CN115965464A - Empty shell enterprise identification method and device, storage medium and electronic device - Google Patents
Empty shell enterprise identification method and device, storage medium and electronic device Download PDFInfo
- Publication number
- CN115965464A CN115965464A CN202310003349.XA CN202310003349A CN115965464A CN 115965464 A CN115965464 A CN 115965464A CN 202310003349 A CN202310003349 A CN 202310003349A CN 115965464 A CN115965464 A CN 115965464A
- Authority
- CN
- China
- Prior art keywords
- target
- risk
- identified
- probability
- identification data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a device for identifying an empty-shell enterprise, a storage medium and an electronic device. Wherein, the method comprises the following steps: acquiring target identification data, wherein the target identification data is used for carrying out risk identification on an object to be identified; generating a target characteristic label based on the target identification data, wherein the target characteristic label is used for determining the risk category of the object to be identified; constructing a target identification network by using the target characteristic tags, and analyzing target identification data based on the target identification network to obtain target risk probability corresponding to an object to be identified, wherein the target identification network comprises a plurality of network nodes, and the plurality of network nodes are used for performing probability analysis on the object to be identified; and generating target prompt information according to the target risk probability, wherein the risk prompt information is used for carrying out risk prompt on the object to be identified. The invention solves the technical problem that the accurate identification of the hollow enterprise is difficult in the related technology.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a method and a device for identifying an empty shell enterprise, a storage medium and an electronic device.
Background
The shell-free company is one of the important risks that financial institutions such as banks need to be vigilant, on one hand, the shell-free company is easy to become a carrier of illegal activities, and on the other hand, a large number of shell-free company accounts also increase the management cost of the banks. For banks, not only account risks need to be prevented, but also account services need to be optimized, how to balance the relationship between the two becomes a key problem, and the core for processing the problem lies in whether empty-shell enterprises can be identified more accurately or not, so that early warning is performed in advance, and management is enhanced.
In the actual business process, the prior supervision of the bank for the vacant enterprises is very important. However, since the business and financial data of the enterprise cannot be obtained in advance, it is difficult to predict the business by using a regression model, and generally, the business can be subjectively judged only by combining the characteristics of the enterprise with the business experience. The current traditional characteristic judgment method, such as modes of 'one person with more enterprises, one person with more households, one address with more photos' and the like, has single index, and is difficult to ensure the accuracy of the judgment result; while the method of Analytic Hierarchy Process (AHP) can comprehensively consider various factors at the same time, the determination of the weight relationship among different characteristics depends on subjective judgment, and the model expression capability of the hierarchical structure is limited, so that the objective and practical situation cannot be well fitted for the complex problem of identification of the empty-shell enterprise.
In view of the above problems, no effective solution has been proposed.
Disclosure of Invention
The embodiment of the invention provides a method and a device for identifying an empty-shell enterprise, a storage medium and an electronic device, which are used for at least solving the technical problem that the empty-shell enterprise is difficult to accurately identify in the related technology.
According to an aspect of the embodiments of the present invention, there is provided a method for identifying an empty-shell enterprise, including: acquiring target identification data, wherein the target identification data is used for carrying out risk identification on an object to be identified; generating a target characteristic label based on the target identification data, wherein the target characteristic label is used for determining the risk category of the object to be identified; constructing a target identification network by using the target characteristic tags, and analyzing target identification data based on the target identification network to obtain target risk probability corresponding to an object to be identified, wherein the target identification network comprises a plurality of network nodes, and the plurality of network nodes are used for performing probability analysis on the object to be identified; and generating target prompt information according to the target risk probability, wherein the risk prompt information is used for carrying out risk prompt on the object to be identified.
Optionally, the obtaining the target identification data comprises: acquiring initial identification data, wherein the initial identification data comprises enterprise attribute information and preset account information of an object to be identified; and carrying out discretization processing on the initial identification data to obtain target identification data.
Optionally, generating the object feature tag based on the object identification data comprises: acquiring a preset labeling rule, wherein the preset labeling rule is used for expressing a historical classification rule for an object to be identified; and generating a target characteristic label based on a preset experience rule and target identification data.
Optionally, constructing the object identification network using the object feature tag includes: acquiring business process information based on the target characteristic label; determining a plurality of risk identification indexes according to the business process information; and determining a plurality of network nodes based on the plurality of risk identification indexes, and constructing a target identification network based on the plurality of network nodes.
Optionally, analyzing the target identification data based on the target identification network, and obtaining the target risk probability corresponding to the object to be identified includes: generating a first conditional probability table by using a preset prior probability, and generating a second conditional probability table by using target identification data; analyzing the first conditional probability table and the second conditional probability table based on the target identification network, and outputting initial risk probabilities corresponding to the plurality of network nodes; and updating the initial risk probability to obtain the target risk probability.
Optionally, the updating the initial risk probability, and obtaining the target risk probability includes: adjusting the preset prior probability to obtain an adjustment result; and updating the initial risk probability based on the adjustment result to obtain the target risk probability.
