Technology transaction platform management system based on big data

Abstract

The invention relates to the technical field of transaction platform management, and discloses a technology transaction platform management system based on big data, and the system comprises a data collection module which collects technology transaction big data related to technology transaction and carries out the data preprocessing; the foreground evaluation module is used for analyzing, calculating and evaluating the technology transaction foreground of the technology based on the technology transaction big data, and establishing a dynamic technology foreground evaluation system through real-time data acquisition and processing; the transaction recommendation module is used for carrying out foreground trend classification on technologies by combining historical change data based on a dynamic technical foreground evaluation system, carrying out reasonable prediction on technical potential values, and recommending and optimizing transaction time through the technical potential values; the risk assessment module is used for calculating the transaction risk of the expected transaction technology analysis technology to obtain a transaction risk value, and analyzing and judging the risk type of the transaction technology based on the transaction risk value; and the reasonable evaluation module comprehensively analyzes and judges the rationality of the technology transaction in combination with the technology transaction foreground and the transaction risk value.

Description

Technical Field

[0001] The present invention relates to the technical field of transaction platform management, and in particular to a technology transaction platform management system based on big data. Background Art

[0002] In existing technologies, there is a lack of a quantitative evaluation system for core information such as technology maturity and market prospects of technology suppliers, making it difficult for demanders to accurately judge the technology prospects. Traditional keyword matching fails to consider the deep correlation between technology and demand dimensions, resulting in a mismatch between supply and demand. Technology prices rely on subjective negotiations or historical case references, lacking a dynamic quantitative model and failing to reflect the real-time market prospects of the technology. Big data is not used to build a multi-dimensional technology evaluation model, resulting in highly subjective evaluation results. Matching algorithms do not integrate dynamic data such as technology attributes, market demand, and subject credit, resulting in insufficient matching accuracy and a lack of a dynamic pricing mechanism based on market supply and demand and the technology life cycle.

[0003] Traditional systems rely heavily on structured data and have weak processing capabilities for unstructured data, particularly lacking in-depth analysis of patent technical features, leading to a lack of technical dimension assessment. Existing technologies often rely on scheduled batch data collection rather than real-time acquisition, making it difficult to capture transient market changes in a timely manner. The lack of a unified data model to integrate patent, market, industry, and internal enterprise data leads to prominent data silos, covering only a few risks while ignoring specific risks such as legal, compliance, and technological substitution. Cross-platform risk transmission mechanisms are fuzzy, weight allocation is crude, and trend classification relies on a single indicator, failing to integrate the multi-dimensional characteristics of policies and patent citations. Prediction models are simple and difficult to adapt to complex scenarios.

[0004] In view of this, it is necessary to provide a technology transaction platform management system based on big data. Summary of the Invention

[0005] The purpose of the present invention is to provide a technology trading platform management system based on big data. In order to solve the above-mentioned existing technical problems, the present invention is achieved through the following technical solutions:

[0006] First, the present invention provides a technology trading platform management system based on big data, which specifically includes the following modules:

[0007] Data collection module: collects big data about technology transactions and performs data preprocessing;

[0008] Prospect Assessment Module: Analyzes and calculates the technology transaction prospects of a technology based on technology transaction big data, and establishes a dynamic technology prospect assessment system through real-time data collection and processing;

[0009] Trading recommendation module: Based on a dynamic technology prospect assessment system, it combines historical change data to classify technology prospects and trends, and makes reasonable predictions of technology potential values. It then recommends and optimizes trading times based on the technology potential values.

[0010] Risk Assessment Module: Analyzes the expected trading technology and calculates the trading risk to obtain the trading risk value. Based on the trading risk value analysis, the risk type of the trading technology is determined.

[0011] Reasonable evaluation module: Combines the technology transaction prospects and transaction risk value to comprehensively analyze and judge the rationality of technology transactions.

[0012] Second, specifically, the present invention provides a method for managing a technology trading platform based on big data, which specifically includes the following steps:

[0013] S1: Collect big data on technology transactions and perform data preprocessing;

[0014] S2: Analyze and evaluate the technology transaction prospects of technologies based on technology transaction big data, and establish a dynamic technology prospect evaluation system through real-time data collection and processing;

[0015] S3: Based on a dynamic technology prospect assessment system, combined with historical change data, the technology prospect trend is classified, and the technology potential value is reasonably predicted. The transaction time is recommended and optimized based on the technology potential value;

[0016] S4: Analyze the expected trading technology's trading risk and calculate the trading risk value, and determine the risk type of the trading technology based on the trading risk value analysis;

[0017] S5: Combine the technology transaction prospects and transaction risk value to comprehensively analyze and judge the rationality of the technology transaction.

[0018] Beneficial effects of the present invention:

[0019] 1. Integrate patent, market, industry, and enterprise data to achieve structured and unstructured data collection and resolve data silos; combine market comparison and income approaches to incorporate data such as patent status and market fluctuations in real time, dynamically adjust model parameters, and form a data-assessment-feedback closed loop; formulate differentiated trading strategies based on technology trends and optimize trading time windows; cover legal, market, compliance, and technological substitution risks, utilize graph databases and NLP to parse contracts, dynamically assign risk weights, and quantify cross-platform risk transmission effects; construct a two-dimensional matrix of prospects and risks, match strategies such as smart contract generation, multi-party negotiation, and observation-level transactions, and achieve efficient and compliant automated execution; extract patent technical features through regular expressions, convert unstructured text into quantifiable indicators, strengthen technical dimension assessment, adapt to complex scenarios such as policy changes and geopolitical conflicts, improve prediction accuracy, and resolve digital asset trading compatibility issues. From real-time data collection to automatic strategy triggering, form an agile data-assessment-decision-making closed loop to improve market responsiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 This is a flowchart of the steps of a technology trading platform management system based on big data provided by Example 1 of the present invention;

[0022] Figure 2 This is a structural diagram of a technology transaction platform management system based on big data provided by Example 2 of the present invention. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of the present invention.

[0024] Example 1

[0025] like Figure 1 As shown, the embodiment of the present invention provides a technology transaction platform management system based on big data, which specifically includes the following modules:

[0026] Data collection module: collects big data about technology transactions and performs data preprocessing;

[0027] It should be noted that technology transaction big data includes but is not limited to: patent data, market transaction data, industry data and internal enterprise data;

[0028] In a specific embodiment, the specific processing method for collecting technology transaction big data about technology transactions and performing data preprocessing is:

[0029] For patent data, the API is used to pull patent data regularly and update the data in full at 2:00 a.m. every day. Incremental data is synchronized every hour. It supports searching by patent number or technical field keyword and returns data in JSON format.

[0030] It should be noted that API refers to a set of definitions, protocols, and tools for interaction and communication between different software components, applications, or systems; JSON stands for JavaScript Object Notation, which is a lightweight data exchange format used for data transmission and storage between network applications;

[0031] For patent claims and specifications, use Python's Beautiful Soup to parse XML / HTML text and extract technical features through regular expressions;

[0032] Subscribe to patent legal status change events through Websocket, capture global patent family layout data once a week, and comprehensively obtain patent validity period, patent citation number and patent family size;

[0033] It should be noted that Websocket refers to a network protocol that implements full-duplex communication over a single TCP connection, allowing two-way real-time data transmission between the client and the server;

[0034] For market transaction data, we obtain order book data in real time through the exchange's Websocket interface, use the Scrapy framework to crawl historical transaction lists, and process PDF transaction reports using OCR technology. For example, after converting the scanned documents into text, we use NLP to identify key figures and comprehensively obtain historical transaction prices, trading activity, and market supply and demand relationships.

[0035] It should be noted that OCR technology stands for optical character recognition technology;

[0036] Directly download CSV / Excel files, read and map them into a unified data model using Pandas, use spaCy to identify keywords for named entities, combine sentiment analysis to determine industry prospects, and comprehensively obtain industry growth rates, technological innovation trends, and industry competition levels;

[0037] For internal enterprise data, authorized access is achieved through the enterprise API gateway, and Kettle is used for scheduled extraction. For non-digital documents, form OCR recognition is performed and then structured into the database, which comprehensively obtains R&D investment costs, technology application effects, and enterprise strategic position.

[0038] Normalize the collected technology transaction big data.

[0039] Prospect Assessment Module: Analyzes and calculates the technology transaction prospects of a technology based on technology transaction big data, and establishes a dynamic technology prospect assessment system through real-time data collection and processing;

[0040] In a specific embodiment, the specific processing method for analyzing and calculating the technology transaction prospects of the technology based on the technology transaction big data is:

[0041] Evaluate the prospect of the target technology by comparing the market transaction prices of similar technologies, determine the selection criteria for comparable cases, collect transaction information of comparable cases, including but not limited to: transaction price, transaction time and transaction conditions, adjust the comparable cases, consider the differences between the target technology and the comparable cases, calculate the prospect of the target technology based on the adjusted comparable case prices, and comprehensively obtain the market prospect SC;

[0042] For example, based on the same target technology, three comparable cases were collected: Case 1, the transaction price was RMB 5 million, the transaction time was March 2021, and the transaction conditions were technology transfer including partial technical support; Case 2, the transaction price was RMB 6 million, the transaction time was April 2022, and the transaction conditions were technology licensing for a period of five years; Case 3, the transaction price was RMB 4.5 million, the transaction time was May 2023, and the transaction conditions were technology equity investment, accounting for 20% of the shares; for technical performance, the energy density of the target technology is 10% higher than that of Case 1, 15% higher than that of Case 2, and 20% higher than that of Case 3. The price adjustment coefficient is set to 1.1 for every 10% increase in technical performance; for market demand, the current market demand for the field where the target technology is located Compared to the transaction in Case 2, the price increased by 20%. For every 10% increase in market demand, the price adjustment coefficient was set at 1.05. Regarding transaction conditions, the target technology transaction involved technology transfer and comprehensive technical support, while Case 1 only included partial technical support, so the adjustment coefficient was 1.05. Case 2 involved technology licensing, so the adjustment coefficient was 1.2. Case 3 involved technology equity investment, so the adjustment coefficient was 1.1. After adjustment, the prices of Cases 1, 2, and 3 were RMB 5.775 million, RMB 8.694 million, and RMB 5.94 million, respectively. The market prospects of the target technology were calculated using a weighted average method, assuming that the weights of Cases 1, 2, and 3 were 0.3, 0.4, and 0.3, respectively. The calculated market prospects were 0.70921.

[0043] Evaluate the technology's future prospects based on the expected future benefits of the technology, consider the cash flow that the technology will bring to the enterprise in a certain period of time in the future, and convert the expected benefits into current prospects by discounting. The technical outlook JS is calculated, where θ represents the preset outlook correction coefficient, R i represents the expected income in year i, r represents the discount rate, and n represents the earnings forecast period;

[0044] The technology transaction prospects are obtained by weighted calculation based on the obtained market prospects and technology prospects;

[0045] In a specific embodiment, the specific processing method for establishing a dynamic technology prospect evaluation system by implementing data collection and processing is:

[0046] Use the data acquisition module to obtain real-time updates on technology transaction big data, including changes in patent status, market transaction price fluctuations, and industry dynamics. Based on real-time technology transaction big data, timely adjust evaluation indicators and model parameters;

[0047] Pay attention to market feedback on technology, including but not limited to: changes in customer needs and technological innovations of competitors. Adjust the evaluation results accordingly if the prospects of technology change based on market feedback;

[0048] Trading recommendation module: Based on a dynamic technology prospect assessment system, it combines historical change data to classify technology prospects and trends, and makes reasonable predictions of technology potential values. It then recommends and optimizes trading times based on the technology potential values.

[0049] In a specific embodiment, the specific method of classifying technology prospects and trends by combining historical change data is as follows:

[0050] Extract historical technology outlook data from the dynamic technology outlook assessment system, select monthly outlook data for the past N years, calculate the standard deviation of the monthly outlook data and the deviation from the moving average, and use NLP to analyze the frequency of technology keywords in policy documents to quantify the degree of policy support or restriction.

[0051] Use K-means algorithm to roughly classify technologies;

[0052] It should be noted that the K-means algorithm represents a classic unsupervised learning clustering algorithm, which is used to divide the data set into K clusters so that the similarity of data points within the same cluster is high and the similarity between different clusters is low;

[0053] For the fluctuation type technology, time series clustering (DTW algorithm) is used to identify periodic and random subclasses;

[0054] It should be noted that the DTW algorithm is an algorithm used to measure the similarity between two time series. It is particularly suitable for comparing sequences whose time axes are not strictly aligned. In time series clustering, DTW solves the problem that traditional Euclidean distance cannot handle time misalignment by calculating the curvature distance between sequences, thereby improving clustering accuracy.

[0055] Technologies with a growth rate of ≥10% for six consecutive months and a policy correlation that deviates positively from the industry mean by more than 2σ are marked as trending technologies, where σ represents the standard deviation of the industry policy correlation.

[0056] Technologies with an annualized prospect decay rate greater than 10% and whose patent citation ranking falls out of the top 30% of the industry are marked as sunset technologies;

[0057] Techniques with monthly volatility > 15% but no sustained downward trend are labeled as volatile techniques;

[0058] In a specific embodiment, the specific method for reasonably predicting the technical potential value is:

[0059] Build an LSTM-Prophet hybrid model. The LSTM neural network captures the long-term and short-term dependencies of technology prospects. Prophet time series analysis decomposes the impact of exogenous variables such as policy shocks and industry cycles. Dynamically adjust model weights through Q-learning, for example, to increase the predictive contribution of policy factors during geopolitical conflicts.

[0060] It should be noted that Prophet time series refers to time series data with periodicity, trend, and holiday effects, and Q-learning refers to a model-free reinforcement learning algorithm used to solve the problem of learning optimal behavior strategies through trial and error in an environment.

[0061] Capture the opinions of industry leaders in real time, generate a market sentiment index mapped to [0,1], monitor changes in the technical NFT collateralization rate in DeFi protocols, and predict liquidity tightening risk factors;

[0062] The pre-processed historical data and real-time data are input into the hybrid model, combined with the market sentiment index and liquidity tightening risk factor to predict the future technical potential value.

[0063] In a specific embodiment, the specific method for recommending and optimizing transaction time based on technical potential value is:

[0064] Construct the utility function for both buyers and sellers: Seller utility = transaction price - technology holding cost - opportunity cost; Buyer utility = expected technology return - transaction price - risk premium. Calculate the price-time Pareto frontier that maximizes the utility of both parties and output the intelligent bargaining range.

[0065] Simulate M trading scenarios and calculate the transaction probability and expected returns at different time points:

[0066] For trending technologies, it is recommended to complete transactions in the early stages of technology diffusion;

[0067] For volatile technologies, identify the low point in the outlook and initiate a reverse takeover;

[0068] Preset trigger conditions, for example, price volatility <5% and market sentiment index >70. When real-time data meets the conditions, a contract signing request is automatically pushed to both the buyer and the seller.

[0069] For OTC block transactions, the threshold signature scheme (TSS) is adopted, which requires the joint signature of three authorized nodes to take effect, to prevent unilateral malicious operations;

[0070] Risk Assessment Module: Analyzes the expected trading technology and calculates the trading risk to obtain the trading risk value. Based on the trading risk value analysis, the risk type of the trading technology is determined.

[0071] In a specific embodiment, the specific method for calculating the transaction risk value by analyzing the expected transaction technology is as follows:

[0072] Through the global patent invalidation litigation database, the invalidation success rate of patents in the same family of target technologies is calculated. For example, if it exceeds 30%, it is marked as high risk;

[0073] Analyze whether the technical features of the independent claims have been circumvented by competing products and comprehensively determine the legal risk factors;

[0074] Calculate the deviation between the order submission rate and the order cancellation rate per second. If it exceeds the industry average by 3σ, the risk value is increased by 20%.

[0075] By building a transaction address graph using a graph database (Neo4j), we can identify fraudulent transactions where the same controller manipulates multiple wallet addresses, and comprehensively derive manipulation risk factors.

[0076] Connect to the database to detect whether the transaction party is involved in a sanctioned entity. For example, if there is a secondary equity connection, the risk value is +50%;

[0077] Use NLP technology to analyze export contracts, identify violations of sensitive data flow clauses, and conduct comprehensive analysis to obtain compliance risk factors;

[0078] Based on academic paper preprints and patent priority data, the breakthrough speed of similar technologies is quantified. For example, if the annual improvement rate of technology energy density exceeds 15%, the risk value is increased by 30%, and the replacement risk factor is obtained comprehensively;

[0079] Calculate the information entropy of each risk factor based on historical data and dynamically assign initial weights;

[0080] For example, the weight of legal risk in patent transactions is set at 40%, and the weight of manipulation risk in cryptocurrency transactions is set at 55%.

[0081] Construct ideal solutions and negative ideal solutions, and calculate the proximity of the target technology to the optimal / worst risk level;

[0082] Specifically, through the formula Calculate the transaction risk value FX, where w i It represents the dynamic weight of the i-th risk factor, F i represents the standardized value of the i-th risk factor, λ represents the regulatory policy correction factor, C r It represents the cross-platform risk contagion coefficient;

[0083] It should be noted that the cross-platform risk contagion coefficient is a dynamic coefficient used to quantify the risk transmission effect of technology assets in multi-market, multi-chain, and multi-platform transactions. Its essence is to measure the probability and impact of a single technology transaction event on related markets.

[0084] In a specific embodiment, the specific method for determining the risk type of a transaction technology based on transaction risk value analysis is:

[0085] Different risk levels are divided according to the size of the transaction risk value;

[0086] Reasonable evaluation module: Combines technology transaction prospects and transaction risk value to comprehensively analyze and judge the rationality of technology transactions;

[0087] In a specific embodiment, the specific method for comprehensively analyzing and judging the rationality of a technology transaction by combining the technology transaction prospects and the transaction risk value is as follows:

[0088] Construct a two-dimensional decision matrix: Based on the weighted results of market mechanism comparison and profit prospect comparison, the matrix is divided into three levels: high, medium, and low according to the preset prospect threshold;

[0089] The stratified results of the aforementioned risk levels are mapped to a normalized coefficient of 0-1;

[0090] By formula The technical rational value HL is calculated, where α represents the industry adjustment coefficient;

[0091] Compare the obtained reasonable value of the technology with the preset reasonable standard value, conduct a comprehensive analysis to determine the rationality of the technology transaction and make a decision;

[0092] Specifically, for high-prospect, low-risk technology transactions, we generate optimal transaction templates, support one-click generation of smart contracts, and prioritize recommendations on the exchange homepage.

[0093] For high-prospect, high-risk technology transactions, we initiate multi-party negotiation agreements and invite technology brokers, legal advisors, and insurance companies to jointly negotiate risk-sharing plans;

[0094] Technology transactions with low prospects and low risks are marked as observation-level transactions and are only allowed to be executed in limited scenarios, such as internal technology transfer or strategic cooperation testing.

[0095] The technical solution of the present invention is as follows: integrating patent, market, industry, and enterprise data to realize structured and unstructured data collection and solve the problem of data silos; combining market comparison method and income method to incorporate data such as patent status and market fluctuations in real time, dynamically adjust model parameters, and form a data-evaluation-feedback closed loop; formulating differentiated trading strategies according to technology trend classification and optimizing trading time windows; covering legal, market, compliance, technology substitution and other risks, using graph databases and NLP to parse contracts, dynamically assigning risk weights, and quantifying cross-platform risk transmission effects; constructing a prospect-risk dual-dimensional matrix, matching strategies such as smart contract generation, multi-party negotiation, and observation-level transactions to achieve efficient and compliant automated execution; extracting patent technical features through regular expressions, converting unstructured text into quantifiable indicators, strengthening technical dimension evaluation, adapting to complex scenarios such as policy changes and geopolitical conflicts, improving prediction accuracy, and solving the compatibility problem of digital asset transactions. From real-time data collection to automatic strategy triggering, an agile data-evaluation-decision-making full-process closed loop is formed to improve market response speed.

[0096] Example 2

[0097] like Figure 2 As shown, an embodiment of the present invention provides a method for managing a technology trading platform based on big data, which specifically includes the following steps:

[0098] S1: Collect big data on technology transactions and perform data preprocessing;

[0099] S2: Analyze and evaluate the technology transaction prospects of technologies based on technology transaction big data, and establish a dynamic technology prospect evaluation system through real-time data collection and processing;

[0100] S3: Based on a dynamic technology prospect assessment system, combined with historical change data, the technology prospect trend is classified, and the technology potential value is reasonably predicted. The transaction time is recommended and optimized based on the technology potential value;

[0101] S4: Analyze the expected trading technology's trading risk and calculate the trading risk value, and determine the risk type of the trading technology based on the trading risk value analysis;

[0102] S5: Combine the technology transaction prospects and transaction risk value to comprehensively analyze and judge the rationality of the technology transaction.

[0103] An embodiment of the present invention is described in detail above, but the content described is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention; the above formulas are all dimensionless and numerical calculations, and the formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field based on actual conditions and historical experience, and can be adjusted according to actual conditions; the above description is only a preferred embodiment of the present invention and is not used to limit the present invention. All equal changes and improvements made according to the scope of application of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A technology trading platform management system based on big data, characterized in that: Includes the following modules: Data collection module: collects big data about technology transactions and performs data preprocessing; Prospect Assessment Module: Analyzes and calculates the technology transaction prospect value of a technology based on technology transaction big data, and establishes a dynamic technology prospect assessment system through real-time data collection and processing; Trading recommendation module: Based on a dynamic technology prospect assessment system, it combines historical change data to classify technology prospects and trends, and makes reasonable predictions of technology potential values. It then recommends and optimizes trading times based on the technology potential values. Risk Assessment Module: Analyzes the expected trading technology and calculates the trading risk to obtain the trading risk value. Based on the trading risk value analysis, the risk type of the trading technology is determined. Reasonable evaluation module: Combines the technology transaction prospects and transaction risk value to comprehensively analyze and judge the rationality of technology transactions.

2. A technology trading platform management system based on big data according to claim 1, characterized in that: The specific method of the data preprocessing is: For patent data, patent data extraction technical features are pulled regularly. For market transaction data, market transaction data extraction technical features are obtained in real time, read and mapped to a unified data model to obtain industry data. For internal enterprise data, authorized access is performed through the enterprise API gateway, and data is extracted regularly. For non-digital documents, they are identified and structured into the warehouse to obtain comprehensive internal enterprise data.

3. A technology transaction platform management system based on big data according to claim 1, characterized in that: The method for obtaining the technology transaction prospects is: Considering the differences between the target technology and comparable cases, the prospect of the target technology is calculated based on the adjusted comparable case prices, and the market prospect SC is obtained comprehensively; By formula Calculate the technical outlook JS, where R i represents the expected income in year i, r represents the discount rate, and n represents the earnings forecast period; The technology transaction prospects are obtained by weighted calculation based on the obtained market prospects and technology prospects.

4. A technology trading platform management system based on big data according to claim 1, characterized in that: The method for establishing a dynamic technology prospect evaluation system is: Use the data acquisition module to obtain real-time updates on technology transaction big data, and adjust evaluation indicators and model parameters in a timely manner based on real-time technology transaction big data; Pay attention to market feedback on technology, and adjust the evaluation results accordingly if the prospects of technology change based on market feedback.

5. A technology transaction platform management system based on big data according to claim 1, characterized in that: The specific method of the prospect trend classification is as follows: Extract historical technology outlook data from the dynamic technology outlook assessment system, select monthly outlook data for the past N years, calculate the standard deviation of the monthly outlook data and the deviation from the moving average, and use NLP to analyze the frequency of technology keywords in policy documents to quantify the degree of policy support or restriction. Technologies with a growth rate of ≥10% for six consecutive months and a policy correlation that deviates positively from the industry mean by more than 2σ are marked as trending technologies, where σ represents the standard deviation of the industry policy correlation. Technologies with an annualized prospect decay rate greater than 10% and whose patent citation ranking falls out of the top 30% of the industry are marked as sunset technologies; Techniques with monthly volatility > 15% but no sustained downward trend are labeled as volatile techniques.

6. A technology transaction platform management system based on big data according to claim 1, characterized in that: The method for reasonably predicting the technical potential value is: Construct an LSTM-Prophet hybrid model. The LSTM neural network captures the long-term and short-term dependencies of technology prospects, analyzes and decomposes the impact of exogenous variables such as policy shocks and industry cycles, and dynamically adjusts model weights. Capture the opinions of industry leaders in real time, generate a market sentiment index mapped to [0,1], monitor changes in the technical NFT collateralization rate in DeFi protocols, and predict liquidity tightening risk factors; The pre-processed historical data and real-time data are input into the hybrid model, combined with the market sentiment index and liquidity tightening risk factor to predict the technical potential value.

7. A technology transaction platform management system based on big data according to claim 1, characterized in that: The method for recommending and optimizing transaction time is as follows: Construct the utility function for both buyers and sellers: Seller utility = transaction price - technology holding cost - opportunity cost; Buyer utility = expected technology return - transaction price - risk premium. Calculate the price-time Pareto frontier that maximizes the utility of both parties and output the intelligent bargaining range. Simulate M trading scenarios and calculate the transaction probability and expected returns at different time points: For trending technologies, it is recommended to complete transactions in the early stages of technology diffusion; For volatile technologies, identify the low point in the outlook and initiate a reverse takeover; Preset trigger conditions, for example, price volatility <5% and market sentiment index >70. When real-time data meets the conditions, a contract signing request is automatically pushed to both the buyer and the seller. For OTC bulk transactions, a threshold signature scheme is adopted, which requires the joint signature of three authorized nodes to take effect, to prevent unilateral malicious operations.

8. The technology transaction platform management system based on big data according to claim 1, characterized in that: The method for obtaining the transaction risk value is: Calculate the information entropy of each risk factor based on historical data and dynamically assign initial weights; Construct ideal solutions and negative ideal solutions, and calculate the proximity of the target technology to the optimal / worst risk level; By formula Calculate the transaction risk value FX, where w i It represents the dynamic weight of the i-th risk factor, F i represents the standardized value of the i-th risk factor, λ represents the regulatory policy correction factor, C r It represents the cross-platform risk contagion coefficient.

9. A technology transaction platform management system based on big data according to claim 1, characterized in that: The calculation method for the rationality of the transaction is: Construct a two-dimensional decision matrix: Based on the weighted results of market mechanism comparison and profit prospect comparison, the matrix is divided into three levels: high, medium, and low according to the preset prospect threshold; The stratified results of the aforementioned risk levels are mapped to a normalized coefficient of 0-1; By formula The technical rational value HL is calculated, where α represents the industry adjustment coefficient.

10. A technology transaction platform management system based on big data according to claim 1, characterized in that: The method for judging the rationality of technology transactions is: Based on the comparison between the obtained reasonable technical value and the preset reasonable standard value, a comprehensive analysis is conducted to determine the rationality of the technical transaction and make a decision.

Images