CN111967729A - Industrialized personnel portrait evaluation method based on data mining - Google Patents
Industrialized personnel portrait evaluation method based on data mining Download PDFInfo
- Publication number
- CN111967729A CN111967729A CN202010736538.4A CN202010736538A CN111967729A CN 111967729 A CN111967729 A CN 111967729A CN 202010736538 A CN202010736538 A CN 202010736538A CN 111967729 A CN111967729 A CN 111967729A
- Authority
- CN
- China
- Prior art keywords
- personnel
- data
- person
- information
- worker
- 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
- G06Q10/06398—Performance of employee with respect to a job function
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a design method of an industrialized personnel portrait evaluation system based on data mining, which comprises the following operation steps: s1: setting attribute characteristics of the industrialized personnel portrait, wherein the setting of the attribute characteristics comprises setting of basic attribute characteristics and setting of implicit attribute characteristics; s2: acquiring personnel performance data of different types, and carrying out preliminary statistics and cleaning on the personnel performance data needing to be modeled; s3: modeling the implicit attribute characteristics of the industrialized personnel; s4: and establishing an industrialized personnel portrait evaluation system, calculating a reference total score for industrialized personnel, and performing auxiliary correction on the evaluation of the personnel. Through the mode, the industrial personnel portrait evaluation system design method based on data mining enables various types of performance data of workers in an enterprise to construct a mapping model of the specified evaluation dimension of the workers, provides an objective, accurate and complete portrait system for the workers through training of label data and intervention and correction of manual evaluation, is convenient to use, and has good practical performance.
Description
Technical Field
The invention belongs to the field of data mining, and relates to a portrait system for evaluating industrialized workers, in particular to a portrait evaluation method for industrialized personnel based on data mining.
Background
The portrait system is derived from the concept of user portrait, and the user portrait is an effective tool for outlining target users and connecting user appeal and design direction, and is widely applied to various fields. User portrayal is originally applied in the E-commerce field, and in the background of the big data era, user information is flooded in a network, each piece of concrete information of a user is abstracted into labels, and the labels are utilized to concretize the user image, so that targeted services are provided for the user. The portrayal system is a wider concept of user portrayal, is not limited to e-commerce users, and is used for constructing models by using some technologies of data mining for practitioners in any field, such as students, workers and public staff, according to some fixed attributes and various types of dynamic information of the practitioners, and quantitatively evaluating the practitioners from different dimensions through the models so as to intelligently select the workers according to evaluation results, evaluate the performance and other matters. The industrial human portrait system takes workers as objects and establishes a reasonable portrait model to evaluate the workers.
When the image system is modeled by data mining, machine learning, deep learning and image embedding are mainly used.
Machine learning is a multi-field cross discipline, and relates to a plurality of disciplines such as probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and the like. The special research on how a computer simulates or realizes the learning behavior of human beings so as to acquire new knowledge or skills and reorganize the existing knowledge structure to continuously improve the performance of the computer. The research direction of the traditional machine learning mainly comprises the research in the aspects of decision trees, random forests, artificial neural networks, Bayesian learning and the like.
Deep Learning (DL) is a new research direction in the field of Machine Learning (ML), which is introduced into Machine Learning to make it closer to the original target, Artificial Intelligence (AI). The concept of deep learning is derived from the research of artificial neural networks, and a multi-layer perceptron comprising a plurality of hidden layers is a deep learning structure. Deep learning forms a more abstract class or feature of high-level representation properties by combining low-level features to discover a distributed feature representation of the data. Currently, common deep learning models include a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN), and the like.
Graph Embedding (also called Network Embedding) is a process for mapping Graph data (usually a high-dimensional dense matrix) into a low-micro dense vector, and can well solve the problem that the Graph data is difficult to be efficiently input into a machine learning algorithm.
The existing industrial chemical worker portrait system is basically that workers are artificially marked in enterprises simply, generally, the portrait system is an information management system of the workers, some basic information of the workers is recorded, and personnel management personnel of the enterprises can artificially mark some labels for the workers according to the ordinary performance of the workers so as to be used for reference later.
The prior art has the defects that the existing industrial man-figure system is too simple in consideration of factors and does not well plan the evaluation dimension of industrial workers. Meanwhile, the existing industrial chemical people portrait system does not well utilize some dynamic data of individual workers. For example, the posture data of workers during construction, the data of workers participating in training and learning, the social evaluation data of workers and the like, which causes that the prior art is excessively dependent on manpower and cannot automatically generate portrait data and evaluation information for the individual workers.
Disclosure of Invention
The invention mainly solves the technical problem of how to provide a mapping model for constructing various types of performance data of workers in an enterprise to the specified evaluation dimension of the workers, provides a relatively objective, accurate and complete worker portrait system for the enterprise through the training of label data and the intervention and correction of manual evaluation, is convenient to use, and has good practical performance.
In order to solve the technical problems, the invention adopts a technical scheme that: the method for evaluating the portrait of the industrialized personnel based on data mining comprises the following operation steps:
s1: setting attribute characteristics of the industrialized personnel portrait, wherein the setting of the attribute characteristics comprises setting of basic attribute characteristics and setting of implicit attribute characteristics;
s2: acquiring personnel performance data of different types, and carrying out preliminary statistics and cleaning on the personnel performance data needing to be modeled;
s3: modeling the implicit attribute characteristics of the industrialized personnel;
s4: and establishing an industrialized personnel portrait evaluation system, calculating a reference total score for industrialized personnel, and performing auxiliary correction on the evaluation of the personnel.
In a preferred embodiment, in the step S1, the implicit attribute feature is set to four dimensions, and meanwhile, a plurality of small indicators are set in the four dimensions, and each small indicator is set with its exact value range and modeling method for determining the small indicator; the four dimensions are: the method comprises the following steps of personnel culture and literacy, personnel skill and literacy, personnel thought and literacy, and personnel physical and mental literacy, wherein the small indexes are divided into discrete types and numerical types.
In a preferred embodiment, the discrete type of small indicators include professional recognition, production safety awareness, work efficiency, learning ability, physical health level, and mental health level.
In a preferred embodiment, in step S3, the value of the professional consent is a discrete type, and the value range is set as: high, medium and low, and a classification model is constructed by using personnel working information, personnel working time information and personnel training information to predict the professional recognition of a certain personnel; the modeling method adopts a supervised learning method, a machine learning classification model or a deep learning classification model is trained, and the real professional acceptance of a certain person is marked in advance by manpower during training.
In a preferred embodiment, in step S3, the value of the manufacturing safety awareness is a discrete type, and the value range is set as: high, medium, low, use person wear safety helmet, trigger danger source, static alarm, fall alarm or call out alarm information to construct classification model to predict a certain person's production safety awareness; the modeling method adopts a supervised learning method, a machine learning classification model or a deep learning classification model is trained, and the real production safety consciousness of a certain person is marked in advance by manpower during training.
In a preferred embodiment, in step S3, the working efficiency value is a discrete type, and the value range is set as: high, medium and low, and the working efficiency of a certain person is quantified by using time or sequence data of different working faces completed by the person in the working time information of the person; the maximum and minimum values of time statistics of different working faces of a certain person are counted or the distribution analysis of the sequence is carried out, and then corresponding threshold values are set and classified into three categories, namely high category, medium category and low category.
In a preferred embodiment, in step S3, the learning ability value is a discrete type, and the value range is set as: the method for modeling adopts a supervised learning method, trains a machine learning classification model or a deep learning classification model, performs time sequence modeling on learning training data and assessment data of a person when characterizing and reducing dimensions of the person training information, and estimates the real learning ability of the person by manually marking in advance or by an education big data analysis method.
In a preferred embodiment, in step S3, the value of the physical health degree is a discrete type, and the value range is set as: high, medium and low, and is directly evaluated according to the physical health data of the person in other data or evaluated by using a means of health big data analysis.
In a preferred embodiment, in step S3, the mental health level is a discrete type, and the value range is set as: high, medium, low, directly evaluated from the mental health data of the person among other data or evaluated by means of analysis of big health data.
In a preferred embodiment, the small indicators of the numerical type include the ability to collaborate, the technical quality, the cultural basis and the professional knowledge.
In a preferred embodiment, in step S3, the human cooperation capability value is a numerical type, and the range of the numerical type is set as: 0-100, using the social evaluation information of the personnel to construct a regression model to predict the interpersonal cooperation ability of a certain person, adopting a supervised learning method as a modeling method, firstly, carrying out feature dimension reduction on network structure features obtained by the social evaluation information of the personnel by adopting a graph embedding method, then, inputting the features into a deep learning model to obtain output, and marking the real interpersonal cooperation ability of a certain person in advance by manpower during training.
In a preferred embodiment, in step S3, the technical quality value is a numerical type, and the value range is set as: 0-100, constructing a regression model by using personnel position information, personnel posture information, personnel working time information and personnel training information to predict the technical quality of a certain personnel; the modeling method adopts a supervised learning method, a machine learning classification model or a deep learning classification model is trained, and the real technical quality of a certain person is marked in advance by manual work during training.
In a preferred embodiment, in step S3, the value of the culture base is a numerical type, and the value range is set as: and 0-100, quantifying the culture basis of a certain person by using the basic academic aptitude information of the person in other data of the person, and setting a specific mapping rule from the basic academic aptitude information of the certain person to the evaluation score.
In a preferred embodiment, in step S3, the value of the professional knowledge is a numerical type, and the value range is set as: 0-100, quantifying the professional knowledge of a certain person by using the time sequence change or the time sequence characteristics of the person training assessment results in the person training information; and performing distribution analysis on the maximum value and the minimum value of all the assessment results of the statistical personnel or the assessment result sequence to obtain a value which can represent the average assessment result of the personnel and is used as the assessment of the professional knowledge level.
In a preferred embodiment, in step S4, reference evaluation scores are respectively obtained for the four set implicit feature dimensions, the scores are obtained by performing numerical normalization and weighted summation on 10 specific implicit feature indexes, the specific weights are set by a user, and finally, a reference total score is calculated for an industrialization worker, and the scores are obtained by weighting the scores of the four set implicit feature dimensions; meanwhile, the personnel department carries out auxiliary correction on the four-dimensional evaluation of the personnel by manpower.
The invention has the beneficial effects that: the method has the advantages that various types of performance data of workers in an enterprise are constructed to the mapping model of the specified evaluation dimension of the workers, and objective, accurate and complete worker portrait system is provided for the enterprise through training of label data and intervention and correction of manual evaluation, so that the method is convenient to use and has good practical performance.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without inventive efforts, wherein:
FIG. 1 is a diagram illustrating the setting of attribute features of an industrial worker image according to an embodiment of the method for evaluating an industrial worker image based on data mining;
FIG. 2 is a schematic diagram of data included in worker working information according to an embodiment of the method for evaluating an industrial person profile based on data mining;
FIG. 3 is a schematic diagram of data included in worker training information according to an embodiment of the data mining-based method for evaluating an image of an industrial person;
FIG. 4 is a schematic diagram of data included in worker location information according to an embodiment of the data mining-based method for evaluating an image of an industrial person;
FIG. 5 is a schematic diagram of data included in worker working time information according to an embodiment of the method for evaluating an image of an industrial person based on data mining;
FIG. 6 is a schematic diagram of data included in worker pose information according to an embodiment of the method for evaluating an industrial person representation based on data mining;
FIG. 7 is a diagram illustrating data contained in a worker wearing a safety helmet/triggering hazard source/static alarm/fall alarm/call alarm message according to an embodiment of the data mining-based industrial personnel image evaluation method of the present invention;
FIG. 8 is a schematic diagram of data included in worker social evaluation information according to an embodiment of the data mining-based method for evaluating an industrial person representation according to the present invention;
FIG. 9 is a schematic diagram of data included in other information of workers in an embodiment of the data mining-based industrial personnel image evaluation method of the present invention;
FIG. 10 is a diagram illustrating the value range of professional recognition and modeling method according to an embodiment of the data mining-based method for evaluating images of industrial people;
FIG. 11 is a schematic diagram of a value range and modeling method of interpersonal cooperation capability according to an embodiment of the data mining-based industrial person image evaluation method of the present invention;
FIG. 12 is a schematic diagram of a security awareness domain generation and modeling method according to an embodiment of the data mining-based industrial personnel image evaluation method of the present invention;
FIG. 13 is a schematic diagram of a technical quality value range and modeling method according to an embodiment of the data mining-based industrial personnel portrait assessment method of the present invention;
FIG. 14 is a schematic diagram of the working efficiency value range and modeling method of an embodiment of the data mining-based industrial personnel portrait assessment method of the present invention;
FIG. 15 is a diagram of a value range and modeling method of a culture foundation of an embodiment of the data mining-based industrial personnel portrait assessment method of the present invention;
FIG. 16 is a diagram illustrating a learning capability value range and a modeling method according to an embodiment of the data mining-based method for evaluating an image of an industrial person;
FIG. 17 is a diagram illustrating the value range and modeling method of professional knowledge according to an embodiment of the data mining-based method for evaluating an image of an industrial person;
FIG. 18 is a schematic diagram of a value range and a modeling method of a health degree of an embodiment of the data mining-based industrial personnel portrait assessment method of the present invention;
FIG. 19 is a schematic diagram of a mental health level value range and a modeling method according to an embodiment of the data mining-based method for evaluating an image of an industrial person;
FIG. 20 is a schematic diagram of a method for building, scoring and aggregating industrial human representation systems according to an embodiment of the present invention;
FIG. 21 is a flowchart illustrating an industrial worker image system according to an embodiment of the method for evaluating an industrial personnel image based on data mining.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-21, in an embodiment of the present invention, a method for evaluating an industrial personnel image based on data mining is provided, the method for evaluating an industrial personnel image based on data mining includes the following steps:
s1: setting attribute characteristics of the industrialized personnel portrait, wherein the setting of the attribute characteristics comprises setting of basic attribute characteristics and setting of implicit attribute characteristics;
s2: acquiring personnel performance data of different types, and carrying out preliminary statistics and cleaning on the personnel performance data needing to be modeled;
s3: modeling the implicit attribute characteristics of the industrialized personnel;
s4: and establishing an industrialized personnel portrait evaluation system, calculating a reference total score for industrialized personnel, and performing auxiliary correction on the evaluation of the personnel.
In the step S1, the implicit attribute feature is set to four dimensions, and meanwhile, a plurality of small indicators are set in the four dimensions, and each small indicator is set with an exact value range and a modeling method thereof to determine the small indicator; the four dimensions are: the method comprises the following steps of personnel culture and literacy, personnel skill and literacy, personnel thought and literacy, and personnel physical and mental literacy, wherein the small indexes are divided into discrete types and numerical types.
In a specific embodiment, the discrete type of small indicators include professional recognition, production safety awareness, work efficiency, learning ability, physical health degree, and mental health degree.
The value of the professional acceptance is of a discrete type, and the value range is set as follows: high, medium and low, and a classification model is constructed by using personnel working information, personnel working time information and personnel training information to predict the professional recognition of a certain personnel; the modeling method adopts a supervised learning method, a machine learning classification model or a deep learning classification model is trained, and the real professional acceptance of a certain person is marked in advance by manpower during training.
The value of the production safety consciousness is of a discrete type, and the value range is set as follows: high, medium, low, use person wear safety helmet, trigger danger source, static alarm, fall alarm or call out alarm information to construct classification model to predict a certain person's production safety awareness; the modeling method adopts a supervised learning method, a machine learning classification model or a deep learning classification model is trained, and the real production safety consciousness of a certain person is marked in advance by manpower during training.
The value of the working efficiency is of a discrete type, and the value range is set as follows: high, medium and low, and the working efficiency of a certain person is quantified by using time or sequence data of different working faces completed by the person in the working time information of the person; the maximum and minimum values of time statistics of different working faces of a certain person are counted or the distribution analysis of the sequence is carried out, and then corresponding threshold values are set and classified into three categories, namely high category, medium category and low category.
The learning ability value is of a discrete type, and the value range is set as follows: the method for modeling adopts a supervised learning method, trains a machine learning classification model or a deep learning classification model, performs time sequence modeling on learning training data and assessment data of a person when characterizing and reducing dimensions of the person training information, and estimates the real learning ability of the person by manually marking in advance or by an education big data analysis method.
The value of the health degree is of a discrete type, and the value range is set as follows: high, medium and low, and is directly evaluated according to the physical health data of the person in other data or evaluated by using a means of health big data analysis.
The value of the mental health degree is of a discrete type, and the value range is set as follows: high, medium, low, directly evaluated from the mental health data of the person among other data or evaluated by means of analysis of big health data.
In a specific embodiment, the small indicators of the numerical type comprise the actual cooperation ability, the technical quality, the cultural basis and the professional knowledge.
The interpersonal cooperation ability value is a numerical type, and the value range is set as follows: 0-100, using the social evaluation information of the personnel to construct a regression model to predict the interpersonal cooperation ability of a certain person, adopting a supervised learning method as a modeling method, firstly, carrying out feature dimension reduction on network structure features obtained by the social evaluation information of the personnel by adopting a graph embedding method, then, inputting the features into a deep learning model to obtain output, and marking the real interpersonal cooperation ability of a certain person in advance by manpower during training.
The technical quality value is a numerical type, and the value range is set as follows: 0-100, constructing a regression model by using personnel position information, personnel posture information, personnel working time information and personnel training information to predict the technical quality of a certain personnel; the modeling method adopts a supervised learning method, a machine learning classification model or a deep learning classification model is trained, and the real technical quality of a certain person is marked in advance by manual work during training.
The value of the culture foundation is a numerical type, and the value range is set as follows: and 0-100, quantifying the culture basis of a certain person by using the basic academic aptitude information of the person in other data of the person, and setting a specific mapping rule from the basic academic aptitude information of the certain person to the evaluation score.
The value of the occupational knowledge is a numerical type, and the value range is set as follows: 0-100, quantifying the professional knowledge of a certain person by using the time sequence change or the time sequence characteristics of the person training assessment results in the person training information; and performing distribution analysis on the maximum value and the minimum value of all the assessment results of the statistical personnel or the assessment result sequence to obtain a value which can represent the average assessment result of the personnel and is used as the assessment of the professional knowledge level.
According to the setting, in step S4, reference evaluation scores are respectively calculated for the four set hidden feature dimensions, the scores are obtained by 10 specific hidden feature indexes through numerical normalization and weighted summation, the specific weights are set by users, and finally, a reference total score is calculated for industrialization personnel, and the scores are obtained by weighting the previously obtained scores of the four hidden feature dimensions; meanwhile, the personnel department carries out auxiliary correction on the four-dimensional evaluation of the personnel by manpower.
In a specific implementation process, the invention provides a design method of an industrial worker portrait evaluation system based on data mining, aiming at the defects in the design of the existing industrial worker portrait system. The invention constructs a mapping model from various types of performance data of workers in an enterprise to the specified evaluation dimension of the workers, and provides the enterprise with a more objective, accurate and complete worker portrayal system through training of label data and intervention and correction of manual evaluation.
The invention regards the problem of portrait of industrial workers as a multi-dimensional label aggregation problem, and one industrial worker has two main aspects of characterization characteristics, namely basic attribute characteristics and implicit attribute characteristics. Where the basic attribute features are basic information of the worker, such as name, age, gender, etc., as part of the system data visualization and fuzzy analysis. The implicit attribute features are the self-defined features of the present invention, which are predicted by the worker's performance data for each category.
The implicit attribute characteristics in the invention are divided into 4 major categories of thought literacy, skill literacy, cultural literacy and physical and mental literacy, and the major categories comprise a plurality of small indexes.
The invention gives the modeling methods and index value ranges of all small indexes, then obtains the numerical scores of the large classes according to the small indexes, and calculates a reference total score according to the scores of the large classes.
The invention widely adopts a characterization method based on statistical machine learning and deep learning in recent years to mine the basic characteristics and the implicit characteristics in the worker performance data, and then establishes a supervised classification or regression model through characteristic fusion and integrated decision making.
The industrial worker portrait data obtained by the method can be directly used as reference on one hand, and can be used as reference indexes to carry out modeling of a recommendation system in different industrial worker recommendation tasks on the other hand.
Therefore, the invention is mainly protected by the following points,
1. the attribute feature setting of the industrial worker portrait comprises setting of basic attribute features and implicit attribute features.
2. A method for preliminary statistics and cleaning of the performance data of industrialized workers.
3. The modeling method for the industrial chemical human implicit attribute characteristics comprises the steps of value domain setting and specific modeling of each index.
4. A method for establishing an industrial chemical human portrait system and grading and aggregating.
The design scheme of one specific embodiment of the invention is as follows: a design method of an industrial chemical person portrait evaluation system based on data mining comprises the following steps:
firstly, setting attribute characteristics of an industrial worker portrait:
1. the invention establishes two major attribute characteristics for industrial and chemical workers: basic attribute features and implicit attribute features.
2. The basic attribute characteristics defining an industrialized worker are as follows: sex, native place, age, identity card, mobile phone number, work and breed.
3. The implicit attribute features defining the industrialized workers are as follows: the culture and literacy of workers, the skill and literacy of workers, the thought and literacy of workers, and the physical and mental literacy of workers.
Wherein:
the small indexes included in worker culture literacy are defined as follows: a culture foundation; professional knowledge; learning ability.
The small indexes included in the skill quality of a worker are defined as follows: the working quality; and (4) working efficiency.
The small indexes of the thought quality of workers are defined as follows: the consciousness of production safety; degree of professional acceptance; interpersonal collaboration capabilities.
The small indexes included in the physical and mental quality of workers are defined as follows: the degree of physical health; the degree of mental health.
Secondly, a preliminary statistics and cleaning stage of worker performance data for modeling the implicit attribute characteristics of the industrial and chemical workers is carried out:
1. the invention requires enterprises to obtain 8 different types of worker performance data, which are respectively:
worker engagement information; worker training information; worker location information; worker work time information; worker posture information; worker wearing safety helmet/triggering hazard source/static alarm/fall alarm/ground alarm/call alarm information; worker social evaluation information; other information of the worker.
2. The worker-used information includes: the worker converts the number of human units (numerical characteristics); total worker work duration (numerical characteristic); number of worker engagement with a project (numerical features); the worker converts the number of times of the work (numerical characteristic).
3. The worker training information includes: the worker receives the total training duration (numerical characteristic); the ratio of the number of passes of worker training and examination to the total number of passes (numerical characteristics); time sequence variation (time sequence characteristics) of worker training assessment results; worker training attendance to total training times ratio (numerical characteristic).
4. The worker position information includes: the number of times the worker leaves the normal working range on average per day (numerical characteristics); the average time of day the worker leaves the normal working range (numerical characteristic); time series change (time series characteristic) in which the worker leaves the normal working range every day.
5. The worker work time information includes: the ratio of the number of attendance of workers on time to the number of attendance (numerical characteristics); the time variation of workers on different working planes every day (multidimensional time series data); time (sequence data) when workers complete different working planes;
6. worker posture information includes: sequence information of worker stillness/movement (sampled for many days) (matrix characterization); worker helmet ambient temperature sequence information (which may be sampled for multiple days) (matrix characterization); worker helmet remaining capacity sequence information (which can be sampled for a plurality of days) (matrix characteristics).
7. Worker wearing safety helmet/triggering hazard source/static alarm/fall alarm/ground alarm/call alarm information includes: workers triggered the total number of times (numerical features) that "no alarm worn"/"hazard approach alarm"/"stationary alarm"/"fall alarm"/"land alarm"/"call for help alarm"; the worker triggers a "unworn alarm"/"hazard approach alarm"/"stationary alarm"/"fall alarm"/"falling alarm"/"call for help alarm" time series change (time series feature).
8. The worker social evaluation information includes: obtaining evaluation data of workers recognizing other workers by themselves through questionnaire survey and other forms, surveying the cooperative satisfaction (percentage system) of a certain worker to other workers, and then converting the data into network structure characteristics: the nodes represent each worker, the directed edges represent that a worker knows other workers, the edges are the cooperation satisfaction, and the network reflects the social information and evaluation information among the workers.
9. Other worker information includes: basic student calendar information of workers; worker physical health data (obtained from worker previous physical records); worker mental health data (obtained from mental test data of the worker, past psychological history).
Then modeling the implicit attribute characteristics of the industrial chemical workers:
1. the implicit attribute characteristics of the industrialized workers comprise four dimensions of worker culture literacy, worker skill literacy, worker thought literacy and worker physical and mental literacy, and the four dimensions have 10 small indexes in total, and the exact value range and the modeling method of the 10 small indexes are specified in the stage.
2. The value of the professional acceptance is of a discrete type, and the specified value range is as follows: (high, medium, low). A classification model is constructed by using worker working information, worker working time information and worker training information to predict the professional acceptance of a certain worker. The modeling method adopts a supervised learning method, a machine learning classification model or a deep learning classification model is trained, and the real professional acceptance of a certain worker is marked in advance by manpower during training.
3. The interpersonal cooperation ability value is a numerical type, and the specified value range is as follows: (0-100). A regression model will be constructed using worker social evaluation information to predict the interpersonal cooperation ability of a worker. The modeling method adopts a supervised learning method, firstly, the network structure characteristics obtained by the social evaluation information of workers are subjected to characteristic dimension reduction by adopting a Graph Embedding (Graph Embedding) method, then the characteristics are input into a deep learning model to obtain output, and the real interpersonal cooperation capability of a certain worker is marked in advance by manpower during training.
4. The value of the production safety consciousness is of a discrete type, and the specified value range is as follows: (high, medium, low). A classification model will be built using worker-worn headgear/triggered hazard source/stationary alarm/fall alarm/call alarm information to predict production safety awareness for a worker. The modeling method adopts a supervised learning method, a machine learning classification model or a deep learning classification model is trained, and the real production safety consciousness of a certain worker is marked in advance by manpower during training.
5. The technical quality value is a numerical type, and the specified value range is as follows: (0-100). The technical quality of a certain worker is predicted by constructing a regression model by using worker position information, worker posture information, worker working time information and worker training information. The modeling method adopts a supervised learning method, a machine learning classification model or a deep learning classification model is trained, and the real technical quality of a certain worker is marked in advance by manual work during training.
6. The value of the working efficiency is of a discrete type, and the specified value range is as follows: (high, medium, low). The time (sequence data) for workers to complete different work planes in the worker work time information is used to quantify the work efficiency of a certain worker. The maximum and minimum values of time statistics of different working faces of a certain worker are counted or the distribution analysis of the sequence is carried out, and then corresponding threshold values are set to classify the workers into three categories, namely high category, medium category and low category.
7. The value of the culture basis is a numerical type, and the specified value range is as follows: (0-100). The basic academic information of the worker in other data of the worker is used for quantifying the cultural basis of the worker, and a specific mapping rule from the basic academic information of the worker to the evaluation score is set.
8. The learning ability value is a discrete type, and the specified value range is as follows: (high, medium, low). A classification model will be constructed using worker training information to predict the learning ability of a worker. The modeling method adopts a supervised learning method, trains a machine learning classification model or a deep learning classification model, refers to an image method of students in the education field when characterizing and reducing dimensions of worker training information, and carries out time sequence modeling on learning training data and assessment data of workers, wherein the real learning ability of a certain worker during training is estimated by manually marking in advance or by an education big data analysis method.
9. The value of the occupational knowledge is a numerical type, and the specified value range is as follows: (0-100). The temporal variation (time series characteristics) of the worker training assessment results in the worker training information will be used to quantify the professional knowledge of a certain worker. And counting the maximum value and the minimum value of all the assessment results of the workers or performing distribution analysis on the assessment result sequence to obtain a value which can represent the average assessment result of the workers and is used as the assessment of the professional knowledge level.
10. The value of the health degree is of a discrete type, and the specified value range is as follows: (high, medium, low).
The evaluation result is directly obtained by a hospital expert according to the physical health data of workers in other data of the workers, and the conditional company can also evaluate the physical health data by using a health big data analysis means.
11. The value of the mental health degree is of a discrete type, and the specified value range is as follows: (high, medium, low).
The evaluation result is directly obtained by hospital experts according to the mental health data of workers in other data of the workers, and the evaluation result can be also evaluated by a conditional company by using a health big data analysis means.
And finally, establishing and grading aggregation stage of an industrial chemical human portrait system:
in the stage, reference evaluation scores are respectively calculated for four specified hidden feature dimensions, the scores are obtained by carrying out numerical value normalization and weighted summation on 10 specific hidden feature indexes, and specific weights are set by enterprises. The total score of a reference is calculated for the industrialization worker, and the score is obtained by weighting the scores of the four dimensions obtained previously. Meanwhile, for the reliability of scoring, the personnel department of the enterprise corrects the four-dimensional evaluation of workers in an auxiliary way.
In a specific industrial implementation process, the invention also provides the following specific examples:
first, the attribute feature setting stage of the industrial worker image is shown in fig. 1, which shows the basic attribute feature and the implicit attribute feature defined in the present invention.
Secondly, in the initial statistics and cleaning stage of the worker performance data for modeling the implicit attribute characteristics of the industrial and chemical workers, the invention needs the enterprise to obtain 8 different types of worker performance data, as shown in fig. 2-9: worker engagement information; worker training information; worker location information; worker work time information; worker posture information; worker wearing safety helmet/triggering hazard source/static alarm/fall alarm/ground alarm/call alarm information; worker social evaluation information; other information of the worker. Wherein each type of information comprises one or more different types of characteristic data.
The modeling stage of the hidden attribute characteristics of the industrial and chemical people is shown in fig. 10-19, which are respectively a value range and a modeling mode schematic diagram of the occupation identity, the interpersonal cooperation capability, the production safety awareness, the technical quality, the working efficiency, the cultural foundation, the learning capability, the occupation knowledge, the physical health degree and the mental health degree.
In fig. 10-13, ML is machine learning and DL is deep learning.
Finally, the establishment and scoring aggregation stage of the industrial chemical human representation system is shown in fig. 20, which is a schematic diagram of the whole process. The above steps are the basic steps established for the whole industrial chemical people portrait system.
In reality, an enterprise needs to build a worker portrait system according to the present invention, as shown in fig. 21, which is a general flow chart for founders, and the core of the general flow chart is three major parts, namely a data side, a model side and an application side.
Wherein:
the data end is divided into two parts, one part is the basic attribute characteristics of workers (name, gender, native place, age, identity card, mobile phone number, work category). The data can be used for generating a plurality of highly summarized charts for enterprise reference by using a data statistics and visualization method. The other part is collected worker performance data, and the data needs to be subjected to statistics and cleaning steps to obtain characteristic data of numerical values, time series, matrixes and the like.
And (3) a model end, wherein the main function of the model end is to train a required mapping model. And training the multi-type worker performance characteristic data obtained by the data terminal and part of worker implicit attribute index data marked manually according to different modeling methods to obtain a prediction model. The model can calculate 10 worker hidden attribute indexes according to new feature input, then obtains scores and total scores of different dimensions through normalization and weighting calculation, and corrects the scores through evaluation data of enterprise personnel departments. All of the above data constitutes an image of the industrial worker.
And the application end is used for responding to the application requirements of the enterprise, and the specific function of the application end is socialized by the enterprise. The embodiment designs two functional examples for the application end: the application end can firstly view index data values of all aspects of workers, wherein the index data values comprise implicit attribute characteristic values predicted by charts and models generated by basic attribute characteristics. A quantitative reference may be provided for business assessment workers. And secondly, when an enterprise needs to select workers, the model can be trained together with worker portrait data obtained by model prediction according to different requirements, so that the purpose of personalized recommendation of industrialized workers is achieved.
Therefore, the invention has the following advantages:
1. compared with the existing industrial chemical people portrait system, the method has more detailed and reasonable attribute feature division. The basic attribute characteristics are basic information of workers, and belong to parts of various types of worker representation systems. The implicit attribute features are original creation of the invention, and the features which cannot be directly obtained by industrial workers are divided into 10 indexes which are 4 categories. The indexes comprehensively reflect the evaluation measures of a productive industrial worker in the aspects of culture, thought, health and skill, and have great value for enterprises.
2. The method is based on a series of technical means of data mining, and the values of the implicit evaluation indexes are obtained by utilizing the expression data of various types of industrialized workers. Particularly, the modeling of part of implicit evaluation indexes is regarded as a supervised learning problem by using the very popular artificial intelligence technology in recent years, such as machine learning, deep learning, graph embedding and the like. Only a part of artificially marked data is used for training, and then the trained model can be used for directly inputting the required worker performance data to obtain the predicted value of the corresponding implicit evaluation index, so that the method is very convenient and fast.
3. The intelligent and informatization pace of the enterprise can be improved, the enterprise is free from the traditional personnel management mode, and the trend of novel enterprise construction and engineering management in the big data era is met.
4. The invention adds manual data correction while establishing the model by using the data mining technology, so that the worker portrays more accurately.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by the present specification, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (15)
1. A design method of an industrialization personnel portrait evaluation system based on data mining is characterized by comprising the following operation steps:
s1: setting attribute characteristics of the industrialized personnel portrait, wherein the setting of the attribute characteristics comprises setting of basic attribute characteristics and setting of implicit attribute characteristics;
s2: acquiring personnel performance data of different types, and carrying out preliminary statistics and cleaning on the personnel performance data needing to be modeled;
s3: modeling the implicit attribute characteristics of the industrialized personnel;
s4: and establishing an industrialized personnel portrait evaluation system, calculating a reference total score for industrialized personnel, and performing auxiliary correction on the evaluation of the personnel.
2. The method for designing an industrial personnel portrait evaluation system based on data mining as claimed in claim 1, wherein in step S1, the implicit attribute features are set to four dimensions, meanwhile, a plurality of small indexes are set in the four dimensions, and each small index is set with its exact value range and modeling method for judgment; the four dimensions are: the method comprises the following steps of personnel culture and literacy, personnel skill and literacy, personnel thought and literacy, and personnel physical and mental literacy, wherein the small indexes are divided into discrete types and numerical types.
3. The method as claimed in claim 2, wherein the discrete type of small indicators include professional recognition, production safety awareness, work efficiency, learning ability, physical health degree, and mental health degree.
4. The method of claim 3, wherein in step S3, the professional recognition value is a discrete type with a range of values set as: high, medium and low, and a classification model is constructed by using personnel working information, personnel working time information and personnel training information to predict the professional recognition of a certain personnel; the modeling method adopts a supervised learning method, a machine learning classification model or a deep learning classification model is trained, and the real professional acceptance of a certain person is marked in advance by manpower during training.
5. The method for designing an industrial personnel image evaluation system based on data mining according to claim 3, wherein in step S3, the value of the production safety awareness is of a discrete type, and the value range is set as: high, medium, low, use person wear safety helmet, trigger danger source, static alarm, fall alarm or call out alarm information to construct classification model to predict a certain person's production safety awareness; the modeling method adopts a supervised learning method, a machine learning classification model or a deep learning classification model is trained, and the real production safety consciousness of a certain person is marked in advance by manpower during training.
6. The method of claim 3, wherein in step S3, the working efficiency is of a discrete type and the range of values is set as: high, medium and low, and the working efficiency of a certain person is quantified by using time or sequence data of different working faces completed by the person in the working time information of the person; the maximum and minimum values of time statistics of different working faces of a certain person are counted or the distribution analysis of the sequence is carried out, and then corresponding threshold values are set and classified into three categories, namely high category, medium category and low category.
7. The method of claim 3, wherein in step S3, the learning ability value is of a discrete type and the value range is set as: the method for modeling adopts a supervised learning method, trains a machine learning classification model or a deep learning classification model, performs time sequence modeling on learning training data and assessment data of a person when characterizing and reducing dimensions of the person training information, and estimates the real learning ability of the person by manually marking in advance or by an education big data analysis method.
8. The method of claim 3, wherein in step S3, the value of the health degree is a discrete type, and the value range is set as: high, medium and low, and is directly evaluated according to the physical health data of the person in other data or evaluated by using a means of health big data analysis.
9. The method of claim 3, wherein in step S3, the mental health level is a discrete type with a range of values set as: high, medium, low, directly evaluated from the mental health data of the person among other data or evaluated by means of analysis of big health data.
10. The design method of the data mining-based industrialization person representation evaluation system, as claimed in claim 2, wherein the small indicators of the numerical type comprise an inter-collaboration ability, a technical quality, a cultural basis and an occupational knowledge.
11. The method of claim 10, wherein in step S3, the interpersonal cooperation ability is of a numerical type and the range is set as: 0-100, using the social evaluation information of the personnel to construct a regression model to predict the interpersonal cooperation ability of a certain person, adopting a supervised learning method as a modeling method, firstly, carrying out feature dimension reduction on network structure features obtained by the social evaluation information of the personnel by adopting a graph embedding method, then, inputting the features into a deep learning model to obtain output, and marking the real interpersonal cooperation ability of a certain person in advance by manpower during training.
12. The method of claim 10, wherein in step S3, the technical quality value is a numerical type, and the value range is set as: 0-100, constructing a regression model by using personnel position information, personnel posture information, personnel working time information and personnel training information to predict the technical quality of a certain personnel; the modeling method adopts a supervised learning method, a machine learning classification model or a deep learning classification model is trained, and the real technical quality of a certain person is marked in advance by manual work during training.
13. The method of claim 10, wherein in step S3, the cultural base is a numerical type with a range of values: and 0-100, quantifying the culture basis of a certain person by using the basic academic aptitude information of the person in other data of the person, and setting a specific mapping rule from the basic academic aptitude information of the certain person to the evaluation score.
14. The method of claim 10, wherein in step S3, the professional knowledge values are numerical types and the value ranges are set as follows: 0-100, quantifying the professional knowledge of a certain person by using the time sequence change or the time sequence characteristics of the person training assessment results in the person training information; and performing distribution analysis on the maximum value and the minimum value of all the assessment results of the statistical personnel or the assessment result sequence to obtain a value which can represent the average assessment result of the personnel and is used as the assessment of the professional knowledge level.
15. The method for designing an industrialization person portrait evaluation system based on data mining according to any one of claims 3 to 14, wherein in step S4, reference evaluation scores are respectively found for four set implicit feature dimensions, the scores are obtained by 10 specific implicit feature indexes through numerical normalization and weighted summation, specific weights are set by users, finally, a reference total score is calculated for industrialization persons, and the scores are obtained by weighting the previously obtained scores of the four dimensions; meanwhile, the personnel department carries out auxiliary correction on the four-dimensional evaluation of the personnel by manpower.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010736538.4A CN111967729A (en) | 2020-07-28 | 2020-07-28 | Industrialized personnel portrait evaluation method based on data mining |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010736538.4A CN111967729A (en) | 2020-07-28 | 2020-07-28 | Industrialized personnel portrait evaluation method based on data mining |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111967729A true CN111967729A (en) | 2020-11-20 |
Family
ID=73362926
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010736538.4A Pending CN111967729A (en) | 2020-07-28 | 2020-07-28 | Industrialized personnel portrait evaluation method based on data mining |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111967729A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112988724A (en) * | 2021-02-19 | 2021-06-18 | 北京明略软件***有限公司 | Work efficiency data acquisition method and system |
CN113128876A (en) * | 2021-04-22 | 2021-07-16 | 北京房江湖科技有限公司 | Image-based object management method, device and computer-readable storage medium |
CN113220463A (en) * | 2021-05-31 | 2021-08-06 | 中科曙光国际信息产业有限公司 | Binding strategy inference method and device, electronic equipment and storage medium |
CN114399205A (en) * | 2022-01-17 | 2022-04-26 | 禅境科技股份有限公司 | Procedural evaluation method, system and equipment suitable for project collaboration |
WO2022179446A1 (en) * | 2021-02-26 | 2022-09-01 | 一智科技有限公司 | Method and system for providing profile label for contractor |
CN115098741A (en) * | 2021-11-23 | 2022-09-23 | 国网浙江省电力有限公司丽水供电公司 | Feature portrait construction method for power operators |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001076032A (en) * | 1999-09-03 | 2001-03-23 | Teru Nishiyama | Personel ability rating system |
CN108256022A (en) * | 2018-01-10 | 2018-07-06 | 广东轩辕网络科技股份有限公司 | Talent evaluation model building method and personnel evaluation methods and system |
CN110135976A (en) * | 2019-04-23 | 2019-08-16 | 上海淇玥信息技术有限公司 | User's portrait generation method, device, electronic equipment and computer-readable medium |
JP2019139521A (en) * | 2018-02-09 | 2019-08-22 | ヤフー株式会社 | Prediction device, prediction method, and prediction program |
JP2020077361A (en) * | 2018-11-05 | 2020-05-21 | 株式会社トランス | Learning model building device, after-employment evaluation predicting device, learning model building method, and after-employment evaluation prediction method |
-
2020
- 2020-07-28 CN CN202010736538.4A patent/CN111967729A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001076032A (en) * | 1999-09-03 | 2001-03-23 | Teru Nishiyama | Personel ability rating system |
CN108256022A (en) * | 2018-01-10 | 2018-07-06 | 广东轩辕网络科技股份有限公司 | Talent evaluation model building method and personnel evaluation methods and system |
JP2019139521A (en) * | 2018-02-09 | 2019-08-22 | ヤフー株式会社 | Prediction device, prediction method, and prediction program |
JP2020077361A (en) * | 2018-11-05 | 2020-05-21 | 株式会社トランス | Learning model building device, after-employment evaluation predicting device, learning model building method, and after-employment evaluation prediction method |
CN110135976A (en) * | 2019-04-23 | 2019-08-16 | 上海淇玥信息技术有限公司 | User's portrait generation method, device, electronic equipment and computer-readable medium |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112988724A (en) * | 2021-02-19 | 2021-06-18 | 北京明略软件***有限公司 | Work efficiency data acquisition method and system |
WO2022179446A1 (en) * | 2021-02-26 | 2022-09-01 | 一智科技有限公司 | Method and system for providing profile label for contractor |
CN113128876A (en) * | 2021-04-22 | 2021-07-16 | 北京房江湖科技有限公司 | Image-based object management method, device and computer-readable storage medium |
CN113220463A (en) * | 2021-05-31 | 2021-08-06 | 中科曙光国际信息产业有限公司 | Binding strategy inference method and device, electronic equipment and storage medium |
CN113220463B (en) * | 2021-05-31 | 2022-09-06 | 中科曙光国际信息产业有限公司 | Binding strategy inference method and device, electronic equipment and storage medium |
CN115098741A (en) * | 2021-11-23 | 2022-09-23 | 国网浙江省电力有限公司丽水供电公司 | Feature portrait construction method for power operators |
CN114399205A (en) * | 2022-01-17 | 2022-04-26 | 禅境科技股份有限公司 | Procedural evaluation method, system and equipment suitable for project collaboration |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111967729A (en) | Industrialized personnel portrait evaluation method based on data mining | |
AU2018101946A4 (en) | Geographical multivariate flow data spatio-temporal autocorrelation analysis method based on cellular automaton | |
Ballas et al. | SimBritain: a spatial microsimulation approach to population dynamics | |
CN111260514A (en) | Student score prediction method based on campus big data | |
CN111950708B (en) | Neural network structure and method for finding daily life habits of college students | |
CN108596420A (en) | A kind of talent assessment system and method for Behavior-based control | |
CN117591944B (en) | Learning early warning method and system for big data analysis | |
CN112256755A (en) | Student abnormal behavior analysis method based on deep learning | |
CN111159763A (en) | System and method for analyzing portrait of law-related personnel group | |
Searle et al. | Modelling forced migration: A framework for conflict-induced forced migration modelling according to an agent-based approach | |
Boateng et al. | Agent-based modeling framework for modeling the effect of information diffusion on community acceptance of mining | |
Yao et al. | Prediction of crime hotspots based on spatial factors of random forest | |
Qin et al. | [Retracted] Evaluation of College Students’ Ideological and Political Education Management Based on Wireless Network and Artificial Intelligence with Big Data Technology | |
CN117726162A (en) | Community risk level assessment method and system based on multi-mode data fusion | |
Mare et al. | Spatial inequality, neighborhood mobility, and residential segregation | |
Chen et al. | A study on the rare factors exploration of learning effectiveness by using fuzzy data mining | |
Vegega et al. | Evaluation of the bias in the management of patient’s appointments in a pediatric office | |
CN114491078A (en) | Community project personnel foothold and peer personnel analysis method based on knowledge graph | |
Nasir et al. | An Agent Based Model for Diffusion of Smart Grid Technology in the Society | |
Roumpani et al. | Data-driven modelling of public library infrastructure and usage in the United Kingdom | |
Farmer | Commuting flows & local labour markets: Spatial interaction modelling of travel-to-work | |
Han et al. | Exploring commercial gentrification using Instagram data | |
Palczewska et al. | RobustSPAM for inference from noisy longitudinal data and preservation of privacy | |
Nandar et al. | Jobs Prediction Model based on Myanmar Labor Force Survey by using Artificial Neural Network | |
CN112561598B (en) | Customer loss prediction and retrieval method and system based on customer portrayal |
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 |