Financial risk control method and system based on big data

Abstract

The invention is suitable for the technical field of financial risk prediction, and provides a financial risk control method and system based on big data, and the method comprises the steps: firstly obtaining the first enterprise name information of a target enterprise, and then obtaining the first enterprise name information of the target enterprise based on the first enterprise name information; according to the method, the public opinion article set information of the target enterprise and the article comment information corresponding to the public opinion article set information are quickly obtained, and finally financial risk prediction information is effectively generated according to the public opinion article set information and the article comment information. According to the method, the potential financial risk outbreak possibility of the target enterprise can be efficiently and accurately predicted, the accuracy and timeliness of financial risk prediction are remarkably improved, the depth and breadth of risk identification are enhanced, scientific decision support is provided for financial institutions, and the risk identification efficiency is improved. The method assists a user in timely formulating and implementing an effective prevention and control strategy before a risk occurs, reduces potential loss to the greatest extent, and guarantees the stability and safety of a financial system.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of financial risk prediction, in particular to a financial risk control method and system based on big data. BACKGROUND

[0002] Due to the high complexity of financial risks, they can often trigger a chain reaction, leading to violent fluctuations in the financial market, and even triggering a systemic financial crisis, which seriously threatens the stability and security of the overall economy. Therefore, it is necessary to prevent potential financial crises from breaking out and maintain the stable operation of the financial system.

[0003] Currently, the identification of financial risks usually relies on the personal experience of financial experts. Due to the subjectivity of the judgment process and the limitations of experience, it is easy to miss the risk identification, and there is a problem of low reliability, which needs to be further improved. SUMMARY

[0004] Therefore, the embodiments of the present application provide a financial risk control method and system based on big data to solve the problem of low reliability in the prior art.

[0005] In a first aspect, the embodiments of the present application provide a financial risk control method based on big data, which comprises: obtaining first enterprise name information of a target enterprise; based on the first enterprise name information, obtaining public opinion article set information of the target enterprise and article comment information corresponding to the public opinion article set information, wherein the public opinion article set information comprises a plurality of public opinion article information; generating financial risk prediction information according to the public opinion article set information and the article comment information.

[0006] Compared with the prior art, the financial risk control method based on big data provided by the embodiments of the present application has the beneficial effects that: the terminal device can first obtain the first enterprise name information of the target enterprise, then quickly obtain the public opinion article set information of the target enterprise and the article comment information corresponding to the public opinion article set information based on the first enterprise name information, and finally effectively generate the financial risk prediction information according to the public opinion article set information and the article comment information, so as to realize the effective prediction of whether the target enterprise is likely to break out a financial risk, reduce the analysis error of personal subjective judgment, greatly improve the prediction reliability of the financial risk, and effectively assist the financial institutions to take preventive measures in advance, to a certain extent, solve the problem of low reliability.

[0007] In a second aspect, the embodiments of the present application provide a financial risk control system based on big data, which comprises: The first enterprise name information acquisition module is configured to acquire first enterprise name information of the target enterprise. The public opinion article set information acquisition module is configured to acquire public opinion article set information of the target enterprise and article comment information corresponding to the public opinion article set information based on the first enterprise name information, wherein the public opinion article set information comprises a plurality of public opinion article information. The financial risk prediction information generation module is configured to generate financial risk prediction information according to the public opinion article set information and the article comment information.

[0008] In a third aspect, an embodiment of the present application provides a terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the method of the first aspect when executing the computer program.

[0009] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executable on a processor to implement the steps of the method of the first aspect.

[0010] It can be understood that the beneficial effects of the second aspect to the fourth aspect can be referred to the related description in the first aspect, and will not be repeated here. BRIEF DESCRIPTION OF DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiments or prior art description will be briefly introduced as follows.

[0012] Figure 1 is a flowchart of a financial risk control method provided by an embodiment of the present application; Figure 2 is a flowchart of the financial risk control method provided by an embodiment of the present application after step S200; Figure 3 is a flowchart of step S300 of the financial risk control method provided by an embodiment of the present application; Figure 4 is a first flowchart of the financial risk control method provided by an embodiment of the present application after step S300; Figure 5 is a second flowchart of the financial risk control method provided by an embodiment of the present application after step S300; Figure 6 is a module block diagram of a financial risk control system provided by an embodiment of the present application; Figure 7 is a schematic diagram of a terminal device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0013] In the following description, for purposes of explanation and not limitation, specific details are set forth such as particular architectures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application can be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known methods, devices, circuits, and

[0014] In the description of the specification and the appended claims, the terms "first", "second", "third", etc. are used only to distinguish descriptions, and cannot be understood as indicating or implying relative importance.

[0015] In the description of the specification, the reference "one embodiment" or "some embodiments" means that the specific feature, structure or characteristic described in connection with the embodiment is included in one or more embodiments of the present application. Therefore, the statements "in one embodiment", "in some embodiments", "in other some embodiments", "in yet some embodiments" appearing in different places in the specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized. The terms "include", "contain", "have" and their variants mean "including but not limited to", unless otherwise specifically emphasized.

[0016] In order to illustrate the technical solutions described in the present application, the following will be described by specific embodiments.

[0017] Please refer to Figure 1 , Figure 1 is a flowchart of a financial risk control method based on big data provided by an embodiment of the present application. In the embodiment, the execution subject of the financial risk control method is a terminal device. It can be understood that the types of the terminal device include but are not limited to mobile phones, tablet computers, notebook computers, ultra-mobile personal computers (UMPC), netbooks, personal digital assistants (PDA), etc., and the specific type of the terminal device is not limited by the embodiments of the present application.

[0018] Please refer to Figure 1 , the financial risk control method provided by the embodiments of the present application includes but is not limited to the following steps: In S100, first enterprise name information of a target enterprise is acquired.

[0019] Specifically, the terminal device can first acquire first enterprise name information of a target enterprise, wherein the target enterprise is used to describe an enterprise to be evaluated whether a financial risk will break out; and the first enterprise name information is used to describe an enterprise name of the target enterprise.

[0020] In S200, based on the first enterprise name information, the terminal device acquires public opinion article set information of the target enterprise and article comment information corresponding to the public opinion article set information.

[0021] Specifically, after the terminal device acquires the first enterprise name information, the terminal device can acquire, based on the first enterprise name information, public opinion article set information of the target enterprise and article comment information corresponding to the public opinion article set information by using big data technology, wherein the public opinion article set information includes a plurality of public opinion article information, and the public opinion article information is used to describe analysis articles, comment articles and / or interpretation articles related to the target enterprise; and the article comment information is used to describe public comments on the public opinion article information.

[0022] In some possible implementation manners, in order to improve the accuracy of financial risk identification, please refer to Figure 2 After S200, the method further includes but is not limited to the following steps: In S201, for each article comment information, based on a preset positive maximum segmentation algorithm, the terminal device performs segmentation processing on the article comment information to generate a plurality of to-be-classified word information.

[0023] Specifically, the terminal device can perform the following processing on each article comment information: based on a preset positive maximum segmentation algorithm, the terminal device performs segmentation processing on the article comment information to effectively generate a plurality of to-be-classified word information, wherein the to-be-classified word information is used to describe an independent word obtained by performing segmentation processing on the article comment information. In S202, based on a dictionary matching algorithm and a preset positive dictionary set information, the terminal device performs classification processing on the plurality of to-be-classified word information to determine positive word information, and based on the dictionary matching algorithm and a preset negative dictionary set information, the terminal device performs classification processing on the plurality of to-be-classified word information to determine negative word information.

[0024] Specifically, after the terminal device generates the plurality of to-be-classified word information, the terminal device can perform classification processing on the plurality of to-be-classified word information based on a dictionary matching algorithm and a preset positive dictionary set information to quickly determine positive word information, wherein the positive dictionary set information is used to describe a dictionary containing a plurality of positive words; and the positive word is used to describe a positive word, such as "integrity", "professionalism", "leadership", "advanced technology" and "excellent quality".

[0025] Without loss of generality, meanwhile, the terminal device can perform classification processing on the plurality of to-be-classified word information based on a dictionary matching algorithm and preset negative dictionary set information, and quickly determine the negative word information, wherein the negative dictionary set information is used to describe a dictionary containing a plurality of negative words; the negative word is used to describe a negative word, such as "management chaos", "instability", "lack of competitiveness", "many customer complaints", and "delayed decision-making".

[0026] In S203, the positive word ratio information is generated according to the number of positive word information and the number of to-be-classified word information, and the negative word ratio information is generated according to the number of negative word information and the number of to-be-classified word information.

[0027] Specifically, after the terminal device determines the positive word information and the negative word information, the terminal device can generate the positive word ratio information according to the number of positive word information and the number of to-be-classified word information, and generate the negative word ratio information according to the number of negative word information and the number of to-be-classified word information, wherein the positive word ratio information is used to describe the quotient value obtained by dividing the number of positive word information by the number of to-be-classified word information; the negative word ratio information is used to describe the quotient value obtained by dividing the number of negative word information by the number of to-be-classified word information.

[0028] In S204, the positive word ratio information and the negative word ratio information are compared.

[0029] Specifically, after the terminal device generates the positive word ratio information and the negative word ratio information, the terminal device can compare the positive word ratio information and the negative word ratio information.

[0030] In S205, if the positive word ratio information is greater than the negative word ratio information, it is determined that the article comment information is positive comment information.

[0031] Specifically, if the positive word ratio information is greater than the negative word ratio information, the terminal device can effectively determine that the article comment information is positive comment information.

[0032] In S206, if the positive word ratio information is less than the negative word ratio information, it is determined that the article comment information is negative comment information.

[0033] Specifically, if the positive word ratio information is less than the negative word ratio information, the terminal device can effectively determine that the article comment information is negative comment information.

[0034] In S207, if the positive word ratio information is equal to the negative word ratio information, it is determined that the article comment information is neutral comment information.

[0035] Specifically, if the positive word ratio information is equal to the negative word ratio information, the terminal device can effectively determine that the article comment information is neutral comment information.

[0036] In S300, generate financial risk prediction information according to the public opinion article set information and the article comment information.

[0037] Specifically, after the terminal device acquires the public opinion article set information and the article comment information, the terminal device can effectively generate the financial risk prediction information according to the public opinion article set information and the article comment information, so as to effectively predict whether the target enterprise is likely to have a financial risk, greatly improve the prediction reliability and analysis value of the financial risk, and assist the financial institutions to take preventive measures in advance to reduce potential losses.

[0038] In some possible implementation manners, in order to achieve the generation of the financial risk prediction information, refer to Figure 3 , the step S300 includes but is not limited to the following steps: In S310, generate positive evaluation quantity information according to the total quantity of the positive comment information corresponding to each piece of public opinion article set information, and generate negative evaluation quantity information according to the total quantity of the negative comment information corresponding to each piece of public opinion article set information.

[0039] Specifically, the terminal device can efficiently generate the positive evaluation quantity information according to the total quantity of the positive comment information corresponding to each piece of public opinion article set information, and efficiently generate the negative evaluation quantity information according to the total quantity of the negative comment information corresponding to each piece of public opinion article set information, where the positive evaluation quantity information is used to describe the total quantity obtained by adding the positive comment information corresponding to each piece of public opinion article set information, and the negative evaluation quantity information is used to describe the total quantity obtained by adding the negative comment information corresponding to each piece of public opinion article set information.

[0040] In S320, compare the positive evaluation quantity information and the negative evaluation quantity information.

[0041] Specifically, after the terminal device generates the positive evaluation quantity information and the negative evaluation quantity information, the terminal device can compare the positive evaluation quantity information and the negative evaluation quantity information.

[0042] In S330, if the positive evaluation quantity information is greater than the negative evaluation quantity information, determine that the financial risk prediction information is low-risk prediction information.

[0043] Specifically, if the positive evaluation quantity information is greater than the negative evaluation quantity information, it indicates that the target enterprise is biased towards positive in the public opinion, and therefore the terminal device can determine that the financial risk prediction information is low-risk prediction information, where the low-risk prediction information is used to describe that the target enterprise has a low probability of having a financial risk.

[0044] In S340, if the positive evaluation quantity information is less than or equal to the negative evaluation quantity information, total browsing quantity information is generated according to the total number of the browsing quantity information corresponding to each public opinion article set information.

[0045] Specifically, if the positive evaluation quantity information is less than or equal to the negative evaluation quantity information, it indicates that the target enterprise is not positive in the public opinion trend, and therefore the terminal device can generate total browsing quantity information according to the total number of the browsing quantity information corresponding to each public opinion article set information, wherein the total browsing quantity information is used to describe the sum value obtained by adding the browsing quantity information corresponding to each public opinion article set information.

[0046] In S350, the total browsing quantity information is compared with the preset browsing quantity threshold information.

[0047] Specifically, after the terminal device generates the total browsing quantity information, the terminal device can compare the total browsing quantity information with the preset browsing quantity threshold information, wherein the specific value of the browsing quantity threshold information is a custom value, and the specific value of the browsing quantity threshold information can be 500, 1000 or 3000.

[0048] In S360, if the total browsing quantity information is less than the browsing quantity threshold information, it is determined that the financial risk prediction information is medium risk prediction information.

[0049] Specifically, if the total browsing quantity information is less than the browsing quantity threshold information, it indicates that the public opinion attention of the target enterprise is low, and therefore the terminal device can determine that the financial risk prediction information is medium risk prediction information, wherein the medium risk prediction information is used to describe that the target enterprise has a medium probability of financial risk.

[0050] In S370, if the total browsing quantity information is greater than or equal to the browsing quantity threshold information, it is determined that the financial risk prediction information is high risk prediction information.

[0051] Specifically, if the total browsing quantity information is greater than or equal to the browsing quantity threshold information, it indicates that the public opinion attention of the target enterprise is high, and therefore the terminal device can determine that the financial risk prediction information is high risk prediction information, wherein the high risk prediction information is used to describe that the target enterprise has a high probability of financial risk.

[0052] In some possible implementation manners, in order to further improve the reliability of the financial risk, please refer to Figure 4 If it is determined that the financial risk prediction information is low risk prediction information, after step S300, the method further includes but is not limited to the following steps: In S400, based on the first enterprise name information, second enterprise name information corresponding to a plurality of cooperative enterprises is obtained.

[0053] Specifically, the terminal device can acquire, based on the first enterprise name information, second enterprise name information corresponding to a plurality of cooperative enterprises based on big data technology, wherein the cooperative enterprises are used to describe other enterprises having a cooperative relationship with the target enterprise, such as suppliers or consignees of the target enterprise.

[0054] In S410, financial risk prediction information corresponding to each cooperative enterprise is determined based on the second enterprise name information.

[0055] Specifically, after the terminal device acquires the second enterprise name information, the terminal device can determine financial risk prediction information corresponding to each cooperative enterprise based on the second enterprise name information, wherein the determination of the financial risk prediction information corresponding to each cooperative enterprise can refer to similar content in the above step S300, and thus is not described in detail.

[0056] In S420, if the financial risk prediction information corresponding to a specified number of cooperative enterprises is high-risk prediction information, the financial risk prediction information of the target enterprise is updated to medium-risk prediction information.

[0057] Specifically, if the financial risk prediction information corresponding to a specified number of cooperative enterprises is high-risk prediction information, it indicates that the target enterprise is cooperating with an enterprise that has a relatively high probability of financial risk outbreak, and thus the terminal device can update the financial risk prediction information of the target enterprise to medium-risk prediction information, wherein the specified number is a self-defined value, such as 10 or 20.

[0058] In some possible implementation manners, in order to further improve the reliability of the financial risk, please refer to Figure 5 If it is determined that the financial risk prediction information is medium-risk prediction information, after step S300, the method further includes but is not limited to the following steps: In S500, medium-risk duration information of the target enterprise is acquired.

[0059] Specifically, the terminal device can acquire medium-risk duration information of the target enterprise, wherein the medium-risk duration information is used to describe a duration when the financial risk prediction information of the target enterprise is medium-risk prediction information, i.e., a time period during which the financial risk prediction information of the target enterprise is medium-risk prediction information.

[0060] In S510, if the medium-risk duration information is greater than preset duration threshold information, it is determined whether the number of public opinion articles at a medium-risk starting time is less than the number of public opinion articles at a medium-risk ending time.

[0061] Specifically, if the medium risk duration information is greater than preset duration threshold information, the terminal device can determine whether the number of public opinion articles at the medium risk starting time is less than the number of public opinion articles at the medium risk ending time, where the duration threshold information is a self-defined value, such as one month or six months; the medium risk starting time is used to describe the starting time of the medium risk duration information, and the medium risk ending time is used to describe the ending time of the medium risk duration information; when the financial risk prediction information of the target enterprise is still the medium risk prediction information, the medium risk ending time is the current time.

[0062] In S520, if the number of public opinion articles at the medium risk starting time is less than the number of public opinion articles at the medium risk ending time, the financial risk prediction information of the target enterprise is updated to high risk prediction information.

[0063] Specifically, if the number of public opinion articles at the medium risk starting time is less than the number of public opinion articles at the medium risk ending time, it indicates that the public opinion attention degree of the target enterprise has increased, and therefore the terminal device can update the financial risk prediction information of the target enterprise to high risk prediction information.

[0064] The implementation principle of the financial risk control method based on big data in the embodiments of the present application is as follows: the terminal device can first acquire first enterprise name information of a target enterprise, then quickly acquire public opinion article set information of the target enterprise and article comment information corresponding to the public opinion article set information based on the first enterprise name information, and finally effectively generate financial risk prediction information according to the public opinion article set information and the article comment information, so as to effectively predict whether the target enterprise is likely to have a financial risk, greatly improve the prediction reliability of the financial risk, and effectively assist financial institutions to take preventive measures in advance.

[0065] It should be noted that the size of the serial number of each step in the above embodiments does not mean the execution order, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0066] The embodiments of the present application also provide a financial risk control system based on big data. For the convenience of description, only the parts related to the present application are shown, as shown in Figure 6 The system 60 includes: A first enterprise name information acquisition module 61 is configured to acquire first enterprise name information of a target enterprise. A public opinion article set information acquisition module 62 is configured to acquire public opinion article set information of the target enterprise and article comment information corresponding to the public opinion article set information based on the first enterprise name information, where the public opinion article set information includes a plurality of public opinion article information. The financial risk prediction information generation module 63 is configured to generate the financial risk prediction information according to the public opinion article set information and the article comment information.

[0067] Optionally, the system 60 further comprises: The to-be-classified word information generation module is configured to, for each article comment information: perform word segmentation processing on the article comment information based on a preset positive maximum word segmentation algorithm, and generate a plurality of to-be-classified word information. The word information determination module is configured to: determine positive word information by performing classification processing on the plurality of to-be-classified word information based on a dictionary matching algorithm and a preset positive dictionary set information, and determine negative word information by performing classification processing on the plurality of to-be-classified word information based on the dictionary matching algorithm and a preset negative dictionary set information. The word ratio information generation module is configured to: generate positive word ratio information according to the number of the positive word information and the number of the to-be-classified word information, and generate negative word ratio information according to the number of the negative word information and the number of the to-be-classified word information. The word ratio information comparison module is configured to compare the positive word ratio information and the negative word ratio information. The positive comment information determination module is configured to determine that the article comment information is positive comment information if the positive word ratio information is greater than the negative word ratio information. The negative comment information determination module is configured to determine that the article comment information is negative comment information if the positive word ratio information is less than the negative word ratio information. The neutral comment information determination module is configured to determine that the article comment information is neutral comment information if the positive word ratio information is equal to the negative word ratio information.

[0068] Optionally, the financial risk prediction information generation module 63 comprises: The evaluation quantity information generation submodule is configured to generate positive evaluation quantity information according to the total number of the positive comment information corresponding to each public opinion article set information, and generate negative evaluation quantity information according to the total number of the negative comment information corresponding to each public opinion article set information. The evaluation quantity information comparison submodule is configured to compare the positive evaluation quantity information and the negative evaluation quantity information. The low-risk prediction information determination submodule is configured to determine that the financial risk prediction information is low-risk prediction information if the positive evaluation quantity information is greater than the negative evaluation quantity information. The total browsing quantity information generation submodule is configured to, if the positive evaluation quantity information is less than or equal to the negative evaluation quantity information, generate total browsing quantity information according to the total number of the browsing quantity information corresponding to each public opinion article set information. Total browse information comparison submodule: used for comparing the total browse information with preset browse threshold information; Medium risk prediction information determination submodule: used for determining the financial risk prediction information as medium risk prediction information if the total browse information is less than the browse threshold information; High risk prediction information determination submodule: used for determining the financial risk prediction information as high risk prediction information if the total browse information is greater than or equal to the browse threshold information.

[0069] Optionally, if the financial risk prediction information is determined as low risk prediction information, the system 60 further comprises: Second enterprise name information acquisition module: used for acquiring second enterprise name information corresponding to the plurality of cooperative enterprises based on the first enterprise name information; Financial risk prediction information determination module: used for determining financial risk prediction information corresponding to each cooperative enterprise based on the second enterprise name information; Medium risk prediction information update module: used for updating the financial risk prediction information of the target enterprise as medium risk prediction information if there are a specified number of cooperative enterprises corresponding to high risk prediction information.

[0070] Optionally, if the financial risk prediction information is determined as medium risk prediction information, the system 60 further comprises: Medium risk duration information acquisition module: used for acquiring medium risk duration information of the target enterprise, wherein the medium risk duration information is used to describe the duration when the financial risk prediction information of the target enterprise is medium risk prediction information; Public opinion article quantity information judgment module: used for judging whether the public opinion article quantity information at a medium risk starting time is less than the public opinion article quantity information at a medium risk ending time if the medium risk duration information is greater than preset duration threshold information, wherein the medium risk starting time is used to describe the starting time of the medium risk duration information, and the medium risk ending time is used to describe the ending time of the medium risk duration information; High risk prediction information update module: used for updating the financial risk prediction information of the target enterprise as high risk prediction information if the public opinion article quantity information at the medium risk starting time is less than the public opinion article quantity information at the medium risk ending time.

[0071] It should be noted that the information interaction, execution process and the like between the above modules are based on the same concept as the method embodiments of the present application, and the specific functions and the technical effects brought by the same can be referred to the method embodiments part, which will not be described here.

[0072] The present application also provides a terminal device, such as Figure 7As shown, the terminal device 70 of this embodiment includes a processor 71, a memory 72, and a computer program 73 stored in the memory 72 and executable on the processor 71. The processor 71 implements the steps in the above financial risk control method embodiments when executing the computer program 73, for example Figure 1 the steps S100 to S300 shown above; or the processor 71 implements the functions of the modules in the above apparatus when executing the computer program 73, for example Figure 6 the functions of the modules 61 to 63 shown above.

[0073] The terminal device 70 can be a desktop computer, a notebook computer, a palm computer, a cloud server, and the like. The terminal device 70 includes but is not limited to the processor 71 and the memory 72. Those skilled in the art can understand that Figure 7 The terminal device 70 is only an example and does not constitute a limitation on the terminal device 70, which can include more or fewer components than shown, or combine some components, or include different components, for example, the terminal device 70 can also include an input / output device, a network access device, a bus, and the like.

[0074] The processor 71 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0075] The memory 72 can be an internal storage unit of the terminal device 70, for example, a hard disk or a memory of the terminal device 70. The memory 72 can also be an external storage device of the terminal device 70, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal device 70. Further, the memory 72 can include both the internal storage unit and the external storage device of the terminal device 70. The memory 72 can also store the computer program 73 and other programs and data required by the terminal device 70. The memory 72 can also be used to temporarily store data that has been output or is about to be output.

[0076] An embodiment of the present application further provides a computer readable storage medium, which stores a computer program. The computer program, when executed by a processor, can implement the steps of each method embodiment described above. The computer program includes computer program code, which can be in the form of source code, object code, executable code, or some intermediate form. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, software distribution medium, and the like.

[0077] The above are preferred embodiments of the present application, which do not limit the protection scope of the present application. Any equivalent changes made according to the methods, principles and structures of the present application should be covered within the protection scope of the present application.

Claims

1. A financial risk control method based on big data, characterized in that, The method includes: Obtain the target company's primary company name information; Based on the first enterprise name information, obtain the public opinion article collection information of the target enterprise and the article comment information corresponding to the public opinion article collection information, wherein the public opinion article collection information includes multiple public opinion article information; Based on the information from the aforementioned collection of public opinion articles and article comments, financial risk prediction information is generated.

2. The method according to claim 1, characterized in that, After obtaining the public opinion article collection information of the target enterprise and the article comment information corresponding to the public opinion article collection information based on the first enterprise name information, the method further includes: For each of the article comment information: based on the preset positive maximum word segmentation algorithm, the article comment information is segmented into words to generate multiple words to be classified; Based on the dictionary matching algorithm and the preset positive dictionary set information, multiple words to be classified are classified to determine positive words. Based on the dictionary matching algorithm and the preset negative dictionary set information, multiple words to be classified are classified to determine negative words. Based on the number of positive word information and the number of word information to be classified, positive word ratio information is generated, and based on the number of negative word information and the number of word information to be classified, negative word ratio information is generated. Compare the positive word ratio information and the negative word ratio information; If the ratio of positive words is greater than the ratio of negative words, then the article comment information is determined to be positive comment information. If the ratio of positive words is less than the ratio of negative words, then the article comment information is determined to be negative comment information. If the positive word ratio information is equal to the negative word ratio information, then the article comment information is determined to be neutral comment information.

3. The method according to claim 2, characterized in that, The step of generating financial risk prediction information based on the information from the public opinion article collection and article comment information includes: Based on the total number of positive comments corresponding to each of the aforementioned public opinion article sets, positive evaluation quantity information is generated, and based on the total number of negative comments corresponding to each of the aforementioned public opinion article sets, negative evaluation quantity information is generated. Compare the number of positive reviews with the number of negative reviews; If the number of positive evaluations is greater than the number of negative evaluations, then the financial risk prediction information is determined to be low-risk prediction information. If the number of positive reviews is less than or equal to the number of negative reviews, then the total number of pageviews is generated based on the total number of pageviews corresponding to each of the public opinion article sets. Compare the total pageview information with the preset pageview threshold information; If the total pageviews are less than the pageview threshold, the financial risk prediction information is determined to be medium-risk prediction information. If the total pageviews are greater than or equal to the pageview threshold, then the financial risk prediction information is determined to be high-risk prediction information.

4. The method according to claim 3, characterized in that, If the financial risk prediction information is determined to be low-risk prediction information, then after generating the financial risk prediction information based on the public opinion article set information and article comment information, the method further includes: Based on the first enterprise name information, obtain the second enterprise name information corresponding to multiple cooperating enterprises; Based on the second company name information, determine the financial risk prediction information corresponding to each of the aforementioned cooperative companies; If a specified number of the cooperating companies have financial risk prediction information that is high-risk, then the financial risk prediction information of the target company will be updated to medium-risk.

5. The method according to claim 3, characterized in that, If the financial risk prediction information is determined to be medium-risk prediction information, then after generating the financial risk prediction information based on the public opinion article set information and article comment information, the method further includes: Obtain the medium-risk duration information of the target enterprise, wherein the medium-risk duration information is used to describe the duration when the financial risk prediction information of the target enterprise is medium-risk prediction information; If the duration of the medium risk is greater than the preset duration threshold, then it is determined whether the number of public opinion articles at the start time of the medium risk is less than the number of public opinion articles at the end time of the medium risk. Here, the start time of the medium risk is used to describe the start time of the duration of the medium risk, and the end time of the medium risk is used to describe the end time of the duration of the medium risk. If the number of public opinion articles at the start of the medium-risk period is less than the number of public opinion articles at the end of the medium-risk period, then the financial risk prediction information of the target enterprise will be updated to high-risk prediction information.

6. A financial risk control system based on big data, characterized in that, The system includes: First Enterprise Name Information Acquisition Module: Used to acquire the first enterprise name information of the target enterprise; The public opinion article collection information acquisition module is used to acquire the public opinion article collection information of the target enterprise and the article comment information corresponding to the public opinion article collection information based on the first enterprise name information, wherein the public opinion article collection information includes multiple public opinion article information; Financial risk prediction information generation module: used to generate financial risk prediction information based on the information in the aforementioned public opinion article set and article comment information.

7. The system according to claim 6, characterized in that, The system also includes: The unclassified word information generation module is used to process the article comment information based on a preset positive maximum word segmentation algorithm to generate multiple unclassified word information. The word information determination module is used to classify multiple words to be classified based on a dictionary matching algorithm and a preset positive dictionary set to determine positive word information, and to classify multiple words to be classified based on the dictionary matching algorithm and a preset negative dictionary set to determine negative word information. Word ratio information generation module: used to generate positive word ratio information based on the number of positive word information and the number of word information to be classified, and to generate negative word ratio information based on the number of negative word information and the number of word information to be classified; Word ratio information comparison module: used to compare the positive word ratio information and the negative word ratio information; Positive comment information determination module: used to determine the article comment information as positive comment information if the ratio of positive words is greater than the ratio of negative words; Negative comment information determination module: used to determine the article comment information as negative comment information if the positive word ratio information is less than the negative word ratio information; Neutral comment information determination module: used to determine the article comment information as neutral comment information if the positive word ratio information is equal to the negative word ratio information.

8. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 5.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 5.

Images