Optionally, the generating the target prompt information according to the target risk probability includes: determining risk grade information corresponding to the object to be identified by using the target risk probability; and generating target prompt information based on the risk level information.
According to another aspect of the embodiments of the present invention, there is also provided an empty shell enterprise identification apparatus, including: the system comprises an acquisition module, a risk identification module and a risk identification module, wherein the acquisition module is used for acquiring target identification data, and the target identification data is used for carrying out risk identification on an object to be identified; the system comprises a first generation module, a second generation module and a third generation module, wherein the first generation module is used for generating a target characteristic label based on target identification data, and the target characteristic label is used for determining the risk category of an object to be identified; the processing module is used for constructing a target identification network by using the target characteristic tags, analyzing target identification data based on the target identification network and obtaining target risk probability corresponding to the object to be identified, wherein the target identification network comprises a plurality of network nodes, and the plurality of network nodes are used for carrying out probability analysis on the object to be identified; and the second generation module is used for generating target prompt information according to the target risk probability, wherein the risk prompt information is used for carrying out risk prompt on the object to be identified.
Optionally, the obtaining module is further configured to: acquiring initial identification data, wherein the initial identification data comprises enterprise attribute information and preset account information of an object to be identified; and carrying out discretization processing on the initial identification data to obtain target identification data.
Optionally, the first generating module is further configured to: acquiring a preset labeling rule, wherein the preset labeling rule is used for expressing a historical classification rule for an object to be identified; and generating a target characteristic label based on a preset experience rule and target identification data.
Optionally, the processing module is further configured to: acquiring business process information based on the target feature tag; determining a plurality of risk identification indexes according to the business process information; and determining a plurality of network nodes based on the plurality of risk identification indexes, and constructing a target identification network based on the plurality of network nodes.
Optionally, the processing module is further configured to: generating a first conditional probability table using a preset prior probability, and generating a second conditional probability table using target identification data; analyzing the first conditional probability table and the second conditional probability table based on the target identification network, and outputting initial risk probabilities corresponding to the plurality of network nodes; and updating the initial risk probability to obtain the target risk probability.
Optionally, the processing module is further configured to: adjusting the preset prior probability to obtain an adjustment result; and updating the initial risk probability based on the adjustment result to obtain the target risk probability.
Optionally, the second generating module is further configured to: determining risk grade information corresponding to the object to be identified by using the target risk probability; and generating target prompt information based on the risk level information.
According to another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium, where the computer-readable storage medium includes a stored program, and when the program runs, the apparatus where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned methods for identifying an empty shell enterprise.
According to another aspect of the embodiments of the present invention, there is also provided an electronic apparatus, including: a memory storing an executable program; and the processor is used for running the program, wherein the program executes any one of the above-mentioned empty shell enterprise identification methods during running.
In the embodiment of the invention, the target identification data is obtained, the target feature tag is generated based on the target identification data, the target identification network is constructed by using the target feature tag, the target identification data is analyzed based on the target identification network to obtain the target risk probability corresponding to the object to be identified, and finally, the target prompt information is generated according to the target risk probability, so that the aims of accurately identifying the empty-case enterprises and timely early warning are fulfilled, the technical effect of improving the identification accuracy of the empty-case enterprises is realized, and the technical problem that the empty-case enterprises are difficult to accurately identify in the related technology is solved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention and do not constitute a limitation of the invention. In the drawings:
fig. 1 is a flow chart of a method for identifying an empty-shell enterprise according to an embodiment of the present application;
FIG. 2 is a schematic structural diagram of a Bayesian network for legal person risk of anomaly according to an embodiment of the present application;
FIG. 3 is a schematic structural diagram of a Bayesian network of risk for an open-shell enterprise in accordance with an embodiment of the present application;
FIG. 4 is a schematic diagram of a legal anomaly risk and its leading node state and prior probability distribution according to an embodiment of the present application;
fig. 5 is a block diagram illustrating an empty-shell enterprise identification apparatus according to an embodiment of the present disclosure.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in other sequences than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
First, some terms or terms appearing in the description of the embodiments of the present application are applicable to the following explanations:
chromatographic assay (analytical Hierarchy Process, AHP): the method is a system method which takes a complex multi-target decision problem as a system, decomposes a target into a plurality of targets or criteria, further decomposes the targets into a plurality of layers of multiple indexes, and calculates the single-layer sequence and the total sequence of the layers by a qualitative index fuzzy quantization method to be used as the multi-index and multi-scheme optimization decision.
Bayesian network: a probability graph model is composed of a directed acyclic graph, nodes of the directed acyclic graph represent random variables, directed edges between the nodes represent correlation systems between the nodes, and the conditional probability is used for expressing the strength of the relation.
Risk identification of the vacant enterprises under the enterprise account opening scene is difficult to predict by utilizing a regression model because the risk identification belongs to prior supervision and the management and financial data of the target enterprises for a period of time cannot be obtained. The evaluation methods commonly used in the prior art mainly comprise a characteristic judgment method and a comprehensive scoring method.
A characteristic judgment method: the method mainly utilizes some key risk characteristics, such as 'one person with multiple enterprises, one person with multiple households and one address with multiple pictures', to set certain threshold values aiming at different characteristics, the risk factors are registered when the threshold values are exceeded, and a client manager carries out risk identification according to actual conditions. The method has the main defects that risk factors cannot be effectively unified, the subjective judgment of a customer manager is required, and the judgment result is easy to be inaccurate.
A comprehensive grading method: aiming at the problem of over-strong subjective factors of a characteristic judgment method, another method considers that a plurality of indexes are respectively scored and then a method of adding a certain weight is adopted, namely a comprehensive scoring method. Generally, the fractional weights of different index levels are respectively determined by an Analytic Hierarchy Process (AHP), and then are summarized step by step. The method has the main defect that the determination difficulty of the weight coefficient is high, for example, the important relation among the indexes is difficult to measure by using the weight coefficient between the legal registration place, the legal age and the legal registration enterprise number, so that the final score is determined.
In accordance with an embodiment of the present invention, there is provided an empty shell enterprise identification method embodiment, it is noted that the steps illustrated in the flowchart of the drawings may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowchart, in some cases, the steps illustrated or described may be performed in an order different than that described herein.
The method embodiments may be performed in an electronic device or similar computing device that includes a memory and a processor. For example, a computer terminal may include one or more processors (which may include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), a Digital Signal Processing (DSP) chip, a Microprocessor (MCU), a Programmable logic device (Field Programmable Gate Array (FPGA)), a Neural-Network Processor (NPU), a Tensor Processing Unit (TPU), an Artificial Intelligence (AI), and a memory for storing data).
The memory may be configured to store a computer program, for example, a software program and a module of application software, such as a computer program corresponding to the method for identifying an empty-shell enterprise in an embodiment of the present invention, and the processor executes various functional applications and data processing by running the computer program stored in the memory, so as to implement the above-mentioned method for identifying an empty-shell enterprise. The memory may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located from the processor, which may be connected to the mobile terminal over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission device is used for receiving or transmitting data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device includes a Network adapter (NIC) that can be connected to other Network devices through a base station to communicate with the internet. In one example, the transmission device may be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.
The Display device may be, for example, a touch screen type Liquid Crystal Display (LCD) and a touch Display (also referred to as a "touch screen" or "touch Display screen"). The liquid crystal display may enable a user to interact with a user interface of the mobile terminal. In some embodiments, the mobile terminal has a Graphical User Interface (GUI) with which a User can interact by touching finger contacts and/or gestures on a touch-sensitive surface, where the man-machine interaction function optionally includes the following interactions: executable instructions for creating web pages, drawing, word processing, making electronic documents, games, video conferencing, instant messaging, emailing, call interfacing, playing digital video, playing digital music, and/or web browsing, etc., for performing the above-described human-computer interaction functions, are configured/stored in one or more processor-executable computer program products or readable storage media.
In an embodiment of the present invention, a method for identifying an empty-shell enterprise running on the above-mentioned computer terminal is provided, and fig. 1 is a flowchart of a method for identifying an empty-shell enterprise according to an embodiment of the present application, and as shown in fig. 1, the method includes the following steps:
step S11, acquiring target identification data, wherein the target identification data is used for carrying out risk identification on an object to be identified;
the object to be identified is an enterprise to be identified, and the target identification data is preprocessed enterprise attribute information and enterprise persistent account information. The enterprise attribute data mainly refers to relevant material information required by enterprise account opening, including but not limited to business information, addresses and contact ways related to enterprise registration, enterprise body properties, related information of affiliated industries and legal persons, and the like. Enterprise information such as some open judicial suits, industry and business penalties and the like is also included for the enterprise with the account opened. The persistent suspension account information is mainly company account information processed by a bank in a persistent suspension mode and can be used for subsequent assignment modeling of network nodes.
Step S12, generating a target characteristic label based on the target identification data, wherein the target characteristic label is used for determining the risk category of the object to be identified;
specifically, the target feature tag may specifically include four types, namely, an enterprise subject risk, a contact risk, a residence address risk, and a legal person abnormal risk.
Step S13, constructing a target identification network by using the target characteristic tags, and analyzing target identification data based on the target identification network to obtain target risk probability corresponding to the object to be identified, wherein the target identification network comprises a plurality of network nodes, and the plurality of network nodes are used for performing probability analysis on the object to be identified;
specifically, the target identification network is a bayesian network, a topological structure of the bayesian network can be constructed by using a target feature tag, the bayesian network includes a plurality of network nodes, the network nodes are connected by directed edges, each network node can represent a random variable, the directed edges can represent a relationship between the network nodes, and the directed edges can point to child nodes from parent nodes. And the target risk probability corresponding to the object to be identified is used for representing the posterior probability of the network node.
