CN109583620B - Enterprise potential risk early warning method, enterprise potential risk early warning device, computer equipment and storage medium - Google Patents
Enterprise potential risk early warning method, enterprise potential risk early warning device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109583620B CN109583620B CN201811184210.5A CN201811184210A CN109583620B CN 109583620 B CN109583620 B CN 109583620B CN 201811184210 A CN201811184210 A CN 201811184210A CN 109583620 B CN109583620 B CN 109583620B
- Authority
- CN
- China
- Prior art keywords
- enterprise
- association
- node
- propagation
- risk
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000012545 processing Methods 0.000 claims abstract description 48
- 238000004590 computer program Methods 0.000 claims description 28
- 230000008901 benefit Effects 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000644 propagated effect Effects 0.000 description 3
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000007418 data mining Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
Abstract
The application relates to the technical field of big data, is applied to the financial industry, and provides an enterprise potential risk early warning method, an enterprise potential risk early warning device, computer equipment and a storage medium. The method comprises the following steps: acquiring an enterprise association graph, extracting node association relations, acquiring a risk parameter label carried by a propagation start node in the enterprise association graph, acquiring a propagation path of the risk parameter label according to the risk parameter label and the node association relations, acquiring propagation coefficients among nodes in the propagation path, and performing label propagation processing on the risk parameter label according to the propagation path and the propagation coefficients to acquire node potential risk early warning information. According to the method, through enterprise association graphs and label propagation processing, the association relations among the corresponding nodes of the enterprise are utilized to determine propagation paths and propagation coefficients, effective propagation of risk parameter labels is carried out, potential risk early warning of the enterprise is obtained through rapid and accurate analysis, and compared with a manual analysis mode, the method improves analysis efficiency and early warning reliability of the potential risk of the enterprise.
Description
Technical Field
The present disclosure relates to the field of big data technologies, and in particular, to a method and apparatus for early warning of potential risks of an enterprise, a computer device, and a storage medium.
Background
With the progress of science and technology and the rapid development of networks, a large data age has been entered, and in the public data of enterprises, a lot of valuable information data, such as investment relation, cooperation relation, bidding information and the like, among enterprises can be seen. The association relationship between enterprises can be intuitively reflected through the data such as cash flow, enterprise mergers and the like, but the potential risk relationship between enterprises cannot be well found.
In the traditional method, risk analysis of enterprises relies on manual collection of data by analysts, research reports are written, and the relevance of risks among enterprises is analyzed according to business experience, so that potential risks of the enterprises are determined, and the method is high in difficulty and low in efficiency.
Disclosure of Invention
In view of the foregoing, it is desirable to provide an enterprise risk potential warning method, apparatus, computer device and storage medium that can improve analysis efficiency.
A method for enterprise potential risk early warning, the method comprising:
Acquiring an enterprise association graph, and extracting node association relations in the enterprise association graph;
acquiring a risk parameter label carried by a propagation starting node in the enterprise association graph;
acquiring a propagation path of the risk parameter label according to the risk parameter label and the node association relation;
acquiring propagation coefficients among nodes in the propagation path;
performing label propagation processing on the risk parameter label according to the propagation path and the propagation coefficient;
and obtaining potential risk early warning information of the enterprise corresponding to each node according to the label propagation processing result of each node in the enterprise association graph.
In one embodiment, before the obtaining the enterprise association graph and obtaining the node association relationship in the enterprise association graph, the method further includes:
acquiring enterprise association data;
extracting information from the enterprise association data to obtain nodes, node association relations and node association relation weight values;
and constructing the enterprise association graph according to the nodes, the node association relationships and the node association relationship weights.
In one embodiment, the extracting information from the enterprise association data to obtain the node, the node association relationship and the node association relationship weight includes:
Extracting associated enterprises and associated words contained in the enterprise associated data;
obtaining the node according to the associated enterprise;
obtaining the node association relationship and the relationship category corresponding to the node association relationship according to the association word;
and acquiring the proportion of the node association relation in the relation category, and acquiring the node association relation weight according to the proportion.
In one embodiment, the obtaining the proportion of the node association relationship in the relationship category, before obtaining the node association relationship weight according to the proportion, further includes:
searching default data of the associated enterprises according to the enterprise associated data;
when the association enterprises all have the default data, judging that the node association relationship is an effective association relationship;
and counting the number of the effective association relations in the relation category, and determining the proportion of the node association relations in the relation category.
In one embodiment, before the obtaining the propagation coefficient between the nodes in the propagation path, the method further includes:
acquiring time damage parameters of nodes of the propagation path;
And acquiring the corresponding weight of the associated node in the enterprise association graph, and determining the propagation coefficient between the adjacent nodes according to the time damage parameter and the corresponding weight of the node association relation.
In one embodiment, before the obtaining the time damage parameter of the node of the propagation path, the method further includes:
acquiring occurrence time difference of the default data among nodes of the propagation path;
and determining a time damage parameter according to the occurrence time difference of the default data.
In one embodiment, after obtaining the potential risk early warning information of the enterprise corresponding to each node according to the label propagation processing result of each node in the enterprise association graph, the method further includes:
acquiring enterprise information to be analyzed, and determining corresponding nodes to be analyzed of the enterprise to be analyzed in the enterprise association graph;
reading various node association relations related to the nodes to be analyzed, and acquiring risk propagation processing results of the various node association relations related to the nodes to be analyzed;
and weighting the risk propagation processing result to obtain comprehensive potential risk information of the enterprise to be analyzed corresponding to the node to be analyzed. .
An enterprise risk potential warning device, the device comprising:
the node association relation extraction module is used for acquiring an enterprise association map and extracting node association relations in the enterprise association map;
the risk parameter label acquisition module is used for acquiring a risk parameter label carried by a propagation starting node in the enterprise association graph;
the propagation path obtaining module is used for obtaining the propagation path of the risk parameter label according to the risk parameter label and the node association relation;
the propagation coefficient obtaining module is used for obtaining the propagation coefficient among the nodes in the propagation path;
the tag propagation module is used for performing tag propagation processing on the risk parameter tag according to the propagation path and the propagation coefficient;
the potential risk obtaining module is used for obtaining potential risk early warning information of the enterprise corresponding to each node according to the label propagation processing result of each node in the enterprise association graph.
A computer device comprising a memory storing a computer program and a processor which when executing the computer program performs the steps of:
acquiring an enterprise association graph, and extracting node association relations in the enterprise association graph;
Acquiring a risk parameter label carried by a propagation starting node in the enterprise association graph;
acquiring a propagation path of the risk parameter label according to the risk parameter label and the node association relation;
acquiring propagation coefficients among nodes in the propagation path;
performing label propagation processing on the risk parameter label according to the propagation path and the propagation coefficient;
and obtaining potential risk early warning information of the enterprise corresponding to each node according to the label propagation processing result of each node in the enterprise association graph.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
acquiring an enterprise association graph, and extracting node association relations in the enterprise association graph;
acquiring a risk parameter label carried by a propagation starting node in the enterprise association graph;
acquiring a propagation path of the risk parameter label according to the risk parameter label and the node association relation;
acquiring propagation coefficients among nodes in the propagation path;
performing label propagation processing on the risk parameter label according to the propagation path and the propagation coefficient;
And obtaining potential risk early warning information of the enterprise corresponding to each node according to the label propagation processing result of each node in the enterprise association graph.
According to the method, the device, the computer equipment and the storage medium for early warning the potential risk of the enterprise, the node association relation is extracted through the enterprise association graph, the propagation path of the risk parameter label is obtained according to the risk parameter label carried by the propagation starting node and the node association relation, label propagation processing is carried out on the risk parameter label according to the propagation path and the obtained propagation coefficient, so that node potential risk early warning information is obtained.
Drawings
FIG. 1 is a flow chart of an enterprise risk potential warning method in one embodiment;
FIG. 2 is a flow chart of an enterprise risk potential warning method according to another embodiment;
FIG. 3 is a flow chart illustrating the sub-steps of step S140 of FIG. 2 in one embodiment;
FIG. 4 is a block diagram of an enterprise risk potential warning device in one embodiment;
fig. 5 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The enterprise potential risk early warning method provided by the application is applied to the financial industry, the node association relation is extracted through the enterprise association graph, the propagation path of the risk parameter label is obtained according to the risk parameter label carried by the propagation starting node and the node association relation, label propagation processing is carried out on the risk parameter label according to the propagation path and the acquired propagation coefficient, thereby node potential risk early warning information is obtained, the analysis of the potential risk condition of the enterprise is realized, early warning information is obtained, the enterprise potential risk early warning method of the application can be realized through a computer program, the computer program can be loaded on a terminal, and the terminal can be but not limited to various personal computers, notebook computers, smartphones and tablet computers.
In one embodiment, as shown in fig. 1, there is provided an enterprise risk potential warning method, including the following steps:
step S200, an enterprise association graph is obtained, and node association relations in the enterprise association graph are extracted.
The enterprise association graph comprises enterprise multidimensional information, a relation link between enterprises is reflected, various association relations in big data are clearly displayed, the enterprise association graph is composed of nodes, edges and weights of the edges, each node represents an enterprise entity, each edge represents the association relation between enterprises, each edge is a directed line, the line direction represents a main body and a receptor of the association relation, and the weights of the edges represent the strength of the relation between the nodes. According to the edges of the enterprise relationship graph, the relationship between two enterprises can be obtained, and the node association relationship for representing the enterprise relationship is extracted.
Step S300, acquiring a risk parameter label carried by a propagation starting node in an enterprise association graph.
The transmission starting node is a node marked with a set label, the set label can be a risk parameter label or other labels needing transmission analysis, the risk parameter label is a parameter index obtained by calculating the risk data of an enterprise which has generated the risk data. In the embodiment, the propagation start node may be a neighboring node of the node that does not include the set tag, and the corresponding propagation layer number is 1, or may be a node indirectly associated with the node that does not include the set tag through the intermediate node, and the intermediate node may be a node that includes the set tag, and the corresponding propagation layer number is 2 or more. In an embodiment, the risk parameter labels of the association relationships of the different categories are different, for example, when the association relationship category is a loan, the corresponding risk parameter label is a loan risk parameter label, and when the association relationship category is an investment, the corresponding risk parameter label is an investment risk parameter label.
Step S400, according to the risk parameter labels and the node association relations, the propagation paths of the risk parameter labels are obtained.
The propagation path of the risk parameter label refers to a path for propagating risk label parameters of a node with the risk parameter label to other nodes, and the propagation path comprises a propagation start node, a propagation intermediate node and a propagation end node, wherein the propagation start node and the propagation intermediate node can be determined by the risk parameter label carried by the node, the connection relationship between the propagation start node and the propagation intermediate node, the connection relationship between a plurality of propagation intermediate nodes, and the connection relationship between the propagation intermediate start point and the propagation end start point can be determined by the node association relationship, and the propagation path of the risk parameter label is obtained according to the determined node and the connection relationship. In an embodiment, in each step of node label propagation, each node updates its own label according to the labels of the adjacent nodes, and the risk parameter label of the propagation start node may reach the propagation end start point through multi-layer propagation, update the risk commitment book label of the propagation intermediate node, and obtain the risk parameter label of the propagation end start point.
