CN108364124B - International capacity cooperative risk assessment and decision service system based on big data - Google Patents

International capacity cooperative risk assessment and decision service system based on big data Download PDF

Info

Publication number
CN108364124B
CN108364124B CN201810077759.8A CN201810077759A CN108364124B CN 108364124 B CN108364124 B CN 108364124B CN 201810077759 A CN201810077759 A CN 201810077759A CN 108364124 B CN108364124 B CN 108364124B
Authority
CN
China
Prior art keywords
data
information
analysis
module
image
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
Application number
CN201810077759.8A
Other languages
Chinese (zh)
Other versions
CN108364124A (en
Inventor
薛文芳
韩艳超
张德馨
郑浩楠
薛金鸽
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tianjin Zhongke Intelligent Identification Co ltd
Original Assignee
Tianjin Zhongke Intelligent Identification Industry Technology Research Institute Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Tianjin Zhongke Intelligent Identification Industry Technology Research Institute Co ltd filed Critical Tianjin Zhongke Intelligent Identification Industry Technology Research Institute Co ltd
Priority to CN201810077759.8A priority Critical patent/CN108364124B/en
Publication of CN108364124A publication Critical patent/CN108364124A/en
Application granted granted Critical
Publication of CN108364124B publication Critical patent/CN108364124B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q10/00Administration; Management
    • G06Q10/06Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063Operations research, analysis or management
    • G06Q10/0637Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q10/00Administration; Management
    • G06Q10/06Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063Operations research, analysis or management
    • G06Q10/0635Risk analysis of enterprise or organisation activities
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q40/00Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/06Asset management; Financial planning or analysis

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Development Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Educational Administration (AREA)
  • Game Theory and Decision Science (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Technology Law (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention discloses an international capacity cooperative risk assessment and decision service system based on big data, which comprises a distributed structural/non-structural database; the data access layer receives data acquired by the front end through a standard communication interface and automatically inputs the data into a distributed structural/non-structural database according to a standard format; the information acquisition and preprocessing layer is used for acquiring data, preprocessing the acquired data, mining and refining effective information, extracting information keywords and constructing an index; the analysis layer is used for identifying valuable information content from the real-time information stream, clustering information aiming at national risk, industry analysis and international public opinion analysis respectively and displaying the information in an information table form; and the application layer provides a query retrieval function for a query user, and outputs the information of the query in a multidimensional visualization way to generate a corresponding report. The invention can strengthen the risk prevention and control capability of enterprises in China in the international capacity cooperation process by using an information technology means.

Description

International capacity cooperative risk assessment and decision service system based on big data
Technical Field
The invention relates to the technical field of overseas investment services, in particular to an international capacity cooperative risk assessment and decision service system based on big data.
Background
The method has the advantages that the method greatly promotes enterprises in China to go out to participate in international capacity cooperation, obtains strategic resources such as capital, technology and market in a wider space, promotes the upgrading of industrial structures, makes an effort to advance to the high-value-added link of an industrial chain, and is a necessary choice for economic development in new period of China. The implementation of the propulsion of international capacity cooperation is a long-term, complex and arduous system engineering. In the process, overseas investment enterprises in China are directly faced with multi-dimensional risk factors such as politics, economy, industry, technology, finance, tax, policy, resources, environmental protection, ecology, biological disasters and natural disasters of target countries.
Overseas investment risk derivation ways are various, various information is complicated, and complexity and difficulty of risk management and control are increased in geometric multiples. Under such a situation, the bottleneck of quantitative evaluation of overseas investment risk by using the traditional method is increasingly highlighted.
The big data is regarded as a powerful tool for decision support as an emerging data processing technology and cognitive thinking, and has become a leading research edge and strategic planning focus of all countries in the world, with high attention paid to the global scientific and technological field, the industry and government departments in recent years. Therefore, various data resources are urgently needed to be integrated, a national-level overseas investment risk intelligent detection, identification, prediction and early warning platform is created by using technical means such as big data, cloud computing and intelligent identification, overseas investment risks such as politics, economy, industry, technology, finance, laws, labor and exchange rates of a target country are quickly, accurately and comprehensively sensed, and the risk prevention and control capability of enterprises in China participating in the international capacity cooperation process is strengthened by using latest information technical means.
Disclosure of Invention
The invention aims to provide an international capacity cooperative risk assessment and decision service system based on big data so as to realize the purpose of strengthening the risk prevention and control capacity of enterprises in China in the process of participating in the international capacity cooperation by using an information technology means.
The technical scheme adopted for realizing the purpose of the invention is as follows:
the big data-based international capacity cooperative risk assessment and decision-making service system is characterized by comprising:
the distributed structural/non-structural database is used for distributed storage of structured data, semi-structured data and non-structured data, and batch and stream processing of PB-level multi-source heterogeneous big data is realized;
the data access layer is used for receiving the data acquired by the front-end data acquisition module through various standard communication interfaces and automatically inputting the acquired data into the distributed structural/non-structural database according to a standard format;
the information acquisition and preprocessing layer is used for acquiring preset data, preprocessing the acquired data, performing format unification and semantic understanding on the data, mining and extracting effective information by using a data mining technology, extracting information keywords and constructing an index;
the preset data sources comprise satellite remote sensing data, internet open source information, intelligence library service data and research data of energy, environment, policy, law and economy;
the analysis layer is used for identifying valuable information content from the real-time information flow, storing the valuable information content in a text form, further processing the text, clustering the information aiming at national risk, industry analysis and international public opinion analysis respectively, and displaying the information in an information table form to provide reliable information for users;
and the application layer is used for providing a query retrieval function for a query user, performing multidimensional visual output on the retrieved and queried information and generating a corresponding report.
In the aspect of collecting open source information of the Internet, a focusing crawler is adopted to automatically classify, identify and collect information pages on the Internet; the method comprises the steps that through a webpage distinguishing module, an information page in a target website is automatically identified according to a manually preset topic word bank, and information which is irrelevant to text content and is mixed around the text content of the webpage and needs to be filtered through a webpage denoising module, wherein the information is acquired through a crawler and comprises advertisement information, navigation information, copyright information and header and footer information; in the crawling process of the web crawler, data duplication elimination processing is carried out through a webpage duplication elimination module;
in the aspect of satellite remote sensing information acquisition, correction recovery, enhancement transformation, image mosaic, feature extraction and image classification operations are carried out on a satellite remote sensing image, and noise and distortion introduced into the image are eliminated; enhancement transformation, i.e. highlighting predetermined features of the data, including color enhancement, contrast enhancement, edge enhancement, density segmentation, ratio operations, deblurring; image mosaic, namely, after one or a plurality of images are subjected to geometric mosaic, tone adjustment and overlap removal processing, the images are mosaic together to generate a complete image; and (4) feature extraction, namely extracting useful remote sensing information from the enhanced image, wherein the useful remote sensing information comprises automatic identification and classification by adopting statistical analysis, cluster analysis and spectrum analysis technologies.
The analysis layer processes data by adopting a multi-source heterogeneous data fusion technology based on cognitive computation and a large graph structure modeling and correlation analysis method:
the multisource heterogeneous data fusion technology based on cognitive computation comprises the following steps:
performing cross-modal multi-source data fusion based on deep learning, realizing feature extraction, concept fusion and combined semantic analysis of cross-modal data, integrating text information and dynamic network structure features aiming at large-scale, multi-source and heterogeneous stream data information, and realizing on-line tracking and evaluation facing to events, topics and groups;
simulating a human brain knowledge acquisition, storage and activation mode based on knowledge representation of cognitive computation to realize concept hierarchy construction, inference rules and high-level cognitive structure representation;
the large graph structure modeling and correlation analysis method comprises the steps of large graph structure representation and modeling, large graph calculation and large graph correlation analysis;
in the aspect of structural representation and modeling of the large graph, according to a distributed large graph representation strategy based on vertex cutting, the structural representation and modeling of the large graph are carried out by adopting a strategy of jointly minimizing the number of edges and the number of vertices of a load node;
in the calculation direction of the large graph, matrix and vector operation is converted into information iterative interaction between adjacent nodes so as to realize integration of various graph algorithms, including PageRank, eigenvalue solution and Unicom subgraph statistics; for each graph algorithm, selecting an optimal calculation strategy according to a calculation target, wherein the optimal calculation strategy is selected by carrying out variational reasoning through a random natural gradient rise algorithm based on random variational;
in the aspect of correlation analysis of a large graph, the positions of nodes in the graph and the dynamic change factors of the nodes along with time are considered, time-varying transfer matrixes of the nodes, the subgraphs and the edges are constructed, and direct correlation and indirect correlation of different nodes, subgraphs and edges are calculated according to transfer entropy correlation monitoring and analysis technology in a time sequence mode aiming at different types of graph structures.
The application layer comprises a query retrieval module, an information multi-dimensional visualization module, a primary report generation module and a data security guarantee module;
the query retrieval module is used for providing a plurality of quick query retrieval modes including special retrieval, title retrieval, fuzzy retrieval, association retrieval and character string retrieval according to a data query request input by a user; the retrieval results support sorting by release time, sorting by category, sorting by similarity, and sorting by repetition.
The information multidimensional visualization module is used for presenting the data information in a form of visualization of a graphic image, and the visualization technology used by the information multidimensional visualization module comprises the following steps:
1) spatial three-dimensional graphics: mapping the combination of different graphic elements into different data dimension interpretations by using transformation mapping, corresponding a visual space structure with data information, and presenting the distribution of data, the similarity between data and the relation between data by the density and the color distribution of a graph;
2) color map: the data volume is divided into a color image and a gray image, each color of the color image corresponds to different attribute dimensions, and the gray image marks the size of the attribute value of the data volume by utilizing the depth of the color;
3) luminance graph: for a specific area, the observation of the viewpoint by human eyes is assisted by different brightness;
4) the mathematical method comprises the following steps: analyzing the data relation by using a statistical method in mathematics to obtain the general distribution information of the data, and then analyzing the detailed data by combining other visualization methods; or mapping the relationship in the data by using a statistical method in mathematics to form a graphic image relationship;
the primary report automatic generation module is used for automatically completing the collection of original data, the processing calculation of the original data, the data extraction and recording, the table editing and the curve drawing, and editing and generating a primary report;
the data security guarantee module is used for guaranteeing the security of data, communication data streams are communicated by using an SSL3.0 security socket layer and transmitted by adopting an https encryption protocol, communication between a server and a client needs to be mutually authenticated, the communication security during remote user operation is guaranteed, and the legality of communication data between functional modules of an application layer, the confidentiality of the data, the non-repudiation of the data and the integrity of the data are guaranteed; in the aspect of system safety management, the operation state of a functional module is detected in real time, double-computer hot backup is provided for important modules, antivirus, Trojan-resistant and firewall software is installed, an intrusion detection system is additionally installed, a virus library and a Trojan library are updated regularly, system patches are updated timely, and the system is prevented from being attacked and infected by viruses and Trojan; the UPS is used for ensuring stable power supply.
The state risk analysis is based on observation of satellite remote sensing to the elements of the geoenvironment, remote sensing data processing, business data analysis and comprehensive visual expression of multi-source information are taken as technical routes by means of big data cloud computing technology, a state risk dynamic analysis mathematical model is constructed from multiple dimensions including politics, economy, industry, resources and environment, and comprehensive study, judgment and quantitative analysis are carried out on investment risk of a target state;
the industry analysis is to extract valuable information from the obtained internet open source data, intellectual library service data and production enterprise data through mining analysis technologies including clustering, association and regression to form information including development level, industry life cycle, industry development situation, capacity distribution map, industry policy, market capacity and market entry and exit barriers at home and abroad;
the international public opinion analysis takes hot spot emergencies including natural disasters, accident disasters, public health events and social security events occurring in target countries as research objects, comprehensively collects all-media big data including internet, plane media, television stations, broadcasting stations and social media, and applies big data analysis and processing technology to monitor, analyze, evaluate and warn information including the incoming and outgoing arteries, development situations, public opinion trends, possible reaching ranges and influence degrees and key character social relationship maps of the hot spot emergencies.
The method provided by the invention realizes collection, fusion and deep mining of overseas investment risk information data by using technical means such as big data, cloud computing, intelligent identification and the like, comprehensively senses political, economic, industrial, technical, policy, resource, environment, biological and ecological information of overseas investment countries, collects, cleans, stores, unifies formats and semantically understands data from different sources, and mines, refines and analyzes effective information by taking space-time-object-content events as a correlation model; powerful data acquisition, multilingual multimedia data analysis and primary report automatic generation services are provided for developing national risk research, international public opinion research and industry analysis research, the overseas investment risk analysis mode is changed from a manual experience type to a computer-assisted intelligence type, and three types of information services of national risk analysis, industry risk analysis and international public opinion analysis can be provided for users.
Drawings
FIG. 1 is a schematic diagram of an international capacity collaborative risk assessment and decision-making service system for big data.
Detailed Description
The invention is described in further detail below with reference to the figures and specific examples. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, the big data based international capacity cooperative risk assessment and decision-making service system and the big data based international capacity cooperative risk assessment and decision-making service system are characterized by comprising:
the distributed structural/non-structural database is used for distributed storage of structured data, semi-structured data and non-structured data, and batch and stream processing of PB-level multi-source heterogeneous big data is realized;
the data access layer is used for receiving the data acquired by the front-end data acquisition module through various standard communication interfaces and automatically inputting the acquired data into the distributed structural/non-structural database according to a standard format;
the information acquisition and preprocessing layer is used for acquiring preset data, preprocessing the acquired data, performing format unification and semantic understanding on the data, mining and extracting effective information by using a data mining technology, extracting information keywords and constructing an index;
the preset data sources comprise satellite remote sensing data, internet open source information, intelligence library service data and research data of energy, environment, policy, law and economy;
the analysis layer is used for identifying valuable information content from the real-time information flow, storing the valuable information content in a text form, further processing the text, clustering the information aiming at national risk, industry analysis and international public opinion analysis respectively, and displaying the information in an information table form to provide reliable information for users;
and the application layer is used for providing a query retrieval function for a query user, performing multidimensional visual output on the retrieved and queried information and generating a corresponding report.
According to the invention, a big data cloud storage platform is built based on Hadoop, an application program is operated on a computer cluster, a parallel distributed system with high reliability and good expansibility is built, and distributed storage of structured data, semi-structured data and unstructured data is supported. After data are collected, cleaned and preprocessed, the Hadoop interaction module judges the size and format of a data file, the data file is combined and uploaded to the HDFS, and batch and stream processing of PB-level multi-source heterogeneous big data can be achieved.
And the data access layer receives the front-end acquisition information through various standard communication interfaces. And automatically inputting the acquired data into a database according to a standard format, when external data needs to be acquired, sending a data receiving request to each data acquisition module by the system, starting a data acquisition task after each data acquisition module receives the request, checking the earliest arriving external data and sending the external data to the system according to a time sequence. In order to ensure efficient and correct transmission of information, a proper receiving and sending mechanism is required to be established, a receiving buffer queue, a receiving task queue and a receiving failure queue are started at a receiving party, and a sending buffer queue, a sending task queue and a sending failure queue are started at a sending party. The effective time of data processing is regulated, the data which is not processed on time during data receiving enters a failure queue, and a breakpoint continuous transmission mechanism is established at the same time according to exception processing to ensure the correct transmission of the files under various conditions.
In the aspect of collecting open source information of the Internet, a focusing crawler is adopted to automatically classify, identify and collect information pages on the Internet; the method comprises the steps that through a webpage distinguishing module, an information page in a target website is automatically identified according to a manually preset topic word bank, and information which is irrelevant to text content and is mixed around the text content of the webpage and needs to be filtered through a webpage denoising module, wherein the information is acquired through a crawler and comprises advertisement information, navigation information, copyright information and header and footer information; in the crawling process of the web crawler, data duplication elimination processing is carried out through the web duplication elimination module, and the problems that repeatedly acquired data occupy a large number of system resources and work efficiency is reduced are solved through the web duplication elimination module, so that the effects of enhancing retrieval efficiency, reducing storage space and enhancing user experience can be achieved;
in the aspect of satellite remote sensing information acquisition, correction recovery, enhancement transformation, image mosaic, feature extraction and image classification operations are carried out on a satellite remote sensing image, and noise and distortion introduced into the image are eliminated; enhancement transformation, i.e. highlighting predetermined features of the data, including color enhancement, contrast enhancement, edge enhancement, density segmentation, ratio operations, deblurring; image mosaic, namely, after one or a plurality of images are subjected to geometric mosaic, tone adjustment and overlap removal processing, the images are mosaic together to generate a complete image; and (4) feature extraction, namely extracting useful remote sensing information from the enhanced image, wherein the useful remote sensing information comprises automatic identification and classification by adopting statistical analysis, cluster analysis and spectrum analysis technologies. A series of operations such as correction recovery, enhancement transformation, image mosaic, feature extraction image classification and the like are carried out on the satellite remote sensing image, and noise and distortion introduced into the image are eliminated, so that the quality of the image can be effectively improved; enhancing the transformation, i.e., highlighting certain features of the data, can improve the visual quality of the image.
When the information acquisition and preprocessing layer processes data, the purpose of constructing the index is to facilitate the system to find needed information in time, and a part of set meeting the conditions is rapidly and selectively read from the whole set.
The analysis layer processes data by adopting a multi-source heterogeneous data fusion technology based on cognitive computation and a large graph structure modeling and correlation analysis method:
the multisource heterogeneous data fusion technology based on cognitive computation comprises the following steps:
performing cross-modal multi-source data fusion based on deep learning, realizing feature extraction, concept fusion and combined semantic analysis of cross-modal data, integrating text information and dynamic network structure features aiming at large-scale, multi-source and heterogeneous stream data information, and realizing on-line tracking and evaluation facing to events, topics and groups;
simulating a human brain knowledge acquisition, storage and activation mode based on knowledge representation of cognitive computation to realize concept hierarchy construction, inference rules and high-level cognitive structure representation;
the large graph structure modeling and correlation analysis method comprises the steps of large graph structure representation and modeling, large graph calculation and large graph correlation analysis;
in the aspect of structural representation and modeling of the large graph, according to a distributed large graph representation strategy based on vertex cutting, the structural representation and modeling of the large graph are carried out by adopting a strategy of jointly minimizing the number of edges and the number of vertices of a load node;
in the calculation direction of the large graph, matrix and vector operation is converted into information iterative interaction between adjacent nodes so as to realize integration of various graph algorithms, including PageRank, eigenvalue solution and Unicom subgraph statistics; for each graph algorithm, selecting an optimal calculation strategy according to a calculation target, wherein the optimal calculation strategy is selected by carrying out variational reasoning through a random natural gradient rise algorithm based on random variational;
in the aspect of correlation analysis of a large graph, the positions of nodes in the graph and the dynamic change factors of the nodes along with time are considered, time-varying transfer matrixes of the nodes, the subgraphs and the edges are constructed, and direct correlation and indirect correlation of different nodes, subgraphs and edges are calculated according to transfer entropy correlation monitoring and analysis technology in a time sequence mode aiming at different types of graph structures.
The application layer comprises a query retrieval module, an information multi-dimensional visualization module, a primary report generation module and a data security guarantee module;
the query retrieval module is used for providing a plurality of quick query retrieval modes including special retrieval, title retrieval, fuzzy retrieval, association retrieval and character string retrieval according to a data query request input by a user; the retrieval results support sorting by release time, sorting by category, sorting by similarity, and sorting by repetition.
The information multidimensional visualization module is used for presenting the data information in a form of visualization of a graphic image, and the visualization technology used by the information multidimensional visualization module comprises the following steps:
1) spatial three-dimensional graphics: mapping the combination of different graphic elements into different data dimension interpretations by using transformation mapping, corresponding a visual space structure with data information, and presenting the distribution of data, the similarity between data and the relation between data by the density and the color distribution of a graph;
2) color map: the data volume is divided into a color image and a gray image, each color of the color image corresponds to different attribute dimensions, and the gray image marks the size of the attribute value of the data volume by utilizing the depth of the color;
3) luminance graph: for a specific area, the observation of the viewpoint by human eyes is assisted by different brightness;
4) the mathematical method comprises the following steps: analyzing the data relation by using a statistical method in mathematics to obtain the general distribution information of the data, and then analyzing the detailed data by combining other visualization methods; or mapping the relationship in the data by using a statistical method in mathematics to form a graphic image relationship;
the primary report automatic generation module is used for automatically completing the collection of original data, the processing calculation of the original data, the data extraction and recording, the table editing and the curve drawing, and editing and generating a primary report;
the data security guarantee module is used for guaranteeing the security of data, communication data streams are communicated by using an SSL3.0 security socket layer and transmitted by adopting an https encryption protocol, communication between a server and a client needs to be mutually authenticated, the communication security during remote user operation is guaranteed, and the legality of communication data between functional modules of an application layer, the confidentiality of the data, the non-repudiation of the data and the integrity of the data are guaranteed; in the aspect of system safety management, the operation state of a functional module is detected in real time, double-computer hot backup is provided for important modules, antivirus, Trojan-resistant and firewall software is installed, an intrusion detection system is additionally installed, a virus library and a Trojan library are updated regularly, system patches are updated timely, and the system is prevented from being attacked and infected by viruses and Trojan; the UPS is used for ensuring stable power supply.
The state risk analysis is based on observation of satellite remote sensing to the elements of the geoenvironment, remote sensing data processing, business data analysis and comprehensive visual expression of multi-source information are taken as technical routes by means of big data cloud computing technology, a state risk dynamic analysis mathematical model is constructed from multiple dimensions including politics, economy, industry, resources and environment, and comprehensive study, judgment and quantitative analysis are carried out on investment risk of a target state;
the industry analysis is to extract valuable information from the obtained internet open source data, intellectual library service data and production enterprise data through mining analysis technologies including clustering, association and regression to form information including development level, industry life cycle, industry development situation, capacity distribution map, industry policy, market capacity and market entry and exit barriers at home and abroad;
the international public opinion analysis takes hot spot emergencies including natural disasters, accident disasters, public health events and social security events occurring in target countries as research objects, comprehensively collects all-media big data including internet, plane media, television stations, broadcasting stations and social media, and applies big data analysis and processing technology to monitor, analyze, evaluate and warn information including the incoming and outgoing arteries, development situations, public opinion trends, possible reaching ranges and influence degrees and key character social relationship maps of the hot spot emergencies.
The system has the multisource heterogeneous data organization management and visualization capacity based on a unified space-time frame, has the multi-dimensional data linkage display capacity, has the professional processing capacity of professional satellite remote sensing images, has the capacity of analyzing and mining macro-economy big data, constructs a national risk dynamic analysis mathematical model from multiple dimensions such as politics, economy, industry, resources and environment, comprehensively studies and judges the target national investment risk and quantitatively analyzes the target national investment risk, improves the timeliness and the accuracy of overseas investment risk assessment, deploys resources in advance for overseas investment enterprises, and provides accurate, rapid and quantitative scientific basis for managing and controlling the overseas investment risk. The macro-economic operation monitoring and early warning index system is shown as the following table:
Figure BDA0001560081490000091
TABLE 1
For a particular country i, its overseas risk at time t may be expressed as several risk elements r depending on the information set ΩijIn the form of a function of (c).
CRit=f(PRit,Erit,Brit,Lrit;Ωt)
Wherein: CRit-a risk assessment indicator for a specific country i,
PRit-a political risk indicator of a particular country i,
Erit-an economic risk indicator for a specific country i,
Brit-a commercial environmental risk indicator for a specific country i,
Lrit-legal risk indicator of a specific country i.
In the industrial risk analysis, the invention uses technical means to collect, arrange and store Internet open source data, intellectual library business data and production enterprise data, and mining analysis such as clustering, association, regression and the like is used for extracting valuable information. And providing information of development level, industry life cycle, industry development situation, capacity distribution map, industry policy, market capacity, market entry and exit barrier and the like of the industry at home and abroad for overseas investment enterprises in China.
In the international public opinion analysis, the invention takes major emergencies and hot spot events such as natural disasters, accident disasters, public health events, social security events and the like which are mainly generated by foreign investment countries in China as research objects, comprehensively collects all-media big data such as internet, plane media, television stations, broadcasting stations, social media and the like, and applies big data analysis and processing technology to deeply, finely and objectively monitor, analyze, evaluate and early warn the information such as the origin and destination, development situation, public opinion tendency, possible spread range and influence degree, key character social relation maps and the like of the overseas hot spot emergencies.
The method provided by the invention realizes collection, fusion and deep mining of overseas investment risk information data by using technical means such as big data, cloud computing, intelligent identification and the like, comprehensively senses information such as politics, economy, industry, technology, policy, resource, environment, biology, ecology and the like of overseas investment countries in China, collects, cleans, stores, unifies formats and semantically understands data from different sources, and mines, refines and analyzes effective information by taking space-time-object-content events as a correlation model; powerful data acquisition, multilingual multimedia data analysis and primary report automatic generation services are provided for developing national risk research, international public opinion research and industry analysis research, the overseas investment risk analysis mode is changed from a manual experience type to a computer-assisted intelligence type, and three types of information services of national risk analysis, industry risk analysis and international public opinion analysis can be provided for users.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.

Claims (4)

1. The international capacity cooperative risk assessment and decision service system based on big data is characterized by comprising:
the distributed structural/non-structural database is used for distributed storage of structured data, semi-structured data and non-structured data, and batch and stream processing of PB-level multi-source heterogeneous big data is realized;
the data access layer is used for receiving the data acquired by the front-end data acquisition module through various standard communication interfaces and automatically inputting the acquired data into the distributed structural/non-structural database according to a standard format;
the information acquisition and preprocessing layer is used for acquiring preset data, preprocessing the acquired data, performing format unification and semantic understanding on the data, mining and extracting effective information by using a data mining technology, extracting information keywords and constructing an index;
the preset data sources comprise satellite remote sensing data, internet open source information, intelligence library service data and research data of energy, environment, policy, law and economy;
the analysis layer is used for identifying valuable information content from the real-time information flow, storing the valuable information content in a text form, further processing the text, clustering the information aiming at national risk, industry analysis and international public opinion analysis respectively, and displaying the information in an information table form to provide reliable information for users;
the application layer is used for providing a query retrieval function for a query user, carrying out multi-dimensional visual output on the retrieved and queried information and generating a corresponding report;
the analysis layer processes data by adopting a multi-source heterogeneous data fusion technology based on cognitive computation and a large graph structure modeling and correlation analysis method:
the multisource heterogeneous data fusion technology based on cognitive computation comprises the following steps:
performing cross-modal multi-source data fusion based on deep learning, realizing feature extraction, concept fusion and combined semantic analysis of cross-modal data, integrating text information and dynamic network structure features aiming at large-scale, multi-source and heterogeneous stream data information, and realizing on-line tracking and evaluation facing to events, topics and groups;
simulating a human brain knowledge acquisition, storage and activation mode based on knowledge representation of cognitive computation to realize concept hierarchy construction, inference rules and high-level cognitive structure representation;
the large graph structure modeling and correlation analysis method comprises the steps of large graph structure representation and modeling, large graph calculation and large graph correlation analysis;
in the aspect of structural representation and modeling of the large graph, according to a distributed large graph representation strategy based on vertex cutting, the structural representation and modeling of the large graph are carried out by adopting a strategy of jointly minimizing the number of edges and the number of vertices of a load node;
in the calculation direction of the large graph, matrix and vector operation is converted into information iterative interaction between adjacent nodes so as to realize integration of various graph algorithms, including PageRank, eigenvalue solution and Unicom subgraph statistics; for each graph algorithm, selecting an optimal calculation strategy according to a calculation target, wherein the optimal calculation strategy is selected by carrying out variational reasoning through a random natural gradient rise algorithm based on random variational;
in the aspect of correlation analysis of a large graph, the positions of nodes in the graph and the dynamic change factors of the nodes along with time are considered, time-varying transfer matrixes of the nodes, the subgraphs and the edges are constructed, and direct correlation and indirect correlation of different nodes, subgraphs and edges are calculated according to transfer entropy correlation monitoring and analysis technology in a time sequence mode aiming at different types of graph structures.
2. The big-data-based international capacity cooperative risk assessment and decision-making service system according to claim 1, wherein in the aspect of collecting open source information of the internet, a focused crawler is adopted to automatically classify, identify and collect information pages on the internet; the method comprises the steps that through a webpage distinguishing module, an information page in a target website is automatically identified according to a manually preset topic word bank, and information which is irrelevant to text content and is mixed around the text content of the webpage and needs to be filtered through a webpage denoising module, wherein the information is acquired through a crawler and comprises advertisement information, navigation information, copyright information and header and footer information; in the crawling process of the web crawler, data duplication elimination processing is carried out through a webpage duplication elimination module;
in the aspect of satellite remote sensing information acquisition, correction recovery, enhancement transformation, image mosaic, feature extraction and image classification operations are carried out on a satellite remote sensing image, and noise and distortion introduced into the image are eliminated; enhancement transformation, i.e. highlighting predetermined features of the data, including color enhancement, contrast enhancement, edge enhancement, density segmentation, ratio operations, deblurring; image mosaic, namely, after one or a plurality of images are subjected to geometric mosaic, tone adjustment and overlap removal processing, the images are mosaic together to generate a complete image; and (4) feature extraction, namely extracting useful remote sensing information from the enhanced image, wherein the useful remote sensing information comprises automatic identification and classification by adopting statistical analysis, cluster analysis and spectrum analysis technologies.
3. The big-data-based international capacity cooperative risk assessment and decision-making service system according to claim 1, wherein the application layer comprises a query retrieval module, an information multidimensional visualization module, a primary report generation module and a data security guarantee module;
the query retrieval module is used for providing a plurality of quick query retrieval modes including special retrieval, title retrieval, fuzzy retrieval, association retrieval and character string retrieval according to a data query request input by a user; the retrieval result supports sorting according to the release time, sorting according to categories, sorting according to similarity and sorting according to repetition;
the information multidimensional visualization module is used for presenting the data information in a form of visualization of a graphic image, and the visualization technology used by the information multidimensional visualization module comprises the following steps:
1) spatial three-dimensional graphics: mapping the combination of different graphic elements into different data dimension interpretations by using transformation mapping, corresponding a visual space structure with data information, and presenting the distribution of data, the similarity between data and the relation between data by the density and the color distribution of a graph;
2) color map: the data volume is divided into a color image and a gray image, each color of the color image corresponds to different attribute dimensions, and the gray image marks the size of the attribute value of the data volume by utilizing the depth of the color;
3) luminance graph: for a specific area, the observation of the viewpoint by human eyes is assisted by different brightness;
4) the mathematical method comprises the following steps: analyzing the data relation by using a statistical method in mathematics to obtain the general distribution information of the data, and then analyzing the detailed data by combining other visualization methods; or mapping the relationship in the data by using a statistical method in mathematics to form a graphic image relationship;
the primary report automatic generation module is used for automatically completing the collection of original data, the processing calculation of the original data, the data extraction and recording, the table editing and the curve drawing, and editing and generating a primary report;
the data security guarantee module is used for guaranteeing the security of data, communication data streams are communicated by using an SSL3.0 security socket layer and transmitted by adopting an https encryption protocol, communication between a server and a client needs to be mutually authenticated, the communication security during remote user operation is guaranteed, and the legality of communication data between functional modules of an application layer, the confidentiality of the data, the non-repudiation of the data and the integrity of the data are guaranteed; in the aspect of system safety management, the operation state of a functional module is detected in real time, double-computer hot backup is provided for important modules, antivirus, Trojan-resistant and firewall software is installed, an intrusion detection system is additionally installed, a virus library and a Trojan library are updated regularly, system patches are updated timely, and the system is prevented from being attacked and infected by viruses and Trojan; the UPS is used for ensuring stable power supply.
4. The big data based international capacity collaborative risk assessment and decision making service system according to claim 1,
the state risk analysis is based on observation of satellite remote sensing to the elements of the geoenvironment, remote sensing data processing, business data analysis and comprehensive visual expression of multi-source information are taken as technical routes by means of big data cloud computing technology, a state risk dynamic analysis mathematical model is constructed from multiple dimensions including politics, economy, industry, resources and environment, and comprehensive study, judgment and quantitative analysis are carried out on investment risk of a target state;
the industry analysis is to extract valuable information from the obtained internet open source data, intellectual library service data and production enterprise data through mining analysis technologies including clustering, association and regression to form information including development level, industry life cycle, industry development situation, capacity distribution map, industry policy, market capacity and market entry and exit barriers at home and abroad;
the international public opinion analysis takes hot spot emergencies including natural disasters, accident disasters, public health events and social security events occurring in target countries as research objects, comprehensively collects all-media big data including internet, plane media, television stations, broadcasting stations and social media, and applies big data analysis and processing technology to monitor, analyze, evaluate and warn information including the incoming and outgoing arteries, development situations, public opinion trends, possible reaching ranges and influence degrees and key character social relationship maps of the hot spot emergencies.
CN201810077759.8A 2018-01-26 2018-01-26 International capacity cooperative risk assessment and decision service system based on big data Active CN108364124B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810077759.8A CN108364124B (en) 2018-01-26 2018-01-26 International capacity cooperative risk assessment and decision service system based on big data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810077759.8A CN108364124B (en) 2018-01-26 2018-01-26 International capacity cooperative risk assessment and decision service system based on big data

Publications (2)

Publication Number Publication Date
CN108364124A CN108364124A (en) 2018-08-03
CN108364124B true CN108364124B (en) 2022-01-07

Family

ID=63007319

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810077759.8A Active CN108364124B (en) 2018-01-26 2018-01-26 International capacity cooperative risk assessment and decision service system based on big data

Country Status (1)

Country Link
CN (1) CN108364124B (en)

Families Citing this family (31)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109190942A (en) * 2018-08-20 2019-01-11 浙江外国语学院 International friend's city commerce and trade risk automatic early-warning system
CN109145031A (en) * 2018-08-20 2019-01-04 国网安徽省电力有限公司合肥供电公司 A kind of multi-source data multidimensional reconstructing method of service-oriented market access demand
CN109325860A (en) * 2018-08-29 2019-02-12 中国科学院自动化研究所 Network public-opinion detection method and system for overseas investment Risk-warning
CN109241758A (en) * 2018-08-30 2019-01-18 安阳工学院 A kind of big data analysis system using computer verification code technology
CN109299082B (en) * 2018-09-13 2021-09-14 北京中科闻歌科技股份有限公司 Big data analysis method and system
WO2020062187A1 (en) * 2018-09-29 2020-04-02 Siemens Aktiengesellschaft Method, apparatus, computer-readable storage media and computer program for data analysis
CN109558966B (en) * 2018-10-28 2022-05-17 西南电子技术研究所(中国电子科技集团公司第十研究所) Processing system for intelligently judging evidence and predicting occurrence of event
CN111309775A (en) * 2018-12-12 2020-06-19 成都脉讯科技有限公司 Birth defect risk consultation data analysis and processing system
CN109710767B (en) * 2019-01-02 2022-08-30 山东省科学院情报研究所 Multilingual big data service platform
CN109829808A (en) * 2019-01-22 2019-05-31 政和科技股份有限公司 A kind of science and technology in enterprise property tax management recommendation generation system and method
CN110162590A (en) * 2019-02-22 2019-08-23 北京捷风数据技术有限公司 A kind of database displaying method and device thereof of calling for tenders of project text combination economic factor
CN109919471A (en) * 2019-02-27 2019-06-21 河南鑫安利安全科技股份有限公司 A kind of wisdom air control appraisal procedure and system
CN109977155A (en) * 2019-03-12 2019-07-05 福建奇点时空数字科技有限公司 A kind of big data visualization system and its control method based on human-computer interaction
CN110147406A (en) * 2019-05-29 2019-08-20 深圳市城市屋超科技有限公司 A kind of visual numeric simulation system and its framework method towards cloud computing
CN110347719B (en) * 2019-06-24 2023-06-30 华南农业大学 Enterprise foreign trade risk early warning method and system based on big data
CN110363586A (en) * 2019-07-03 2019-10-22 哈尔滨工业大学(威海) A kind of man-machine interactive system and its data processing method towards intelligence analysis
CN112183916B (en) * 2019-07-09 2023-10-31 浙江时空智子大数据有限公司 Land reserve life cycle management system
CN110413662B (en) * 2019-08-05 2021-11-26 中国地质大学(北京) Multichannel economic data input system, acquisition system and method
CN110648217A (en) * 2019-09-08 2020-01-03 贵州普惠链电子商务有限公司 Wind control system based on big data and artificial intelligence
CN110928922B (en) * 2019-11-27 2020-07-24 开普云信息科技股份有限公司 Public policy analysis model deployment method and system based on big data mining
CN111026780A (en) * 2019-12-18 2020-04-17 成都迪普曼林信息技术有限公司 Regional security situation information management system
CN110990748B (en) * 2019-12-18 2023-06-27 成都迪普曼林信息技术有限公司 Public opinion data collection and release system
CN111128308B (en) * 2019-12-26 2023-03-24 上海市精神卫生中心(上海市心理咨询培训中心) New mutation information knowledge platform for neuropsychiatric diseases
CN111898916A (en) * 2020-08-05 2020-11-06 辽宁工程技术大学 Coal industry chain risk monitoring system and monitoring method thereof
CN112491962A (en) * 2020-11-03 2021-03-12 深圳市中博科创信息技术有限公司 Model-driven intelligent distributed architecture method and platform
CN112559618B (en) * 2020-12-23 2023-07-11 光大兴陇信托有限责任公司 External data integration method based on financial wind control business
CN113220672A (en) * 2021-04-26 2021-08-06 中国人民解放军军事科学院国防科技创新研究院 Military and civil fusion policy information database system
CN113807645A (en) * 2021-07-26 2021-12-17 北京清博智能科技有限公司 Industrial chain risk deduction method based on open source information
CN116501779A (en) * 2023-06-26 2023-07-28 图林科技(深圳)有限公司 Big data mining analysis system for real-time feedback
CN116667745B (en) * 2023-07-27 2023-10-03 大澳电器(江苏)有限公司 Motor internal temperature display and control system
CN117010697B (en) * 2023-09-25 2023-12-19 山东财经大学 Visual enterprise risk assessment method based on artificial intelligence

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040162777A1 (en) * 2003-02-14 2004-08-19 Sullivan James L. Method of apportioning investments within a multi-country fund
CN104933093B (en) * 2015-05-19 2018-08-07 武汉泰迪智慧科技有限公司 The monitoring of regional public sentiment and decision support system (DSS) based on big data and method
CN106127583A (en) * 2016-06-28 2016-11-16 长沙星际泛函网络科技有限公司 The Internet overseas investment resource integration system
CN106251227A (en) * 2016-06-28 2016-12-21 长沙星际泛函网络科技有限公司 The Internet overseas investment risk management system
CN106649498A (en) * 2016-10-10 2017-05-10 合肥红珊瑚软件服务有限公司 Network public opinion analysis system based on crawler and text clustering analysis
CN107196910B (en) * 2017-04-18 2019-09-10 国网山东省电力公司电力科学研究院 Threat early warning monitoring system, method and deployment framework based on big data analysis
CN107590181A (en) * 2017-08-01 2018-01-16 佛山市深研信息技术有限公司 A kind of intelligent analysis system of big data

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
国际科技合作创新风险决策模型研究;李琪;《北方经济》;20121201;第85-87页 *
基于多源数据融合的网络风险评估;梁智学,郭俊颖;《船舶电子工程》;20110430;第60-64页 *

Also Published As

Publication number Publication date
CN108364124A (en) 2018-08-03

Similar Documents

Publication Publication Date Title
CN108364124B (en) International capacity cooperative risk assessment and decision service system based on big data
Ragan et al. Characterizing provenance in visualization and data analysis: an organizational framework of provenance types and purposes
López-Robles et al. Understanding the intellectual structure and evolution of Competitive Intelligence: A bibliometric analysis from 1984 to 2017
Wang et al. Information Computing and Applications
CN111708773A (en) Multi-source scientific and creative resource data fusion method
CN111967761A (en) Monitoring and early warning method and device based on knowledge graph and electronic equipment
CN109325860A (en) Network public-opinion detection method and system for overseas investment Risk-warning
CN111708774B (en) Industry analytic system based on big data
CN114399006A (en) Multi-source abnormal composition image data fusion method and system based on super-calculation
KR20210129465A (en) Apparatus for managing laboratory note and method for searching laboratory note using thereof
Dormezil et al. Differentiating between Educational Data Mining and Learning Analytics: A Bibliometric Approach.
Wang et al. Safety intelligence toward safety management in a big-data environment: A general model and its application in urban safety management
Davey et al. Visual analytics: Towards intelligent interactive internet and security solutions
CN106777124B (en) Semantic knowledge method, apparatus and system
Fernández-Rosillo San Isidro et al. Micro-database for sustainability (ESG) indicators developed at the Banco de España (2022)
Benjamin et al. Distributed information gathering, exploration and sensemaking toolkit (DIGEST)
Shanti et al. Knowledge data map—A framework for the field of data mining and knowledge discovery
KR20210045172A (en) Big Data Management and System for Livestock Disease Outbreak Analysis
Upadhyay et al. The major boom of an Unstructured Big Data on Social Media
Chen et al. Research on Network Intelligent Finance Data Mining and Analysis System and Quantitative Model
Cao et al. ACM TIST Special Issue on Visual Analytics
Zhang Python Data Analysis Techniques in Administrative Information Integration Management System
Anbu et al. A Comprehensive WebScraping of IMDb’s Top 50 Movies using Beautiful Soup
Liu A public opinion monitoring system based on big data technology
Balamurugan et al. Data Management and Visual Information Processing in Financial Organization using Machine Learning

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
CP03 Change of name, title or address

Address after: 300457 unit msd-g1-1001, TEDA, No.57, 2nd Street, Tianjin Economic and Technological Development Zone, Binhai New Area, Tianjin

Patentee after: Tianjin Zhongke intelligent identification Co.,Ltd.

Address before: Unit 300465 TEDA MSD-G1-1001, 57 Second Avenue, Tianjin Economic and Technological Development Zone, Binhai New Area, Tianjin

Patentee before: TIANJIN ZHONGKE INTELLIGENT IDENTIFICATION INDUSTRY TECHNOLOGY RESEARCH INSTITUTE Co.,Ltd.

CP03 Change of name, title or address