CN109271593A - Military project group personal information labeling process based on cluster - Google Patents
Military project group personal information labeling process based on cluster Download PDFInfo
- Publication number
- CN109271593A CN109271593A CN201811315268.9A CN201811315268A CN109271593A CN 109271593 A CN109271593 A CN 109271593A CN 201811315268 A CN201811315268 A CN 201811315268A CN 109271593 A CN109271593 A CN 109271593A
- Authority
- CN
- China
- Prior art keywords
- military project
- project group
- module
- neural network
- data
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
Abstract
The invention belongs to information processing and analysis technical fields, more particularly to a kind of military project group personal information labeling process based on cluster, this method is implemented based on labeling system, the system comprises: data collection module, data preprocessing module, machine learning neural network clustering module, tag generation module, label application module；Compared with prior art, technical solution of the present invention can be quickly to enterprise personnel labeling, and real-time update label information, in real time into quasi- and comprehensively to enterprise personnel evaluation.And can continuous optimization neural network so that cluster more comprehensively, accuracy it is higher.Wherein, it is based on machine learning neural network clustering algorithm, by the inherent law and essential attribute in Automatic-searching sample, self-organizing, adaptive change mesh parameter and mechanism can be accurate and comprehensively to employee information cluster.Also, high fault-tolerant ability is had based on machine learning neural network clustering algorithm, clustering information is precisely and comprehensive.
Description
Technical field
The invention belongs to information processing and analysis technical fields, and in particular to a kind of military project group personnel letter based on cluster
Cease labeling process.
Background technique
Select in military project group personnel, in post scheduling, often use for reference essential information, the annual appraisal result examination of worker with
And subjective evaluation etc., but these information cannot all cover the value and devotion degree of employee's routine work.And pass through
And behavioral data information labels static to the personnel in drainage of human resources, portal, operation system, can be precisely and comprehensive
One employee is assessed, is examined, while personal information labeling can also be applied to precision marketing, data application and user
Analysis etc..When to employee information labeling, need to obtain portal, the behavioural information of personnel and manpower money in operation system
The basic static information in source, how effectively to static state and behavioral data as the main problem that label is that clustering algorithm solves.Often
Clustering algorithm includes: that K-mean algorithm can quickly, be simply gathered to data based on the almost distance between sample point
Class；DBSCAN is connected sufficiently large adjacent area based on Density Clustering, can effectively handle abnormal data；Hierarchical
Based on this cluster of layer, the decomposition of level is carried out to data set, until certain condition meets.Military enterprise personnel are believed by cluster
When ceasing labeling, the cluster of personal information is may be implemented in most of clustering method, but all there is certain deficiency.K-mean
Algorithm can quickly, simply to data clusters, but to the unknown sense of abnormal data；DBSCAN is based on Density Clustering can be effective
Abnormal data is handled, but it is unobvious to sparse data clustering effect, it effectively cannot comprehensively cluster；Hierarchical is based on
This clusters similar greedy algorithm to layer, can only local optimum.
Summary of the invention
(1) technical problems to be solved
The technical problem to be solved by the present invention is how to be directed to military enterprise personnel static state and behavioural information fast tag
Change, in order to military project group personnel select, post scheduling etc..
