CN113159528A - Post matching evaluation method and device - Google Patents
Post matching evaluation method and device Download PDFInfo
- Publication number
- CN113159528A CN113159528A CN202110349507.8A CN202110349507A CN113159528A CN 113159528 A CN113159528 A CN 113159528A CN 202110349507 A CN202110349507 A CN 202110349507A CN 113159528 A CN113159528 A CN 113159528A
- Authority
- CN
- China
- Prior art keywords
- vector
- evaluation
- historical
- value
- result
- 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
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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a post matching evaluation method and a device, wherein the method comprises the following steps: acquiring a vector result made by the evaluated person on the evaluation question in the database and a target position of the evaluated person, wherein the vector result comprises a first vector used for representing an MBTI character test result and a second vector used for representing a Howland occupational character test result; inputting the first vector and the second vector into a score prediction linear model and outputting a prediction score of the evaluated person; and inputting the first vector, the second vector and the prediction score into a matching degree decision tree model, and evaluating the matching degree of the evaluated person and the target position. The evaluation questions in the database quickly and accurately analyze the characters of the person to be evaluated, so that the defects of inaccuracy and incompleteness in the character analysis and evaluation process are avoided; the character analysis result is input into the prediction linear model and the matching degree decision tree model, so that an evaluation result can be generated according to character analysis, and the analysis result can be fed back to enterprise managers in time.
Description
Technical Field
The invention relates to the technical field of data mining, in particular to a post matching evaluation method and device.
Background
The post matching refers to the matching relationship between the personnel and the post. Each job has different requirements on the quality, ability, experience, etc. of the job-taker. Only when the job-holder has more than the required qualities can the job be better qualified, thereby realizing the win-win situation between the enterprise and the job-holder. At present, most of methods for people post matching of enterprises are offline manual combing, and for important posts of enterprises, such as picking and selecting of people at posts such as managers and supervisors, a great amount of time can be spent by personnel departments in combing and selecting people.
Disclosure of Invention
The present invention is directed to a method and an apparatus for post matching evaluation, so as to solve the problems in the background art.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
in one aspect, a method for evaluating post matching is provided, where the method includes:
acquiring a vector result made by the evaluated person on the evaluation questions in the database and a target position of the evaluated person, wherein the vector result comprises a first vector used for representing the MBTI character test result and a second vector used for representing the Holland occupational character test result;
inputting the first vector and the second vector into a score prediction linear model to output a prediction score of the evaluated person;
and inputting the first vector, the second vector and the prediction score into a matching degree decision tree model, and evaluating the matching degree of the evaluated person and the target position.
As a further improvement of the present invention, the method further comprises:
calling an average work performance value of each historical employee corresponding to the target post and a reference result made to an evaluation subject in the database; wherein the reference results comprise a first reference vector representing MBTI character test results and a second reference vector representing Holland occupational character test results;
and training to obtain the score prediction linear model and the matching degree decision tree model based on the first reference vector and the second reference vector of each historical employee and the average work performance value.
As a further improvement of the present invention, the average performance value is obtained by the following method for any historical employee:
acquiring a plurality of work performance total values of the historical staff, wherein each work performance total value is obtained by an enterprise manager according to the work condition of the historical staff in a preset period and a performance evaluation system in the enterprise correspondingly;
obtaining the average work performance value of the historical staff by adopting the following formula:
wherein, ykRepresents the total performance value in each preset period, and T represents the number of preset periods.
As a further improvement of the present invention, the score prediction linear model trained based on the first reference vector, the second reference vector and the average work performance value of each historical employee comprises:
for each historical employee, taking a first reference vector corresponding to the historical employee as M, a second reference vector as H and an average work performance value as y, and inputting an evaluation model y ═ w [ M, H ] + b;
and calculating the loss of the linear evaluation model by using a least square method, and adjusting a w value and a b value according to the loss to obtain the trained score prediction linear model.
As a further improvement of the present invention, the training to obtain the matching degree decision tree model based on the first reference vector, the second reference vector and the average work performance value of each historical employee includes:
taking a first reference vector, a second reference vector, an average work performance effective value and a work competence condition of each historical employee as sample data, and taking an MBTI character test result, a Holland occupational character test result and an average work performance as an attribute set;
taking sample data contained in a leaf node in the previous layer of the current layer as a root node of the current layer, and calculating the information entropy of the root node;
taking each attribute in the attribute set as a classification index in turn so as to divide the root node into a plurality of leaf nodes and calculate the information entropy of each leaf node;
and calculating the information gain of each attribute based on the information entropy and the information entropy of each leaf node, taking the attribute with the maximum information gain value as the optimal partition attribute of the current layer, and partitioning the root node into a plurality of leaf nodes based on the optimal partition attribute.
In another aspect, a station matching evaluation apparatus is provided, the apparatus including:
the vector result acquisition module is used for acquiring a vector result made by the evaluated person on the evaluation questions in the database and a target position of the evaluated person, wherein the vector result comprises a first vector used for representing the MBTI character test result and a second vector used for representing the Howland occupational character test result;
a prediction score obtaining module for inputting the first vector and the second vector into a score prediction linear model to output a prediction score of the evaluated person;
and the evaluation result acquisition module is used for inputting the first vector, the second vector and the prediction score into a matching degree decision tree model and evaluating the matching degree of the evaluated person and a target post.
As a further improvement of the present invention, the apparatus further comprises:
the reference result acquisition module is used for calling the average work performance value of each historical employee in the target post and a reference result made for the evaluation questions in the database; wherein the reference results comprise a first reference vector representing MBTI character test results and a second reference vector representing Holland occupational character test results;
and the linear model generation module is used for training to obtain the score prediction linear model and the matching degree decision tree model based on the first reference vector and the second reference vector of each historical employee and the average work performance value.
As a further improvement of the present invention, the reference result acquiring module further includes:
the system comprises a total performance value acquisition unit, a performance evaluation unit and a management unit, wherein the total performance value acquisition unit is used for acquiring a plurality of total work performance values of historical employees aiming at any historical employee, and each total performance value is obtained by corresponding an enterprise manager to a performance evaluation system in an enterprise according to the working conditions of the historical employees in a preset period;
the average performance value acquiring unit is used for acquiring the average work performance value of the historical staff by adopting the following formula:
wherein, ykRepresents the total performance value in each preset period, and T represents the number of the preset periods.
As a further improvement of the present invention, the linear model generation module includes:
an evaluation model establishing unit, which is used for inputting a first reference vector corresponding to each historical employee as M, a second reference vector as H and an average work performance value as y into an evaluation model y ═ w [ M, H ] + b for each historical employee;
and the linear model generating unit is used for calculating the loss of the linear evaluation model by using a least square method, and adjusting the w value and the b value according to the loss to obtain the trained score prediction linear model.
As a further improvement of the present invention, the model generation module further comprises:
the processing unit is used for taking the first reference vector, the second reference vector, the average work performance effective value and the work competence condition of each historical employee as sample data and taking the MBTI character test result, the Holland occupational character test result and the average work performance as an attribute set;
the first computing unit is used for taking sample data contained in a leaf node in the layer above the current layer as a root node of the current layer and computing the information entropy of the root node;
the second calculation unit is used for sequentially taking each attribute in the attribute set as a classification index so as to divide the root node into a plurality of leaf nodes and calculate the information entropy of each leaf node;
and the dividing unit is used for calculating the information gain of each attribute based on the information entropy and the information entropy of each leaf node, taking the attribute with the maximum information gain value as the optimal dividing attribute of the current layer, and dividing the root node into a plurality of leaf nodes based on the optimal dividing attribute.
Adopt the produced beneficial effect of above-mentioned technical scheme to lie in:
according to the post matching evaluation method and device provided by the embodiment of the invention, the evaluation questions in the database are set to quickly and accurately analyze the characters of the person to be evaluated, so that the defects of inaccuracy and incompleteness in the character analysis and evaluation process are avoided; the character analysis result is input into the prediction linear model and the matching degree decision tree model, so that the evaluation result can be generated according to character analysis, the advantages of big data and machine learning are fully utilized, the analysis result can be fed back to enterprise management personnel in time, and the use experience of a user is improved.
Drawings
In order to more clearly illustrate the detailed description of the invention or the technical solutions in the prior art, the drawings needed for the detailed description or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a method for evaluating post matching according to an embodiment of the present invention.
Fig. 2 is a flowchart of another post matching evaluation method according to an embodiment of the present invention.
FIG. 3 is a schematic score chart of an MBTI character test provided by the embodiment of the invention.
Fig. 4 is a schematic diagram of the relationship between types in a hoard occupational character test according to an embodiment of the present invention.
Fig. 5 is a schematic score chart of a hoard occupational character test according to an embodiment of the present invention.
Fig. 6 is a schematic structural diagram of a station matching evaluation apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in detail and fully with reference to the following embodiments.
The embodiment of the invention provides a flow chart of a post matching evaluation method, and as shown in fig. 1, the method comprises the following steps:
s101, obtaining a vector result of an evaluated person on an evaluation question in a database and a target post of the evaluated person;
the vector results include a first vector representing MBTI personality test results and a second vector representing Holland occupational personality test results.
And S102, inputting the first vector and the second vector into a score prediction linear model and outputting a prediction score of the evaluated person.
S103, inputting the first vector, the second vector and the prediction score into a matching degree decision tree model, and evaluating the matching degree of the evaluated person and the target post.
According to the post matching evaluation method provided by the embodiment of the invention, the evaluation questions in the database are set to quickly and accurately analyze the characters of the person to be evaluated, so that the defects of inaccuracy and incompleteness in the character analysis and evaluation process are avoided; the character analysis result is input into the prediction linear model and the matching degree decision tree model, so that the evaluation result can be generated according to character analysis, the advantages of big data and machine learning are fully utilized, the analysis result can be fed back to enterprise managers in time, and the use experience of users is improved.
Because different kinds of work contents have different requirements on the thinking way bias, sensibility and communication of people, people with different character characteristics can have different performances on work motivation, willingness and victory degree when doing different kinds of work.
Fig. 2 is a flowchart of another post matching evaluation method provided in an embodiment of the present invention, where the method may be operated in a terminal such as a smart phone (e.g., an Android phone, an IOS phone, etc.), a tablet computer, a notebook computer, and an intelligent device, and may also be operated in a corresponding server. The terminal or the server can obtain the personality type and the target position of the user by logging in the app or answering through the online webpage by the evaluated person, and generate the matching degree analysis with the target position of the evaluated person through the personality type, so that enterprise managers can accurately evaluate the matching degree of the evaluated person and the target position. As shown in fig. 2, the method includes:
s201, obtaining a vector result of the evaluated person to the evaluation questions in the database and a target position of the evaluated person.
The vector results include a first vector representing MBTI personality test results and a second vector representing Holland occupational personality test results.
As shown in table 1, the MBTI divides the personality type into four dimensions, and each dimension has two directions, and there are eight aspects in total, namely eight personality characteristics, which are: the personality characteristics of the formula are shown in FIG. 2, Nei-Wai (I-E), sensory-intuition (S-N), thought-emotional (T-F), judgment-intuition (J-P).
TABLE 1MBTI type index introduction
TABLE 2 introduction of character types
After the evaluated person finishes the evaluation subject of the MBTI character test in the database, the character of the evaluated person can be scored in the eight dimensions, and a first vector containing eight dimensional scores is generated. The first vector can be labeled as M (Me, Mi, Ms, Mn, Mt, Mf, Mj, Mp), and Me-Mp represents the fraction of eight dimensions, respectively, as shown in fig. 3, and its corresponding first vector is M (2.00,20.00,9.00,10.00,15.00,4.00,12.00, 5.00).
The hoard occupational character test is mainly used for determining the occupational interest tendency of a tested person and further guiding the tested person to select professional development directions and occupational development directions suitable for the self occupational interest, and comprises 6 basic occupational types: the current type R, the research type I, the art type A, the social type S, the enterprise type E and the conventional type C, the 6 types are not parallel and have clear boundaries, and the 6 types of relations are shown in figure 4.
After the evaluated person finishes the evaluation subject of the Holland occupational character test in the database, the character of the evaluated person can be scored in the six dimensions, and a second vector containing six dimensional scores is generated. The second vector may be labeled H (Hr, Hi, Ha, Hs, He, Hc), with Hr-Hc representing six-dimensional divisions, respectively. As shown in fig. 5, the corresponding second vector is H (75,71,42,46,46, 28).
S202, retrieving the post experience of each historical employee in the target post and making a reference result for the evaluation questions in the database.
Wherein, the historical employees refer to employees who have been in employment in the target post, for example: when the company engages the general manager of the department A, the employees which have been used as the general manager of the department A are the historical employees. The station experience includes an average work performance value and a work-qualified case, the work-qualified case including being work-qualified and work-not-qualified, the reference result including a first reference vector to represent the MBTI performance test result and a second reference vector to represent the Holland performance test result.
In actual operation, the terminal or the server acquires and stores a plurality of posts and post experiences and reference results of all historical employees for any one post in advance, and after the evaluated person selects the target post, the terminal or the server can call the post experience and reference result of each historical employee corresponding to the target post.
Hereinafter, the manner of acquiring the job competency in the post experience, the average job performance value, and the reference result will be described separately.
In one possible implementation, the enterprise administrator may log in to the operating system interface, manually input the manner of the work-competency condition, or select any one of the two conditions.
Regarding the way of obtaining the average work performance value, it includes but is not limited to the following steps:
and S1021, acquiring a plurality of total performance values of the historical employees, wherein each total performance value is obtained by the enterprise manager according to the historical employee working condition in the preset period and the performance evaluation system in the enterprise correspondingly.
The preset period can be 3 months, 6 months or 1 year, and for any historical employee, the total performance value in a plurality of different preset times can be obtained when the employee works for a plurality of years on the target post, so the performance is recorded according to the time period. The work performance is recorded by adopting a 10-point system, and the 10-point system shows that the performance is the best.
S1022, obtaining the average work performance effective value of the historical staff by adopting the following formula:
wherein, ykRepresents the total performance value in each preset period, and T represents the number of preset periods.
Regarding the manner of obtaining the job competence, it is similar to step S101, and the difference is only that the evaluated person is changed to each historical employee, which is not described in detail in the embodiment of the present invention.
S203, training based on the first reference vector and the second reference vector of each historical employee and the average work performance value to obtain a score prediction linear model and a matching degree decision tree model.
The method for training the score-derived predictive linear model includes, but is not limited to, the following steps:
s2031, for each historical employee, inputting a first reference vector corresponding to the historical employee as M, a second reference vector as H, and an average work performance value as y into an evaluation model y ═ w [ M, H ] + b;
s2032, calculating loss of the linear evaluation model by using a least square method, and adjusting a w value and a b value according to the loss to obtain a trained score prediction linear model.
The method for training the score predictive linear model includes but is not limited to the following steps:
s2033, taking the first reference vector, the second reference vector, the average work performance effective value and the work competence condition of each historical employee as sample data, and taking the MBTI character test result, the Holland occupational character test result and the average work performance as an attribute set;
s2034, taking sample data contained in a leaf node in the previous layer of the current layer as a root node of the current layer, and calculating the information entropy of the root node;
s2035, sequentially using each attribute in the attribute set as a classification index to divide the root node into a plurality of leaf nodes and calculate the information entropy of each leaf node;
s2036, based on the information entropy and the information entropy of each leaf node, calculating the information gain of each attribute, taking the attribute with the maximum value of the information gain as the optimal partition attribute of the current layer, and partitioning the root node into a plurality of leaf nodes based on the optimal partition attribute.
And S204, inputting the first vector and the second vector into a score prediction linear model and outputting a prediction score of the evaluated person.
S205, inputting the first vector, the second vector and the prediction score into a matching degree decision tree model, and evaluating the matching degree of the evaluated person and the target post.
Therefore, the first vector and the second vector are input into the score prediction linear model to obtain the prediction score, and then the prediction score is input into the matching degree decision tree model to obtain an evaluation result, wherein the evaluation result not only comprises whether the evaluated person is suitable for the target post, but also comprises a judgment basis for enterprise management personnel to refer.
According to the post matching evaluation method provided by the embodiment of the invention, the evaluation questions in the database are set to quickly and accurately analyze the characters of the person to be evaluated, so that the defects of inaccuracy and incompleteness in the character analysis and evaluation process are avoided; the character analysis result is input into the prediction linear model and the matching degree decision tree model, so that the evaluation result can be generated according to character analysis, the analysis result can be fed back to enterprise management personnel in time, and the use experience of a user is improved.
Because different kinds of work contents have different requirements on the thinking way bias, sensibility and communication of people, people with different character characteristics can have different performances on work motivation, willingness and victory degree when doing different kinds of work.
Fig. 6 is a diagram of a station matching evaluation apparatus according to an embodiment of the present invention, and as shown in fig. 6, the apparatus includes:
a vector result obtaining module 601, configured to obtain vector results made by the person to be evaluated on the evaluation questions in the database and target positions of the person to be evaluated, where the vector results include a first vector used to represent the MBTI character test result and a second vector used to represent the hollander occupational character test result;
a prediction score obtaining module 602, configured to input the first vector and the second vector into a score prediction linear model to output a prediction score of the person to be evaluated;
and the evaluation result obtaining module 603 is configured to input the first vector, the second vector and the prediction score into the matching degree decision tree model, and evaluate the matching degree between the evaluated person and the target position.
Further, the apparatus further comprises:
the reference result acquisition module is used for calling the average work performance effective value of each historical employee in the target post and the reference result made to the evaluation subject in the database; wherein the reference result comprises a first reference vector representing the MBTI character test result and a second reference vector representing the Holland occupational character test result;
and the linear model generation module is used for training to obtain a score prediction linear model and a matching degree decision tree model based on the first reference vector and the second reference vector of each historical employee and the average work performance value.
Further, the reference result obtaining module further includes:
the system comprises a total performance value acquisition unit, a performance evaluation unit and a management unit, wherein the total performance value acquisition unit is used for acquiring a plurality of total work performance values of historical employees aiming at any historical employee, and each total performance value is obtained by corresponding an enterprise manager to a performance evaluation system in an enterprise according to the working conditions of the historical employees in a preset period;
the average performance value acquiring unit is used for acquiring the average work performance value of the historical staff by adopting the following formula:
wherein, ykRepresents the total performance value in each preset period, and T represents the number of the preset periods.
Further, the linear model generation module includes:
an evaluation model establishing unit, which is used for inputting a first reference vector corresponding to each historical employee as M, a second reference vector as H and an average work performance value as y into an evaluation model y which is w [ M, H ] + b;
and the linear model generating unit is used for calculating the loss of the linear evaluation model by using a least square method, and adjusting the w value and the b value according to the loss to obtain a trained score prediction linear model.
Further, the model generation module further comprises:
the processing unit is used for taking the first reference vector, the second reference vector, the average work performance effective value and the work competence condition of each historical employee as sample data and taking the MBTI character test result, the Holland occupational character test result and the average work performance as an attribute set;
a first calculation unit, configured to calculate an information entropy of a root node by using sample data included in a leaf node in a layer above a current layer as the root node of the current layer;
the second calculation unit is used for sequentially taking each attribute in the attribute set as a classification index so as to divide the root node into a plurality of leaf nodes and calculate the information entropy of each leaf node;
and the dividing unit is used for calculating the information gain of each attribute based on the information entropy and the information entropy of each leaf node, taking the attribute with the maximum information gain value as the optimal dividing attribute of the current layer, and dividing the root node into a plurality of leaf nodes based on the optimal dividing attribute.
According to the post matching evaluation device provided by the embodiment of the invention, the evaluation questions in the database are set to quickly and accurately analyze the characters of the person to be evaluated, so that the defects of inaccuracy and incompleteness in the character analysis and evaluation process are avoided; the character analysis result is input into the prediction linear model and the matching degree decision tree model, so that the evaluation result can be generated according to character analysis, the advantages of big data and machine learning are fully utilized, the analysis result can be fed back to enterprise managers in time, and the use experience of users is improved.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for evaluating post matching, the method comprising:
acquiring a vector result made by the evaluated person on the evaluation questions in the database and a target position of the evaluated person, wherein the vector result comprises a first vector used for representing an MBTI character test result and a second vector used for representing a Hirand occupational character test result;
inputting the first vector and the second vector into a score prediction linear model to output a prediction score of the evaluated person;
and inputting the first vector, the second vector and the prediction score into a matching degree decision tree model, and evaluating the matching degree of the evaluated person and the target position.
2. The method for evaluating post matching according to claim 1, further comprising:
calling an average work performance value of each historical employee corresponding to the target post and a reference result made to an evaluation subject in the database; wherein the reference results comprise a first reference vector representing MBTI character test results and a second reference vector representing Holland occupational character test results;
and training to obtain the score prediction linear model and the matching degree decision tree model based on the first reference vector and the second reference vector of each historical employee and the average work performance value.
3. The post matching evaluation method according to claim 2, wherein the average performance value is obtained by the following method for any one historical employee:
acquiring a plurality of work performance total values of the historical staff, wherein each work performance total value is obtained by corresponding an enterprise manager to a performance evaluation system in the enterprise according to the work condition of the historical staff in a preset period;
obtaining the average work performance value of the historical staff by adopting the following formula:
wherein, ykRepresents the total performance value in each preset period, and T represents the number of the preset periods.
4. The method for evaluating the post match according to claim 2, wherein the training of the score prediction linear model based on the first reference vector, the second reference vector and the average work performance value of each historical employee comprises:
for each historical employee, taking a first reference vector corresponding to the historical employee as M, a second reference vector as H and an average work performance value as y, and inputting an evaluation model y ═ w [ M, H ] + b;
and calculating the loss of the linear evaluation model by using a least square method, and adjusting a w value and a b value according to the loss to obtain the trained score prediction linear model.
5. The method for evaluating post matching according to claim 2, wherein the training of the matching degree decision tree model based on the first reference vector, the second reference vector and the average work performance value of each historical employee comprises:
taking a first reference vector, a second reference vector, an average work performance effective value and a work competence condition of each historical employee as sample data, and taking an MBTI character test result, a Holland occupational character test result and an average work performance as an attribute set;
taking sample data contained in a leaf node in the previous layer of the current layer as a root node of the current layer, and calculating the information entropy of the root node;
taking each attribute in the attribute set as a classification index in turn so as to divide the root node into a plurality of leaf nodes and calculate the information entropy of each leaf node;
and calculating the information gain of each attribute based on the information entropy and the information entropy of each leaf node, taking the attribute with the maximum information gain value as the optimal partition attribute of the current layer, and partitioning the root node into a plurality of leaf nodes based on the optimal partition attribute.
6. A station matching evaluation apparatus, characterized in that the apparatus comprises:
the vector result acquisition module is used for acquiring a vector result made by the evaluated person on the evaluation questions in the database and a target position of the evaluated person, wherein the vector result comprises a first vector used for representing the MBTI character test result and a second vector used for representing the Howland occupational character test result;
a prediction score obtaining module for inputting the first vector and the second vector into a score prediction linear model to output a prediction score of the evaluated person;
and the evaluation result acquisition module is used for inputting the first vector, the second vector and the prediction score into a matching degree decision tree model and evaluating the matching degree of the evaluated person and a target post.
7. The station matching evaluation device according to claim 6, further comprising:
the reference result acquisition module is used for calling the average work performance effective value of each historical employee in the target post and a reference result made for the evaluation questions in the database; wherein the reference results comprise a first reference vector representing MBTI character test results and a second reference vector representing Holland occupational character test results;
and the model generation module is used for training to obtain the score prediction linear model and the matching degree decision tree model based on the first reference vector and the second reference vector of each historical employee and the average work performance value.
8. The station matching evaluation device according to claim 7, wherein the reference result obtaining module further comprises:
the system comprises a total performance value acquisition unit, a performance evaluation unit and a management unit, wherein the total performance value acquisition unit is used for acquiring a plurality of total work performance values of historical employees aiming at any historical employee, and each total performance value is obtained by an enterprise manager according to the working conditions of the historical employees in a preset period and a performance evaluation system in an enterprise;
the average performance value acquiring unit is used for acquiring the average work performance value of the historical staff by adopting the following formula:
wherein, ykRepresents the total performance value in each preset period, and T represents the number of the preset periods.
9. The station matching evaluation device according to claim 7, wherein the model generation module comprises:
an evaluation model establishing unit, which is used for inputting a first reference vector corresponding to each historical employee as M, a second reference vector as H and an average work performance value as y into an evaluation model y ═ w [ M, H ] + b for each historical employee;
and the linear model generating unit is used for calculating the loss of the linear evaluation model by using a least square method, and adjusting a w value and a b value according to the loss to obtain the trained score prediction linear model.
10. The station matching evaluation device according to claim 7, wherein the model generation module further comprises:
the processing unit is used for taking the first reference vector, the second reference vector, the average work performance effective value and the work competence condition of each historical employee as sample data and taking the MBTI character test result, the Holland occupational character test result and the average work performance as an attribute set;
the first computing unit is used for taking sample data contained in a leaf node in the previous layer of the current layer as a root node of the current layer and computing the information entropy of the root node;
the second calculation unit is used for sequentially taking each attribute in the attribute set as a classification index so as to divide the root node into a plurality of leaf nodes and calculate the information entropy of each leaf node;
and the dividing unit is used for calculating the information gain of each attribute based on the information entropy and the information entropy of each leaf node, taking the attribute with the maximum information gain value as the optimal dividing attribute of the current layer, and dividing the root node into a plurality of leaf nodes based on the optimal dividing attribute.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110349507.8A CN113159528A (en) | 2021-03-31 | 2021-03-31 | Post matching evaluation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110349507.8A CN113159528A (en) | 2021-03-31 | 2021-03-31 | Post matching evaluation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113159528A true CN113159528A (en) | 2021-07-23 |
Family
ID=76885784
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110349507.8A Pending CN113159528A (en) | 2021-03-31 | 2021-03-31 | Post matching evaluation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113159528A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113780997A (en) * | 2021-09-16 | 2021-12-10 | 湖北天天数链技术有限公司 | Evaluation method and device for people and sentry matching, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103902566A (en) * | 2012-12-26 | 2014-07-02 | 中国科学院心理研究所 | Personality prediction method based on microblog user behaviors |
| CN107506928A (en) * | 2017-08-28 | 2017-12-22 | 北京育铭天下科技有限公司 | The occupational orientation assessment device and method of a kind of synthesis |
| US20180330390A1 (en) * | 2011-05-27 | 2018-11-15 | Ashutosh Malaviya | Enhanced systems, processes, and user interfaces for targeted marketing associated with a population of assets |
| CN110232498A (en) * | 2019-04-26 | 2019-09-13 | 平安科技（深圳）有限公司 | Employee's Potential Analysis method, apparatus, equipment and computer readable storage medium |
| WO2020119563A1 (en) * | 2018-12-14 | 2020-06-18 | 深圳壹账通智能科技有限公司 | Applicant evaluation method and device employing neural network model |
| CN112329825A (en) * | 2020-10-23 | 2021-02-05 | 贵州电网有限责任公司 | Transformer mechanical fault diagnosis method based on information dimension division and decision tree lifting |
-
2021
- 2021-03-31 CN CN202110349507.8A patent/CN113159528A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180330390A1 (en) * | 2011-05-27 | 2018-11-15 | Ashutosh Malaviya | Enhanced systems, processes, and user interfaces for targeted marketing associated with a population of assets |
| CN103902566A (en) * | 2012-12-26 | 2014-07-02 | 中国科学院心理研究所 | Personality prediction method based on microblog user behaviors |
| CN107506928A (en) * | 2017-08-28 | 2017-12-22 | 北京育铭天下科技有限公司 | The occupational orientation assessment device and method of a kind of synthesis |
| WO2020119563A1 (en) * | 2018-12-14 | 2020-06-18 | 深圳壹账通智能科技有限公司 | Applicant evaluation method and device employing neural network model |
| CN110232498A (en) * | 2019-04-26 | 2019-09-13 | 平安科技（深圳）有限公司 | Employee's Potential Analysis method, apparatus, equipment and computer readable storage medium |
| CN112329825A (en) * | 2020-10-23 | 2021-02-05 | 贵州电网有限责任公司 | Transformer mechanical fault diagnosis method based on information dimension division and decision tree lifting |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113780997A (en) * | 2021-09-16 | 2021-12-10 | 湖北天天数链技术有限公司 | Evaluation method and device for people and sentry matching, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Shepherd | Venture Capitalists' Introspection: A Comparison of" In Use" and" Espoused" Decision Policies. | |
| CN113269662A (en) | Intelligent teaching system based on big data | |
| CN108256022A (en) | Talent evaluation model building method and personnel evaluation methods and system | |
| CN110570097A (en) | business personnel risk identification method and device based on big data and storage medium | |
| CN111652513A (en) | Enterprise performance assessment system and method based on cloud platform | |
| CN114358733A (en) | Big data human resource management system | |
| CN114139065B (en) | Talent screening and recommending method and system based on big data and readable storage medium | |
| CN113159528A (en) | Post matching evaluation method and device | |
| CN114971693A (en) | Engineering cost consultation management system based on BIM | |
| CN111159429B (en) | Knowledge graph-based data analysis method and device, equipment and storage medium | |
| CN117522222A (en) | Education assessment software implementation method based on big data | |
| CN116402391B (en) | Comprehensive capability evaluation method and system based on big data | |
| CN116681410A (en) | Human resource data management system and management method based on cloud computing | |
| CN115330358B (en) | Education and training management system and education and training method | |
| CN111444409A (en) | Learning situation analysis system based on big data | |
| US20230186219A1 (en) | System and method for enterprise change management evaluation | |
| Jayakumar et al. | On-Demand Job-Based Recruitment For Organisations Using Artificial Intelligence | |
| CN115274113A (en) | Evaluation system based on psychological assessment scale scoring algorithm | |
| CN114298685A (en) | Engineering consultation supervision test operation and maintenance overall process management system | |
| Ali et al. | The Effect of Activating Artificial Intelligence techniques on Enhancing Internal Auditing Activities" Field Study" | |
| CN113793004A (en) | Power grid manpower configuration application system and configuration method thereof | |
| Nuntalid et al. | Poster: Machine Learning for Predicting Emergency Medical Incidents that Need an Air-ambulance | |
| Cusumano et al. | Intelligent building contract tendering-potential and exploration | |
| Okike et al. | Academic data Federation, Knowledge Base Construction and Heterogeneous Data Analysis for Improved management at University levels | |
| JP7382100B1 (en) | Programs and information processing equipment |
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 |