Financial risk spatial correlation monitoring method and device, and medium

Abstract

The invention discloses a financial risk spatial correlation monitoring method and device, and a medium, belongs to the technical field of financial public opinion data monitoring, and is used for solving the technical problems that financial risk spatial correlation monitoring among cities is relatively difficult, systematic financial risk prevention is not facilitated, and financial risk spatial overflow is easily caused. The method comprises the steps of performing word segmentation processing on public opinion text data through a preset financial emotion corpus to obtain public opinion text word segmentation result data; carrying out weight calculation related to positive and negative sentiment words on word data representing sentiment tendency in the public opinion text word segmentation result data, and determining financial risk text data; carrying out keyword identification processing based on risk associated enterprises on the financial risk text data to obtain enterprise main body information; and performing spatial matrix association processing between the enterprise main body information and the city name information to obtain an inter-city financial risk association index.

Description

Technical Field

[0001] The present application relates to the field of financial public opinion data monitoring, and in particular to a method, device and medium for monitoring the spatial correlation of financial risks. Background Art

[0002] The identification of spatial correlation of financial risks plays an important role in preventing and defusing systemic financial risks and maintaining financial stability. The spatial correlation of financial risks refers to the phenomenon that risks between different regions or different financial institutions influence and transmit each other. This correlation may lead to a chain reaction of risks, which in turn triggers systemic financial risks. The spatial correlation of financial risks has the following characteristics:

[0003] Suddenness: The outbreak of systemic financial risks often occurs in a relatively short period of time and spreads very quickly. The highly connected financial networks will produce chain reactions, causing huge shocks to the financial system and the economy.

[0004] Complexity: There are complex connections between entities and markets in the financial system. Financial institutions form a network of relationships through loans, guarantees, etc. Small-scale risk events may trigger large-scale shocks.

[0005] Cross-cutting: There are correlations between different financial entities and markets, such as the "risk triangle" formed by real estate, local debt and small and medium-sized financial institutions. Risks spread from one market to other related markets, forming a vicious circle.

[0006] The existing spatial correlation of financial risks among cities has problems such as "difficult and slow identification". It is difficult to dynamically query and present the correlation of financial risks among different cities, which is not conducive to the prevention of systemic financial risks and will have certain adverse effects on the high-quality development of the economy. Summary of the invention

[0007] The embodiments of the present application provide a method, device and medium for monitoring the spatial correlation of financial risks, which are used to solve the following technical problems: the existing monitoring of the spatial correlation of financial risks among cities is relatively difficult, which is not conducive to the prevention of systemic financial risks and easily causes the spatial spillover of financial risks.

[0008] The present application embodiment adopts the following technical solutions:

[0009] On the one hand, the embodiments of the present application provide a method, device and medium for monitoring the spatial correlation of financial risks, including: performing word segmentation processing on public opinion text data through a preset financial sentiment corpus to obtain public opinion text segmentation result data; performing weight calculation on the word data representing sentiment tendency in the public opinion text segmentation result data regarding the positive and negative sentiment words to determine the financial risk text data; performing keyword recognition processing on the financial risk text data based on risk-related enterprises to obtain enterprise entity information; performing keyword recognition processing on the financial risk text data based on risk-related cities to obtain city name information; performing spatial matrix association processing between the enterprise entity information and the city name information to obtain an inter-city financial risk correlation index.

[0010] The embodiment of the present application uses the financial sentiment corpus to perform word segmentation processing on public opinion text data, which helps to capture market sentiment and the public's views on financial risks and provide early warning signals about financial risks. You can focus on specific companies and cities to understand their connections and influences in financial risks. It can reveal the interrelationships and propagation patterns of financial risks between different cities, helping regulators and decision makers to better understand the spatial distribution and correlation of financial risks. Targeted measures can also be taken to prevent and respond to financial risks and improve the stability of the financial system. It optimizes resource allocation and reduces the impact of financial risks. At the same time, a large amount of text information is used to monitor financial risks. This data-driven approach can supplement traditional financial risk monitoring methods and provide a more comprehensive and real-time perspective.

[0011] In a feasible implementation, the public opinion text data is segmented through a preset financial sentiment corpus to obtain public opinion text segmentation result data, specifically including: extracting the public opinion text data stored in a financial data resource library; based on the financial sentiment corpus words in the financial sentiment corpus, and through a segmentation tool, the public opinion text data is segmented based on the financial sentiment corpus words in the segmentation format to obtain initial public opinion text segmentation result data; deleting the current stop words in the initial public opinion text segmentation result data to obtain the public opinion text segmentation result.

[0012] In a feasible implementation manner, the data representing sentiment tendency words in the public opinion text segmentation result data are weighted for positive and negative sentiment words to determine the financial risk text data, specifically including: using the financial sentiment corpus, screening the public opinion text segmentation result data in each of the public opinion text data for the words representing sentiment tendency to obtain the data representing sentiment tendency words; classifying the data representing sentiment tendency words into positive and negative sentiment words to obtain positive sentiment words and negative sentiment words; determining the first weight of the positive sentiment words and the second weight of the negative sentiment words based on a preset weight allocation rule; calculating the score of the financial risk tendency weight for the first weight and the second weight to obtain the financial risk score of each of the public opinion text data; sorting a number of the financial risk scores, and determining the public opinion text data corresponding to the financial risk score in the first sorting threshold as the financial risk text data.

[0013] In a feasible implementation, the financial risk text data is processed for keyword recognition based on risk-related enterprises to obtain enterprise entity information, specifically including: collecting industrial and commercial data associated with the public opinion text data, and extracting industrial and commercial enterprise entity name information in the industrial and commercial data; processing the industrial and commercial enterprise entity name information for keyword identification of risk-related enterprises to obtain a first keyword; using the first keyword, performing keyword recognition and matching on enterprise text terms in the financial risk text data to determine the enterprise entity information in the financial risk text data; wherein the enterprise entity information includes: enterprise entity name information and enterprise registration place information.

[0014] In a feasible implementation, the financial risk text data is processed based on risk-related city keyword recognition to obtain city name information, specifically including: obtaining city information in the public opinion text data; processing the city information with risk-related city keyword identification to obtain a second keyword; and using the second keyword to perform keyword recognition and matching on city text words in the financial risk text data to determine the city name information in the financial risk text data.

[0015] In a feasible implementation, spatial matrix association processing is performed between the enterprise entity information and the city name information to obtain the inter-city financial risk association index, which specifically includes: spatial mapping association processing is performed between the enterprise registration place information in the enterprise entity information and the city name information to construct a city association matrix; wherein the city association matrix is ​​the enterprise entity information involved in the financial risk text data between different cities; based on the city association matrix, the inter-city financial risk association index between different cities is determined.

[0016] In a feasible implementation, based on the city association matrix, the inter-city financial risk association index between different cities is determined, specifically including: according to the financial risk text data, counting the number of financial risk associations between two cities with associated financial risks in the city association matrix to obtain the inter-city financial risk association index between the two cities.

[0017] In a feasible implementation, the inter-city financial risk correlation index is the total financial risk correlation index obtained by adding together multiple financial risk text data; the inter-city financial risk correlation index between different cities is structuredly represented to obtain financial risk correlation characteristics based on urban spatial correlation.

[0018] In the second aspect, an embodiment of the present application also provides a financial risk spatial correlation monitoring device, the device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor so that the at least one processor can execute a financial risk spatial correlation monitoring method described in any of the above-mentioned embodiments.

[0019] In the third aspect, an embodiment of the present application also provides a non-volatile computer storage medium, characterized in that the storage medium is a non-volatile computer-readable storage medium, and the non-volatile computer-readable storage medium stores at least one program, each of which includes instructions, and when the instructions are executed by a terminal, the terminal executes a method for monitoring the spatial correlation of financial risks described in any of the above-mentioned embodiments.

[0020] The present application provides a method, device and medium for monitoring the spatial correlation of financial risks. Compared with the prior art, the embodiments of the present application have the following beneficial technical effects:

[0021] 1. By using the financial sentiment corpus to segment the public opinion text data and calculate the weights of the words that represent sentiment tendencies, financial risk text data can be determined. This helps capture market sentiment and the public's views on financial risks and provide early warning signals about financial risks.

[0022] 2. By performing keyword recognition processing on financial risk text data based on risk-related enterprises and cities, we can extract enterprise entity information and city name information related to financial risks. This helps to focus on specific enterprises and cities and understand their connection and impact on financial risks.

[0023] 3. Perform spatial matrix correlation processing on the enterprise entity information and city name information to obtain the inter-city financial risk correlation index. This can reveal the relationship and transmission pattern of financial risks between different cities and help regulators and decision makers better understand the spatial distribution and correlation of financial risks.

[0024] 4. This method provides a means to monitor the spatial correlation of financial risks, and can timely discover the spread and diffusion trend of financial risks among different cities. This helps to take targeted measures to prevent and respond to financial risks and improve the stability of the financial system.

[0025] 5. The inter-city financial risk correlation index can provide valuable information for regulators, financial institutions and decision makers, helping them to formulate reasonable policies and strategies, optimize resource allocation and reduce the impact of financial risks.

[0026] 6. This method is based on public opinion text data and keyword recognition technology, using a large amount of text information to monitor financial risks. This data-driven approach can supplement traditional financial risk monitoring methods and provide a more comprehensive and real-time perspective. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0028] Figure 1 A method flow chart of a method for monitoring spatial correlation of financial risks provided in an embodiment of the present application;

[0029] Figure 2 A structural schematic diagram of a financial risk spatial correlation monitoring method and device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this application.

[0031] The present application embodiment provides a method for monitoring the spatial correlation of financial risks, such as Figure 1 As shown, the method for monitoring the spatial correlation of financial risks specifically includes steps S101-S105:

[0032] S101. Perform word segmentation processing on the public opinion text data through a preset financial sentiment corpus to obtain the public opinion text word segmentation result data.

[0033] Specifically, we first need to extract the public opinion text data stored in the financial data resource library from the data resource subsystem. The data resource subsystem is responsible for storing the required data resources, including public opinion text data, national industrial and commercial data, national city names, etc., so that other subsystems can call data resources.

[0034] Furthermore, based on the financial sentiment corpus words in the financial sentiment corpus and through the word segmentation tool, the public opinion text data is processed by text segmentation based on the financial sentiment corpus word segmentation format to obtain the initial public opinion text segmentation result data.

[0035] Furthermore, the current stop words in the initial public opinion text segmentation result data are deleted to obtain the public opinion text segmentation result.

[0036] In one embodiment, a preset financial risk identification subsystem can be used to rely on the collected public opinion text data to identify whether the public opinion belongs to financial risk public opinion through natural language processing technology (NLP). That is, based on the acquired financial sentiment corpus, the public opinion text data is segmented using a word segmentation tool, and the public opinion text data is segmented based on the word segmentation format of the financial sentiment corpus, and stop words are removed to finally obtain the public opinion text segmentation result.

[0037] S102, calculating the weights of the positive and negative sentiment words in the sentiment tendency word data in the public opinion text segmentation result data, and determining the financial risk text data.

[0038] Specifically, it is also necessary to use the financial sentiment corpus to screen the words representing sentiment tendencies in the public opinion text segmentation result data in each public opinion text data to obtain the data of words representing sentiment tendencies.

[0039] Furthermore, the data representing the words of sentiment tendency are classified into positive and negative sentiment words to obtain positive sentiment words and negative sentiment words.

[0040] Furthermore, based on a preset weight allocation rule, a first weight of the positive sentiment words and a second weight of the negative sentiment words are determined.

[0041] Furthermore, the first weight and the second weight are used to calculate the score of the financial risk tendency weight to obtain the financial risk score of each public opinion text data.

[0042] Furthermore, a plurality of financial risk scores are sorted, and public opinion text data corresponding to financial risk scores within a first sorting threshold are determined as financial risk text data.

[0043] As a feasible implementation method, the financial risk identification subsystem is used to match the financial sentiment corpus with the word segmentation results of the public opinion text, and the words representing the sentiment tendency in the public opinion text are screened. Then, the data representing the sentiment tendency words are classified into positive and negative sentiment words to obtain positive sentiment words and negative sentiment words. By assigning the first weight and the second weight to the positive words and the negative words respectively, the financial risk tendency score of the public opinion text data is calculated, and the public opinion text data with a higher score in the first sorting threshold is marked as financial risk text data.

[0044] S103, performing keyword recognition processing on the financial risk text data based on risk-related enterprises to obtain enterprise entity information.

[0045] Specifically, the industrial and commercial data associated with the public opinion text data is first collected, and the name information of the industrial and commercial enterprise entity in the industrial and commercial data is extracted.

[0046] Furthermore, the name information of the industrial and commercial enterprise entity is processed with keyword identification of risk-related enterprises to obtain the first keyword.

[0047] Furthermore, the first keyword is used to identify and match the enterprise text words in the financial risk text data, and the enterprise subject information in the financial risk text data is determined. The enterprise subject information includes: enterprise subject name information and enterprise registration place information. That is, it is determined whether the financial risk text involves an enterprise subject by keyword hits. At the same time, the enterprise registration place information is obtained from the identified enterprise name information through industrial and commercial data.

[0048] S104, performing risk-related city keyword recognition processing on the financial risk text data to obtain city name information.

[0049] Specifically, it is also necessary to obtain city information in the public opinion text data.

[0050] Furthermore, the city information is processed with keyword identification of risk-related cities to obtain a second keyword.

[0051] Furthermore, the second keyword is used to identify and match the city text words in the financial risk text data, and the city name information in the financial risk text data is determined. That is, it is determined whether a certain city is involved in the financial risk text by keyword hits.

[0052] S105. Perform spatial matrix correlation processing between the enterprise entity information and the city name information to obtain the inter-city financial risk correlation index.

[0053] Specifically, the enterprise registration location information in the enterprise subject information is first mapped and associated with the city name information in spatial position, and then a city association matrix is ​​constructed. Among them, the city association matrix is ​​the enterprise subject information involved in the financial risk text data between different cities.

[0054] Furthermore, based on the city association matrix, the inter-city financial risk association index between different cities is determined. That is, it is necessary to count the number of financial risk associations between two cities with financial risks in the city association matrix according to the financial risk text data, and obtain the inter-city financial risk association index between the two cities. The inter-city financial risk association index is the total financial risk association index of multiple financial risk text data added together.

[0055] In one embodiment, under a specific "time A" condition, there are two pieces of public opinion data, "Financial Risk Text 1" and "Financial Risk Text 2". Among them, "Financial Risk Text 1" involves "City A, City B, City C", which corresponds to the formation of "City A-City B", "City A-City C" and "City B-City C" 1 financial risk association; "Financial Risk Text 2" involves "City A, City B", which corresponds to the formation of "City A-City B" 1 financial risk association. Finally, through summary, the financial risk association index between cities under the condition of "Time A" is: "City A-City B, 2 times", "City A-City C, 1 time", "City B-City C, 1 time".

[0056] Furthermore, the inter-city financial risk correlation index between different cities is structured and characterized to obtain the financial risk correlation characteristics based on the spatial correlation of cities. The unstructured public opinion text data is extracted into structured data (inter-city financial risk correlation index) that represents the correlation of financial risks between cities, which is convenient for graphically presenting the characteristics of financial risk correlation between cities, can assist in monitoring the spatial correlation of financial risks, and plays an important role in preventing systemic risks and hindering the spatial spillover effects of financial risks.

[0057] In addition, the present application embodiment also provides a financial risk spatial correlation monitoring device, such as Figure 2 As shown, the financial risk spatial correlation monitoring device 200 specifically includes:

[0058] At least one processor 201. And a memory 202 in communication with the at least one processor 201. The memory 202 stores instructions that can be executed by the at least one processor 201, so that the at least one processor 201 can execute:

[0059] Through the preset financial sentiment corpus, the public opinion text data is segmented to obtain the public opinion text segmentation result data;

[0060] The data representing the sentiment tendency in the word segmentation result data of the public opinion text is weighted to calculate the positive and negative sentiment words, and the financial risk text data is determined;

[0061] Perform keyword recognition processing on financial risk text data based on risk-related enterprises to obtain enterprise entity information;

[0062] The financial risk text data is processed based on the risk-related city keywords to obtain the city name information;

[0063] The spatial matrix correlation processing is performed between the enterprise entity information and the city name information to obtain the inter-city financial risk correlation index.

[0064] The embodiment of the present application uses the financial sentiment corpus to perform word segmentation processing on public opinion text data, which helps to capture market sentiment and the public's views on financial risks and provide early warning signals about financial risks. You can focus on specific companies and cities to understand their connections and influences in financial risks. It can reveal the interrelationships and propagation patterns of financial risks between different cities, helping regulators and decision makers to better understand the spatial distribution and correlation of financial risks. Targeted measures can also be taken to prevent and respond to financial risks and improve the stability of the financial system. It optimizes resource allocation and reduces the impact of financial risks. At the same time, a large amount of text information is used to monitor financial risks. This data-driven approach can supplement traditional financial risk monitoring methods and provide a more comprehensive and real-time perspective.

[0065] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0066] The devices and media provided in the embodiments of the present application correspond one-to-one to the methods. Therefore, the devices and media also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0067] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0068] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0069] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0070] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0071] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0072] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0073] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0074] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0075] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for monitoring the spatial correlation of financial risks, characterized in that: The method comprises: Through the preset financial sentiment corpus, the public opinion text data is segmented to obtain the public opinion text segmentation result data; The word data representing the sentiment tendency in the word segmentation result data of the public opinion text is weighted to calculate the positive and negative sentiment words, and the financial risk text data is determined; Perform keyword recognition processing on the financial risk text data based on risk-related enterprises to obtain enterprise entity information; Perform risk-related city keyword recognition processing on the financial risk text data to obtain city name information; A spatial matrix association process is performed between the enterprise entity information and the city name information to obtain an inter-city financial risk association index.

2. A method for monitoring spatial correlation of financial risks according to claim 1, characterized in that: Through the preset financial sentiment corpus, the public opinion text data is segmented to obtain the public opinion text segmentation result data, including: Extracting the public opinion text data stored in the financial data resource library; Based on the financial sentiment corpus words in the financial sentiment corpus, and using a word segmentation tool, the public opinion text data is subjected to text segmentation processing based on the financial sentiment corpus word segmentation format to obtain initial public opinion text segmentation result data; The current stop words in the initial public opinion text segmentation result data are deleted to obtain the public opinion text segmentation result.

3. A method for monitoring spatial correlation of financial risks according to claim 1, characterized in that: The word data representing the sentiment tendency in the public opinion text segmentation result data is weighted to calculate the positive and negative sentiment words to determine the financial risk text data, specifically including: Through the financial sentiment corpus, the public opinion text segmentation result data in each of the public opinion text data is screened for words representing sentiment tendency to obtain the word data representing sentiment tendency; Classifying the data of words representing sentiment tendency into positive and negative sentiment words to obtain positive sentiment words and negative sentiment words; Based on a preset weight allocation rule, determining a first weight of the positive sentiment words and a second weight of the negative sentiment words; Calculate the score of the financial risk tendency weight by using the first weight and the second weight to obtain the financial risk score of each of the public opinion text data; The financial risk scores are sorted, and the public opinion text data corresponding to the financial risk scores within a first sorting threshold are determined as the financial risk text data.

4. A method for monitoring spatial correlation of financial risks according to claim 1, characterized in that: The financial risk text data is processed by keyword recognition based on risk-related enterprises to obtain enterprise subject information, including: Collecting industrial and commercial data associated with the public opinion text data, and extracting the name information of the industrial and commercial enterprise entity in the industrial and commercial data; The name information of the industrial and commercial enterprise is processed by keyword identification of risk-related enterprises to obtain a first keyword; Through the first keyword, the enterprise text words in the financial risk text data are identified and matched by keywords to determine the enterprise entity information in the financial risk text data; wherein the enterprise entity information includes: enterprise entity name information and enterprise registration location information.

5. A method for monitoring spatial correlation of financial risks according to claim 1, characterized in that: The financial risk text data is processed based on risk-related city keyword recognition to obtain city name information, specifically including: Obtain city information from public opinion text data; The city information is processed by keyword identification of risk-related cities to obtain a second keyword; The second keyword is used to identify and match the city text words in the financial risk text data, and the city name information in the financial risk text data is determined.

6. A method for monitoring spatial correlation of financial risks according to claim 1, characterized in that: Perform spatial matrix association processing between the enterprise entity information and the city name information to obtain the inter-city financial risk association index, which specifically includes: Mapping and associating the enterprise registration location information in the enterprise subject information with the city name information in spatial position to construct a city association matrix; wherein the city association matrix is ​​the enterprise subject information between different cities involved in the financial risk text data; Based on the city association matrix, the inter-city financial risk association index between different cities is determined.

7. A method for monitoring spatial correlation of financial risks according to claim 6, characterized in that: Based on the city association matrix, the inter-city financial risk association index between different cities is determined, specifically including: According to the financial risk text data, the number of financial risk associations between two cities with associated financial risks in the city association matrix is ​​counted to obtain the inter-city financial risk association index between the two cities.

8. A method for monitoring spatial correlation of financial risks according to claim 1, characterized in that: The inter-city financial risk correlation index is the total financial risk correlation index obtained by adding together a plurality of the financial risk text data; The inter-city financial risk correlation index between different cities is structured and characterized to obtain the financial risk correlation characteristics based on the urban spatial correlation.

9. A financial risk spatial correlation monitoring device, characterized in that: The device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, so that the at least one processor can execute a method for monitoring the spatial correlation of financial risks according to any one of claims 1-8.

10. A non-volatile computer storage medium, characterized in that: The storage medium is a non-volatile computer-readable storage medium, and the non-volatile computer-readable storage medium stores at least one program, each of which includes instructions, and when the instructions are executed by a terminal, the terminal executes a financial risk spatial correlation monitoring method according to any one of claims 1-8.

Images