And S14, generating target prompt information according to the target risk probability, wherein the risk prompt information is used for carrying out risk prompt on the object to be identified.
Specifically, the target prompt information may be risk early warning information about an enterprise to be identified, the risk early warning information may be used to determine an identification result for the enterprise to be identified, and the target prompt information may be displayed on a graphical user interface of the terminal device.
Through the steps S11 to S12, the target identification data is obtained, the target characteristic label is generated based on the target identification data, the target characteristic label is used for constructing the target identification network, the target identification data is analyzed based on the target identification network, the target risk probability corresponding to the object to be identified is obtained, and finally the target prompt information is generated according to the target risk probability, so that the aims of accurately identifying the empty-shell enterprises and timely early warning are fulfilled, the technical effect of improving the identification accuracy of the empty-shell enterprises is achieved, and the technical problem that the empty-shell enterprises are difficult to accurately identify in the related technology is solved.
The method for identifying an empty shell enterprise in the above embodiment is further described below.
Optionally, in step S11, the acquiring the target identification data includes:
step S111, acquiring initial identification data, wherein the initial identification data comprises enterprise attribute information and preset account information of an object to be identified;
step S112, discretizing the initial identification data to obtain target identification data.
Specifically, the preset account information may be persistent account information associated with the enterprise to be identified, the initial identification data includes a continuous variable, the continuous variable is discretized, and target identification data can be obtained, so that a data preprocessing process can be realized. Besides applying a general discretization method, the grouping is performed in combination with business conditions, for example, the age is directly related to the civil performance capability, and the association degree is high with the wealth condition, the social and economic activity range, the risk preference and the like of the client. Based on this discretization of the age information, the age can be further divided into four sections of less than 18 years old, 18 to 26 years old, 27 to 60 years old, 60 years old or older.
Based on the optional embodiment, the directly acquired enterprise attribute information can be quickly preprocessed, so that target identification data is obtained, and whether the enterprise to be identified is a vacant enterprise or not is accurately judged.
Optionally, in step S12, generating the object feature tag based on the object identification data includes:
step S121, acquiring a preset labeling rule, wherein the preset labeling rule is used for expressing a historical classification rule for an object to be identified;
and S122, generating a target feature label based on a preset experience rule and target identification data.
Specifically, the preset labeling rule may include historical business experience data recognized by the bare-shell enterprise, and the preset experience rule and the target recognition data are combined to perform labeling processing, so that four types of labels including enterprise subject risks, contact way risks, address of residence risks and legal person abnormal risks can be obtained.
For example, in the business entity risk label class, a simple business name has no label meaning, but based on the business name, a feature label may be derived: the naming mode of the enterprise name is the same. And identifying the name of the thunder enterprise through a Natural Language Processing (NLP) tool, further judging by combining the registration time of the thunder enterprise, and marking the target characteristic label as 'yes' if the registration time of the thunder enterprise with the name of the enterprise is relatively close.
Based on the optional embodiment, the target feature tag can be quickly generated by acquiring the preset labeling rule and further based on the preset experience rule and the target identification data.
Optionally, in step S13, constructing an object identification network using the object feature tag includes:
step S131, acquiring service process information based on the target characteristic label;
step S132, determining a plurality of risk identification indexes according to the business process information;
step S133, determining a plurality of network nodes based on the plurality of risk identification indicators, and constructing a target identification network based on the plurality of network nodes.
Specifically, the main content of the bayesian network construction is to construct a topological structure of the bayesian network, and the bayesian network construction is mainly divided into two parts of content of node identification and network structure determination. The node identification is to determine some key risk indexes and risk inducers in the identification of the bare-case enterprises according to the business process information and the identification experience data, and further to determine a plurality of network nodes in the Bayesian network according to the key risk indexes and the risk inducers, so that the Bayesian network can be constructed based on a plurality of network points.
Currently, the highest and most immediate risk of data availability is the risk factor surrounding the associated legal person, and a bayesian network is constructed below by taking the abnormal risk of the legal person as an example.
Fig. 2 is a schematic structural diagram of a bayesian network of abnormal risk of a legal person according to an embodiment of the present application, and as shown in fig. 2, when network node identification is performed, the abnormal risk of the legal person is mainly caused by two parts, namely real control risk and legal person representative risk, so that distribution of the empty-shell enterprises is affected. For the actual control person, if the actual control person is overseas or has a complex and dispersed equity relationship, the possibility that the risk is caused by the fact that the main body of the actual control person hides the real beneficiary is high, and the probability that the related company is the shell company is also higher. For legal representatives, the age, the number of enterprises under the name and the proportion of existing high-risk industries under the name of the legal representatives are all the core influencing factors for identifying and comparing the vacant enterprises as directly identifiable natural persons. And determining the network structure according to the analysis to obtain the Bayesian network topology structure of the legal person abnormal risk.
Fig. 3 is a schematic structural diagram of a bayesian network of risk of an open-shell enterprise according to an embodiment of the present application, and as shown in fig. 3, the risk of the open-shell enterprise is mainly determined by a legal person abnormal risk, a contact address abnormal risk, a residence address abnormal risk, and an enterprise subject risk. The main risk of the enterprise is determined by the high-risk industry or the operation range and the main property of the enterprise, namely the factors of the monster and thunder of the enterprise name; when the registered address is fuzzy and the registered address has the same enterprise, the risk of abnormal residence address can exist, wherein the enterprise with the same registered address may be a hosting agency enterprise; the contact information of the managed agency enterprise is also managed agency, and the contact information risks can be caused by the contact information, invalid contact information and contact information repetition rate; the process of constructing the bayesian network structure topology corresponding to the legal person abnormal risk refers to the description corresponding to fig. 2, and is not repeated.
Based on the optional embodiment, the business process information is obtained based on the target feature tag, the risk identification indexes are determined according to the business process information, the network nodes are determined based on the risk identification indexes, and a reasonable target identification network can be quickly constructed based on the network nodes, so that the enterprise to be identified is accurately identified.
Optionally, in step S13, analyzing the target identification data based on the target identification network, and obtaining the target risk probability corresponding to the object to be identified includes:
step S134 of generating a first conditional probability table using a preset prior probability, and generating a second conditional probability table using target identification data;
step S135, analyzing the first conditional probability table and the second conditional probability table based on the target identification network, and outputting initial risk probabilities corresponding to a plurality of network nodes;
and S136, updating the initial risk probability to obtain a target risk probability.
The first conditional probability table is a partial conditional probability table generated according to expert experience, the second conditional probability table is a partial conditional probability table based on data statistics, and the first conditional probability table and the second conditional probability table are combined to perform analysis processing, so that the posterior probability of each network node in the Bayesian network can be obtained, and the posterior probability can be updated and perfected by adjusting the prior probability.
Specifically, based on the bayesian network topology, each network node in fig. 3 needs to be assigned with a value, i.e., a condition probability table is generated. Fig. 4 is a schematic diagram of the state and prior probability distribution of the legal person abnormal risk and its leading nodes according to the embodiment of the application, and as shown in fig. 4, the conditional probability table needs to be based on objective historical data for a period of time, but it is difficult to obtain enough available risk data in the identification scenario of the bank open-shell enterprise. In addition to being based on the existing available data, some nodes in the embodiments of the present application may identify an initial conditional probability table based on experience of a service expert. Wherein, the node such as 'age by legal person' can obtain the proportion of 18-26 years old in the people who are taken as the legal person representatives through the existing sample. For example, "the beneficiary cannot penetrate the system by overseas personnel or institutions" cannot directly reflect the system through data, and needs to be confirmed after comprehensive evaluation from a business perspective in combination with expert experience.
Based on the above node assignments, the posterior probability distribution of all network nodes is calculated next:
suppose there are i nodes in the bayesian network, each node representing a variable or event, and each node corresponding to a conditional probability table. For node X i Assuming that it has k values, the probability of each value occurring is θ 1 ，θ 2 ，...，θ k 。
Existing observation data D, wherein X i The number of occurrences of each value is m 1 ，m 2 ，...，m k Then a likelihood function is obtained as
Assuming the prior distribution as a Dirichlet distribution, i.e.
Wherein alpha is 1 ，...，α k For considering the probability of each value appearing in advance, bayesian estimation can be used to find the posterior distribution:
P(θ 1 ，...，θ k |D)∝P(D|θ 1 ，...，θ k )P(θ 1 ，...，θ k )。
based on the above, the probability distribution of the legal person abnormity can be deduced through operation according to the conditional probability of each node. For example, a certain enterprise "legal person stands for age" is 32 years old, "high risk industry enterprise stands for" low, "and" beneficial person is unable to penetrate by foreign persons or organizations "is" yes. Through calculation, the probability of legal abnormality is 12.68%. And by analogy, calculating the posterior probability of all the related nodes of the enterprise to be evaluated.
Based on the optional embodiment, the first conditional probability table is generated by using the preset prior probability, the second conditional probability table is generated by using the target identification data, the first conditional probability table and the second conditional probability table are analyzed and processed based on the target identification network, the initial risk probabilities corresponding to the plurality of network nodes are output, and finally the initial risk probabilities are updated to obtain the target risk probabilities, so that the air-shell enterprises can be accurately identified.
Optionally, in step S136, performing update processing on the initial risk probability, and obtaining the target risk probability includes:
step S1361, adjusting the preset prior probability to obtain an adjustment result;
step S1362, update the initial risk probability based on the adjustment result to obtain the target risk probability.
Specifically, after data is updated, according to the enterprise information labels corresponding to the suspended accounts for a long time, the Bayesian network can automatically correct the prior probability distribution alpha corresponding to the suspended accounts, so that the posterior probability of the risk identification of the bare-case enterprises is closer to the real probability.
Based on the optional embodiment, the preset prior probability is adjusted to obtain an adjustment result, the initial risk probability is updated based on the adjustment result to obtain the target risk probability, more accurate posterior probability can be obtained, and the identification accuracy of the vacant shell enterprise is further improved.
Optionally, in step S14, generating the target prompt information according to the target risk probability includes:
step S141, determining risk grade information corresponding to an object to be identified by using the target risk probability;
and step S142, generating target prompt information based on the risk level information.
Specifically, based on the openness of the bayesian network, after data updating, except for counting the available labels, the banking staff can adjust the probability value of the expert experience condition according to the macroscopic environment and the business process, and then update the early warning information of the identification risk of the shell-less enterprise. If the conditions are not changed, the next step of outputting the posterior probability value of the network node can be directly carried out.
Further, the probability distribution of whether the enterprise is a vacant enterprise or not is obtained based on current enterprise information operation, and the probability distribution is divided into three levels of high risk, medium risk and low risk according to the probability.
And finally, displaying the risk level information on a graphical user interface of the terminal equipment for information prompt. For example, businesses rated "high risk" are prompted to "strictly handle operational risk, actually perform field review and accountability" for the public customer manager.
According to the method, the Bayesian network foundation of the vacant enterprises is established based on existing data mining and expert experience mainly for the risk identification problem of the vacant enterprises under the enterprise account setting scene, the prior probability of the network nodes is automatically assigned through Bayesian estimation according to existing objective data, and then posterior probability estimation is carried out on the probability that the newly registered enterprises are vacant enterprises.
The main advantages of the present application are:
1. the Bayesian idea is to make an inference after correcting the prior probability according to an experimental result under the condition of considering the prior probability, and make up for the problem of weak statistical data in a prior supervision scene to a certain extent by not completely depending on a statistical value.
2. The probability function (adjusting factor) in the Bayes formula can adjust the prior probability through the probability function, so that the problem of too strong subjectivity caused by only depending on the prior probability is avoided.
3. Compared with hierarchical analysis, the network analysis can express a more complex relation structure, and the hierarchical analysis comprises not only a hierarchical structure, but also a hierarchical structure with internal dependency and feedback, so that the model expression is stronger, and the actual business situation can be better fitted.
4. The posterior distribution obtained at the present stage can be used as the prior distribution of a certain stage in the future, the current posterior distribution can be used as the subsequent prior distribution along with the increase of data volume, and the distribution can be closer to the real probability distribution along with the continuous correction of the distribution, so that the method has good adaptivity.
Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but the former is a better implementation mode in many cases. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present application.
In this embodiment, a device for identifying an empty-shell enterprise is further provided, and the device is used to implement the foregoing embodiments and preferred embodiments, and the description of the device that has been already made is omitted. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware or a combination of software and hardware is also possible and contemplated.
Fig. 5 is a block diagram illustrating a structure of an empty business identification apparatus according to an embodiment of the present application, and as shown in fig. 5, the empty business identification apparatus 500 includes:
an obtaining module 501, configured to obtain target identification data, where the target identification data is used to perform risk identification on an object to be identified;
a first generating module 502, configured to generate a target feature tag based on the target identification data, where the target feature tag is used to determine a risk category of the object to be identified;
a processing module 503, configured to construct a target identification network by using the target feature tag, and analyze the target identification data based on the target identification network to obtain a target risk probability corresponding to the object to be identified, where the target identification network includes a plurality of network nodes, and the plurality of network nodes are used to perform probability analysis on the object to be identified;
a second generating module 504, configured to generate target prompt information according to the target risk probability, where the risk prompt information is used to perform risk prompt on the object to be identified.
Optionally, the obtaining module 501 is further configured to: acquiring initial identification data, wherein the initial identification data comprises enterprise attribute information and preset account information of an object to be identified; and carrying out discretization processing on the initial identification data to obtain target identification data.
Optionally, the first generating module 501 is further configured to: acquiring a preset labeling rule, wherein the preset labeling rule is used for expressing a historical classification rule for an object to be identified; and generating a target characteristic label based on a preset experience rule and target identification data.
Optionally, the processing module 503 is further configured to: acquiring business process information based on the target characteristic label; determining a plurality of risk identification indexes according to the business process information; a plurality of network nodes are determined based on the plurality of risk identification indicators, and a target identification network is constructed based on the plurality of network nodes.
Optionally, the processing module 503 is further configured to: generating a first conditional probability table using a preset prior probability, and generating a second conditional probability table using target identification data; analyzing the first conditional probability table and the second conditional probability table based on the target identification network, and outputting initial risk probabilities corresponding to the plurality of network nodes; and updating the initial risk probability to obtain a target risk probability.
Optionally, the processing module 503 is further configured to: adjusting the preset prior probability to obtain an adjustment result; and updating the initial risk probability based on the adjustment result to obtain the target risk probability.
Optionally, the second generating module 504 is further configured to: determining risk grade information corresponding to the object to be identified by using the target risk probability; and generating target prompt information based on the risk level information.
It should be noted that the above modules may be implemented by software or hardware, and for the latter, the following may be implemented, but not limited to: the modules are all positioned in the same processor; alternatively, the modules are located in different processors in any combination.
Embodiments of the present application further provide a computer-readable storage medium having a computer program stored therein, wherein the computer program is configured to perform the steps in any of the above method embodiments when executed.
Alternatively, in this embodiment, the above-mentioned nonvolatile storage medium may be configured to store a computer program for executing the steps of:
s1, acquiring target identification data, wherein the target identification data is used for carrying out risk identification on an object to be identified;
s2, generating a target characteristic label based on the target identification data, wherein the target characteristic label is used for determining the risk category of the object to be identified;
s3, constructing a target identification network by using the target characteristic tags, and analyzing target identification data based on the target identification network to obtain target risk probability corresponding to the object to be identified, wherein the target identification network comprises a plurality of network nodes, and the plurality of network nodes are used for performing probability analysis on the object to be identified;
and S4, generating target prompt information according to the target risk probability, wherein the risk prompt information is used for carrying out risk prompt on the object to be identified.
Optionally, in this embodiment, the nonvolatile storage medium may include but is not limited to: various media capable of storing computer programs, such as a usb disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk.
Embodiments of the present application further provide an electronic device, including a memory and a processor, where the memory stores a computer program, and the processor is configured to execute the computer program to perform the steps in any of the above method embodiments.
Optionally, in this embodiment, the processor may be configured to execute the following steps by a computer program:
s1, acquiring target identification data, wherein the target identification data is used for carrying out risk identification on an object to be identified;
s2, generating a target feature tag based on the target identification data, wherein the target feature tag is used for determining the risk category of the object to be identified;
s3, constructing a target identification network by using the target characteristic tags, and analyzing target identification data based on the target identification network to obtain target risk probability corresponding to the object to be identified, wherein the target identification network comprises a plurality of network nodes, and the plurality of network nodes are used for performing probability analysis on the object to be identified;
and S4, generating target prompt information according to the target risk probability, wherein the risk prompt information is used for carrying out risk prompt on the object to be identified.
Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation manners, and this embodiment is not described herein again.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technical content can be implemented in other manners. The above-described apparatus embodiments are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or may not be executed. In addition, the shown or discussed coupling or direct coupling or communication connection between each other may be an indirect coupling or communication connection through some interfaces, units or modules, and may be electrical or in other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention, which is substantially or partly contributed by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and amendments can be made without departing from the principle of the present invention, and these modifications and amendments should also be considered as the protection scope of the present invention.
Claims (10)
1. A method for identifying an empty shell enterprise is characterized by comprising the following steps:
acquiring target identification data, wherein the target identification data is used for carrying out risk identification on an object to be identified;
generating a target feature tag based on the target identification data, wherein the target feature tag is used for determining the risk category of the object to be identified;
constructing a target identification network by using the target feature tag, and analyzing the target identification data based on the target identification network to obtain a target risk probability corresponding to the object to be identified, wherein the target identification network comprises a plurality of network nodes, and the plurality of network nodes are used for performing probability analysis on the object to be identified;
and generating target prompt information according to the target risk probability, wherein the risk prompt information is used for carrying out risk prompt on the object to be identified.
2. The method for identifying an open-shell enterprise according to claim 1, wherein the obtaining of the target identification data comprises:
acquiring initial identification data, wherein the initial identification data comprises enterprise attribute information and preset account information of the object to be identified;
and carrying out discretization processing on the initial identification data to obtain the target identification data.
3. The method for identifying an empty shell enterprise according to claim 1, wherein generating the target feature tag based on the target identification data comprises:
acquiring a preset labeling rule, wherein the preset labeling rule is used for expressing a historical classification rule for the object to be identified;
and generating the target feature tag based on the preset experience rule and the target identification data.
4. The method for identifying an open-shell enterprise according to claim 1, wherein constructing the object identification network using the object feature tag comprises:
acquiring business process information based on the target feature tag;
determining a plurality of risk identification indexes according to the business process information;
determining the plurality of network nodes based on the plurality of risk identification indicators and constructing the target identification network based on the plurality of network nodes.
5. The method for identifying the shell-less enterprise according to claim 1, wherein analyzing the target identification data based on the target identification network to obtain the target risk probability corresponding to the object to be identified comprises:
generating a first conditional probability table by using a preset prior probability, and generating a second conditional probability table by using the target identification data;
analyzing the first conditional probability table and the second conditional probability table based on the target identification network, and outputting initial risk probabilities corresponding to the plurality of network nodes;
and updating the initial risk probability to obtain the target risk probability.
6. The method for identifying an empty-shell enterprise according to claim 5, wherein the step of updating the initial risk probability to obtain the target risk probability comprises:
adjusting the preset prior probability to obtain an adjustment result;
and updating the initial risk probability based on the adjustment result to obtain the target risk probability.
7. The method for identifying an open-shell enterprise according to claim 1, wherein generating the target prompt message according to the target risk probability comprises:
determining risk grade information corresponding to the object to be identified by using the target risk probability;
and generating the target prompt information based on the risk level information.
8. An empty shell enterprise identification device, comprising:
the system comprises an acquisition module, a risk identification module and a risk identification module, wherein the acquisition module is used for acquiring target identification data, and the target identification data is used for carrying out risk identification on an object to be identified;
a first generating module, configured to generate a target feature tag based on the target identification data, where the target feature tag is used to determine a risk category of the object to be identified;
the processing module is used for constructing a target identification network by using the target feature tag, analyzing the target identification data based on the target identification network and obtaining a target risk probability corresponding to the object to be identified, wherein the target identification network comprises a plurality of network nodes, and the plurality of network nodes are used for performing probability analysis on the object to be identified;
and the second generation module is used for generating target prompt information according to the target risk probability, wherein the risk prompt information is used for carrying out risk prompt on the object to be identified.
9. A computer-readable storage medium, comprising a stored program, wherein the program, when executed, controls an apparatus in which the computer-readable storage medium is located to perform the method for identifying an empty shell enterprise as claimed in any one of claims 1 to 7.
10. An electronic device, comprising: a memory storing an executable program; a processor configured to execute the program, wherein the program executes the method for identifying an empty shell enterprise according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310003349.XA CN115965464A (en) | 2023-01-03 | 2023-01-03 | Empty shell enterprise identification method and device, storage medium and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310003349.XA CN115965464A (en) | 2023-01-03 | 2023-01-03 | Empty shell enterprise identification method and device, storage medium and electronic device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115965464A true CN115965464A (en) | 2023-04-14 |
Family
ID=87357679
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310003349.XA Pending CN115965464A (en) | 2023-01-03 | 2023-01-03 | Empty shell enterprise identification method and device, storage medium and electronic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115965464A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116485559A (en) * | 2023-06-21 | 2023-07-25 | 杭州大鱼网络科技有限公司 | Batch insurance business processing risk monitoring method and system |
-
2023
- 2023-01-03 CN CN202310003349.XA patent/CN115965464A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116485559A (en) * | 2023-06-21 | 2023-07-25 | 杭州大鱼网络科技有限公司 | Batch insurance business processing risk monitoring method and system |
| CN116485559B (en) * | 2023-06-21 | 2023-09-01 | 杭州大鱼网络科技有限公司 | Batch insurance business processing risk monitoring method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109345399B (en) | Method, device, computer equipment and storage medium for evaluating risk of claim settlement | |
| CN110070391B (en) | Data processing method and device, computer readable medium and electronic equipment | |
| US10817779B2 (en) | Bayesian network based hybrid machine learning | |
| CA3032693A1 (en) | Utilizing artificial intelligence to make a prediction about an entity based on user sentiment and transaction history | |
| CN111145009A (en) | Method and device for evaluating risk after user loan and electronic equipment | |
| CN114186626A (en) | Abnormity detection method and device, electronic equipment and computer readable medium | |
| CN116402512B (en) | Account security check management method based on artificial intelligence | |
| CN111192133A (en) | Method and device for generating risk model after user loan and electronic equipment | |
| CN110322254A (en) | Online fraud recognition methods, device, medium and electronic equipment | |
| Javedani Sadaei et al. | Multilayer stock forecasting model using fuzzy time series | |
| CN111369344A (en) | Method and device for dynamically generating early warning rule | |
| US11556873B2 (en) | Cognitive automation based compliance management system | |
| CN114078050A (en) | Loan overdue prediction method and device, electronic equipment and computer readable medium | |
| CN115965464A (en) | Empty shell enterprise identification method and device, storage medium and electronic device | |
| CN115545886A (en) | Overdue risk identification method, overdue risk identification device, overdue risk identification equipment and storage medium | |
| US20220129754A1 (en) | Utilizing machine learning to perform a merger and optimization operation | |
| CN112950359B (en) | User identification method and device | |
| CN114092230A (en) | Data processing method and device, electronic equipment and computer readable medium | |
| CN113392920A (en) | Method, apparatus, device, medium, and program product for generating cheating prediction model | |
| CN108460049A (en) | A kind of method and system of determining information category | |
| CN115619245A (en) | Portrait construction and classification method and system based on data dimension reduction method | |
| CN117010892A (en) | Payment risk detection method, device, electronic equipment and readable medium | |
| CN115600818A (en) | Multi-dimensional scoring method and device, electronic equipment and storage medium | |
| CN115147195A (en) | Bidding purchase risk monitoring method, apparatus, device and medium | |
| CN112712270A (en) | Information processing method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |