CN113627883B - Cloud customization recruitment method and system - Google Patents
Cloud customization recruitment method and system Download PDFInfo
- Publication number
- CN113627883B CN113627883B CN202110910036.3A CN202110910036A CN113627883B CN 113627883 B CN113627883 B CN 113627883B CN 202110910036 A CN202110910036 A CN 202110910036A CN 113627883 B CN113627883 B CN 113627883B
- Authority
- CN
- China
- Prior art keywords
- matching
- information
- semantic
- target
- recruitment
- 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.)
- Active
Links
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
- G06F16/30—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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Computational Linguistics (AREA)
- Marketing (AREA)
- Economics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a cloud customization recruitment method and a system, wherein the method comprises the following steps: customizing a recruitment through a cloud server, and broadcasting a preset first questionnaire and a preset second questionnaire corresponding to the recruitment; respectively acquiring job seeking information filled in by a job seeking user based on a preset first questionnaire and recruitment information filled in by an enterprise user based on a preset second questionnaire; matching the job hunting information with the recruitment information, and determining target job hunting information and target recruitment information which are successfully matched; and pushing the target job hunting information to the enterprise user corresponding to the target recruitment information, and pushing the target recruitment information to the job hunting user corresponding to the target job hunting information. According to the cloud customization recruitment method and system, information docking between the job seeker and the recruitment enterprise is achieved through the cloud server, the enterprise is helped to judge whether the recruitment needs to be attended, convenience of the enterprise in understanding talent conditions is improved, the job seeker can be helped to know enterprise information suitable for the job seeker in advance, and convenience of the job seeker in learning the enterprise is improved.
Description
Technical Field
The invention relates to the technical field of internet cloud computing, in particular to a cloud customization recruitment method and system.
Background
At present, the enterprise registers and participates in a recruitment, who can not know in advance to participate in the recruitment, can not grasp the information of the job seekers who participate in the recruitment, so that the enterprise is blind to participate in the recruitment, can not judge whether the talents required by the enterprise exist in the job seekers who participate in the recruitment, the effect of the talents is difficult to predict and grasp, and the enterprise can not accurately judge whether to participate in the recruitment, and meanwhile, the job seeker registers and participates in a recruitment, only can obtain the information related to the enterprise which participates in the recruitment, needs to search the enterprise one by one, is very troublesome, and can not accurately judge whether to participate in the recruitment.
Disclosure of Invention
The cloud customization recruitment method and system have the advantages that information docking of the recruiter and the recruitment enterprise is achieved through the cloud server, the recruitment enterprise can be helped to master information of the recruiter participating in the recruitment in advance, whether talents needed by the enterprise exist in the recruiter participating in the recruitment or not is accurately judged, recruiter effect participating in the recruitment is predicted, accordingly the enterprise is helped to judge whether the recruitment needs to be participated in, convenience of the enterprise in talent knowledge is improved, the recruiter can be helped to know enterprise information suitable for the enterprise in advance, and convenience of the recruiter in enterprise knowledge is improved.
The cloud customization recruitment method provided by the embodiment of the invention is applied to a cloud server, and the following operations are executed through the cloud server:
customizing a recruitment, and broadcasting a preset first questionnaire and a preset second questionnaire corresponding to the recruitment;
respectively acquiring job seeking information filled in by a job seeking user based on a preset first questionnaire and recruitment information filled in by an enterprise user based on a preset second questionnaire;
matching the job hunting information with the recruitment information, and determining target job hunting information and target recruitment information which are successfully matched;
and pushing the target job hunting information to the enterprise user corresponding to the target recruitment information, and pushing the target recruitment information to the job hunting user corresponding to the target job hunting information.
Preferably, matching the job hunting information with the recruitment information includes:
acquiring a preset matching task set, and selecting any matching task from the matching task set;
respectively acquiring importance data through a plurality of preset acquisition paths, and integrating the importance data to acquire importance big data;
determining an importance value of the matching task based on the importance big data;
sequencing all matching tasks in the matching task set from large to small based on the corresponding importance values to obtain a target matching task set;
Selecting target matching tasks from the target matching task set according to a preset sequence;
respectively extracting first to-be-matched information corresponding to a target matching task in job hunting information and second to-be-matched information corresponding to the target matching task in recruitment information;
matching the first information to be matched with the second information to be matched based on an information matching technology to obtain a first matching value;
if the first matching value is greater than or equal to a preset matching value threshold, the execution result of the target matching task is that the matching is successful, otherwise, the matching is failed;
if the execution results of the target matching tasks of the previous preset number in the target matching task set are successful in matching, the job hunting information and the recruitment information are successfully matched, otherwise, the matching is failed.
Preferably, determining the importance value of the matching task based on the importance big data includes:
preprocessing the importance big data to obtain target big data;
determining associated data associated with the matching task in the target big data;
determining the proportion of the associated data in the target big data;
the scale is taken as an important value of the matching task.
Preferably, the preprocessing is performed on the big importance data, including;
analyzing the importance big data to obtain a plurality of target data and a plurality of acquisition nodes corresponding to the target data one by one;
Acquiring verification data by each acquisition node, integrating the verification data to obtain verification big data, wherein the verification big data comprises: a plurality of historical data that a user who published the target data published historically;
determining the target moment when the user issues target data;
determining a plurality of historical data which are released by a user in a preset time period before a target moment in verification big data, and integrating the historical data into first historical big data;
determining a plurality of historical data released by a user in a preset time period after a target moment in the verification big data, and integrating the historical data into second historical big data;
identifying the first historical big data based on a semantic identification technology to obtain a plurality of first semantic features, and constructing a first semantic feature database based on each first semantic feature;
identifying the second historical big data based on a semantic identification technology to obtain a plurality of second semantic features, and constructing a second semantic feature database based on each second semantic feature;
identifying the target data based on a semantic identification technology to obtain a third semantic feature;
matching the third semantic features with the first semantic features in the first semantic feature database, and determining the first number of successfully matched first semantic features;
Matching the third semantic features with second semantic features in a second semantic feature database, and determining a second number of successfully matched second semantic features;
converting the third semantic features into a plurality of negative semantic features and negative-like semantic features based on a preset conversion rule, wherein the negative semantic features and the negative-like semantic features are classified according to the degree of negation;
matching each negative semantic feature with the first semantic features in the first semantic feature database, and determining the third number of successfully matched first semantic features;
matching each negative semantic feature with a second semantic feature in a second semantic feature database, and determining a fourth number of successfully matched second semantic features;
matching each negative semantic feature with a first semantic feature in a first semantic feature database, and determining a fifth number of successfully matched first semantic features;
matching each negative semantic feature with a second semantic feature in a second semantic feature database, and determining a sixth number of successfully matched second semantic features;
calculating a judgment index based on the first number, the second number, the third number, the fourth number, the fifth number and the sixth number, wherein the calculation formula is as follows:
Wherein, gamma is the judgment index, alpha 1 For the first number, alpha 2 For the second number, alpha 3,i For the third number of the first semantic features successfully matched with the ith negative semantic feature in the first semantic feature database, alpha 4,i For the fourth number of second semantic features successfully matched with the ith negative semantic feature in the second semantic feature database, alpha 5,i For the fifth number of the first semantic features successfully matched with the ith class of negative semantic features in the first semantic feature database, alpha 6,i For the sixth number, sigma, of second semantic features successfully matched with the ith class of negative semantic features in the second semantic feature database 1,i For the level of negativity, σ, corresponding to the ith negative semantic feature 2,i A level of negation corresponding to the ith class of negation semantic features, n 1 To negate the total number of semantic features, n 2 X is the total number of negative semantic features 1 X is the total number of first semantic features in the first semantic feature database 2 Mu, the total number of second semantic features in the second semantic feature database 1 Sum mu 2 Is a preset weight value theta 1 And theta 2 Is an intermediate variable;
if the judgment index is smaller than or equal to a preset judgment index threshold value, eliminating target data from the important big data;
And after all the target data to be eliminated are eliminated, finishing preprocessing.
Preferably, the job hunting information and the recruitment information are preprocessed before the job hunting information and the recruitment information are matched;
the preprocessing of job hunting information and recruitment information comprises the following steps:
acquiring first meeting information of job seeker, wherein the first meeting information comprises: historically, the job seeker referred to a first record of the recruitment;
acquiring second meeting information of the enterprise user, wherein the second meeting information comprises: a second record of the enterprise user participating in the recruitment historically;
determining a seventh number of the first record and the second record having the same record;
the masking index is calculated based on the seventh number, and the calculation formula is as follows:
wherein beta is the shielding index, d 1 D is the total number of first records in the first reference information 2 Z is a seventh number, which is the total number of second records in the second reference information;
and if the shielding index is greater than or equal to a preset shielding index threshold value, not matching the corresponding job hunting information and recruitment information.
The cloud customization recruitment system provided by the embodiment of the invention is applied to a cloud server, and the cloud server comprises:
the customization and broadcasting module is used for customizing a recruitment and broadcasting a preset first questionnaire and a preset second questionnaire corresponding to the recruitment;
The acquisition module is used for respectively acquiring job hunting information filled in by a job hunting user based on a preset first questionnaire and recruitment information filled in by an enterprise user based on a preset second questionnaire;
the matching module is used for matching the job hunting information with the recruitment information and determining target job hunting information and target recruitment information which are successfully matched;
and the pushing module is used for pushing the target job hunting information to the enterprise user corresponding to the target recruitment information and pushing the target recruitment information to the job hunting user corresponding to the target job hunting information.
Preferably, the matching module performs the following operations:
acquiring a preset matching task set, and selecting any matching task from the matching task set;
respectively acquiring importance data through a plurality of preset acquisition paths, and integrating the importance data to acquire importance big data;
determining an importance value of the matching task based on the importance big data;
sequencing all matching tasks in the matching task set from large to small based on the corresponding importance values to obtain a target matching task set;
selecting target matching tasks from the target matching task set according to a preset sequence;
respectively extracting first to-be-matched information corresponding to a target matching task in job hunting information and second to-be-matched information corresponding to the target matching task in recruitment information;
Matching the first information to be matched with the second information to be matched based on an information matching technology to obtain a first matching value;
if the first matching value is greater than or equal to a preset matching value threshold, the execution result of the target matching task is that the matching is successful, otherwise, the matching is failed;
if the execution results of the target matching tasks of the previous preset number in the target matching task set are successful in matching, the job hunting information and the recruitment information are successfully matched, otherwise, the matching is failed.
Preferably, the matching module performs the following operations:
preprocessing the importance big data to obtain target big data;
determining associated data associated with the matching task in the target big data;
determining the proportion of the associated data in the target big data;
the scale is taken as an important value of the matching task.
Preferably, the matching module performs the following operations:
analyzing the importance big data to obtain a plurality of target data and a plurality of acquisition nodes corresponding to the target data one by one;
acquiring verification data by each acquisition node, integrating the verification data to obtain verification big data, wherein the verification big data comprises: a plurality of historical data that a user who published the target data published historically;
Determining the target moment when the user issues target data;
determining a plurality of historical data which are released by a user in a preset time period before a target moment in verification big data, and integrating the historical data into first historical big data;
determining a plurality of historical data released by a user in a preset time period after a target moment in the verification big data, and integrating the historical data into second historical big data;
identifying the first historical big data based on a semantic identification technology to obtain a plurality of first semantic features, and constructing a first semantic feature database based on each first semantic feature;
identifying the second historical big data based on a semantic identification technology to obtain a plurality of second semantic features, and constructing a second semantic feature database based on each second semantic feature;
identifying the target data based on a semantic identification technology to obtain a third semantic feature;
matching the third semantic features with the first semantic features in the first semantic feature database, and determining the first number of successfully matched first semantic features;
matching the third semantic features with second semantic features in a second semantic feature database, and determining a second number of successfully matched second semantic features;
Converting the third semantic features into a plurality of negative semantic features and negative-like semantic features based on a preset conversion rule, wherein the negative semantic features and the negative-like semantic features are classified according to the degree of negation;
matching each negative semantic feature with the first semantic features in the first semantic feature database, and determining the third number of successfully matched first semantic features;
matching each negative semantic feature with a second semantic feature in a second semantic feature database, and determining a fourth number of successfully matched second semantic features;
matching each negative semantic feature with a first semantic feature in a first semantic feature database, and determining a fifth number of successfully matched first semantic features;
matching each negative semantic feature with a second semantic feature in a second semantic feature database, and determining a sixth number of successfully matched second semantic features;
calculating a judgment index based on the first number, the second number, the third number, the fourth number, the fifth number and the sixth number, wherein the calculation formula is as follows:
wherein, gamma is the judgment index, alpha 1 For the first number, alpha 2 For the second number, alpha 3,i For the third number of the first semantic features successfully matched with the ith negative semantic feature in the first semantic feature database, alpha 4,i For the fourth number of second semantic features successfully matched with the ith negative semantic feature in the second semantic feature database, alpha 5,i For the fifth number of the first semantic features successfully matched with the ith class of negative semantic features in the first semantic feature database, alpha 6,i For the sixth number, sigma, of second semantic features successfully matched with the ith class of negative semantic features in the second semantic feature database 1,i For the level of negativity, σ, corresponding to the ith negative semantic feature 2,i A level of negation corresponding to the ith class of negation semantic features, n 1 To negate the total number of semantic features, n 2 X is the total number of negative semantic features 1 X is the total number of first semantic features in the first semantic feature database 2 Mu, the total number of second semantic features in the second semantic feature database 1 Sum mu 2 Is a preset weight value theta 1 And theta 2 Is an intermediate variable;
if the judgment index is smaller than or equal to a preset judgment index threshold value, eliminating target data from the important big data;
and after all the target data to be eliminated are eliminated, finishing preprocessing.
