# Patent Keyword Analysis Using Time Series and Copula Models

^{1}

^{2}

^{3}

^{*}

## Abstract

**:**

## Featured Application

**This work can be applied to the research and development planning or sustainable technology management.**

## Abstract

## 1. Introduction

## 2. Research Background

- Step 1:
- Select and understand the target technology
- Step 2:
- Make a keyword equation for patent searching and collect patents related to the target technology
- Step 3:
- Transform the collected patent documents into structured data
- Step 4:
- Analyze structured data (a patent-keyword matrix) using statistics or machine learning
- Step 5:
- Apply patent analysis results to technology management.

## 3. Patent Analysis Model Using Copula Directional Dependence via Integer-Valued GARCH

_{t}and F

_{t-1}are integer-valued time series data at time t and information set up to time t-1, and then the INGARCH(p,q) model is represented by a Poisson distribution as follows [20].

_{t}is Poisson in the INGARCH(p,q) model, and then the conditional mean depends on the past values of the time series and its own past values. In addition, the INGARCH(1,1) model is shown as follows [20]:

_{t}is a response variable (keyword) on the unit interval at time t, and x

_{t}is a covariate vector (keyword vector). In the beta regression model, Y

_{t}|x

_{t}follows the beta distribution as follows [23]:

_{t}was obtained by a logit mode of mean parameter(${\mu}_{t}$) as follows:

_{t}, and ${\beta}_{x}$ is coefficient vector. Our proposed copula directional dependence by integer-valued GARCH model, which is based on nonlinear logit model, is more flexible than the current available approaches to directional dependence by linear regression type model [24]. To verify the accuracy of the model, we used two measures: Akaike information criterion (AIC) and Bayes information criterion (BIC). The AIC is defined as follows [25]:

## 4. Experimental Results

## 5. Conclusions

## Author Contributions

## Funding

## Conflicts of Interest

## References

- Hunt, D.; Nguyen, L.; Rodgers, M. Patent Searching Tools & Techniques; Wiley: Hoboken, NJ, USA, 2007. [Google Scholar]
- Jun, S.; Lee, S. Patent Analysis Using Bayesian Network Models. Int. J. Softw. Eng. Appl.
**2013**, 7, 205–212. [Google Scholar] - Choi, J.; Hwang, Y.S. Patent keyword network analysis for improving technology development efficiency. Technol. Forecast. Soc. Chang.
**2014**, 83, 170–182. [Google Scholar] [CrossRef] - Jun, S. Central technology forecasting using social network analysis. Commun. Comput. Inf. Sci.
**2012**, 340, 1–8. [Google Scholar] - Yuna, S.; Lee, J. An innovation network analysis of science clusters in South Korea and Taiwan. Asian J. Technol. Innov.
**2013**, 21, 277–289. [Google Scholar] [CrossRef] - Kim, J.; Jun, S.; Jang, D.; Park, S. An Integrated Social Network Mining for Product-based Technology Analysis of Apple. Ind. Manag. Data Syst.
**2017**, 117, 2417–2430. [Google Scholar] [CrossRef] - Kim, J.; Ryu, J.; Lee, S.; Jun, S. Penalized Regression Models for Patent Keyword Analysis. Model. Assist. Stat. Appl. Int. J.
**2017**, 12, 239–244. [Google Scholar] [CrossRef] - Uhm, D.; Ryu, J.; Jun, S. An Interval Estimation Method of Patent Keyword Data for Sustainable Technology Forecasting. Sustainability
**2017**, 9, 2025. [Google Scholar] [CrossRef] - Guidolin, M.; Guseo, R. Modelling seasonality in innovation diffusion. Technol. Forecast. Soc. Chang.
**2014**, 86, 33–40. [Google Scholar] [CrossRef] - Hong, J.; Shin, J.; Lee, D. Strategic management of next-generation connected life: Focusing on smart key and car–home connectivity. Technol. Forecast. Soc. Chang.
**2016**, 103, 11–20. [Google Scholar] [CrossRef] - Lakka, S.; Michalakelis, C.; Varoutas, D.; Martakos, D. Competitive dynamics in the operating systems market: Modeling and policy implications. Technol. Forecast. Soc. Chang.
**2013**, 80, 88–105. [Google Scholar] [CrossRef] - Kim, J.; Jun, S. Integer-Valued GARCH Processes for Apple Technology Analysis. Ind. Manag. Data Syst.
**2017**, 117, 2381–2399. [Google Scholar] [CrossRef] - Kim, J.; Hwang, S.Y. Directional Dependence via Gaussian Copula Beta Regression Model with Asymmetric GARCH Marginals. Commun. Stat. Simul. Comput.
**2016**, 46, 7639–7653. [Google Scholar] [CrossRef] - Roper, A.T.; Cunningham, S.W.; Porter, A.L.; Mason, T.W.; Rossini, F.A.; Banks, J. Forecasting and Management of Technology; John Wiley & Sons: Hoboken, NJ, USA, 2011. [Google Scholar]
- Jun, S.; Park, S. Examining technological competition between BMW and Hyundai in the Korean car market. Technol. Anal. Strateg. Manag.
**2016**, 28, 156–175. [Google Scholar] [CrossRef] - Kim, J.; Jun, S. Graphical causal inference and copula regression model for apple keywords by text mining. Adv. Eng. Inform.
**2015**, 29, 918–929. [Google Scholar] [CrossRef] - Kim, J.; Im, D.; Jun, S. Factor analysis and structural equation model for patent analysis: A case study of Apple’s technology. Technol. Anal. Strateg. Manag.
**2017**, 29, 717–734. [Google Scholar] [CrossRef] - Park, S.; Kim, J.; Jang, D.; Lee, H.; Jun, S. Methodology of Technological Evolution for Three-dimensional Printing. Ind. Manag. Data Syst.
**2016**, 116, 122–146. [Google Scholar] [CrossRef] - Jun, S.; Park, S.; Jang, D. Technology Forecasting using Matrix Map and Patent Clustering. Ind. Manag. Data Syst.
**2012**, 112, 786–807. [Google Scholar] [CrossRef] - Ferland, R.; Latour, A.; Oraichi, D. Integer-valued GARCH process. J. Time Ser. Anal.
**2006**, 27, 923–942. [Google Scholar] [CrossRef] - Sklar, A. Fonctions de repartition á n dimensions et leurs marges. Publ. De L’institut De Stat. De L’universit De Paris
**1959**, 8, 229–231. [Google Scholar] - Guolo, A.; Varin, C. Beta regression for time series analysis of bounded data, with application to Canada Google flu trends. Ann. Appl. Stat.
**2014**, 8, 74–88. [Google Scholar] [CrossRef] - Casella, G.; Berger, R. Statistical Inference, 2nd ed.; Duxbury: Pacific Grove, CA, USA, 2002. [Google Scholar]
- Wiedermann, W.; Hagmann, M.; Eye, A. Significance tests to determine the direction of effects in linear regression models. J. Time Ser. Anal.
**2015**, 68, 116–141. [Google Scholar] [CrossRef] [PubMed] - Akritas, M. Probability and Statistics with R for Engineers and Scientists; Pearson: Boston, MA, USA, 2016. [Google Scholar]
- Jun, S.; Park, S. Examining Technological Innovation of Apple Using Patent Analysis. Ind. Manag. Data Syst.
**2013**, 113, 890–907. [Google Scholar] [CrossRef] - USPTO. The United States Patent and Trademark Office. Available online: http://www.uspto.gov (accessed on 10 July 2018).
- WIPSON. WIPS Corporation. Available online: http://www.wipson.com (accessed on 30 April 2018).
- Feinerer, I.; Hornik, K. R Package ‘tm’ Ver. 0.7–5, Text Mining Package, CRAN of R Project. Available online: https://cran.r-project.org/web/packages/tm/tm.pdf (accessed on 1 January 2018).
- Liboschik, T.; Fried, R.; Fokianos, K.; Probst, P.; Rathjens, J. R Package ‘tscount’ Ver. 1.4.1, Analysis of Count Time Series, CRAN of R Project. Available online: https://cran.r-project.org/web/packages/tscount/tscount.pdf (accessed on 1 January 2018).
- R Core Team. R: A Language and Environment for Statistical Computing; R Foundation for Statistical Computing: Vienna, Austria, 2018. [Google Scholar]
- Kojadinovic, I.; Yan, J. Modeling Multivariate Distributions with Continuous Margins Using the copula R Package. J. Stat. Softw.
**2010**, 34, 1–20. [Google Scholar] [CrossRef] - Hoff, P.D. Extending the rank likelihood for semiparametric copula estimation. Ann. Appl. Stat.
**2007**, 1, 265–283. [Google Scholar] [CrossRef] - Kim, J.; Jung, Y.; Sungur, E.A.; Han, K.; Park, C.; Sohn, I. A copula method for modeling directional dependence of genes. BMC Bioinform.
**2008**, 9, 225. [Google Scholar] [CrossRef] [PubMed] - Jung, Y.; Kim, J.; Kim, J. New approach of directional dependence in exchange markets using generalized FGM copula functions. Commun. Stat. Simul. Comput.
**2008**, 37, 772–788. [Google Scholar] [CrossRef] - Kim, J.; Jung, Y.; Soderberg, T. Directional dependence of genes using survival truncated FGM type modification copulas. Commun. Stat. Simul. Comput.
**2009**, 38, 1470–1484. [Google Scholar] [CrossRef] - Uhm, D.; Kim, J.; Jung, Y. Large asymmetry and directional dependence by using copula modeling to currency exchange rates. Models Assist. Stat. Appl.
**2012**, 7, 327–340. [Google Scholar] [CrossRef] - Kim, J.; Jung, Y.; Sungur, E.A. Copulas with Directional Dependence Property: Application to Foreign Exchange Currency Data. Models Assist. Stat. Appl.
**2014**, 9, 309–324. [Google Scholar] - Rodríguez-Lallena, J.A.; beda-Flores, M.U. A new class of bivariate copulas. Stat. Probab. Lett.
**2004**, 66, 315–325. [Google Scholar] [CrossRef]

INGARCH(1,1) | α_{0} | α_{1} | β_{1} | AIC | BIC |
---|---|---|---|---|---|

Device | 25.7 | 0.951 | 3.98E-10 | 2491.4 | 2495.7 |

Data | 25.4 | 0.939 | 8.79E-11 | 1963.1 | 1967.4 |

System | 12.2464 | 0.9327 | 0.0112 | 1665.6 | 1669.9 |

User | 8.2126 | 0.9694 | 0.0005 | 1479.6 | 1484 |

Media | 2.15 | 0.989 | 5.34E-10 | 1300.4 | 1304.7 |

AIC | ARMA(0,0) | ARMA(1,0) | ARMA(0,1) | ARMA(1,1) |
---|---|---|---|---|

(Device, Data) | −24.848 | −23.484 | −23.476 | −21.492 |

(Data, Device) | −23.6 | −21.703 | −21.699 | −19.703 |

(Device, System) | −15.411 | −14.322 | −14.121 | −12.332 |

(System, Device) | −15.966 | −15.649 | −16.334 | −14.414 |

(Device, user) | −26.51 | −26.271 | −26.145 | −24.272 |

(User, Device) | −23.615 | −23.448 | −23.471 | −21.484 |

(device, Media) | 1.395 | 3.071 | 3.135 | 4.6435 |

(Media, Device) | 0.802 | −0.171 | −2.793 | −1.757 |

(Data, System) | −28.602 | −27.202 | −26.941 | −25.838 |

(System, Data) | −28.315 | −28.185 | −28.154 | −26.185 |

(Data, User) | −43.011 | −41.428 | −41.367 | −39.435 |

(User, Data) | −44.151 | −43.743 | −43.888 | −41.909 |

(Data, Media) | 3.297 | 3.786 | 4.166 | 5.455 |

(Media, Data) | 1.728 | 0.898 | −1.571 | −0.195 |

(System, User) | −20.926 | −19.512 | −19.459 | −17.521 |

(User, System) | −19.231 | −17.5 | −17.411 | −15.693 |

(System, Media) | 4.494 | 5.98 | 5.922 | 7.904 |

(Media, System) | 4.25 | 2.109 | −5.697 | −4.235 |

(User, Media) | 1.947 | 3.817 | 3.842 | 5.498 |

(Media, User) | 1.452 | 0.934 | −1.487 | −0.498 |

Keywords | 2.5% Quantile | 50% Quantile | 97.5% Quantile |
---|---|---|---|

Device×Data | 0.49 | 0.72 | 0.85 |

Device×System | 0.42 | 0.64 | 0.79 |

Device×User | 0.48 | 0.73 | 0.86 |

Device×Media | 0.08 | 0.37 | 0.67 |

Data×System | 0.54 | 0.73 | 0.87 |

Data×User | 0.63 | 0.81 | 0.89 |

Data×Media | −0.09 | 0.27 | 0.58 |

System×User | 0.39 | 0.67 | 0.81 |

System×Media | −0.14 | 0.17 | 0.51 |

User×Media | −0.05 | 0.33 | 0.62 |

© 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Kim, J.-M.; Yoon, J.; Hwang, S.Y.; Jun, S. Patent Keyword Analysis Using Time Series and Copula Models. *Appl. Sci.* **2019**, *9*, 4071.
https://doi.org/10.3390/app9194071

**AMA Style**

Kim J-M, Yoon J, Hwang SY, Jun S. Patent Keyword Analysis Using Time Series and Copula Models. *Applied Sciences*. 2019; 9(19):4071.
https://doi.org/10.3390/app9194071

**Chicago/Turabian Style**

Kim, Jong-Min, Jaeeun Yoon, Sun Young Hwang, and Sunghae Jun. 2019. "Patent Keyword Analysis Using Time Series and Copula Models" *Applied Sciences* 9, no. 19: 4071.
https://doi.org/10.3390/app9194071