CN112116331A - Talent recommendation method and device - Google Patents
Talent recommendation method and device Download PDFInfo
- Publication number
- CN112116331A CN112116331A CN202011042735.2A CN202011042735A CN112116331A CN 112116331 A CN112116331 A CN 112116331A CN 202011042735 A CN202011042735 A CN 202011042735A CN 112116331 A CN112116331 A CN 112116331A
- Authority
- CN
- China
- Prior art keywords
- talent
- data
- label
- talents
- employee
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 33
- 230000003595 spectral effect Effects 0.000 claims abstract description 27
- 238000001228 spectrum Methods 0.000 claims abstract description 17
- 238000012545 processing Methods 0.000 claims abstract description 14
- 238000005516 engineering process Methods 0.000 claims description 18
- 238000011068 loading method Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 5
- 238000013075 data extraction Methods 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 11
- 230000006399 behavior Effects 0.000 description 9
- 230000011218 segmentation Effects 0.000 description 9
- 238000013473 artificial intelligence Methods 0.000 description 8
- 230000000694 effects Effects 0.000 description 7
- 230000009471 action Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 238000012797 qualification Methods 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 241000282376 Panthera tigris Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013501 data transformation Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000002688 persistence Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/105—Human resources
- G06Q10/1053—Employment or hiring
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
- G06F16/254—Extract, transform and load [ETL] procedures, e.g. ETL data flows in data warehouses
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Computational Linguistics (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Animal Behavior & Ethology (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention provides a talent recommendation method and a talent recommendation device, wherein the method comprises the following steps: generating a talent label according to a spectral clustering algorithm found by the community; processing data according to a spectrum clustering algorithm discovered by a community, forming entity and attribute information of staff relationships according to the processed data, and finally generating a staff relationship spectrum; receiving the requirements of the user; and determining the talents to be recommended matched with the personnel demand according to the personnel demand, the talent labels and the employee relationship map. According to the embodiment of the invention, the shortest employee relationship path of each recommended expert talent is automatically calculated by introducing the employee relationship map and combining the talent label library, and effective recommendation is carried out through employees to form a more effective recommendation relationship.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to a talent recommendation method and device.
Background
For large and medium-sized enterprises, a large amount of expert talents are gathered. However, for many branches, the branches do not necessarily have the required talents exactly, and in the face of new business products, the branches often need to search for or request superior support by themselves, and an effective way for quickly seeking expert guidance in the enterprise range is lacking.
FIG. 1 is a flow chart of a prior art talent recommendation method. As shown in fig. 1, the existing common solution mainly includes: performing database retrieval based on database basic data of talents, displaying retrieval results, and performing communication coordination through a contact way or superior leaders; the method further comprises the steps of constructing talent labels through basic data, retrieving based on the talent labels, and then performing communication coordination through a contact way or superior leaders.
In the process of implementing the invention, the inventor finds that at least the following problems exist in the prior art:
in the prior art, fuzzy query or accurate query based on talents basic information or talents labels is adopted, effective links of talents are not considered in talents searching and positioning, and although the contact ways of talents can be searched in a certain authority range, the abrupt contact may have a counterproductive effect.
Disclosure of Invention
The embodiment of the invention provides a talent recommendation method and device, which are used for realizing rapid and effective recommendation of cross-organization expert talents.
To achieve the above object, in a first aspect, an embodiment of the present invention provides a talent recommendation method, which includes:
generating a talent label according to a spectral clustering algorithm found by the community;
processing data according to a spectrum clustering algorithm discovered by a community, forming entity and attribute information of staff relationships according to the processed data, and finally generating a staff relationship spectrum;
receiving the requirements of the user;
and determining the talents to be recommended matched with the personnel demand according to the personnel demand, the talent labels and the employee relationship map.
In a second aspect, an embodiment of the present invention provides a talent recommendation device, which includes:
the label generation module is used for generating a talent label according to a spectral clustering algorithm found by the community;
the spectrum generation module is used for processing data according to a spectrum clustering algorithm discovered by the community, forming entity and attribute information of staff relation according to the processed data and finally generating a staff relation spectrum;
the demand interface module is used for receiving the demand of the user;
and the talent recommendation module is used for determining the talents to be recommended, which are matched with the personnel demand, according to the personnel demand, the talent labels and the employee relationship map.
In a third aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the talent recommendation method as described above.
In a fourth aspect, an embodiment of the present invention provides a computer device, including:
one or more processors;
storage means for storing one or more programs;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the talent recommendation method as described above.
The technical scheme has the following beneficial effects:
the embodiment of the invention generates the talent label through a spectral clustering algorithm according to community discovery; processing data according to a spectrum clustering algorithm discovered by a community, forming entity and attribute information of staff relationships according to the processed data, and finally generating a staff relationship spectrum; receiving the requirements of the user; determining talents to be recommended, which are matched with the personnel demand, according to the personnel demand, the talent labels and the employee relationship map; therefore, the problem of rapid and effective recommendation of the cross-organization expert talents is solved. According to the embodiment of the invention, the shortest employee relationship path of each recommended expert talent is automatically calculated by introducing the employee relationship map and combining the talent label library, and effective recommendation is carried out through employees to form a more effective recommendation relationship.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of a prior art talent recommendation method;
FIG. 2 is a flow chart of a talent recommendation method according to an embodiment of the present invention;
FIG. 3 is another flow chart of a talent recommendation method according to an embodiment of the present invention;
FIG. 4 is a process for computing employee labels using a spectral clustering algorithm according to an embodiment of the present invention;
FIG. 5 is a functional block diagram of a talent recommendation device according to an embodiment of the present invention;
FIG. 6 is a functional block diagram of a computer device of an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The following is a term explanation:
and (3) spectral clustering algorithm: spectral Clustering (SC) is a graph theory-based Clustering method, namely a weighted undirected graph is divided into two or more optimal sub-graphs, so that the interior of the sub-graphs is similar as much as possible, and the distance between the sub-graphs is far as much as possible, thereby achieving the aim of common Clustering. The related introduction of the algorithm can be specifically referred to as follows: https:// blog.csdn.net/u 011596455/article/details/53443848.
Employee relationship atlas: the relation graph is constructed based on information of working processes, social activities, life events and the like of the staff, and the staff relation is a key factor influencing staff behavior attitude, working efficiency and execution capacity.
Staff labeling: a visual representation of employee characteristics includes base tags, performance tags, competency tags, behavior tags, and the like.
ETL: Extraction-Transformation-Loading, data Extraction, Transformation and Loading. The ETL is responsible for extracting data in distributed and heterogeneous data sources, such as relational data, flat data files, and the like, to a temporary intermediate layer, then cleaning, converting, integrating, and finally loading to a data warehouse or a data mart, which becomes the basis of online analysis processing and data mining. The ETL technique may be replaced with a data warehouse technique in this embodiment.
ES: an elastic search, search engine, and in particular, ES, is an open source distributed search engine based on the RESTful web interface and built on top of the Apache Lucene. ES is also a distributed document database in which each field can be indexed and the data in each field can be searched, expanding laterally to hundreds of servers storing and processing PB-level data. The ES can store, search, and analyze a large amount of data in an extremely short time. Typically as a core engine with complex search scenarios. The ES is generated for high availability and extensibility, and on one hand, system extension can be completed by upgrading hardware, namely Vertical Scale/Scaling Up; on the other hand, more servers are added to complete the system expansion, called Horizontal expansion or Scaling Out.
CLOB: character Large Object, a Large Object of the Character type, is a type used in databases to hold files. In the Oracle database, the field capacity of the LOB (Large Object) type is Large (can accommodate 4GB of data at most), and a plurality of fields of this type can be present in one table, which is flexible and suitable for the business fields (such as images, files, etc.) with very Large data volume. LOB types include: BLOB, CLOB, and NCLOB. BLOB, a Binary Large Object, is suitable for storing non-text byte stream data (e.g., programs, images, video, etc.). The CLOB is associated with a character set and is adapted to store textual data (e.g., historical files, capitalized works, etc.). In the ORACLE database, information such as pictures, files, music and the like is stored by using BLOB fields, and the files are firstly converted into binary files and then stored. The articles or longer characters are stored by using CLOB, thus providing great convenience for the operations of updating and storing the subsequent query and the like. NCLOB is an internal fixed-length multi-byte character large object,
HanLP: han Language Processing, Chinese Language Processing package. The word segmentation method in the Hanlp Chinese natural language processing comprises standard word segmentation, NLP word segmentation, index word segmentation, N-shortest path word segmentation, CRF word segmentation, rapid dictionary word segmentation and the like. The Chinese word segmentation algorithm is of various types, such as the Chinese academy of sciences computing institute NLPIR, the Hadoda LTP, the Qinghua university THULAC, the Stanford word segmenter, the Hanlp segmenter, the jieba segmenter, the IKAnalyzer and the like.
neo 4J: neo4j is a high-performance NOSQL graph database that stores structured data on a network rather than in tables. It is an embedded, disk-based Java persistence engine with full transactional properties that stores structured data on the network (called a graph mathematically) instead of in tables. Neo4j can also be viewed as a high performance graph engine with all the features of a full database. Currently there are 5 major stream databases: neo4j, tiger graph, Amazon Neptune, JanusGraph, ArangoDB.
One of the objectives of embodiments of the present invention is to address the rapid and efficient recommendation of cross-institution expert talents. The prior talent recommendation method is mainly used for talent query based on talent basic data, and further, talent labels are constructed and retrieved based on the talent labels. The main problems with this approach are: even if the information of the prior talents is searched and matched, the effect is not ideal in the process of seeking help of expert talents for assistance because no intermediate person is effectively linked.
According to the embodiment of the invention, the shortest employee relationship path of each recommended expert talent is automatically calculated by introducing the employee relationship map and combining the talent label library, and effective recommendation is carried out through employees to form a more effective recommendation relationship.
The embodiment of the invention relates to the field of artificial intelligence, and discloses a method for generating talent labels and an employee relationship map.
The embodiment of the invention forms talent labels by technologies such as clustering and classifying; and constructing the relation graph of the staff by a knowledge graph technology.
The embodiment of the invention introduces the staff relationship on the basis of general database-based or label-based retrieval, carries out shortest path and most effective reachable talent recommendation on the basis of the staff relationship map, and carries out effective recommendation by the intermediate person, thereby well solving the problem of poor talent assistance effect caused by no intersection.
Fig. 2 is a flowchart of a talent recommendation method according to an embodiment of the present invention. As shown in fig. 2, the method comprises the steps of:
s110: and generating the talent label according to a spectral clustering algorithm found by the community.
Spectral Clustering (SC) is a graph theory-based Clustering method: the weighted undirected graph is divided into two or more optimal sub-graphs, so that the interior of the sub-graphs is similar as much as possible, and the distance between the sub-graphs is far as possible, thereby achieving the purpose of common clustering.
S120: and processing data according to a spectrum clustering algorithm discovered by the community, forming entity and attribute information of the staff relationship according to the processed data, and finally generating a staff relationship spectrum.
Entities of the knowledge graph: refers to something that is distinguishable and exists independently. Such as a person, a good, an animal, etc. Everything in the world is composed of specific things, which are referred to as entities. The entity is the most basic element in the knowledge graph, and different relationships exist among different entities.
Attributes of the knowledge graph: an attribute is an abstraction of the relationship between entities, for example, jieren is an entity, jieren is a person (type), two sticks are entities, and two sticks are music (type), and it is obvious that the relationship between two entities is: zhou Ji Lun → singer → nunchakus, so the relationship between Zhou Ji Lun and nunchakus can be characterized by the attribute "music". Then a layer of relationships, person (type) → singer (property) → music (type), can be built from the attributes.
S130: receiving human needs.
In this step, the human resources section mainly meets the requirements of the leaders and the professionals, such as: and (3) a certain department promotes the vice manager, formulates basic conditions and requirements of the vice manager for employment, and needs to extract leaders or staffs meeting corresponding conditions from the talent library of the enterprise and the talent labels to perform accurate talent matching recommendation.
S140: and determining the talents to be recommended matched with the personnel demand according to the personnel demand, the talent labels and the employee relationship atlas.
In some exemplary embodiments, step S140 may specifically include the following steps:
s141: calculating the shortest employee relationship path according to the personnel demand, the talent labels and the employee relationship map;
s142: and determining the talents to be recommended matched with the personnel demand according to the shortest employee relationship path.
In some exemplary embodiments, step S110 may specifically include the following steps:
s111: setting a label rule and a label classification corresponding to the talents, wherein the label classification comprises any more than one of the following: basic labels, performance labels, competency labels, behavior labels;
s112: extracting the structured data of talents by adopting ETL data extraction, conversion and loading technologies to form relational database data;
s113: calculating according to the label rule to form a basic label and a performance label of the talent;
s114: extracting unstructured document data from a talent document library; for example: photographed employee resume papery documents, employee basic file information papery documents, employee performance assessment result papery forms and the like.
S115: extracting unstructured document data of the staff by adopting a distributed search engine in combination with a plug-in to form character type large object CLOB data information of a relational database; the personnel refers to all the personnel of the enterprise, and the talents refer to the personnel who have certain skills, are marked with corresponding labels and enter a talent bank;
s116: extracting key words and abstract information from the CLOB data information; the existing various key words and abstract extraction algorithms can be adopted in the step;
s117: and calculating the extracted key words and abstract information and the label rule to form corresponding label data.
In some exemplary embodiments, step S120 specifically includes the following steps:
s121: extracting and analyzing data from the human resource data mart by adopting an ETL technology to form a database entity relationship network among the employees;
s122: establishing relationship map body information based on database entity relationship data, and establishing an employee relationship map by adopting a graphic database;
s123: graph traversal based on a graph database provides a graph traversal service interface based on entity attributes of an employee relationship graph.
In some exemplary embodiments, step S140 specifically includes the following steps:
s141: talent matching is carried out through a tag retrieval service interface;
s142: searching the shortest relation path for the talents required by the personnel and matched and searched talents through an employee relation atlas algorithm, and searching and determining a talent list corresponding to the shortest relation path;
s143: and applying a spectral clustering algorithm, displaying the talent list corresponding to the shortest relation path determined by searching according to the matching degree of the calculation result of spectral clustering, and displaying the employee relation information of the shortest relation path.
Fig. 3 is another flowchart of a talent recommendation method according to an embodiment of the present invention. As shown in fig. 3, the technical solution of the embodiment of the present invention includes the following processing steps:
s1: setting a label rule and a label classification of the expert talents, comprising: and classification information such as a basic label, a performance label, a competency label, a behavior label and the like.
Basic label rules: extracting from the human resources system staff resume including, but not limited to, staff age interval (under 25 years old, 25-35, 35-45, 45-55, over 55 years old), staff academic definition (under this department, master, over master), staff native place (north China, east China, south China, etc.), staff position information (line leader, general department manager level, treatment level, department level, below science and technology), etc.;
performance labeling: excellence, good, title job below;
competence quality label: differentiate the business ability quality of different lines, for public business line, for private business line, financial science and technology line, risk compliance line, financial accounting line etc. for example: financial science and technology lines, big data qualification, big data experts, artificial intelligence qualification, artificial intelligence experts, artificial intelligence high level, artificial intelligence medium level, artificial intelligence primary level, and the like;
behavior tag: for the employee behavior management information formed in the daily work of the employee, different business lines are distinguished, for example: acquiring frequently delayed arrival and frequently overtime according to attendance data; acquiring a purchasing work behavior according to purchasing data; and acquiring whether the employee has an illegal behavior according to the daily risk compliance.
FIG. 4 is a process for calculating employee labels using a spectral clustering algorithm according to an embodiment of the present invention. As shown in fig. 4, the process includes the steps of:
s210: and (5) data initialization operation. This step aggregates relevant structured and unstructured human resource data into a human resource data mart.
S220: data ETL and normalization.
S230: and clustering and dividing the data according to a spectral clustering algorithm.
S240: multiple substitutions are made.
S250: is it judged whether the parameter adjustment iteration has achieved the effect? If yes, step S260 is performed, and if no, step S230 is performed. In this step, parameters are adjusted for many times, and the result or effect meets the requirements or demands of business personnel, such as: the talents obtained by a certain talent base after algorithm calculation and parameter adjustment meet the service requirements.
S260: and selecting the talent label which best meets the business requirement.
S2: extracting the basic information, work history, post information, job information, professional specialties, project experience, assessment and evaluation results and other structured data of the expert talents by adopting an extract-Transformation-Loading (ETL) technology to form label data of a relational database, and performing operation according to a preset label rule to form personal basic label data and achievement label data of the expert talents.
S3: extracting unstructured document data such as work summaries, paper works, evaluation comments and the like from a talent document library, and extracting data of the unstructured document by combining ES with plugins such as Word \ Excel \ Pdf and the like to form CLOB data information of a relational database;
s4: and extracting and analyzing data from the data related to the employees by adopting an ETL technology to form a database entity relationship network among the employees.
S5: and (3) establishing relation graph ontology information, and establishing a knowledge graph (such as Neo4j) comprising nodes such as personnel, organizations, projects, tasks, schools, teams, meetings, processes, organizations and the like, and a knowledge graph of staff relations such as administrative relations, party and workgroup relations, training relations, marketing team relations, task relations, project relations, meeting relations, work circle relations, process relations, mail relations and the like.
S6: providing unified external expert talent recommendation engine interfaces to receive talent demands from various mechanisms, decomposing query demands by adopting technologies such as natural language word segmentation and the like, firstly carrying out expert matching through a tag retrieval service interface, then searching shortest relation paths between talent demands and retrieved expert talents through spectral clustering, and returning the shortest relation paths to the expert talent recommendation engine interfaces.
S7: and displaying the searched expert talent list according to the matching degree, and displaying the employee relationship information of the shortest relationship path.
The invention combines the label retrieval and the employee relationship map technology, and carries out shortest path and most effective reachable talent recommendation based on the employee relationship map, thereby well solving the problem of feasibility of expert talent recommendation, and having the specific advantages that:
the embodiment of the invention can effectively classify the expert talent information by the label, and can quickly search based on the label classification, the priority and the matching degree;
the embodiment of the invention can construct the employee relationship through the employee relationship map and quickly position the shortest path relationship based on the graph retrieval technology.
Fig. 5 is a functional block diagram of a talent recommendation device according to an embodiment of the present invention. As shown in fig. 5, the talent recommendation device 300 includes:
the label generation module 310 is configured to generate a talent label according to a spectral clustering algorithm found by a community;
the map generation module 320 is used for processing data according to a spectrum clustering algorithm discovered by the community, forming entity and attribute information of staff relationships according to the processed data, and finally generating a staff relationship map;
a requirement interface module 330 for receiving a person requirement;
and the talent recommendation module 340 is used for determining talents to be recommended, which are matched with the requirement of personnel, according to the requirement of personnel, the talent labels and the employee relationship maps.
In some exemplary embodiments, the recommendation module 340 is specifically configured to: calculating the shortest employee relationship path according to the personnel demand, the talent labels and the employee relationship map; and determining the talents to be recommended matched with the personnel demand according to the shortest employee relationship path.
In some exemplary embodiments, the tag generation module 310 may be specifically configured to:
setting a label rule and a label classification corresponding to the talents, wherein the label classification comprises any more than one of the following: basic labels, performance labels, competency labels, behavior labels;
extracting the structured data of talents by adopting ETL data extraction, conversion and loading technologies to form data of a relational database;
calculating according to the label rule to form a basic label and a performance label of the talent;
extracting unstructured document data from a talent document library;
extracting unstructured document data of the staff by adopting a distributed search engine in combination with a plug-in to form character type large object CLOB data information of a relational database;
extracting key words and abstract information from the CLOB data information;
and calculating the extracted key words and abstract information and the label rule to form corresponding label data.
In some exemplary embodiments, the atlas generation module 320 may be specifically configured to:
extracting and analyzing data from a human resource data mart by adopting an ETL technology to form a database entity relationship network among employees;
establishing relationship map body information based on database entity relationship data, and establishing an employee relationship map by adopting a graphic database;
graph traversal based on a graph database provides a graph traversal service interface based on entity attributes of an employee relationship graph.
In some exemplary embodiments, the talent recommendation module 340 is specifically configured to:
talent matching is carried out through a tag retrieval service interface;
searching the shortest relation path for the talents required by the user and the searched talents through the spectral clustering algorithm, and searching and determining a talent list corresponding to the shortest relation path;
and applying a spectral clustering algorithm, displaying the talent list corresponding to the shortest relation path determined by searching according to the matching degree of the calculation result of spectral clustering, and displaying the employee relation information of the shortest relation path.
According to the embodiment of the invention, the shortest employee relationship path of each recommended expert talent is automatically calculated by introducing the employee relationship map and combining the talent label library, and effective recommendation is carried out through employees to form a more effective recommendation relationship.
The embodiment of the invention relates to the field of artificial intelligence, and discloses a method for generating talent labels and an employee relationship map.
The embodiment of the invention introduces the staff relationship on the basis of general database-based or label-based retrieval, carries out shortest path and most effective reachable talent recommendation on the basis of the staff relationship map, and carries out effective recommendation by the intermediate person, thereby well solving the problem of poor talent assistance effect caused by no intersection.
An embodiment of the present invention further provides an electronic device, as shown in fig. 6, including one or more processors 401, a communication interface 402, a memory 403, and a communication bus 404, where the processors 401, the communication interface 402, and the memory 403 complete communication with each other through the communication bus 404.
A memory 403 for storing a computer program;
the processor 401 is configured to implement the steps of any one of the talent recommendation methods described above when executing the program stored in the memory 403.
The communication bus mentioned in the electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus. The communication interface is used for communication between the electronic equipment and other equipment.
The Memory may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components.
The embodiment of the invention also provides a computer readable storage medium, wherein a computer program is stored in the computer readable storage medium, and when being executed by a processor, the computer program realizes the steps of the continuous integration automatic testing method.
Those of skill in the art will further appreciate that the various illustrative logical blocks, units, and steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate the interchangeability of hardware and software, various illustrative components, elements, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design requirements of the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present embodiments.
The various illustrative logical blocks, or elements, described in connection with the embodiments disclosed herein may be implemented or performed with a general purpose processor, a digital signal processor, an Application Specific Integrated Circuit (ASIC), a field programmable gate array or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general-purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, e.g., a digital signal processor and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a digital signal processor core, or any other similar configuration.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the device, the electronic device and the readable storage medium embodiments, since they are substantially similar to the method embodiments, the description is simple, and the relevant points can be referred to the partial description of the method embodiments.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.
Claims (12)
1. A talent recommendation method, comprising:
generating a talent label according to a spectral clustering algorithm found by the community;
processing data according to a spectrum clustering algorithm discovered by a community, forming entity and attribute information of staff relationships according to the processed data, and finally generating a staff relationship spectrum;
receiving the requirements of the user;
and determining the talents to be recommended matched with the personnel demand according to the personnel demand, the talent labels and the employee relationship map.
2. The method according to claim 1, wherein the determining the talents to be recommended that match the human need according to the human need, the talent labels and the employee relationship graph specifically comprises:
calculating the shortest employee relationship path according to the personnel demand, the talent label and the employee relationship map;
and determining the talents to be recommended matched with the personnel demand according to the shortest staff relation path.
3. The method according to claim 2, wherein the generating of the talent label according to the spectral clustering algorithm found in the community specifically comprises:
setting a label rule and a label classification corresponding to the talents, wherein the label classification comprises any more than one of the following: basic labels, performance labels, competency labels, behavior labels;
extracting the structured data of talents by adopting ETL data extraction, conversion and loading technologies to form relational database data;
calculating according to the label rule to form a basic label and a performance label of the talent;
extracting unstructured document data from a talent document library;
extracting unstructured document data of the staff by adopting a distributed search engine in combination with a plug-in to form character type large object CLOB data information of a relational database;
extracting key words and abstract information from the CLOB data information;
and calculating the extracted keywords and the abstract information and the label rule to form corresponding label data.
4. The method according to claim 1 or 3, wherein the data are integrated according to a spectral clustering algorithm discovered by the community to form entity and attribute graph database information of the employee relationship, and finally the employee relationship graph is generated, specifically comprising:
extracting and analyzing data from the human resource data mart by adopting an ETL technology to form a database entity relationship network among the employees;
establishing relationship map body information based on database entity relationship data, and establishing an employee relationship map by adopting a graphic database;
graph traversal based on a graph database provides a graph traversal service interface based on entity attributes of an employee relationship graph.
5. The method according to any one of claims 1 to 3, wherein the determining of the talents to be recommended that match the human need according to the human need, the talent labels and the employee relationship graph specifically comprises:
talent matching is carried out through a tag retrieval service interface;
searching the shortest relation path for the personnel demand and the searched talents through the employee relation graph, and searching and determining a talent list corresponding to the shortest relation path;
and applying a spectral clustering algorithm, displaying the talent list corresponding to the shortest relation path determined by searching according to the matching degree of the calculation result of spectral clustering, and displaying the employee relation information of the shortest relation path.
6. An talent recommendation device, comprising:
the label generation module is used for generating a talent label according to a spectral clustering algorithm found by the community;
the spectrum generation module is used for processing data according to a spectrum clustering algorithm discovered by the community, forming entity and attribute information of staff relation according to the processed data and finally generating a staff relation spectrum;
the demand interface module is used for receiving the demand of the user;
and the talent recommendation module is used for determining the talents to be recommended, which are matched with the personnel demand, according to the personnel demand, the talent labels and the employee relationship map.
7. The apparatus according to claim 6, wherein the recommendation module is specifically configured to calculate a shortest employee relationship path according to the employment requirement, the talent label, and the employee relationship graph; and determining the talents to be recommended matched with the personnel demand according to the shortest staff relation path.
8. The apparatus of claim 7, wherein the tag generation module is specifically configured to:
setting a label rule and a label classification corresponding to the talents, wherein the label classification comprises any more than one of the following: basic labels, performance labels, competency labels, behavior labels;
extracting the structured data of talents by adopting ETL data extraction, conversion and loading technologies to form data of a relational database;
calculating according to the label rule to form a basic label and a performance label of the talent;
extracting unstructured document data from a talent document library;
extracting unstructured document data of the staff by adopting a distributed search engine in combination with a plug-in to form character type large object CLOB data information of a relational database;
extracting key words and abstract information from the CLOB data information; and calculating the extracted keywords and the abstract information and the label rule to form corresponding label data.
9. The apparatus according to claim 6 or 8, wherein the atlas generation module is specifically configured to:
extracting and analyzing data from the human resource data mart by adopting an ETL technology to form a database entity relationship network among the employees;
establishing relationship map body information based on database entity relationship data, and establishing an employee relationship map by adopting a graphic database;
graph traversal based on a graph database provides a graph traversal service interface based on entity attributes of an employee relationship graph.
10. The apparatus according to any one of claims 6-8, wherein the talent recommendation module is specifically configured to:
talent matching is carried out through a tag retrieval service interface;
searching the shortest relation path for the personnel using requirements and the searched talents through the spectral clustering algorithm, and searching and determining a talent list corresponding to the shortest relation path;
and applying a spectral clustering algorithm, displaying the talent list corresponding to the shortest relation path determined by searching according to the matching degree of the calculation result of spectral clustering, and displaying the employee relation information of the shortest relation path.
11. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the talent recommendation method according to any one of claims 1-5.
12. A computer device, comprising:
one or more processors;
storage means for storing one or more programs;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the talent recommendation method of any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011042735.2A CN112116331A (en) | 2020-09-28 | 2020-09-28 | Talent recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011042735.2A CN112116331A (en) | 2020-09-28 | 2020-09-28 | Talent recommendation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112116331A true CN112116331A (en) | 2020-12-22 |
Family
ID=73797248
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011042735.2A Pending CN112116331A (en) | 2020-09-28 | 2020-09-28 | Talent recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112116331A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112380359A (en) * | 2021-01-18 | 2021-02-19 | 平安科技（深圳）有限公司 | Knowledge graph-based training resource allocation method, device, equipment and medium |
| CN113537922A (en) * | 2021-05-31 | 2021-10-22 | 东莞理工学院 | Science and technology project talent recommendation system and method based on big data |
| CN114925289A (en) * | 2022-05-23 | 2022-08-19 | 中国平安财产保险股份有限公司 | Employee recommendation method, device, equipment and readable storage medium |
| CN116596412A (en) * | 2023-07-19 | 2023-08-15 | 中国电子科技集团公司第十五研究所 | Method and system for realizing talent type portrait |
| CN117217392A (en) * | 2023-11-07 | 2023-12-12 | 中国电子科技集团公司第十五研究所 | Method and device for determining general equipment guarantee requirement |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109584094A (en) * | 2018-11-23 | 2019-04-05 | 中国运载火箭技术研究院 | A kind of interpersonal path quick positioning system, method and medium |
| CN109859065A (en) * | 2019-02-28 | 2019-06-07 | 桂林理工大学 | Multiple target complex network community discovery method based on spectral clustering |
| CN111008215A (en) * | 2019-11-29 | 2020-04-14 | 中科院计算技术研究所大数据研究院 | Expert recommendation method combining label construction and community relation avoidance |
| CN111625722A (en) * | 2020-05-27 | 2020-09-04 | 海南大学 | Talent recommendation method, system and storage medium based on deep learning |
-
2020
- 2020-09-28 CN CN202011042735.2A patent/CN112116331A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109584094A (en) * | 2018-11-23 | 2019-04-05 | 中国运载火箭技术研究院 | A kind of interpersonal path quick positioning system, method and medium |
| CN109859065A (en) * | 2019-02-28 | 2019-06-07 | 桂林理工大学 | Multiple target complex network community discovery method based on spectral clustering |
| CN111008215A (en) * | 2019-11-29 | 2020-04-14 | 中科院计算技术研究所大数据研究院 | Expert recommendation method combining label construction and community relation avoidance |
| CN111625722A (en) * | 2020-05-27 | 2020-09-04 | 海南大学 | Talent recommendation method, system and storage medium based on deep learning |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112380359A (en) * | 2021-01-18 | 2021-02-19 | 平安科技（深圳）有限公司 | Knowledge graph-based training resource allocation method, device, equipment and medium |
| CN112380359B (en) * | 2021-01-18 | 2021-04-20 | 平安科技（深圳）有限公司 | Knowledge graph-based training resource allocation method, device, equipment and medium |
| CN113537922A (en) * | 2021-05-31 | 2021-10-22 | 东莞理工学院 | Science and technology project talent recommendation system and method based on big data |
| CN113537922B (en) * | 2021-05-31 | 2024-02-13 | 东莞理工学院 | Science and technology project talent recommendation system and method based on big data |
| CN114925289A (en) * | 2022-05-23 | 2022-08-19 | 中国平安财产保险股份有限公司 | Employee recommendation method, device, equipment and readable storage medium |
| CN114925289B (en) * | 2022-05-23 | 2024-04-30 | 中国平安财产保险股份有限公司 | Employee recommendation method, device, equipment and readable storage medium |
| CN116596412A (en) * | 2023-07-19 | 2023-08-15 | 中国电子科技集团公司第十五研究所 | Method and system for realizing talent type portrait |
| CN117217392A (en) * | 2023-11-07 | 2023-12-12 | 中国电子科技集团公司第十五研究所 | Method and device for determining general equipment guarantee requirement |
| CN117217392B (en) * | 2023-11-07 | 2024-01-09 | 中国电子科技集团公司第十五研究所 | Method and device for determining general equipment guarantee requirement |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107368468B (en) | Operation and maintenance knowledge map generation method and system | |
| AU2019204976B2 (en) | Intelligent data ingestion system and method for governance and security | |
| CN112116331A (en) | Talent recommendation method and device | |
| US11734233B2 (en) | Method for classifying an unmanaged dataset | |
| US11714831B2 (en) | Data processing and classification | |
| US9542412B2 (en) | Method and system for large scale data curation | |
| CN108713205A (en) | System and method for the data type that automatic mapping and data stream environment are used together | |
| Varshney et al. | Predicting employee expertise for talent management in the enterprise | |
| CN117033654A (en) | Science and technology event map construction method for science and technology mist identification | |
| Ali et al. | Distributed data mining systems: techniques, approaches and algorithms | |
| Basharat et al. | Semantically enriched task and workflow automation in crowdsourcing for linked data management | |
| Nedumov et al. | Automation of data normalization for implementing master data management systems | |
| US20220156228A1 (en) | Data Tagging And Synchronisation System | |
| Panagopoulos et al. | Scientometrics for success and influence in the microsoft academic graph | |
| CN115329083A (en) | Document classification method and device, computer equipment and storage medium | |
| TWI419071B (en) | Active knowledge management system, method and computer program product for problem solving | |
| Li et al. | Retrieving and classifying LinkedIn job titles for alumni career analysis | |
| Basharat et al. | Crowdlink: Crowdsourcing for large-scale linked data management | |
| Dahiya et al. | Effective data warehouse for information delivery: a literature survey and classification | |
| Lu et al. | Overview of knowledge mapping construction technology | |
| US20190087485A1 (en) | Selection device, selection method, and non-transitory computer readable storage medium | |
| Dashdorj et al. | High‐level event identification in social media | |
| Feng et al. | ASMaaS: Automatic Semantic Modeling as a Service | |
| Brunnert et al. | Enterprise people and skill discovery using tolerant retrieval and visualization | |
| Labib et al. | A Proposed Data Mining Model to Enhance Counter-Criminal Systems with Application on National Security Crimes |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |