented without one or more of these details. In other examples, in order to avoid confusion with the present invention, some technical features well known in the art are not described.

[0039] It should be understood that the present invention can be implemented in different forms and should not be interpreted as being limited to the embodiments proposed herein. On the contrary, providing these embodiments will make the disclosure thorough and complete, and the scope of the present invention will be fully conveyed to those skilled in the art. And the purpose of the terms used herein is only to describe specific embodiments and is not intended to be a limitation of the present invention. When used herein, the singular forms of "one", "one" and "said / the" are also intended to include plural forms, unless the context clearly indicates another way. It should also be understood that the terms "compose" and / or "include" when used in this specification determine the presence of the features, integers, steps, operations, elements and / or parts, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, parts and / or groups. When used herein, the term "and / or" includes any and all combinations of the relevant listed items.

[0040] It should also 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. The terms "vertical", "horizontal", "inside", "outside", "left", "right" and similar expressions used herein are for illustrative purposes only and are not intended to be the only implementation method.

[0041] In order to fully understand the present invention, a detailed structure will be proposed in the following description to illustrate the technical solution proposed by the present invention. The optional embodiments of the present invention are described in detail as follows, but in addition to these detailed descriptions, the present invention may also have other implementations.

[0042] Please refer to the attached Figures 1 to 3 In a first aspect, the present invention discloses a method for recommending scarce talents for enterprises based on multi-party co-construction and sharing, and the method comprises the following steps:

[0043] S1. Obtain talent information from multiple channels and build an international talent pool based on the talent information;

[0044] S2. Establish DIKWP models for different types of talents based on the talent information and talent type requirements in the international talent pool;

[0045] S3, obtaining detailed information of the job position, and constructing a job DIKWP model based on the detailed information of the job position;

[0046] S4. Calculate the cognitive deviation between individual talents and job intentions based on the job DIKWP model and different types of individual talent DIKWP models to obtain the first initial recommendation result;

[0047] S5. According to the constraints of job-seeking needs, weights are assigned to the first initial recommendation results, and they are sorted based on the assigned results to obtain the final talent recommendation results.

[0048] In an optional implementation, talent information is obtained from multiple channels, specifically including: obtaining talent information from internal channels and external channels, wherein internal channels refer to talents generated or recommended within the company, which come from: 1. Recommendation of suitable talents by existing employees; 2. Discovery and cultivation of internal talents in competition activities conducted within the company; 3. Identification of high-potential employees through performance evaluation. The external channels further include recruitment websites, social media, headhunting companies, campus recruitment, industry associations and other channels, such as cooperating with recruitment websites to obtain the talent pool of recruitment websites, or cooperating with headhunting companies to obtain the high-end talent pool of headhunting companies, etc.

[0049] In an optional implementation, the talent information includes basic information, education background, work experience, work experience, skill certificates, and project experience. For example, personal information includes name: candidate's full name; gender: candidate's gender; age: candidate's age; contact information: phone number, email address, etc.; place of residence: candidate's city or region of residence. Education background includes highest degree: candidate's highest degree, school graduated, major, and year of graduation; work experience includes companies where you have worked, positions in the company, start and end time of working in the company, and main work content and responsibilities; project experience includes project names, roles and responsibilities in the project, and main achievements and contributions of the project, etc.

[0050] The present application is mainly aimed at the recommendation demand for international talents. Therefore, in an optional implementation, according to the talent needs of the enterprise, the talent type needs are divided into business-type international talent needs, management-type international talent needs, and professional-type international talent needs. Similarly, based on the talent needs, talents are divided into individual business talents, individual management talents, and individual professional talents. A corresponding individual business talent DIKWP model is constructed based on each individual business talent, a corresponding individual management talent DIKWP model is constructed based on each individual management talent, and a corresponding individual professional talent DIKWP model is constructed based on each individual professional talent.

[0051] Among them, the individual DIKWP model of business talents, the individual DIKWP model of management talents, the individual DIKWP model of professional talents, and the position DIKWP model all include data models, information models, knowledge models, value system models and intention models.

[0052] The data resources are discrete objects without binding intentions collected by directly observing a segment of existing semantics. Data resources are divided into numerical data, probabilistic data, logical data, and range data according to different attributes and structures. Numerical data is a specific numerical value obtained by observation, measurement, or simple calculation, including Arabic numerals, time, date, or numerical data associated with character data. Probabilistic data represents an inference or prediction of the development trend of other things based on personal cognition, and is an uncertain description. Logical data uses (yes) to represent data resources, which can filter and classify things and use digital codes to represent each category. Range data is a data type used to describe a value of a certain data type. It can express multiple data of a single data object. The higher the overlap of range data, the more similar it is. Range data is divided into bounded ranges and unbounded ranges according to whether there are boundaries.

[0053] The information resource is formed by data directly or indirectly associated with one or more intentions and is time-sensitive. Information can be partial order information, usage information and change information. Partial order information is the comparison of data objects of the same type or different types based on the comparison intention at the same standard level under the premise of the same attributes. Usage information is to analyze the functional attributes of data based on the usage intention to achieve the ultimate goal. Change information is a description of the process of modifying the selected object and causing changes.

[0054] The knowledge resources are structured and formalized category reasoning of data resources and / or information resources or empirical rules derived based on probability statistics.

[0055] In addition, the type resources can be converted through modal operations to obtain new type resources. The modal operations include homomodal operations and cross-modal operations. Homomodal operations are to obtain new type resources by operating on type resources of the same modality. Cross-modal operations are to obtain new type resources by operating on type resources of different modalities. For example, new information resources can be obtained by performing cross-modal operations on data resources and information resources.

[0056] The value system model is used to reflect the user's value orientation in various aspects, that is, the value of different things to the user; the intention model is used to reflect the user's intention, that is, what the user wants to do and what he wants to get. Specifically in this application, for example, the intention model in the job DIKWP model is used to reflect the demander's ultimate demand for the recruitment position, that is, what the demander wants to do and what he wants to get. The intention model in the individual DIKWP model of management talents is used to reflect the ultimate needs of the talent, such as what the talent wants to get, career ideals and expectations, etc.

[0057] In an optional implementation, an individual DIKWP model for business talents, an individual DIKWP model for management talents, and an individual DIKWP model for professional talents are established, specifically including:

[0058] S201, mapping the individual information of business talents / management talents / professional talents into the first type of resources;

[0059] S202, obtaining information on social media and online footprints of individual information of business talents / individual information of management talents / individual information of professional talents, and mapping the information on social media and online footprints as the first intention resource;

[0060] S203. Construct an individual DIKWP model for business talents, an individual DIKWP model for management talents, and an individual DIKWP model for professional talents based on the first type of resources and the first intention resources.

[0061] For example, the individual information of a business talent A, that is, the talent information mentioned above, is taken as the first type of resource, and then the information on social media and online footprints of business talent A is obtained. For foreign talents, the information on their foreign social media and online footprints can provide more additional perspectives on the career goals, personal characteristics, professional abilities, etc. of the talent A, and can better understand the personal intentions of the talent A. Finally, a DIKWP model of the individual business talent A is constructed based on the first type of resources and the first intention resources.

[0062] Furthermore, the following are the types of information that can be obtained through social media and online footprints, such as obtaining personal data including professional title, current position, work experience, educational background, skill certificates, etc. from the LinkedIn platform: obtaining detailed work experience and job descriptions; listed professional skills and certifications obtained; letters of recommendation and skill endorsements from colleagues and clients; published articles, shared content and participated in discussions; groups followed and joined: industry leaders followed, professional groups joined, for example, obtaining professional title, personal profile, location and other information from the Twitter (now "X") platform; obtaining the content of posted tweets, which can reflect the candidate's views and interests; obtaining interaction records, such as replies, reposts, likes, etc.; obtaining a list of followed users and fans to understand their social network.

[0063] For professional talent B, you can also obtain the code repository created and contributed by the user from the GitHub platform to evaluate his programming ability and project experience, obtain the record of contribution to open source projects, understand his teamwork and project management ability; obtain the list of users and fans he follows, and understand his influence in the developer community. Or you can obtain the questions and answers posted on the Quora platform to evaluate his knowledge level and expression ability; obtain the list of users and fans he follows, and understand his influence in the knowledge community. It is understandable that this application only lists the applications of some platforms, and it is not a restriction on the data collection of the platform.

[0064] In an optional implementation, detailed information of the job position is obtained, and a job DIKWP model is constructed according to the detailed information of the job position, specifically including:

[0065] S301, mapping detailed information of company information, industry information, and job positions into second type resources, wherein company information refers to all information of the company, industry information refers to basic information of the industry, and job position information includes at least job responsibilities, skill requirements, work experience, educational background, and other requirements;

[0066] S302, mapping the recruitment preferences of the demanding company to the second intention resource. The recruitment preferences may be age requirements for talents, MBTI personality requirements for talents, etc.;

[0067] S303: construct a position DIKWP model according to the second type of resources and the second intended resources.

[0068] In an optional implementation, based on the job DIKWP model and different types of individual talent DIKWP models, the cognitive deviation between individual talents and job intentions is calculated to obtain a first initial recommendation result, which specifically includes:

[0069] According to the recruitment needs of the demand company, select one of the individual DIKWP model of business talents, the individual DIKWP model of management talents and the individual DIKWP model of professional talents to compare and match with the position DIKWP model, and by traversing the intention model nodes of the position DIKWP model, judge whether the talent individual corresponding to the individual DIKWP model of business talents / the individual DIKWP model of management talents / the individual DIKWP model of professional talents meets the intention content corresponding to the intention model node in the position DIKWP model;

[0070] When multiple talent individuals corresponding to the individual DIKWP model for business talent / the individual DIKWP model for management talent / the individual DIKWP model for professional talent meet the job intention corresponding to the intention model node in the job DIKWP model, the multiple talent individuals corresponding to the individual DIKWP model for business talent / the individual DIKWP model for management talent / the individual DIKWP model for professional talent will traverse the value system model nodes in the job DIKWP model, quantify the value of the talent individuals in the value system model in the job DIKWP model, and output the quantitative score of each talent individual relative to the job. The quantitative scores of the multiple talent individuals will be used as the first initial recommendation results.

[0071] In an optional implementation, the first initial recommendation result is weighted according to the constraints of job search needs, specifically including setting whether the talent individual has job search needs as the constraints of job search needs; if the talent individual has job search needs, the first weight is assigned to the talent individual; if the talent individual does not have job search needs, the second weight is assigned to the talent individual, wherein the second weight is lower than the first weight.

[0072] Furthermore, the total talent score is calculated according to the quantitative scores and weights of the individual talents, and the multiple total scores are sorted. Based on the sorting results, the top n individual talents are selected as the final talent recommendation results.

[0073] For example, the first initial recommendation result for business talents includes 5 talents, and they are sorted according to the quantitative scores. By performing constraint analysis on the 5 talents, it can be known that 3 of them have job-seeking needs, and 2 talents do not have job-seeking needs. The total talent score is recalculated based on the quantitative scores and the first and second weights. The total talent score = quantitative score * first weight / second weight. The total talent score is re-sorted based on the total talent score obtained for each talent, and the final talent recommendation result is obtained based on the sorting results.

[0074] If the talent with a high total talent score has a job-seeking need, an interview request will be sent to the talent. If the talent with a high total talent score does not have a job-seeking need, communication can be conducted through channels such as headhunting companies.

[0075] The second aspect of the present invention discloses a talent recommendation system, which is used to implement the talent recommendation method applied to the talent recommendation system, and the talent recommendation system includes:

[0076] A talent pool building module, configured to obtain talent information from multiple channels and build an international talent pool based on the talent information;

[0077] A job information building module is configured to build a job DIKWP model based on detailed information of the job;

[0078] The talent information building module is configured to build different types of talent individual DIKWP models based on the talent information in the international talent pool and talent type requirements;

[0079] The recommendation module is configured to calculate the cognitive deviation between individual talents and job intentions based on the job DIKWP model and the DIKWP models of different types of individual talents, obtain a first initial recommendation result, and assign weights to the first initial recommendation results according to the constraints of job search needs, and sort based on the assigned results to obtain the final talent recommendation results.

[0080] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. The protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for recommending scarce talents for enterprises based on multi-party co-construction and sharing, characterized in that: The method comprises the following steps: S1. Obtain talent information from multiple channels and build an international talent pool based on the talent information; S2. Establish DIKWP models for different types of talents based on the talent information and talent type requirements in the international talent pool; S3, obtaining detailed information of the job position, and constructing a job DIKWP model based on the detailed information of the job position; S4. Calculate the cognitive deviation between individual talents and job intentions based on the job DIKWP model and different types of individual talent DIKWP models to obtain the first initial recommendation result; S5. According to the constraints of job-seeking needs, weights are assigned to the first initial recommendation results, and they are sorted based on the assigned results to obtain the final talent recommendation results.

2. The method for recommending scarce talents for enterprises based on multi-party co-construction and sharing according to claim 1 is characterized in that: Obtain talent information from multiple channels, specifically including: obtaining talent information from internal channels and external channels. The external channels further include recruitment websites, social media, headhunting companies, campus recruitment, industry associations and other channels. The talent information includes basic information, educational background, work experience, work experience, skill certificates, and project experience.

3. The method for recommending scarce talents for enterprises based on multi-party co-construction and sharing according to claim 2 is characterized in that: The talent type demands include business talent demands, management talent demands, and professional talent demands, and different types of talent individual DIKWP models include business talent individual DIKWP model, management talent individual DIKWP model, and professional talent individual DIKWP model.

4. The method for recommending scarce talents for enterprises based on multi-party co-construction and sharing according to claim 3 is characterized in that: The individual DIKWP model for business talents, the individual DIKWP model for management talents, the individual DIKWP model for professional talents, and the position DIKWP model all include a data model, an information model, a knowledge model, a value system model, and an intention model.

5. The method for recommending scarce talents for enterprises based on multi-party co-construction and sharing according to claim 4 is characterized in that: Establish individual DIKWP models for business talents, management talents and professional talents, including: S201, mapping the individual information of business talents / management talents / professional talents into the first type of resources; S202, obtaining information on social media and online footprints of individual information of business talents / individual information of management talents / individual information of professional talents, and mapping the information on social media and online footprints as the first intention resource; S203. Construct an individual DIKWP model for business talents, an individual DIKWP model for management talents, and an individual DIKWP model for professional talents based on the first type of resources and the first intention resources.

6. The method for recommending scarce talents for enterprises based on multi-party co-construction and sharing according to claim 5 is characterized in that: Get detailed information about the job position and build a job DIKWP model based on the detailed information of the job position, including: S301, mapping detailed information of company information, industry information, and job positions into second type resources; S302, mapping the recruitment preference of the demand company into the second intended resource; S303: construct a position DIKWP model according to the second type of resources and the second intended resources.

7. The method for recommending scarce talents for enterprises based on multi-party co-construction and sharing according to claim 6 is characterized in that: Based on the job DIKWP model and different types of individual talent DIKWP models, the cognitive deviation between individual talent and job intention is calculated to obtain the first initial recommendation results, including: According to the recruitment needs of the demand company, select one of the individual DIKWP model of business talents, the individual DIKWP model of management talents and the individual DIKWP model of professional talents to compare and match with the position DIKWP model, and by traversing the intention model nodes of the position DIKWP model, judge whether the talent individual corresponding to the individual DIKWP model of business talents / the individual DIKWP model of management talents / the individual DIKWP model of professional talents meets the intention content corresponding to the intention model node in the position DIKWP model; When multiple talent individuals corresponding to the individual DIKWP model for business talent / the individual DIKWP model for management talent / the individual DIKWP model for professional talent meet the job intention corresponding to the intention model node in the job DIKWP model, the multiple talent individuals corresponding to the individual DIKWP model for business talent / the individual DIKWP model for management talent / the individual DIKWP model for professional talent will traverse the value system model nodes in the job DIKWP model, quantify the value of the talent individuals in the value system model in the job DIKWP model, and output the quantitative score of each talent individual relative to the job. The quantitative scores of the multiple talent individuals will be used as the first initial recommendation results.

8. The method for recommending scarce talents for enterprises based on multi-party co-construction and sharing according to claim 7 is characterized in that: According to the constraints of job search needs, the first initial recommendation results are weighted, specifically including setting whether the talent individual has job search needs as the constraints of job search needs; if the talent individual has job search needs, the first weight is assigned to the talent individual; if the talent individual does not have job search needs, the second weight is assigned to the talent individual.

9. The method for recommending scarce talents for enterprises based on multi-party co-construction and sharing according to claim 8 is characterized in that: According to the quantitative scores and weights of the individual talents, the total talent score is calculated, and the multiple total scores are sorted. Based on the sorting results, the top n individual talents are selected as the final talent recommendation results.

10. The method for recommending scarce talents for enterprises based on multi-party co-construction and sharing according to any one of claims 1 to 9, characterized in that: The talent recommendation method is applied to a talent recommendation system, and the talent recommendation system comprises: A talent pool building module, configured to obtain talent information from multiple channels and build an international talent pool based on the talent information; A job information building module is configured to build a job DIKWP model based on detailed information of the job; The talent information building module is configured to build different types of talent individual DIKWP models based on the talent information in the international talent pool and talent type requirements; The recommendation module is configured to calculate the cognitive deviation between individual talents and job intentions based on the job DIKWP model and the DIKWP models of different types of individual talents, obtain a first initial recommendation result, and assign weights to the first initial recommendation results according to the constraints of job search needs, and sort based on the assigned results to obtain the final talent recommendation results.

Images