CN109635006A - Social security business association rule digging and recommendation apparatus and method based on Apriori - Google Patents
Social security business association rule digging and recommendation apparatus and method based on Apriori Download PDFInfo
- Publication number
- CN109635006A CN109635006A CN201811542221.6A CN201811542221A CN109635006A CN 109635006 A CN109635006 A CN 109635006A CN 201811542221 A CN201811542221 A CN 201811542221A CN 109635006 A CN109635006 A CN 109635006A
- Authority
- CN
- China
- Prior art keywords
- business
- information
- social security
- apriori
- association rule
- 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
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses social security business association rule diggings and recommendation apparatus and method based on Apriori, obtain module, and related data required for obtaining from related data is as analysis data；Social security business association rule module, business diary information, ownness's information based on acquisition, construct Apriori model, the incidence relation between personal attribute and business handling item is obtained by model analysis, generate social security business association rule, and be stored in social security business association rule base, model parameter is continued to optimize using model evaluation index, improves the precision of model；Prediction module, based on social security business association rule base, predict that insured people is possible to the business handled and its prediction result is recommended business handling personnel, form sensed in advance, dynamic analysis and the ability to predict that demand is serviced service object, the working efficiency and quality for improving business handling personnel, to provide personalization, precision, the service of activeization for service object.
Description
Technical field
The present invention relates to computer application technologies, and in particular to a kind of social security business association rule based on Apriori
Then excavation and recommendation apparatus and method.
Background technique
Current social security business handles, the service mode of social security service or a kind of business handling of passive type, passive type,
This outmoded service mode becomes the difficult point for restricting service level and being promoted, pain spot.Lack precisely perception individual demand and service
The ability of experience does not grasp the behavioural characteristic and service condition of individual accurately, can not provide more personalized for service object
Take the initiative in offering a hand.Social security field precipitating has accumulated a large amount of data simultaneously, these data are for science decision, effectively management, clothes
It is that a valuable resource not yet can make full use of data mining for current data application situation for business society
Technology utilizes the data deployment analysis of precipitating accumulation, does not form the ability to predict of service demand, business handler's business
Handle that selection is more, task performance is low, cause service object be lined up it is more, be lined up long, working inconvenience, the problems such as time-consuming.Cause
How this using data mining technology and theory provides more precision, personalized service for the public, become building facilitate it is fast
Victory, justice Pu Hui, high-quality and efficient people society service system important content and inevitable requirement.
Therefore, it is necessary to explore the new technology of one kind to solve the above problems.
Summary of the invention
(1) the technical issues of solving
In view of the deficiencies of the prior art, the present invention provides based on Apriori social security business association rule digging and push away
Device and method is recommended, solves the problems, such as that insurant selection is more, time-consuming for queuing, it is real by generating social security business association rule
The business that prediction insured people's future handles is showed.
(2) technical solution
In order to achieve the above object, the present invention is achieved by the following technical programs: a kind of social security industry based on Apriori
Business association rule mining and recommendation apparatus, for predicting the demand of insurant, the device includes:
Module is obtained, for storing the business diary information and ownness's information of insured people；
Apriori model module is constructed, handles to obtain frequent item set unit by connection certainly and the beta pruning based on confidence level,
The Strong association rule for meeting min confidence is generated from frequent item set unit, then the set of the correlation rule of generation is arranged
Sequence obtains Apriori model；
Social security business association rule module, the information for will acquire module are converted to the data mode of Apriori model,
And be input in Apriori model, analysis obtains the incidence relation between personal attribute and business handling item, obtains social security industry
Business correlation rule；
Prediction module predicts the business to be handled of insured people based on social security business association rule.
Preferably, described device further includes model optimization module, and the model optimization module is based on evaluation index pair
Apriori model optimizes.
Preferably, the acquisition module further include:
Log information acquisition unit and status information generation unit, the log information acquisition unit are based on customized day
Will information collection rule, and the log of related social security operation system is collected and is stored in business diary information；
The status information generation unit for obtaining ownness's information, and by the data generated in business procedure and
The basic data of people is mapped in tag unit and stores into ownness's information.
Preferably, the item collection that the frequent item set unit obtains is to meet all item collections of minimum support threshold value.
Preferably, the business diary information is used to store the service attribute item information of insured people；The ownness
Information is for storing personal attribute information.
Preferably, it is associated between the business diary information and ownness's information by individual ID.
Social security business association rule digging and recommended method based on Apriori, it is characterised in that: wanted for realizing right
Social security business association rule digging and the recommendation apparatus described in 1-6 based on Apriori are sought, the described method comprises the following steps:
Obtain the business diary information and ownness's information of insured people；
Business diary information and ownness's information are converted to the data mode in Apriori model, and data are passed
The defeated frequent item set unit in Apriori model；
By alternative manner Mining Frequent Itemsets Based, and the correlation rule for meeting min confidence is generated in frequent item set；
Based on Apriori model evaluation index, optimize Apriori model, generate social security business association rule, and by social security
Business association rule is stored in business rule base；
When insured people's transacting business, the newest business state information and personal attribute's letter of insured people are obtained and updated
Breath；
Newest business state information and personal attribute information are sent in business rule base, analysis obtains personal attribute
The confidence level of correlation rule and its rule between item and business handling item；
The correlation rule of generation is sorted, obtains the maximum correlation rule of confidence level as prediction rule, and prediction is tied
Fruit recommends business personnel.
Preferably, the method also includes being stored in business diary for business information after insured people completes business
In information.
(3) beneficial effect
The present invention have it is following the utility model has the advantages that
1, social security business association rule digging and recommendation apparatus and method of the building based on Apriori, utilizes data mining
Technology is to multivariate data deployment analysis, and dynamic grasps service object's behavioural characteristic rule, service condition comprehensively, can be with auxiliary judgment
Qualification is enjoyed in the treatment of insurant；
2, the business for predicting that insured people's future handles is realized by generating social security business association rule, reduces insurant
Queuing, improve business handling personnel working efficiency and quality.
Detailed description of the invention
Fig. 1 is social security business association rule digging and recommendation apparatus flow chart based on Apriori.
Fig. 2 is social security business association rule digging and recommended method flow chart based on Apriori.
Fig. 3 is to obtain module flow diagram.
Fig. 4 is building Apriori model module flow chart.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Apriori algorithm: being a kind of algorithm of most influential Mining Boolean Association Rules frequent item set；Its core is base
Collect the recursive algorithm of thought in two stages frequency；The correlation rule belongs to one-dimensional, single layer, Boolean Association Rules in classification.
Embodiments of the present invention one: referring to Fig. 1, Fig. 3 and Fig. 4, the social security business association rule digging based on Apriori
And recommendation apparatus, by acquisition module 101, building Apriori model module 103, social security business association rule module 102 and prediction
The most of composition of module 104 4.
Obtaining module 101 includes log information acquisition unit 1011, business diary information 1012, status information generation unit
1013 and ownness's information 1014；Social security business association analysis module 102 includes data transformation, building Apriori pattern die
Block 103, model optimization module 104, social security business association rule 1021 generate；It includes frequent for constructing Apriori model module 103
Item collection generation unit 1031, Strong association rule generate 1032, correlation rule sequence 1033.
Module 101 is obtained, for analyzing the acquisition of data, related data conduct required for being obtained from related data sources
Analyze data；Log information acquisition unit 1011, for acquiring the log information needed, based on customized log collection rule
The log of social security operation system is collected, filter, is analyzed, the system business log of acquisition is stored in business diary information
In library；Business diary information 1012, for storing time, the place, business handler, business handling that insured people's business occurs
The information such as content, the excavation for social security business association rule provide information support；Status information generation unit 1013, for obtaining
Ownness's information will pass through number for business procedure data, personal basic data etc. to be mapped in the label model of building
The ownness's attribute information generated after handling according to labeling is stored in ownness's information bank；Ownness's information 1014,
For storing the newest social security business state information such as insured people's personal attribute information and endowment, medical treatment, industrial injury, fertility, unemployment,
Excavation for social security business association rule provides information support.
Social security business association rule module 102 generates social security business association rule 1021, the industry based on acquisition for analyzing
Business log information 1012, ownness's information 1014, construct the Association Rule Analysis model based on Apriori algorithm, by mould
Type analysis obtains the incidence relation between personal attribute and business handling item, generates social security business association rule 1021, storage
In social security business association rule base, using model evaluation index to the continuous adjusting and optimizing of model parameter, the accurate of model is improved
Degree；Data transformation, for converting the form of data, by smoothly assembling, Data generalization, the modes such as standardization believe business diary
The data conversions such as breath 1012, ownness's information 1014 are at the manageable data mode of Apriori algorithm model；Social security business
Correlation rule 1021, for storing the social security business association rule excavated and generated, the industry that may be handled for the insured people of forecast analysis
It is engaged in and carries out recommending to provide foundation to business personnel.
Apriori model module 103 is constructed, for constructing the Association Rules Model based on Apriori algorithm；Frequent item set
Unit 1031 is to generate by the beta pruning processing from connection, based on confidence level and meet minimum support for generating frequent item set
Spend all item collections of threshold value；Strong association rule 1032 generates from frequent episode set for generating Strong association rule and meets minimum
The correlation rule of confidence level；Correlation rule sequence 1033, is ranked up the correlation rule set of generation, according to confidence level, branch
Degree of holding, cardinal of the set, label frequency successively sort.
Model optimization module 104, is based on model evaluation index, and continuous adjusting parameter Optimized model promotes correlation rule mould
The confidence level of type, confidence level, promotion degree.
Prediction module 105, the business for predicting to recommend insured people that may handle, is based on social security business association rule base,
Predict that insured people is possible to the business handled and its prediction result is recommended business handling personnel.
Embodiments of the present invention two: referring to Fig. 1-4, social security business association rule digging and recommendation based on Apriori
Method, comprising the following steps:
Step 1: acquiring social security business according to predefined log collection rule by log information acquisition unit 1011
The business diary information 1012 of system, is stored in business diary information 1012, models and uses to follow-up data mining analysis.
Step 2: business procedure data, personal basic data etc. are mapped to structure by status information generation unit 1013
In the label model built, the ownness's attribute information generated after data labelization processing is stored in ownness's information
In 1014, models and use to follow-up data mining analysis.
Step 3: business diary information 1012, ownness's information 1014 are converted by data conversion process
The manageable data mode of Apriori algorithm model, and pass data to the frequency in Apriori algorithm model construction module
Numerous item collection unit.
Step 4: passing through 1031 Mining Frequent Itemsets Based of frequent item set unit using the alternative manner successively searched for.Scanning is searched
Rope goes out candidate 1 item collection and corresponding support, beta pruning remove 1 item collection of candidate lower than support, obtain frequent 1 item collection, should
Set is denoted as L1；Remaining frequent 1 item collection is carried out to obtain candidate 2 item collections from connecting, the candidate lower than support is removed in screening
2 item collections, obtain frequent 2 item collection, which is denoted as L2；So iteration continues, until that cannot find any frequent k item collection again.
Step 5: generating the correlation rule for meeting min confidence from frequent episode set using Strong association rule 1032.
Step 6: using model optimization module 104, adjusting parameter Optimized model, promoted Association Rules Model confidence level,
Confidence level, promotion degree.
7th: the social security business association rule that the model after optimization generates is stored in social security business association rule base mould
In block, using correlation rule sequence 1033, the correlation rule set of generation is ranked up, according to confidence level, support, set
Radix, label frequency successively sort.
Step 8: obtaining the newest personal attribute's status data of insured people, newest business shape when insured people's transacting business
State information data updates ownness's information 1014.
Step 9: newest ownness's information is sent to social security business association rule module 102, analysis obtains a Genus Homo
Property item and business handling item between correlation rule and its regular confidence level.
Step 10: the correlation rule set to generation is ranked up, the maximum correlation rule of confidence level is chosen as prediction
Rule, and prediction result is recommended into business handling personnel, traffic forecast recommendation is realized by business handling prediction module.
Step 11: this business handling relevant information is stored in business diary after the completion of insured people's business handling
In information 1012.
Claims (8)
1. a kind of social security business association rule digging and recommendation apparatus based on Apriori, which is characterized in that insured for predicting
The demand of personnel, the device include:
It obtains module (101), for storing the business diary information (1012) and ownness's information (1014) of insured people；
It constructs Apriori model module (103), handles to obtain frequent item set list by connection certainly and the beta pruning based on confidence level
Member, generates the Strong association rule (1032) for meeting min confidence from the frequent item set unit (1031), then by the association of generation
The set of rule is ranked up, and obtains Apriori model；
Social security business association rule module (102), the information for will acquire module (101) are converted to the number of Apriori model
It according to form, and is input in Apriori model, analysis obtains the incidence relation between personal attribute and business handling item, obtains
It is regular (1021) to social security business association；
Prediction module (105) predicts the business to be handled of insured people based on social security business association regular (1021).
2. the social security business association rule digging and recommendation apparatus, feature according to claim 1 based on Apriori exists
In: described device further includes model optimization module (104), and the model optimization module (104) is based on evaluation index pair
Apriori model optimizes.
3. the social security business association rule digging and recommendation apparatus, feature according to claim 1 based on Apriori exists
In: the acquisition module (101) further include:
Log information acquisition unit (1011) and status information generation unit (1013), the log information acquire (1011) unit
Based on customized log information collection rule, and the log of related social security operation system is collected and stores business day
In will information (1012)；
The status information generation unit (1013) for obtaining ownness's information, and by the data generated in business procedure and
Personal basic data is mapped in tag unit and stores Dao ownness's information (1014) in.
4. the social security business association rule digging and recommendation apparatus, feature according to claim 1 based on Apriori exists
In: the item collection that the frequent item set unit (1031) obtains is to meet all item collections of minimum support threshold value.
5. the social security business association rule digging and recommendation apparatus, feature according to claim 1 based on Apriori exists
In: the business diary information (1012) is used to store the service attribute item information of insured people；Ownness's information
(1014) for storing personal attribute information.
6. the social security business association rule digging and recommendation apparatus, feature according to claim 1 based on Apriori exists
In: it is associated between the business diary information (1012) and ownness's information (1014) by individual ID.
7. social security business association rule digging and recommended method based on Apriori, it is characterised in that: for realizing claim
Social security business association rule digging and recommendation apparatus described in 1-6 based on Apriori, the described method comprises the following steps:
Obtain business diary information (1012) and ownness's information (1014) of insured people；
Business diary information (1012) and ownness's information (1014) are converted to the data mode in Apriori model, and
Transfer data to the frequent item set unit (1031) in Apriori model；
By alternative manner Mining Frequent Itemsets Based, and the correlation rule for meeting min confidence is generated in frequent item set；
Based on Apriori model evaluation index, optimize Apriori model, generate social security business association rule, and by social security business
Correlation rule is stored in business rule base；
When insured people's transacting business, the newest business state information and personal attribute information of insured people are obtained and updated；
Newest business state information and personal attribute information are sent in business rule base, analysis obtain personal attribute with
The confidence level of correlation rule and its rule between business handling item；
The correlation rule of generation is sorted (1033), obtains the maximum correlation rule of confidence level as prediction rule, and will prediction
As a result business personnel is recommended.
8. the social security business association rule digging and recommended method, feature according to claim 7 based on Apriori exists
In: the method also includes after insured people completes business, business information is stored in business diary information (1012).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811542221.6A CN109635006A (en) | 2018-12-17 | 2018-12-17 | Social security business association rule digging and recommendation apparatus and method based on Apriori |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811542221.6A CN109635006A (en) | 2018-12-17 | 2018-12-17 | Social security business association rule digging and recommendation apparatus and method based on Apriori |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109635006A true CN109635006A (en) | 2019-04-16 |
Family
ID=66074643
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811542221.6A Pending CN109635006A (en) | 2018-12-17 | 2018-12-17 | Social security business association rule digging and recommendation apparatus and method based on Apriori |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109635006A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110222094A (en) * | 2019-06-14 | 2019-09-10 | 国网新疆电力有限公司电力科学研究院 | Based on the electric energy meter risk analysis method and system for improving Apriori algorithm |
| CN110489453A (en) * | 2019-07-02 | 2019-11-22 | 广东工业大学 | User's game real-time recommendation method and system based on big data log analysis |
| CN111274331A (en) * | 2020-01-15 | 2020-06-12 | 中国建设银行股份有限公司 | Relational data management maintenance system and method |
| CN111666519A (en) * | 2020-05-13 | 2020-09-15 | 中国科学院软件研究所 | Dynamic mining method and system for network access behavior feature group under enhanced condition |
| CN112131273A (en) * | 2020-09-23 | 2020-12-25 | 南京数云信息科技有限公司 | Data relation mining method and device based on Mysql database log |
| CN112241420A (en) * | 2020-10-26 | 2021-01-19 | 浪潮云信息技术股份公司 | Government affair service item recommendation method based on association rule algorithm |
| CN115203311A (en) * | 2022-07-05 | 2022-10-18 | 南京云创大数据科技股份有限公司 | Industry data analysis mining method and system based on data brain |
| CN117056869A (en) * | 2023-10-11 | 2023-11-14 | 轩创(广州)网络科技有限公司 | Electronic information data association method and system based on artificial intelligence |
| WO2024087428A1 (en) * | 2022-10-25 | 2024-05-02 | 浪潮电子信息产业股份有限公司 | Parameter configuration recommendation method and apparatus for memory product, and device and medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103198418A (en) * | 2013-03-15 | 2013-07-10 | 北京亿赞普网络技术有限公司 | Application recommendation method and application recommendation system |
| CN106874693A (en) * | 2017-03-15 | 2017-06-20 | 国信优易数据有限公司 | A kind of medical big data analysis process system and method |
| CN107944990A (en) * | 2017-12-29 | 2018-04-20 | 山大地纬软件股份有限公司 | A kind of integral counter-employee device and method of the precision push based on machine learning |
| CN108090787A (en) * | 2017-12-18 | 2018-05-29 | 北京工业大学 | A kind of call bill data depth based on Apriori algorithm is excavated and the method for user's behavior prediction |
-
2018
- 2018-12-17 CN CN201811542221.6A patent/CN109635006A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103198418A (en) * | 2013-03-15 | 2013-07-10 | 北京亿赞普网络技术有限公司 | Application recommendation method and application recommendation system |
| CN106874693A (en) * | 2017-03-15 | 2017-06-20 | 国信优易数据有限公司 | A kind of medical big data analysis process system and method |
| CN108090787A (en) * | 2017-12-18 | 2018-05-29 | 北京工业大学 | A kind of call bill data depth based on Apriori algorithm is excavated and the method for user's behavior prediction |
| CN107944990A (en) * | 2017-12-29 | 2018-04-20 | 山大地纬软件股份有限公司 | A kind of integral counter-employee device and method of the precision push based on machine learning |
Non-Patent Citations (1)
| Title |
|---|
| 刘莉丽: "数据挖掘技术在社保联网审计中的应用研究", 《万方数据知识服务平台》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110222094A (en) * | 2019-06-14 | 2019-09-10 | 国网新疆电力有限公司电力科学研究院 | Based on the electric energy meter risk analysis method and system for improving Apriori algorithm |
| CN110489453A (en) * | 2019-07-02 | 2019-11-22 | 广东工业大学 | User's game real-time recommendation method and system based on big data log analysis |
| CN110489453B (en) * | 2019-07-02 | 2023-04-14 | 广东工业大学 | User game real-time recommendation method and system based on big data log analysis |
| CN111274331A (en) * | 2020-01-15 | 2020-06-12 | 中国建设银行股份有限公司 | Relational data management maintenance system and method |
| CN111666519A (en) * | 2020-05-13 | 2020-09-15 | 中国科学院软件研究所 | Dynamic mining method and system for network access behavior feature group under enhanced condition |
| CN112131273A (en) * | 2020-09-23 | 2020-12-25 | 南京数云信息科技有限公司 | Data relation mining method and device based on Mysql database log |
| CN112241420A (en) * | 2020-10-26 | 2021-01-19 | 浪潮云信息技术股份公司 | Government affair service item recommendation method based on association rule algorithm |
| CN115203311A (en) * | 2022-07-05 | 2022-10-18 | 南京云创大数据科技股份有限公司 | Industry data analysis mining method and system based on data brain |
| WO2024087428A1 (en) * | 2022-10-25 | 2024-05-02 | 浪潮电子信息产业股份有限公司 | Parameter configuration recommendation method and apparatus for memory product, and device and medium |
| CN117056869A (en) * | 2023-10-11 | 2023-11-14 | 轩创(广州)网络科技有限公司 | Electronic information data association method and system based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109635006A (en) | Social security business association rule digging and recommendation apparatus and method based on Apriori | |
| CN105160038B (en) | Data analysis method and system based on audit database | |
| CN104077407B (en) | A kind of intelligent data search system and method | |
| CN108229828A (en) | A kind of analysis system based on industrial data | |
| KR101616544B1 (en) | Method for analyzing patent documents using a latent dirichlet allocation | |
| CN104809188A (en) | Enterprise talent drainage data mining analysis method and device | |
| Chen et al. | A patent time series processing component for technology intelligence by trend identification functionality | |
| WO2016040304A1 (en) | A method for detection and characterization of technical emergence and associated methods | |
| CN100470547C (en) | Method, system and device for implementing data mining model conversion and application | |
| CN110147389A (en) | Account number treating method and apparatus, storage medium and electronic device | |
| CN109472490A (en) | Military project group personal information labeling system based on cluster | |
| CN103995828B (en) | A kind of cloud storage daily record data analysis method | |
| CN111738331A (en) | User classification method and device, computer-readable storage medium and electronic device | |
| KR20140081721A (en) | System and method for deducting imporant keyword using textmining, and a medium having computer readable program for executing the method | |
| KR20200004183A (en) | Systema and method for predicting price using article search | |
| CN117113159A (en) | Deep learning-based power consumer side load classification method and system | |
| Shi et al. | Human resources balanced allocation method based on deep learning algorithm | |
| JP2004199377A (en) | Remote monitoring diagnostic system | |
| KR101693727B1 (en) | Apparatus and method for reorganizing social issues from research and development perspective using social network | |
| EP3493082A1 (en) | A method of exploring databases of time-stamped data in order to discover dependencies between the data and predict future trends | |
| CN107423320B (en) | Medical field self-media platform data pushing method under big data architecture | |
| CN115409541A (en) | Cigarette brand data processing method based on data blood relationship | |
| CN111091410B (en) | Node embedding and user behavior characteristic combined net point sales prediction method | |
| CN113780673A (en) | Training method and device of job leaving prediction model and job leaving prediction method and device | |
| Schuh et al. | Identification of requirements for focused crawlers in technology intelligence |
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 |
Application publication date: 20190416 |
|
| RJ01 | Rejection of invention patent application after publication |