Financial science and technology patent classification method based on technical field

Abstract

The invention provides a financial science and technology patent classification method based on the technical field, and the method comprises the steps: building a three-stage classification system, obtaining a text, carrying out the keyword extraction, carrying out the text classification based on the three-stage classification system, and setting a corresponding three-stage label for a financial science and technology patent based on a classification result, the three-level classification system comprises a first-level key technology, a second-level technology application and a third-level technology point, systematized and subdivided classification is carried out on the financial science and technology patents, different technology ranges of the financial science and technology patents are reasonably defined, and therefore the accuracy and efficiency of financial science and technology patent classification are remarkably improved; the classified financial science and technology patents are retrieved, different types of financial science and technology patents can be rapidly and accurately recognized from massive patent data, financial science and technology patent information management and application are optimized, and financial science and technology innovation development analysis in different technical fields is promoted.

Description

Technical Field

[0001] The present invention belongs to the technical field of patent classification methods, and specifically relates to a fintech patent classification method based on the technical field. Background Art

[0002] As an important manifestation of innovative achievements, patents play an important role in legal protection and market competitive advantages, and demonstrate the technological strength of an institution. In October 2020, the People's Bank of China issued the "Financial Technology Development Index" JR / T0201-2020, which included the "number of patent applications authorized" and "number of software copyrights" in the "R&D capability" indicators of banking and financial institutions to encourage and examine their financial technology research and innovation capabilities. Studying the development of financial technology from the perspective of "financial technology patents" not only helps to gain an in-depth understanding of the hot spots and trends of technological innovation, but also provides valuable intelligence support for enterprises and research institutions, and effectively prevents technological infringement and market competition risks. The quantity and quality of financial technology patents directly reflect the technological innovation capabilities and market competitiveness of a country or region in the field of financial technology. Therefore, systematic research and analysis of financial technology patents has important academic and practical significance.

[0003] However, due to the problems of fuzzy concept definition and overlapping fields in financial technology, its patent classification and retrieval are very difficult. At present, the classification research on financial technology patents at home and abroad is still in a blank stage, lacking a systematic and unified classification standard. The existing patent classification methods mainly rely on the International Patent Classification (IPC) system and the patent classification systems of various countries, such as the United States Patent Classification (USPC) and the European Patent Classification (ECLA). However, the classification based on patent classification numbers cannot directly correspond to the classification of financial technology patents. These classification systems are more based on macro fields and application scenarios, lacking the subdivision of technical fields unique to financial technology, resulting in many limitations and deficiencies in practical applications. In addition, some studies have attempted to classify from the perspective of business type and financial service category, but have ignored the cross-domain characteristics and complexity of the technology itself, making it difficult to fully reflect the current status of technological innovation in financial technology.

[0004] Existing fintech patent classifications are almost all constructed through manual induction. Most of them are searched in patent databases by limiting a single or a few IPC classification numbers and constructing a search keyword set. The data range is difficult to fully cover the fintech field, resulting in limitations in the comprehensiveness and rationality of existing fintech patent technology classifications. Summary of the invention

[0005] In order to solve the above problems, a fintech patent classification method based on the technical field is provided. The present invention adopts the following technical solutions:

[0006] The present invention provides a method for classifying fintech patents based on the technical field, which has the following technical features: step S1, establishing a three-level classification system for fintech patents; step S2, classifying the fintech patents according to the text of the fintech patents to be classified and the three-level classification system, wherein the three-level classification system includes a primary classification, a secondary classification and a tertiary classification, the primary classification is a primary key technology in the financial field, the secondary classification is a secondary technical application corresponding to the primary key technology, and the tertiary classification is a tertiary technical point corresponding to the secondary technical application.

[0007] The fintech patent classification method based on the technical field provided by the present invention may also have such technical features, wherein the first-level key technologies include: artificial intelligence, big data, blockchain, Internet of Things, biometrics, cloud computing, cryptographic security, quantum security, communication technology, privacy computing, robotic process automation, human-computer interaction, AR and VR technology and future key technologies.

[0008] The financial technology patent classification method based on the technical field provided by the present invention may also have such technical features, wherein the secondary technical applications corresponding to the artificial intelligence include: machine learning technology, natural language processing technology, computer vision technology, expert system technology, intelligent recommendation system technology, and large model technology; the secondary technical applications corresponding to the big data include: big data storage and management technology, big data analysis and mining technology, big data processing and computing technology, and big data privacy and security technology; the secondary technical applications corresponding to the blockchain include: blockchain data structure and algorithm, blockchain consensus algorithm optimization, smart contracts, and privacy protection applications in blockchain; the secondary technical applications corresponding to the Internet of Things include: financial Internet of Things applications, Internet of Things data analysis, and Internet of Things security; the secondary technical applications corresponding to biometrics include: fingerprint recognition, iris recognition, voiceprint recognition, DNA recognition, behavioral feature recognition, and the application of biometrics in financial security; the secondary technical applications corresponding to cloud computing include: cloud storage and computing technology technology, financial cloud platform technology, cloud security technology, virtualization technology; the secondary technology applications corresponding to the cryptographic security include: encryption algorithm, password management and storage, authentication and authorization, key management; the secondary technology applications corresponding to the quantum security include: quantum key distribution, quantum cryptography, quantum secure communication, quantum computing security; the secondary technology applications corresponding to the communication technology include: network protocol, communication network, data transmission; the secondary technology applications corresponding to the privacy computing include: secure multi-party computing, federated learning, trusted execution environment; the secondary technology applications corresponding to the robotic process automation include: financial and accounting automation, customer service automation, human resources automation, supply chain and logistics automation, IT service management automation, sales and marketing automation; the secondary technology applications corresponding to the human-computer interaction include: voice interaction, somatosensory interaction, gesture interaction, brain-computer interaction, visual interaction, multimodal interaction; the secondary technology applications corresponding to the AR and VR technology include: AR technology, VR technology, AR and VR applications.

[0009] The fintech patent classification method based on the technical field provided by the present invention may also have such technical features, wherein the secondary technology applications corresponding to the future key technologies include: future networks, advanced computing, web3.0, massive storage, security and reliability, and digital twins.

[0010] The fintech patent classification method based on the technical field provided by the present invention may also have such a technical feature, wherein the three-level classification system is pyramid-shaped, each of the first-level key technologies corresponds to one or more of the second-level technical applications, and each of the second-level technical applications corresponds to one or more of the third-level technical points.

[0011] The fintech patent classification method based on the technical field provided by the present invention may also have such a technical feature, wherein, in step S2, the text of the fintech patent to be classified is obtained, the text content is analyzed and keywords are extracted, and the first-level key technology, the second-level technical application involved, and the third-level technical points included in the fintech patent are determined in turn according to the extracted keywords, so as to classify the fintech patent.

[0012] The fintech patent classification method based on the technical field provided by the present invention may also have such a technical feature, wherein, in step S2, a corresponding three-level label is set for the fintech patent according to the classification result, and a fintech patent subject database is constructed based on the fintech patent and the corresponding three-level label.

[0013] The fintech patent classification method based on the technical field provided by the present invention may also have such technical features, and the method may further include the following steps: Step S3, developing a fintech patent classification system and tools based on the three-level classification system to realize the automatic classification and management of fintech patents; Step S4, optimizing the three-level classification system at least according to the technology update situation, and updating the fintech patent classification system and tools accordingly.

[0014] Functions and Effects of the Invention

[0015] According to the method for classifying fintech patents based on the technical field provided by the present invention, the method includes the steps of establishing a three-level classification system, obtaining text and extracting keywords, classifying text based on the three-level classification system, and setting corresponding three-level labels for fintech patents based on the classification results, wherein the three-level classification system includes the first-level key technology, the second-level technical application and the third-level technical point, and systematically and subdividedly classifies fintech patents, reasonably defines the different technical scopes of fintech patents, so as to significantly improve the accuracy and efficiency of fintech patent classification, and retrieves the fintech patents classified in this way, so as to realize the rapid and accurate identification of different categories of fintech patents from massive patent data, optimize the management and application of fintech patent information, and promote the analysis of fintech innovation and development in different technical fields. In addition, by constructing such a three-level classification system, the current status and trend of fintech technological innovation can be more comprehensively reflected, which will help the healthy and sustainable development of the industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a flow chart of a method for classifying fintech patents based on technical fields in an embodiment of the present invention;

[0017] Figure 2 is a flow chart of step S1 in an embodiment of the present invention;

[0018] Figure 3 It is a schematic diagram of the classification system of fintech patents in an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the following is a detailed description of the financial technology patent classification method based on the technical field of the present invention in combination with embodiments and drawings.

[0020] <Example>

[0021] Figure 1 It is a flow chart of the fintech patent classification method based on the technical field in this embodiment.

[0022] like Figure 1 As shown, the method comprises the following steps:

[0023] Step S1, establish a three-level classification system for fintech patents.

[0024] Step S2: classify the fintech patent according to the fintech patent text to be classified and the three-level classification system.

[0025] Optionally, the method may further include the following steps:

[0026] Step S3, develop a fintech patent classification system and tools based on the three-level classification system of fintech patents to achieve automated classification and management of fintech patents.

[0027] Step S4, optimize the three-level classification system and update the fintech patent classification system and tools accordingly.

[0028] The above steps will be described in detail below.

[0029] Step S1, establish a three-level classification system for fintech patents.

[0030] Figure 2 is a flow chart of step S1 in this embodiment.

[0031] like Figure 2 As shown, step S1 specifically includes the following sub-steps:

[0032] Step S1-1, obtain relevant texts in the financial field and analyze the major categories of science and technology to which the text content belongs, and set multiple first-level key technologies based on the analysis results.

[0033] The text related to the financial field may be a patent text in the financial field, or may further include papers, web page data, and the like.

[0034] In this embodiment, 14 first-level key technologies are set according to the key technologies currently widely used in the financial field, including artificial intelligence, big data, blockchain, Internet of Things, biometrics, cloud computing, cryptographic security, quantum security, communication technology, privacy computing, robotic process automation, human-computer interaction, AR and VR technology, and future key technologies. The following Table 1 shows the names of these 14 first-level key technologies and their technical application overview.

[0035] Table 1 Classification and overview of first-level key technologies in financial technology

[0036]

[0037]

[0038] Step S1-2: for each first-level key technology corresponding to the financial field related text, analyze the technical applications involved in the text content, and set one or more second-level technical applications for each first-level key technology according to the analysis results.

[0039] Among them, the secondary technology applications corresponding to artificial intelligence include six secondary categories: machine learning technology, natural language processing technology, computer vision technology, expert system technology, intelligent recommendation system technology and large model technology.

[0040] The secondary technical applications corresponding to big data include four secondary categories: big data storage and management technology, big data analysis and mining technology, big data processing and computing technology, and big data privacy and security technology.

[0041] The secondary technical applications corresponding to blockchain include four secondary categories: blockchain data structure and algorithm, blockchain consensus algorithm optimization, smart contracts, and the application of privacy protection in blockchain.

[0042] The secondary technical applications corresponding to the Internet of Things include three secondary categories: financial Internet of Things applications, Internet of Things data analysis, and Internet of Things security.

[0043] The secondary technical applications corresponding to biometrics include six secondary categories: fingerprint recognition, iris recognition, voiceprint recognition, DNA recognition, behavioral feature recognition, and the application of biometrics in financial security.

[0044] The secondary technical applications corresponding to cloud computing include four secondary categories: cloud storage and computing technology, financial cloud platform technology, cloud security technology, and virtualization technology.

[0045] The secondary technical applications corresponding to password security include four secondary categories: encryption algorithm, password management and storage, authentication and authorization, and key management.

[0046] The secondary technical applications corresponding to quantum security include four secondary categories: quantum key distribution, quantum cryptography, quantum secure communication, and quantum computing security.

[0047] The secondary technical applications corresponding to communication technology include three secondary categories: network protocol, communication network, and data transmission.

[0048] The secondary technical applications corresponding to privacy computing include three secondary categories: secure multi-party computing, federated learning, and trusted execution environment.

[0049] The secondary technical applications corresponding to robotic process automation include six secondary categories: financial and accounting automation, customer service automation, human resources automation, supply chain and logistics automation, IT service management automation, and sales and marketing automation.

[0050] The secondary technical applications corresponding to human-computer interaction include six secondary categories: voice interaction, somatosensory interaction, gesture interaction, brain-computer interaction, visual interaction, and multimodal interaction.

[0051] The secondary technical applications corresponding to AR and VR technologies include three secondary categories: AR technology, VR technology, and AR and VR applications.

[0052] The secondary technology applications corresponding to future key technologies include six secondary categories: future networks, advanced computing, web3.0, massive storage, security and trust, and digital twins.

[0053] Step S1-3: Analyze the technical points involved in the financial field related text corresponding to each secondary technical application, and set one or more tertiary technical points for each secondary technical application according to the analysis results.

[0054] Among them, the third-level technical points are more specific descriptions of the corresponding second-level technical applications. For example, for machine learning technology, the corresponding third-level technical points include supervised learning, deep learning, reinforcement learning, and transfer learning.

[0055] Through the above steps, a complete three-level classification system for fintech patents is constructed. The classification system is pyramid-shaped and includes 14 first-level key technologies (first-level classification), 62 second-level technology applications (second-level classification) and 197 third-level technology points (third-level classification).

[0056] Figure 3 is a schematic diagram of the three-level classification system of fintech patents in this embodiment. The following Table 2 shows the detailed information of the three-level classification system.

[0057] Table 2: Three-level classification system of fintech patents

[0058]

[0059]

[0060]

[0061]

[0062]

[0063]

[0064] Step S2: classify the fintech patent according to the fintech patent text to be classified and the three-level classification system.

[0065] For example, the text of the financial technology patent to be classified can be obtained, the text content can be analyzed and keywords can be extracted, and the first-level key technology to which the financial technology patent belongs can be determined based on the extracted keywords, and then the second-level technology applications involved in the financial technology patent can be determined based on the keywords and multiple second-level technology applications under the determined first-level key technology. Similarly, the third-level technology points contained in the financial technology patent can be determined based on the keywords and multiple third-level technology points under the determined second-level technology applications. Optionally, the corresponding classification model can be trained to realize the automatic classification of the financial technology patent text.

[0066] Then, a corresponding three-level label can be set for each financial technology patent according to the classification results, and a financial technology patent database can be constructed based on the financial technology patent text and the corresponding three-level label. Optionally, the database can also further contain other information such as extracted keywords corresponding to the patent text. Users with corresponding search needs can directly perform a quick search in the database. For example, if the user is a scientific researcher, he can select the corresponding first-level key technology, second-level technology application, and third-level technology point in turn according to the specific technical points he is studying, and obtain a list of all financial technology patents containing the third-level technology point.

[0067] Step S3, develop a fintech patent classification system and tools based on the three-level classification system of fintech patents to achieve automated classification and management of fintech patents.

[0068] At present, the School of Financial Technology of Fudan University has completed the construction of the "Fintech Patent Thematic Library" based on the above classification system, which saves the tedious patent search process for users with corresponding testing needs. Based on the Fintech Patent Thematic Library, researchers can quickly locate relevant patents according to the research field. In addition, the system supports online intelligent patent data analysis, which can help researchers achieve efficient patent layout and innovation.

[0069] Step S4, optimize the three-level classification system and update the fintech patent classification system and tools accordingly.

[0070] Among them, in actual patent management and analysis, the actual effect of the system based on the three-level classification system can be determined according to user feedback, and the above three-level classification system can be continuously optimized and improved according to the actual effect and technological updates to ensure its stability and accuracy.

[0071] Functions and Effects of the Embodiments

[0072] According to the fintech patent classification method based on the technical field provided in this embodiment, it includes the steps of establishing a three-level classification system, obtaining text and extracting keywords, classifying text based on the three-level classification system, and setting corresponding three-level labels for fintech patents based on the classification results, wherein the three-level classification system includes the first-level key technology, the second-level technical application and the third-level technical point, and systematically and subdividedly classifies fintech patents, reasonably defines the different technical scopes of fintech patents, so as to significantly improve the accuracy and efficiency of fintech patent classification, and retrieves the fintech patents classified in this way, so as to realize the rapid and accurate identification of different categories of fintech patents from massive patent data, optimize the management and application of fintech patent information, and promote the analysis of fintech innovation and development in different technical fields. In addition, by constructing such a three-level classification system, it is possible to more comprehensively reflect the current status and trend of fintech technological innovation and help the healthy and sustainable development of the industry.

[0073] Specifically, the method of the present invention achieves the following beneficial effects:

[0074] Improved the accuracy and efficiency of fintech patent classification: By building a fintech patent classification system from the perspectives of technical fields such as artificial intelligence, cloud computing, and blockchain, fintech patent data can be processed and retrieved more quickly and accurately.

[0075] Improved the management and application level of FinTech patent information: The classification system of the present invention provides comprehensive and systematic patent information analysis support for research institutions and enterprises to better carry out technology layout and strategic planning.

[0076] Promoted cross-domain technology exchange and cooperation: The technology field classification method helps researchers and developers in different technology fields to communicate and cooperate more effectively, and promotes cross-domain technology integration and innovation.

[0077] Provide strong data support for policy formulation and market supervision: The classification system of the present invention can provide data support for policy formulation and market supervision, and promote the standardized development of the financial technology industry.

[0078] Enhanced my country's position and influence in the global financial technology competition: The classification system of the present invention can also promote international exchanges and cooperation in the field of financial technology, and enhance my country's position and influence in the global financial technology competition.

[0079] Assisting the strategic layout of national industries and micro-enterprises: The present invention also helps to identify innovations in the field of financial technology, analyze the branches and industry applications with the greatest development potential, so as to grasp the development trends of financial technology and assist the strategic layout of national industries and micro-enterprises.

[0080] In addition, the three-level classification system constructed in the present invention also has a certain reference value for the classification and analysis of patents in emerging cross-fields similar to the financial technology field.

[0081] The above embodiments are only used to illustrate the specific implementation of the present invention, and the present invention is not limited to the description scope of the above embodiments. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only to illustrate the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, and these changes and improvements fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A classification method for fintech patents based on technical fields, characterized in that: The following steps are involved: Step S1, establish a three-level classification system for fintech patents; Step S2, classifying the fintech patent to be classified according to the text of the fintech patent and the three-level classification system, The three-level classification system includes primary classification, secondary classification and tertiary classification. The first-level classification is the first-level key technology in the financial field. The second-level classification is the second-level technology application corresponding to the first-level key technology. The three-level classification is a three-level technical point corresponding to the second-level technical application.

2. The method for classifying fintech patents based on technical fields according to claim 1 is characterized by: in, The first-level key technologies include: artificial intelligence, big data, blockchain, the Internet of Things, biometrics, cloud computing, cryptographic security, quantum security, communication technology, privacy computing, robotic process automation, human-computer interaction, AR and VR technologies, as well as future key technologies.

3. The method for classifying fintech patents based on technical fields according to claim 2 is characterized by: in, The secondary technology applications corresponding to the artificial intelligence include: machine learning technology, natural language processing technology, computer vision technology, expert system technology, intelligent recommendation system technology, and large model technology. The secondary technology applications corresponding to the big data include: big data storage and management technology, big data analysis and mining technology, big data processing and computing technology, and big data privacy and security technology. The secondary technical applications corresponding to the blockchain include: blockchain data structure and algorithm, blockchain consensus algorithm optimization, smart contracts, and privacy protection applications in blockchain. The secondary technology applications corresponding to the Internet of Things include: financial Internet of Things applications, Internet of Things data analysis, and Internet of Things security. The secondary technology applications corresponding to the biometrics include: fingerprint recognition, iris recognition, voiceprint recognition, DNA recognition, behavioral feature recognition, and the application of biometrics in financial security. The secondary technology applications corresponding to the cloud computing include: cloud storage and computing technology, financial cloud platform technology, cloud security technology, and virtualization technology. The secondary technical applications corresponding to the password security include: encryption algorithm, password management and storage, authentication and authorization, key management, The secondary technical applications corresponding to the quantum security include: quantum key distribution, quantum cryptography, quantum secure communication, and quantum computing security. The secondary technology applications corresponding to the communication technology include: network protocol, communication network, data transmission, The secondary technical applications corresponding to the privacy computing include: secure multi-party computing, federated learning, and trusted execution environment. The secondary technology applications corresponding to the robotic process automation include: financial and accounting automation, customer service automation, human resources automation, supply chain and logistics automation, IT service management automation, sales and marketing automation, The secondary technical applications corresponding to the human-computer interaction include: voice interaction, somatosensory interaction, gesture interaction, brain-computer interaction, visual interaction, and multimodal interaction. The secondary technology applications corresponding to the AR and VR technologies include: AR technology, VR technology, AR and VR applications.

4. The method for classifying fintech patents based on technical fields according to claim 2 is characterized by: in, The secondary technology applications corresponding to the future key technologies include: future networks, advanced computing, web3.0, massive storage, security and reliability, and digital twins.

5. The method for classifying fintech patents based on technical fields according to claim 1 is characterized by: in, The three-level classification system is pyramid-shaped. Each of the first-level key technologies corresponds to one or more of the second-level technical applications, and each of the second-level technical applications corresponds to one or more of the third-level technical points.

6. The method for classifying fintech patents based on technical fields according to claim 1 is characterized by: in, In step S2, the text of the fintech patent to be classified is obtained, the text content is analyzed and keywords are extracted, and the first-level key technology, the second-level technical application, and the third-level technical points included in the fintech patent are determined in turn according to the extracted keywords, so as to classify the fintech patent.

7. The method for classifying fintech patents based on technical fields according to claim 6 is characterized by: in, In step S2, corresponding three-level labels are set for the fintech patents according to the classification results, and a fintech patent subject database is constructed based on the fintech patents and the corresponding three-level labels.

8. The method for classifying fintech patents based on technical fields according to claim 1 is characterized in that: The following steps are also included: Step S3, developing a fintech patent classification system and tools based on the three-level classification system to achieve automated classification and management of fintech patents; Step S4, at least optimize the three-level classification system according to the technological update, and update the fintech patent classification system and tools accordingly.

Images