CN117436453B - Technical line change trend analysis method and system based on patent data change - Google Patents
Technical line change trend analysis method and system based on patent data change Download PDFInfo
- Publication number
- CN117436453B CN117436453B CN202311743882.6A CN202311743882A CN117436453B CN 117436453 B CN117436453 B CN 117436453B CN 202311743882 A CN202311743882 A CN 202311743882A CN 117436453 B CN117436453 B CN 117436453B
- Authority
- CN
- China
- Prior art keywords
- technical
- data
- analysis
- adopting
- report
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 193
- 230000008859 change Effects 0.000 title claims abstract description 106
- 238000011161 development Methods 0.000 claims abstract description 110
- 238000000034 method Methods 0.000 claims abstract description 55
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 41
- 238000007637 random forest analysis Methods 0.000 claims abstract description 27
- 238000012706 support-vector machine Methods 0.000 claims abstract description 27
- 238000007405 data analysis Methods 0.000 claims abstract description 22
- 238000013528 artificial neural network Methods 0.000 claims abstract description 19
- 230000010354 integration Effects 0.000 claims abstract description 18
- 238000012300 Sequence Analysis Methods 0.000 claims abstract description 12
- 238000010276 construction Methods 0.000 claims abstract description 11
- 230000018109 developmental process Effects 0.000 claims description 108
- 238000011156 evaluation Methods 0.000 claims description 66
- 238000005516 engineering process Methods 0.000 claims description 55
- 238000012545 processing Methods 0.000 claims description 45
- 238000002372 labelling Methods 0.000 claims description 31
- 238000000605 extraction Methods 0.000 claims description 26
- 230000004927 fusion Effects 0.000 claims description 13
- 238000013075 data extraction Methods 0.000 claims description 11
- 238000007619 statistical method Methods 0.000 claims description 11
- 238000006243 chemical reaction Methods 0.000 claims description 10
- 230000011218 segmentation Effects 0.000 claims description 9
- 238000003058 natural language processing Methods 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000003672 processing method Methods 0.000 claims description 7
- 238000013135 deep learning Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 4
- 238000000547 structure data Methods 0.000 claims description 4
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 claims 2
- 230000000007 visual effect Effects 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000012827 research and development Methods 0.000 description 3
- 238000012731 temporal analysis Methods 0.000 description 3
- 238000000700 time series analysis Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 230000004931 aggregating effect Effects 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 230000036962 time dependent Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/042—Knowledge-based neural networks; Logical representations of neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
- G06N3/0455—Auto-encoder networks; Encoder-decoder networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
- G06N5/025—Extracting rules from data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/18—Legal services
- G06Q50/184—Intellectual property management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2123/00—Data types
- G06F2123/02—Data types in the time domain, e.g. time-series data
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Tourism & Hospitality (AREA)
- Technology Law (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to the technical field of intellectual property analysis, in particular to a technical line change trend analysis method and a system based on patent data change. In the invention, by utilizing a time sequence analysis method, the time trend of patent application and expiration can be more effectively analyzed, and important information is provided for solving the history and current state of technical development. The application of the graphic neural network plays a key role in the construction of the technical roadmap, and provides an intuitive tool for understanding the complex technical relationship. The trend analysis is carried out by combining a random forest algorithm and a support vector machine, so that the prediction accuracy is enhanced, and the direction, speed and potential influence of the technical development can be more comprehensively disclosed. By integrating data analysis and report integration techniques, valuable insight and decision support is provided for decision makers.
Description
Technical Field
The invention relates to the technical field of intellectual property analysis, in particular to a technical line change trend analysis method and system based on patent data change.
Background
Intellectual property analysis refers to the process of collecting, arranging, evaluating and analyzing intellectual property such as patents, trademarks and copyrights, and aims to know the development trend, competition pattern and technical innovation direction of the technical field. By analyzing the changes of the patent data, hot spots, trends of technical development and correlations among technologies can be revealed, and a reference basis is provided for making technological innovation strategies for enterprises.
The method for analyzing the change trend of the technical line based on the change of the patent data is a method for researching the change trend of the technical line by using the patent data. The method reveals the development conditions of different technical lines in the technical field through collecting, arranging and analyzing the patent data, and predicts the future technical development direction. The method aims to help enterprises to know the development trend of the technical field through analyzing the patent data, grasp the opportunity of technical innovation and avoid repeated research and development and resource waste. Meanwhile, the method can help enterprises to identify the technical advantages and disadvantages of competitors and formulate corresponding competition strategies.
In the aspect of time sequence analysis, the prior method does not fully utilize an advanced statistical model to analyze and predict the technical development trend, so that the obtained conclusion is inaccurate or has weak adaptability. The existing methods are not intuitive enough to visualize technical routes and lack effective tools to demonstrate complex relationships between technologies. In terms of overall trend analysis and prediction, conventional methods lack the ability to comprehensively utilize multiple algorithms and models, which can lead to limitations in analysis results when dealing with complex, varied technological development data.
Disclosure of Invention
The invention aims to solve the defects in the prior art, and provides a technical line change trend analysis method and a technical line change trend analysis system based on patent data change.
