CN112288391A - Interval matching-based method and system for matching human posts - Google Patents
Interval matching-based method and system for matching human posts Download PDFInfo
- Publication number
- CN112288391A CN112288391A CN202011171084.7A CN202011171084A CN112288391A CN 112288391 A CN112288391 A CN 112288391A CN 202011171084 A CN202011171084 A CN 202011171084A CN 112288391 A CN112288391 A CN 112288391A
- Authority
- CN
- China
- Prior art keywords
- characteristic
- matched
- capability
- matching degree
- matching
- 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 51
- 238000012163 sequencing technique Methods 0.000 claims abstract description 17
- 238000007405 data analysis Methods 0.000 claims abstract description 6
- 238000012216 screening Methods 0.000 claims description 27
- 238000013139 quantization Methods 0.000 claims description 5
- 238000010191 image analysis Methods 0.000 claims description 2
- 238000012549 training Methods 0.000 abstract description 9
- 238000012545 processing Methods 0.000 abstract description 8
- 238000011156 evaluation Methods 0.000 description 15
- 238000005516 engineering process Methods 0.000 description 6
- 238000007726 management method Methods 0.000 description 6
- 238000001914 filtration Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000002262 irrigation Effects 0.000 description 3
- 238000003973 irrigation Methods 0.000 description 3
- 238000012937 correction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000005192 partition Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 230000000717 retained effect 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a method and a system for matching a human sentry based on interval matching, and belongs to the technical field of big data analysis and processing. Firstly, acquiring a characteristic image set of an object to be matched, wherein the characteristic image set of the object to be matched comprises N characteristic images of the object to be matched, and N is an integer more than or equal to 2; secondly, acquiring a characteristic image of the target object; then acquiring the comprehensive matching degree of the characteristic images of the target object and the characteristic images of M objects to be matched in the characteristic image set of the objects to be matched, wherein M is an integer not less than 1, and M is not more than N; and finally, sequencing the M comprehensive matching degrees, and performing post matching according to a sequencing result. Under the support of a big data method, the speed and the efficiency of the people post matching are effectively improved, the accuracy of the people post matching is improved, and big data support is provided for managers in aspects of post-to-post people selection, post-to-person people selection, personnel education and training and the like.
Description
Technical Field
The invention belongs to the technical field of big data analysis and processing, and particularly relates to a method and a system for a human sentry matching based on interval matching.
Background
The core of human resource management is that the resource allocation is effective, and the human-job matching is the basis for the effective allocation and reasonable use of human resources. Particularly, in the process of managing the post matching of the personnel in the enterprise, the bidirectional adaptation between the personnel and the post is realized, the continuous cultivation of the personnel is also realized so as to adapt to the post requirement, or the mutual competition between the personnel and the post is promoted so that the personnel can be more suitable for the post requirement.
The existing sentry matching theory comprises a Holland occupational theory, a Rocky value classification and an iceberg diathesis model, and although the theories are widely applied, the theories all use the subjective thought of a manager as a prerequisite condition, and the following problems mainly exist:
the subjective thought of the excessive human-guard matching process is mixed, so that the human-guard matching degree is low;
when the post is used for selecting, all objects meeting the conditions cannot be selected fairly, and selection omission or selection mistake is easy to occur;
when people select the post, the personal tendency is considered too much, and the capability requirement of the post is ignored;
it is difficult to provide guidance in targeted training of talents and in human-to-human competition.
Disclosure of Invention
Based on this, it is necessary to provide a human sentry matching method and system based on interval matching by taking big data analysis as a main means, aiming at the technical problems of strong subjectivity, low matching degree and difficulty in meeting the requirement of human resource management in the prior art.
The technical scheme adopted by the invention for solving the technical problems is as follows:
on one hand, the invention provides a method for matching the human sentry based on interval matching, which comprises the following steps:
acquiring a characteristic image set of an object to be matched, wherein the characteristic image set of the object to be matched comprises N characteristic images of the object to be matched, and N is an integer more than or equal to 2;
acquiring a characteristic image of a target object;
acquiring the comprehensive matching degree of the characteristic images of the target object and the characteristic images of M objects to be matched in the characteristic image set of the objects to be matched, wherein M is an integer not less than 1, and M is not more than N;
sequencing the M comprehensive matching degrees;
and performing the people's post matching according to the sorting result.
Preferably, the step of "obtaining a comprehensive matching degree between the feature images of the target object and the feature images of the M objects to be matched in the feature image set of the object to be matched, where M is an integer no less than 1 and M is no greater than N", includes the steps of:
reading a first characteristic factor in the characteristic image of the target object;
quantizing the first characteristic factor;
reading second characteristic factors in the characteristic images of the N objects to be matched;
quantizing the second characteristic factor;
comparing the first characteristic factor to the second characteristic factor;
screening M according to the comparison result and the set screening conditions1The characteristic images of the objects to be matched are taken as a characteristic image set of a preselected object to be matched, wherein M is1Is an integer of 1 or more, and M1≥M;
Acquiring the characteristic image of the target object and M in the characteristic image set of the preselected object to be matched1And the comprehensive matching degree of the characteristic portrait of the object to be matched.
Preferably, the step of "obtaining a comprehensive matching degree between the feature images of the target object and the feature images of the M objects to be matched in the feature image set of the object to be matched, where M is an integer no less than 1 and M is no greater than N", further includes the steps of:
reading a first capability label in the characteristic image of the target object;
reading M1A second capability label in the characteristic image set of the preselected object to be matched;
Obtaining the first capability tag and M1A capability matching degree of each second capability label;
comparing M according to the threshold condition of the set capability matching degree1The capability matching degree of the first capability label and the second capability label is equal to a capability matching degree threshold value;
according to the comparison result, screening out M2The characteristic images of the objects to be matched are taken as a characteristic image set of two objects to be matched, wherein M is2Is an integer of 1 or more, and M1≥M2≥M。
Preferably, the step of "obtaining said first capability tag and M1In the comprehensive matching degree of the second capability label, the first capability label and the M are obtained through text data analysis or image analysis1A capability matching degree of each second capability label.
Preferably, the step of "obtaining a comprehensive matching degree between the feature images of the target object and the feature images of the M objects to be matched in the feature image set of the object to be matched, where M is an integer no less than 1 and M is no greater than N", further includes the steps of:
reading a first character label in the characteristic image of the target object;
reading M2Second character labels in the feature image set of the two selected objects to be matched;
obtaining the first character label and M2A character matching degree of each second character label;
calculating the characteristic image and M of the target object according to the set weight coefficient, the capability matching degree and the character matching degree2And the comprehensive matching degree of the characteristic portrait of the object to be matched.
In another aspect, the present invention provides a human sentry matching system based on interval matching, including:
the talent characteristic image library is used for storing a plurality of talent characteristic images;
the post characteristic image library is used for storing a plurality of post characteristic images;
the system comprises a first acquisition module, a second acquisition module and a matching module, wherein the first acquisition module is used for acquiring a characteristic image set of an object to be matched from the talent characteristic image library or the post characteristic image library, the characteristic image set of the object to be matched comprises N characteristic images of the object to be matched, and N is an integer more than or equal to 2;
the second acquisition module is used for acquiring the characteristic image of the target object from the talent characteristic image library or the post characteristic image library;
the comprehensive matching degree acquisition module is used for acquiring the comprehensive matching degrees of the characteristic images of the target object and the characteristic images of the M objects to be matched in the characteristic image set of the objects to be matched, wherein M is an integer not less than 1, and M is not more than N; and
and the sequencing module is used for sequencing the M comprehensive matching degrees.
Preferably, the comprehensive matching degree obtaining module includes:
a first characteristic factor reading unit for reading a first characteristic factor in a characteristic image of the target object;
a first characteristic factor quantization unit configured to quantize the first characteristic factor;
the second characteristic factor reading unit is used for reading second characteristic factors in the characteristic images of the N objects to be matched;
a second characteristic factor quantization unit, configured to quantize the second characteristic factor;
a first comparing unit for comparing the first characteristic factor with the second characteristic factor;
a first screening unit for screening M according to the comparison result and the set screening condition1The characteristic images of the objects to be matched are taken as a characteristic image set of a preselected object to be matched, wherein M is1Is an integer of 1 or more, and M1More than or equal to M; and
a first comprehensive matching degree obtaining unit, configured to obtain the feature image of the target object and the feature image set of the preselected object to be matchedM1And the comprehensive matching degree of the characteristic portrait of the object to be matched.
Preferably, the comprehensive matching degree obtaining module further includes:
a first capability tag reading unit, configured to read a first capability tag in the feature image of the target object;
a second capability tag reading unit for reading M1A second capability label in the characteristic image set of the preselected object to be matched
A capability matching degree obtaining unit for obtaining the first capability label and M1A capability matching degree of each second capability label;
a second comparison unit for comparing M according to the set threshold condition of capability matching degree1The capability matching degree of the first capability label and the second capability label is equal to a capability matching degree threshold value; and
a second screening unit for screening M according to the comparison result2The characteristic images of the objects to be matched are taken as a characteristic image set of two objects to be matched, wherein M is2Is an integer of 1 or more, and M1≥M2≥M。
Preferably, the comprehensive matching degree obtaining module further includes:
a first character tag reading unit configured to read a first character tag in the feature image of the target object;
a second character tag reading unit for reading M2Second character labels in the feature image set of the two selected objects to be matched;
a character matching degree obtaining unit for obtaining the first character label and M2A character matching degree of each second character label; and
a calculating unit for calculating the characteristic image and M of the target object according to the set weight coefficient, the first ability matching degree and the character matching degree2And comprehensively matching the characteristic images of the objects to be matched.
The invention provides a method and a system for matching a post based on interval matching, which achieve the following technical effects by adopting an interval matching method through a preset talent characteristic image library and a post characteristic image library:
firstly, a post selects people, talent objects with high comprehensive matching degree are obtained in a talent feature portrait base according to the feature portrait of a target post, the obtained feature portraits of the talent objects and the comprehensive matching degree of the feature portraits of the target post are sorted, and the most suitable talent objects are matched for the target post according to the sorting result. The method and the device solve the problems of inaccurate matching and low matching degree caused by large influence of subjective factors in the traditional post matching process. Under the support of a big data method, the personnel and post matching process is accurate and efficient, so that each talent meeting the conditions is effectively verified, and the omission of talent objects is avoided. The man-shift matching process adopts a matching mode between the partitions, so that the man-shift matching speed and efficiency are improved.
And secondly, selecting a post by a person, acquiring a post object with high matching degree in a post feature image library according to the feature image of the target talent, sequencing the acquired feature image of the post object and the comprehensive matching degree of the feature image of the target talent, and matching the most suitable post object for the target talent according to a sequencing result. The invention solves the problems that the talents cannot adapt to the post requirements and use small materials or use small materials because of large influence of subjective factors in the traditional process of arranging posts for the talents. Under the support of a big data method, the post matching process is accurate and efficient, so that each post is traversed, and the most suitable post is avoided being missed. The man-shift matching process adopts a matching mode between the partitions, so that the man-shift matching speed and efficiency are improved.
And thirdly, training and education of people comprises two aspects, on one hand, cultivating people for a certain post pertinently, obtaining the comprehensive matching degree of the characteristic image of the target post and the characteristic image of the target talent according to the characteristic image of the target post and the characteristic image (possibly more than one) of the target talent, analyzing the unmatched reason, and performing targeted training and education on the target talent to provide guidance data for manpower resource education and training. On the other hand, the competition between people is strengthened, and the self-learning and self-progress of the talent subjects are promoted. According to the feature portrait of the target talent, feature portraits of other target talents are obtained from the talent feature portraits library, the comprehensive matching degree of the feature portraits of the target talent and the feature portraits of the other target talents is obtained, and the reason of mismatching is analyzed, so that self-learning of the talent object is promoted, and self-promotion of the talent object provides visual data reference.
Drawings
FIG. 1 is a flowchart of a method for a human sentry matching method based on interval matching in an embodiment.
FIG. 2 is a flowchart of a method for a human sentry matching method based on interval matching in yet another embodiment.
FIG. 3 is a flowchart of a method for a human sentry matching method based on interval matching in another embodiment.
FIG. 4 is a flowchart of a method for a human sentry matching method based on interval matching in yet another embodiment.
FIG. 5 is a block flow diagram of a human sentry matching system based on interval matching.
Detailed Description
To facilitate an understanding of the invention, the invention will now be described more fully hereinafter with reference to the accompanying drawings. The preferred embodiments of the present invention are shown in the drawings and examples, but the present invention may be embodied in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
Referring to fig. 1, in an embodiment, a method for human-job matching based on interval matching includes the following steps:
s100, acquiring a characteristic image set of an object to be matched, wherein the characteristic image set of the object to be matched comprises N characteristic images of the object to be matched, and N is an integer larger than or equal to 2;
s200, acquiring a characteristic image of a target object;
s300, acquiring the comprehensive matching degree of the feature images of the target object and the feature images of M objects to be matched in the feature image set of the objects to be matched, wherein M is an integer larger than or equal to 1, and M is smaller than or equal to N;
s400, sequencing the M comprehensive matching degrees;
and performing the people's post matching according to the sorting result.
Specifically, the talent matching method based on interval matching provided by the invention is realized based on a talent feature image library and a post feature image library which are collected and established in advance.
The talent feature image library comprises a plurality of talent feature images capable of covering all people in a team, and the talent feature images at least comprise basic information labels of personnel (including but not limited to the basic information of the personnel such as name, sex, age, working age, native place, post level and the like), basic capability evaluation labels of the personnel and character evaluation labels of the personnel. The talent characteristic image is stored in a text format (XML or TXT) or a picture format (JPG or PNG), and a background updating inlet is provided so as to correct or update the basic information label, the basic capability evaluation label, the character evaluation label and the like in the talent characteristic image in real time.
The post characteristic image library comprises a plurality of post characteristic images which can cover the post setting of a team, and the post characteristic images at least comprise post requirement index labels (including but not limited to post requirement information such as age distribution, gender, work age distribution, native place distribution, post level distribution and the like of post requirement personnel), post basic capability requirement labels and post character requirement labels. The post characteristic portrait is stored in a text format or a picture format, and a background updating inlet is provided so as to correct or update a demand index label, an instinct demand label, a character demand label and the like in the post characteristic portrait in real time.
Based on the talent feature image library and the post feature image library, the method for matching the posts based on interval matching provided by the embodiment can efficiently and quickly complete post matching operation according to actual human resource management requirements.
Referring to fig. 2, further, to improve matching efficiency and matching accuracy, in one embodiment, the step "obtaining a comprehensive matching degree between the feature images of the target object and the feature images of M to-be-matched objects in the feature image set of the to-be-matched object, where M is an integer greater than or equal to 1 and M is less than or equal to N" includes the following steps:
s311, reading a first characteristic factor in the characteristic image of the target object;
quantizing the first characteristic factor;
s312, reading second characteristic factors in the characteristic images of the N objects to be matched;
quantizing the second characteristic factor;
s313, comparing the first characteristic factor with the second characteristic factor;
s314, screening M according to the comparison result and the set screening condition1The characteristic images of the objects to be matched are taken as a characteristic image set of a preselected object to be matched, wherein M is1Is an integer of 1 or more, and M1≥M;
S315, obtaining the characteristic image of the target object and M in the characteristic image set of the preselected object to be matched1And the comprehensive matching degree of the characteristic portrait of the object to be matched.
In this embodiment, the first and second feature factors are one or more of a basic information tag and a demand indicator tag in a talent feature image or a post feature image. That is, the first and second characteristic factors may be an age field, a work age field, a professional field, a native field, a gender field, a post level field, etc. in a basic information tag or a requirement index tag in a talent feature representation or a post feature representation. Quantizing one or more read fields to form effective data capable of being actually compared or screened, filtering out object characteristic images which do not meet the rigid condition according to the actual comparison or screening result, reserving the object characteristic images which meet the rigid condition as a characteristic image set of a preselected object to be matched, and then obtaining the comprehensive matching degree of the characteristic images of the target object and the object to be matched in the characteristic image set of the preselected object to be matched.
By adopting a one-dimensional screening mode, firstly, a characteristic image set of an object to be matched is screened, the object to be matched which does not meet the requirement is filtered, and the matching accuracy is improved. Meanwhile, a complex matching degree obtaining process or program does not need to be set and executed, and the post matching efficiency is improved.
Referring to fig. 3, further, to improve the matching accuracy, in one embodiment, the step "obtaining a comprehensive matching degree between the feature images of the target object and the M feature images of the object to be matched in the feature image set of the object to be matched," where M is an integer greater than or equal to 1 and M is less than or equal to N "includes the following steps:
s321, reading a first capability label in the characteristic image of the target object;
s322. read M1A second capability label in the characteristic image set of the preselected object to be matched;
s323, acquiring the first capability label and M1A capability matching degree of each second capability label;
s324, comparing M according to the set threshold condition of the capability matching degree1The capability matching degree of the first capability label and the second capability label is equal to a capability matching degree threshold value;
s325, screening out M according to the comparison result2The characteristic images of the objects to be matched are taken as a characteristic image set of two objects to be matched, wherein M is2Is an integer of 1 or more, and M1≥M2≥M。
In this embodiment, the first capability label and the second capability label refer to one or more of a basic capability evaluation label and a basic capability requirement label in the talent feature image or the post feature image. For example, the first capability label and the second capability label refer to a leadership field, an executive force field, a team awareness field, a learning capability field, an innovation capability field, a management capability field, and the like of a basic capability evaluation label or a basic capability requirement label in a talent feature representation or a post feature representation. For example, if the fields exist in a text format, the text information of the fields can be obtained through a text processing technology, and the capability matching degree can be obtained by performing duplication checking and matching according to the text information of the fields. Preferably, each capability field in the basic capability evaluation tag or the basic capability requirement tag is quantized, namely scored, and then compared and matched according to the quantized score, so as to obtain the capability matching degree. Further, according to the quantized values, a capability chart is formed, and according to the picture analysis processing technology, the difference of the capability chart is compared to obtain the capability matching degree.
And after the capability matching degree of the feature images of the objects to be matched in the feature image set of the preselected objects to be matched is obtained, comparing a plurality of obtained capability matching degrees with a capability matching degree threshold value according to a preset capability matching degree threshold value condition to obtain the feature images of the objects to be matched, and taking the feature images as the feature image set of the two selected objects to be matched. For example, if the preset capability matching degree threshold condition is "the feature images of the object to be matched with the capability matching degree greater than or equal to 60% are retained" or "the feature images of the object to be matched with the capability matching degree less than 60% are filtered", each acquired capability matching degree is compared with the capability matching degree threshold of 60%, and according to the comparison result, filtering is performed or a feature image set of two selected objects to be matched is formed.
The method comprises the steps of firstly obtaining the capability matching degrees of all objects from a characteristic image set of a preselected object to be matched, simplifying the comprehensive matching degree obtaining process and improving the matching efficiency. Meanwhile, through a capability matching degree threshold value method, objects with partial capability not meeting the requirements are filtered, and matching accuracy is improved.
It is worth explaining that screening the objects in the feature image set of the preselected object to be matched through the threshold value of the capability matching degree can screen out not only the objects whose capability or capability requirement is obviously lower than that of the object to be matched, but also the objects whose capability or capability requirement is obviously higher than that of the object to be matched, so that the matching is proper, and the accuracy of the post matching is improved.
Referring to fig. 4, in order to improve the matching accuracy, the method performs auxiliary correction on the ranking result in the feature image set of two selected objects to be matched, which meets both the hard index condition and the threshold requirement of the capability matching degree, for example, performs auxiliary correction on the ranking result through a character tag, and specifically includes the following steps:
s331, reading a first character label in the characteristic image of the target object;
s332. reading M2Second character labels in the feature image set of the two selected objects to be matched;
s333, acquiring the first character label and M2A character matching degree of each second character label;
s334, calculating the characteristic image and the M of the target object according to the set weight coefficient, the capability matching degree and the character matching degree2And the comprehensive matching degree of the characteristic portrait of the object to be matched.
In this embodiment, the first character label or the second character label is a character evaluation label or a character requirement label in the talent feature image or the post feature image. For example, the character evaluation tags comprise a main tag and a plurality of secondary tags according to characters of the personnel objects, the character requirement tags set a main requirement and a plurality of secondary requirements according to the post requirements, and when the characters are matched, the main tag and the main requirement are used as the main requirement, the secondary tags and the secondary requirements are assisted, and the matching degree of the first character tag and the second character tag is obtained.
Obtaining the characteristic image and M of the target object according to the capability matching degree and the character matching degree by a weight method2And the comprehensive matching degree of the second character labels. For example, if the capability matching degree of the feature image of the target object and one of the feature images of the two selected objects to be matched is M, and the character matching degree is N, the overall matching degree a = α M + (1- α) N, where α is a constant and 0<α<1。
And sequencing the obtained comprehensive matching degrees, and performing post matching by referring to a sequencing result.
According to the human-guard matching method based on interval matching, a rapid, accurate and efficient human-guard matching degree obtaining mode is provided according to a big data analysis means, on one hand, when people are selected by a guard, each qualified talent object is comprehensively and fairly considered, subjective consciousness influence of a supervisor is reduced, probability of object omission and object matching errors is reduced, and accuracy of human-guard matching is improved. On the other hand, when people select the post, all the intentional posts are traversed to find the most suitable post, so that the small size and the large size of talents are prevented, and effective data reference is provided for personnel management of supervisors. On the other hand, the drip irrigation type training system can provide data support for drip irrigation type training and targeted training of the supervisor, and provides data reference for self learning and self progress of the talent subject.
In one embodiment, selecting a person on a job, for example, selecting a team leader for a production team, performs the following process:
acquiring all talent characteristic images in the talent characteristic image library;
acquiring a post characteristic image of a team leader of a production team;
reading explicit requirements (hard requirements) about academic calendar, age, working age, post level and the like in the post feature images of the team leader, and quantizing the explicit requirements to form data which can be compared;
traversing, reading and quantizing the dominant indexes corresponding to the dominant requirements in the talent characteristic images in the talent characteristic image library, comparing the dominant indexes with the dominant requirements, filtering out talent characteristic images which do not meet the dominant requirements, and forming a preselected talent characteristic image set by the remaining talent characteristic images which can meet the dominant requirements;
reading capability requirement labels in post feature images of team leaders, matching the capability requirement labels with capability evaluation labels of each talent feature image in a preselected talent feature image set by adopting a text processing technology or an image processing technology to obtain a plurality of capability matching degrees, comparing the capability matching degrees with a capability matching degree threshold (in the embodiment, 60 percent can be selected), and retaining the talent feature images with the capability matching degrees higher than the capability matching degree threshold to form a two-choice talent feature image;
reading a character requirement label in the group long position feature image, matching the character requirement label with a character evaluation label of each talent feature image in the two-choice talent feature image to obtain a character matching degree, and calculating a comprehensive matching degree through a formula A = alpha M + (1-alpha) N according to the capacity character weight (in the embodiment, the selection weight is 80% of the capacity matching degree, and the character matching degree is 20%), wherein A is the comprehensive matching degree, M is the capacity matching degree, N is the character matching degree, and alpha is a weight coefficient.
And sequencing the plurality of comprehensive matching degrees obtained by calculation, and carrying out team leader election by managers according to sequencing results of the comprehensive matching degrees and matching with other factors.
In another embodiment, when a person selects a post, for example, a suitable post is arranged for three times of the employee, the following process is performed:
acquiring all post characteristic images in the post characteristic image library;
acquiring a talent characteristic image of Zhang III;
reading the dominant indexes (hard indexes) related to the academic calendar, the age, the working age, the post level and the like in the talent characteristic image of the third page, and quantizing the dominant indexes to form data which can be compared;
traversing, reading and quantizing the dominant requirements corresponding to the dominant indexes in the post characteristic images in the post characteristic image library, comparing the dominant indexes with the dominant requirements, filtering out the post characteristic images obviously not matching the dominant indexes, and forming a preselected post characteristic image set by the rest post characteristic images capable of matching the dominant indexes;
reading a capability evaluation label in the talent feature image of Zhang III, matching the capability evaluation label with a capability requirement label of each post feature image in a preselected post feature image set by adopting a text processing technology or an image processing technology to obtain a plurality of capability matching degrees, comparing the plurality of capability matching degrees with a capability matching degree threshold (in the embodiment, 60 percent can be selected), and reserving the post feature image with the capability matching degree higher than the capability matching degree threshold to form a second-choice feature image;
reading a character evaluation label in the talent feature image of the third page, matching the character evaluation label with a character requirement label of each position feature image in the two-choice position feature image to obtain a character matching degree, and calculating a comprehensive matching degree through a formula A = alpha M + (1-alpha) N according to the weight of the capacity character (in the embodiment, the selection weight is 80% of the capacity matching degree, and the character matching degree is 20%), wherein A is the comprehensive matching degree, M is the capacity matching degree, N is the character matching degree, and alpha is a weight coefficient.
And sequencing the plurality of comprehensive matching degrees obtained by calculation, and using managers to engage Zhang III by referring to the sequencing result of the comprehensive matching degrees and matching with other factors.
In another embodiment, a targeted drip irrigation cultivation is performed, that is, a targeted cultivation is performed on a given employee or employee group according to the requirement of a specific post. The specific process is discussed in the Taoist section. And the manager checks the capacity matching degree and the defects in the character matching degree of the person with the post cultivation potential who is ranked later according to the ranking result, so that a targeted cultivation plan is formulated, and effective data reference is provided for the training management of the manager.
In another embodiment, data reference is provided for self-learning and self-progressing of employees, namely, the employees can pertinently strengthen learning according to target post requirements or target competitors, the self-ability level and business literacy are improved, and guidance is provided for self-progressing of the employees and improving the mutual competitiveness. The specific process is referred to the discussion in the post section. It should be noted that, when the employee is compared with the target competitor, the following process is performed:
firstly, referring to the discussion of a person selection post part, obtaining the comprehensive matching degree sequence of the matching posts of the staff;
sorting according to the comprehensive matching degree, and selecting the posts in which the employees are interested;
referring to the discussion of selecting people by post, acquiring a talent characteristic image with higher comprehensive matching degree of the post in which the employee is interested;
and (4) referring to the characteristic image of the talent with higher comprehensive matching degree, making a self-learning plan, determining a target, continuously learning and improving the self.
Referring to fig. 5, in another embodiment, the present invention further provides a human sentry matching system based on interval matching, including: a talent feature picture library 10 for storing a plurality of talent feature pictures; a post feature image library 20 for storing a plurality of post feature images; a first obtaining module 100, configured to obtain a feature image set of an object to be matched from the talent feature image library or the post feature image library, where the feature image set of the object to be matched includes N feature images of the object to be matched, and N is an integer greater than or equal to 2; a second obtaining module 200 for obtaining the characteristic image of the target object from the talent characteristic image library 10 or the post characteristic image library 20; a comprehensive matching degree obtaining module 300 for obtaining comprehensive matching degrees of the feature images of the target object and the feature images of the M objects to be matched in the feature image set of the objects to be matched, wherein M is an integer not less than 1, and M is not more than N; and a ranking module 400 for ranking the M combined matches.
Preferably, the comprehensive matching degree obtaining module 300 includes: a first feature factor reading unit 311 for reading a first feature factor in the feature image of the target object; a first feature factor quantization unit 312 for quantizing the first feature factor; a second characteristic factor reading unit 313 for reading second characteristic factors in the characteristic images of the N objects to be matched; second for quantizing the second characteristic factorA characteristic factor quantizing unit 314; a first comparing unit 315 for comparing the first characteristic factor with the second characteristic factor; for screening out M according to the comparison result and the set screening condition1A first screening unit 316 for pre-selecting the characteristic images of the objects to be matched as a set of characteristic images of the objects to be matched, wherein M1Is an integer of 1 or more, and M1More than or equal to M; and M in the characteristic image set for obtaining the characteristic image of the target object and the preselected object to be matched1A first comprehensive matching degree obtaining unit 317 for the comprehensive matching degree of the characteristic portrait of the object to be matched.
Preferably, the comprehensive matching degree obtaining module 300 further includes: a first capability tag reading unit 321 for reading a first capability tag in the feature image of the target object; for reading M1A second ability tag reading unit 322 for preselecting a second ability tag in the feature image set of the object to be matched; for obtaining the first capability tag and M1A capability matching degree obtaining unit 323 for obtaining a capability matching degree of each second capability label; for comparing M according to a set threshold condition of capability matching degree1A second comparing unit 324 for comparing the capability matching degree of the first capability label and the second capability label with a capability matching degree threshold, and a module for screening out M according to the comparison result2A second screening unit 325 for selecting the feature images of the object to be matched as a feature image set of two objects to be matched, wherein M is2Is an integer of 1 or more, and M1≥M2≥M。
Preferably, the comprehensive matching degree obtaining module 300 further includes: a first character tag reading unit 331 for reading a first character tag in the feature image of the target object; for reading M2A second character label reading unit 332 for a second character label in the feature image set of the two selected objects to be matched; for obtaining the first character label and M2A character matching degree obtaining unit 333 of the character matching degree of each of the second character labels; and for setting the weight coefficient according to the weight coefficient and theThe first ability matching degree and the character matching degree are calculated, and the characteristic image and the M of the target object are calculated2And a calculation unit 334 for comprehensive matching of the characteristic portrait of the object to be matched.
The human-sentry matching system based on interval matching provided by the embodiment of the invention has the same realization principle and technical effect as the embodiment of the method, and for brief description, the embodiment of the device is partially not mentioned, and reference can be made to the corresponding content in the embodiment of the method
In another specific embodiment, there is provided a people post matching device, including: the system comprises one or more processors and a data memory, wherein the data memory is used for storing a plurality of talent characteristic images, a plurality of post characteristic images and one or more programs; the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the above-described interval matching-based human duty matching method.
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (9)
1. A method for matching the human sentry based on interval matching is characterized by comprising the following steps:
acquiring a characteristic image set of an object to be matched, wherein the characteristic image set of the object to be matched comprises N characteristic images of the object to be matched, and N is an integer more than or equal to 2;
acquiring a characteristic image of a target object;
acquiring the comprehensive matching degree of the characteristic images of the target object and the characteristic images of M objects to be matched in the characteristic image set of the objects to be matched, wherein M is an integer not less than 1, and M is not more than N;
sequencing the M comprehensive matching degrees;
and performing the people's post matching according to the sorting result.
2. The method according to claim 1, wherein the step of obtaining the comprehensive matching degree between the feature images of the target object and the feature images of the M objects to be matched in the feature image set of the objects to be matched, where M is an integer no less than 1 and M is no greater than N, comprises the steps of:
reading a first characteristic factor in the characteristic image of the target object;
quantizing the first characteristic factor;
reading second characteristic factors in the characteristic images of the N objects to be matched;
quantizing the second characteristic factor;
comparing the first characteristic factor to the second characteristic factor;
screening M according to the comparison result and the set screening conditions1The characteristic images of the objects to be matched are taken as a characteristic image set of a preselected object to be matched, wherein M is1Is an integer of 1 or more, and M1≥M;
Acquiring the characteristic image of the target object and M in the characteristic image set of the preselected object to be matched1And the comprehensive matching degree of the characteristic portrait of the object to be matched.
3. The method according to claim 2, wherein the step of obtaining a comprehensive matching degree between the feature images of the target object and the feature images of the M objects to be matched in the feature image set of the objects to be matched, where M is an integer no less than 1 and M is no greater than N, further comprises the steps of:
reading a first capability label in the characteristic image of the target object;
reading M1A second capability label in the characteristic image set of the preselected object to be matched;
obtaining the first capability tag and M1A capability matching degree of each second capability label;
comparing M according to the threshold condition of the set capability matching degree1The capability matching degree of the first capability label and the second capability label is equal to a capability matching degree threshold value;
according to the comparison result, screening out M2The characteristic images of the objects to be matched are taken as a characteristic image set of two objects to be matched, wherein M is2Is an integer of 1 or more, and M1≥M2≥M。
4. The method according to claim 3, wherein the step of obtaining the first capability label and M is a step of obtaining the first capability label and M1In the comprehensive matching degree of the second capability label, the first capability label and the M are obtained through text data analysis or image analysis1A capability matching degree of each second capability label.
5. The method according to claim 3, wherein the step of obtaining the comprehensive matching degree between the feature images of the target object and the feature images of the M objects to be matched in the feature image set of the objects to be matched, where M is an integer greater than or equal to 1 and M is less than or equal to N, further comprises the steps of:
reading a first character label in the characteristic image of the target object;
reading M2Second character labels in the feature image set of the two selected objects to be matched;
obtaining the first character label and M2A character matching degree of each second character label;
calculating the characteristic image and M of the target object according to the set weight coefficient, the capability matching degree and the character matching degree2And the comprehensive matching degree of the characteristic portrait of the object to be matched.
6. The utility model provides a people's post matching system based on interval matching which characterized in that includes:
the talent characteristic image library is used for storing a plurality of talent characteristic images;
the post characteristic image library is used for storing a plurality of post characteristic images;
the system comprises a first acquisition module, a second acquisition module and a matching module, wherein the first acquisition module is used for acquiring a characteristic image set of an object to be matched from the talent characteristic image library or the post characteristic image library, the characteristic image set of the object to be matched comprises N characteristic images of the object to be matched, and N is an integer more than or equal to 2;
the second acquisition module is used for acquiring the characteristic image of the target object from the talent characteristic image library or the post characteristic image library;
the comprehensive matching degree acquisition module is used for acquiring the comprehensive matching degrees of the characteristic images of the target object and the characteristic images of the M objects to be matched in the characteristic image set of the objects to be matched, wherein M is an integer not less than 1, and M is not more than N; and
and the sequencing module is used for sequencing the M comprehensive matching degrees.
7. The human-sentry matching system based on interval matching as claimed in claim 6, wherein the comprehensive matching degree obtaining module comprises:
a first characteristic factor reading unit for reading a first characteristic factor in a characteristic image of the target object;
a first characteristic factor quantization unit configured to quantize the first characteristic factor;
the second characteristic factor reading unit is used for reading second characteristic factors in the characteristic images of the N objects to be matched;
a second characteristic factor quantization unit, configured to quantize the second characteristic factor;
a first comparing unit for comparing the first characteristic factor with the second characteristic factor;
a first screening unit for screening M according to the comparison result and the set screening condition1The characteristic images of the objects to be matched are taken as a characteristic image set of a preselected object to be matched, wherein M is1Is an integer of 1 or more, and M1More than or equal to M; and
a first comprehensive matching degree obtaining unit, configured to obtain the feature image of the target object and M in the feature image set of the preselected object to be matched1And the comprehensive matching degree of the characteristic portrait of the object to be matched.
8. The human-sentry matching system based on interval matching as claimed in claim 7, wherein said comprehensive matching degree obtaining module further comprises:
a first capability tag reading unit, configured to read a first capability tag in the feature image of the target object;
a second capability tag reading unit for reading M1A second capability label in the characteristic image set of the preselected object to be matched
A capability matching degree obtaining unit for obtaining the first capability label and M1A capability matching degree of each second capability label;
a second comparison unit for comparing M according to the set threshold condition of capability matching degree1The capability matching degree of the first capability label and the second capability label is equal to a capability matching degree threshold value; and
a second screening unit for screening M according to the comparison result2The characteristic images of the objects to be matched are taken as a characteristic image set of two objects to be matched, wherein M is2Is an integer of 1 or more, and M1≥M2≥M。
9. The human-sentry matching system based on interval matching as claimed in claim 8, wherein said comprehensive matching degree obtaining module further comprises:
a first character tag reading unit configured to read a first character tag in the feature image of the target object;
a second character tag reading unit for reading M2Second character labels in the feature image set of the two selected objects to be matched;
a character matching degree obtaining unit for obtaining the first character label and M2A character matching degree of each second character label; and
a calculating unit for calculating the characteristic image and M of the target object according to the set weight coefficient, the first ability matching degree and the character matching degree2And comprehensively matching the characteristic images of the objects to be matched.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011171084.7A CN112288391A (en) | 2020-10-28 | 2020-10-28 | Interval matching-based method and system for matching human posts |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011171084.7A CN112288391A (en) | 2020-10-28 | 2020-10-28 | Interval matching-based method and system for matching human posts |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112288391A true CN112288391A (en) | 2021-01-29 |
Family
ID=74372506
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011171084.7A Pending CN112288391A (en) | 2020-10-28 | 2020-10-28 | Interval matching-based method and system for matching human posts |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112288391A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114372731A (en) * | 2022-03-21 | 2022-04-19 | 成都明途科技有限公司 | Post target making method, device, equipment and storage medium based on big data |
