Intelligent matching and recommendation method based on social network and relationship credibility analysis

Abstract

The present application discloses an intelligent matching and recommendation method based on social network and relationship credibility analysis, which relates to the field of artificial intelligence technology. The matching degree between talents and positions is calculated according to the attribute information of talents. When the matching degree exceeds the matching threshold, the talents are regarded as seed talents; a talent social circle is constructed, the relationship credibility of the explicit relationship of the talents is calculated, and the high-credibility relationship set of the talents is obtained from the explicit relationship whose relationship credibility is greater than the high-credibility threshold; the sum of the path confidences between the talents is calculated to obtain the comprehensive confidence, and the high-confidence relationship set of the talents is screened out; a social network of seed talents is constructed, and the direct neighbor nodes are judged as strong-relation talents with talents as the starting point; the second matching degree is calculated to obtain the employment status of the strong-relation talents, the comprehensive matching degree is calculated, and the strong-relation talents with the comprehensive matching degree greater than the recommendation threshold are added to the talent recommendation library, thereby realizing efficient talent matching and recommendation.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to an intelligent matching and recommendation method based on social network and relationship credibility analysis. Background Art

[0002] With the rapid development of big data and artificial intelligence, how to effectively use data to find and tap talents is a major challenge facing enterprises and the recruitment industry. The talent pool is an important information resource for organizations to manage and develop talents, and its construction and application are of great significance to human resource management.

[0003] Traditional talent pools are mainly based on structured data such as relational databases for storage and management. However, in the era of big data, massive, heterogeneous, and dynamically changing talent data poses new challenges to traditional methods. As a knowledge-oriented intelligent information organization method, knowledge graphs can better represent semantic associations in talent data and support complex analysis and intelligent applications. Therefore, building talent pools based on knowledge graphs has become a new research direction.

[0004] Existing methods of building talent pools mostly rely on active submission of talents. Enterprises are often restricted by limited talent pools and channels, and find it difficult to reach more potential high-quality talent resources. For many excellent talents who are not actively seeking jobs, it is difficult for enterprises to discover and attract them through conventional channels. Summary of the invention

[0005] The present application aims to solve at least one of the technical problems in the related art to a certain extent. To this end, one purpose of the present application is to propose an intelligent matching and recommendation method based on social network and relationship credibility analysis, so as to achieve efficient talent matching and recommendation.

[0006] One aspect of the present application provides an intelligent matching and recommendation method based on social network and relationship credibility analysis, including:

[0007] Step S100: Collect job demand information, obtain attribute information and employment status provided by each talent, and calculate the matching degree between talent a and position A based on the attribute information of talent a who submits a resume to position A. When the matching degree exceeds the matching threshold, talent a is regarded as a seed talent;

[0008] The specific method of obtaining the job requirement information and the attribute information and employment status provided by each talent, and calculating the matching degree between talent a and job A based on the attribute information of talent a who submits a resume to job A, and treating talent a as a seed talent when the matching degree exceeds the matching threshold is as follows:

[0009] Step S110: Acquire attribute information provided by the talent, the attribute information including: the talent's education experience and work experience;

[0010] Step S120: Obtaining the employment status provided by the talent;

[0011] Step S130: Obtain the initial talent set U = {U1, U2, ..., U N}, where N is the total number of talents in the initial talent set, U n is the nth talent in the initial talent set, n∈{1, 2, ..., N};

[0012] Step S140: Obtain the job requirement information of position A, and find the corresponding attribute information and employment status of talent a who submitted a resume to position A according to the attribute information and employment status provided by the talent. The attribute information and employment status of talent a constitute the attribute vector sx a , extract the job demand vector sx from the job demand information of job A A , calculate the matching degree between talent a and position A;

[0013] Step S150: Preset a matching threshold b. If the matching degree of talent a is greater than the matching threshold, talent a is regarded as seed talent a and added to the seed talent set.

[0014] Step S200: Based on the attribute information provided by the talent, the explicit relationship is obtained, the talent social circle is constructed, the relationship credibility of the explicit relationship of the talent a is calculated, and the high-credibility relationship set of the talent a is obtained from the explicit relationships whose relationship credibility is greater than the high-credibility threshold;

[0015] The specific method of obtaining the explicit relationships based on the attribute information provided by the talents, constructing the talent social circle, calculating the relationship credibility of the explicit relationships of the talent a, and obtaining the high-credibility relationship set of the talent a from the explicit relationships whose relationship credibility is greater than the high-credibility threshold is:

[0016] Step S210: For any talent U in the initial talent set n And TalentU n′ , n′∈{1, 2, ..., N}, according to the talent U n And TalentU n′ Provided attribute information, get its explicit relationship r(U n , U n′ );

[0017] According to the talent U n And TalentU n′ The specific method to obtain the explicit relationship of the provided attribute information is:

[0018] Step S211: According to the talent U n And TalentU n′The educational experience in the provided attribute information is n And TalentU n′ Graduated from the same school, the same major, and the graduation time difference is less than or equal to 4 years, then the talent U n And TalentU n′ The explicit relation r(U n , U n′ ) = classmates;

[0019] Step S212: According to the talent U n And TalentU n′ If the work experience in the provided attribute information is n And TalentU n′ All have worked in the same company, and the overlap of their tenure is more than 50%. n And TalentU n′ The explicit relation r(U n , U n′ ) = colleague;

[0020] Step S213: If talent U n And TalentU n′ If they are both colleagues and classmates, then their explicit relationship r(U n , U n′ ) = classmates + colleagues;

[0021] Step S214: If talent U n And TalentU n′ Neither colleagues nor classmates, then their explicit relationship r(U n , U n′ ) = non-classmate + non-colleague;

[0022] Step S220: For each pair of talents with an explicit relationship, the explicit relationship is expressed as t=(U n , r, U n′ ), build a talent social circle, and for talent a, calculate the relationship credibility of each explicit relationship;

[0023] Step S230: Preset a high credibility threshold, select explicit relationships of talent a whose credibility is greater than the high credibility threshold as high credibility relationships of talent a, and add the high credibility relationships and the corresponding talents to a high credibility relationship set;

[0024] Step S300: Find talent U in the talent social circle who has a high trust relationship with talent a b , calculate talent a and talent U b The sum of the path confidences of all relationship paths between them is used to obtain the comprehensive confidence of the high-confidence relationship. The high-confidence relationship set of talent a is screened out from the high-confidence relationship set according to the comprehensive confidence.

[0025] The talent U with a high-trust relationship with the talent a is found in the talent social circle b , calculate talent a and talent U b The sum of the path confidences of all relationship paths between them is used to obtain the comprehensive confidence of the high-confidence relationship. The specific method for selecting the high-confidence relationship set of talent a from the high-confidence relationship set according to the comprehensive confidence is as follows:

[0026] Step S310: For talent U in the high-trust relationship set of talent a b , use the depth-first search algorithm to find the number of people from a to U in the talent social circle b All relationship paths P(a, U b )=(p1,p2,...,p C ), the cth relationship path is expressed as: p c =(t1, t2, ..., t D ), where t1 = (a, r1, U1), t2 = (U1, r2, U2), …, t D =(U D-1 , r D , U b ), t D represents the Dth high-confidence relationship in the cth relationship path, U D-1 is the D-1th talent in the cth relationship path, r D Represents Connecting Talents U D-1 And TalentU b Explicit relationship of

[0027] Step S320: Calculate talent a and talent U b The path confidence of each relationship path between them;

[0028] The calculation formula of the path confidence is: Among them, len(p c ) represents the length of the cth relationship path, α is the path length attenuation factor, c(t d ) represents the relationship credibility of the dth high-credibility relationship, Πc(t d ) refers to the total product of the relationship credibility of all high-credibility relationships in the relationship path;

[0029] len(p c ) is equal to the number of high-confidence relationships in the relationship path D;

[0030] Step S330: According to the b All relationship paths P(a, U b ) path confidence, calculate a and U b The overall confidence between Where C is the total number of relationship paths;

[0031] Step S340: Preset implicit relationship confidence threshold λ ys , if talent a and talent U b The comprehensive confidence of the relationship path between ys , then select talent a and talent U b The relationship path with the highest confidence between the two paths is obtained by merging all the explicit relationships in the relationship path to generate the relationship between talent a and talent U. b The implicit relation r'(a, U b );

[0032] Step S350: Talent A and Talent U b , implicit relation r'(a, U b ) to form a high-confidence relationship, calculate the comprehensive confidence between talent a and all talents in the high-confidence relationship set, select talents that have a high-confidence relationship with talent a, and obtain a high-confidence relationship set;

[0033] Step S400: Taking the talents in the high-confidence relationship set as nodes and the explicit relationships as edges, the edge weights are calculated according to the relationship credibility and comprehensive confidence between the talents, and the social network of seed talents is constructed. Taking talent a as the starting point, it is determined whether each direct neighbor node of talent a is a strong relationship talent;

[0034] The method of taking the talents in the high-confidence relationship set as nodes and the explicit relationships as edges, calculating the edge weights according to the relationship credibility and comprehensive confidence between the talents, and constructing a social network of seed talents, and taking talent a as the starting point, judging whether each direct neighbor node of talent a is a strong-relation talent is as follows:

[0035] Step S410: constructing a social network of seed talents using all talents in the high confidence relationship set as nodes and explicit relationships between talent a and other talents in the high confidence relationship set as edges;

[0036] Step S420: For each edge e in the social network, the edge weight is calculated according to the relationship credibility and comprehensive confidence between the talents corresponding to the two nodes connecting the edge;

[0037] Step S430: Talent a is used as a seed talent. Talent a is used as a starting point to perform a breadth-first search on the social network to obtain all direct neighbor nodes of the seed talent.

[0038] Step S440: for each direct neighbor node v of the seed talent, according to the edge weight w(a, v) between the direct neighbor node v and the seed talent, determine whether the direct neighbor node is a strong relationship talent;

[0039] Step S450: Preset a strong relationship threshold μ. If w(a, v) is greater than the strong relationship threshold μ, the direct neighbor node is regarded as a strong relationship talent and added to the candidate talent set. Otherwise, the direct neighbor node is regarded as a weak relationship talent.

[0040] Step S460: performing deduplication processing on all strongly related talents in the candidate talent set to ensure that each strongly related talent appears only once in the candidate talent set;

[0041] Step S500: Calculate the second matching degree between the strong relationship talent and position A, obtain the employment status of the strong relationship talent, obtain the edge weight connected to the seed talent, calculate the comprehensive matching degree of the strong relationship talent, sort all the strong relationship talents according to the comprehensive matching degree, and add the strong relationship talents whose comprehensive matching degree is greater than the recommendation threshold into the talent recommendation database;

[0042] The specific method of calculating the second matching degree between the strong relationship talent and position A, obtaining the employment status of the strong relationship talent, obtaining the edge weight connected to the seed talent, calculating the comprehensive matching degree of the strong relationship talent, sorting all the strong relationship talents according to the comprehensive matching degree, and adding the strong relationship talents with a comprehensive matching degree greater than the recommendation threshold into the talent recommendation database is as follows:

[0043] Step S510: For the strong relationship talent q, obtain its attribute information and employment status to form the attribute vector sx of the strong relationship talent q q , obtain the edge weight w(a, q) between the strong relationship talent q and the seed talent a from the talent social network, and calculate the second matching degree between the strong relationship talent q and the position A;

[0044] Step S520: Calculate the comprehensive matching degree of the strong relationship talent by using the second matching degree between the strong relationship talent q and the position A, the employment status of the strong relationship talent q, and the edge weight connecting the strong relationship talent q and the seed talent;

[0045] Step S530: sort all the strong relationship talents in descending order according to the corresponding comprehensive matching degrees, set a recommendation threshold Y, and add H strong relationship talents whose comprehensive matching degrees are greater than the recommendation threshold to the talent recommendation database.

[0046] One aspect of the present application provides an intelligent matching and recommendation system based on social network and relationship credibility analysis, including:

[0047] The data collection module is used to collect job demand information, obtain the attribute information and employment status provided by each talent, and calculate the matching degree between talent a and position A based on the attribute information of talent a who submits a resume to position A. When the matching degree exceeds the matching threshold, talent a is regarded as a seed talent;

[0048] The credibility calculation module is used to obtain the explicit relationships of talent a based on the attribute information provided by the talent, build the talent social circle, calculate the relationship credibility of the explicit relationships of talent a, and obtain the high-credibility relationship set of talent a from the explicit relationships whose relationship credibility is greater than the high-credibility threshold;

[0049] The confidence calculation module is used to find talent U in the talent social circle that has a high-confidence relationship with talent a. b , calculate talent a and talent U b The sum of the path confidences of all relationship paths between them is used to obtain the comprehensive confidence of the high-confidence relationship. The high-confidence relationship set of talent a is screened out from the high-confidence relationship set according to the comprehensive confidence.

[0050] The network construction module is used to take the talents in the high-confidence relationship set as nodes and the explicit relationships as edges, calculate the edge weights according to the relationship credibility and comprehensive confidence between talents, build a social network of seed talents, and take talent a as the starting point to determine whether each direct neighbor node of talent a is a strong relationship talent;

[0051] The talent screening module is used to calculate the second matching degree between the strong relationship talent and position A, obtain the employment status of the strong relationship talent, obtain the edge weight connected to the seed talent, calculate the comprehensive matching degree of the strong relationship talent, sort all the strong relationship talents according to the comprehensive matching degree, and add the strong relationship talents whose comprehensive matching degree is greater than the recommendation threshold to the talent recommendation library.

[0052] One aspect of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in the intelligent matching and recommendation method based on social network and relationship credibility analysis are implemented.

[0053] One aspect of the present application provides a readable storage medium storing a computer program, wherein the computer program is suitable for being loaded by a processor to execute steps in an intelligent matching and recommendation method based on social network and relationship credibility analysis.

[0054] Compared with the prior art, the intelligent matching and recommendation method based on social network and relationship credibility analysis proposed in this application has the following advantages:

[0055] This application uses the matching degree between talents and positions to find talents who actively submit resumes and are highly matched with positions as seed talents. By using the high matching degree between talents who actively submit resumes and positions, seed talents can be determined more accurately and efficiently. Traditional methods usually select seed talents from passive candidates of enterprises, while this application achieves more efficient talent recruitment by actively matching seed talents and talents with strong relationships related to seed talents as candidates.

[0056] This application deeply analyzes the various connections between talents such as education and work, and introduces relationship credibility calculation, comprehensively considering the relationship type and talent similarity, so as to build a more comprehensive and reliable talent social circle.

[0057] This application uses depth-first search to find all possible relationship paths between talents, calculates the confidence of each path and the comprehensive confidence between talents, and comprehensively evaluates the strength of the relationship between two talents. Different from the traditional method that only considers direct relationships, this application can discover more potential indirect connections and is more in line with actual conditions.

[0058] This application builds a social network of seed talents, measures the strength of the relationship between the seed talents and other talents by the weight of the edge between them, and calculates the comprehensive matching degree of the selected strong-relationship talents by comprehensively considering their matching degree with the position, employment status and the strength of their relationship with the seed talents, and gives priority to recommending talents with high matching degree, thus achieving accurate targeted recruitment. Different from recommendations based solely on talent conditions or relationships, the matching degree calculation of this solution integrates factors of more dimensions, making the recommendation results more comprehensive and reliable. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 A method flow chart of the intelligent matching and recommendation method based on social network and relationship credibility analysis provided in this application;

[0060] Figure 2 A flow chart of the method for determining whether a direct neighbor node is a strong-relationship talent provided in this application;

[0061] Figure 3 Functional module diagram of the intelligent matching and recommendation system based on social network and relationship credibility analysis provided in this application;

[0062] Figure 4 A schematic diagram of the structure of an electronic device provided in this application;

[0063] Figure 5 It is a schematic diagram of the structure of a readable storage medium provided by this application. DETAILED DESCRIPTION

[0064] In order to better understand the present application, various aspects of the present application will be described in more detail with reference to the accompanying drawings. It should be understood that these detailed descriptions are only descriptions of exemplary embodiments of the present application and do not limit the scope of the present application in any way. Throughout the specification, the same reference numerals refer to the same elements. The expression "and / or" includes any and all combinations of one or more of the associated listed items.

[0065] In the accompanying drawings, the size, dimensions and shapes of the elements have been slightly adjusted for ease of illustration. The drawings are for illustration only and are not strictly drawn to scale. As used herein, the terms "substantially", "approximately" and similar terms are used as terms of approximation, not as terms of degree, and are intended to illustrate the inherent deviations in measurements or calculations that will be recognized by those of ordinary skill in the art. In addition, in this application, the order in which the steps are described does not necessarily represent the order in which these processes occur in actual operation, unless otherwise specified or can be derived from the context.

[0066] It should also be understood that expressions such as "including", "comprising", "having", "containing" and / or "comprising" are open rather than closed expressions in this specification, which indicate the presence of the stated features, elements and / or components, but do not exclude the presence of one or more other features, elements, components and / or combinations thereof. In addition, when expressions such as "at least one of..." appear after a list of listed features, they modify the entire list of features rather than just the individual elements in the list. In addition, when describing embodiments of the present application, "may" is used to mean "one or more embodiments of the present application". And, the term "exemplary" is intended to refer to an example or illustration.

[0067] Unless otherwise specified, all words (including engineering terms and scientific and technological terms) used in this article have the same meaning as those commonly understood by ordinary technicians in the field to which this application belongs. It should also be understood that, unless clearly stated in this application, words defined in common dictionaries should be interpreted as having the same meaning as their meaning in the context of the relevant technology, and should not be interpreted in an idealized or overly formal sense.

[0068] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0069] Example 1

[0070] like Figure 1 As shown, the intelligent matching and recommendation method based on social network and relationship credibility analysis provided by this application includes:

[0071] Step S100: Collect job demand information, obtain attribute information and employment status provided by each talent, and calculate the matching degree between talent a and position A based on the attribute information of talent a who submits a resume to position A. When the matching degree exceeds the matching threshold, talent a is regarded as a seed talent;

[0072] The specific method of obtaining the job requirement information and the attribute information and employment status provided by each talent, and calculating the matching degree between talent a and job A based on the attribute information of talent a who submits a resume to job A, and treating talent a as a seed talent when the matching degree exceeds the matching threshold is as follows:

[0073] Step S110: Acquire attribute information provided by the talent, the attribute information including: the talent's education experience and work experience;

[0074] Step S120: Obtaining the employment status provided by the talent;

[0075] The employment status includes: employed with no intention to change jobs, employed with intention to change jobs, and unemployed;

[0076] Step S130: Obtain the initial talent set U = {U1, U2, ..., U N}, where N is the total number of talents in the initial talent set, U n is the nth talent in the initial talent set, n∈{1, 2, ..., N};

[0077] Step S140: Obtain the job requirement information of position A, and find the corresponding attribute information and employment status of talent a who submitted a resume to position A according to the attribute information and employment status provided by the talent. The attribute information and employment status of talent a constitute the attribute vector sx a , extract the job demand vector sx from the job demand information of job A A , calculate the matching degree between talent a and position A;

[0078] The calculation formula of the matching degree is: Among them, ||·|| is the calculation symbol of the modulus;

[0079] Step S150: Preset a matching threshold b. If the matching degree of talent a is greater than the matching threshold, talent a is regarded as seed talent a and added to the seed talent set.

[0080] When an enterprise builds a talent pool, it calculates the match between positions and talents based on the attribute information and employment status of the talents who submitted their resumes, and preliminarily screens whether the talents who actively submitted their resumes meet the requirements of the position; talents who meet the requirements of the position are regarded as seed talents, and seed talents indicate that the talent is highly matched with the position; generally speaking, talents with similar educational or work experience as the seed talents can also be regarded as potential recommendations for the position; based on the above ideas, this application mines the social relationships of seed talents who have submitted their resumes, thereby establishing a talent recommendation pool that is highly matched with the position.

[0081] This step determines the seed talent by the matching degree between talent and position, making full use of the relevance of the talent who actively submits resumes. The quality of seed talent directly affects the accuracy of subsequent recommendations, and this method can provide a high-quality starting point for subsequent steps.

[0082] Step S200: Based on the attribute information provided by the talent, the explicit relationship is obtained, the talent social circle is constructed, the relationship credibility of the explicit relationship of the talent a is calculated, and the high-credibility relationship set of the talent a is obtained from the explicit relationships whose relationship credibility is greater than the high-credibility threshold;

[0083] The talent social circle is composed of all talents and their explicit relationships;

[0084] The specific method of obtaining the explicit relationships based on the attribute information provided by the talents, constructing the talent social circle, calculating the relationship credibility of the explicit relationships of the talent a, and obtaining the high-credibility relationship set of the talent a from the explicit relationships whose relationship credibility is greater than the high-credibility threshold is:

[0085] Step S210: For any talent U in the initial talent set n And TalentU n′ , n′∈{1, 2, ..., N}, according to the talent U n And TalentU n′ Provided attribute information, get its explicit relationship r(U n , U n′ );

[0086] According to the talent U n And TalentU n′ The specific method to obtain the explicit relationship of the provided attribute information is:

[0087] Step S211: According to the talent U n And TalentU n′ The educational experience in the provided attribute information is n And TalentU n′ Graduated from the same school, the same major, and the graduation time difference is less than or equal to 4 years, then the talent Un And TalentU n′ The explicit relation r(U n , U n′ ) = classmates;

[0088] Step S212: According to the talent U n And TalentU n′ If the work experience in the provided attribute information is n And TalentU n′ All have worked in the same company, and the overlap of their tenure is more than 50%. n And TalentU n′ The explicit relation r(U n , U n′ ) = colleague;

[0089] Step S213: If talent U n And TalentU n′ If they are both colleagues and classmates, then their explicit relationship r(U n , U n′ ) = classmates + colleagues;

[0090] Step S214: If talent U n And TalentU n′ Neither colleagues nor classmates, then their explicit relationship r(U n , U n′ ) = non-classmate + non-colleague;

[0091] Step S220: For each pair of talents with an explicit relationship, the explicit relationship is expressed as t=(U n , r, U n′ ), build a talent social circle, and for talent a, calculate the relationship credibility of each explicit relationship;

[0092] The calculation formula of the relationship credibility is: Among them, w r is the relationship type weight of the explicit relationship, a′ is the talent with an explicit relationship with talent a, sx a 、sx a′ are the attribute vectors of talent a and talent a′ respectively;

[0093] The relationship type weight of the explicit relationship is determined by the type of explicit relationship between talents; n And TalentU n′ For example, when the explicit relation r(U n , U n′ )=classmates, w r is equal to 0.6; when the explicit relationship r(U n , U n′)=colleagues, w r is equal to 0.6; when the explicit relationship r(U n , U n′ )=classmates+colleagues, w r is equal to 0.8; when the explicit relationship r(U n , U n′ )=non-classmate+non-colleague, w r is equal to 0;

[0094] Step S230: Preset a high credibility threshold, select explicit relationships of talent a whose credibility is greater than the high credibility threshold as high credibility relationships of talent a, and add the high credibility relationships and the corresponding talents to a high credibility relationship set;

[0095] The value of the high confidence threshold is set by those skilled in the art based on actual needs and experience;

[0096] Explicit relationships are obtained based on the attribute information directly provided by talents. They are the most obvious relationships between talents. By screening high-credibility relationships between talents based on explicit relationships, we can preliminarily judge talents related to seed talents based on the attribute information and employment status of the talents.

[0097] This step comprehensively considers various connections between talents, such as education and work. The calculation of relationship credibility also takes into account the similarity of relationship type and talent attributes, thus building a high-quality talent relationship network foundation.

[0098] Step S300: Find talent U in the talent social circle who has a high trust relationship with talent a b , calculate talent a and talent U b The sum of the path confidences of all relationship paths between them is used to obtain the comprehensive confidence of the high-confidence relationship. The high-confidence relationship set of talent a is screened out from the high-confidence relationship set according to the comprehensive confidence.

[0099] The talent U with a high-trust relationship with the talent a is found in the talent social circle b , calculate talent a and talent U b The sum of the path confidences of all relationship paths between them is used to obtain the comprehensive confidence of the high-confidence relationship. The specific method for selecting the high-confidence relationship set of talent a from the high-confidence relationship set according to the comprehensive confidence is as follows:

[0100] Step S310: For talent U in the high-trust relationship set of talent a b , use the depth-first search algorithm to find the number of people from a to U in the talent social circle b All relationship paths P(a, U b )=(p1,p2,...,p C), the cth relationship path is expressed as: p c =(t1, t2, ..., t D ), where t1 = (a, r1, U1), t2 = (U1, r2, U2), ..., t D =(U D-1 , r D , U b ), t D represents the Dth high-confidence relationship in the cth relationship path, U D-1 is the D-1th talent in the cth relationship path, r D Represents Connecting Talents U D-1 And TalentU b Explicit relationship of

[0101] Step S320: Calculate talent a and talent U b The path confidence of each relationship path between them;

[0102] The calculation formula of the path confidence is: Among them, 1en(p c ) represents the length of the cth relationship path, α is the path length attenuation factor, c(t d ) represents the relationship credibility of the dth high-credibility relationship, Πc(t d ) refers to the total product of the relationship credibility of all high-credibility relationships in the relationship path;

[0103] len(p c ) is equal to the number of high-confidence relationships in the relationship path D;

[0104] The path length attenuation factor is used to control the influence of the path length on the path confidence, and the value of the path length attenuation factor is set by those skilled in the art according to actual needs and experience;

[0105] Preferably, αα is equal to 0.5;

[0106] Step S330: According to the b All relationship paths P(a, U b ) path confidence, calculate a and U b The overall confidence between Where C is the total number of relationship paths;

[0107] Step S340: Preset implicit relationship confidence threshold λ ys , if talent a and talent U b The comprehensive confidence of the relationship path between ys , then select talent a and talent U bThe relationship path with the highest confidence between the two paths is obtained by merging all the explicit relationships in the relationship path to generate the relationship between talent a and talent U. b The implicit relation r'(a, U b );

[0108] The implicit relationship confidence threshold λ ys The value of is preset by those skilled in the art based on actual needs and experience;

[0109] Step S350: Talent A and Talent U b , implicit relation r'(a, U b ) to form a high-confidence relationship, calculate the comprehensive confidence between talent a and all talents in the high-confidence relationship set, select talents that have a high-confidence relationship with talent a, and obtain a high-confidence relationship set;

[0110] There are not only explicit relationships between talents, but also implicit relationships. For example, the explicit relationship between talent a and talent b is colleagues. However, since talent a and talent c are college classmates, and talent c and talent b are graduate school classmates, there is also an implicit relationship between talent a and talent b connected by talent c. Implicit relationships explore the social relationships between talents from a hidden level. By jointly exploring and analyzing implicit and explicit relationships, we can more comprehensively analyze the social relationship network of seed talents, thereby exploring talents with a higher degree of job matching in the relationship network of seed talents.

[0111] The calculation of this step takes into account the attenuation of path length, which is in line with the characteristics of relationship transmission strength. This method can comprehensively evaluate the relationship strength between two talents and lay the foundation for the subsequent mining of potential strong relationship talents.

[0112] Step S400: Taking the talents in the high-confidence relationship set as nodes and the explicit relationships as edges, the edge weights are calculated according to the relationship credibility and comprehensive confidence between the talents, and the social network of seed talents is constructed. Taking talent a as the starting point, it is determined whether each direct neighbor node of talent a is a strong relationship talent;

[0113] The direct neighbor node refers to the node directly adjacent to the seed talent;

[0114] like Figure 2 As shown, it is a flow chart of a method for judging whether a direct neighbor node is a strong-relation talent;

[0115] The method of taking the talents in the high-confidence relationship set as nodes and the explicit relationships as edges, calculating the edge weights according to the relationship credibility and comprehensive confidence between the talents, and constructing a social network of seed talents, and taking talent a as the starting point, judging whether each direct neighbor node of talent a is a strong-relation talent is as follows:

[0116] Step S410: constructing a social network of seed talents using all talents in the high confidence relationship set as nodes and explicit relationships between talent a and other talents in the high confidence relationship set as edges;

[0117] Step S420: For each edge e in the social network, the edge weight is calculated according to the relationship credibility and comprehensive confidence between the talents corresponding to the two nodes connecting the edge;

[0118] The edge weight calculation formula is: w(e) = β × d zh (a+U b′ )+(1-β)×c(t) a，b′ , where w(e) represents the relationship between node a and node U b′ The edge weight between zh (a+U b′ ) is node a and node U b′ The comprehensive confidence between a，b′ For nodes a and U b′ The relationship credibility between them, β is the balance factor, which is used to adjust the influence of relationship credibility and comprehensive confidence on edge weight;

[0119] The value of the balance factor is set by those skilled in the art according to actual needs;

[0120] Step S430: Talent a is used as a seed talent. Talent a is used as a starting point to perform a breadth-first search on the social network to obtain all direct neighbor nodes of the seed talent.

[0121] Step S440: for each direct neighbor node v of the seed talent, according to the edge weight w(a, v) between the direct neighbor node v and the seed talent, determine whether the direct neighbor node is a strong relationship talent;

[0122] Step S450: Preset a strong relationship threshold μ. If w(a, v) is greater than the strong relationship threshold μ, the direct neighbor node is regarded as a strong relationship talent and added to the candidate talent set. Otherwise, the direct neighbor node is regarded as a weak relationship talent.

[0123] Step S460: performing deduplication processing on all strongly related talents in the candidate talent set to ensure that each strongly related talent appears only once in the candidate talent set;

[0124] A social network for seed talents is constructed based on a set of high-confidence relationships. Talents are used as nodes and explicit relationships as edges. Edge weights are calculated based on the credibility and comprehensive confidence of the relationships between talents. The influence of explicit and implicit relationships on the weights of edges in the social network for seed talents is comprehensively considered. The constructed social network is more comprehensive and can better demonstrate the talent relationships that are highly relevant to seed talents.

[0125] This step can quickly focus on high-value talents and improve the efficiency of subsequent recommendations.

[0126] Step S500: Calculate the second matching degree between the strong relationship talent and position A, obtain the employment status of the strong relationship talent, obtain the edge weight connected to the seed talent, calculate the comprehensive matching degree of the strong relationship talent, sort all the strong relationship talents according to the comprehensive matching degree, and add the strong relationship talents whose comprehensive matching degree is greater than the recommendation threshold into the talent recommendation database;

[0127] The specific method of calculating the second matching degree between the strong relationship talent and position A, obtaining the employment status of the strong relationship talent, obtaining the edge weight connected to the seed talent, calculating the comprehensive matching degree of the strong relationship talent, sorting all the strong relationship talents according to the comprehensive matching degree, and adding the strong relationship talents with a comprehensive matching degree greater than the recommendation threshold into the talent recommendation database is as follows:

[0128] Step S510: For the strong relationship talent q, obtain its attribute information and employment status to form the attribute vector sx of the strong relationship talent q q , obtain the edge weight w(a, q) between the strong relationship talent q and the seed talent a from the talent social network, and calculate the second matching degree between the strong relationship talent q and the position A;

[0129] The calculation formula of the second matching degree is:

[0130] Step S520: Calculate the comprehensive matching degree of the strong relationship talent by using the second matching degree between the strong relationship talent q and the position A, the employment status of the strong relationship talent q, and the edge weight connecting the strong relationship talent q and the seed talent;

[0131] The calculation formula of the comprehensive matching degree is: Among them, q state is the employment status score of the strong relationship talent q, δ1, δ2, and δ3 are the weight factors of the second matching degree, employment status, and edge weight respectively;

[0132] The employment status score is set according to the employment status. When the employment status is employed and has no intention to change jobs, the employment status score is 0.1; when the employment status is employed and has the intention to change jobs, the employment status score is 0.5; when the employment status is unemployed, the employment status score is 1;

[0133] The weight factors of the second matching degree, employment status and edge weight are set by those skilled in the art according to actual needs and experiments;

[0134] Step S530: sort all the strong relationship talents in descending order according to the corresponding comprehensive matching degree, set the recommendation threshold Y, and add H strong relationship talents whose comprehensive matching degree is greater than the recommendation threshold to the talent recommendation database;

[0135] The recommended threshold value Y is set by those skilled in the art according to actual needs and experiments;

[0136] By comprehensively considering the employment status of strong-relationship talents and the weight of the edge connected to the seed talent, the comprehensive matching degree between the strong-relationship talents and the positions is calculated. This step comprehensively considers the second matching degree of talents to positions, employment status and the strength of the relationship with the seed talent. The weight of each factor can be adjusted, which has strong flexibility. Sorting and threshold screening can flexibly control the quality and quantity of recommended talents, which is convenient for balancing the cost and benefit of recommendations.

[0137] Example 2

[0138] like Figure 3 As shown, the intelligent matching and recommendation system based on social network and relationship credibility analysis provided by this application includes:

[0139] The data collection module is used to collect job demand information, obtain the attribute information and employment status provided by each talent, and calculate the matching degree between talent a and position A based on the attribute information of talent a who submits a resume to position A. When the matching degree exceeds the matching threshold, talent a is regarded as a seed talent;

[0140] The credibility calculation module is used to obtain the explicit relationships of talent a based on the attribute information provided by the talent, build the talent social circle, calculate the relationship credibility of the explicit relationships of talent a, and obtain the high-credibility relationship set of talent a from the explicit relationships whose relationship credibility is greater than the high-credibility threshold;

[0141] The confidence calculation module is used to find talent U in the talent social circle that has a high-confidence relationship with talent a. b , calculate talent a and talent U b The sum of the path confidences of all relationship paths between them is used to obtain the comprehensive confidence of the high-confidence relationship. The high-confidence relationship set of talent a is screened out from the high-confidence relationship set according to the comprehensive confidence.

[0142] The network construction module is used to take the talents in the high-confidence relationship set as nodes and the explicit relationships as edges, calculate the edge weights according to the relationship credibility and comprehensive confidence between talents, build a social network of seed talents, and take talent a as the starting point to determine whether each direct neighbor node of talent a is a strong relationship talent;

[0143] The talent screening module is used to calculate the second matching degree between the strong relationship talent and position A, obtain the employment status of the strong relationship talent, obtain the edge weight connected to the seed talent, calculate the comprehensive matching degree of the strong relationship talent, sort all the strong relationship talents according to the comprehensive matching degree, and add the strong relationship talents whose comprehensive matching degree is greater than the recommendation threshold to the talent recommendation library.

[0144] Example 3

[0145] Figure 4 Schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Figure 4 As shown, according to another aspect of the present application, an electronic device is also provided. The electronic device may include one or more processors and one or more memories. The memories store computer readable codes, and when the computer readable codes are executed by one or more processors, the intelligent matching and recommendation method based on social network and relationship credibility analysis as described above can be executed.

[0146] The method or system according to the embodiment of the present application can also be Figure 4 The electronic device architecture shown in FIG. Figure 4 As shown, the electronic device may include a bus, one or more CPUs, a read-only memory (ROM), a random access memory (RAM), a communication port connected to a network, an input / output component, a hard disk, etc. The storage device in the electronic device, such as a ROM or a hard disk, can store the intelligent matching and recommendation method based on social network and relationship credibility analysis provided in this application. The intelligent matching and recommendation method based on social network and relationship credibility analysis may, for example, include: collecting job demand information, obtaining attribute information and employment status provided by each talent, and calculating the matching degree between talent a and position A based on the attribute information of talent a who submits a resume to position A. When the matching degree exceeds the matching threshold, talent a is regarded as a seed talent; based on the attribute information provided by the talent, its explicit relationship is obtained, a talent social circle is constructed, and the relationship credibility of the explicit relationship of talent a is calculated. The high-credibility relationship set of talent a is obtained from the explicit relationship whose relationship credibility is greater than the high-credibility threshold; and talent U with a high-credibility relationship with talent a is found in the talent social circle. b , calculate talent a and talent U bThe sum of the path confidences of all relationship paths between them is used to obtain the comprehensive confidence of the high-confidence relationship, and the high-confidence relationship set of talent a is screened out from the high-confidence relationship set according to the comprehensive confidence; the talents in the high-confidence relationship set are used as nodes and the explicit relationships are used as edges, and the edge weights are calculated according to the relationship credibility and comprehensive confidence between the talents to build a social network for seed talents, and talent a is used as the starting point to determine whether each direct neighbor node of talent a is a strong relationship talent; the second matching degree between the strong relationship talent and position A is calculated, the employment status of the strong relationship talent is obtained, the edge weight connected to the seed talent is obtained, and the comprehensive matching degree of the strong relationship talent is calculated, all the strong relationship talents are sorted according to the comprehensive matching degree, and the strong relationship talents with a comprehensive matching degree greater than the recommendation threshold are added to the talent recommendation library. Furthermore, the electronic device may also include a user interface. Of course, Figure 4 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 4 One or more components of an electronic device are shown.

[0147] Example 4

[0148] Figure 5 Schematic diagram of a readable storage medium structure provided by an embodiment of the present application. Figure 5 As shown, it is a readable storage medium according to an embodiment of the present application. Computer-readable instructions are stored on the computer-readable storage medium. When the computer-readable instructions are executed by the processor, the intelligent matching and recommendation method based on social network and relationship credibility analysis according to the embodiment of the present application described with reference to the above figures can be executed. The storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0149] In addition, according to the implementation mode of the present application, the process described in the above reference flowchart can be implemented as a computer software program. For example, the present application provides a non-temporary machine-readable storage medium, which stores machine-readable instructions, and the machine-readable instructions can be executed by a processor to execute instructions corresponding to the method steps provided in the present application, such as: collecting job demand information, obtaining attribute information and employment status provided by each talent, and calculating the matching degree between talent a and position A based on the attribute information of talent a who submits a resume to position A. When the matching degree exceeds the matching threshold, talent a is regarded as a seed talent; based on the attribute information provided by the talent, its explicit relationship is obtained, and a talent social circle is constructed, and the relationship credibility of the explicit relationship of talent a is calculated, and the high-credibility relationship set of talent a is obtained from the explicit relationship whose relationship credibility is greater than the high-credibility threshold; in the talent social circle, talent U with a high-credibility relationship with talent a is found; b , calculate talent a and talent U b The sum of the path confidences of all relationship paths between them is used to obtain the comprehensive confidence of the high-confidence relationship, and the high-confidence relationship set of talent a is screened out from the high-confidence relationship set according to the comprehensive confidence; the talents in the high-confidence relationship set are used as nodes and the explicit relationships are used as edges, and the edge weights are calculated according to the relationship credibility and comprehensive confidence between the talents, and the social network of seed talents is constructed, and talent a is used as the starting point to determine whether each direct neighbor node of talent a is a strong relationship talent; the second matching degree between the strong relationship talent and position A is calculated, the employment status of the strong relationship talent is obtained, the edge weight connected to the seed talent is obtained, and the comprehensive matching degree of the strong relationship talent is calculated, and all the strong relationship talents are sorted according to the comprehensive matching degree, and the strong relationship talents with a comprehensive matching degree greater than the recommendation threshold are added to the talent recommendation library. When the computer program is executed by the central processing unit (CPU), the above functions defined in the method of this application are executed.

[0150] The methods, apparatuses, and devices of the present application may be implemented in many ways. For example, the methods, apparatuses, and devices of the present application may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present application are not limited to the order specifically described above unless otherwise specified. In addition, in some embodiments, the present application may also be implemented as programs recorded in a recording medium, which include machine-readable instructions for implementing the method according to the present application. Therefore, the present application also covers recording media storing programs for executing the method according to the present application.

[0151] In addition, the parts of the above-mentioned technical solutions provided in the embodiments of the present application that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive redundancy.

[0152] The specific implementation modes as described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation mode of the present invention and is not intended to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent matching and recommendation method based on social network and relationship credibility analysis, characterized in that: include: Collect job demand information, obtain the attribute information and employment status provided by each talent, and calculate the matching degree between talent a and position A based on the attribute information of talent a who submitted a resume to position A. When the matching degree exceeds the matching threshold, talent a is regarded as a seed talent; Based on the attribute information provided by the talent, its explicit relationships are obtained, the talent social circle is constructed, the relationship credibility of the explicit relationships of talent a is calculated, and the high-credibility relationship set of talent a is obtained from the explicit relationships whose relationship credibility is greater than the high-credibility threshold; Find talent U who has a high-trust relationship with talent a in the talent social circle b , calculate talent a and talent U b The sum of the path confidences of all relationship paths between them is used to obtain the comprehensive confidence of the high-confidence relationship. The high-confidence relationship set of talent a is screened out from the high-confidence relationship set according to the comprehensive confidence. Taking the talents in the high-confidence relationship set as nodes and the explicit relationships as edges, the edge weights are calculated according to the relationship credibility and comprehensive confidence between talents, and the social network of seed talents is constructed. Starting from talent a, it is determined whether each direct neighbor node of talent a is a strong relationship talent; Calculate the second matching degree between the strong relationship talent and position A, obtain the employment status of the strong relationship talent, obtain the edge weight connected to the seed talent, calculate the comprehensive matching degree of the strong relationship talent, sort all the strong relationship talents according to the comprehensive matching degree, and add the strong relationship talents whose comprehensive matching degree is greater than the recommendation threshold to the talent recommendation pool.

2. The intelligent matching and recommendation method based on social network and relationship credibility analysis as claimed in claim 1, characterized in that: The specific method of obtaining the job requirement information and the attribute information and employment status provided by each talent, and calculating the matching degree between talent a and job A based on the attribute information of talent a who submits a resume to job A, and treating talent a as a seed talent when the matching degree exceeds the matching threshold is as follows: Acquire attribute information provided by the talent, the attribute information including: the talent's education experience and work experience; Obtain the employment status provided by talents; The initial talent set U = {U1, U2, ..., U N }, where N is the total number of talents in the initial talent set, U n is the nth talent in the initial talent set, n∈{1, 2, ..., N}; Obtain the job requirement information of position A, and find the corresponding attribute information and employment status of talent a who submitted a resume to position A according to the attribute information and employment status provided by the talent. The attribute information and employment status of talent a constitute the attribute vector sx a , extract the job demand vector sx from the job demand information of job A A , calculate the matching degree between talent a and position A; A matching threshold b is preset. If the matching degree of talent a is greater than the matching threshold, talent a is regarded as seed talent a and added to the seed talent set.

3. The intelligent matching and recommendation method based on social network and relationship credibility analysis as claimed in claim 2, characterized in that: The specific method of obtaining the explicit relationships based on the attribute information provided by the talents, constructing the talent social circle, calculating the relationship credibility of the explicit relationships of the talent a, and obtaining the high-credibility relationship set of the talent a from the explicit relationships whose relationship credibility is greater than the high-credibility threshold is: For any talent U in the initial talent set n And TalentU n′ , n′∈{1, 2, ..., N}, according to the talent U n And TalentU n ′ provides the attribute information, and obtains its explicit relationship r(U n , U n ~); For each pair of talents with an explicit relationship, the explicit relationship between them is expressed as t = (U n , r, U n′ ), build a talent social circle, and for talent a, calculate the relationship credibility of each explicit relationship; A high credibility threshold is preset, and explicit relationships of talent a whose relationship credibility is greater than the high credibility threshold are screened out as high credibility relationships of talent a, and the high credibility relationships and corresponding talents are added to a high credibility relationship set.

4. The intelligent matching and recommendation method based on social network and relationship credibility analysis as claimed in claim 3, characterized in that: The analytical talent U n And TalentU n ′’s attribute information, and the specific method to obtain its explicit relationship is: According to TalentU n And TalentU n ′The educational experience in the attribute information provided by talent U n And TalentU n ′ Graduated from the same school, the same major, and the graduation time difference is less than or equal to 4 years, then talent U n And TalentU n The explicit relation r(U n , U n ′) = classmates; According to TalentU n And TalentU n ~The work experience in the attribute information provided by the talent U n And TalentU n ′ have worked in the same company, and the overlap of their tenure time exceeds 50%, then talent U n And TalentU n '''s explicit relation r(U n , U n ~) = colleague; If talent U n And TalentU n ′ is both a colleague and a classmate, then their explicit relationship r(U n , U n ~) = classmates + colleagues; If talent U n And TalentU n ′ is neither a colleague nor a classmate, then the explicit relationship r(U n , U n ~) = non-classmate + non-colleague.

5. The intelligent matching and recommendation method based on social network and relationship credibility analysis as claimed in claim 4, characterized in that: The talent U with a high-trust relationship with the talent a is found in the talent social circle b , calculate talent a and talent U b The sum of the path confidences of all relationship paths between them is used to obtain the comprehensive confidence of the high-confidence relationship. The specific method for selecting the high-confidence relationship set of talent a from the high-confidence relationship set according to the comprehensive confidence is as follows: For talent U in the high-confidence relationship set of talent a b , use the depth-first search algorithm to find the number of people from a to U in the talent social circle b All relationship paths P(a, U b )=(p1,p2,...,p C ), the cth relationship path is expressed as: p c =(t1, t2, ..., t D ), where t1 = (a, r1, U1), t2 = (U1, r2, U2), …, t D =(U D-1 , r D , U b ), t D represents the Dth high-confidence relationship in the cth relationship path, U D -1 is the D-1th talent in the cth relationship path, r D Represents Connecting Talents U D-1 And TalentU b Explicit relationship of Computing Talent A and Talent U b The path confidence of each relationship path between them; The calculation formula of the path confidence is: Among them, len(p c ) represents the length of the cth relationship path, α is the path length attenuation factor, c(t d ) represents the relationship credibility of the dth high-credibility relationship, Πc(t d ) refers to the total product of the relationship credibility of all high-credibility relationships in the relationship path; According to from a to U b All relationship paths P(a, U b ) path confidence, calculate a and U b The overall confidence between Where C is the total number of relationship paths; Preset implicit relationship confidence threshold λ ys , if talent a and talent U b The comprehensive confidence of the relationship path between ys , then select talent a and talent U b The relationship path with the highest confidence between the two paths is obtained by merging all the explicit relationships in the relationship path to generate the relationship between talent a and talent U. b The implicit relation r'(a, U b ); Talent A and Talent U b , implicit relation r'(a, U b ) to form a high-confidence relationship, calculate the comprehensive confidence between talent a and all talents in the high-confidence relationship set, screen the talents that have a high-confidence relationship with talent a, and obtain a high-confidence relationship set.

6. The intelligent matching and recommendation method based on social network and relationship credibility analysis as claimed in claim 5, characterized in that: The method of taking the talents in the high-confidence relationship set as nodes and the explicit relationships as edges, calculating the edge weights according to the relationship credibility and comprehensive confidence between the talents, and constructing a social network of seed talents, and taking talent a as the starting point, judging whether each direct neighbor node of talent a is a strong-relation talent is as follows: Using all talents in the high-confidence relationship set as nodes and the explicit relationships between talent a and other talents in the high-confidence relationship set as edges, a social network of seed talents is constructed. For each edge e in the social network, the edge weight is calculated based on the credibility and comprehensive confidence of the relationship between the talents corresponding to the two nodes connecting the edge; Talent a is used as the seed talent. Starting from talent a, a breadth-first search is performed on the social network to obtain all the direct neighbor nodes of the seed talent. For each direct neighbor node v of the seed talent, determine whether the direct neighbor node is a strong relationship talent based on the edge weight w(a, v) between the direct neighbor node v and the seed talent; A strong relationship threshold μ is preset. If w(a, v) is greater than the strong relationship threshold μ, the direct neighbor node is regarded as a strong relationship talent and added to the candidate talent set. Otherwise, the direct neighbor node is regarded as a weak relationship talent. All strongly related talents in the candidate talent set are deduplicated to ensure that each strongly related talent appears only once in the candidate talent set.

7. The intelligent matching and recommendation method based on social network and relationship credibility analysis according to claim 6, characterized in that: The specific method of calculating the second matching degree between the strong relationship talent and position A, obtaining the employment status of the strong relationship talent, obtaining the edge weight connected to the seed talent, calculating the comprehensive matching degree of the strong relationship talent, sorting all the strong relationship talents according to the comprehensive matching degree, and adding the strong relationship talents with a comprehensive matching degree greater than the recommendation threshold into the talent recommendation database is as follows: For the strong relationship talent q, obtain its attribute information and employment status to form the attribute vector sx of the strong relationship talent q q , obtain the edge weight w(a, q) between the strong relationship talent q and the seed talent a from the talent social network, and calculate the second matching degree between the strong relationship talent q and the position A; The comprehensive matching degree of the strong relationship talent q is calculated by using the second matching degree between the strong relationship talent q and the position A, the employment status of the strong relationship talent q, and the edge weight between the strong relationship talent q and the seed talent; Sort all strong-relationship talents in descending order according to their corresponding comprehensive matching degrees, set a recommendation threshold Y, and add H strong-relationship talents whose comprehensive matching degrees are greater than the recommendation threshold to the talent recommendation pool.

8. An intelligent matching and recommendation system based on social network and relationship credibility analysis, which is implemented based on the intelligent matching and recommendation method based on social network and relationship credibility analysis according to any one of claims 1 to 7, characterized in that: include: The data collection module is used to collect job demand information, obtain the attribute information and employment status provided by each talent, and calculate the matching degree between talent a and position A based on the attribute information of talent a who submits a resume to position A. When the matching degree exceeds the matching threshold, talent a is regarded as a seed talent; The credibility calculation module is used to obtain the explicit relationships of talent a based on the attribute information provided by the talent, build the talent social circle, calculate the relationship credibility of the explicit relationships of talent a, and obtain the high-credibility relationship set of talent a from the explicit relationships whose relationship credibility is greater than the high-credibility threshold; The confidence calculation module is used to find talent U in the talent social circle that has a high-confidence relationship with talent a. b , calculate talent a and talent U b The sum of the path confidences of all relationship paths between them is used to obtain the comprehensive confidence of the high-confidence relationship. The high-confidence relationship set of talent a is screened out from the high-confidence relationship set according to the comprehensive confidence. The network construction module is used to take the talents in the high-confidence relationship set as nodes and the explicit relationships as edges, calculate the edge weights according to the relationship credibility and comprehensive confidence between talents, build a social network of seed talents, and take talent a as the starting point to determine whether each direct neighbor node of talent a is a strong relationship talent; The talent screening module is used to calculate the second matching degree between the strong relationship talent and position A, obtain the employment status of the strong relationship talent, obtain the edge weight connected to the seed talent, calculate the comprehensive matching degree of the strong relationship talent, sort all the strong relationship talents according to the comprehensive matching degree, and add the strong relationship talents whose comprehensive matching degree is greater than the recommendation threshold to the talent recommendation library.

9. An electronic device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps in the intelligent matching and recommendation method based on social network and relationship credibility analysis as described in any one of claims 1 to 7 are implemented.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and the computer program is suitable for being loaded by a processor to execute the steps in the intelligent matching and recommendation method based on social network and relationship credibility analysis as described in any one of claims 1 to 7.

Images