In order to achieve the above purpose, the present invention adopts the following technical scheme: the patent data change-based technical line change trend analysis method comprises the following steps,
s1: based on a patent information base, adopting a natural language processing technology to perform text processing, entity identification and relation extraction to generate a patent data set;
s2: based on the patent data set, applying for and analyzing the expiration time by adopting a time sequence analysis method, and generating time point change information;
S3: based on the patent data set, adopting a BERT deep learning algorithm to extract entities and relations and generate labeling patent data;
s4: based on the labeling patent data, a graphic neural network is adopted to construct a technical roadmap, and the technical roadmap is generated;
s5: based on the time point change information and the technical roadmap, adopting a random forest algorithm and a support vector machine to perform trend analysis and generate a technical development trend analysis report;
s6: based on the technical development trend analysis report, carrying out future technical evaluation by adopting a data analysis technology, and generating a future technical development evaluation report;
s7: based on the technical roadmap and the future technical development evaluation report, adopting a report integration technology to generate a comprehensive technical line change trend analysis report;
the patent data set comprises the technical field, patent description and key entity information, the time point change information is specifically patent application and outdated time sequence data, the labeling patent data is specifically patent data containing key technical entities and relations thereof, the technical roadmap is specifically graph structures representing multiple technical fields and relations thereof, the technical development trend analysis report specifically comprises the technical development direction, the speed and potential influence, the future technical development evaluation report specifically comprises comprehensive evaluation for predicting the technical development direction and the development speed, and the comprehensive technical line change trend analysis report specifically comprises key technical nodes, time marks and development trends.
As a further scheme of the invention, based on the patent information base, the text processing, entity identification and relation extraction are carried out by adopting a natural language processing technology, the specific steps of generating the patent data set are,
s101: based on the patent information base, adopting a text word segmentation algorithm to perform initial text processing to generate text processing data;
s102: based on the text processing data, adopting an HMM model to perform part-of-speech recognition, assisting in entity recognition, and generating part-of-speech tagging data;
s103: based on the part-of-speech tagging data, identifying key entities by adopting a CRF model, and generating entity identification data;
s104: based on the entity identification data, an RNN model is adopted to extract the relation among the entities and generate a patent data set.
As a further aspect of the present invention, the method for applying for and analyzing the expiration time based on the patent data set by using a time series analysis method comprises the specific steps of,
s201: based on the patent data set, a data extraction technology is adopted to extract the patent application date and the expiration date, and patent time information data is generated;
s202: generating standardized time data by adopting a time formatting processing method based on the patent time information data;
S203: based on the standardized time data, adopting an ARIMA model to perform trend analysis on the patent application and the expiration time, and generating time trend analysis data;
s204: based on the time trend analysis data, a Matplotlib library is adopted to display the application and expiration time change trend, and time point change information is generated.
As a further scheme of the invention, based on the patent data set, adopting BERT deep learning algorithm to extract entity and relation, the specific steps of generating labeled patent data are,
s301: based on the patent data set, adopting BERT preprocessing technology to generate processed text data;
s302: based on the processed text data, performing entity identification by adopting a BERT model, identifying key entities in the patent text, and generating an entity identification result;
s303: based on the entity identification result, performing relationship extraction by adopting a BERT model, identifying the relationship among the entities, and generating a relationship extraction result;
s304: and carrying out data integration and labeling based on the relation extraction result to generate labeled patent data.
As a further scheme of the invention, based on the labeling patent data, a graphic neural network is adopted to construct a technical roadmap, the specific steps of generating the technical roadmap are as follows,
S401: based on the labeling patent data, converting the labeling data into graph structure data by adopting a data conversion method to generate graph structured patent data;
s402: based on the structured patent data of the graph, adopting a GNN model to perform node feature learning, and generating a node feature learning result;
s403: based on the node characteristic learning result, predicting edges by adopting a graphic neural network to generate edge prediction results;
s404: and constructing a technical roadmap based on the edge prediction result, and generating the technical roadmap.
As a further scheme of the invention, based on the time point change information and the technical roadmap, adopting a random forest algorithm and a support vector machine to perform trend analysis, generating a technical development trend analysis report comprises the following specific steps of,
s501: based on the time point change information and the technical roadmap, carrying out normalization processing to generate analysis processing data;
s502: based on the analysis processing data, carrying out preliminary trend analysis by adopting a random forest algorithm, identifying key trends and modes, and generating random forest trend analysis results;
s503: based on the random forest trend analysis result, carrying out deep trend analysis by adopting a support vector machine, and generating a support vector machine trend analysis result;
S504: and carrying out report compiling based on the support vector machine trend analysis result, integrating the analysis result and generating a technical development trend analysis report.
As a further aspect of the present invention, based on the technical development trend analysis report, a data analysis technique is adopted to perform future technical evaluation, the specific steps of generating a future technical development evaluation report are,
s601: based on the technical development trend analysis report, data extraction and arrangement are carried out to generate evaluation arrangement data;
s602: based on the evaluation and arrangement data, adopting a descriptive statistical analysis method to analyze the basic characteristics and modes of the technical trend and generate descriptive statistical analysis results;
s603: based on the descriptive statistics analysis result, adopting time sequence analysis to generate a data analysis result;
s604: and based on the data analysis result, performing evaluation report writing, integrating the analysis result and generating a future technical development evaluation report.
As a further scheme of the invention, based on the technical roadmap and the future technical development evaluation report, the report integration technology is adopted, the specific steps of generating the comprehensive technical line change trend analysis report are as follows,
s701: based on the technical roadmap and the future technical development evaluation report, extracting and arranging information to generate a key information data set;
S702: based on the key information data set, a data fusion technology is used for generating a data fusion analysis result;
s703: based on the data fusion analysis result, a trend prediction algorithm is applied to generate a trend prediction analysis result;
s704: and based on the trend prediction analysis result, writing a report, comprehensively analyzing results and generating a comprehensive technical line change trend analysis report.
The technical line change trend analysis system based on patent data change comprises a patent data processing module, a time analysis module, a BERT entity relation analysis module, a technical roadmap construction module, a trend analysis module and a technical evaluation report module.
As a further scheme of the invention, the patent data processing module adopts a text word segmentation algorithm, an HMM model, a CRF model and an RNN model to perform text processing, part-of-speech tagging, entity identification and relation extraction based on a patent information base to generate a patent data set;
the time analysis module is used for analyzing the patent application and the expiration time by adopting a data extraction technology, a time formatting processing method and an ARIMA model based on the patent data set to generate time point change information;
The BERT entity relation analysis module is used for identifying and extracting entities and relations by adopting a BERT preprocessing technology and a BERT model based on a patent data set to generate labeled patent data;
the technical roadmap construction module is used for constructing a technical roadmap by adopting a data conversion method and a graphic neural network GNN based on labeling patent data to generate the technical roadmap;
the trend analysis module adopts a random forest algorithm and a support vector machine to perform trend analysis based on the time point change information and the technical roadmap, performs data analysis, and generates a technical development trend analysis report and a future technical development evaluation report;
the technical evaluation report module generates a comprehensive technical line change trend analysis report by adopting a report integration technology based on the technical development trend analysis report and the future technical development evaluation report.
Compared with the prior art, the invention has the advantages and positive effects that:
in the invention, by utilizing a time sequence analysis method, the time trend of patent application and expiration can be more effectively analyzed, and important information is provided for solving the history and current state of technical development. The application of the graphic neural network plays a key role in the construction of the technical roadmap, helps to visualize the interrelation among multiple technical fields, and provides an intuitive tool for understanding the complex technical relationship. The trend analysis is carried out by combining a random forest algorithm and a support vector machine, so that the prediction accuracy is enhanced, and the direction, speed and potential influence of the technical development can be more comprehensively disclosed. By integrating data analysis and report integration technology, a comprehensive technical line change trend analysis report can be generated, and precious hole finding and decision support are provided for a decision maker.
Drawings
FIG. 1 is a schematic workflow diagram of the present invention;
FIG. 2 is a S1 refinement flowchart of the present invention;
FIG. 3 is a S2 refinement flowchart of the present invention;
FIG. 4 is a S3 refinement flowchart of the present invention;
FIG. 5 is a S4 refinement flowchart of the present invention;
FIG. 6 is a S5 refinement flowchart of the present invention;
FIG. 7 is a S6 refinement flowchart of the present invention;
FIG. 8 is a S7 refinement flowchart of the present invention;
fig. 9 is a system flow diagram of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
In the description of the present invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like indicate orientations or positional relationships based on the orientation or positional relationships shown in the drawings, merely to facilitate describing the present invention and simplify the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and therefore should not be construed as limiting the present invention. Furthermore, in the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
Example 1
Referring to fig. 1, the present invention provides a technical solution: the patent data change-based technical line change trend analysis method comprises the following steps,
s1: based on a patent information base, adopting a natural language processing technology to perform text processing, entity identification and relation extraction to generate a patent data set;
s2: based on a patent data set, applying for and analyzing expiration time by adopting a time sequence analysis method, and generating time point change information;
s3: based on the patent data set, adopting BERT deep learning algorithm to extract entity and relation and generate labeling patent data;
s4: based on the labeling patent data, a graphic neural network is adopted to construct a technical roadmap, and the technical roadmap is generated;
s5: based on the time point change information and the technical roadmap, adopting a random forest algorithm and a support vector machine to perform trend analysis and generate a technical development trend analysis report;
s6: based on the technical development trend analysis report, carrying out future technical evaluation by adopting a data analysis technology, and generating a future technical development evaluation report;
s7: based on a technical roadmap and a future technical development evaluation report, adopting a report integration technology to generate a comprehensive technical line change trend analysis report;
The patent data set comprises the technical field, patent description and key entity information, the time point change information is specifically patent application and expired time sequence data, the labeling patent data is specifically patent data containing key technical entities and relations thereof, the technical roadmap is specifically a graph structure representing multiple technical fields and relations thereof, the technical development trend analysis report specifically comprises the technical development direction, the speed and potential influence, the future technical development evaluation report specifically comprises the comprehensive evaluation of the predicted technical direction and the development speed, and the comprehensive technical line change trend analysis report specifically comprises key technical nodes, time marks and development trends.
The method can comprehensively understand the development trend of the technical field. By processing and analyzing the patent data set, the development condition of different technical lines in the technical field can be revealed, and the future technical development direction can be predicted. This helps enterprises to grasp opportunities for technological innovation, avoiding repeated research and development and resource waste. Can help enterprises identify the technical advantages and disadvantages of competitors. By analyzing the changes of the patent data, hot spots, trends and correlations among technologies in the technical field can be found. The method is beneficial to the enterprises to know the technical strength of competitors and to formulate corresponding competition strategies.
The method can provide visual technical roadmap and trend analysis report. By adopting the graphic neural network to construct the technical roadmap, the multiple technical fields and the association thereof can be displayed in the form of a graph structure. Meanwhile, by adopting a random forest algorithm and a support vector machine to carry out trend analysis, a technical development trend analysis report can be generated, wherein the technical development trend analysis report comprises the technical development direction, the speed, the potential influence and the like. The report can help a decision maker to better understand the change trend of the technical field and make decisions for future technical development.
The method can be used for future technical evaluation and comprehensive analysis report generation. Through the data analysis technology and the report integration technology, a future technical development evaluation report can be generated according to the time point change information and the technical roadmap, and the future technical development evaluation report comprises comprehensive evaluation for predicting the technical direction and the development speed. Meanwhile, a comprehensive technical line change trend analysis report can be generated, wherein the comprehensive technical line change trend analysis report comprises key technical nodes, time marks, development trends and the like. The reports can help a decision maker to comprehensively know the change trend of the technical field, and make accurate assessment and planning for future technical development.
In summary, the technical line change trend analysis method based on patent data change can provide comprehensive technical field development trend analysis for enterprises, help identify advantages and disadvantages of competitors, provide visual technical roadmap and trend analysis report, and generate future technical evaluation and comprehensive analysis report. The method is beneficial to enterprises to maintain competitive advantages in the technical field, and the method takes the opportunity of technical innovation and realizes sustainable development.
Referring to fig. 2, based on the patent information base, text processing, entity recognition and relation extraction are performed by using natural language processing technology, and the specific steps of generating a patent data set are,
s101: based on the patent information base, adopting a text word segmentation algorithm to perform initial text processing to generate text processing data;
s102: based on text processing data, adopting an HMM model to perform part-of-speech recognition, assisting in entity recognition, and generating part-of-speech tagging data;
s103: based on the part-of-speech tagging data, identifying key entities by adopting a CRF model, and generating entity identification data;
s104: based on the entity identification data, an RNN model is adopted to extract the relation among the entities and generate a patent data set.
And performing initial text processing on the text in the patent information base by using a text word segmentation algorithm. This step aims to segment long sentences into shorter words or phrases for subsequent processing and analysis. Through text segmentation, the original text can be converted into a series of meaningful words. Based on the results of the initial text processing, part-of-speech tagging is performed using Hidden Markov Models (HMMs). By training the model, the part of speech of each word, such as nouns, verbs, adjectives, etc., can be automatically marked. Part-of-speech tagging helps to further identify entities because different entities typically have different part-of-speech characteristics. Key entity identification is performed using a Conditional Random Field (CRF) model. According to the part-of-speech labeling result, the CRF model can learn probability dependency relations among different entities and identify key entities such as person names, place names, organization names and the like. And the method is helpful for extracting important information in the patent text. And extracting the relation among the entities by using a cyclic neural network (RNN) model. The RNN model may capture semantic associations between entities by considering context information. By analyzing and modeling the entity recognition result, the relation and interaction between different entities in the patent text can be extracted. These relationships can be used to construct patent datasets and provide the basis for subsequent analysis and application.
In summary, through the natural language processing technology based on the patent information base, initial text processing, part-of-speech tagging, key entity identification and extraction of relationships between entities can be performed, so as to generate a patent data set.
Referring to fig. 3, based on the patent data set, the time sequence analysis method is adopted to analyze the application and expiration time, the specific steps of generating the time point change information are,
s201: based on the patent data set, adopting a data extraction technology to extract the patent application date and expiration date and generate patent time information data;
s202: based on the patent time information data, generating standardized time data by adopting a time formatting processing method;
s203: based on the standardized time data, adopting an ARIMA model to perform trend analysis on the patent application and the expiration time, and generating time trend analysis data;
s204: based on time trend analysis data, a Matplotlib library is adopted to display the change trend of application and expiration time, and time point change information is generated.
Patent application date and expiration date are extracted from the patent dataset using a data extraction technique to generate patent time information data. This may be accomplished by parsing relevant information fields in the patent text or by using a database query, etc. And carrying out time formatting processing on the patent time information data to generate standardized time data. It is intended to convert date and time unification of different formats into a standard form that can be compared and analyzed, such as converting a date in the form of a string into a numeric-type time stamp. Based on the normalized time data, an autoregressive moving average model (ARIMA) is used to perform trend analysis on the patent application and expiration time, and time trend analysis data is generated. The ARIMA model captures trends, seasonal and periodic features in the time series data, revealing long-term trends in patent applications and expiration times. And displaying the change trend of the patent application and the expiration time by using a Matplotlib library, and generating time point change information. Through drawing a line graph or a graph, the change condition of patent application and expiration time along with time can be intuitively observed, and important information about the development trend of the technical field can be obtained from the change condition.
In summary, by the time series analysis method based on the patent data set, the patent application and the expiration time can be analyzed, and the time point change information can be generated. The implementation needs to be refined and adjusted according to actual conditions, including selecting a proper data extraction technology and a time formatting processing method, optimizing ARIMA model parameters, reasonably selecting visualization tools and the like.
Referring to fig. 4, based on the patent data set, the BERT deep learning algorithm is adopted to extract entities and relations, and the specific steps of generating labeled patent data are,
s301: based on the patent data set, adopting BERT preprocessing technology to generate processed text data;
s302: based on the processed text data, performing entity identification by adopting a BERT model, identifying key entities in the patent text, and generating an entity identification result;
s303: based on the entity identification result, adopting a BERT model to perform relation extraction, identifying the relation among the entities, and generating a relation extraction result;
s304: and carrying out data integration and labeling based on the relation extraction result to generate labeled patent data.
And processing the patent data set by using the BERT preprocessing technology to generate processed text data. Including the operations of word segmentation, stop word removal, conversion to the input format required by the BERT model, etc. Based on the processed text data, performing entity recognition by using the BERT model, recognizing key entities in the patent text, and generating an entity recognition result. The BERT model can learn rich semantic information through a pre-trained language model, so that entities in the text can be accurately identified. And according to the entity identification result, performing relation extraction by using the BERT model, identifying the relation among the entities, and generating a relation extraction result. By analyzing the context information and semantic associations between entities, specific relationships between them, such as collaboration, reference, etc., can be inferred. And carrying out data integration and labeling according to the relation extraction result, and generating labeled patent data. May include associating entity and relationship information with the original patent text, adding additional attributes or tags, and the like. The labeled patent data may be used for further machine learning or natural language processing tasks such as classification, clustering, knowledge graph construction, and the like.
In summary, through the BERT deep learning algorithm based on the patent data set, entity and relationship extraction can be performed, and labeled patent data can be generated. During implementation, the method is required to be refined and adjusted according to actual conditions, and comprises the steps of selecting proper preprocessing technology and model parameters, optimizing data integration and labeling methods and the like.
Referring to fig. 5, based on the labeling patent data, a graphic neural network is adopted to construct a technical roadmap, the specific steps of generating the technical roadmap are,
s401: based on the labeling patent data, converting the labeling data into graph structure data by adopting a data conversion method to generate graph structured patent data;
s402: based on the graph structured patent data, adopting a GNN model to perform node feature learning, and generating a node feature learning result;
s403: based on the node characteristic learning result, predicting edges by adopting a graphic neural network to generate edge prediction results;
s404: and constructing a technical roadmap based on the edge prediction result, and generating the technical roadmap.
And converting the labeling patent data into graph structure data by using a data conversion method, and generating the graph structure patent data. Including converting entity and relationship information into the form of nodes and edges, and adding additional attributes or labels. Based on the structured patent data of the graph, the GNN model is used for node feature learning, and a node feature learning result is generated. The GNN model can update the feature representation of the node by aggregating the information of neighboring nodes, thereby capturing the context information and semantic associations of the node in the graph. And according to the node characteristic learning result, predicting edges by using a graph neural network, and generating an edge prediction result. By analyzing the context information and semantic associations between nodes, possible relationships between them, such as collaboration, references, etc., can be inferred. And constructing a technical roadmap according to the edge prediction result, and generating the technical roadmap. The method comprises the steps of connecting predicted edges with existing nodes to form a complete graph structure, and carrying out visual display according to a specific layout algorithm.
In summary, the technical roadmap can be constructed by using the graphic neural network based on the labeling patent data. During implementation, the method needs to be refined and adjusted according to actual conditions, and comprises the steps of selecting a proper data conversion method and GNN model parameters, optimizing edge prediction, a layout algorithm and the like.
Referring to fig. 6, based on the time point change information and the technical roadmap, the trend analysis is performed by adopting a random forest algorithm and a support vector machine, the specific steps of generating a technical development trend analysis report are,
s501: based on the time point change information and the technical roadmap, carrying out normalization processing to generate analysis processing data;
s502: based on analysis processing data, carrying out preliminary trend analysis by adopting a random forest algorithm, identifying key trends and modes, and generating random forest trend analysis results;
s503: based on random forest trend analysis results, carrying out deep trend analysis by adopting a support vector machine, and generating support vector machine trend analysis results;
s504: and (3) carrying out report programming based on the support vector machine trend analysis result, integrating the analysis result, and generating a technical development trend analysis report.
And carrying out normalization processing on the time point change information and the technical roadmap to generate analysis processing data. The method comprises the steps of converting time point change information into numerical time series data, and carrying out operations such as standardization or coding on nodes and edges in a technical roadmap. Based on the analysis processing data, a random forest algorithm is used for carrying out preliminary trend analysis, key trends and modes are identified, and a random forest trend analysis result is generated. Random forest algorithms can be predicted and classified by integrating multiple decision tree models, capturing complex relationships and nonlinear features in the data. And carrying out deep trend analysis by using a support vector machine according to the random forest trend analysis result, and generating a support vector machine trend analysis result. The support vector machine is a supervised learning algorithm, and can be used for classifying and carrying out regression analysis on data by constructing an optimal hyperplane, so that deeper trends and modes are revealed. And (3) according to the trend analysis result of the support vector machine, carrying out report programming, integrating the analysis result and generating a technical development trend analysis report. The method comprises the steps of reading and summarizing trend analysis results, extracting important findings and insights, and arranging the important findings and insights into a visual report form.
In summary, through the random forest algorithm and the support vector machine based on the time point change information and the technical roadmap, trend analysis can be performed, and a technical development trend analysis report can be generated.
Referring to fig. 7, based on the technical development trend analysis report, the data analysis technique is adopted to perform future technical evaluation, and the specific steps of generating the future technical development evaluation report are,
s601: based on the technical development trend analysis report, data extraction and arrangement are carried out to generate evaluation arrangement data;
s602: based on the evaluation and arrangement data, adopting a descriptive statistical analysis method to analyze the basic characteristics and modes of the technical trend and generate descriptive statistical analysis results;
s603: based on descriptive statistical analysis results, generating data analysis results by adopting time sequence analysis;
s604: based on the data analysis result, the evaluation report is written, the analysis result is integrated, and the future technical development evaluation report is generated.
And according to the technical development trend analysis report, extracting and sorting the data to generate evaluation sorting data. Including extracting key trend information, technical indicators, etc. from the report and converting it into a format and structure suitable for analysis. Based on the assessment arrangement data, basic features and patterns of technical trends are analyzed using descriptive statistical analysis methods, and descriptive statistical analysis results are generated. Descriptive statistical analysis can reveal the central trend, degree of dispersion and distribution of data by calculating statistical indexes such as mean, standard deviation, frequency distribution and the like. According to the descriptive statistical analysis result, a time sequence analysis method is adopted to further analyze the change rule and trend prediction of the technical trend, and a data analysis result is generated. The time series analysis may be applied to modeling and prediction of time-dependent data, such as ARIMA model, exponential smoothing, etc. And according to the data analysis result, writing an evaluation report, integrating the analysis result, and generating a future technical development evaluation report. Including interpretation and summarization of analytical results, extraction of important findings and insights, and sorting into visual reporting forms.
In summary, through the data analysis technology based on the technology development trend analysis report, the evaluation of the future technology can be performed, and the future technology development evaluation report can be generated.
Referring to fig. 8, based on the technical roadmap and the future technical development evaluation report, the report integration technology is adopted to generate the comprehensive technical line change trend analysis report by the specific steps of,
s701: based on the technical roadmap and the future technical development evaluation report, extracting and arranging information to generate a key information data set;
s702: based on the key information data set, generating a data fusion analysis result by using a data fusion technology;
s703: based on the data fusion analysis result, a trend prediction algorithm is applied to generate a trend prediction analysis result;
s704: and based on the trend prediction analysis result, writing a report, comprehensively analyzing the result and generating a comprehensive technical line change trend analysis report.
And extracting and arranging information according to the technical roadmap and the future technical development evaluation report to generate a key information data set. Including extracting key technical indicators, trend information, etc. from the report and converting it into a format and structure suitable for analysis. Based on the key information data set, data fusion technology is used for integrating data from different sources, and data fusion analysis results are generated. Data fusion can integrate and correlate information from different data sources to provide more comprehensive and accurate analysis results. And according to the data fusion analysis result, a trend prediction algorithm is applied to predict the change trend of the technical line, and a trend prediction analysis result is generated. The trend prediction algorithm can infer future development trends and changes through analysis and modeling of historical data. And according to the trend prediction analysis result, writing a report, comprehensively analyzing the result and generating a comprehensive technical line change trend analysis report. Including interpretation and summarization of the analysis results, extraction of important findings and sorting into visual reporting forms.
In summary, through the report integration technology based on the technical roadmap and the future technical development evaluation report, analysis of the comprehensive technical line change trend can be performed, and a corresponding analysis report can be generated.
Referring to fig. 9, the system for analyzing the trend of the technical line change based on the patent data change includes a patent data processing module, a time analysis module, a BERT entity relationship analysis module, a technical roadmap construction module, a trend analysis module, and a technical evaluation report module.
The patent data processing module is used for carrying out text processing, part-of-speech tagging, entity identification and relation extraction by adopting a text word segmentation algorithm, an HMM model, a CRF model and an RNN model based on a patent information base to generate a patent data set;
the time analysis module is used for analyzing the patent application and the expiration time by adopting a data extraction technology, a time formatting processing method and an ARIMA model based on the patent data set to generate time point change information;
the BERT entity relation analysis module is used for identifying and extracting entities and relations by adopting a BERT preprocessing technology and a BERT model based on a patent data set to generate labeled patent data;
the technical roadmap construction module is used for constructing a technical roadmap by adopting a data conversion method and a graphic neural network GNN based on the labeling patent data to generate the technical roadmap;
The trend analysis module is used for carrying out trend analysis by adopting a random forest algorithm and a support vector machine based on the time point change information and the technical roadmap, carrying out data analysis, and generating a technical development trend analysis report and a future technical development evaluation report;
the technical evaluation report module generates a comprehensive technical line change trend analysis report by adopting a report integration technology based on the technical development trend analysis report and the future technical development evaluation report.
The patent data processing module can perform text processing, part-of-speech tagging, entity identification and relation extraction on a large amount of patent information to generate a patent data set. This helps to improve the quality and usability of the patent data, providing a reliable data base for subsequent analysis work.
The time analysis module can generate time point change information through analysis of patent application and expiration time. The method has important significance for knowing the development trend and the change condition of the technology, can help enterprises grasp the opportunity of technological innovation, and avoids repeated research and development and application of outdated technology.
The BERT entity relation analysis module utilizes a pre-trained BERT model to identify and extract entities and relations and generate labeling patent data. The accuracy and the reliability of the entity relationship can be improved, and powerful support is provided for the construction of the technical roadmap.
The technical roadmap construction module adopts a data conversion method and a graphic neural network GNN to convert the labeling patent data into a graphic structure so as to generate a technical roadmap. Is helpful for intuitively displaying the development venation and key nodes of the technology and provides important references for enterprises to formulate technical development strategies.
The trend analysis module analyzes the time point change information and the technical roadmap through a random forest algorithm and a support vector machine, performs data analysis, and generates a technical development trend analysis report and a future technical development evaluation report. The method can help enterprises to know the development trend and potential risk of the technology, and make scientific decisions for future technology development and application.
The technical evaluation report module generates a comprehensive technical line change trend analysis report by integrating the technical development trend analysis report and the future technical development evaluation report. Is beneficial to comprehensively evaluating the development prospect and market potential of the technology and provides important basis for making a long-term development strategy for enterprises.
The present invention is not limited to the above embodiments, and any equivalent embodiments which can be changed or modified by the technical disclosure described above can be applied to other fields, but any simple modification, equivalent changes and modification made to the above embodiments according to the technical matter of the present invention will still fall within the scope of the technical disclosure.
Claims (7)
1. The technical line change trend analysis method based on patent data change is characterized by comprising the following steps,
based on a patent information base, adopting a natural language processing technology to perform text processing, entity identification and relation extraction to generate a patent data set;
based on the patent data set, applying for and analyzing the expiration time by adopting a time sequence analysis method, and generating time point change information;
based on the patent data set, adopting a BERT deep learning algorithm to extract entities and relations and generate labeling patent data;
based on the labeling patent data, a graphic neural network is adopted to construct a technical roadmap, and the technical roadmap is generated;
based on the time point change information and the technical roadmap, adopting a random forest algorithm and a support vector machine to perform trend analysis and generate a technical development trend analysis report;
based on the technical development trend analysis report, carrying out future technical evaluation by adopting a data analysis technology, and generating a future technical development evaluation report;
based on the technical roadmap and the future technical development evaluation report, adopting a report integration technology to generate a comprehensive technical line change trend analysis report;
The patent data set comprises the technical field, patent description and key entity information, the time point change information is specifically patent application and outdated time sequence data, the labeling patent data is specifically patent data containing key technical entities and relations thereof, the technical roadmap is specifically a graph structure representing multiple technical fields and relations thereof, the technical development trend analysis report specifically comprises the technical development direction, the speed and potential influence, the future technical development evaluation report specifically comprises comprehensive evaluation for predicting the technical development direction and the development speed, and the comprehensive technical line change trend analysis report specifically comprises key technical nodes, time marks and development trends;
based on the patent data set, adopting a time sequence analysis method to apply for and analyze the expiration time, generating time point change information,
based on the patent data set, a data extraction technology is adopted to extract the patent application date and the expiration date, and patent time information data is generated;
generating standardized time data by adopting a time formatting processing method based on the patent time information data;
based on the standardized time data, adopting an ARIMA model to perform trend analysis on the patent application and the expiration time, and generating time trend analysis data;
Based on the time trend analysis data, a Matplotlib library is adopted to display the application and expiration time change trend, and time point change information is generated;
based on the labeling patent data, adopting a graphic neural network to construct a technical roadmap, and generating the technical roadmap comprises the following specific steps of,
based on the labeling patent data, converting the labeling data into graph structure data by adopting a data conversion method to generate graph structured patent data;
based on the structured patent data of the graph, adopting a GNN model to perform node feature learning, and generating a node feature learning result;
based on the node characteristic learning result, predicting edges by adopting a graphic neural network to generate edge prediction results;
constructing a technical roadmap based on the edge prediction result, and generating the technical roadmap;
based on the time point change information and the technical roadmap, adopting a random forest algorithm and a support vector machine to perform trend analysis, generating a technical development trend analysis report,
based on the time point change information and the technical roadmap, carrying out normalization processing to generate analysis processing data;
based on the analysis processing data, carrying out preliminary trend analysis by adopting a random forest algorithm, identifying key trends and modes, and generating random forest trend analysis results;
Based on the random forest trend analysis result, carrying out deep trend analysis by adopting a support vector machine, and generating a support vector machine trend analysis result;
and carrying out report compiling based on the support vector machine trend analysis result, integrating the analysis result and generating a technical development trend analysis report.
2. The method for analyzing the trend of the technical line change based on the change of the patent data according to claim 1, wherein the text processing, the entity recognition and the relation extraction are performed by adopting a natural language processing technology based on a patent information base, the specific steps of generating the patent data set are as follows,
based on the patent information base, adopting a text word segmentation algorithm to perform initial text processing to generate text processing data;
based on the text processing data, adopting an HMM model to perform part-of-speech recognition, assisting in entity recognition, and generating part-of-speech tagging data;
based on the part-of-speech tagging data, identifying key entities by adopting a CRF model, and generating entity identification data;
based on the entity identification data, an RNN model is adopted to extract the relation among the entities and generate a patent data set.
3. The method for analyzing the change trend of technical lines based on the change of patent data according to claim 1, wherein the specific steps of extracting entities and relations and generating labeled patent data are as follows,
Based on the patent data set, adopting BERT preprocessing technology to generate processed text data;
based on the processed text data, performing entity identification by adopting a BERT model, identifying key entities in the patent text, and generating an entity identification result;
based on the entity identification result, performing relationship extraction by adopting a BERT model, identifying the relationship among the entities, and generating a relationship extraction result;
and carrying out data integration and labeling based on the relation extraction result to generate labeled patent data.
4. The method for analyzing the trend of technical line change based on patent data change according to claim 1, wherein based on the technical trend analysis report, a data analysis technique is adopted to perform future technical evaluation, the specific steps of generating a future technical development evaluation report are,
based on the technical development trend analysis report, data extraction and arrangement are carried out to generate evaluation arrangement data;
based on the evaluation and arrangement data, adopting a descriptive statistical analysis method to analyze the basic characteristics and modes of the technical trend and generate descriptive statistical analysis results;
based on the descriptive statistics analysis result, adopting time sequence analysis to generate a data analysis result;
And based on the data analysis result, performing evaluation report writing, integrating the analysis result and generating a future technical development evaluation report.
5. The method for analyzing the trend of the technical line change based on the change of the patent data according to claim 1, wherein the specific steps for generating the comprehensive technical line change trend analysis report by adopting the report integration technology based on the technical line graph and the future technical development evaluation report are,
based on the technical roadmap and the future technical development evaluation report, extracting and arranging information to generate a key information data set;
based on the key information data set, a data fusion technology is used for generating a data fusion analysis result;
based on the data fusion analysis result, a trend prediction algorithm is applied to generate a trend prediction analysis result;
and based on the trend prediction analysis result, writing a report, comprehensively analyzing results and generating a comprehensive technical line change trend analysis report.