Step S500, obtaining propagation coefficients among nodes in the propagation path.
The propagation coefficient refers to the influence weight of the risk parameter propagation, and the similarity between the propagation coefficient and the node, namely the node association relation weight is relevant, the larger the node association relation weight is, the larger the influence weight of the adjacent node to the label is, the more consistent the labels of the similar nodes tend to be, and the easier the labels of the similar nodes are propagated. The propagation coefficient can be determined by the node association relation weight in the enterprise association graph, or can be determined by the node association relation weight and other damage parameters according to set requirements, for example, when the risk propagation parameter is greatly influenced by time, the propagation coefficient can be determined by the node association relation weight and the time damage parameter.
Step S600, performing label propagation processing on the risk parameter labels according to the propagation paths and the propagation coefficients.
The label propagation processing can be performed through a label propagation algorithm, the label propagation algorithm is a graph-based semi-supervised learning method, the basic idea is to predict label information of unlabeled nodes by using label information of labeled nodes, edges of the nodes represent similarity of two nodes, labels of the nodes are transmitted to other nodes according to the similarity, the label data is a source, label data are labeled, and the label is easier to propagate as the similarity of the nodes is larger. And according to the propagation path and the propagation coefficient, the risk parameter label of the propagation starting node is propagated to the next node and is propagated in sequence, so that a label propagation processing result, namely the risk parameter label of the propagation ending node, is obtained.
And step S700, obtaining potential risk early warning information of each node corresponding to the enterprise according to the label propagation processing result of each node in the enterprise association graph.
According to the label propagation processing result, the node which does not contain the risk data label is enabled to obtain the corresponding label, the label content is analyzed, the potential risk information of the node is obtained, and when the risk information meets the preset early warning condition, the potential risk early warning information corresponding to the node is pushed.
According to the enterprise potential risk early warning method, the node association relation is extracted through the enterprise association graph, the propagation path of the risk parameter label is obtained according to the risk parameter label carried by the propagation start node and the node association relation, label propagation processing is carried out on the risk parameter label according to the propagation path and the obtained propagation coefficient, so that node potential risk early warning information is obtained.
In one embodiment, as shown in fig. 2, step S200, before obtaining the enterprise association graph and obtaining the node association relationship in the enterprise association graph, further includes:
step S120, acquiring enterprise association data.
And step S140, extracting information from the enterprise association data to obtain nodes, node association relations and node association relation weights.
Step S160, an enterprise association graph is constructed according to the nodes, the node association relationships and the node association relationship weights.
The enterprise association data refers to related data among enterprises, web pages, search engines and the like can be crawled by adopting a crawler technology to collect and acquire, and multi-azimuth and comprehensive enterprise association data comprising business information, stock market information, management information, risk information, financial information, public opinion information, administrative supervision information, credit information and the like is obtained through data mining technology. Such as business name, legal representatives thereof, investors, liabilities or creditors, branches, supply chain relationships, litigation relationships, guarantees, public opinion references, document references, etc., by extracting keywords from the business association data to determine whether there are associated businesses and associated words; when the enterprise association data contains 2 or more enterprise information, screening out association enterprises, and determining association relations among the association enterprises and relation categories corresponding to the association relations, such as loan relations, stock relations and purchasing relations, according to association words. Etc., where there may be multiple relationships between two enterprises. For example, a stock-holding relationship and a lending relationship exist between enterprise a and enterprise B at the same time.
In one embodiment, as shown in fig. 3, step S140, extracting information from the enterprise association data, and obtaining the node, the node association relationship, and the node association relationship weight includes:
in step S142, the related enterprises and related words contained in the enterprise related data are extracted.
Step S144, obtaining the nodes according to the associated enterprises.
Step S146, according to the association words, obtaining the node association relationship and the relationship category corresponding to the node association relationship.
Step S148, the occupied proportion of the node association relation in the relation category is obtained, and the node association relation weight is obtained according to the occupied proportion.
For the acquired enterprise association data, a named entity recognition mode can be adopted to recognize enterprise names in a text, when the enterprise names recognized in the text comprise a plurality of enterprise names, the enterprise in the text is an association enterprise, the association words of the association enterprise are extracted through part-of-speech analysis, for example, the acquired enterprise association data are news titles of 'three-in-one dollars of all-in-one dollars' and hungry, the enterprise names are recognized to comprise 'three-in-one's first and 'hungry', the association words are 'acquired' as the association enterprises, the 'three-in-one's first and 'hungry' are taken as nodes of an enterprise association map according to recognition and analysis results, the node association relationship is acquired, and the corresponding relationship category is acquired relationship. By counting the number of the association relations of each category meeting the set condition in the enterprise association graph, the proportion occupied by the node association relation correspondence between every two nodes can be determined, for example, if 8 investment relations meeting the set condition in the enterprise association graph exist, the proportion occupied by the node association relation correspondence between every two nodes is 1/8.
In one embodiment, the method further includes the steps of:
and searching the default data of the associated enterprise according to the enterprise associated data.
When the associated enterprises all have default data, the node association relationship is judged to be an effective association relationship.
And counting the number of the effective association relations in the relation class, and determining the proportion of the node association relations in the relation class.
In the propagation process of the risk parameter labels, mainly considering the default situation of enterprises, determining the associated enterprises according to the enterprise association data, so as to find out whether the associated enterprises have the history situation of default or not, when the associated enterprises have the default data at the same time, the corresponding node association relations among the associated enterprises are effective relations, and the propagation of the risk parameter labels can be realized, and the number of the effective association relations in the relation category corresponding to the node association relations is counted, so that the proportion of the node association relations in the relation category is determined. If one enterprise in the associated enterprises does not have the default data or both enterprises do not have the default data, the node association relationship between the associated enterprises is an invalid relationship.
In one embodiment, before obtaining the propagation coefficient between the nodes in the propagation path, the method further includes:
the time damage parameters of the nodes of the propagation path are acquired.
And acquiring the corresponding weight of the associated node in the enterprise association graph, and determining the propagation coefficient between the adjacent nodes according to the time damage parameters and the corresponding weight of the node association relation.
When the risk level changes with time, the time damage coefficient is an influence factor of risk parameter label transmission and is used for measuring the attenuation level of risk conduction. The larger the weight of the node association relationship between two association enterprises is, the smaller the time damage is, which means that the more similar the two nodes are, the more favorable the propagation of risk parameter labels is.
In one embodiment, before obtaining the time damage parameter of the node of the propagation path, the method further includes:
the occurrence time difference of the default data among the nodes of the propagation path is acquired.
And determining a time damage parameter according to the occurrence time difference of the default data.
Defining a time loss benefit coefficient by associating time differences in occurrence of breach data between enterprises:wherein x is the occurrence time difference of two enterprise default data, θ is the degree of damage, and is a parameter that can be adjusted according to the actual business situation.
In one embodiment, after obtaining the potential risk early warning information of each node corresponding to the enterprise according to the label propagation processing result of each node in the enterprise association graph, the method further includes:
acquiring enterprise information to be analyzed, and determining corresponding nodes to be analyzed of the enterprise to be analyzed in an enterprise association graph;
reading various node association relations related to the nodes to be analyzed, and acquiring risk propagation processing results of the various node association relations related to the nodes to be analyzed;
and weighting the risk propagation processing result to obtain comprehensive potential risk information of the node to be analyzed corresponding to the enterprise to be analyzed.
When an enterprise is newly added in a new enterprise association graph and the potential risk situation of the enterprise needs to be analyzed, firstly determining node association relations between nodes to be analyzed corresponding to the enterprise to be analyzed in the enterprise association graph and other nodes, searching a propagation starting node corresponding to the category and a risk parameter label of the propagation starting node by reading various node association relations related to the nodes to be analyzed, determining a propagation path according to the risk parameter label and the node association relations, acquiring corresponding propagation coefficients, acquiring risk propagation processing results corresponding to various association relations of the nodes to be analyzed through a label propagation algorithm, and finally weighting various risk propagation processing results of the nodes to be analyzed to obtain comprehensive potential risk information of the enterprise to be analyzed.
It should be understood that, although the steps in the flowcharts of fig. 1-3 are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in fig. 1-3 may include multiple sub-steps or phases that are not necessarily performed at the same time, but may be performed at different times, nor does the order in which the sub-steps or phases are performed necessarily occur sequentially, but may be performed alternately or alternately with at least a portion of the sub-steps or phases of other steps or other steps.
In one embodiment, as shown in fig. 4, there is provided an enterprise risk potential warning device, including:
the node association relation extraction module 200 is configured to obtain an enterprise association graph, and extract a node association relation in the enterprise association graph.
The risk parameter label obtaining module 300 is configured to obtain a risk parameter label carried by a propagation start node in the enterprise association graph.
The propagation path obtaining module 400 is configured to obtain a propagation path of the risk parameter label according to the risk parameter label and the node association relationship.
The propagation coefficient obtaining module 500 is configured to obtain propagation coefficients between nodes in the propagation path.
The tag propagation module 600 is configured to perform tag propagation processing on the risk parameter tag according to the propagation path and the propagation coefficient.
The potential risk obtaining module 700 is configured to obtain potential risk early warning information corresponding to each node in the enterprise according to the label propagation processing result of each node in the enterprise association graph.
In one embodiment, the enterprise potential risk early warning device further includes an enterprise association graph construction module, configured to acquire enterprise association data, extract information from the enterprise association data, obtain nodes, node association relationships, and node association relationship weights, and construct an enterprise association graph according to the nodes, node association relationships, and node association relationship weights.
In one embodiment, the enterprise association graph construction module is further configured to extract an association enterprise and an association word included in the enterprise association data, obtain a node according to the association enterprise, obtain a node association relationship and a relationship category corresponding to the node association relationship according to the association word, obtain a proportion of the node association relationship in the relationship category, and obtain a node association relationship weight according to the proportion.
In one embodiment, the enterprise association graph construction module is further configured to search for default data of the associated enterprise according to the enterprise association data, determine that the node association relationship is an effective association relationship when the default data exists in the associated enterprise, count the number of the effective association relationships in the relationship category, and determine the proportion of the node association relationship in the relationship category.
In one embodiment, the enterprise potential risk early warning device further includes a propagation coefficient determining module, configured to obtain a time damage parameter of a node of the propagation path, obtain a corresponding weight of an associated node in the enterprise association graph, and determine a propagation coefficient between adjacent nodes according to the time damage parameter and the corresponding weight of the node association relationship.