(2) technical solution
In order to solve the above technical problems, the present invention provides a kind of personal information labeling side of military project group based on cluster
Method, this method are implemented based on military project group personal information labeling system, the system comprises: data collection module, data
Preprocessing module, machine learning neural network clustering module, tag generation module, label application module；
Described method includes following steps:
Step 1: military project group personnel in military project group human resource system are collected and summarized to the data collection module
The behavioral data of military project group personnel in static data and portal, operation system；
Step 2: the data preprocessing module to the static data of the military project group personnel being collected into and behavioral data into
Row cleaning, smooth noise, remove exceptional value completion missing values, obtain the use of the military project group personnel of pretreated vector form
User data；
Step 3: the machine learning neural network clustering module includes input layer and output layer, and input layer receives data
Preprocessing module treated user data；Its output layer, also referred to as competition layer are gathered using based on machine learning neural network
Neuron is arranged in two-dimensional space by class algorithm in a matrix fashion, the user of one of node on behalf military project group personnel
A result of the data after clustering operation；Wherein, in neural network, cluster calculating process in weight be first with compared with
Small random value initialization, then multiplies to update weight according to initial personal information and weight vector difference, completes neural network
Network design；
Step 4: the tag generation module is exported according to the neural network of machine learning neural network clustering module, and root
Rule is set according to presetting user tag, is selected in conjunction with military project group personnel and the demand of post scheduling, formation is corresponding
User tag, and real-time iterative is changed according to personal information and updates user tag information；
Step 5: the label application module realizes showing for military project group personal information labeling, passes through military project people from group
The information of member's label and by the calculated corresponding demand similarity of label is selected and post to be used for military project group personnel
Scheduling.
(3) beneficial effect
Compared with prior art, technical solution proposed by the present invention can be and real quickly to enterprise personnel labeling
Shi Gengxin label information, in real time into standard and comprehensively to enterprise personnel evaluation.And can continuous optimization neural network,
So that cluster more comprehensively, accuracy it is higher.
Wherein, it is based on machine learning neural network clustering algorithm, passes through the inherent law and essence in Automatic-searching sample
Attribute, self-organizing, adaptive change mesh parameter and mechanism can be accurate and comprehensively to employee information cluster.
Also, high fault-tolerant ability is had based on machine learning neural network clustering algorithm, clustering information is precisely and comprehensive.
Detailed description of the invention
Fig. 1 is technical solution of the present invention schematic diagram.
Specific embodiment
To keep the purpose of the present invention, content and advantage clearer, with reference to the accompanying drawings and examples, to of the invention
Specific embodiment is described in further detail.
To solve prior art problem, the present invention provides a kind of personal information labeling system of military project group based on cluster
System comprising: data collection module, data preprocessing module, machine learning neural network clustering module, tag generation module,
Label application module；
The data collection module is used to collect and summarize the quiet of military project group personnel in military project group human resource system
The behavioral data of military project group personnel in state data and portal, operation system；
The data preprocessing module is used to carry out the static data and behavioral data of the military project group personnel being collected into
Cleaning, smooth noise, remove exceptional value completion missing values, obtain the user of the military project group personnel of pretreated vector form
Data；
The machine learning neural network clustering module includes input layer and output layer, and input layer is pre- for receiving data
Processing module treated user data；Its output layer, also referred to as competition layer, for gathering using based on machine learning neural network
Neuron is arranged in two-dimensional space by class algorithm in a matrix fashion, the user of one of node on behalf military project group personnel
A result of the data after clustering operation；Wherein, in neural network, cluster calculating process in weight be first with compared with
Small random value initialization, then multiplies to update weight according to initial personal information and weight vector difference, completes neural network
Network design；
The tag generation module is used to be exported according to the neural network of machine learning neural network clustering module, and according to
Presetting user tag sets rule, selects in conjunction with military project group personnel and the demand of post scheduling, forms corresponding use
Family label, and real-time iterative is changed according to personal information and updates user tag information；
Label application module the showing for realizing military project group personal information labeling, pass through military project group personnel
The information of label and by the calculated corresponding demand similarity of label is selected and post tune to be used for military project group personnel
Degree.
In addition, the present invention also provides a kind of military project group personal information labeling process based on cluster, this method are based on
Military project group personal information labeling system is implemented, the system comprises: data collection module, data preprocessing module, machine
Device learning neural network cluster module, tag generation module, label application module；
As shown in Figure 1, described method includes following steps:
Step 1: military project group personnel in military project group human resource system are collected and summarized to the data collection module
The behavioral data of military project group personnel in static data and portal, operation system；
Step 2: the data preprocessing module to the static data of the military project group personnel being collected into and behavioral data into
Row cleaning, smooth noise, remove exceptional value completion missing values, obtain the use of the military project group personnel of pretreated vector form
User data；
Step 3: the machine learning neural network clustering module includes input layer and output layer, and input layer receives data
Preprocessing module treated user data；Its output layer, also referred to as competition layer are gathered using based on machine learning neural network
Neuron is arranged in two-dimensional space by class algorithm in a matrix fashion, the user of one of node on behalf military project group personnel
A result of the data after clustering operation；Wherein, in neural network, cluster calculating process in weight be first with compared with
Small random value initialization, then multiplies to update weight according to initial personal information and weight vector difference, completes neural network
Network design；
Step 4: the tag generation module is exported according to the neural network of machine learning neural network clustering module, and root
Rule is set according to presetting user tag, is selected in conjunction with military project group personnel and the demand of post scheduling, formation is corresponding
User tag, and real-time iterative is changed according to personal information and updates user tag information；
Step 5: the label application module realizes showing for military project group personal information labeling, passes through military project people from group
The information of member's label and by the calculated corresponding demand similarity of label is selected and post to be used for military project group personnel
Scheduling.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, without departing from the technical principles of the invention, several improvement and deformations can also be made, these improvement and deformations
Also it should be regarded as protection scope of the present invention.
Claims (1)
1. a kind of military project group personal information labeling process based on cluster, which is characterized in that this method is based on military project group
Personal information labeling system is implemented, the system comprises: data collection module, data preprocessing module, machine learning mind
Through network clustering module, tag generation module, label application module；
Described method includes following steps:
Step 1: the static state of military project group personnel in military project group human resource system is collected and summarized to the data collection module
The behavioral data of military project group personnel in data and portal, operation system；
Step 2: the data preprocessing module carries out the static data and behavioral data of the military project group personnel being collected into clear
Reason, smooth noise, remove exceptional value completion missing values, obtain the number of users of the military project group personnel of pretreated vector form
According to；
Step 3: the machine learning neural network clustering module includes input layer and output layer, and input layer receives data and locates in advance
User data after managing resume module；Its output layer, also referred to as competition layer are calculated using based on machine learning neural network clustering
Neuron is arranged in two-dimensional space by method in a matrix fashion, the user data of one of node on behalf military project group personnel
A result after clustering operation；Wherein, in neural network, the weight clustered in calculating process is first with lesser
Random value initialization, then multiplies to update weight according to initial personal information and weight vector difference, completes the net of neural network
The design of lattice structure；
Step 4: the tag generation module is exported according to the neural network of machine learning neural network clustering module, and according to pre-
The user tag of setting sets rule, selects in conjunction with military project group personnel and the demand of post scheduling, forms corresponding user
Label, and real-time iterative is changed according to personal information and updates user tag information；
Step 5: the label application module realizes showing for military project group personal information labeling, is marked by military project group personnel
The information of label and by the calculated corresponding demand similarity of label is selected and post tune to be used for military project group personnel
Degree.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811315268.9A CN109271593A (en) | 2018-11-06 | 2018-11-06 | Military project group personal information labeling process based on cluster |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811315268.9A CN109271593A (en) | 2018-11-06 | 2018-11-06 | Military project group personal information labeling process based on cluster |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109271593A true CN109271593A (en) | 2019-01-25 |
Family
ID=65192292
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811315268.9A Pending CN109271593A (en) | 2018-11-06 | 2018-11-06 | Military project group personal information labeling process based on cluster |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109271593A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114970775A (en) * | 2022-07-29 | 2022-08-30 | 国家国防科技工业局军工项目审核中心 | Clustering-based military industry group personnel information labeling method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060229896A1 (en) * | 2005-04-11 | 2006-10-12 | Howard Rosen | Match-based employment system and method |
| US20130073496A1 (en) * | 2011-09-21 | 2013-03-21 | Botond Szatmary | Tag-based apparatus and methods for neural networks |
| CN106503015A (en) * | 2015-09-07 | 2017-03-15 | 国家计算机网络与信息安全管理中心 | A kind of method for building user's portrait |
| CN108062657A (en) * | 2017-11-30 | 2018-05-22 | 朱学松 | Method and system are interviewed in personnel recruitment |
| CN108256755A (en) * | 2018-01-09 | 2018-07-06 | 信雅达***工程股份有限公司 | A kind of scheduling method for being competent at more job position requests simultaneously based on single employee |
-
2018
- 2018-11-06 CN CN201811315268.9A patent/CN109271593A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060229896A1 (en) * | 2005-04-11 | 2006-10-12 | Howard Rosen | Match-based employment system and method |
| US20130073496A1 (en) * | 2011-09-21 | 2013-03-21 | Botond Szatmary | Tag-based apparatus and methods for neural networks |
| CN106503015A (en) * | 2015-09-07 | 2017-03-15 | 国家计算机网络与信息安全管理中心 | A kind of method for building user's portrait |
| CN108062657A (en) * | 2017-11-30 | 2018-05-22 | 朱学松 | Method and system are interviewed in personnel recruitment |
| CN108256755A (en) * | 2018-01-09 | 2018-07-06 | 信雅达***工程股份有限公司 | A kind of scheduling method for being competent at more job position requests simultaneously based on single employee |
Non-Patent Citations (2)
| Title |
|---|
| 杨倩等: "《陕西省兵工企业管理岗位人岗匹配研究》", 《西安工业大学学报》 * |
| 马刚: "《商务智能》", 31 July 2010, 东北财经大学出版社 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114970775A (en) * | 2022-07-29 | 2022-08-30 | 国家国防科技工业局军工项目审核中心 | Clustering-based military industry group personnel information labeling method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109472490A (en) | Military project group personal information labeling system based on cluster | |
| CN110134786A (en) | A kind of short text classification method based on theme term vector and convolutional neural networks | |
| CN104112026B (en) | A kind of short message text sorting technique and system | |
| CN105893225A (en) | Automatic error processing method and device | |
| KR102236298B1 (en) | Big data-based artificial intelligence integration platform system | |
| CN106557558A (en) | A kind of data analysing method and device | |
| Paramesh et al. | Classifying the unstructured IT service desk tickets using ensemble of classifiers | |
| Radhakrishna et al. | Normal distribution based similarity profiled temporal association pattern mining (N-SPAMINE) | |
| CN110196943A (en) | A kind of position intelligent recommendation system, method and its system | |
| CN109710826A (en) | A kind of internet information artificial intelligence acquisition method and its system | |
| CN109241446A (en) | A kind of position recommended method and system | |
| CN110019703A (en) | Data markers method and device, intelligent answer method and system | |
| CN107729377A (en) | Customer classification method and system based on data mining | |
| Varghese et al. | INFOPLANT: Plant recognition using convolutional neural networks | |
| Meena et al. | Reduced time compression in big data using mapreduce approach and hadoop | |
| US9141686B2 (en) | Risk analysis using unstructured data | |
| CN109271593A (en) | Military project group personal information labeling process based on cluster | |
| CN116644184A (en) | Human Resource Information Management System Based on Data Clustering | |
| Sathyabama et al. | Intelligent Monitoring and Forecasting Using Machine Learning Techniques | |
| CN110717089A (en) | User behavior analysis system and method based on weblog | |
| CN110472122A (en) | A kind of dynamic distributed academic resources acquisition method of multichannel | |
| Bi et al. | Fine-grained tourism demand forecasting: A decomposition ensemble deep learning model | |
| Wibowo et al. | Bumblebee friendly planting recommendations with citizen science data | |
| CN110209941B (en) | Method for maintaining push content pool, push method, device, medium and server | |
| CN115034839A (en) | Office area state detection method and device, storage medium and electronic 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190125 |