Public resource transaction data processing and real-time monitoring early warning method and system

Abstract

The invention discloses a public resource transaction data processing and real-time monitoring early warning method and system, and relates to the technical field of transaction data processing and monitoring, and the method comprises the steps: receiving public resource transaction data, carrying out the preprocessing of the data, carrying out the feature extraction of the preprocessed data, obtaining a feature vector set, and carrying out the real-time monitoring of the feature vector set; training an adaptive transaction data prediction model by using the feature vector, automatically identifying and optimizing a transaction process, performing risk assessment on a transaction behavior by using the optimized transaction process data, generating an early warning report, performing dynamic data processing according to a risk assessment result, and adjusting a data processing strategy. And an interactive decision support interface is established by using the processed data, and real-time monitoring and intelligent scheduling of transaction resources are carried out through an interactive analysis result. According to the method, the transaction process can be identified and optimized more accurately through extraction of the feature vectors and training of the self-adaptive prediction model, so that the method has remarkable advantages in the aspects of risk assessment and early warning report generation.

Description

Technical Field

[0001] The present invention relates to the technical field of transaction data processing and monitoring, and in particular to a method and system for public resource transaction data processing and real-time monitoring and early warning. Background Art

[0002] In the field of public resource transactions, the efficiency of data processing and the accuracy of monitoring are crucial to ensuring the fairness and transparency of transactions. With the development of information technology, public resource transaction platforms have accumulated a large amount of transaction data, which contains rich information and is of great value for predicting transaction trends and identifying potential risks. In recent years, relevant technologies have made significant progress, especially in the application of big data analysis and machine learning technologies, providing new solutions for the processing and monitoring of transaction data.

[0003] However, the existing public resource transaction data processing and monitoring technologies still have many shortcomings. First, traditional data processing methods often rely on simple statistical analysis and rule engines, which make it difficult to capture complex patterns and potential risks in the data. Second, the existing monitoring systems lack real-time and adaptive capabilities, and can often only respond after risks occur, and cannot achieve advance warning and dynamic adjustment. In addition, current technologies for optimizing transaction processes are mostly based on experience-based judgments and lack data-driven decision support, resulting in limited optimization effects. Summary of the invention

[0004] In view of the above-mentioned existing problems, the present invention provides a method and system for public resource transaction data processing and real-time monitoring and early warning, which is used to solve the problems in the prior art that it is difficult to capture complex patterns and potential risks in the data, cannot achieve advance warning and dynamic adjustment, and lacks data-driven decision support.

[0005] In order to solve the above technical problems, a method for public resource transaction data processing and real-time monitoring and early warning is proposed, including:

[0006] Receive public resource transaction data, pre-process the data, extract features from the pre-processed data, and obtain a feature vector set; use the feature vectors to train an adaptive transaction data prediction model, and automatically identify and optimize the transaction process, use the optimized transaction process data to conduct risk assessment on transaction behaviors, and generate early warning reports; perform dynamic data processing based on risk assessment results, adjust data processing strategies, use the processed data to establish an interactive decision support interface, and conduct real-time monitoring and intelligent scheduling of transaction resources through interactive analysis results.

[0007] As a preferred solution of the method for processing public resource transaction data and real-time monitoring and early warning of the present invention, wherein: the receiving of public resource transaction data includes receiving transaction record data, subject information data, project information data, legal and regulatory data, market information data and financial data, and pre-processing the collected data;

[0008] The transaction record data includes transaction time, transaction amount, information of both parties to the transaction and transaction project type; the subject information data includes information and credit records of enterprises, individuals and government agencies; the project information data includes the overview, scale, geographical location, construction period and investment amount of the project; the legal and regulatory data includes laws and regulations, policy documents and industry standards; the market information data includes market supply and demand, price fluctuations and industry trends; the financial data includes the financial statements, capital flows and profitability of both parties to the transaction;

[0009] The preprocessing includes data cleaning, data integration, data conversion and data standardization; the data cleaning includes removing invalid, erroneous and duplicated data, filling missing values ​​and unifying data formats; the data conversion includes converting unstructured data into structured data.

[0010] As a preferred solution of the method for processing public resource transaction data and real-time monitoring and early warning of the present invention, wherein: the obtaining of the feature vector set includes performing text feature extraction, numerical feature extraction, time series feature extraction and image feature extraction on the pre-processed data to obtain the feature vector set;

[0011] The text feature extraction includes segmenting the text data into words or phrases, removing common words that do not contain useful information, removing the ending changes of the words, counting the frequency of each word in the text, and calculating the importance of the word by combining the word frequency and the inverse document frequency;

[0012] The numerical feature extraction includes calculating the statistics of the numerical features, i.e., calculating the maximum, minimum, mean and standard deviation of the numerical features, and combining the statistics into a feature vector; the time series feature extraction includes calculating the difference between adjacent time points in the time series, and at each time point, taking the data within a specific time range as a feature vector; the image feature extraction includes adjusting the image size, normalizing the pixel values, extracting features using a pre-trained CNN model, and obtaining a feature vector from the fully connected layer of the CNN.

[0013] As a preferred solution of the public resource transaction data processing and real-time monitoring and early warning method described in the present invention, wherein: the optimization of the transaction process includes using the obtained feature vector set to train a prediction model based on a hybrid neural network, automatically identifying bottlenecks and inefficient links in the transaction process, and optimizing the transaction process using the transaction data prediction results output by the prediction model;

[0014] The training of the prediction model formula based on the hybrid neural network includes:

[0015] H cnn =σ(W cnn *F+b cnn )

[0016] H lstm =LSTM(H cnn )

[0017] Y=W out H lstm +b out

[0018] Among them, H cnn is a convolutional neural network, H lstm is a long short-term memory network, F is a feature vector set, σ is an activation function, W cnn and W out is the weight, b cnn and b out is the bias, Y is the objective function;

[0019] The optimized transaction process formula is:

[0020] Q(s,a)←Q(s,a)+α[R(s,a)+γmax a′ Q(s′, a′)-Q(s, a)]

[0021] Among them, R(s, a) is the reward formula, α is the learning rate, Q(s, a) is the value function of taking action a in state s, γ is the discount factor, and max a′ Q(s′, a′) is the maximum value obtained by taking the best action a′ in the next state s′, where s′ and s are states, and a′ and a are actions taken.

[0022] As a preferred solution of the method for processing public resource transaction data and real-time monitoring and early warning of the present invention, the generating of early warning report includes: using the optimized transaction process data to conduct risk assessment, setting risk thresholds according to the risk assessment results, conducting risk warning, and generating early warning report;

[0023] The risk assessment formula is expressed as:

[0024] RS=W1·VI+W2·CRI+W3·MRI

[0025] Among them, RS is the risk measure, W1, w2 and w3 are risk weights, VI is the asset price volatility index, CRI is the credit risk index, and MRI is the market risk index;

[0026] The risk warning includes setting a risk measurement threshold RS based on historical data th , when the risk metric is greater than or equal to RS th When abnormal transaction behavior is detected and the risk level exceeds the normal level, it is necessary to issue an early warning for the transaction risk, record the early warning information, and form an early warning report.

[0027] As a preferred solution of the method for processing public resource transaction data and real-time monitoring and early warning of the present invention, wherein: the adjustment of the data processing strategy includes, according to the risk assessment result, when abnormal transaction behavior and risk level exceeding the threshold are detected, triggering the dynamic data processing mechanism, and using time series analysis combined with sliding window technology to update the transaction data characteristics in real time and adjust the data processing strategy;

[0028] The sliding window technique formula is:

[0029] D′ t =f(D t , ΔD t-1 )

[0030] Where f is a nonlinear function, ΔD t-1 is the data change from time window t-1 to t, D t is the transaction data at time point t, D′ t It is a dynamic data processing model;

[0031] The adjustment of the data processing strategy includes adding market sentiment indicators, adjusting model parameters, increasing sampling frequency, and re-evaluating risks after adjustments when abnormal trading behavior is detected and risk levels exceed thresholds until the risk measurement is at a normal level.

[0032] As a preferred solution of the method for processing public resource transaction data and real-time monitoring and early warning of the present invention, the real-time monitoring and intelligent scheduling include designing a user-friendly interface, displaying the processed data in the form of charts, and performing data interaction, analyzing the interaction process and providing real-time feedback, and performing real-time monitoring and intelligent scheduling of transaction resources through the interactive analysis results;

[0033] The data interaction includes allowing users to interact with data by clicking and dragging; the analysis and interaction process includes users simulating different trading scenarios, viewing risk changes, and testing through the interface, observing result changes, and providing real-time feedback on the results; the intelligent scheduling includes automatically adjusting the fund allocation strategy according to the risk status, automatically implementing trading restrictions and circuit breakers when the risk exceeds the threshold, and automatically executing scheduling instructions.

[0034] Another object of the present invention is to provide a public resource transaction data processing and real-time monitoring and early warning system, which improves the speed and accuracy of public resource transaction data processing and enhances the real-time and adaptive capabilities of the monitoring system; the system of the present invention automatically identifies and optimizes bottlenecks and inefficient links in the transaction process, realizes real-time risk assessment, promptly discovers anomalies and generates early warning reports; based on the risk assessment results, the system dynamically adjusts the data processing strategy to ensure that it matches the market environment and transaction risk conditions.

[0035] As a preferred solution of the public resource transaction data processing and real-time monitoring and early warning system described in the present invention, it is characterized by including a data receiving module, a data preprocessing and feature extraction module, a transaction data prediction module, a risk assessment module, an intelligent early warning module and an intelligent scheduling module.

[0036] The data receiving module is used to receive and integrate public resource transaction data, that is, to receive transaction records, subject information, project information, laws and regulations, market information and financial data.

[0037] The data preprocessing and feature extraction module is used to preprocess the received data, extract features from the preprocessed data, and generate a feature vector set.

[0038] The transaction data prediction module is used to use the feature vector set to train the prediction model based on the hybrid neural network, automatically identify the bottlenecks and inefficient links in the transaction process, and optimize the transaction process according to the transaction data prediction results output by the prediction model.

[0039] The risk assessment module is used to perform risk assessment using the optimized transaction process data, calculate risk metrics, and determine risk levels based on risk weights.

[0040] The intelligent early warning module is used to set a risk threshold and generate an early warning report to provide risk warning information when abnormal trading behavior is detected or the risk level exceeds the threshold.

[0041] The intelligent scheduling module is used to adjust the data processing strategy according to the risk assessment results, establish an interactive decision support interface, and perform intelligent scheduling according to the interactive analysis results.

[0042] A computer device includes a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, the steps of a method described in a method for public resource transaction data processing and real-time monitoring and early warning are implemented.

[0043] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of a method described in a method for public resource transaction data processing and real-time monitoring and early warning are implemented.

[0044] Beneficial effects of the present invention: The present invention cleans, converts and standardizes transaction data, eliminates invalid and erroneous data, fills in missing values, unifies formats, and converts unstructured data into structured data; and extracts features, including extraction of text, numerical values, time series and image features, to obtain a feature vector set, and text feature extraction calculates word importance through word frequency and inverse document frequency; and uses feature vectors to train a hybrid neural network prediction model to automatically identify and optimize bottlenecks and inefficient links in the transaction process, and adjust the process through prediction results; uses optimized process data to conduct risk assessment, set thresholds, and implement risk warnings; and when abnormal transaction behavior and risks exceeding thresholds are detected, a dynamic data processing mechanism is triggered, and time series analysis and sliding window technology are combined to update features and adjust strategies in real time; data is displayed through a user-friendly interface, interactive analysis is supported, and the intelligent scheduling module automatically adjusts fund allocation according to risk conditions, implements transaction restrictions and fuse mechanisms, and realizes real-time monitoring and intelligent scheduling of transaction resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work, among which:

[0046] Figure 1 An overall flow chart of a method for public resource transaction data processing and real-time monitoring and early warning provided by an embodiment of the present invention.

[0047] Figure 2 A system solution flow chart of a public resource transaction data processing and real-time monitoring and early warning system provided for one embodiment of the present invention. DETAILED DESCRIPTION

[0048] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0049] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0050] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it an embodiment that is mutually exclusive with other embodiments, either individually or selectively.

[0051] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0052] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0053] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0054] Example 1, reference Figure 1 , which is the first embodiment of the present invention, provides a method for processing public resource transaction data and real-time monitoring and early warning, including:

[0055] S1: Receive public resource transaction data, preprocess the data, extract features from the preprocessed data, and obtain a feature vector set.

[0056] The receiving of public resource transaction data includes receiving transaction record data, subject information data, project information data, legal and regulatory data, market information data and financial data, and pre-processing the collected data;

[0057] The transaction record data includes transaction time, transaction amount, information of both parties to the transaction and transaction project type; the subject information data includes basic information and credit records of enterprises, individuals and government agencies; the project information data includes the overview, scale, geographical location, construction period and investment amount of the project; the legal and regulatory data includes laws and regulations, policy documents and industry standards; the market information data includes market supply and demand, price fluctuations and industry trends; the financial data includes the financial statements, capital flows and profitability of both parties to the transaction;

[0058] The preprocessing includes data cleaning, data integration, data conversion and data standardization; the data cleaning includes removing invalid, erroneous and duplicated data, filling missing values ​​and unifying data formats; the data conversion includes converting unstructured data into structured data.

[0059] It should be noted that the obtaining of the feature vector set includes performing text feature extraction, numerical feature extraction, time series feature extraction and image feature extraction on the preprocessed data to obtain the feature vector set;

[0060] The text feature extraction includes segmenting the text data into words or phrases, removing common words that do not contain useful information, restoring the words to their basic form, removing word ending changes, counting the frequency of each word in the text, and calculating the importance of the word by combining the word frequency and the inverse document frequency;

[0061] The formula for calculating word frequency is:

[0062]

[0063] Among them, f t , d is the number of times word t appears in the document, ∑ t′∈d f t′，d is the sum of the number of occurrences of all words in the document, TF(t, d) is the frequency of word t appearing in the document, d is the document, and t is the word;

[0064] The inverse document frequency calculation formula is:

[0065]

[0066] Where N is the total number of documents, n t is the number of documents containing word t, IDF(t) is the inverse document frequency, and t is the word;

[0067] The formula for calculating word importance is:

[0068] A(t, d) = TF(t, d) × IDF(t)

[0069] Where A(t, d) is the importance of word t, TF(t, d) is the frequency of word t in the document, IDF(t) is the inverse document frequency, d is the document, and t is the word;

[0070] The numerical feature extraction includes calculating the statistics of the numerical features, i.e., calculating the maximum value, minimum value, mean value and standard deviation of the numerical features, and combining the statistics into a feature vector; the time series feature extraction includes calculating the difference between adjacent time points in the time series, and at each time point, taking the data within a specific time range as a feature vector; the image feature extraction includes adjusting the image size, normalizing the pixel values, extracting features using a pre-trained CNN model, and obtaining a feature vector from the fully connected layer of the CNN;

[0071] The convolution formula is:

[0072] f(x)=(k*g)(x)+b

[0073] Among them, k is the convolution kernel, x is the eigenvalue, f(x) is the eigenvector, g is the input image, b is the bias term, and * is the convolution operation.

[0074] S2: Use feature vectors to train an adaptive transaction data prediction model, automatically identify and optimize transaction processes, use the optimized transaction process data to conduct risk assessment on transaction behaviors, and generate early warning reports.

[0075] Furthermore, the optimization of the transaction process includes using the obtained feature vector set to train a prediction model based on a hybrid neural network to automatically identify bottlenecks and inefficient links in the transaction process, and using the transaction data prediction results output by the prediction model to optimize the transaction process;

[0076] The training of the prediction model formula based on the hybrid neural network includes:

[0077] H cnn =σ(W cnn *F+b cnn )

[0078] H lstm =LSTM(H cnn )

[0079] Y=W out H lstm +b out

[0080] Among them, H cnn is a convolutional neural network, H lstm is a long short-term memory network, F is a feature vector set, σ is an activation function, W cnn and W out is the weight, b cnn and bout is the bias, Y is the objective function;

[0081] The optimized transaction process formula is:

[0082] Q(s,a)←Q(s,a)+α[R(s,a)+ymax a′ Q(s′, a′)-Q(s, a)]

[0083] Among them, R(s, a) is the reward formula, α is the learning rate, Q(s, a) is the value function of taking action a in state s, γ is the discount factor, and max a′ Q(s′, a′) is the maximum value obtained by taking the best action a′ in the next state s′, s′ and s are states, a′ and a are actions taken;

[0084] The reward formula is expressed as:

[0085] R(s,a)=λ·Efficiency(s,a)-(1-λ)·Risk(s,a)

[0086] Among them, R(s, a) is the reward formula, λ is the weight coefficient, Efficiency(s, a) is the efficiency function, that is, the efficiency of taking action a in state s, and Risk(s, a) is the risk function, that is, the risk of taking action a in state s.

[0087] Furthermore, the generating of the early warning report includes using the optimized transaction process data to conduct risk assessment, setting risk thresholds according to the risk assessment results, conducting risk warnings, and generating early warning reports;

[0088] The risk assessment formula is expressed as:

[0089] RS=W1·VI+W2·CRI+W3·MRI

[0090] Among them, RS is the risk measure, W1, w2 and w3 are risk weights, VI is the asset price volatility index, CRI is the credit risk index, and MRI is the market risk index;

[0091] The risk warning includes setting a risk measurement threshold RS based on historical data th , when the risk metric is greater than or equal to RS th When abnormal transaction behavior is detected and the risk level exceeds the normal level, it is necessary to issue an early warning for the transaction risk, record the early warning information, and form an early warning report.

[0092] S3: Perform dynamic data processing based on risk assessment results and adjust data processing strategies. Use the processed data to establish an interactive decision support interface, and conduct real-time monitoring and intelligent scheduling of transaction resources through interactive analysis results.

[0093] Furthermore, the adjustment of the data processing strategy includes, according to the risk assessment results, triggering a dynamic data processing mechanism when abnormal transaction behavior and risk level exceeding a threshold are detected, and using time series analysis combined with sliding window technology to update transaction data features in real time and adjust the data processing strategy;

[0094] The sliding window technique formula is:

[0095] D′ t =f(D t , ΔD t-1 )

[0096] Where f is a nonlinear function, ΔD t-1 is the data change from time window t-1 to t, D t is the transaction data at time point t, D′ t It is a dynamic data processing model;

[0097] The adjustment of the data processing strategy includes adding market sentiment indicators, adjusting model parameters, increasing sampling frequency, and re-evaluating risks after adjustments when abnormal trading behavior is detected and risk levels exceed thresholds until the risk measurement is at a normal level.

[0098] Furthermore, the real-time monitoring and intelligent scheduling include designing a user-friendly interface, displaying the processed data in the form of charts, and performing data interaction, analyzing the interaction process and providing real-time feedback, and performing real-time monitoring and intelligent scheduling of transaction resources through the interactive analysis results;

[0099] The data interaction includes allowing users to interact with data by clicking and dragging; the analysis and interaction process includes users simulating different trading scenarios, viewing risk changes, and testing through the interface, observing result changes, and providing real-time feedback on the results; the intelligent scheduling includes automatically adjusting the fund allocation strategy according to the risk status, automatically implementing trading restrictions and circuit breakers when the risk exceeds the threshold, and automatically executing scheduling instructions.

[0100] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0101] Example 2, reference Figure 2 , which is the second embodiment of the present invention, provides a public resource transaction data processing and real-time monitoring and early warning system, including a data receiving module 100, a data preprocessing and feature extraction module 200, a transaction data prediction module 300, a risk assessment module 400, an intelligent early warning module 500 and an intelligent scheduling module 600.

[0102] The data receiving module 100 is used to receive and integrate public resource transaction data, that is, to receive transaction records, subject information, project information, laws and regulations, market information and financial data.

[0103] The data preprocessing and feature extraction module 200 is used to preprocess the received data, extract features from the preprocessed data, and generate a feature vector set.

[0104] The transaction data prediction module 300 is used to train a prediction model based on a hybrid neural network using a feature vector set, automatically identify bottlenecks and inefficient links in the transaction process, and optimize the transaction process based on the transaction data prediction results output by the prediction model.

[0105] The risk assessment module 400 is used to perform risk assessment using the optimized transaction process data, calculate risk metrics, and determine risk levels according to risk weights.

[0106] The intelligent early warning module 500 is used to set a risk threshold and generate an early warning report to provide risk early warning information when abnormal transaction behavior is detected or the risk level exceeds the threshold.

[0107] The intelligent scheduling module 600 is used to adjust the data processing strategy according to the risk assessment results, establish an interactive decision support interface, and perform intelligent scheduling according to the interactive analysis results.

[0108] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0109] Embodiment 3, the third embodiment of the present invention, is different from the first two embodiments in that:

[0110] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0111] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0112] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0113] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

Claims

1. A method for processing public resource transaction data and real-time monitoring and early warning, characterized in that: include, Receive public resource transaction data, preprocess the data, extract features from the preprocessed data, and obtain a feature vector set; Use feature vectors to train adaptive transaction data prediction models, automatically identify and optimize transaction processes, use optimized transaction process data to conduct risk assessments on transaction behaviors, and generate early warning reports; Dynamic data processing is performed based on risk assessment results, and data processing strategies are adjusted. The processed data is used to establish an interactive decision support interface, and real-time monitoring and intelligent scheduling of transaction resources are carried out through interactive analysis results.

2. A method for processing public resource transaction data and real-time monitoring and early warning according to claim 1, characterized in that: The receiving of public resource transaction data includes receiving transaction record data, subject information data, project information data, legal and regulatory data, market information data and financial data, and pre-processing the collected data; The transaction record data includes transaction time, transaction amount, information of both parties to the transaction and transaction project type; the subject information data includes information and credit records of enterprises, individuals and government agencies; the project information data includes the overview, scale, geographical location, construction period and investment amount of the project; the legal and regulatory data includes laws and regulations, policy documents and industry standards; the market information data includes market supply and demand, price fluctuations and industry trends; the financial data includes the financial statements, capital flows and profitability of both parties to the transaction; The preprocessing includes data cleaning, data integration, data conversion and data standardization; the data cleaning includes removing invalid, erroneous and duplicated data, filling missing values ​​and unifying data formats; the data conversion includes converting unstructured data into structured data.

3. A method for processing public resource transaction data and real-time monitoring and early warning according to claim 2, characterized in that: The obtaining of the feature vector set comprises performing text feature extraction, numerical feature extraction, time series feature extraction and image feature extraction on the preprocessed data to obtain the feature vector set; The text feature extraction includes segmenting the text data into words or phrases, removing common words that do not contain useful information, removing the ending changes of the words, counting the frequency of each word in the text, and calculating the importance of the word by combining the word frequency and the inverse document frequency; The numerical feature extraction includes calculating the statistics of the numerical features, i.e., calculating the maximum, minimum, mean and standard deviation of the numerical features, and combining the statistics into a feature vector; the time series feature extraction includes calculating the difference between adjacent time points in the time series, and at each time point, taking the data within a specific time range as a feature vector; the image feature extraction includes adjusting the image size, normalizing the pixel values, extracting features using a pre-trained CNN model, and obtaining a feature vector from the fully connected layer of the CNN.

4. A method for processing public resource transaction data and real-time monitoring and early warning as claimed in claim 3, characterized in that: The optimization of the transaction process includes using the obtained feature vector set to train a prediction model based on a hybrid neural network to automatically identify bottlenecks and inefficient links in the transaction process, and using the transaction data prediction results output by the prediction model to optimize the transaction process; The training of the prediction model formula based on the hybrid neural network includes: H cnn =σ(W cnn *F+b cnn ) H lstm =LSTM(H cnn ) Y=W out H lstm +b out Among them, H cnn is a convolutional neural network, H lstm is a long short-term memory network, F is a feature vector set, σ is an activation function, W cnn and W out is the weight, b cnn and b out is the bias, Y is the objective function; The optimized transaction process formula is: Q(s,a)←Q(s,a)+α[R(s,a)+γmax a' Q(s',a')-Q(s,a)] Among them, R(s,a) is the reward formula, α is the learning rate, Q(s,a) is the value function of taking action a in state s, γ is the discount factor, and max a' Q(s',a') is the maximum value obtained by taking the best action a' in the next state s', s' and s are states, and a' and a are actions taken.

5. A method for processing public resource transaction data and real-time monitoring and early warning as claimed in claim 4, characterized in that: Generating the early warning report includes using the optimized transaction process data to conduct risk assessment, setting risk thresholds according to the risk assessment results, conducting risk warnings, and generating early warning reports; The risk assessment formula is expressed as: RS=w1·VI+w2·CRI+w3·MRI Among them, RS is the risk measure, w1, w2 and w3 are risk weights, VI is the asset price volatility index, CRI is the credit risk index, and MRI is the market risk index; The risk warning includes setting a risk measurement threshold RS based on historical data th , when the risk metric is greater than or equal to RS th When abnormal transaction behavior is detected and the risk level exceeds the normal level, it is necessary to issue an early warning for the transaction risk, record the early warning information, and form an early warning report.

6. A method for processing public resource transaction data and real-time monitoring and early warning as claimed in claim 5, characterized in that: The adjustment of the data processing strategy includes, according to the risk assessment results, triggering a dynamic data processing mechanism when abnormal transaction behavior and risk level exceeding a threshold are detected, and using time series analysis combined with sliding window technology to update transaction data features in real time and adjust the data processing strategy; The sliding window technique formula is: D' t =f(D t ,ΔD t-1 ) Where f is a nonlinear function, ΔD t-1 is the data change from time window t-1 to t, D t is the transaction data at time point t, D' t It is a dynamic data processing model; The adjustment of the data processing strategy includes adding market sentiment indicators, adjusting model parameters, increasing sampling frequency, and re-evaluating risks after adjustments when abnormal trading behavior is detected and risk levels exceed thresholds until the risk measurement is at a normal level.

7. A method for processing public resource transaction data and real-time monitoring and early warning according to claim 6, characterized in that: The real-time monitoring and intelligent scheduling include designing a user-friendly interface, displaying the processed data in the form of charts, performing data interaction, analyzing the interaction process and providing real-time feedback, and performing real-time monitoring and intelligent scheduling of transaction resources through the interactive analysis results; The data interaction includes allowing the user to interact with the data by clicking and dragging; The analysis and interaction process includes users simulating different trading scenarios, checking risk changes, testing through the interface, observing result changes, and providing real-time feedback on the results; the intelligent scheduling includes automatically adjusting the fund allocation strategy according to the risk situation, automatically implementing trading restrictions and circuit breakers when the risk exceeds the threshold, and automatically executing scheduling instructions.

8. A system using a method for processing public resource transaction data and real-time monitoring and early warning as claimed in any one of claims 1 to 7, characterized in that: It includes data receiving module, data preprocessing and feature extraction module, transaction data prediction module, risk assessment module, intelligent early warning module and intelligent scheduling module; The data receiving module is used to receive and integrate public resource transaction data, that is, to receive transaction records, subject information, project information, laws and regulations, market information and financial data; The data preprocessing and feature extraction module is used to preprocess the received data, extract features from the preprocessed data, and generate a feature vector set; The transaction data prediction module is used to train a prediction model based on a hybrid neural network using a feature vector set, automatically identify bottlenecks and inefficient links in the transaction process, and optimize the transaction process based on the transaction data prediction results output by the prediction model; The risk assessment module is used to perform risk assessment using the optimized transaction process data, calculate risk metrics, and determine risk levels based on risk weights; The intelligent early warning module is used to set a risk threshold and generate an early warning report to provide risk warning information when abnormal trading behavior is detected or the risk level exceeds the threshold; The intelligent scheduling module is used to adjust the data processing strategy according to the risk assessment results, establish an interactive decision support interface, and perform intelligent scheduling according to the interactive analysis results.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of a method for processing public resource transaction data and real-time monitoring and early warning according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a method for processing public resource transaction data and real-time monitoring and early warning as described in any one of claims 1 to 7 are implemented.

Images