In one embodiment, the propagation coefficient determining module is further configured to obtain an occurrence time difference of the default data between nodes of the propagation path, and determine the time damage parameter according to the occurrence time difference of the default data.
In one embodiment, the enterprise potential risk early warning device further includes a comprehensive potential risk information acquisition module, configured to acquire enterprise information to be analyzed, determine corresponding nodes to be analyzed of the enterprise to be analyzed in an enterprise association graph, read association relationships of various nodes related to the nodes to be analyzed, acquire risk propagation processing results of the association relationships of the various nodes related to the nodes to be analyzed, and weight the risk propagation processing results to obtain comprehensive potential risk information of the enterprise to be analyzed corresponding to the nodes to be analyzed.
According to the enterprise potential risk early warning device, the node association relation is extracted through the enterprise association graph, the propagation path of the risk parameter label is obtained according to the risk parameter label carried by the propagation start node and the node association relation, label propagation processing is carried out on the risk parameter label according to the propagation path and the obtained propagation coefficient, so that node potential risk early warning information is obtained.
For specific definitions of the enterprise risk warning device, reference may be made to the above definition of the enterprise risk warning method, which is not repeated here. The modules in the enterprise risk potential warning device can be all or partially implemented by software, hardware and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a terminal, and the internal structure of which may be as shown in fig. 5. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program when executed by a processor implements an enterprise risk potential warning method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in fig. 5 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory storing a computer program and a processor that when executing the computer program performs the steps of:
acquiring an enterprise association graph, and extracting node association relations in the enterprise association graph;
acquiring a risk parameter label carried by a propagation starting node in an enterprise association graph;
acquiring a propagation path of the risk parameter label according to the risk parameter label and the node association relation;
acquiring propagation coefficients among nodes in a propagation path;
performing label propagation processing on the risk parameter label according to the propagation path and the propagation coefficient;
and obtaining potential risk early warning information of each node corresponding to the enterprise according to the label propagation processing result of each node in the enterprise association graph.
In one embodiment, the processor when executing the computer program further performs the steps of:
acquiring enterprise association data;
extracting information from the enterprise association data to obtain nodes, node association relations and node association relation weight values;
and constructing an enterprise association graph according to the nodes, the node association relationships and the node association relationship weights.
In one embodiment, the processor when executing the computer program further performs the steps of:
extracting associated enterprises and associated words contained in the enterprise associated data;
obtaining nodes according to the associated enterprises;
obtaining a node association relation and a relation category corresponding to the node association relation according to the association word;
and acquiring the proportion of the node association relation in the relation category, and acquiring the node association relation weight according to the proportion.
In one embodiment, the processor when executing the computer program further performs the steps of:
searching default data of the associated enterprises according to the enterprise associated data;
when the associated enterprises all have default data, judging that the node association relationship is an effective association relationship;
and counting the number of the effective association relations in the relation class, and determining the proportion of the node association relations in the relation class.
In one embodiment, the processor when executing the computer program further performs the steps of:
acquiring time damage parameters of nodes of a propagation path;
and acquiring the corresponding weight of the associated node in the enterprise association graph, and determining the propagation coefficient between the adjacent nodes according to the time damage parameters and the corresponding weight of the node association relation.
In one embodiment, the processor when executing the computer program further performs the steps of:
acquiring occurrence time difference of default data among nodes of a propagation path;
and determining a time damage parameter according to the occurrence time difference of the default data.
In one embodiment, the processor when executing the computer program further performs the steps of:
acquiring enterprise information to be analyzed, and determining corresponding nodes to be analyzed of the enterprise to be analyzed in an enterprise association graph;
reading various node association relations related to the nodes to be analyzed, and acquiring risk propagation processing results of the various node association relations related to the nodes to be analyzed;
and weighting the risk propagation processing result to obtain comprehensive potential risk information of the node to be analyzed corresponding to the enterprise to be analyzed.
According to the computer equipment for realizing the enterprise potential risk early warning method, the node association relation is extracted through the enterprise association graph, the propagation path of the risk parameter label is obtained according to the risk parameter label carried by the propagation starting node and the node association relation, label propagation processing is carried out on the risk parameter label according to the propagation path and the obtained propagation coefficient, so that node potential risk early warning information is obtained.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring an enterprise association graph, and extracting node association relations in the enterprise association graph;
acquiring a risk parameter label carried by a propagation starting node in an enterprise association graph;
acquiring a propagation path of the risk parameter label according to the risk parameter label and the node association relation;
acquiring propagation coefficients among nodes in a propagation path;
performing label propagation processing on the risk parameter label according to the propagation path and the propagation coefficient;
and obtaining potential risk early warning information of each node corresponding to the enterprise according to the label propagation processing result of each node in the enterprise association graph.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring enterprise association data;
extracting information from the enterprise association data to obtain nodes, node association relations and node association relation weight values;
and constructing an enterprise association graph according to the nodes, the node association relationships and the node association relationship weights.
In one embodiment, the computer program when executed by the processor further performs the steps of:
Extracting associated enterprises and associated words contained in the enterprise associated data;
obtaining nodes according to the associated enterprises;
obtaining a node association relation and a relation category corresponding to the node association relation according to the association word;
and acquiring the proportion of the node association relation in the relation category, and acquiring the node association relation weight according to the proportion.
In one embodiment, the computer program when executed by the processor further performs the steps of:
searching default data of the associated enterprises according to the enterprise associated data;
when the associated enterprises all have default data, judging that the node association relationship is an effective association relationship;
and counting the number of the effective association relations in the relation class, and determining the proportion of the node association relations in the relation class.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring time damage parameters of nodes of a propagation path;
and acquiring the corresponding weight of the associated node in the enterprise association graph, and determining the propagation coefficient between the adjacent nodes according to the time damage parameters and the corresponding weight of the node association relation.
In one embodiment, the computer program when executed by the processor further performs the steps of:
Acquiring occurrence time difference of default data among nodes of a propagation path;
and determining a time damage parameter according to the occurrence time difference of the default data.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring enterprise information to be analyzed, and determining corresponding nodes to be analyzed of the enterprise to be analyzed in an enterprise association graph;
reading various node association relations related to the nodes to be analyzed, and acquiring risk propagation processing results of the various node association relations related to the nodes to be analyzed;
and weighting the risk propagation processing result to obtain comprehensive potential risk information of the node to be analyzed corresponding to the enterprise to be analyzed.
According to the method for realizing the enterprise potential risk early warning, the node association relation is extracted through the enterprise association graph, the propagation path of the risk parameter label is obtained according to the risk parameter label carried by the propagation starting node and the node association relation, label propagation processing is carried out on the risk parameter label according to the propagation path and the obtained propagation coefficient, so that node potential risk early warning information is obtained.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples represent only a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.
Claims (10)
1. A method for enterprise potential risk early warning, the method comprising:
acquiring an enterprise association graph, and extracting node association relations in the enterprise association graph;
acquiring a risk parameter label carried by a propagation starting node in the enterprise association graph;
acquiring a propagation path of the risk parameter label according to the risk parameter label and the node association relation;
Acquiring occurrence time difference of the default data among nodes of the propagation path;
determining time damage parameters according to the occurrence time difference of the default data; wherein, the time loss and benefit parameter is a time loss and benefit coefficient:wherein x is the occurrence time difference value of two enterprise default data, θ is the benefit degree, and the benefit degree is a parameter which can be adjusted according to the actual service condition;
acquiring corresponding weights of the node association relations in the enterprise association graphs, and determining propagation coefficients among nodes in the propagation path according to the time damage parameters and the corresponding weights of the node association relations;
performing label propagation processing on the risk parameter label according to the propagation path and the propagation coefficient;
and obtaining potential risk early warning information of the enterprise corresponding to each node according to the label propagation processing result of each node in the enterprise association graph.
2. The method of claim 1, wherein before the step of obtaining the enterprise association graph and obtaining the node association relationship in the enterprise association graph, further comprises:
acquiring enterprise association data;
extracting information from the enterprise association data to obtain nodes, node association relations and node association relation weight values;
And constructing the enterprise association graph according to the nodes, the node association relationships and the node association relationship weights.
3. The method of claim 2, wherein the extracting information from the enterprise association data to obtain nodes, node association relationships, and node association relationship weights comprises:
extracting associated enterprises and associated words contained in the enterprise associated data;
obtaining the node according to the associated enterprise;
obtaining the node association relationship and the relationship category corresponding to the node association relationship according to the association word;
and acquiring the proportion of the node association relation in the relation category, and acquiring the node association relation weight according to the proportion.
4. The method of claim 3, wherein the obtaining the proportion of the node association relationship in the relationship category, before obtaining the node association relationship weight according to the proportion, further comprises:
searching default data of the associated enterprises according to the enterprise associated data;
when the association enterprises all have the default data, judging that the node association relationship is an effective association relationship;
And counting the number of the effective association relations in the relation category, and determining the proportion of the node association relations in the relation category.
5. The method of claim 1, wherein after obtaining the potential risk early warning information of the enterprise corresponding to each node according to the label propagation processing result of each node in the enterprise association graph, further comprises:
acquiring enterprise information to be analyzed, and determining corresponding nodes to be analyzed of the enterprise to be analyzed in the enterprise association graph;
reading various node association relations related to the nodes to be analyzed, and acquiring risk propagation processing results of the various node association relations related to the nodes to be analyzed;
and weighting the risk propagation processing result to obtain comprehensive potential risk information of the enterprise to be analyzed corresponding to the node to be analyzed.
6. An enterprise risk potential warning device, the device comprising:
the node association relation extraction module is used for acquiring an enterprise association map and extracting node association relations in the enterprise association map;
the risk parameter label acquisition module is used for acquiring a risk parameter label carried by a propagation starting node in the enterprise association graph;
The propagation path obtaining module is used for obtaining the propagation path of the risk parameter label according to the risk parameter label and the node association relation;
the propagation coefficient obtaining module is used for obtaining the occurrence time difference of the default data among the nodes of the propagation path; determining time damage parameters according to the occurrence time difference of the default data; acquiring corresponding weights of the node association relations in the enterprise association graphs, and determining propagation coefficients among nodes in the propagation path according to the time damage parameters and the corresponding weights of the node association relations; wherein, the time loss and benefit parameter is a time loss and benefit coefficient:wherein x is two enterprise violationsAbout the occurrence time difference value of the data, wherein theta is the damage degree, and the damage degree is a parameter which can be adjusted according to the actual service condition;
the tag propagation module is used for performing tag propagation processing on the risk parameter tag according to the propagation path and the propagation coefficient;
the potential risk obtaining module is used for obtaining potential risk early warning information of the enterprise corresponding to each node according to the label propagation processing result of each node in the enterprise association graph.
7. The apparatus of claim 6, wherein the enterprise risk potential warning apparatus further comprises an enterprise association graph construction module configured to obtain enterprise association data; extracting information from the enterprise association data to obtain nodes, node association relations and node association relation weight values; and constructing the enterprise association graph according to the nodes, the node association relationships and the node association relationship weights.
8. The apparatus of claim 7, wherein the enterprise association graph construction module is further configured to extract associated enterprises and associated words contained in the enterprise association data; obtaining the node according to the associated enterprise; obtaining the node association relationship and the relationship category corresponding to the node association relationship according to the association word; and acquiring the proportion of the node association relation in the relation category, and acquiring the node association relation weight according to the proportion.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 5 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811184210.5A CN109583620B (en) | 2018-10-11 | 2018-10-11 | Enterprise potential risk early warning method, enterprise potential risk early warning device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811184210.5A CN109583620B (en) | 2018-10-11 | 2018-10-11 | Enterprise potential risk early warning method, enterprise potential risk early warning device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109583620A CN109583620A (en) | 2019-04-05 |
| CN109583620B true CN109583620B (en) | 2024-03-01 |
Family
ID=65920306
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811184210.5A Active CN109583620B (en) | 2018-10-11 | 2018-10-11 | Enterprise potential risk early warning method, enterprise potential risk early warning device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109583620B (en) |
Families Citing this family (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110163413A (en) * | 2019-04-15 | 2019-08-23 | 深圳壹账通智能科技有限公司 | Enterprise supervision and method for early warning, device, computer equipment and readable storage medium storing program for executing |
| CN110245165B (en) * | 2019-05-20 | 2023-04-11 | 平安科技（深圳）有限公司 | Risk conduction associated graph optimization method and device and computer equipment |
| CN110223168B (en) * | 2019-06-24 | 2022-06-28 | 浪潮卓数大数据产业发展有限公司 | Label propagation anti-fraud detection method and system based on enterprise relationship map |
| CN110458399A (en) * | 2019-07-05 | 2019-11-15 | 深圳壹账通智能科技有限公司 | Risk information generation method, device, computer equipment and storage medium |
| CN110503295A (en) * | 2019-07-05 | 2019-11-26 | 深圳壹账通智能科技有限公司 | Risk analysis method, device, computing terminal and the storage medium of supply chain finance |
| CN110738388B (en) * | 2019-09-02 | 2023-09-12 | 深圳壹账通智能科技有限公司 | Method, device, equipment and storage medium for evaluating risk conduction through association map |
| CN110557393B (en) * | 2019-09-05 | 2021-10-12 | 腾讯科技（深圳）有限公司 | Network risk assessment method and device, electronic equipment and storage medium |
| CN110659981A (en) * | 2019-09-26 | 2020-01-07 | 北京明略软件系统有限公司 | Enterprise dependency relationship identification method and device and electronic equipment |
| CN110689426A (en) * | 2019-09-30 | 2020-01-14 | 中诚信征信有限公司 | Risk identification method and device, electronic equipment and storage medium |
| CN110717824A (en) * | 2019-10-17 | 2020-01-21 | 北京明略软件系统有限公司 | Method and device for conducting and calculating risk of public and guest groups by bank based on knowledge graph |
| CN110825933B (en) * | 2019-11-07 | 2022-05-17 | 北京明略软件系统有限公司 | Relation graph display method and device, electronic equipment and readable storage medium |
| CN111191853B (en) * | 2020-01-06 | 2022-07-15 | 支付宝(杭州)信息技术有限公司 | Risk prediction method and device and risk query method and device |
| CN111695760B (en) * | 2020-04-23 | 2023-04-07 | 优渊领智科技(武汉)有限公司 | Production quality risk recording and tracing method and system |
| CN113643035A (en) * | 2020-05-11 | 2021-11-12 | 阿里巴巴集团控股有限公司 | Information processing method, information display method, device, equipment and storage medium |
| CN111861119B (en) * | 2020-06-17 | 2023-07-11 | 国家计算机网络与信息安全管理中心 | Enterprise risk data processing method and device based on enterprise risk association graph |
| CN111784488B (en) * | 2020-06-28 | 2023-08-01 | 中国工商银行股份有限公司 | Enterprise fund risk prediction method and device |
| CN111724250A (en) * | 2020-06-29 | 2020-09-29 | 深圳壹账通智能科技有限公司 | Risk propagation determination method and device, computer system and readable storage medium |
| CN112150014A (en) * | 2020-09-27 | 2020-12-29 | 平安资产管理有限责任公司 | Enterprise risk early warning method, device, equipment and readable storage medium |
| CN112463981A (en) * | 2020-11-26 | 2021-03-09 | 福建正孚软件有限公司 | Enterprise internal operation management risk identification and extraction method and system based on deep learning |
| CN112668836B (en) * | 2020-12-07 | 2024-04-05 | 数据地平线（广州）科技有限公司 | Risk spectrum-oriented associated risk evidence efficient mining and monitoring method and apparatus |
| CN112364182A (en) * | 2020-12-09 | 2021-02-12 | 交通银行股份有限公司 | Graph feature-based enterprise risk conduction prediction method and device and storage medium |
| CN112613763B (en) * | 2020-12-25 | 2024-04-16 | 北京知因智慧科技有限公司 | Data transmission method and device |
| CN112734270B (en) * | 2021-01-19 | 2024-01-23 | 中国科学院地理科学与资源研究所 | Energy risk conduction measurement method, system and data platform |
| CN113642867A (en) * | 2021-07-30 | 2021-11-12 | 南京星云数字技术有限公司 | Method and system for assessing risk |
| CN113837648B (en) * | 2021-10-11 | 2023-11-17 | 讯飞智元信息科技有限公司 | Enterprise relevance analysis method, associated enterprise recommendation method and device |
| CN116307724A (en) * | 2023-03-22 | 2023-06-23 | 江苏风云科技服务有限公司 | Complex network-based industrial chain risk propagation method and system |
| CN116664153A (en) * | 2023-07-28 | 2023-08-29 | 中国(上海)宝玉石交易中心有限公司 | Supervision method and device for precious jade Dan Qiye integrity information |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6760715B1 (en) * | 1998-05-01 | 2004-07-06 | Barnhill Technologies Llc | Enhancing biological knowledge discovery using multiples support vector machines |
| CN107203946A (en) * | 2016-03-15 | 2017-09-26 | 阿里巴巴集团控股有限公司 | The localization method of group of corporations, the localization method of risk group and device |
| CN107239882A (en) * | 2017-05-10 | 2017-10-10 | 平安科技（深圳）有限公司 | Methods of risk assessment, device, computer equipment and storage medium |
| CN107767258A (en) * | 2017-09-29 | 2018-03-06 | 新华三大数据技术有限公司 | Risk of Communication determines method and device |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040044617A1 (en) * | 2002-09-03 | 2004-03-04 | Duojia Lu | Methods and systems for enterprise risk auditing and management |
| US20140164012A1 (en) * | 2008-08-06 | 2014-06-12 | Noel Guillama | System and methods for simulating future medical episodes |
| US20140115010A1 (en) * | 2012-10-18 | 2014-04-24 | Google Inc. | Propagating information through networks |
| CN105991397B (en) * | 2015-02-04 | 2020-03-03 | 阿里巴巴集团控股有限公司 | Information dissemination method and device |
| EP3282668B1 (en) * | 2016-08-12 | 2020-10-21 | Tata Consultancy Services Limited | Comprehensive risk assessment in a heterogeneous dynamic network |
-
2018
- 2018-10-11 CN CN201811184210.5A patent/CN109583620B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6760715B1 (en) * | 1998-05-01 | 2004-07-06 | Barnhill Technologies Llc | Enhancing biological knowledge discovery using multiples support vector machines |
| CN107203946A (en) * | 2016-03-15 | 2017-09-26 | 阿里巴巴集团控股有限公司 | The localization method of group of corporations, the localization method of risk group and device |
| CN107239882A (en) * | 2017-05-10 | 2017-10-10 | 平安科技（深圳）有限公司 | Methods of risk assessment, device, computer equipment and storage medium |
| CN107767258A (en) * | 2017-09-29 | 2018-03-06 | 新华三大数据技术有限公司 | Risk of Communication determines method and device |
Non-Patent Citations (2)
| Title |
|---|
| 关联图谱和舆情分析在异常传导路径分析中的应用;王泊;;电子世界(09);第13-15页 * |
| 吕苏越 ; .银行业担保圈风险与化解之道.中国农村金融.2016,(第12期),第16-18页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109583620A (en) | 2019-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109583620B (en) | Enterprise potential risk early warning method, enterprise potential risk early warning device, computer equipment and storage medium | |
| Wang et al. | Mining semantic soft factors for credit risk evaluation in peer-to-peer lending | |
| García et al. | An insight into the experimental design for credit risk and corporate bankruptcy prediction systems | |
| Moffitt et al. | AIS in an age of Big Data | |
| CN111881447B (en) | Intelligent evidence obtaining method and system for malicious code fragments | |
| Shu | Knowledge discovery in the social sciences: A data mining approach | |
| US20220343433A1 (en) | System and method that rank businesses in environmental, social and governance (esg) | |
| CN111241161A (en) | Invoice information mining method and device, computer equipment and storage medium | |
| Thelwall et al. | Do journal data sharing mandates work? Life sciences evidence from Dryad | |
| CN108647281B (en) | Webpage access risk detection and prompting method and device and computer equipment | |
| Moeller et al. | Completing keyword patent search with semantic patent search: introducing a semiautomatic iterative method for patent near search based on semantic similarities | |
| CN114139539A (en) | Enterprise social responsibility index quantification method, system and application | |
| Tu et al. | Bidirectional sensing of user preferences and application changes for dynamic mobile app recommendations | |
| Zhang et al. | To be forgotten or to be fair: Unveiling fairness implications of machine unlearning methods | |
| Abdi et al. | A globally convergent BFGS method for pseudo-monotone variational inequality problems | |
| Bao et al. | Summarization of corporate risk factor disclosure through topic modeling | |
| CN115827877B (en) | Proposal-assisted case merging method, device, computer equipment and storage medium | |
| CN112288279A (en) | Business risk assessment method and device based on natural language processing and linear regression | |
| CN112149413A (en) | Method and device for identifying state of internet website based on neural network and computer readable storage medium | |
| CN114579834B (en) | Webpage login entity identification method and device, electronic equipment and storage medium | |
| US20220164374A1 (en) | Method of scoring and valuing data for exchange | |
| Almozayen et al. | Data mining techniques: a systematic mapping review | |
| CN116029544A (en) | Predicting policy violations in documents using enterprise data sources | |
| US20140201103A1 (en) | System for research and development information assisting in investment, and a method, a computer program, and a readable and recordable media for computer thereof | |
| Li et al. | Incorporating textual network improves Chinese stock market analysis |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |