A method and apparatus for early warning, an electronic device and a computer readable medium

Abstract

The application discloses a prewarning method and device, electronic equipment and a computer readable medium, relates to the technical field of big data processing, and specifically comprises the following steps: receiving a prewarning request, obtaining a corresponding data source identifier, and then calling a data source corresponding to the data source identifier to obtain to-be-processed data; based on a preset dimension, corresponding dimension features in the to-be-processed data are extracted, and then a business type corresponding to the dimension features is determined; a prewarning program corresponding to the business type is executed to determine a prewarning type corresponding to the dimension features, and then prewarning information is generated and output. The operation of the post-loan prewarning business can be standardized, the possible risks can be pre-judged in advance, and the accuracy and the fund recall rate of the prewarning business are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of big data data processing, and particularly relates to a pre-warning method and device, electronic equipment and a computer readable medium. BACKGROUND

[0002] Most of the existing bank post-loan warning systems do not analyze the business characteristics and current situation of the project during development, so the existing post-loan warning systems often cannot accurately identify the projects that may have problems, and thus cannot make early predictions of risks. SUMMARY

[0003] Therefore, the embodiments of the present application provide a pre-warning method, device, electronic equipment and computer readable medium, which can solve the problem that the existing post-loan warning system often cannot accurately identify the projects that may have problems, and thus cannot make early predictions of risks.

[0004] To achieve the above object, according to an aspect of the embodiments of the present application, a pre-warning method is provided, comprising:

[0005] receiving a pre-warning request, obtaining a corresponding data source identifier, and then calling a data source corresponding to the data source identifier to obtain to-be-processed data;

[0006] extracting corresponding dimension features in the to-be-processed data based on a preset dimension, and then determining a business type corresponding to the dimension features;

[0007] executing a pre-warning program corresponding to the business type to determine a pre-warning type corresponding to the dimension features, and then generating pre-warning information and outputting.

[0008] Optionally, the extracting of the corresponding dimension features in the to-be-processed data based on the preset dimension comprises:

[0009] extracting corresponding first range dimension features in the to-be-processed data based on a first range dimension;

[0010] extracting corresponding second range dimension features in the to-be-processed data based on a second range dimension; wherein,

[0011] the first range corresponding to the first range dimension is greater than the second range corresponding to the second range dimension.

[0012] Optionally, the determining of the business type corresponding to the dimension features comprises:

[0013] grabbing negative public opinion data of the day, and then matching the negative public opinion data with the dimension features, and determining a corresponding business type according to a matching result.

[0014] Optionally, the determining of the business type corresponding to the dimension features according to the matching result comprises:

[0015] In response to the matching result being a match, it is determined that the business type corresponding to the dimension feature is a negative public opinion business;

[0016] In response to the matching result being a mismatch, a preset workflow is obtained to determine a next node, and the next node is transferred to execute matching logic of the next node, and then a business type corresponding to the dimension feature is determined according to an execution result of the matching logic.

[0017] Optionally, obtaining the preset workflow comprises:

[0018] The monitoring model is called to obtain a preset workflow in the monitoring model.

[0019] Optionally, generating and outputting the early warning information comprises:

[0020] The number of the second range contained in the first range is determined.

[0021] According to the number and the early warning type, the early warning information is generated and outputted.

[0022] Optionally, generating and outputting the early warning information according to the number and the early warning type comprises:

[0023] The second range corresponding to the early warning type is determined.

[0024] According to the early warning type and the corresponding second range, the same number of early warning information as the number is generated and outputted.

[0025] In addition, the application also provides an early warning device, comprising:

[0026] The receiving unit is configured to receive an early warning request, obtain a corresponding data source identifier, and then call a data source corresponding to the data source identifier to obtain to-be-processed data.

[0027] The business type determination unit is configured to extract a corresponding dimension feature in the to-be-processed data based on a preset dimension, and then determine a business type corresponding to the dimension feature.

[0028] The early warning unit is configured to execute an early warning program corresponding to the business type to determine an early warning type corresponding to the dimension feature, and then generate and output early warning information.

[0029] Specifically, the business type determination unit is further configured to:

[0030] The first range dimension feature in the to-be-processed data is extracted based on the first range dimension.

[0031] The second range dimension feature in the to-be-processed data is extracted based on the second range dimension; wherein

[0032] The first range corresponding to the first range dimension is greater than the second range corresponding to the second range dimension.

[0033] Specifically, the business type determination unit is further configured to:

[0034] The negative public opinion data of the day is captured, and then the negative public opinion data is matched with the dimension feature, and the corresponding business type is determined according to the matching result.

[0035] Specifically, the business type determination unit is further configured to:

[0036] In response to the matching result being matching, it is determined that the business type corresponding to the dimension feature is a negative public opinion business;

[0037] In response to the matching result being non-matching, a preset workflow is obtained to determine a next node, and the next node is transferred to execute the matching logic of the next node, and then the business type corresponding to the dimension feature is determined according to the execution result of the matching logic.

[0038] Specifically, the business type determination unit is further configured to:

[0039] The monitoring model is called to obtain a preset workflow in the monitoring model.

[0040] Specifically, the early warning unit is further configured to:

[0041] Determine the number of second ranges contained in the first range;

[0042] According to the number and the early warning type, the early warning information is generated and output.

[0043] Specifically, the early warning unit is further configured to:

[0044] Determine the second range corresponding to the early warning type;

[0045] According to the early warning type and the corresponding second range, the same number of early warning information as the number is generated and output.

[0046] In addition, the present application also provides an early warning electronic device, comprising: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, so that the one or more processors implement the early warning method as described above.

[0047] In addition, the present application also provides a computer readable medium, which stores a computer program, and the program is executed by a processor to implement the early warning method as described above.

[0048] To achieve the above-mentioned purpose, according to another aspect of the embodiment of the present application, a computer program product is provided.

[0049] The computer program product of an embodiment of the application comprises a computer program, and the program is executed by a processor to implement the early warning method provided by the embodiment of the application.

[0050] An embodiment of the above application has the following advantages or beneficial effects: the application receives an early warning request, obtains a corresponding data source identifier, and then calls a data source corresponding to the data source identifier to obtain to-be-processed data; based on a preset dimension, a corresponding dimension feature in the to-be-processed data is extracted, and then a business type corresponding to the dimension feature is determined; an early warning program corresponding to the business type is executed to determine an early warning type corresponding to the dimension feature, and then early warning information is generated and output. The operation of the post-loan early warning business can be standardized, the possible risks can be predicted in advance, and the accuracy of the early warning business and the fund recall rate are improved.

[0051] The further effects of the above non-conventional optional mode will be described in the following in combination with the specific embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0052] The accompanying drawings are used to better illustrate the application, and do not constitute an improper limitation on the application. Among them:

[0053] Figure 1 is a schematic diagram of the main process of the early warning method according to an embodiment of the application;

[0054] Figure 2 is a schematic diagram of the main process of the early warning method according to an embodiment of the application;

[0055] Figure 3 is a schematic diagram of the main process of the early warning method according to an embodiment of the application;

[0056] Figure 4 is a schematic diagram of the application scenario of the early warning method according to an embodiment of the application;

[0057] Figure 5 is a schematic diagram of the main unit of the early warning device according to an embodiment of the application;

[0058] Figure 6 is an exemplary system architecture diagram to which the embodiment of the application can be applied;

[0059] Figure 7 is a structural schematic diagram of a computer system of a terminal device or a server suitable for implementing the embodiments of the application. DETAILED DESCRIPTION

[0060] The exemplary embodiments of the present application are described below with reference to the accompanying drawings, which include various details of the embodiments of the present application to assist in understanding them. These should be considered as merely exemplary. Thus, those of ordinary skill in the art will recognize various changes and modifications of the embodiments described herein, which do not depart from the scope and spirit of the application. Also, for the sake of brevity and clarity, descriptions of well-known functions and constructions are omitted herein. It should be noted that in the technical solutions of the present application, the collection, analysis, use, transmission, storage, etc. of user personal information involved in the technical solutions comply with relevant laws and regulations, are used for legal and reasonable purposes, are not shared, disclosed or sold outside these legal uses, and are subject to supervision and management by regulatory authorities. Necessary measures should be taken for user personal information to prevent illegal access to such personal information data, to ensure that personnel with access to personal information data comply with relevant laws and regulations, and to ensure the security of user personal information. Once these user personal information data are no longer needed, the risk should be minimized by limiting or even prohibiting data collection and / or deleting data.

[0061] When used, including in certain related applications, user privacy is protected by de-identifying data, such as by removing specific identifiers, controlling the amount or specificity of data stored, controlling how data is stored, and / or other methods of de-identifying.

[0062] Figure 1 is a schematic diagram of the main process of the early warning method according to an embodiment of the present application, as Figure 1 The early warning method includes:

[0063] Step S101, receiving an early warning request, obtaining a corresponding data source identifier, and then calling a data source corresponding to the data source identifier to obtain to-be-processed data.

[0064] In this embodiment, the execution subject of the early warning method (for example, which can be a server) can receive an early warning request through wired or wireless connection. The data source identifier can be carried in the early warning request. After obtaining the data source identifier, the execution subject can use the corresponding data source based on the data source table to obtain to-be-processed data. The data source can be a loan data source corresponding to a real estate project. The to-be-processed data can include, for example, loan data corresponding to a target real estate project in the real estate project, wherein the loan data can include loan personnel data, credit limit, loan product, loan amount, whether overdue, credit information, and basic information of the development enterprise.

[0065] Step S102, based on a preset dimension, extracting a corresponding dimension feature in the to-be-processed data, and then determining a business type corresponding to the dimension feature.

[0066] The preset dimensions can be, for example, two dimensions of a building and a building block. Embodiments of the present application do not make specific limitations on the preset dimensions. Specifically, the data processing and output can be performed on the to-be-processed data from the two dimensions of the building and the building block. Specifically, a feature extraction model can be called to extract the dimension features corresponding to the two dimensions of the building and the building block in the to-be-processed data. For example, the dimension features corresponding to the two dimensions of the building and the building block can include key time point progress features, post-delivery certificate handling timeliness features, negative public opinion features, mortgage registration should-be-done-but-not-done ratio features, mortgage value trend features, whether the margin balance is sufficient features, and stop-work-hold-construction pilot features.

[0067] The corresponding business type is determined according to the dimension features. The business type can be an early warning business or a non-early warning business. The non-early warning business can include post-loan fund use monitoring business and post-loan fund use certificate uploading business. Embodiments of the present application do not make specific limitations on the non-early warning business.

[0068] Specifically, based on the preset dimensions, the corresponding dimension features in the to-be-processed data are extracted, including:

[0069] The corresponding first range dimension features in the to-be-processed data are extracted based on the first range dimension. The first range dimension can be, for example, a building dimension. The first range dimension features can be, for example, building dimension features.

[0070] The corresponding second range dimension features in the to-be-processed data are extracted based on the second range dimension. The second range dimension can be, for example, a building block dimension. The second range dimension features can be, for example, building block dimension features.

[0071] The first range corresponding to the first range dimension is greater than the second range corresponding to the second range dimension. For example, the building range corresponding to the building dimension is greater than the building block range corresponding to the building block dimension.

[0072] In step S103, the early warning program corresponding to the business type is executed to determine the early warning type corresponding to the dimension features, and then the early warning information is generated and output.

[0073] When the business type is an early warning business, the early warning program corresponding to the early warning business can be called to determine the corresponding early warning type according to the dimension features. The early warning type can be, for example, an early warning level. The early warning level can be divided into a first-level early warning, a second-level early warning, and a third-level early warning. The severity of the third-level early warning is higher than that of the second-level early warning, which is higher than that of the first-level early warning.

[0074] Specifically, the execution subject can execute the early warning procedure corresponding to the business type to call the classification model, input the dimension features into the classification model, and output the corresponding early warning level, i.e., the early warning type. The early warning information is generated according to the early warning type. For example, the early warning information can be "the post-loan early warning level is a third-level early warning, please handle in time", and the content and form of the early warning information are not limited in the embodiments of the present application.

[0075] In the embodiments of the present application, the early warning method comprises the following steps.

[0076] Figure 2 is the main flow diagram of the early warning method according to an embodiment of the present application, as shown in Figure 2 The early warning method comprises the following steps.

[0077] In step S201, the early warning request is received, the corresponding data source identifier is obtained, and then the data source corresponding to the data source identifier is called to obtain the to-be-processed data.

[0078] The data source identifier can be carried in the early warning request. After obtaining the data source identifier, the execution subject can use the corresponding data source based on the data source table to obtain the to-be-processed data. The data source can be a loan data source corresponding to a vehicle sales project. The to-be-processed data may, for example, include loan data corresponding to a target vehicle sales project in the vehicle sales project, wherein the loan data can include loan personnel data, credit limit, loan product, loan amount, whether overdue, credit information, and vehicle sales enterprise basic information.

[0079] In step S202, the corresponding dimension features in the to-be-processed data are extracted based on preset dimensions.

[0080] The preset dimensions may, for example, be vehicle type and vehicle price. The execution subject can extract the corresponding dimension features in the to-be-processed data based on the vehicle type and the vehicle price. The dimension features can include high-level features and low-level features related to the vehicle type and the vehicle price. The high-level features may, for example, be abstract features such as the overall appreciation space of the vehicle and the attractiveness of the vehicle, and the low-level features may, for example, be specific features such as the shape and color of the vehicle.

[0081] In step S203, the negative public opinion data of the day is captured, and then the negative public opinion data is matched with the dimension features to determine the corresponding business type according to the matching result.

[0082] The execution subject can capture the negative public opinion data of the day when the early warning request is received. The negative public opinion data may, for example, be vehicle quality problems, vehicle delivery problems, etc. When the negative public opinion data is successfully matched with the dimension feature, it is determined that the corresponding business type is a negative public opinion processing business.

[0083] In step S204, the early warning program corresponding to the business type is executed to determine the early warning type corresponding to the dimension feature, and then early warning information is generated and output.

[0084] When the business type is a negative public opinion processing business, the early warning program corresponding to the negative public opinion processing business is executed to determine the early warning type corresponding to the negative public opinion processing business, i.e. the early warning level, and the corresponding early warning information is generated and output according to the early warning level. The operation of the post-loan early warning business can be standardized, and the accuracy and fund recall rate of the early warning business can be improved.

[0085] Figure 3 is the main flow diagram of the early warning method according to an embodiment of the present application, as Figure 2 shown, the early warning method comprises:

[0086] In step S301, an early warning request is received, a corresponding data source identifier is obtained, and then a data source corresponding to the data source identifier is called to obtain to-be-processed data.

[0087] The data source may, for example, be a credit loan data source. The to-be-processed data may, for example, be credit loan data of a user.

[0088] In step S302, based on a preset dimension, corresponding dimension features in the to-be-processed data are extracted.

[0089] The preset dimension may, for example, be a salary dimension and an asset dimension of a user participating in a credit loan. The execution subject can extract corresponding dimension features in the to-be-processed data based on the salary dimension and the asset dimension. The dimension features may, for example, include fusion features corresponding to high-level features and low-level features corresponding to the salary dimension in the to-be-processed data and may, for example, include fusion features corresponding to high-level features and low-level features corresponding to the asset dimension in the to-be-processed data.

[0090] In step S303, negative public opinion data of the day is captured, and then the negative public opinion data is matched with the dimension features.

[0091] The negative public opinion data of the day may, for example, be overdue data of a user participating in a credit loan, and the overdue data is matched with the obtained dimension features.

[0092] In step S304, in response to a matching result being matching, it is determined that the business type corresponding to the dimension features is a negative public opinion business.

[0093] When the negative public opinion data matches the dimension feature, it is determined that the business type corresponding to the dimension feature is a negative public opinion business.

[0094] In step S305, in response to the matching result being not matching, a preset workflow is obtained to determine the next node, and the next node is transferred to execute the matching logic of the next node, and then the business type corresponding to the dimension feature is determined according to the execution result of the matching logic.

[0095] When the overdue data does not match the dimension feature, a preset workflow is obtained. The execution programs of each node in the preset workflow are respectively: project key time node progress overdue dimension detection program, project delivery long-term unable to obtain certificate detection program, project major negative public opinion detection program, mortgage registration should be done but not done ratio detection program, mortgage value decline detection program, cooperation project guarantee fund balance insufficient detection program, and project stop construction and slow construction leading detection program. After obtaining the preset workflow, the execution program of the next node corresponding to the current detection program is determined, for example, when the current detection program is the project major negative public opinion detection program, the execution program of the next node corresponding to it is the mortgage registration should be done but not done ratio detection program. The execution subject can introduce the dimension feature into the execution program of the next node, that is, the mortgage registration should be done but not done ratio detection program, to determine whether it matches. If it matches, it is determined that the business type corresponding to the dimension feature is the mortgage registration should be done but not done ratio detection business. If it does not match, the dimension feature is introduced into the execution program of the next node, that is, the mortgage value decline detection program, to determine whether it matches. If it does not match, the dimension feature is introduced into the cooperation project guarantee fund balance insufficient detection program, and so on, until the matching node execution program is found to determine the business type corresponding to the dimension feature.

[0096] Specifically, the preset workflow is obtained by calling a monitoring model to obtain the preset workflow in the monitoring model.

[0097] In step S306, the warning program corresponding to the business type is executed to determine the warning type corresponding to the dimension feature, and then the warning information is generated and outputted.

[0098] Specifically, the warning information is generated and outputted by determining the number of the second range contained in the first range, and generating and outputting the warning information according to the number and the warning type.

[0099] For example, the first range can be a building range corresponding to a credit data source. The second range can be a building range corresponding to each building corresponding to the building range corresponding to the credit data source.

[0100] Specifically, the warning information is generated and outputted according to the number and the warning type, including:

[0101] The second range corresponding to the early warning type is determined. When the early warning type is a major negative public opinion secondary early warning, the corresponding second range may be, for example, the range of each building.

[0102] According to the early warning type and the corresponding second range, the same number of early warning information is generated and outputted.

[0103] The execution subject can generate early warning information according to the early warning type, the first range, and the number of second ranges corresponding to the first range. The number of early warning information can be the same as the number of second ranges. For example, when the first range is a building range, the second range is a building range, and there are 5 second ranges, 5 early warning information needs to be generated and outputted according to 1 first range (for example, 1 building) and the corresponding 5 second ranges (for example, 5 buildings corresponding to 1 building). For example, according to the risk matter (that is, the early warning type of the present application), the building project, and the project building dimension, the output display is performed. That is, one risk matter, one building project number, and one building output one early warning information. If the same building project involves multiple risk matters, and the same building project has multiple handling lines (corresponding to multiple project numbers), then multiple early warning information is outputted accordingly.

[0104] In addition, the data output item can also include: statistical time, first-level branch code, first-level branch name, second-level branch code, second-level branch name, handling line code, handling line name, project name, project number, group enterprise name, group enterprise number, cooperation party name, social unified credit code, cooperation actual controller, cooperation legal representative, cooperation major shareholder, cooperation agreement number, cooperation state, cooperation start date, cooperation end date, first loan issuance date, last loan issuance date, loan balance, loan number, overdue balance, overdue number, overdue rate, non-performing balance, non-performing number, non-performing rate, pre-registered mortgage number, formal registered mortgage number, pre-registered mortgage rate, formal registered mortgage rate, agreed ceiling time, agreed completion time, agreed delivery time, monitoring type, early warning progress type, problem type (building problem, project problem), and whether the building is newly added this month. Through the entire data output item, the project doubts can be evaluated with as few fields as possible, and the manual cost of business personnel is reduced.

[0105] Figure 4 FIG. 1 is a schematic diagram of an application scene of an early warning method according to an embodiment of the present application. The early warning method of the present embodiment is applied to a post-loan early warning scene. As shown in FIG. 1, the early warning method of the present embodiment is applied to a post-loan early warning scene. Figure 4As shown, the early warning method first performs data extraction in different data sources, which are data components of different systems and external data, including loan data, project data, building data, guarantee contract data, and external data. After data deduplication and cleaning preprocessing, the data is input into the monitoring model for data processing. The embodiments of the present application design multiple monitoring models for different scenarios and risk factors of the building project and perform early warning monitoring from two detection dimensions of the building and the building. Finally, the data processed by the model (i.e., integrated output items, including suspected buildings and suspected buildings) is transmitted to the early warning system background and front end to show the early warning business personnel, and the early warning business process is completed. Among them, the monitoring model can include a building project key time point progress overdue early warning model, a building project long-term unable to obtain a license after delivery early warning model, a building project major negative public opinion early warning model, a building project mortgage registration rate too low early warning model, a building project mortgage value decline early warning model, a building project guarantee fund insufficient early warning model, and a building project construction suspension early warning model.

[0106] For example, the embodiments of the present application design and implement 7 kinds of risk event early warning models according to the business scenarios and characteristics of the building project, and perform data processing and output according to two different dimensions of the building and the building. The details of the early warning models are as follows:

[0107] (1) Early warning of cooperation building project key time node progress overdue

[0108] Every month, the system extracts building projects "agreed ceiling time, agreed completion time or agreed delivery time" at the monitoring time point or before the monitoring time point. The projects that have passed the cooperation end time or the formal mortgage registration rate of the existing loan is higher than 90% are excluded, and the early warning project list is generated.

[0109] (2) Early warning of cooperation building project long-term unable to obtain a license after delivery

[0110] Every month, the system extracts building projects that have been over 2 years since the agreed delivery date, or the first individual loan has been over 3 years, and the formal mortgage registration rate is still 0. The building project is warned.

[0111] (3) Early warning of major negative public opinion of building project

[0112] Every day, the system automatically extracts the developers or building projects with negative public opinion and matches them with the target cooperation building project. If the matching is successful, the developer, building project and target cooperation building project are warned.

[0113] (4) Early warning of building project mortgage registration should be done but not done rate too high

[0114] If the same real estate project should be handled and not handled the rate of pre-registered mortgage is greater than or equal to 50%, or the rate of formal mortgage registration is greater than or equal to 50%, the real estate project is warned.

[0115] (5) The value of the construction project mortgage is declining

[0116] The value of the real estate development loan project collateral category "house property under construction" is less than the latest mortgage evaluation value of the under-construction project, and the latest mortgage rate of the under-construction project is greater than the highest collateral mortgage rate set for the real estate development loan project, and the real estate development loan project is warned.

[0117] (6) The balance of the guarantee fund is insufficient

[0118] Find the balance of the guarantee fund account this month through the new generation of account management, find the corresponding information of the cooperative project or the building in the individual loan system, and reveal the specific handling bank of the personal loan. If the balance of the guarantee fund account this month is less than the minimum balance of the guarantee fund deposit of the cooperative building project, the building project is warned.

[0119] (7) The building project is stopped and the construction is delayed

[0120] The construction progress of the building project under construction, the number of workers on duty at the construction site, the water and electricity consumption at the construction site, the use of engineering machinery such as tower crane, and the allocation of supervision funds corresponding to the engineering progress are monitored monthly.

[0121] Then the following situations are counted:

[0122] A. Compare the changes in worker attendance: for the same building project, compare the monitoring data of the adjacent two months (this month compared with last month), and the number of workers on duty decreases by more than 30% (the specific amount of change needs to be discussed and determined).

[0123] B. Compare the progress of the project: for the building projects with records of allocation of supervision account funds in the monitoring month, grab the corresponding engineering progress information, and grab the "topping time" and "completion time" (actual completion time) from the system for the projects in the monitoring month. Compare whether the actual engineering progress has been topped for the projects with "topping time" in the system as the monitoring month, and whether the actual engineering progress has been completed for the projects with "completion time" in the system as the monitoring month.

[0124] C. The situation of workers' salary payment: through the bank salary supervision special account, through the monitoring of bank salary supervision special account, monitor whether the workers' salary is normally paid, and compare the relevant data with last month, and the decrease of the amount of money is more than 50%.

[0125] D. Project status monitoring: monitoring the status of the project, and reporting the status of "stop work" and other abnormal status.

[0126] E. Project fund monitoring: monitoring the bank account funds, comparing the account fund balance of the adjacent two months (this month compared with last month), and the fund transfer exceeding 50% or more.

[0127] The real estate project that meets any of the above conditions is matched with the target cooperative project real estate, and the real estate that matches the target cooperative project real estate is identified. Based on all real estate projects that meet the above conditions, a warning list is generated. The suspicious details of the real estate project can be obtained through the monitoring model processing of the embodiments of the application. These information contains many field information, but some fields may be less helpful for suspicious checking, and on the other hand, the information between the fields may be redundant. In order to facilitate business personnel to check the suspicious information of the real estate project, the embodiments of the application design a core output item for the suspicious information of the real estate project by summarizing the information related to the risk of the real estate project and combining the loan business characteristics of the real estate project. The core output item can evaluate the suspiciousness of the real estate project with as few fields as possible, reducing the manual cost of business personnel. The output is displayed according to the risk items, real estate projects, and project building dimensions. That is, one risk item, one real estate project number, and one building output one warning information. If a real estate project involves multiple risk items and the same real estate project has multiple handling lines (corresponding to multiple project numbers), multiple outputs are output accordingly. This can make the post-loan monitoring business personnel have a clearer workflow and framework. It can standardize the operation of the post-loan warning business and improve efficiency. It can improve the accuracy and recall rate of the post-project warning business. External factors are introduced in the warning business to evaluate the risk of the project from multiple angles. Based on the integrated output item, the suspiciousness of the real estate project can be evaluated with as few fields as possible, reducing the manual cost of business personnel.

[0128] Figure 5 is a schematic diagram of the main unit of the warning device according to the embodiments of the application. As shown in Figure 5 , the warning device 500 includes a receiving unit 501, a business type determination unit 502, and a warning unit 503.

[0129] The receiving unit 501 is configured to receive a warning request, obtain a corresponding data source identifier, and then call the data source corresponding to the data source identifier to obtain the to-be-processed data.

[0130] The business type determination unit 502 is configured to extract the corresponding dimension feature in the to-be-processed data based on a preset dimension, and then determine the business type corresponding to the dimension feature.

[0131] The early warning unit 503 is configured to execute a business type corresponding early warning program to determine a dimension feature corresponding early warning type, and then generate early warning information and output.

[0132] In some embodiments, the business type determination unit 502 is further configured to: extract a first range dimension feature corresponding in the to-be-processed data based on a first range dimension; extract a second range dimension feature corresponding in the to-be-processed data based on a second range dimension; and wherein a first range corresponding to the first range dimension is greater than a second range corresponding to the second range dimension.

[0133] In some embodiments, the business type determination unit 502 is further configured to: crawl negative public opinion data of the day, and then match the negative public opinion data with the dimension feature, and determine the corresponding business type according to the matching result.

[0134] In some embodiments, the business type determination unit 502 is further configured to: in response to the matching result being matching, determine that the business type corresponding to the dimension feature is negative public opinion business; and in response to the matching result being non-matching, obtain a preset workflow to determine a next node, flow to the next node to execute matching logic of the next node, and then determine the business type corresponding to the dimension feature according to an execution result of the matching logic.

[0135] In some embodiments, the business type determination unit 502 is further configured to: call a monitoring model to obtain a preset workflow in the monitoring model.

[0136] In some embodiments, the early warning unit 503 is further configured to: determine a number of the second range contained in the first range; and generate and output early warning information according to the number and the early warning type.

[0137] In some embodiments, the early warning unit 503 is further configured to: determine a second range corresponding to the early warning type; and generate and output the same number of early warning information according to the early warning type and the corresponding second range.

[0138] It should be noted that the early warning method and the early warning device of the present application have a corresponding relationship in the specific implementation content, and therefore repeated content will not be described.

[0139] Figure 6 An exemplary system architecture 600 to which the early warning method or early warning device of embodiments of the present application can be applied is shown.

[0140] As Figure 6As shown, the system architecture 600 can include terminal devices 601, 602, 603, a network 604, and a server 605. The network 604 is a medium for providing a communication link between the terminal devices 601, 602, 603 and the server 605. The network 604 can include various connection types, such as wired, wireless communication links, or optical fiber cables, etc.

[0141] A user can use the terminal devices 601, 602, 603 to interact with the server 605 through the network 604 to receive or send messages, etc. Various communication client applications can be installed on the terminal devices 601, 602, 603, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only as examples).

[0142] The terminal devices 601, 602, 603 can be various electronic devices with early warning processing screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, etc.

[0143] The server 605 can be a server providing various services, such as a background management server supporting early warning requests submitted by users using the terminal devices 601, 602, 603 (only as an example). The background management server can receive an early warning request, obtain a corresponding data source identifier, and then call a data source corresponding to the data source identifier to obtain to-be-processed data; based on a preset dimension, extract a corresponding dimension feature in the to-be-processed data, and then determine a business type corresponding to the dimension feature; execute an early warning program corresponding to the business type to determine an early warning type corresponding to the dimension feature, and then generate early warning information and output. The operation of the post-loan early warning business can be standardized, the possible risks can be predicted in advance, and the accuracy of the early warning business and the fund recall rate can be improved.

[0144] It should be noted that the early warning method provided by the embodiments of the present application is generally executed by the server 605, and correspondingly, the early warning device is generally arranged in the server 605.

[0145] It should be understood that Figure 6 The number of terminal devices, networks, and servers in the above description is only illustrative. According to the needs of implementation, there can be any number of terminal devices, networks, and servers.

[0146] Reference will be made to Figure 7 which shows a structural schematic diagram of a computer system 700 of a terminal device suitable for implementing the embodiments of the present application. Figure 7 The terminal device shown is only an example and should not impose any limitation on the functions and use range of the embodiments of the present application.

[0147] As Figure 7As shown, the computer system 700 includes a central processing unit (CPU) 701 which can perform various appropriate actions and processes according to programs stored in a read only memory (ROM) 702 or loaded into a random access memory (RAM) 703 from a storage section 708. In the RAM 703, various programs and data required for the operation of the computer system 700 are also stored. The CPU 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0148] Connected to the I / O interface 705 are an input section 706 including a keyboard, a mouse, etc.; an output section 707 including a display device such as a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN card, a modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as necessary. A removable recording medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is attached to the drive 710 as necessary, so that a computer program read therefrom is installed into the storage section 708 as necessary.

[0149] In particular, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, the embodiments of the present disclosure include a computer program product including a computer program carried on a computer-readable medium, the computer program containing program codes for executing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network by the communication section 709, and / or installed from the removable recording medium 711. When the computer program is executed by the central processing unit (CPU) 701, the above-described functions defined in the system of the present disclosure are executed.

[0150] Note that the computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium or a combination thereof. The computer-readable storage medium can include, for example, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the computer-readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, the computer-readable storage medium can be any tangible medium that contains or stores a program used by an instruction execution system, apparatus, or device to function according to the program. In the present application, the computer-readable signal medium can include a computer-readable storage medium or any computer-readable medium that transmits, propagates, or transfers programs used by an instruction execution system, apparatus, or device to function according to the programs. The program code contained in the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wireline, optical fiber, RF, etc., or any suitable combination of the foregoing.

[0151] The flow diagrams and block diagrams in the drawings are schematic illustrations of possible architectures, functions, and operations of systems, methods, and computer program products in accordance with various embodiments of the present application. In this regard, each block in the flow diagrams or block diagrams can represent a module, a segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or in the reverse order, depending on the functionality involved. It will also be noted that each block of the block diagrams or flow diagrams, and combinations of blocks in the block diagrams or flow diagrams, can be implemented by special purpose hardware-based systems that perform the specified functions or operations, or combinations of special purpose hardware and computer instructions.

[0152] The units described in the embodiments of the present application can be implemented in the form of software, or can be implemented in the form of hardware. The described units can also be arranged in a processor, for example, can be described as: a processor comprising a receiving unit, a service type determining unit and a pre-warning unit. In some cases, the names of these units do not constitute a limitation on the units themselves.

[0153] As another aspect, the present application also provides a computer readable medium, which can be included in the device described in the above embodiments, or can exist independently without being assembled into the device. The computer readable medium carries one or more programs, when the one or more programs are executed by the device, the device receives a pre-warning request, obtains a corresponding data source identifier, and then calls a data source corresponding to the data source identifier to obtain to-be-processed data; based on a preset dimension, extracts a corresponding dimension feature in the to-be-processed data, and then determines a service type corresponding to the dimension feature; executes a pre-warning program corresponding to the service type to determine a pre-warning type corresponding to the dimension feature, and then generates pre-warning information and outputs.

[0154] The computer program product of the present application comprises a computer program, and the computer program implements the pre-warning method in the embodiments of the present application when executed by a processor.

[0155] According to the technical scheme of the embodiments of the present application, the operation of the post-loan pre-warning business can be standardized, the possible risks can be predicted in advance, and the accuracy of the pre-warning business and the fund recall rate can be improved.

[0156] The above specific embodiments do not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can occur depending on design requirements and other factors. Any modification, equivalent replacement and improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. An early warning method, characterized in that, include: Receive an early warning request, obtain the corresponding data source identifier, and then call the data source corresponding to the data source identifier to obtain the data to be processed; Based on a preset dimension, extract the corresponding dimensional features from the data to be processed, including: extracting the corresponding first-range dimensional features from the data to be processed based on a first-range dimension; extracting the corresponding second-range dimensional features from the data to be processed based on a second-range dimension; wherein, the first range corresponding to the first-range dimension is greater than the second range corresponding to the second-range dimension; Then, the business type corresponding to the dimensional feature is determined; Execute the early warning program corresponding to the business type to determine the early warning type corresponding to the dimension feature, and then generate and output early warning information, including: determining the number of the second range included in the first range; generating and outputting early warning information based on the number and the early warning type.

2. The method according to claim 1, characterized in that, Determining the business type corresponding to the dimensional feature includes: The system captures negative public opinion data for the day, matches the negative public opinion data with the dimensional features, and determines the corresponding business type based on the matching results.

3. The method according to claim 2, characterized in that, The step of determining the corresponding business type based on the matching results includes: If the matching result is a match, the business type corresponding to the dimension feature is determined to be negative public opinion business. In response to a mismatch result, a preset workflow is obtained to determine the next node, and the process is transferred to the next node to execute the matching logic of the next node. Then, the business type corresponding to the dimension feature is determined based on the execution result of the matching logic.

4. The method according to claim 3, characterized in that, The process of obtaining the preset workflow includes: Invoke the monitoring model to obtain the preset workflow in the monitoring model.

5. The method according to claim 1, characterized in that, The step of generating and outputting warning information based on the quantity and the warning type includes: Determine the second range corresponding to the warning type; Based on the warning type and the corresponding second range, generate and output the same number of warning messages as the stated quantity.

6. An early warning device, characterized in that, include: The receiving unit is configured to receive an early warning request, obtain the corresponding data source identifier, and then call the data source corresponding to the data source identifier to obtain the data to be processed. The business type determination unit is configured to extract the corresponding dimension features from the data to be processed based on a preset dimension, and then determine the business type corresponding to the dimension features. The early warning unit is configured to execute the early warning program corresponding to the business type to determine the early warning type corresponding to the dimension feature, and then generate and output early warning information; The business type determination unit is further configured to: extract the corresponding first range dimension features from the data to be processed based on the first range dimension; extract the corresponding second range dimension features from the data to be processed based on the second range dimension; wherein, the first range corresponding to the first range dimension is greater than the second range corresponding to the second range dimension; The warning unit is further configured to: determine the number of the second ranges included in the first range; generate and output warning information based on the number and the warning type.

7. The apparatus according to claim 6, characterized in that, The service type determination unit is further configured to: The system captures negative public opinion data for the day, matches the negative public opinion data with the dimensional features, and determines the corresponding business type based on the matching results.

8. The apparatus according to claim 7, characterized in that, The service type determination unit is further configured to: If the matching result is a match, the business type corresponding to the dimension feature is determined to be negative public opinion business. In response to a mismatch result, a preset workflow is obtained to determine the next node, and the process is transferred to the next node to execute the matching logic of the next node. Then, the business type corresponding to the dimension feature is determined based on the execution result of the matching logic.

9. The apparatus according to claim 8, characterized in that, The service type determination unit is further configured to: Invoke the monitoring model to obtain the preset workflow in the monitoring model.

10. An early warning electronic device, characterized in that, include: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-5.

11. A computer-readable medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-5.

12. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-5.

Images