CN114943037A (en) * | 2022-07-20 | 2022-08-26 | 平安银行股份有限公司 | System method, computer equipment and storage medium for talent portrayal |
WO2022252014A1 (en) * | 2021-05-30 | 2022-12-08 | 浙江省北大信息技术高等研究院 | Method for intelligently matching supply and demand in innovation and entrepreneurship services |
CN116090766A (en) * | 2022-12-29 | 2023-05-09 | 安徽深迪科技有限公司 | EP production mistake proofing system towards intelligent manufacturing |
CN116431902A (en) * | 2023-03-10 | 2023-07-14 | 青软创新科技集团股份有限公司 | Post recommendation method, computing equipment and storage medium |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020198766A1 (en) * | 2001-02-22 | 2002-12-26 | Magrino Susan A. | Human capital management inventory and position matching system and methods |
CN108062657A (en) * | 2017-11-30 | 2018-05-22 | 朱学松 | Method and system are interviewed in personnel recruitment |
CN109767182A (en) * | 2018-12-29 | 2019-05-17 | 金现代信息产业股份有限公司 | A kind of cadre's method of adjustment and system in rule-based library |
CN110119877A (en) * | 2019-04-04 | 2019-08-13 | 平安科技(深圳)有限公司 | A kind of choosing method and equipment of target employee |
CN110297973A (en) * | 2019-06-18 | 2019-10-01 | 中国平安财产保险股份有限公司 | A kind of data recommendation method based on deep learning, device and terminal device |
CN110310095A (en) * | 2019-07-03 | 2019-10-08 | 广东倍智测聘网络科技股份有限公司 | Management-control method and device, the electronic equipment of human resource data |
US20190317966A1 (en) * | 2018-04-12 | 2019-10-17 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for talent-post matching and computer readable storage medium |
CN111325529A (en) * | 2020-03-20 | 2020-06-23 | 广东人啊人网络技术开发有限公司 | Talent evaluation-based personnel and post matching method and system |
-
2020
- 2020-10-28 CN CN202011171084.7A patent/CN112288391A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020198766A1 (en) * | 2001-02-22 | 2002-12-26 | Magrino Susan A. | Human capital management inventory and position matching system and methods |
CN108062657A (en) * | 2017-11-30 | 2018-05-22 | 朱学松 | Method and system are interviewed in personnel recruitment |
US20190317966A1 (en) * | 2018-04-12 | 2019-10-17 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for talent-post matching and computer readable storage medium |
CN109767182A (en) * | 2018-12-29 | 2019-05-17 | 金现代信息产业股份有限公司 | A kind of cadre's method of adjustment and system in rule-based library |
CN110119877A (en) * | 2019-04-04 | 2019-08-13 | 平安科技(深圳)有限公司 | A kind of choosing method and equipment of target employee |
CN110297973A (en) * | 2019-06-18 | 2019-10-01 | 中国平安财产保险股份有限公司 | A kind of data recommendation method based on deep learning, device and terminal device |
CN110310095A (en) * | 2019-07-03 | 2019-10-08 | 广东倍智测聘网络科技股份有限公司 | Management-control method and device, the electronic equipment of human resource data |
CN111325529A (en) * | 2020-03-20 | 2020-06-23 | 广东人啊人网络技术开发有限公司 | Talent evaluation-based personnel and post matching method and system |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2022252014A1 (en) * | 2021-05-30 | 2022-12-08 | 浙江省北大信息技术高等研究院 | Method for intelligently matching supply and demand in innovation and entrepreneurship services |
CN114372731A (en) * | 2022-03-21 | 2022-04-19 | 成都明途科技有限公司 | Post target making method, device, equipment and storage medium based on big data |
CN114943037A (en) * | 2022-07-20 | 2022-08-26 | 平安银行股份有限公司 | System method, computer equipment and storage medium for talent portrayal |
CN116090766A (en) * | 2022-12-29 | 2023-05-09 | 安徽深迪科技有限公司 | EP production mistake proofing system towards intelligent manufacturing |
CN116431902A (en) * | 2023-03-10 | 2023-07-14 | 青软创新科技集团股份有限公司 | Post recommendation method, computing equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112288391A (en) | Interval matching-based method and system for matching human posts | |
Otaye-Ebede | Employees’ perception of diversity management practices: scale development and validation | |
Naong | The impact of skills-development training on lower-level employee’s motivation and job satisfaction–A case-study of five South African companies | |
CN112801636A (en) | Intelligent talent recommendation culture platform and method based on learning map and post image | |
Esposto | Skill: An elusive and ambiguous concept in labour market studies | |
Coronado et al. | Characterization of the federal workforce at the Centers for Disease Control and Prevention | |
CN113656687A (en) | Teacher portrait construction method based on teaching and research data | |
CN111967836A (en) | Generation method of talent 'holographic digital portrait' and application thereof | |
Gungor et al. | The evaluation of instructional leadership researches between 2002 and 2017 in Turkey | |
CN112465457A (en) | Supervision project management method, system, device and computer storage medium | |
Doering et al. | Intraorganizational and interorganizational job change: A discriminant analysis | |
CN115775140A (en) | System and method for urban talent planning and intelligent human resource allocation | |
Houston | COGNITIVE STRUCTURE AND INFORMATION SEARCH PATTERNS OF PROSPECTIVE GRADUATE BUSINESS STUDENTS. | |
Silvia et al. | Research methods used in analysing organisational culture | |
Swamy et al. | Recruitment and selection process in the IT firms | |
CN114626654A (en) | Personnel training early warning analysis method based on professional skill training personnel management system | |
Hosseinpour et al. | The relationship between structure and performance organizational from emergency staff viewpoints | |
CN111724128A (en) | Talent screening system for personnel selection interview of institution and public institution | |
Yakin et al. | Evaluating an electronic performance support system for crime scene investigation units in Turkey | |
Nointin | Hierachical model of internal marketing to predict employee satisfaction and turnover intention | |
JP6959386B2 (en) | Talent analysis systems, methods, and programs | |
Newman | UNDERSTANDING EMPLOYEE REACTIONS TO THE WORK ENVIRONMENT THROUGH PERSONALAND ORGANIZATIONAL FRAMES OF REFERENCE AND PERCEPTIONS OF THE WORK ENVIRONMENT. | |
Stanton et al. | Selecting personnel in the nuclear power industry | |
Abdi et al. | Structural Model of Job Satisfaction in Agricultural Research, Education and Extension Organization (AREEO) Staff Based on Herzberg Motivational Theory | |
Toader et al. | The Informatic Application Smart Personnel Evaluation |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210129 |