KR20200023657A - System and method for analyzing patent based on visualizing big data - Google Patents

Abstract

The present invention relates to a system for analyzing patent based on big data visualization and a method thereof, which can effectively visualize a patent big data analysis result. According to one embodiment of the present invention, the system comprises: a patent data collection unit collecting patent data in a target technique field; an evaluation index calculation unit calculating a patent index from the collected patent data; a SOM generation unit generating a self-organizing map (SOM) using the patent index as an input vector; and a visualization unit visualizing the SOM.

Description

Patent analysis system based on big data visualization and method thereof {SYSTEM AND METHOD FOR ANALYZING PATENT BASED ON VISUALIZING BIG DATA}

The present invention relates to a patent analysis system and a method thereof, and more particularly, to a technology for analyzing a patent based on big data visualization.

In the modern society, companies must continuously discover new growth engines for future growth through technological innovation for sustainable growth. In other words, a company can earn huge profits through successful R & D and gain a competitive advantage in the market.

However, if a company fails to research and develop, it will have to suffer huge losses over time and time invested in research and development. Therefore, in the initial process for R & D, the establishment of the correct R & D direction and the R & D strategy have become essential factors for successful R & D.

On the other hand, patents are used as the optimal data to obtain the insights necessary to set the direction of research and development and strategy establishment.

Accordingly, as the importance of patent mining (Mining) for technology innovation increases, the number of cases of technology innovation through patent analysis is increasing, and researches on various patent analysis methodologies are being actively conducted.

However, the known patent analysis methodology lacks a technique for visualizing the analysis results, and as the data grows, it is difficult to visualize the analysis results.

Korean Patent No. 10-0751276, "Patent Map Providing System and Method for Identifying Correlation Between Data"

The present invention is to provide a patent analysis system and method for effectively visualizing a large amount of patent big data analysis results.

In addition, the present invention is to provide a patent analysis system and method that can quickly and easily extract significant features for patent analysis on patent big data through the visualization results.

In addition, the present invention is to provide a patent analysis system and method that can easily analyze the rising technology, blank technology and core technology in the field of interest by visualizing the self-organization map and heat map resulting from the patent big data analysis do.

Patent analysis system according to an embodiment of the present invention is a patent data collection unit for collecting patent data of the target technology, an evaluation index calculation unit for calculating a patent index (Patent index) from the collected patent data, and patent evaluation It may include a SOM generator for generating a self-organizing map (SOM) and a visualization unit for visualizing a self-organizing map using the index as an input vector.

According to one side, the patent data collector may collect the patent data of the target technology field from the patent database using a search expression entered by the user.

According to one side, the evaluation index calculation unit from the collected patent data (Technology influence index, Technology marketability index, Technology marketability index, Novelty index and at least one of the inventor grade (Applicant grade) Can be calculated.

According to one side, the inventor grade may be calculated from at least one of the application index of the patents held by the inventor, the cited patent index of the patents held by the inventor, and the family patent index of the patents held by the inventor.

According to one side, the visualization unit may visualize the self-organization map in the form of at least one of a count plot (Codes plot) and a code plot (Codes plot).

According to one side, the SOM generator may perform hierarchical clustering between output nodes of the self-organization map.

According to one side, the visualization unit may visualize the hierarchical clustering results in the form of a mapping plot.

According to one side, the visualization unit may generate a heat map (Mapping) mapping the relationship between the output node of the self-organization map and the patent evaluation index, and intuitively visualize the characteristics of the output node through the heat map. .

Patent analysis method according to an embodiment of the present invention comprises the steps of collecting the patent data of the target technology in the patent data collection unit, calculating the patent index from the patent data in the evaluation index calculation unit (Patent index), The SOM generator may include generating a self-organizing map (SOM) using the patent evaluation index as an input vector, and visualizing the self-organizing map in the visualization unit.

According to one side, the step of calculating the patent evaluation index is a technology influence index, technology marketability index, novelty index and inventor grade from the patent data collected by the evaluation index calculation unit It is possible to calculate a patent evaluation index including at least one of.

According to one side, the inventor grade may be calculated from at least one of the application index of the patents held by the inventor, the cited patent index of the patents held by the inventor, and the family patent index of the patents held by the inventor.

According to one side, generating the self-organization map may further include performing hierarchical clustering between the output nodes of the self-organization map in the SOM generator.

According to one side, the step of visualizing the self-organization map in the visualization unit generates a heat map (Mapping) the relationship between the output node of the self-organization map and the patent evaluation index, the output node through the heat map The method may further include the step of intuitively visualizing the features of the.

According to one embodiment, a large amount of patent big data analysis results can be effectively visualized.

In addition, according to an embodiment, it is possible to quickly and easily extract significant features for patent analysis on patent big data through visualization results.

In addition, according to an embodiment, the self-organization map and heat map derived as a result of the patent big data analysis may be visualized to easily analyze the rising technology, the blank technology, and the core technology of the technology of interest.

1 is a diagram illustrating a patent analysis system according to an embodiment of the present invention.
2A to 2E are diagrams illustrating an embodiment of visualizing a self-organizing map in a patent analysis system according to an embodiment of the present invention.
3 is a diagram illustrating a patent analysis method according to an embodiment of the present invention.

Hereinafter, various embodiments of the present disclosure will be described with reference to the accompanying drawings.

The examples and terms used therein are not intended to limit the techniques described in this document to specific embodiments, but should be understood to include various modifications, equivalents, and / or substitutes of the embodiments.

In the following description of the various embodiments, when it is determined that a detailed description of a related known function or configuration may unnecessarily obscure the subject matter of the present invention, the detailed description thereof will be omitted.

In addition, terms to be described below are terms defined in consideration of functions in various embodiments, and may vary according to a user's or operator's intention or custom. Therefore, the definition should be made based on the contents throughout the specification.

In connection with the description of the drawings, similar reference numerals may be used for similar components.

Singular expressions may include plural expressions unless the context clearly indicates otherwise.

In this document, expressions such as "A or B" or "at least one of A and / or B" may include all possible combinations of items listed together.

Expressions such as "first," "second," "first," or "second," etc. may modify the components in any order or in importance, to distinguish one component from another. Used only and do not limit the components.

When any (eg first) component is said to be "(functionally or communicatively)" or "connected" to another (eg second) component, a component is said other configuration. It may be directly connected to the element or through another component (eg, a third component).

As used herein, “configured to” is modified to have the ability to “fit,” “fit,” “to,” for example, in hardware or software. Can be used interchangeably with "made to", "doing", or "designed to".

In some situations, the expression "device configured to" may mean that the device "can" along with other devices or components.

For example, the phrase “processor configured (or configured to) perform A, B, and C” may be executed by executing a dedicated processor (eg, an embedded processor) to perform the operation, or one or more software programs stored in a memory device. It may mean a general purpose processor (eg, a CPU or an application processor) capable of performing the corresponding operations.

In addition, the term 'or' means inclusive or 'inclusive or' rather than 'exclusive or'.

In other words, unless stated otherwise or unclear from the context, the expression 'x uses a or b' means any one of natural inclusive permutations.

In the above-described specific embodiments, the components included in the invention are expressed in the singular or plural according to the specific embodiments presented.

However, the singular or plural expressions are selected to suit the circumstances presented for convenience of description, and the above-described embodiments are not limited to the singular or plural elements, and the singular or plural elements may be composed of the singular or the plural. However, even a component expressed in the singular may be configured in plural.

Meanwhile, in the description of the present invention, specific embodiments have been described, but various modifications may be made without departing from the scope of the technical idea that the various embodiments include.

Therefore, the scope of the present invention should not be limited to the described embodiments, but should be defined by the claims below and equivalents thereof.

1 is a diagram illustrating a patent analysis system according to an embodiment of the present invention.

Referring to FIG. 1, the patent analysis system 100 according to an embodiment visualizes a self-organization map and a heat map derived as a result of a patent big data analysis, thereby facilitating the rising technology, the blank technology, and the core technology of the technical field of interest. Can be analyzed.

To this end, the patent analysis system 100 may include a patent data collector 110, an evaluation index calculator 120, a SOM generator 130, and a visualization unit 140.

In detail, the patent data collection unit 110 may collect patent data of a target technology field.

According to one side, the patent data collection unit 110 may collect patent data of the target technology field from the patent database by using a search expression entered by the user.

For example, the patent database may be a patent search database such as Wipson, Kipris, and Wisdomain, but the patent database of the present invention is not limited to the above-described example.

Table 1 below shows an example of collecting related patent data to derive key patents and promising patents in the 3D display technology field.

Analysis Data Database Search Words Period US
(4,875) Wigson TI = {(3d OR 3-d OR ORDER / 1 ((three, 3), dimension) OR tridimension OR threedimension OR stereoscope) AND (display)} AND {(glassless OR glassesless OR ORDER / 1 (no, glasses) OR ORDER / 1 (without, glasses)) OR ((ORDER / 1 (parallax, barrier) OR parallaxbarrier) OR lenticular OR ORDER / 1 (integration, image) OR volumetric OR holography OR ORDER / 1 (super, multi, view)) } ~ 12. 31. 2015

Specifically, according to the example of Table 1, the user can derive the relevant patent data by searching the search words (Search Words) related to the 3D display technology in the patent search database (Database), collecting patent data according to an embodiment The unit 110 may collect the derived patent data.

For example, in Table 1, a user may derive 4,875 patents registered in the US by 2015 through a patent search using a patent search database, and according to an embodiment, the patent data collection unit 110 may derive 4,875 patents. You can collect patent data for any patent.

Next, the evaluation index calculator 120 may calculate a patent index from the collected patent data.

According to one side, the evaluation index calculation unit 120 includes at least one of a technology influence index, a technology marketability index, a novelty index, and an inventor grade from the collected patent data. The patent evaluation index can be calculated.

For example, the technology impact index may be a forward citation patent index, the technology marketability index may be a family patent index, and the novelty index may be a backward citation patent index. Each of the patent index, family patent index, and novelty patent index is sum, average, and average for each of the cited patents, family patents, and cited patents derived from the patent data collected through the patent data collection unit 110. At least one of a maximum value Max, a minimum value Min, and a variance value may be included.

For example, the sum of the cited patents means the sum of the total number of cited patents for each patent in the collected patent data, and the maximum value of the cited patents is the most The number of citation patents of the patents having the cited patent may be referred to, and the minimum value may refer to the number of citation patents of the patents having the least citation patents in each patent case.

In addition, the cited patent index, family patent index and novelty patent index is the number of cited patents, the number of family patents and cited patents for each single patent in the patent data collected through the patent data collection unit 110 It may be a number.

According to one side, the inventor grade may be calculated from at least one of the application index of the patents held by the inventor, the cited patent index of the patents held by the inventor, and the family patent index of the patents held by the inventor.

Specifically, the evaluation index calculation unit 120 may classify the patent data collected through the patent data collection unit 110 according to the inventor information, and the application index of the patents owned by a specific inventor in the classified patents, the specific inventor At least one of the cited patent index of the patents owned by the family and the family patent index of the patents held by the particular inventor can be calculated.

For example, the application index of patents held by the inventor may be the number of patent applications held by the inventor.

In addition, each of the citation and family patent indices of patents owned by the inventors is sum, average, maximum, and minimum of the citation and family patents of the citations of the inventors. And a variance value.

Table 2 below shows an example of the patent evaluation index.

Patent Index Example Technology influence index Citation Patent Index Technology marketability Family Patent Index Novelty Index Cited Patent Index Inventor Grade Application index of patents owned by inventor
Cited Patent Index of Inventors
Family patent index of patents owned by inventor

In general, a patent not only describes the principles of the technology, but may also include patent indicators that quantitatively indicate the characteristics and values of the technology as patents.

Specifically, the patent indicator is a measure of the value of the technology as a patent such as the influence of the technology, the marketability, the novelty, and the level of the technology owner (inventor grade), and can be usefully used for quantitative patent analysis. Representative patent indicators may include IPC (International Patent Classification), cited patent index, cited patent index and family patent index.

The evaluation index calculator 120 according to an embodiment of the present invention calculates a patent evaluation index including a cited patent index, a cited patent index, a family patent index, and an inventor's grade among patent indices, thereby increasing the technology of interest. This allows for easy analysis of gap techniques and key techniques.

Specifically, according to the example of Table 2, since the number of the cited patent indicates that the patent has a greater influence on other technologies after filing, the evaluation index calculator 120 according to an embodiment has a technical influence. A cited patent index can be used as an index.

In addition, since the number of family patents indicates that the corresponding patents have rights in many countries, the evaluation index calculator 120 may use the family patent index as a technology marketability index.

In addition, since the number of cited patents means that many related patents are already filed before the patent is applied, the number of cited patents may be determined to be high in novelty.

Accordingly, the evaluation index calculator 120 may use the cited patent index as the novelty index.

In addition, the inventor grade standardizes the number of patents owned by the inventors in the technical field, the number of cited patents and the size of the family patent, and determines the rank of the inventors based on the sum of the standardized indexes. Can be.

For example, the inventor's grade can be given to the top 10% or more by 9 points, the top 20% or more by 8 points, and the top 80% or more by 2 points.

Hereinafter, the technical impact index will be described as a cited patent index, the technical marketability index as a family patent index, and the novelty index as a cited patent index.

Table 3 below shows an example of the patent evaluation index calculation.

Backward
Citation Forward
Citation Applicant
Grade Family Average 20.23 17.00 6.06 4.10 Sum 98614 82894 29539 19993 Max 1701 536 9 35 Min 0 0 2 0 Variance 4591.45 909.80 4.408 11.89

As described above, the evaluation index calculation unit 120 according to an embodiment of the citation patent index, family patent index, citation (Backward citation) patent index and inventor grade ( Patent evaluation indexes including applicant grades can be calculated.

Also, the cited patent index, family patent index, and cited patent index are sum, average, and average for the cited patent, family patent, and cited patent in the patent data collected through the patent data collection unit 110. It may include a maximum value Max, a minimum value Min, and a variance value.

According to the example of Table 3, the number of patent holders is 1,725, the average value of cited patents, which are information included in the patent evaluation index, is 20.23, the average value of cited patents is 17.00, the average value of inventor grades is 6.06, and the average value of family patents. Was found to be 4.10.

Next, the SOM generator 130 may generate a self-organizing map (SOM) using the patent evaluation index calculated by the evaluation index calculator 120 as an input vector. .

In general, self-organizing guidance is a competitive learning neural network model proposed by Kohonen and is used in a wide range of fields that require clustering analysis. Specifically, self-organizing map is a method of creating and visualizing high-dimensionally expressed data as a low-dimensional map and performing cluster analysis through repeated autonomous learning and visualizing the results, which is useful for patent big data analysis. Can be.

On the other hand, self-organizing maps are actively used in all fields requiring clustering analysis, but in the field of patent mining, they are limitedly used for keyword-based clustering using text mining. In other words, the known technologies aim to automatically classify patents according to their technical characteristics.

In other words, until now, researchers in the field of patents have tried to find research trends and blank technologies using self-organizing maps, but they have been useful to identify research trends through keywords by being limited to studies using keywords as input vectors. There was a problem that it was impossible to know what value the technology community had as intellectual property.

On the other hand, the patent analysis system 100 according to an embodiment performs a technology cluster using a patent evaluation index as an input vector of the self-organization map, so that patents included in each cluster can be easily selected as core patents and promising patents. Can be.

In other words, the patent analysis system 100 according to an exemplary embodiment may derive a core technology cluster and a promising technology cluster by clustering each patent based on the value of the intellectual property rights instead of keywords.

More specifically, the structure of the self-organizing map is composed of an input layer composed of m input nodes and an output layer composed of n output nodes, and an input vector X may be input to each input node and may be mapped to the output layer. .

In addition, the output layer generally uses a two-dimensional structure, the number of output nodes can be any number you want, all the output nodes are connected to all input nodes and the connection weight between 0 and 1 )

In addition, the connection weight is given a random initial value, but the learning is repeated and adjusted, and the learning method may determine the nearest output node as the winner node by calculating the Euclidean distance between the input vector and the connection strength.

Meanwhile, another output node close to the winner node is called a neighbor node, and the winner node may decrease the number of neighbor nodes as the difference between the connection weight and the input vector is reduced. That is, the winner node may be adjusted while reducing the difference between the input vector and the connection weight so that neighboring nodes do not exist as the learning is repeated.

Summarizing the learning process of the self-organizing map, we input an input vector into the input layer, then calculate the distance between the input vector and the connection strength to determine one winner node, and then adjust the connection strength according to the learning rules. Can be.

In addition, the self-organizing map may repeat the above-described learning procedure until there is no neighbor node.

Meanwhile, since the SOM generator 130 uses a patent evaluation index as an input vector, it is highly likely that patents having a patent evaluation index of a similar pattern are mapped to the same output node.

In other words, the patents mapped to the output node of the self-organization map generated by the SOM generation unit 130 may be clustered into patents that are similar in impact, marketability, novelty, and the level of the owner (class of the inventor) of the technology.

According to one side, the SOM generator 130 may perform hierarchical clustering between output nodes of the generated self-organization map.

More specifically, the SOM generator 130 may perform hierarchical clustering between output nodes using average vector values of patents mapped to each output node.

Next, the visualization unit 140 may visualize the self-organization map generated by the SOM generator 130.

According to one side, the visualization unit 140 may visualize the self-organization map in the form of at least one of a counts plot (Codes plot) and a code plot (Codes plot), the hierarchical clustering results of the mapping plot (Mapping plot) It can also be visualized in form.

Meanwhile, the visualization unit 140 generates a heat map that maps the relationship between the output node of the self-organizing map and the patent evaluation index, and intuitively visualizes the characteristics of the output node through the heat map. Can be.

Specifically, one of the visualization tools, heat map, is a word combining a heat representing a column and a map representing a map, and it is possible to output various information that can be expressed in color as visual graphics in the form of a heat distribution on a certain image. have.

The above-described heat map features can be usefully used for big data visualization because they can compare the differences between the data at a glance and are very effective for intuitively finding hidden patterns within the entire data. The system 100 may further include an analysis result provider (not shown) for extracting meaningful data from a self-organizing map and providing the same to a user.

Specifically, the analysis result providing unit according to an embodiment may derive an output node including at least one of the injury technology, blank technology and core technology in the self-organization map, and the Data can be extracted as significant data.

The process of visualizing the self-organization map in the visualization unit 140 and the process of extracting meaningful data from the analysis result providing unit will be described in more detail with reference to FIGS. 2A through 2E.

2A to 2E are diagrams illustrating an embodiment of visualizing a self-organizing map in a patent analysis system according to an embodiment of the present invention.

Referring to FIGS. 2A to 2E, reference numerals 210 to 250 show visualization results of a two-dimensional self-organizing map that maps 4,875 patent data collected from the patent database described through the example of Table 1 above. do.

Specifically, reference numeral 210 shows a result of visualizing the self-organizing map in the form of a counts plot, and reference numeral 220 shows a result of visualizing the self-organizing map in the form of a code plot. .

In addition, reference numerals 230 and 240 denote results of visualization of hierarchical clustering results in the form of a mapping plot, and reference numeral 250 denotes results of visualization in the form of a heat map. Illustrated.

In the visualization results illustrated by reference numerals 210 to 240, reference numeral 201 denotes a first node, reference numeral 202 denotes a second node, and reference numeral 203 denotes a sixth node. That is, in the visualization results shown by reference numerals 210 to 240, the node numbers may be sequentially assigned from the bottom left to the top right.

More specifically, as shown by reference numeral 210, the patent analysis system according to an embodiment may visualize a self-organizing map in the form of a count plot. In other words, the patent analysis system according to an embodiment may visualize the number of patents assigned to each output node in the self-organization map by the density of colors and provide the same to the user.

According to the visualization result of the reference numeral 210, the number of patents assigned to the first node 201 and the eighth node is the most, about 600, and the number of patents allocated to the 16th to 20th nodes located at the top It can be seen that less than 100.

Table 4 below shows the number of patents at each output node.

Node One 2 3 4 5 6 7 8 9 10 Patents 657 191 162 512 413 197 423 628 495 194 Node 11 12 13 14 15 16 17 18 19 20 Patents 75 59 371 229 96 13 61 10 63 26

According to Table 4, as described above, the number of patents allocated to the first node 201 and the eighth node is about 600, which is the largest number.

That is, the patent analysis system according to an embodiment of the present invention may assist the user to easily identify the feature according to the patent distribution for each output node by visualizing the number of patents assigned to each output node through a count plot.

Next, as shown by the reference numeral 220, the patent analysis system according to an embodiment visualizes the self-organization map in the form of a code plot, thereby piling up the patent evaluation index of the patents assigned to each output node in the self-organization map. Can be provided to the user as a chart

According to the visualization result of the reference numeral 220, the 16th node has the highest citation patent index indicating the technical influence, and the inventor grade is also high. Most likely a node.