6. The technical line change trend analysis system based on patent data change is characterized in that the system comprises a patent data processing module, a time analysis module, a BERT entity relation analysis module, a technical roadmap construction module, a trend analysis module and a technical evaluation reporting module according to the technical line change trend analysis method based on patent data change of any one of claims 1 to 5.
7. The system for analyzing the change trend of the technical line based on the change of the patent data according to claim 6, wherein the patent data processing module is used for performing text processing, part-of-speech tagging, entity identification and relation extraction by adopting a text word segmentation algorithm, an HMM model, a CRF model and an RNN model based on a patent information base to generate a patent data set;
the time analysis module is used for analyzing the patent application and the expiration time by adopting a data extraction technology, a time formatting processing method and an ARIMA model based on the patent data set to generate time point change information;
the BERT entity relation analysis module is used for identifying and extracting entities and relations by adopting a BERT preprocessing technology and a BERT model based on a patent data set to generate labeled patent data;
the technical roadmap construction module is used for constructing a technical roadmap by adopting a data conversion method and a graphic neural network GNN based on labeling patent data to generate the technical roadmap;
the trend analysis module adopts a random forest algorithm and a support vector machine to perform trend analysis based on the time point change information and the technical roadmap, performs data analysis, and generates a technical development trend analysis report and a future technical development evaluation report;
The technical evaluation report module generates a comprehensive technical line change trend analysis report by adopting a report integration technology based on the technical development trend analysis report and the future technical development evaluation report.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311743882.6A CN117436453B (en) | 2023-12-19 | 2023-12-19 | Technical line change trend analysis method and system based on patent data change |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311743882.6A CN117436453B (en) | 2023-12-19 | 2023-12-19 | Technical line change trend analysis method and system based on patent data change |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117436453A CN117436453A (en) | 2024-01-23 |
CN117436453B true CN117436453B (en) | 2024-04-09 |
Family
ID=89551887
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311743882.6A Active CN117436453B (en) | 2023-12-19 | 2023-12-19 | Technical line change trend analysis method and system based on patent data change |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117436453B (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101996175A (en) * | 2009-08-11 | 2011-03-30 | 上海汉光知识产权数据科技有限公司 | Patent technology path analysis method |
CN105677907A (en) * | 2016-02-16 | 2016-06-15 | 大连理工大学 | Patent technology evolution analysis method and system |
WO2021060875A2 (en) * | 2019-06-25 | 2021-04-01 | 김정중 | Patent network establishment guide system and method using big data technique |
CN115238965A (en) * | 2022-06-29 | 2022-10-25 | 广东省智湾汇科技有限公司 | Technical trend prediction method, device, equipment and medium based on patent information |
-
2023
- 2023-12-19 CN CN202311743882.6A patent/CN117436453B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101996175A (en) * | 2009-08-11 | 2011-03-30 | 上海汉光知识产权数据科技有限公司 | Patent technology path analysis method |
CN105677907A (en) * | 2016-02-16 | 2016-06-15 | 大连理工大学 | Patent technology evolution analysis method and system |
WO2021060875A2 (en) * | 2019-06-25 | 2021-04-01 | 김정중 | Patent network establishment guide system and method using big data technique |
CN115238965A (en) * | 2022-06-29 | 2022-10-25 | 广东省智湾汇科技有限公司 | Technical trend prediction method, device, equipment and medium based on patent information |
Also Published As
Publication number | Publication date |
---|---|
CN117436453A (en) | 2024-01-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110825882B (en) | Knowledge graph-based information system management method | |
Ansari | Cost-based text understanding to improve maintenance knowledge intelligence in manufacturing enterprises | |
WO2018184518A1 (en) | Microblog data processing method and device, computer device and storage medium | |
CN113138920B (en) | Software defect report allocation method and device based on knowledge graph and semantic role labeling | |
CN112507691A (en) | Interpretable financial subject matter generating method and device fusing emotion, industrial chain and case logic | |
CN100470547C (en) | Method, system and device for implementing data mining model conversion and application | |
CN117271767B (en) | Operation and maintenance knowledge base establishing method based on multiple intelligent agents | |
CN116542800A (en) | Intelligent financial statement analysis system based on cloud AI technology | |
CN116861924A (en) | Project risk early warning method and system based on artificial intelligence | |
CN115203338A (en) | Label and label example recommendation method | |
Addepalli et al. | A proposed framework for measuring customer satisfaction and product recommendation for ecommerce | |
CN116610592B (en) | Customizable software test evaluation method and system based on natural language processing technology | |
CN117290508A (en) | Post-loan text data processing method and system based on natural language processing | |
CN117436453B (en) | Technical line change trend analysis method and system based on patent data change | |
CN114388108A (en) | User feedback analysis method based on multi-task learning | |
CN117216221A (en) | Intelligent question-answering system based on knowledge graph and construction method | |
Liu et al. | A two-stage clustering ensemble algorithm applicable to risk assessment of railway signaling faults | |
CN115858805A (en) | Knowledge graph construction management system and method | |
Karthikeyan et al. | Machine learning based student performance analysis system | |
Van der Aa | Comparing and Aligning Process Representations. | |
CN111563162A (en) | MOOC comment analysis system and method based on text emotion analysis | |
CN117787569B (en) | Intelligent auxiliary bid evaluation method and system | |
Ayele | Adapting CRISP-DM for Idea Mining: A Data Mining Process for Generating Ideas Using a Textual Dataset | |
CN117435777B (en) | Automatic construction method and system for industrial chain map | |
CN117852637B (en) | Definition-based subject concept knowledge system automatic construction method and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |