Intelligent decision-making method and system based on industrial big data

Abstract

The invention relates to the technical field of commercial big data intelligent decision making, and discloses an intelligent decision making method based on industrial big data, and the method comprises the steps: obtaining business ticket data; preprocessing the business ticket data; extracting identification features of the preprocessed business ticket data; performing risk assessment according to the identification features of the business ticket data; and giving decision suggestions according to the identification features and risk assessment of the business ticket data. According to the method and the device, the reasonable decision-making suggestions can be given according to the identification features of the business ticket data and the risk assessment result, so that a decision maker can visually select the decision-making suggestions, the energy consumed by the decision maker is reduced, the given decision-making suggestions are relatively comprehensive and accurate, and the loss of an enterprise is reduced. The invention further discloses an intelligent decision-making system based on the industrial big data.

Description

Technical Field

[0001] The present application relates to the technical field of commercial big data intelligent decision-making, and specifically to an intelligent decision-making method and system based on industrial big data. Background Art

[0002] In modern commercial activities, commercial bills, such as invoices, order tickets, and commercial bills, are securities that reflect creditor-debtor relationships and can be used as a means of payment. In a broad sense, bills include various securities and certificates, such as stocks, treasury bonds, corporate bonds, bills of lading, etc.

[0003] In the related technology, there is a method of building a large model by collecting information of the commercial bills of enterprises, and processing and analyzing the collected commercial bills through the large model, and evaluating the risks of the corresponding enterprises in combination with the processed and analyzed commercial bill information, and then presenting the results of the risk evaluation to the decision makers. The decision makers make decisions based on the results of the data processing and analysis of the commercial bills and the results of the risk evaluation.

[0004] In the process of implementing the embodiments of the present disclosure, it is found that there are at least the following problems in the related art:

[0005] Corporate decision makers make decisions based on the results of analysis and risk assessment, which will consume a lot of their energy. Moreover, since their energy is limited and they cannot fully understand the existence of risks, the decisions they make may contain misjudgments and cause losses to the company.

[0006] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present application, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0007] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical components or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.

[0008] The disclosed embodiments provide an intelligent decision-making method and system based on industrial big data, which gives reasonable decision suggestions according to the identification features of commercial bill data and risk assessment results, so that decision makers can intuitively select decision suggestions, reducing the energy consumed by decision makers, and the decision suggestions given are more comprehensive and accurate, reducing the losses of enterprises.

[0009] In some embodiments, the intelligent decision-making method based on industrial big data includes:

[0010] Get commercial bill data;

[0011] Pre-process the commercial bill data;

[0012] Extract identification features of pre-processed commercial bill data;

[0013] Conduct risk assessment based on the identification features of commercial bill data;

[0014] Provide decision-making recommendations based on the identification features and risk assessment of commercial bill data.

[0015] Optionally, obtaining the commercial bill data includes: obtaining the commercial bill data associated with the target enterprise from the internal system of the target enterprise and the external database.

[0016] Optionally, obtaining the commercial bill data associated with the target enterprise in the internal system and external database of the target enterprise includes: obtaining the commercial bill data associated with the target enterprise in the internal system and external database of the target enterprise within a set time period.

[0017] Optionally, the commercial bill data is preprocessed, including: data cleaning, data type conversion, data normalization and standardization, data transformation and data encoding of the commercial bill data.

[0018] Optionally, extracting identification features of the preprocessed commercial bill data includes: performing multi-dimensional analysis on the preprocessed commercial bill data to extract key identification features of the preprocessed commercial bill data.

[0019] Optionally, before performing multi-dimensional analysis on the pre-processed commercial bill data, the process includes: modeling the pre-processed commercial bill data, and analyzing the modeled data model.

[0020] Optionally, risk assessment is performed based on identification features of the commercial bill data, including: assessing the risk of the commercial bill data through a machine learning model.

[0021] Optionally, after evaluating the risk of the commercial bill data through a machine learning model, the process also includes: quantifying the risk assessment results into risk levels or risk probabilities and displaying them to decision makers.

[0022] Optionally, the decision suggestions provided include: one or more of decision suggestions on credit risk assessment, decision suggestions on management risk control, and decision suggestions on interest rate risk management.

[0023] In some embodiments, the intelligent decision-making system based on industrial big data includes: a data collection module, a data processing module, a feature extraction module, a risk assessment module and a decision suggestion module. The data collection module is configured to obtain commercial bill data; the data processing module is configured to pre-process the commercial bill data; the feature extraction module is configured to extract the identification features of the pre-processed commercial bill data; the risk assessment module is configured to perform risk assessment based on the identification features of the commercial bill data; and the decision suggestion module is configured to give decision suggestions based on the identification features of the commercial bill data and the risk assessment.

[0024] The intelligent decision-making method and system based on industrial big data provided by the embodiments of the present disclosure can achieve the following technical effects:

[0025] By collecting commercial bill data, pre-processing the commercial bill data, extracting identification features and risk assessment, and then giving reasonable decision-making suggestions based on the identification features of the commercial bill data and the risk assessment results, decision makers can intuitively choose decision suggestions, reducing the energy spent by decision makers. The decision suggestions given are more comprehensive and accurate, reducing the losses of the enterprise.

[0026] The above general description and the following description are exemplary and explanatory only and are not intended to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] One or more embodiments are exemplarily described by corresponding drawings, which do not limit the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements, and the drawings do not constitute a scale limitation, and wherein:

[0028] Figure 1 is a schematic diagram of an intelligent decision-making method based on industrial big data provided by an embodiment of the present disclosure;

[0029] Figure 2 is a schematic diagram of another intelligent decision-making method based on industrial big data provided by an embodiment of the present disclosure;

[0030] Figure 3 is a schematic diagram of another intelligent decision-making method based on industrial big data provided by an embodiment of the present disclosure;

[0031] Figure 4 It is a schematic diagram of an intelligent decision-making system based on industrial big data provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0032] In order to be able to understand the features and technical contents of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure is described in detail below in conjunction with the accompanying drawings. The attached drawings are for reference only and are not used to limit the embodiments of the present disclosure. In the following technical description, for the convenience of explanation, a full understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, to simplify the drawings, well-known structures and devices can be simplified for display.

[0033] The terms "first", "second", etc. in the specification and claims of the disclosed embodiments and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged where appropriate to describe the disclosed embodiments here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions.

[0034] Unless otherwise stated, the term "plurality" means two or more.

[0035] The term "correspondence" may refer to an association relationship or a binding relationship. The correspondence between A and B means that there is an association relationship or a binding relationship between A and B.

[0036] Combination Figure 1 As shown, in some embodiments, the intelligent decision-making method based on industrial big data includes:

[0037] Intelligent decision-making methods based on industrial big data include:

[0038] S01, obtain commercial bill data;

[0039] S02, pre-processing the commercial bill data;

[0040] S03, extracting identification features of the pre-processed commercial bill data;

[0041] S04, conduct risk assessment based on the identification features of commercial bill data;

[0042] S05, provide decision recommendations based on the identification features and risk assessment of commercial bill data.

[0043] By adopting the intelligent decision-making method based on industrial big data provided by the embodiment of the present disclosure, commercial bill data is collected, pre-processed, identification features are extracted, and risk is assessed. Then, reasonable decision suggestions are given according to the identification features of the commercial bill data and the risk assessment results, so that decision makers can intuitively choose decision suggestions, reducing the energy consumed by decision makers. The decision suggestions given are more comprehensive and accurate, thereby reducing the losses of enterprises.

[0044] In one embodiment, obtaining the commercial bill data includes: obtaining the commercial bill data associated with the target enterprise from the internal system of the target enterprise and the external database. In this way, when cooperating with the target enterprise, by obtaining the commercial bill data associated with the target enterprise from the internal system of the target enterprise or the external database, the obtained commercial bill data is more comprehensive and can cover most of the business of the target enterprise, so that the decision-making suggestions given are more accurate.

[0045] It can be understood that the target enterprise is the enterprise that the decision maker is going to cooperate with, and there are one or more target enterprises.

[0046] Exemplarily, when it is necessary to obtain the commercial bill data of the target enterprise, the system obtains permission to enter the internal system and external database of the target enterprise, and obtains the commercial bill data associated with the target enterprise in the internal system and external database of the target enterprise.

[0047] Optionally, obtaining the commercial bill data associated with the target enterprise from the internal system and external database of the target enterprise includes: obtaining the commercial bill data associated with the target enterprise from the internal system and external database of the target enterprise within a set time period. In this way, the commercial bill data of the target enterprise within a certain time period can better reflect the real situation of the target enterprise, so by obtaining the commercial bill data of the target enterprise within the set time period, more accurate decision suggestions can be made.

[0048] Optionally, the time period is set to 5 years. In this way, by obtaining the commercial bill data of the target enterprise within 5 years, the real situation of the target enterprise can be accurately reflected.

[0049] It can be understood that obtaining the commercial bill data of the target enterprise within a set period of time means: calculating from the date of acquisition, the commercial bill data of the target enterprise within the previous 5 years.

[0050] In another embodiment, obtaining the commercial bill data includes: retrieving the commercial bill data about the target enterprise stored in the database of the system. In this way, the target enterprise is a settled enterprise of the system, and the system can obtain the commercial bill data of the target enterprise in real time through the settlement agreement and store it in the database, and when it is necessary to obtain the commercial bill data of the target enterprise, retrieve the stored commercial bill data about the target enterprise from the database.

[0051] In one embodiment, the commercial bill data is preprocessed, including: data cleaning, data type conversion, data normalization and standardization, data transformation, and data encoding. In this way, the effect of preprocessing the acquired commercial bill data is improved by performing a series of operations such as data cleaning, data deduplication, data type conversion, data normalization and standardization, data transformation, and data encoding on the acquired commercial bill data.

[0052] Optionally, the commercial invoice data is cleaned, including: processing missing values, processing outliers, and deleting duplicate records.

[0053] For example, fillna() function is used to fill missing values ​​in DataFrame, and you can choose to fill them with 0, mean, median or other specific values; identify and handle outliers through statistical methods (such as Z-score, IQR) or domain knowledge. For example, Boolean indexing can be used to filter rows in DataFrame that meet specific conditions and only retain data within the normal range. Use drop_duplicates() function to delete duplicate rows in DataFrame to avoid model bias.

[0054] Optionally, convert the data type of the commercial invoice data, including: checking the type of the data set, using type(data) to check the data set type, and converting it as needed.

[0055] For example, use the astype() function to convert a column to an integer type or other required type.

[0056] For example, the commercial bill data is normalized and standardized using methods such as MinMaxScaler and MaxAbsScaler to normalize the data so that the data is within a unified range for easy comparison and analysis. StandardScaler is used for Z-score standardization so that the mean of the data is 0 and the standard deviation is 1, which is suitable for models that are sensitive to data distribution.

[0057] Optionally, the bill data is transformed, including logarithmic transformation and quantile transformation. In this way, the skewed data is transformed by natural logarithm to reduce the skewness of the data and make the data closer to normal distribution. QuantileTransformer is used to perform quantile transformation to map the quantiles of the data to the target distribution, such as uniform distribution or normal distribution, which is suitable for nonlinear transformation to reduce skewness or change distribution characteristics.

[0058] Optionally, the commercial invoice data is encoded, including: label encoding the categorical variables, mapping each category to a unique integer.

[0059] In the disclosed embodiment, the above-mentioned method is used to preprocess the commercial bill data, which can improve the performance of the model. Through the preprocessing steps, the performance of the subsequent analysis and model can be improved, making the model results more accurate and reliable. It can also reduce the risk of data leakage. By encapsulating all preprocessing steps in the pipeline, the risk of data leakage can be reduced and the security of data processing can be improved. It can also improve the quality of data. Preprocessing helps to improve the overall quality of data, including the integrity, consistency and accuracy of the data, and provide a more solid data foundation for decision-making. It can also achieve automation and intelligence. With the development of technology, the preprocessing steps can gradually achieve automation and intelligence, improve work efficiency, and reduce human errors.

[0060] In one embodiment, extracting identification features of pre-processed commercial bill data includes: performing multi-dimensional analysis on the pre-processed commercial bill data and extracting key identification features of the pre-processed commercial bill data. In this way, by performing multi-dimensional analysis and feature extraction on the pre-processed commercial bill data, valuable information can be effectively extracted from the commercial bill data, and a solid foundation can be provided for subsequent risk assessment and decision-making recommendations, thereby improving the accuracy of risk assessment and decision-making recommendations.

[0061] Exemplarily, multi-dimensional analysis of pre-processed commercial bill data means: machine learning algorithms, such as principal component analysis (PCA), t-SNE and UMAP, can be used to reduce the dimension of commercial bill data and extract key features to facilitate multi-dimensional analysis. These methods help to reduce data complexity while retaining the most important information; extracting key identification features of pre-processed commercial bill data means: by parsing the data domain structure object, reading the start and end keywords, dividing the bill content into corresponding extraction areas according to these keywords, reducing the extraction range, and improving the extraction efficiency. Then, an extraction expression is generated to describe the context structure information where the extraction keyword is located, and the expression is matched in the divided extraction domain to output data, which can improve the accuracy of the extracted key identification features.

[0062] Optionally, before performing multi-dimensional analysis on the pre-processed commercial bill data, the pre-processed commercial bill data is modeled and the modeled data model is analyzed. This helps to standardize bill data of different formats and lays a foundation for subsequent feature extraction. It also helps to identify key information areas in the bill and prepare for accurate extraction.

[0063] Exemplarily, modeling the preprocessed commercial bill data means: dividing the commercial bill data to be extracted to form multiple data domains, creating a data model, and storing the created data model in the model library; analyzing the modeled data model means: deserializing the created data model into several data domain structures, each structure containing a set of data domain start and end keywords and a specified extraction point feature value array.

[0064] In the disclosed embodiments, through the above-mentioned feature extraction method, key information can be quickly and accurately extracted from commercial bills, reducing manual intervention and improving the efficiency and accuracy of data processing. It can also reduce maintenance costs. Due to the use of modeling and machine learning methods, when the format of the bill changes, only the data model needs to be updated without changing the program algorithm, which greatly reduces the cost of software upgrades and maintenance. It can also enhance the generalization ability of the model. Through multi-dimensional analysis and feature extraction, a more robust model can be built to enhance the model's generalization ability for different bill formats. The extracted features can be used for further data mining and analysis, such as customer behavior analysis, risk assessment, etc., to provide support for business decisions.

[0065] In one embodiment, risk assessment is performed based on identification features of commercial bill data, including: assessing the risk of commercial bill data through a machine learning model. In this way, the risk assessment result obtained through the machine learning model is more accurate and the efficiency of obtaining the risk assessment result is higher.

[0066] Exemplarily, the system uses machine learning models, such as random forests, neural networks, etc., to assess the risks of commercial bill data.

[0067] Optionally, after the risk of the commercial bill data is assessed by the machine learning model, the process further includes: quantifying the risk assessment results into risk levels or risk probabilities and presenting them to decision makers. In this way, by quantifying the risk assessment results into risk levels or risk probabilities and presenting the risk levels or risk probabilities to decision makers, decision makers can more intuitively understand the risk assessment results, which is convenient for decision makers to understand. Decision makers can make accurate judgments based on the displayed results, and thus select decisions with relatively low risks from the given decision suggestions for execution.

[0068] For example, when the risk assessment results are quantified into risk levels, the risk levels can be divided into three levels: high, medium, and low; when the risk assessment results are quantified into risk probabilities, a probability map can be generated according to the occurrence of the risk.

[0069] In one embodiment, the decision suggestions provided include: one or more of the decision suggestions on credit risk assessment, the decision suggestions on management risk control, and the decision suggestions on interest rate risk management. In this way, since the risk assessment results are diversified, the credit risk of the target enterprise, the management risk of the target enterprise, and the interest rate risk of the fiscal policy can all affect the decision suggestions. Therefore, one or more of the decision suggestions on credit risk assessment, the decision suggestions on management risk control, and the decision suggestions on interest rate risk management are provided based on the identification characteristics of the commercial bill data and the risk assessment results, so that the decision maker can intuitively understand the various risks and the corresponding decision suggestions, so that the decision maker can make more accurate decisions and reduce the risks of decisions.

[0070] Optionally, the decision suggestions given include: decision suggestions on credit risk assessment. In this way, since the payment of commercial acceptance bills is based on the credit of commercial enterprises, there is a risk of non-payment. Therefore, when making decisions, the credit status and payment ability of the accepting enterprise should be evaluated to avoid accepting commercial acceptance bills with unsecured credit. Therefore, decision suggestions are given based on the results of the credit risk assessment of the target enterprise.

[0071] Optionally, the decision suggestions given include: decision suggestions on management risk control. In this way, since the commercial bill data has the characteristics of textual meaning and formality, improper operation may affect the bill rights. When making decisions, the operation should be standardized and timely to reduce management risks.

[0072] Optionally, the decision suggestions given include: decision suggestions on interest rate risk management. In this way, since the value of bills may fluctuate due to factors such as fiscal policy and monetary policy, affecting the discount rate of commercial bills, when making decisions, the impact of interest rate changes on the value of commercial bills should be considered, and corresponding risk management measures should be formulated.

[0073] Optionally, the decision suggestions given also include: one or more of the decision suggestions on policy risk considerations, the decision suggestions on liquidity risk assessment, and the decision suggestions on force majeure risk provision. In this way, policy risk considerations, liquidity risk, and force majeure risk can all affect the decision suggestions. Therefore, one or more of the decision suggestions on policy risk considerations, the decision suggestions on liquidity risk assessment, and the decision suggestions on force majeure risk provision are given based on the identification characteristics of the commercial bill data and the risk assessment results, so that the decision maker can intuitively understand the various risks and the corresponding decision suggestions, so that the decision maker can make more accurate decisions and reduce the risk of decision making.

[0074] Optionally, the decision-making suggestions given also include: decision-making suggestions on policy risk considerations. In this way, since changes in relevant laws, regulations or regulatory policies may affect the transaction and redemption of commercial bills, when making decisions, we should pay close attention to policy trends and prepare strategies to deal with policy changes.

[0075] Optionally, the decision suggestions given also include: decision suggestions on liquidity risk assessment. In this way, since the payment of commercial bills may be affected by factors such as the credit of the accepting entity and monetary policy, liquidity risk may be brought about. When making decisions, the financing ability of the holder of the bill and possible liquidity risks should be evaluated.

[0076] Optionally, the decision-making suggestions given also include: decision-making suggestions for force majeure risk preparation. In this way, force majeure factors such as natural disasters and wars may seriously affect the financial market. When making decisions, force majeure risks should be considered and countermeasures should be formulated.

[0077] Combination Figure 2 As shown, in other embodiments, the intelligent decision-making method based on industrial big data includes:

[0078] Intelligent decision-making methods based on industrial big data include:

[0079] S01, obtain commercial bill data;

[0080] S02, pre-processing the commercial bill data;

[0081] S03, extracting identification features of the pre-processed commercial bill data;

[0082] S04, conduct risk assessment based on the identification features of commercial bill data;

[0083] S05, giving decision suggestions based on the identification features and risk assessment of the commercial bill data;

[0084] S06, calibrate decision recommendations based on historical bill data and market trends.

[0085] By adopting the intelligent decision-making method based on industrial big data provided by the embodiment of the present disclosure, commercial bill data is collected, pre-processed, identification features are extracted, and risk assessment is performed on the commercial bill data, and then reasonable decision suggestions are given based on the identification features of the commercial bill data and the risk assessment results, so that decision makers can intuitively choose decision suggestions and reduce the energy consumed by decision makers. The decision suggestions given are further calibrated and optimized based on historical commercial bill data and market trends, so that the decision suggestions given are more comprehensive and accurate, reducing the losses of enterprises.

[0086] Combination Figure 3 As shown, in other embodiments, the intelligent decision-making method based on industrial big data includes:

[0087] Intelligent decision-making methods based on industrial big data include:

[0088] S01, obtain commercial bill data;

[0089] S02, pre-processing the commercial bill data;

[0090] S03, extracting identification features of the pre-processed commercial bill data;

[0091] S04, conduct risk assessment based on the identification features of commercial bill data;

[0092] S05: Provide decision-making suggestions based on the identification characteristics and risk assessment of commercial bill data

[0093] S07, determine the target decision suggestion and execute it, and send the target decision suggestion to a third-party agency for notarization.

[0094] By adopting the intelligent decision-making method based on industrial big data provided by the embodiment of the present disclosure, commercial bill data is collected, pre-processed, identification features are extracted, and risk assessed, and then reasonable decision-making suggestions are given based on the identification features of the commercial bill data and the risk assessment results, so that decision makers can intuitively choose decision suggestions, reduce the energy consumed by decision makers, make the decision suggestions given more comprehensive and accurate, and reduce the losses of enterprises. With the increasing modernization of the national governance system and governance capabilities, the third-party intervention mechanism in the social stability risk assessment of major decisions has become an inevitable choice for social governance innovation. By introducing third-party institutions, the fairness, scientificity and objectivity of decision-making can be increased.

[0095] Exemplarily, the third-party institution may be a bank or other institution. After the decision maker has determined and implemented the target decision proposal, the target decision proposal will be sent to the third-party institution for notarization to further ensure the smooth implementation of the decision and reduce the risk of the enterprise.

[0096] Combination Figure 4 As shown, in some embodiments, the intelligent decision-making system based on industrial big data includes: a data collection module, a data processing module, a feature extraction module, a risk assessment module and a decision suggestion module. The data collection module is configured to obtain commercial bill data; the data processing module is configured to pre-process the commercial bill data; the feature extraction module is configured to extract the identification features of the pre-processed commercial bill data; the risk assessment module is configured to perform risk assessment based on the identification features of the commercial bill data; and the decision suggestion module is configured to give decision suggestions based on the identification features of the commercial bill data and the risk assessment.

[0097] The intelligent decision-making system based on industrial big data provided by the embodiment of the present disclosure collects commercial bill data, pre-processes the commercial bill data, extracts identification features and conducts risk assessment, and then gives reasonable decision-making suggestions based on the identification features of the commercial bill data and the risk assessment results, so that decision makers can intuitively choose decision suggestions, reducing the energy consumed by decision makers, and the decision suggestions given are more comprehensive and accurate, thereby reducing the losses of enterprises.

[0098] An embodiment of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured to execute the above-mentioned intelligent decision-making method based on industrial big data.

[0099] It can be understood that the above-mentioned computer-readable storage medium is stored in an intelligent decision-making system based on industrial big data.

[0100] The technical solution of the embodiment of the present disclosure can be embodied in the form of a software product, which is stored in a storage medium and includes one or more instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiment of the present disclosure. The aforementioned storage medium may be a non-transient storage medium, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, and other media that can store program codes.

[0101] The above description and the accompanying drawings fully illustrate the embodiments of the present disclosure so that those skilled in the art can practice them. Other embodiments may include structural, logical, electrical, process and other changes. The embodiments represent only possible changes. Unless explicitly required, separate components and functions are optional, and the order of operation may vary. The parts and features of some embodiments may be included in or replace the parts and features of other embodiments. Moreover, the words used in this application are only used to describe the embodiments and are not used to limit the claims. As used in the description of the embodiments and the claims, unless the context clearly indicates, the singular forms of "a", "an" and "the" are intended to include plural forms as well. Similarly, the term "and / or" as used in this application refers to any and all possible combinations of listings containing one or more associated ones. In addition, when used in the present application, the term "comprise" and its variants "comprises" and / or comprising refer to the presence of stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups thereof. In the absence of further restrictions, the elements defined by the sentence "comprising a ..." do not exclude the presence of other identical elements in the process, method or device comprising the elements. In this article, each embodiment may focus on the differences from other embodiments, and the same and similar parts between the various embodiments may refer to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, then the relevant parts can refer to the description of the method part.

[0102] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software may depend on the specific application and design constraints of the technical solution. The technicians may use different methods for each specific application to implement the described functions, but such implementations should not be considered to exceed the scope of the embodiments of the present disclosure. The technicians may clearly understand that, for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above may refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0103] In the embodiments disclosed herein, the disclosed methods and products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units can be only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to implement this embodiment. In addition, each functional unit in the embodiment of the present disclosure may be integrated in a processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit.

[0104] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. An intelligent decision-making method based on industrial big data, characterized in that: include: Get commercial bill data; Pre-process the commercial bill data; Extract identification features of pre-processed commercial bill data; Conduct risk assessment based on the identification features of commercial bill data; Provide decision-making recommendations based on the identification features and risk assessment of commercial bill data.

2. The method according to claim 1, characterized in that Obtain commercial bill data, including: Obtain the commercial bill data associated with the target enterprise from the target enterprise's internal system and external database.

3. The method according to claim 2, characterized in that Obtain the target enterprise's internal system and external databases and the commercial bill data associated with the target enterprise, including: Obtain the commercial bill data associated with the target enterprise from the target enterprise's internal system and external database within a set period of time.

4. The method according to claim 1, characterized in that Preprocess the commercial bill data, including: The commercial bill data is cleaned, data type converted, data normalized and standardized, data transformed and data encoded.

5. The method according to claim 1, characterized in that Extract identification features of pre-processed bill data, including: Perform multi-dimensional analysis on the pre-processed commercial bill data and extract key identification features of the pre-processed commercial bill data.

6. The method according to claim 5, characterized in that Before conducting multi-dimensional analysis on the pre-processed commercial bill data, the following steps should be taken: The preprocessed commercial bill data is modeled and the modeled data model is analyzed.

7. The method according to any one of claims 1 to 6, characterized in that: Risk assessment is performed based on the identification features of commercial bill data, including: Assess the risks of commercial bill data through machine learning models.

8. The method according to claim 7, characterized in that After the risk assessment of commercial bill data is carried out through machine learning models, it also includes: Quantify risk assessment results into risk levels or risk probabilities and present them to decision makers.

9. The method according to any one of claims 1 to 6, characterized in that: Decision-making recommendations include: One or more of: decision recommendations on credit risk assessment, decision recommendations on management risk control, and decision recommendations on interest rate risk management.

10. An intelligent decision-making system based on industrial big data, characterized in that: include: A data collection module is configured to obtain commercial bill data; A data processing module, configured to pre-process the commercial bill data; A feature extraction module, configured to extract identification features of the pre-processed commercial bill data; A risk assessment module, configured to perform risk assessment based on identification features of the commercial bill data; The decision suggestion module is configured to give decision suggestions based on the identification features and risk assessment of the commercial bill data.

Images