In addition, since the eighteenth node is analyzed to have a high citation patent index, it is highly likely to include technology-related patents that have been continuously developed in the target technology field.

In addition, in the 19th node and the 20th node, the family patent index indicating inventor rating and technology marketability is high, while the citation index and the citation index are analyzed to be very low. Is likely to be included. That is, the patents included in the nineteenth node and the twentieth node are likely to be promising technologies.

On the other hand, according to the visualization result of the reference numeral 220, it can be seen that the output nodes having similar characteristics are close. In addition, Table 5 below shows the average value of the patent evaluation index for each output node.

Backward
Citation Forward
Citation Applicant
Grade Family
Patent Node 1 -.0648 -.2837 1.1323 -.6020 Node 2 -.0888 1.2608 1.0345 -.3869 Node 3 -.1228 1.4784 -.6958 -.4142 Node 4 -.0894 -.2936 -.7491 -.7479 Node 5 -.1636 -.3209 -1.7910 -.6452 Node 6 .3654 -.0311 1.0493 1.4444 Node 7 -.0849 -.1765 1.1835 .2836 Node 8 -.0740 -.2542 .1787 -.6163 Node 9 -.1326 -.3631 -.7172 -.0029 Node 10 -.1645 -.3878 -1.3745 .5809 Node 11 .1655 2.3873 .6473 1.4701 Node 12 3.9260 .2597 .5756 .7222 Node 13 -.1129 -.3109 .2212 .2140 Node 14 -.1131 .1589 -.2073 .09227 Node 15 -.1244 -.2338 -.8510 2.3482 Node 16 .3326 10.2107 .4315 1.0033 Node 17 -.0337 4.5111 .2196 .0293 Node 18 16.4313 -.0619 .5824 2.0151 Node 19 .2170 -.0260 .8411 3.5134 Node 20 -.1512 0.4419 .3154 5.9775

That is, the patent analysis system according to an embodiment of the present invention may support a user to easily analyze a promising technology by visualizing a patent evaluation index of patents assigned to each output node through a code plot.

Next, as shown by the reference numerals 230 to 240, the patent analysis system according to an embodiment may visualize the self-organization map in the form of a mapping plot. In other words, the patent analysis system according to an embodiment may visually provide clustered output nodes to a user through hierarchical clustering in a self-organizing map.

Specifically, in the mapping plot, the sixteenth node derived from the core technology code, the eighteenth node derived from the source technology code, and the nineteenth node and the twentieth node derived from the probable technology code are respectively included in the code plot shown at 220. Formed a colony.

That is, the patent analysis system according to an embodiment of the present invention may support a user to easily analyze output nodes having similar characteristics by visualizing a clustering result of each output node through a mapping plot.

Next, as shown by reference numeral 250, the patent analysis system according to an embodiment may visualize the clustering result through the self-organization map through a heat map, and the user may glance at the difference between output nodes through the heat map. Can be compared to and intuitive patterns can be found hidden within the entire data.

Specifically, the heat map is generated by mapping the relationship between the output node of the self-organizing map and the patent evaluation indexes such as citation index (BC), citation index (FC), inventor grade (AG), and family patent index (FP). In addition to the sixteenth, eighteenth, nineteenth, and twentieth nodes identified in the self-organization map through the heat map of reference numeral 250, the eleventh node, the seventeenth node, A twelfth node similar to the eighteenth node that is the original technology node may be additionally derived.

Meanwhile, the analysis result providing unit of the patent analysis system according to an embodiment may automatically analyze the visualization results shown by reference numerals 210 to 250 to extract meaningful data, and provide the extracted meaningful data to the user.

In detail, the analysis result providing unit may derive the sixteenth node as a core technology and extract 13 core patents assigned to the sixteenth node as meaningful data through the visualization results shown at 210 to 250.

In addition, the analysis result provider may derive the eleventh node and the seventeenth node additionally derived through the heat map as key technology candidates, and extract 75 and 61 key patent candidates as significant data, respectively.

In addition, the analysis result provider may derive the 18th node as the source technology and extract the 10 source patents assigned as meaningful data. Finally, the 19th and 20th nodes may be derived as the promising technology and 63 cases may be allocated respectively. And 26 promising technical patents can be extracted as significant data.

Table 6 below shows examples of significant data extracted from the analysis result providing unit.

Number of patents Patent number Core
Patents
(Node 16) 13 US7226196, US6755547, US5904493, US8692267, US8270674, US8154039, US7916221, US5101279, US8577097, US7986375, US7289741, US6734838, US6735482 Source
Patents
(Node 18) 10 US8385610, US8270003, US8174037, US8169688, US7568688, US7300177, US7783075, US7760430, US7750981, US4517580 Emerging Patents
(Node 19,20) 89 US7852384, US7564271, US7138629, US7128270, US6804244, US7734715, US7681799, US7643189, US5323251, US5289023, US8660293, USRE42974, US6947954, US6541284, US9019263, US7558499, US7404642, US7382890, US7302777, 728 US5953148, US5696552, US7869126, US7479141, US7214919, US7154541, US7118134, US6527443, US6172799, US6055027, US5995132, US5416611, US5150138, US7683337, US5424852, US8587757, US8418952, US6785048, US26857, US $ 378,385, US $ 385,385, US $ 385,789 US6089720, US5966167, US8125558, US8933878, US8761412, US8546154, US7922339, US5272029, US5479587, US4432010, US6692097, US8120687, US6122769, US7963687, US8405725, US7917077, US7796753, US7654580, US7646452423, US $ 6983423 US6035071, US4808808, US8934049, US8611658, US8423655, US8274556, US6392726, US6084703, US8189143, US4456336, US6226906, US6053268, US4955580, US4625925

As a result, by using the present invention, it is possible to effectively visualize a large amount of patent big data analysis results, and through the visualization results, it is possible to extract meaningful features for patent analysis on patent big data more quickly and easily.

In addition, based on the patent visualization results, it is possible to easily analyze the floating technology, the blank technology and the core technology in the target technology field.

3 is a diagram illustrating a patent analysis method according to an embodiment of the present invention.

3 is a diagram illustrating a patent analysis method using a patent analysis system according to an embodiment described with reference to FIG. 1, and the description overlapping with the contents described through the patent analysis system according to one embodiment of the contents described through FIG. 3. Will be omitted.

Referring to FIG. 3, in operation 310, the patent analysis method may collect patent data of a target technology field in a patent data collection unit.

Next, in operation 320, the patent analysis method may calculate a patent index from the patent data in the evaluation index calculator.

According to one side, in step 320, the patent analysis method according to an embodiment is a technology influence index, technology marketability index, novelty index and inventor rating from the patent data collected by the evaluation index calculation unit Patent evaluation index including at least one of (Applicant grade) can be calculated.

According to one side, the inventor grade may be calculated from at least one of the application index of the patents held by the inventor, the cited patent index of the patents held by the inventor, and the family patent index of the patents held by the inventor.

Next, in step 330, the patent analysis method according to an embodiment may generate a self-organizing map (SOM) using the patent evaluation index as an input vector in the SOM generator.

According to one side, in step 330, the patent analysis method according to an embodiment may perform hierarchical clustering between the output nodes of the self-organization map in the SOM generator.

Next, in step 340, the patent analysis method according to the embodiment may visualize the self-organization map in the visualization unit.

According to one side, in step 340, the patent analysis method according to an embodiment generates a heat map (Mapping) the mapping between the output node of the self-organizing map and the patent evaluation index in the visualization unit, heat map This allows you to intuitively visualize the characteristics of the output node.

According to one side, in step 340, the patent analysis method according to an embodiment may be provided to the user by extracting significant data from the self-organization map in the analysis result providing unit.

Specifically, the analysis result providing unit according to an embodiment may derive an output node including at least one of the injury technology, blank technology and core technology in the self-organization map, and the Data can be extracted as significant data.

As a result, using the present invention, it is possible to effectively visualize a large amount of patent big data analysis results.

In addition, through the visualization results, it is possible to quickly and easily extract significant features for patent analysis on patent big data.

In addition, self-organization maps and heat maps derived from patent big data analysis can be visualized to easily analyze rising technologies, blank technologies, and core technologies in the field of interest.

The apparatus described above may be implemented as a hardware component, a software component, and / or a combination of hardware components and software components. For example, the devices and components described in the embodiments may include, for example, processors, controllers, arithmetic logic units (ALUs), digital signal processors, microcomputers, field programmable arrays (FPAs), It may be implemented using one or more general purpose or special purpose computers, such as a programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. The processing device may also access, store, manipulate, process, and generate data in response to the execution of the software. For convenience of explanation, one processing device may be described as being used, but one of ordinary skill in the art will appreciate that the processing device includes a plurality of processing elements and / or a plurality of types of processing elements. It can be seen that it may include. For example, the processing device may include a plurality of processors or one processor and one controller. In addition, other processing configurations are possible, such as parallel processors.

The software may include a computer program, code, instructions, or a combination of one or more of the above, and may configure the processing device to operate as desired, or process independently or collectively. You can command the device. Software and / or data may be any type of machine, component, physical device, virtual equipment, computer storage medium or device in order to be interpreted by or to provide instructions or data to the processing device. Or may be permanently or temporarily embodied in a signal wave to be transmitted.

The software may be distributed over networked computer systems so that they may be stored or executed in a distributed manner. Software and data may be stored on one or more computer readable recording media.

The method according to the embodiment may be embodied in the form of program instructions that can be executed by various computer means and recorded on a computer readable medium. The computer readable medium may include program instructions, data files, data structures, and the like, alone or in combination. The program instructions recorded on the media may be those specially designed and constructed for the purposes of the embodiments, or they may be of the kind well-known and available to those having skill in the computer software arts. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tape, optical media such as CD-ROMs, DVDs, and magnetic disks, such as floppy disks. Magneto-optical media, and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine code generated by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like. The hardware device described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

100: patent analysis system 110: patent data collection unit
120: evaluation index calculation unit 130: SOM generation unit
140: visualization unit

Claims (13)

A patent data collecting unit collecting patent data of a target technology field;
An evaluation index calculator configured to calculate a patent index from the collected patent data;
A SOM generator for generating a self-organizing map (SOM) using the patent evaluation index as an input vector;
Visualization unit for visualizing the self-organization map
Patent analysis system comprising a. The method of claim 1,
The patent data collection unit
Collecting the patent data of the target technical field from the patent database using a search expression entered by the user
Patent Analysis System. The method of claim 1,
The evaluation index calculation unit
Calculating the patent evaluation index including at least one of a technology influence index, a technology marketability index, a novelty index, and an applicant grade from the collected patent data.
Patent Analysis System. The method of claim 3,
The inventor rating is
Calculated from at least one of an application index of patents held by the inventor, a cited patent index of patents held by the inventor, and a family patent index of patents held by the inventor
Patent Analysis System. The method of claim 1,
The visualization unit
Visualizing the self-organizing map in the form of at least one of a counts plot and a codes plot
Patent Analysis System. The method of claim 1,
The SOM generation unit
Hierarchical clustering between output nodes of the self-organization map
Patent Analysis System. The method of claim 6,
The visualization unit
Visualizing the hierarchical clustering result in the form of a mapping plot
Patent Analysis System. The method of claim 1,
The visualization unit
Generating a heat map (Mapping) the relationship between the output node of the self-organizing map and the patent evaluation index, and intuitively visualizes the characteristics of the output node through the heat map
Patent Analysis System. Collecting patent data of a target technical field by a patent data collector;
Calculating a patent index from the patent data by a evaluation index calculator;
Generating a self-organizing map (SOM) by using the patent evaluation index as an input vector in an SOM generator;
Visualizing the self-organizing map in a visualization unit
Patent analysis method comprising a. The method of claim 9,
Computing the patent evaluation index
The patent evaluation index including at least one of a technology influence index, a technology marketability index, a novelty index, and an inventor grade from the collected patent data in the evaluation index calculator; To calculate
Patent Analysis Method. The method of claim 10,
The inventor rating is
Calculated from at least one of an application index of patents held by the inventor, a cited patent index of patents held by the inventor, and a family patent index of patents held by the inventor
Patent Analysis Method. The method of claim 9,
Generating the self-organizing map
And performing hierarchical clustering between output nodes of the self-organization map in the SOM generator.
Patent Analysis Method. The method of claim 9,
Visualizing the self-organization map
The visualization unit generates a heat map that maps the relationship between the output node of the self-organizing map and the patent evaluation index, and intuitively visualizes the characteristics of the output node through the heat map. Including more steps
Patent Analysis Method.

Images