Preferably, the cloud server further comprises:
the preprocessing module is used for preprocessing the job hunting information and the recruitment information before matching the job hunting information with the recruitment information;
The preprocessing module performs the following operations:
acquiring first meeting information of job seeker, wherein the first meeting information comprises: historically, the job seeker referred to a first record of the recruitment;
acquiring second meeting information of the enterprise user, wherein the second meeting information comprises: a second record of the enterprise user participating in the recruitment historically;
determining a seventh number of the first record and the second record having the same record;
the masking index is calculated based on the seventh number, and the calculation formula is as follows:
wherein beta is the shielding index, d 1 D is the total number of first records in the first reference information 2 Z is a seventh number, which is the total number of second records in the second reference information;
and if the shielding index is greater than or equal to a preset shielding index threshold value, not matching the corresponding job hunting information and recruitment information.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
fig. 1 is a flowchart of a cloud customized recruitment method in accordance with an embodiment of the present invention;
fig. 2 is a schematic diagram of a cloud customized recruitment system in accordance with an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
The embodiment of the invention provides a cloud customization recruitment method, which is applied to a cloud server, and as shown in fig. 1, the following operations are executed through the cloud server:
s1, customizing a recruitment, and broadcasting a preset first questionnaire and a preset second questionnaire corresponding to the recruitment;
s2, job seeking information filled in by a job seeking user based on a preset first questionnaire and recruitment information filled in by an enterprise user based on a preset second questionnaire are respectively obtained;
s3, matching the job hunting information with the recruitment information, and determining target job hunting information and target recruitment information which are successfully matched;
And S4, pushing the target job hunting information to enterprise users corresponding to the target recruitment information, and pushing the target recruitment information to job hunting users corresponding to the target job hunting information.
The working principle and the beneficial effects of the technical scheme are as follows:
customizing recruitment (such as time, place and interview mode), broadcasting a preset first questionnaire (a questionnaire filled by a job-required person and comprising a plurality of filling items such as names, ages, academies, hobbies, family backgrounds, working experiences and the like) and a preset second questionnaire (a questionnaire filled by an enterprise HR and comprising a plurality of filling items such as age requirements, academies requirements, working experience requirements and the like); each user views two questionnaires of the recruitment through a network terminal (a mobile phone, a computer, a tablet and the like), the questionnaires are marked with information (time, place and interview mode) of the recruitment, and after confirmation of participation, the corresponding questionnaires are selected for filling; matching the job hunting information with the recruitment information, determining any group of successfully matched target job hunting information and target recruitment information, pushing the target recruitment information to the corresponding job hunting users for viewing, and pushing the target job hunting information to the corresponding enterprise users for viewing.
According to the embodiment of the invention, the information butt joint of the job seeker and the recruitment enterprise is realized through the cloud server, the recruitment enterprise can be helped to grasp the job seeker information of participating in the recruitment in advance, whether the talents needed by the enterprise exist in the job seeker of participating in the recruitment or not is accurately judged, and the talent effect of participating in the recruitment is predicted, so that the enterprise is helped to judge whether the recruitment is needed to participate in, the convenience of the enterprise in understanding talent conditions is improved, the job seeker can be helped to know the enterprise information suitable for the job seeker in advance, and the convenience of the job seeker in understanding the enterprise is improved.
The embodiment of the invention provides a cloud customization recruitment method, which is used for matching job hunting information with recruitment information and comprises the following steps:
acquiring a preset matching task set, and selecting any matching task from the matching task set;
respectively acquiring importance data through a plurality of preset acquisition paths, and integrating the importance data to acquire importance big data;
determining an importance value of the matching task based on the importance big data;
sequencing all matching tasks in the matching task set from large to small based on the corresponding importance values to obtain a target matching task set;
selecting target matching tasks from the target matching task set according to a preset sequence;
Respectively extracting first to-be-matched information corresponding to a target matching task in job hunting information and second to-be-matched information corresponding to the target matching task in recruitment information;
matching the first information to be matched with the second information to be matched based on an information matching technology to obtain a first matching value;
if the first matching value is greater than or equal to a preset matching value threshold, the execution result of the target matching task is that the matching is successful, otherwise, the matching is failed;
if the execution results of the target matching tasks of the previous preset number in the target matching task set are successful in matching, the job hunting information and the recruitment information are successfully matched, otherwise, the matching is failed.
The working principle and the beneficial effects of the technical scheme are as follows:
the preset matching task set specifically comprises the following steps: a plurality of matching tasks, for example: work experience item matching tasks, academic item matching tasks, interest item matching tasks and the like; the preset plurality of acquisition paths specifically include: connecting with a plurality of forum websites (such as recruitment communication forums, HR communication forums and the like), acquiring importance data (such as data about information about a job seeker in recruitment skill articles published by each authentication expert on a certain HR communication forum) through the acquisition path, and integrating (such as time sequence combination) all the importance data to acquire importance big data; determining the importance value of each matching task based on the importance big data, wherein the larger the importance value is, which indicates that certain information of job seekers is required to be matched with enterprise requirements, and sequencing each matching task from big to small based on the corresponding importance value to obtain a target matching task set; selecting target matching tasks according to a preset sequence (preferentially selecting the top item); executing the target matching task, and when the execution results of the current preset number (for example, 8) of target matching tasks are all successful in matching, indicating that the important part of job-seeking information of the job seeker accords with the enterprise, and the matching is successful; the preset matching degree threshold value is specifically: for example, 95.5.
When the matching tasks are executed, the important value of each matching task is determined, the tasks with larger important values are preferentially executed, and when the matching tasks with the front important values are successfully executed, the important part of job hunting information of the job seeker can be indicated to be consistent with the enterprise, the other matching tasks with lower important values do not need to be executed continuously, the working efficiency of the system is improved, and a large amount of time is saved.
The embodiment of the invention provides a cloud customization recruitment method, which determines an important value of a matching task based on important big data, and comprises the following steps:
preprocessing the importance big data to obtain target big data;
determining associated data associated with the matching task in the target big data;
determining the proportion of the associated data in the target big data;
the scale is taken as an important value of the matching task.
The working principle and the beneficial effects of the technical scheme are as follows:
the larger the proportion of the associated data corresponding to the matching task in the target big data is, the more users (such as an authentication expert, a senior HR and the like) consider that the information item (such as a life planning) corresponding to the matching task accords with the enterprise requirement, and therefore the proportion is taken as an important value.
The embodiment of the invention takes the proportion of the associated data in the target big data as an important value, and is reasonable in setting.
The embodiment of the invention provides a cloud customization recruitment method, which is used for preprocessing important big data and comprises the following steps of;
analyzing the importance big data to obtain a plurality of target data and a plurality of acquisition nodes corresponding to the target data one by one;
acquiring verification data by each acquisition node, integrating the verification data to obtain verification big data, wherein the verification big data comprises: a plurality of historical data that a user who published the target data published historically;
determining the target moment when the user issues target data;
determining a plurality of historical data which are released by a user in a preset time period before a target moment in verification big data, and integrating the historical data into first historical big data;
determining a plurality of historical data released by a user in a preset time period after a target moment in the verification big data, and integrating the historical data into second historical big data;
identifying the first historical big data based on a semantic identification technology to obtain a plurality of first semantic features, and constructing a first semantic feature database based on each first semantic feature;
identifying the second historical big data based on a semantic identification technology to obtain a plurality of second semantic features, and constructing a second semantic feature database based on each second semantic feature;
Identifying the target data based on a semantic identification technology to obtain a third semantic feature;
matching the third semantic features with the first semantic features in the first semantic feature database, and determining the first number of successfully matched first semantic features;
matching the third semantic features with second semantic features in a second semantic feature database, and determining a second number of successfully matched second semantic features;
converting the third semantic features into a plurality of negative semantic features and negative-like semantic features based on a preset conversion rule, wherein the negative semantic features and the negative-like semantic features are classified according to the degree of negation;
matching each negative semantic feature with the first semantic features in the first semantic feature database, and determining the third number of successfully matched first semantic features;
matching each negative semantic feature with a second semantic feature in a second semantic feature database, and determining a fourth number of successfully matched second semantic features;
matching each negative semantic feature with a first semantic feature in a first semantic feature database, and determining a fifth number of successfully matched first semantic features;
matching each negative semantic feature with a second semantic feature in a second semantic feature database, and determining a sixth number of successfully matched second semantic features;
Calculating a judgment index based on the first number, the second number, the third number, the fourth number, the fifth number and the sixth number, wherein the calculation formula is as follows:
wherein, gamma is the judgment index, alpha 1 For the first number, alpha 2 For the second number, alpha 3,i For the third number of the first semantic features successfully matched with the ith negative semantic feature in the first semantic feature database, alpha 4,i For the fourth number of second semantic features successfully matched with the ith negative semantic feature in the second semantic feature database, alpha 5,i For the fifth number of the first semantic features successfully matched with the ith class of negative semantic features in the first semantic feature database, alpha 6,i For the sixth number, sigma, of second semantic features successfully matched with the ith class of negative semantic features in the second semantic feature database 1,i For the level of negativity, σ, corresponding to the ith negative semantic feature 2,i A level of negation corresponding to the ith class of negation semantic features, n 1 To negate the total number of semantic features, n 2 X is the total number of negative semantic features 1 X is the total number of first semantic features in the first semantic feature database 2 Mu, the total number of second semantic features in the second semantic feature database 1 Sum mu 2 Is a preset weight value theta 1 And theta 2 Is an intermediate variable;
if the judgment index is smaller than or equal to a preset judgment index threshold value, eliminating target data from the important big data;
and after all the target data to be eliminated are eliminated, finishing preprocessing.
The working principle and the beneficial effects of the technical scheme are as follows:
the preset time period is specifically as follows: for example, 30 days; the preset conversion rule specifically comprises the following steps: for example, when target data "recruit job seekers," whether the personal plan accords with the development plan of a company or not "should be emphasized, the third semantic feature" see the personal plan "is converted into a plurality of negative semantic features" do not see the personal plan "," do not matter what the personal plan is not important "and a plurality of negative semantic features" do not matter what the personal plan is not important "," do plan returns to line ", and the like, and the negative degree level of the negative semantic features is larger than the negative level of the negative semantic features; the importance big data comprises a plurality of target data (data issued by a user) and a plurality of acquisition nodes corresponding to the target data one by one (each acquisition node can acquire data about information about a career and a job applicant issued by the user at an external station, and the user needs to provide expert proof, HR working experience proof and the like and account links (for example, homepage links) at the external station when registering); the more the first number of successfully matching the first semantic features and the third semantic features in the first semantic feature database and the second number of successfully matching the second semantic features and the third semantic features in the second semantic feature database, the more the user is informed that the corresponding view of the target data is fixed historically, and the user is not disagreeable; the third number of successful match of the first semantic features in the first semantic feature database, the fourth number of successful match of the first semantic features in the first semantic feature database and the negative-like semantic features, the fifth number of successful match of the second semantic features in the second semantic feature database and the negative-like semantic features, and the sixth number of successful match of the second semantic features in the second semantic feature database and the negative-like semantic features are more, so that the user is not fixed with the corresponding view of the target data historically; calculating a judgment index based on the first number, the second number, the third number, the fourth number, the fifth number and the sixth number, and summarizing judgment results, wherein the larger the judgment index is, the more the user historically, the more firm the corresponding point of view of the target data is, and when the judgment index is smaller than or equal to a preset judgment index threshold (for example, 97), the corresponding target data is eliminated;
The method and the device for determining the target data of the website according to the embodiment of the invention aim to determine whether the user publishes the data about which information is completely inconsistent or approximately inconsistent with the website corresponding to the acquisition path at the external station, if so, the target data published by the user cannot be determined in a real mode, and the possibility of randomly publishing the data exists, the data can be removed, the utilization value of important big data is improved, the method and the device are quite intelligent, meanwhile, the judgment index can be rapidly given through the formula, the judgment result is directly given by comparing the judgment index with the threshold value, and the working efficiency of the system is greatly improved.
The embodiment of the invention provides a cloud customization recruitment method, which comprises the steps of preprocessing job hunting information and recruitment information before matching the job hunting information with the recruitment information;
the preprocessing of job hunting information and recruitment information comprises the following steps:
acquiring first meeting information of job seeker, wherein the first meeting information comprises: historically, the job seeker referred to a first record of the recruitment;
acquiring second meeting information of the enterprise user, wherein the second meeting information comprises: a second record of the enterprise user participating in the recruitment historically;
determining a seventh number of the first record and the second record having the same record;
The masking index is calculated based on the seventh number, and the calculation formula is as follows:
wherein beta is the shielding index, d 1 D is the total number of first records in the first reference information 2 Z is a seventh number, which is the total number of second records in the second reference information;
and if the shielding index is greater than or equal to a preset shielding index threshold value, not matching the corresponding job hunting information and recruitment information.
The working principle and the beneficial effects of the technical scheme are as follows:
the larger the seventh number is, the more times that the job-seeking user corresponding to the job-seeking information and the enterprise user corresponding to the recruitment information see the same recruitment are indicated; calculating a shielding index based on the seventh number, wherein the larger the shielding index is, the more the job hunting information and the recruitment information are not required to be matched; the preset shielding index threshold value is specifically: for example 75.
The method and the device can identify the job seeker and the enterprise user which frequently see the same recruitment, do not match the job seeker information with the recruitment information, and are reasonable in arrangement.
The embodiment of the invention provides a cloud customization recruitment system, which is applied to a cloud server, as shown in fig. 2, wherein the cloud server comprises:
the customization and broadcasting module 1 is used for customizing a recruitment and broadcasting a preset first questionnaire and a preset second questionnaire corresponding to the recruitment;
The acquisition module 2 is used for respectively acquiring job seeking information filled in by a job seeking user based on a preset first questionnaire and recruitment information filled in by an enterprise user based on a preset second questionnaire;
the matching module 3 is used for matching the job hunting information with the recruitment information and determining target job hunting information and target recruitment information which are successfully matched;
and the pushing module 4 is used for pushing the target job hunting information to the enterprise user corresponding to the target recruitment information and pushing the target recruitment information to the job hunting user corresponding to the target job hunting information.
The working principle and the beneficial effects of the technical scheme are as follows:
customizing recruitment (such as time, place and interview mode), broadcasting a preset first questionnaire (a questionnaire filled by a job-required person and comprising a plurality of filling items such as names, ages, academies, hobbies, family backgrounds, working experiences and the like) and a preset second questionnaire (a questionnaire filled by an enterprise HR and comprising a plurality of filling items such as age requirements, academies requirements, working experience requirements and the like); each user views two questionnaires of the recruitment through a network terminal (a mobile phone, a computer, a tablet and the like), the questionnaires are marked with information (time, place and interview mode) of the recruitment, and after confirmation of participation, the corresponding questionnaires are selected for filling; matching the job hunting information with the recruitment information, determining any group of successfully matched target job hunting information and target recruitment information, pushing the target recruitment information to the corresponding job hunting users for viewing, and pushing the target job hunting information to the corresponding enterprise users for viewing.
According to the embodiment of the invention, the information butt joint of the job seeker and the recruitment enterprise is realized through the cloud server, the recruitment enterprise can be helped to grasp the job seeker information of participating in the recruitment in advance, whether the talents needed by the enterprise exist in the job seeker of participating in the recruitment or not is accurately judged, and the talent effect of participating in the recruitment is predicted, so that the enterprise is helped to judge whether the recruitment is needed to participate in, the convenience of the enterprise in understanding talent conditions is improved, the job seeker can be helped to know the enterprise information suitable for the job seeker in advance, and the convenience of the job seeker in understanding the enterprise is improved.
The embodiment of the invention provides a cloud customization recruitment system, and a matching module 3 executes the following operations:
acquiring a preset matching task set, and selecting any matching task from the matching task set;
respectively acquiring importance data through a plurality of preset acquisition paths, and integrating the importance data to acquire importance big data;
determining an importance value of the matching task based on the importance big data;
sequencing all matching tasks in the matching task set from large to small based on the corresponding importance values to obtain a target matching task set;
selecting target matching tasks from the target matching task set according to a preset sequence;
Respectively extracting first to-be-matched information corresponding to a target matching task in job hunting information and second to-be-matched information corresponding to the target matching task in recruitment information;
matching the first information to be matched with the second information to be matched based on an information matching technology to obtain a first matching value;
if the first matching value is greater than or equal to a preset matching value threshold, the execution result of the target matching task is that the matching is successful, otherwise, the matching is failed;
if the execution results of the target matching tasks of the previous preset number in the target matching task set are successful in matching, the job hunting information and the recruitment information are successfully matched, otherwise, the matching is failed.
The working principle and the beneficial effects of the technical scheme are as follows:
the preset matching task set specifically comprises the following steps: a plurality of matching tasks, for example: work experience item matching tasks, academic item matching tasks, interest item matching tasks and the like; the preset plurality of acquisition paths specifically include: connecting with a plurality of forum websites (such as recruitment communication forums, HR communication forums and the like), acquiring importance data (such as data about information about a job seeker in recruitment skill articles published by each authentication expert on a certain HR communication forum) through the acquisition path, and integrating (such as time sequence combination) all the importance data to acquire importance big data; determining the importance value of each matching task based on the importance big data, wherein the larger the importance value is, which indicates that certain information of job seekers is required to be matched with enterprise requirements, and sequencing each matching task from big to small based on the corresponding importance value to obtain a target matching task set; selecting target matching tasks according to a preset sequence (preferentially selecting the top item); executing the target matching task, and when the execution results of the current preset number (for example, 8) of target matching tasks are all successful in matching, indicating that the important part of job-seeking information of the job seeker accords with the enterprise, and the matching is successful; the preset matching degree threshold value is specifically: for example, 95.5.
When the matching tasks are executed, the important value of each matching task is determined, the tasks with larger important values are preferentially executed, and when the matching tasks with the front important values are successfully executed, the important part of job hunting information of the job seeker can be indicated to be consistent with the enterprise, the other matching tasks with lower important values do not need to be executed continuously, the working efficiency of the system is improved, and a large amount of time is saved.
The embodiment of the invention provides a cloud customization recruitment system, and a matching module 3 executes the following operations:
preprocessing the importance big data to obtain target big data;
determining associated data associated with the matching task in the target big data;
determining the proportion of the associated data in the target big data;
the scale is taken as an important value of the matching task.
The working principle and the beneficial effects of the technical scheme are as follows:
the larger the proportion of the associated data corresponding to the matching task in the target big data is, the more users (such as an authentication expert, a senior HR and the like) consider that the information item (such as a life planning) corresponding to the matching task accords with the enterprise requirement, and therefore the proportion is taken as an important value.
The embodiment of the invention takes the proportion of the associated data in the target big data as an important value, and is reasonable in setting.
The embodiment of the invention provides a cloud customization recruitment system, and a matching module 3 executes the following operations:
analyzing the importance big data to obtain a plurality of target data and a plurality of acquisition nodes corresponding to the target data one by one;
acquiring verification data by each acquisition node, integrating the verification data to obtain verification big data, wherein the verification big data comprises: a plurality of historical data that a user who published the target data published historically;
determining the target moment when the user issues target data;
determining a plurality of historical data which are released by a user in a preset time period before a target moment in verification big data, and integrating the historical data into first historical big data;
determining a plurality of historical data released by a user in a preset time period after a target moment in the verification big data, and integrating the historical data into second historical big data;
identifying the first historical big data based on a semantic identification technology to obtain a plurality of first semantic features, and constructing a first semantic feature database based on each first semantic feature;
identifying the second historical big data based on a semantic identification technology to obtain a plurality of second semantic features, and constructing a second semantic feature database based on each second semantic feature;
Identifying the target data based on a semantic identification technology to obtain a third semantic feature;
matching the third semantic features with the first semantic features in the first semantic feature database, and determining the first number of successfully matched first semantic features;
matching the third semantic features with second semantic features in a second semantic feature database, and determining a second number of successfully matched second semantic features;
converting the third semantic features into a plurality of negative semantic features and negative-like semantic features based on a preset conversion rule, wherein the negative semantic features and the negative-like semantic features are classified according to the degree of negation;
matching each negative semantic feature with the first semantic features in the first semantic feature database, and determining the third number of successfully matched first semantic features;
matching each negative semantic feature with a second semantic feature in a second semantic feature database, and determining a fourth number of successfully matched second semantic features;
matching each negative semantic feature with a first semantic feature in a first semantic feature database, and determining a fifth number of successfully matched first semantic features;
matching each negative semantic feature with a second semantic feature in a second semantic feature database, and determining a sixth number of successfully matched second semantic features;
Calculating a judgment index based on the first number, the second number, the third number, the fourth number, the fifth number and the sixth number, wherein the calculation formula is as follows:
wherein, gamma is the judgment index, alpha 1 For the first number, alpha 2 For the second number, alpha 3,i For the third number of the first semantic features successfully matched with the ith negative semantic feature in the first semantic feature database, alpha 4,i For the fourth number of second semantic features successfully matched with the ith negative semantic feature in the second semantic feature database, alpha 5,i For the fifth number of the first semantic features successfully matched with the ith class of negative semantic features in the first semantic feature database, alpha 6,i For the sixth number, sigma, of second semantic features successfully matched with the ith class of negative semantic features in the second semantic feature database 1,i For the level of negativity, σ, corresponding to the ith negative semantic feature 2,i A level of negation corresponding to the ith class of negation semantic features, n 1 To negate the total number of semantic features, n 2 X is the total number of negative semantic features 1 X is the total number of first semantic features in the first semantic feature database 2 Mu, the total number of second semantic features in the second semantic feature database 1 Sum mu 2 Is a preset weight value theta 1 And theta 2 Is an intermediate variable;
if the judgment index is smaller than or equal to a preset judgment index threshold value, eliminating target data from the important big data;
and after all the target data to be eliminated are eliminated, finishing preprocessing.
The working principle and the beneficial effects of the technical scheme are as follows:
the preset time period is specifically as follows: for example, 30 days; the preset conversion rule specifically comprises the following steps: for example, when target data "recruit job seekers," whether the personal plan accords with the development plan of a company or not "should be emphasized, the third semantic feature" see the personal plan "is converted into a plurality of negative semantic features" do not see the personal plan "," do not matter what the personal plan is not important "and a plurality of negative semantic features" do not matter what the personal plan is not important "," do plan returns to line ", and the like, and the negative degree level of the negative semantic features is larger than the negative level of the negative semantic features; the importance big data comprises a plurality of target data (data issued by a user) and a plurality of acquisition nodes corresponding to the target data one by one (each acquisition node can acquire data about information about a career and a job applicant issued by the user at an external station, and the user needs to provide expert proof, HR working experience proof and the like and account links (for example, homepage links) at the external station when registering); the more the first number of successfully matching the first semantic features and the third semantic features in the first semantic feature database and the second number of successfully matching the second semantic features and the third semantic features in the second semantic feature database, the more the user is informed that the corresponding view of the target data is fixed historically, and the user is not disagreeable; the third number of successful match of the first semantic features in the first semantic feature database, the fourth number of successful match of the first semantic features in the first semantic feature database and the negative-like semantic features, the fifth number of successful match of the second semantic features in the second semantic feature database and the negative-like semantic features, and the sixth number of successful match of the second semantic features in the second semantic feature database and the negative-like semantic features are more, so that the user is not fixed with the corresponding view of the target data historically; calculating a judgment index based on the first number, the second number, the third number, the fourth number, the fifth number and the sixth number, and summarizing judgment results, wherein the larger the judgment index is, the more the user historically, the more firm the corresponding point of view of the target data is, and when the judgment index is smaller than or equal to a preset judgment index threshold (for example, 97), the corresponding target data is eliminated;
The method and the device for determining the target data of the website according to the embodiment of the invention aim to determine whether the user publishes the data about which information is completely inconsistent or approximately inconsistent with the website corresponding to the acquisition path at the external station, if so, the target data published by the user cannot be determined in a real mode, and the possibility of randomly publishing the data exists, the data can be removed, the utilization value of important big data is improved, the method and the device are quite intelligent, meanwhile, the judgment index can be rapidly given through the formula, the judgment result is directly given by comparing the judgment index with the threshold value, and the working efficiency of the system is greatly improved.
The embodiment of the invention provides a cloud customization recruitment system, and a cloud server further comprises:
the preprocessing module is used for preprocessing the job hunting information and the recruitment information before matching the job hunting information with the recruitment information;
the preprocessing module performs the following operations:
acquiring first meeting information of job seeker, wherein the first meeting information comprises: historically, the job seeker referred to a first record of the recruitment;
acquiring second meeting information of the enterprise user, wherein the second meeting information comprises: a second record of the enterprise user participating in the recruitment historically;
Determining a seventh number of the first record and the second record having the same record;
the masking index is calculated based on the seventh number, and the calculation formula is as follows:
wherein beta is the shielding index, d 1 D is the total number of first records in the first reference information 2 Z is a seventh number, which is the total number of second records in the second reference information;
and if the shielding index is greater than or equal to a preset shielding index threshold value, not matching the corresponding job hunting information and recruitment information.
The working principle and the beneficial effects of the technical scheme are as follows:
the larger the seventh number is, the more times that the job-seeking user corresponding to the job-seeking information and the enterprise user corresponding to the recruitment information see the same recruitment are indicated; calculating a shielding index based on the seventh number, wherein the larger the shielding index is, the more the job hunting information and the recruitment information are not required to be matched; the preset shielding index threshold value is specifically: for example 75.
The method and the device can identify the job seeker and the enterprise user which frequently see the same recruitment, do not match the job seeker information with the recruitment information, and are reasonable in arrangement.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (4)
1. The cloud customization recruitment method is applied to a cloud server and is characterized by comprising the following steps of:
customizing a recruitment, and broadcasting a preset first questionnaire and a preset second questionnaire corresponding to the recruitment;
respectively acquiring job seeking information filled in by a job seeking user based on the preset first questionnaire and recruitment information filled in by an enterprise user based on the preset second questionnaire;
matching the job hunting information with the recruitment information, and determining target job hunting information and target recruitment information which are successfully matched;
pushing the target job hunting information to the enterprise user corresponding to the target recruitment information, and pushing the target recruitment information to the job hunting user corresponding to the target job hunting information;
matching the job hunting information with the recruitment information includes:
acquiring a preset matching task set, and selecting any matching task from the matching task set;
respectively acquiring importance data through a plurality of preset acquisition paths, and integrating the importance data to acquire importance big data;
determining an importance value of the matching task based on the importance big data;
sequencing all the matching tasks in the matching task set from large to small based on the corresponding importance values to obtain a target matching task set;
Selecting target matching tasks from the target matching task set according to a preset sequence;
respectively extracting first to-be-matched information corresponding to the target matching task in the job hunting information and second to-be-matched information corresponding to the target matching task in the recruitment information;
matching the first information to be matched with the second information to be matched based on an information matching technology to obtain a first matching value;
if the first matching value is greater than or equal to a preset matching value threshold, the execution result of the target matching task is that the matching is successful, otherwise, the matching is failed;
if the execution results of the target matching tasks of the previous preset number in the target matching task set are successful in matching, the job hunting information and the recruitment information are successfully matched, otherwise, the matching is failed;
determining an importance value of the matching task based on the importance big data, including:
preprocessing the importance big data to obtain target big data;
determining associated data associated with the matching task in the target big data;
determining the proportion of the associated data in the target big data;
taking the proportion as an important value of the matching task;
Preprocessing the importance big data, including;
analyzing the importance big data to obtain a plurality of target data and a plurality of acquisition nodes corresponding to the target data one by one;
acquiring verification data through each acquisition node, and integrating the verification data to obtain verification big data, wherein the verification big data comprises the following components: a plurality of historical data historically published by a user who published the target data;
determining a target moment when the user issues the target data;
determining a plurality of historical data published by the user in a preset time period before the target moment in the verification big data, and integrating the historical data into first historical big data;
determining a plurality of historical data published by the user in a preset time period after the target moment in the verification big data, and integrating the historical data into second historical big data;
identifying the first historical big data based on a semantic identification technology to obtain a plurality of first semantic features, and constructing a first semantic feature database based on each first semantic feature;
identifying the second historical big data based on a semantic identification technology to obtain a plurality of second semantic features, and constructing a second semantic feature database based on each second semantic feature;
Identifying the target data based on a semantic identification technology to obtain a third semantic feature;
matching the third semantic features with the first semantic features in the first semantic feature database, and determining the first number of the first semantic features successfully matched;
matching the third semantic features with the second semantic features in the second semantic feature database, and determining a second number of the second semantic features successfully matched;
converting the third semantic features into a plurality of negative semantic features and negative-like semantic features based on a preset conversion rule, wherein the negative semantic features and the negative-like semantic features are classified according to a negative degree level;
matching each negative semantic feature with the first semantic feature in the first semantic feature database, and determining a third number of successfully matched first semantic features;
matching each negative semantic feature with the second semantic feature in the second semantic feature database, and determining a fourth number of the second semantic features successfully matched;
matching each negative semantic feature with the first semantic feature in the first semantic feature database, and determining a fifth number of the first semantic features successfully matched;
Matching each negative semantic feature with the second semantic feature in the second semantic feature database, and determining a sixth number of the second semantic features successfully matched;
calculating a judgment index based on the first number, the second number, the third number, the fourth number, the fifth number and the sixth number, wherein the calculation formula is as follows:
wherein gamma is the said decision index, alpha 1 For the first number, α 2 For the second number, α 3,i For said third number, α, of said first semantic features in said first semantic feature database that successfully matches an ith said negative semantic feature 4,i For said fourth number, α, of said second semantic features in said second semantic feature database that successfully matches an ith said negative semantic feature 5,i For the fifth number, alpha, of the first semantic features successfully matched with the ith negative-like semantic feature in the first semantic feature database 6,i For said sixth number, σ, of said second semantic features in said second semantic feature database that successfully matches an ith said negative-like semantic feature 1,i For the level of negation corresponding to the ith negative semantic feature, σ 2,i Negation semantics for the ith classThe negative degree grade corresponding to the characteristic, n 1 N, the total number of negative semantic features 2 X is the total number of the negative semantic features 1 X is the total number of the first semantic features in the first semantic feature database 2 Mu, the total number of the second semantic features in the second semantic feature database 1 Sum mu 2 Is a preset weight value theta 1 And theta 2 Is an intermediate variable;
if the judgment index is smaller than or equal to a preset judgment index threshold value, eliminating the target data from the important big data;
and finishing preprocessing after all the target data to be eliminated are eliminated.
2. The cloud customized recruitment method of claim 1, wherein the job hunting information and the recruitment information are preprocessed prior to matching the job hunting information with the recruitment information;
the preprocessing of the job hunting information and the recruitment information comprises the following steps:
acquiring first meeting information of the job hunting user, wherein the first meeting information comprises: historically the job seeker referred to a first record of recruitment;
acquiring second meeting information of the enterprise user, wherein the second meeting information comprises: a second record of the enterprise user historically participating in a recruitment;
Determining a seventh number of the first record and the second record having the same record;
and calculating a shielding index based on the seventh number, wherein the calculation formula is as follows:
wherein beta is the shielding index, d 1 D, the total number of the first records in the first reference information 2 Is saidThe total number of the second records in the second reference information, Z is the seventh number;
and if the shielding index is greater than or equal to a preset shielding index threshold, not matching the job hunting information and the recruitment information.
3. The utility model provides a cloud custom recruitment system, is applied to high in the clouds server, its characterized in that, high in the clouds server includes:
the customization and broadcasting module is used for customizing a recruitment and broadcasting a preset first questionnaire and a preset second questionnaire corresponding to the recruitment;
the acquisition module is used for respectively acquiring job seeking information filled in by a job seeking user based on the preset first questionnaire and recruitment information filled in by an enterprise user based on the preset second questionnaire;
the matching module is used for matching the job hunting information with the recruitment information and determining target job hunting information and target recruitment information which are successfully matched;
the pushing module is used for pushing the target job hunting information to the enterprise user corresponding to the target recruitment information and pushing the target recruitment information to the job hunting user corresponding to the target job hunting information;
The matching module performs the following operations:
acquiring a preset matching task set, and selecting any matching task from the matching task set;
respectively acquiring importance data through a plurality of preset acquisition paths, and integrating the importance data to acquire importance big data;
determining an importance value of the matching task based on the importance big data;
sequencing all the matching tasks in the matching task set from large to small based on the corresponding importance values to obtain a target matching task set;
selecting target matching tasks from the target matching task set according to a preset sequence;
respectively extracting first to-be-matched information corresponding to the target matching task in the job hunting information and second to-be-matched information corresponding to the target matching task in the recruitment information;
matching the first information to be matched with the second information to be matched based on an information matching technology to obtain a first matching value;
if the first matching value is greater than or equal to a preset matching value threshold, the execution result of the target matching task is that the matching is successful, otherwise, the matching is failed;
if the execution results of the target matching tasks of the previous preset number in the target matching task set are successful in matching, the job hunting information and the recruitment information are successfully matched, otherwise, the matching is failed;
The matching module performs the following operations:
preprocessing the importance big data to obtain target big data;
determining associated data associated with the matching task in the target big data;
determining the proportion of the associated data in the target big data;
taking the proportion as an important value of the matching task;
the matching module performs the following operations:
analyzing the importance big data to obtain a plurality of target data and a plurality of acquisition nodes corresponding to the target data one by one;
acquiring verification data through each acquisition node, and integrating the verification data to obtain verification big data, wherein the verification big data comprises the following components: a plurality of historical data historically published by a user who published the target data;
determining a target moment when the user issues the target data;
determining a plurality of historical data published by the user in a preset time period before the target moment in the verification big data, and integrating the historical data into first historical big data;
determining a plurality of historical data published by the user in a preset time period after the target moment in the verification big data, and integrating the historical data into second historical big data;
Identifying the first historical big data based on a semantic identification technology to obtain a plurality of first semantic features, and constructing a first semantic feature database based on each first semantic feature;
identifying the second historical big data based on a semantic identification technology to obtain a plurality of second semantic features, and constructing a second semantic feature database based on each second semantic feature;
identifying the target data based on a semantic identification technology to obtain a third semantic feature;
matching the third semantic features with the first semantic features in the first semantic feature database, and determining the first number of the first semantic features successfully matched;
matching the third semantic features with the second semantic features in the second semantic feature database, and determining a second number of the second semantic features successfully matched;
converting the third semantic features into a plurality of negative semantic features and negative-like semantic features based on a preset conversion rule, wherein the negative semantic features and the negative-like semantic features are classified according to a negative degree level;
matching each negative semantic feature with the first semantic feature in the first semantic feature database, and determining a third number of successfully matched first semantic features;
Matching each negative semantic feature with the second semantic feature in the second semantic feature database, and determining a fourth number of the second semantic features successfully matched;
matching each negative semantic feature with the first semantic feature in the first semantic feature database, and determining a fifth number of the first semantic features successfully matched;
matching each negative semantic feature with the second semantic feature in the second semantic feature database, and determining a sixth number of the second semantic features successfully matched;
calculating a judgment index based on the first number, the second number, the third number, the fourth number, the fifth number and the sixth number, wherein the calculation formula is as follows:
wherein gamma is the said decision index, alpha 1 For the first number, α 2 For the second number, α 3,i For said third number, α, of said first semantic features in said first semantic feature database that successfully matches an ith said negative semantic feature 4,i For said fourth number, α, of said second semantic features in said second semantic feature database that successfully matches an ith said negative semantic feature 5,i For the fifth number, alpha, of the first semantic features successfully matched with the ith negative-like semantic feature in the first semantic feature database 6,i For said sixth number, σ, of said second semantic features in said second semantic feature database that successfully matches an ith said negative-like semantic feature 1,i For the level of negation corresponding to the ith negative semantic feature, σ 2,i For the level of negation degree corresponding to the ith negative-like semantic feature, n 1 N, the total number of negative semantic features 2 X is the total number of the negative semantic features 1 X is the total number of the first semantic features in the first semantic feature database 2 Is the total number of the second semantic features in the second semantic feature database,μ 1 Sum mu 2 Is a preset weight value theta 1 And theta 2 Is an intermediate variable;
if the judgment index is smaller than or equal to a preset judgment index threshold value, eliminating the target data from the important big data;
and finishing preprocessing after all the target data to be eliminated are eliminated.
4. The cloud customized recruitment system of claim 3, wherein the cloud server further comprises:
The preprocessing module is used for preprocessing the job hunting information and the recruitment information before the job hunting information and the recruitment information are matched;
the preprocessing module performs the following operations:
acquiring first meeting information of the job hunting user, wherein the first meeting information comprises: historically the job seeker referred to a first record of recruitment;
acquiring second meeting information of the enterprise user, wherein the second meeting information comprises: a second record of the enterprise user historically participating in a recruitment;
determining a seventh number of the first record and the second record having the same record;
and calculating a shielding index based on the seventh number, wherein the calculation formula is as follows:
wherein beta is the shielding index, d 1 D, the total number of the first records in the first reference information 2 Z is the seventh number for the total number of the second records in the second reference information;
and if the shielding index is greater than or equal to a preset shielding index threshold, not matching the job hunting information and the recruitment information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110910036.3A CN113627883B (en) | 2021-08-09 | 2021-08-09 | Cloud customization recruitment method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110910036.3A CN113627883B (en) | 2021-08-09 | 2021-08-09 | Cloud customization recruitment method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113627883A CN113627883A (en) | 2021-11-09 |
CN113627883B true CN113627883B (en) | 2023-06-27 |
Family
ID=78383734
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110910036.3A Active CN113627883B (en) | 2021-08-09 | 2021-08-09 | Cloud customization recruitment method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113627883B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112102133A (en) * | 2020-11-16 | 2020-12-18 | 深圳市易博天下科技有限公司 | Efficient recruitment method, device and system based on information delivery and electronic equipment |
CN112445979A (en) * | 2020-12-29 | 2021-03-05 | 普工宝网络科技(重庆)有限公司 | Talent information intelligent matching method and system |
CN112749951A (en) * | 2021-01-18 | 2021-05-04 | 南京可宇科技有限公司 | Human resource intelligent matching management system based on multivariate data analysis |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101826174A (en) * | 2009-03-02 | 2010-09-08 | 一零四管理顾问股份有限公司 | System for evaluating employers and consulting on job-seeking website and method thereof |
CN106447239B (en) * | 2016-11-21 | 2020-09-29 | 北京字节跳动科技有限公司 | Data release auditing method and device |
CN108734445A (en) * | 2018-05-24 | 2018-11-02 | 佛山市轻遣网络有限公司 | A kind of recruitment management system and method |
CN109918638B (en) * | 2018-12-05 | 2023-03-24 | 国网浙江桐乡市供电有限公司 | Network data monitoring method |
CN109684441A (en) * | 2018-12-21 | 2019-04-26 | 义橙网络科技(上海)有限公司 | Matched method, system, equipment and medium are carried out to position and resume |
CN111833019A (en) * | 2020-07-15 | 2020-10-27 | 北京亮马手信息咨询有限公司 | Cloud customization recruitment method and system |
-
2021
- 2021-08-09 CN CN202110910036.3A patent/CN113627883B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112102133A (en) * | 2020-11-16 | 2020-12-18 | 深圳市易博天下科技有限公司 | Efficient recruitment method, device and system based on information delivery and electronic equipment |
CN112445979A (en) * | 2020-12-29 | 2021-03-05 | 普工宝网络科技(重庆)有限公司 | Talent information intelligent matching method and system |
CN112749951A (en) * | 2021-01-18 | 2021-05-04 | 南京可宇科技有限公司 | Human resource intelligent matching management system based on multivariate data analysis |
Also Published As
Publication number | Publication date |
---|---|
CN113627883A (en) | 2021-11-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Schumann et al. | We need fairness and explainability in algorithmic hiring | |
Yeh | A problem‐based selection of multi‐attribute decision‐making methods | |
US11176154B1 (en) | Collaborative dataset management system for machine learning data | |
Chandler et al. | Risks and rewards of crowdsourcing marketplaces | |
CN103761254B (en) | Method for matching and recommending service themes in various fields | |
US20160335603A1 (en) | Evaluating service providers using a social network | |
CN109558530A (en) | User's portrait automatic generation method and system based on data processing | |
US20100324970A1 (en) | System and Method For Intelligent Job Hunt | |
Jung et al. | Real-time data-driven discrete-event simulation for garment production lines | |
CN107993019B (en) | Resume evaluation method and device | |
CN109584094B (en) | Interpersonal path rapid positioning system, method and medium | |
CN111737485A (en) | Human-sentry matching method and human-sentry matching system based on knowledge graph and deep learning | |
CN111833019A (en) | Cloud customization recruitment method and system | |
CN113934868A (en) | Government affair big data management method and system | |
CN111738778B (en) | User portrait generation method and device, computer equipment and storage medium | |
Appadoo et al. | Job recommendation system, machine learning, regression, classification, natural language processing | |
CN113592036A (en) | Flow cheating behavior identification method and device, storage medium and electronic equipment | |
CN108182512B (en) | Resume evaluation method and device | |
CN112052310A (en) | Information acquisition method, device, equipment and storage medium based on big data | |
CN113627883B (en) | Cloud customization recruitment method and system | |
CN109992592B (en) | College poverty and poverty identification method based on flow data of campus consumption card | |
McKenna et al. | Reconceptualising project management methodologies for a post-postmodern era | |
US20160217216A1 (en) | Systems, methods, and devices for implementing a referral search | |
CN116452165A (en) | Talent information recommendation method, service system and storage medium | |
CN108182513B (en) | Resume evaluation method and device |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |