CN107909274B - Enterprise investment risk assessment method and device and storage medium - Google Patents
Enterprise investment risk assessment method and device and storage medium Download PDFInfo
- Publication number
- CN107909274B CN107909274B CN201711141730.3A CN201711141730A CN107909274B CN 107909274 B CN107909274 B CN 107909274B CN 201711141730 A CN201711141730 A CN 201711141730A CN 107909274 B CN107909274 B CN 107909274B
- Authority
- CN
- China
- Prior art keywords
- enterprise
- entity
- entities
- risk assessment
- feature vector
- 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
Images
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
- G06Q10/06—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
Abstract
The invention provides an enterprise investment risk assessment method, which comprises the following steps: crawling the news corpora related to the investment target enterprise entity, and extracting other entities related to the enterprise entity; constructing a relationship network by taking the name as a node and taking the association relationship between the enterprise entity and other entities as an edge; calculating the vector representation of the enterprise entity, and generating a first characteristic vector of the enterprise entity; according to a first preset rule, quantifying the internal information of the enterprise entity to generate a second feature vector; according to a second preset rule, quantifying external information of the enterprise entity to generate a third feature vector; and inputting the first feature vector, the second feature vector and the third feature vector into an enterprise risk assessment model, and outputting to obtain a risk label corresponding to the enterprise entity. The invention also provides an electronic device and a computer readable storage medium. By utilizing the method and the system, the information disclosed in the news corpus is analyzed, and the risk of the investment target enterprise can be evaluated.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to an enterprise investment risk assessment method, an electronic device, and a computer-readable storage medium.
Background
At present, from the perspective of observing investment targets, related tools on the market are relatively simple, most of the related tools stay in the traditional financial analysis and report analysis level, and the consideration of association quantification of upstream and downstream, associated parties, market hotspots and policy clues is lacked.
With the popularization of the network, each news website has thousands of news every day, and the news is updated in real time. If the big data associated with the investment target enterprise can be extracted from the massive news corpus, such as the internal conditions of the enterprise: management, finance, high management, recruitment, website updating frequency and the like, conditions outside the enterprise, such as conditions of related companies, upstream and downstream, clients and the like, information such as the rating of the enterprise by a rating organization, news media related reports and the like, a relationship network is formed by the information, and the risk coefficient of the investment target enterprise is analyzed and evaluated, so that the investor can consider whether to accept the risk and decide whether to invest the enterprise according to the risk coefficient. Therefore, how to extract information related to the investment target enterprise from the news corpus and utilize the information for risk assessment is an urgent problem to be solved.
Disclosure of Invention
The invention provides an enterprise investment risk assessment method, an electronic device and a computer readable storage medium, and mainly aims to assess the risk of an investment target enterprise by analyzing information disclosed in news corpora.
To achieve the above object, the present invention provides an electronic device, comprising: a memory, a processor, said memory storing an enterprise investment risk assessment program operable on said processor, which when executed by said processor, performs the steps of:
a1, crawling news corpora related to enterprise entities to be assessed for risks, preprocessing the news corpora, and extracting other entities related to the enterprise entities from the preprocessed news corpora;
a2, using the name as a node and the association relationship between the enterprise entity and other entities as an edge to construct a relationship network between the enterprise entity and other entities;
a3, calculating the vector representation of the enterprise entity according to the relationship network, and generating a first characteristic vector of the enterprise entity;
a4, quantifying internal information of the enterprise entity according to a first preset rule to generate a second feature vector;
a5, extracting external information of the enterprise entity from the news corpus, and quantifying the external information of the enterprise entity according to a second preset rule to generate a third feature vector of the enterprise entity; and
and A6, inputting the first characteristic vector, the second characteristic vector and the third characteristic vector into a predetermined enterprise risk assessment model, and outputting to obtain a risk label corresponding to the enterprise entity.
In addition, in order to achieve the above object, the present invention further provides an enterprise investment risk assessment method, including:
s1, crawling news corpora related to enterprise entities to be assessed for risks, preprocessing the news corpora, and extracting other entities related to the enterprise entities from the preprocessed news corpora;
s2, constructing a relationship network between the enterprise entity and other entities by taking the name as a node and taking the association relationship between the enterprise entity and other entities as an edge;
s3, calculating the vector representation of the enterprise entity according to the relational network, and generating a first characteristic vector of the enterprise entity;
s4, quantifying the internal information of the enterprise entity according to a first preset rule to generate a second feature vector;
s5, extracting external information of the enterprise entity from the news corpus, and quantifying the external information of the enterprise entity according to a second preset rule to generate a third feature vector of the enterprise entity; and
and S6, inputting the first feature vector, the second feature vector and the third feature vector into a predetermined enterprise risk assessment model, and outputting to obtain a risk label corresponding to the enterprise entity.
In addition, to achieve the above object, the present invention further provides a computer-readable storage medium storing an enterprise investment risk assessment program, which when executed by a processor implements any of the steps of the enterprise investment risk assessment method as described above.
The enterprise investment risk assessment method, the electronic device and the computer readable storage medium provided by the invention respectively obtain the first eigenvector, the second eigenvector and the third eigenvector of the enterprise entity by knowing the relationship between the enterprise entity and the associated entity, the internal information and the external information of the enterprise entity from the news corpus, and perform risk assessment on the enterprise entity by utilizing a risk assessment model and the first eigenvector, the second eigenvector and the third eigenvector, thereby facilitating the investors to capture market investment opportunities and predicting investment risks in advance.
Drawings
FIG. 1 is a schematic diagram of an application environment of a preferred embodiment of the enterprise investment risk assessment method of the present invention;
FIG. 2 is a network diagram of the relationships between Business entity A and associated other entities;
FIG. 3 is a vector representation of Business entity A;
FIG. 4 is a block diagram of the enterprise investment risk assessment program of FIG. 1;
FIG. 5 is a flowchart illustrating a preferred embodiment of the enterprise investment risk assessment method of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention.
The invention provides an enterprise investment risk assessment method, which is applied to an electronic device 1. Referring to fig. 1, a schematic diagram of an application environment of a preferred embodiment of the enterprise investment risk assessment method of the present invention is shown.
In the present embodiment, the electronic apparatus 1 may be a PC (Personal Computer), or may be a terminal device such as a smart phone, a tablet Computer, an electronic book reader, or a portable Computer.
The electronic device 1 comprises a memory 11, a processor 12, a communication bus 13, and a network interface 14.
The memory 11 includes at least one type of readable storage medium, which includes a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, and the like. The memory 11 may in some embodiments be an internal storage unit of the electronic device 1, such as a hard disk of the electronic device 1. The memory 11 may also be an external storage device of the electronic apparatus 1 in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic apparatus 1. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic apparatus 1. The memory 11 may be used to store not only the application software and various data installed in the electronic device 1, such as the enterprise investment risk assessment program 10, but also temporarily store data that has been output or will be output.
The communication bus 13 is used to realize connection communication between these components.
The network interface 14 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), typically used to establish a communication link between the apparatus and other electronic devices.
Fig. 1 only shows the electronic device 1 with components 11-14, but it is to be understood that not all of the shown components are required to be implemented, and that more or fewer components may alternatively be implemented.
Optionally, the electronic device 1 may further comprise a user interface, the user interface may comprise a Display (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface may further comprise a standard wired interface, a wireless interface.
Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is used for displaying information processed in the electronic apparatus 1 and for displaying a visualized user interface.
In the embodiment of the apparatus shown in fig. 1, a corporate investment risk assessment program 10 is stored in the memory 11; the processor 12, when executing the corporate investment risk assessment program 10 stored in the memory 11, performs the following steps:
a1, crawling news corpora related to enterprise entities to be assessed for risks, preprocessing the news corpora, and extracting other entities related to the enterprise entities from the preprocessed news corpora;
a2, constructing a relationship network between the enterprise entity and other entities by taking the name as a node and taking the association relationship between the enterprise entity and other entities as an edge;
a3, calculating the vector representation of the enterprise entity according to the relationship network, and generating a first characteristic vector of the enterprise entity;
a4, quantifying the internal information of the enterprise entity according to a first preset rule to generate a second feature vector;
a5, extracting external information of the enterprise entity from the news corpus, and quantizing the external information of the enterprise entity according to a second preset rule to generate a third feature vector of the enterprise entity; and
and A6, inputting the first characteristic vector, the second characteristic vector and the third characteristic vector into a predetermined enterprise risk assessment model, and outputting to obtain a risk label corresponding to the enterprise entity.
The corpus relates to a plurality of different fields, and the embodiment takes news corpus as an example to illustrate a specific scheme of the present invention, but is not limited to the news field. When the investor needs to know the current news to acquire internal data and external data associated with the investment target enterprise, the web crawler is utilized to crawl the web news from the internet, for example, the web news of the newwave, the hundredth, the news of the Tencent and the like is crawled by the crawler. It can be understood that the business conditions of each enterprise are different in different time periods, and therefore, in order to enable an investor to know the information of an investment target enterprise more accurately, the crawled network news is filtered in the time dimension, a preset time interval is set, and only the network news in the time period is crawled, for example, only the network news of the last half year is crawled. Because the sources of the news corpora have diversity, the corpora have more format types, so that the subsequent processing of the corpora is facilitated, the news corpora needs to be preprocessed to obtain the text data of the news corpora, and a news corpus text set is formed.
In other embodiments, the pre-processing may unify the format of the news corpus into a text format, remove advertising noise from the news corpus, and filter one or more of dirty words and sensitive words. When the formats of the news corpora are unified into a text format, the content which cannot be converted into the text format in the prior art can be filtered.
Then, by using the word segmentation method, all enterprise names are extracted from the preprocessed news corpus according to a predetermined enterprise name library, and then other entities related to the enterprise entity to be assessed in risk (namely, the investment target enterprise) are screened out according to the related enterprise data of the enterprise entity to be assessed in risk, and the enterprise entity and the other entities are constructed into a relational network. Wherein the associated enterprise data is available via third party data. It can be understood that there may be many other entities associated with the business entity extracted from the corpus, and if it is unreasonable to construct all the associated entities in the relationship network, the extracted other entities associated with the business entity are filtered and screened before the relationship network is constructed, and specifically, the other entities associated with the business entity that remain after the filtering and screening step include: the stakeholders of the business entity, other entities with whom the business entity has monetary transactions, suppliers, customers, credit rating structures, etc.
In this embodiment, taking enterprise entity a as an example, after screening other entities extracted from the news corpus and associated with enterprise entity a, it is assumed that the other retained entities are B1, B2, and B3, respectively, where B1 is a rating mechanism for rating credit for enterprise entity a, it can be known from the historical rating data that the credit rating given to enterprise entity a by B1 is BBB, B2 is a supplier for providing raw materials or goods for enterprise entity a, the amount owed by enterprise entity a for B2 is 30 ten thousand, B3 is a customer of enterprise entity a, and enterprise entity a defaults for B3 2 times. The relationship network diagram between the enterprise entities and other entities as shown in fig. 2 is constructed by taking the enterprise entities A, B, B2 and B3 as nodes and taking the association relationship between B1, B2, B3 and a as an edge.
Then, according to the above-mentioned relational network diagram, the vector representation of the business entity a is calculated, and the Skip-Gram method is adopted in the present embodiment, because there is a management relationship between the vector representation of the business entity a and the vector representations of the entities B1, B2, B3 associated therewith in the relational network. For the training of business entity name vectors, the Skip-Gram approach uses the current business entity to predict surrounding entities, as shown in FIG. 3. An1, an2, an3, an4 in fig. 3 are unordered and all represent neighboring entities of business entity a. Similar to the method of using Skip-Gram training word vectors, a fixed prediction length L is set to predict L adjacent entities around the enterprise entity A, and if the number of the adjacent entities is less than L in the real situation, the output is NULL. By the method, the vector representation of the enterprise entity A can be obtained as embedding (E1), embedding (E2) and …, and the vector representation is used as the first characteristic vector of the enterprise entity A.
It can be understood that to know the risk of the enterprise entity a, the financial and management information of the enterprise entity a must be known, and therefore, the internal information of the enterprise entity a needs to be considered, wherein the internal information includes the management, financial and recruitment information, the website update frequency information, and the like of the enterprise entity a, and some of the information is digital information, for example, the financial information includes the net profit, the stock profit, and the like of the enterprise in the last year. Each reference factor in the internal information of the enterprise is converted into a number according to a rule for quantification, for example, a numerical value in the financial information may be converted into a characteristic value, for example, in this embodiment, the net profit is 30 ten thousand yuan, 30 is taken as a corresponding characteristic value, the update frequency of the website and the number of recruiters in the last year are also numerical values, or corresponding numerical values may be obtained according to a preset conversion rule. In other embodiments, 30 ten thousand yuan may be converted into other values according to a preset conversion ratio. And after quantifying each reference factor in the internal information of the enterprise entity A, generating a second feature vector of the enterprise entity A.
It should be noted that, the business entity a is good and bad, and besides its own factors, external factors are also very important, so the external information of the business entity a needs to be considered, where the external information includes the upstream and downstream relationships of the business entity a, such as the supplier and the customer, whether the business has violated or owed the other entities in the upstream and downstream relationships, and if so, the number of violations and the period of owed are respectively. In addition, the external information of business entity a also includes ratings of business entity a by rating agencies (rating level 3a,2a indicates good, a indicates good, BBB indicates general, etc.), positive/negative reports of news media to the business entity a, etc. Then, each reference factor in the internal information of the enterprise is converted into a number for quantization according to a rule, for example, in the embodiment, the number of default times can be quantized into 3 numerical values, no default is-0, slight default is-1, and severe default is-2; the arrearage can be quantified into 2 numerical values, no arrearage is-0, and the arrearage is-1; the rating may be quantified as a number of values, rating level 3A-6, rating level 2A-5, rating level A-4, rating level BBB-3, rating level BB-2, rating level B-1. And according to the specific situation of the enterprise entity A, quantifying external information of the enterprise entity A, wherein the default times are-1, the arrearage times are-1, and the grade is-3, and generating a third feature vector of the enterprise entity A according to the quantified information.
Thus, after learning the internal information and the external information of the other entities associated with the business entity a, the investment business entity a can be risk-assessed. And inputting the name of the enterprise entity A and the first feature vector, the second feature vector and the third feature vector of the enterprise entity A into a predetermined risk assessment model for risk assessment, and outputting a risk assessment result. Wherein the training of the predetermined risk assessment model comprises: the steps A1 to A5 are utilized to obtain a large number of first feature vectors, second feature vectors and third feature vectors of the enterprise entities, and the specific implementation manner is consistent with the steps, which is not described herein again. And then labeling a risk label for each enterprise entity, labeling the risk label as 0 for the enterprise entity without risk, labeling the risk label as 1 for the enterprise entity with high risk, and then taking the first characteristic vector, the second characteristic vector, the third characteristic vector and the corresponding risk label of each enterprise entity as sample data. Randomly extracting a first proportion (for example, 60%) of the first feature vector, the second feature vector, the third feature vector and the risk label corresponding to the first proportion (for example, 60%) of the business entities from the sample data as a training set, randomly extracting a second proportion (for example, 50%) of the first feature vector, the second feature vector, the third feature vector and the risk label corresponding to the second proportion (for example, 50%) of the business entities from the remaining sample set as a verification set, that is, extracting 20% of the sample data as the verification set; training a support vector machine by using the 50% sample data, determining model parameters of a risk assessment model, and determining the relationship among the associated entities, the internal information and the external information of the enterprise entities and the risk of investing the enterprise entities; and verifying the accuracy of the risk assessment model by using 20% of sample data, and finishing the training if the accuracy is greater than or equal to a preset accuracy (for example, 90%), or increasing the number of samples and re-executing the training step if the accuracy is less than the preset accuracy (for example, 90%).
After the first feature vector, the second feature vector and the third feature vector of the enterprise entity A are input into the risk assessment model, if the output result of the model is 0, the investment enterprise entity A is basically free of risk, and if the output result of the model is 1, the investment enterprise entity A is shown to have greater risk.
The electronic device 1 provided in the above embodiment obtains the first feature vector, the second feature vector, and the third feature vector of the enterprise entity by knowing the relationship between the enterprise entity and the associated entity, the internal information of the enterprise entity, and the external information of the enterprise entity, and performs risk assessment on the enterprise entity by using the risk assessment model and the first feature vector, the second feature vector, and the third feature vector, so as to facilitate the investor to capture market investment opportunities.
Alternatively, in other embodiments, the enterprise investment risk assessment program 10 may be divided into one or more modules, one or more modules being stored in the memory 11 and executed by one or more processors (in this embodiment, the processor 12) to implement the present invention, wherein a module refers to a series of computer program instruction segments capable of performing a specific function. For example, referring to fig. 4, which is a schematic block diagram of the enterprise investment risk assessment program 10 in fig. 1, in this embodiment, the program may be divided into an extraction module 110, a construction module 120, a first calculation module 130, a second calculation module 140, a third calculation module 150, and an assessment module 160, where the functions or operation steps implemented by the modules 110 to 160 are similar to those described above and will not be described in detail here, for example:
the extraction module 110 is configured to crawl a news corpus related to an enterprise entity to be assessed for risk, pre-process the news corpus, and extract other entities related to the enterprise entity from the pre-processed news corpus;
a building module 120, configured to build a relationship network between the enterprise entity and other entities by taking the name as a node and taking the association relationship between the enterprise entity and other entities as an edge;
a first calculating module 130, configured to calculate a vector representation of the business entity according to a relationship network, and generate a first feature vector of the business entity;
the second calculation module 140 is configured to quantize the internal information of the enterprise entity according to a first preset rule, and generate a second feature vector;
the third calculation module 150 is configured to extract external information of the enterprise entity from the news corpus, quantize the external information of the enterprise entity according to a second preset rule, and generate a third feature vector of the enterprise entity; and
and the evaluation module 160 is configured to input the first feature vector, the second feature vector, and the third feature vector into a predetermined enterprise risk evaluation model, and output a risk label corresponding to the enterprise entity.
In addition, the invention also provides an enterprise investment risk assessment method. Referring to fig. 5, a flow chart of a preferred embodiment of the enterprise investment risk assessment method of the present invention is shown. The method may be performed by an apparatus, which may be implemented by software and/or hardware.
In this embodiment, the method for assessing investment risk of an enterprise includes:
s1, crawling news corpora related to enterprise entities to be assessed for risks, preprocessing the news corpora, and extracting other entities related to the enterprise entities from the preprocessed news corpora;
s2, constructing a relationship network between the enterprise entity and other entities by taking the name as a node and taking the association relationship between the enterprise entity and other entities as an edge;
s3, calculating the vector representation of the enterprise entity according to the relational network, and generating a first characteristic vector of the enterprise entity;
s4, quantifying the internal information of the enterprise entity according to a first preset rule to generate a second feature vector;
s5, extracting external information of the enterprise entity from the news corpus, and quantifying the external information of the enterprise entity according to a second preset rule to generate a third feature vector of the enterprise entity; and
and S6, inputting the first feature vector, the second feature vector and the third feature vector into a predetermined enterprise risk assessment model, and outputting to obtain a risk label corresponding to the enterprise entity.
The corpus relates to a plurality of different fields, and the embodiment takes news corpus as an example to illustrate the specific scheme of the invention, but not limited to the news field. When the investor needs to know the current news to acquire internal data and external data associated with the investment target enterprise, the web crawler is utilized to crawl the web news from the internet, for example, the web news of the newwave, the hundredth, the news of the Tencent and the like is crawled by the crawler. It can be understood that the business conditions of each enterprise are different in different time periods, and therefore, in order to enable an investor to know the information of an investment target enterprise more accurately, the crawled network news is filtered in a time dimension, a preset time interval is set, and only the network news in the time period is crawled, for example, only the network news of the last half year is crawled. Because the sources of the news corpora have diversity, the corpora have more format types, so that the news corpora need to be preprocessed to obtain the text data of the news corpora so as to form a text set of the news corpora for facilitating the subsequent processing of the corpora.
In other embodiments, the pre-processing may unify the format of the news corpus into a text format, remove advertising noise from the news corpus, and filter one or more of dirty words and sensitive words. When the formats of the news corpora are unified into a text format, the content which cannot be converted into the text format in the prior art can be filtered.
Then, by using the word segmentation method, all enterprise names are extracted from the preprocessed news corpus according to a predetermined enterprise name library, and then other entities related to the enterprise entity to be assessed in risk (namely, the investment target enterprise) are screened out according to the related enterprise data of the enterprise entity to be assessed in risk, and the enterprise entity and the other entities are constructed into a relational network. Wherein the associated enterprise data is available via third party data. It can be understood that there may be many other entities associated with the business entity extracted from the corpus, and if it is unreasonable to construct all the associated entities in the relationship network, the extracted other entities associated with the business entity are filtered and screened before the relationship network is constructed, and specifically, the other entities associated with the business entity that remain after the filtering and screening step include: the stakeholders of the business entity, other entities with whom the business entity has monetary transactions, suppliers, customers, credit rating structures, etc.
In this embodiment, taking the business entity a as an example, after screening other entities extracted from the news corpus and associated with the business entity a, it is assumed that the remaining other entities are B1, B2, and B3, respectively, where B1 is a rating mechanism for rating credit for the business entity a, it can be known from the historical rating data that the credit rating of B1 for the business entity a is BBB, B2 is a supplier for providing raw materials or goods for the business entity a, the amount owed by the business entity a for B2 is 30 ten thousand, B3 is a customer of the business entity a, and the business entity a defaults B3 for 2 times. The enterprise entities A, B, B2 and B3 are used as nodes, and the association relations between B1, B2, B3 and a are used as edges, so as to construct a relationship network diagram between the enterprise entities and other entities as shown in fig. 2.
Then, according to the above-mentioned relational network diagram, the vector representation of the business entity a is calculated, and the Skip-Gram method is adopted in the present embodiment, because there is a management relationship between the vector representation of the business entity a and the vector representations of the entities B1, B2, B3 associated therewith in the relational network. For the training of business entity name vectors, the Skip-Gram approach uses the current business entity to predict surrounding entities, as shown in FIG. 3. An1, an2, an3, an4 in fig. 3 are unordered and all represent neighboring entities of business entity a. Similar to the method of training word vectors by using Skip-Gram, a fixed prediction length L is set to predict L adjacent entities around the enterprise entity A, and if the adjacent entities are less than L in the real situation, the output is NULL. By the method, the vector representation of the enterprise entity A can be obtained as embedding (E1), embedding (E2) and …, and the vector representation is used as the first characteristic vector of the enterprise entity A.
It can be understood that to know the risk of the enterprise entity a, the financial and management information of the enterprise entity a must be known, and therefore, the internal information of the enterprise entity a needs to be considered, wherein the internal information includes the management, financial and recruitment information, the website update frequency information, and the like of the enterprise entity a, and some of the information is digital information, for example, the financial information includes the net profit, the stock profit, and the like of the enterprise in the last year. Each reference factor in the internal information of the enterprise is converted into a number according to a rule for quantification, for example, a numerical value in the financial information may be converted into a characteristic value, for example, in this embodiment, the net profit is 30 ten thousand yuan, 30 is taken as a corresponding characteristic value, the update frequency of the website and the number of recruiters in the last year are also numerical values, or corresponding numerical values may be obtained according to a preset conversion rule. In other embodiments, 30 ten thousand yuan may be converted into other values according to a preset conversion ratio. And after quantifying each reference factor in the internal information of the enterprise entity A, generating a second feature vector of the enterprise entity A.
It should be noted that, the business entity a is good and bad, and besides its own factors, external factors are also very important, so the external information of the business entity a needs to be considered, where the external information includes the upstream and downstream relationships of the business entity a, such as the supplier and the customer, whether the business has violated or owed the other entities in the upstream and downstream relationships, and if so, the number of violations and the period of owed are respectively. In addition, the external information of business entity a also includes ratings of business entity a by rating agencies (rating level 3a,2a indicates good, a indicates good, BBB indicates general, etc.), positive/negative reports of news media to the business entity a, etc. Then, each reference factor in the internal information of the enterprise is converted into a number for quantization according to the rule, for example, in the embodiment, the number of default times can be quantized into 3 values, no default-0, slight default-1, and severe default-2; the arrearage can be quantified into 2 numerical values, no arrearage is-0, and the arrearage is-1; the rating may be quantified as a number of values, rating level 3A-6, rating level 2A-5, rating level A-4, rating level BBB-3, rating level BB-2, rating level B-1. And according to the specific situation of the enterprise entity A, quantifying external information of the enterprise entity A, wherein the default times are-1, the arrearage times are-1, and the grade is-3, and generating a third feature vector of the enterprise entity A according to the quantified information.
Thus, after learning the internal information and the external information of the other entities associated with the business entity a, the investment business entity a can be risk-assessed. And inputting the name of the enterprise entity A and the first feature vector, the second feature vector and the third feature vector of the enterprise entity A into a predetermined risk assessment model for risk assessment, and outputting a risk assessment result. Wherein the training of the predetermined risk assessment model comprises: the steps S1 to S5 are utilized to obtain a large number of first feature vectors, second feature vectors, and third feature vectors of the enterprise entity, and the specific implementation is consistent with the steps described above, which is not described herein again. And then marking a risk label for each enterprise entity, marking a risk label as 0 for the enterprise entity without risk, marking a risk label as 1 for the enterprise entity with high risk, and then taking the first characteristic vector, the second characteristic vector, the third characteristic vector and the corresponding risk label of each enterprise entity as sample data. Randomly extracting a first proportion (for example, 60%) of the first feature vector, the second feature vector, the third feature vector and the risk label corresponding to the first proportion (for example, 60%) of the business entities from the sample data as a training set, randomly extracting a second proportion (for example, 50%) of the first feature vector, the second feature vector, the third feature vector and the risk label corresponding to the second proportion (for example, 50%) of the business entities from the remaining sample set as a verification set, that is, extracting 20% of the sample data as the verification set; training a support vector machine by using the 50% sample data, determining model parameters of a risk assessment model, and determining the relationship among the associated entities, the internal information and the external information of the enterprise entities and the risk of investing the enterprise entities; and verifying the accuracy of the risk assessment model by using 20% of sample data, and ending the training if the accuracy is greater than or equal to a preset accuracy (for example, 90%), or increasing the number of samples and re-executing the training step if the accuracy is less than the preset accuracy (for example, 90%).
After the first feature vector, the second feature vector and the third feature vector of the enterprise entity A are input into the risk assessment model, if the output result of the model is 0, the investment enterprise entity A is basically free of risk, and if the output result of the model is 1, the investment enterprise entity A is shown to have greater risk.
The enterprise investment risk assessment method provided in the above embodiment obtains the first feature vector, the second feature vector, and the third feature vector of the enterprise entity by knowing the relationship between the enterprise entity and the associated entity, and the internal information and the external information of the enterprise entity, and performs risk assessment on the enterprise entity by using a risk assessment model and the first feature vector, the second feature vector, and the third feature vector, so as to facilitate the investor to capture market investment opportunities.
Furthermore, an embodiment of the present invention further provides a computer-readable storage medium, in which an enterprise investment risk assessment program is stored, and when executed by a processor, the enterprise investment risk assessment program implements the following operations:
a1, crawling news corpora related to enterprise entities to be assessed for risks, preprocessing the news corpora, and extracting other entities related to the enterprise entities from the preprocessed news corpora;
a2, constructing a relationship network between the enterprise entity and other entities by taking the name as a node and taking the association relationship between the enterprise entity and other entities as an edge;
a3, calculating the vector representation of the enterprise entity according to the relationship network, and generating a first characteristic vector of the enterprise entity;
a4, quantifying the internal information of the enterprise entity according to a first preset rule to generate a second feature vector;
a5, extracting external information of the enterprise entity from the news corpus, and quantifying the external information of the enterprise entity according to a second preset rule to generate a third feature vector of the enterprise entity; and
and A6, inputting the first characteristic vector, the second characteristic vector and the third characteristic vector into a predetermined enterprise risk assessment model, and outputting to obtain a risk label corresponding to the enterprise entity.
The embodiment of the computer-readable storage medium of the present invention is substantially the same as the embodiments of the enterprise investment risk assessment method and the electronic device, and will not be described herein again.
It should be noted that, the above numbers of the embodiments of the present invention are only for description, and do not represent the advantages and disadvantages of the embodiments. And the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising a … …" does not exclude the presence of another identical element in a process, apparatus, article, or method that comprises the element.
Through the description of the foregoing embodiments, it is clear to those skilled in the art that the method of the foregoing embodiments may be implemented by software plus a necessary general hardware platform, and certainly may also be implemented by hardware, but in many cases, the former is a better implementation. Based on such understanding, the technical solution of the present invention 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) as described above 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 invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (8)
1. An enterprise investment risk assessment method is applied to an electronic device, and is characterized by comprising the following steps:
s1, crawling news corpora of a plurality of different fields related to enterprise entities to be assessed for risks, preprocessing the news corpora, and extracting other entities related to the enterprise entities from the preprocessed news corpora, wherein the preprocessing comprises the following steps: unifying the formats of the news corpora into a text format, removing advertisement noise from the news corpora and filtering one or more of dirty words and sensitive words;
s2, constructing a relationship network between the enterprise entity and other entities by taking the name as a node and taking the association relationship between the enterprise entity and other entities as an edge;
s3, calculating the vector representation of the enterprise entity according to the relationship network by adopting a Skip-Gram method, and generating a first characteristic vector of the enterprise entity;
s4, quantifying internal information of the enterprise entity according to a first preset rule to generate a second feature vector;
s5, extracting external information of the enterprise entity from the news corpus, and quantifying the external information of the enterprise entity according to a second preset rule to generate a third feature vector of the enterprise entity; and
and S6, taking the first feature vector, the second feature vector, the third feature vector and the corresponding risk label as sample data, inputting the sample data into a predetermined enterprise risk evaluation model, and outputting to obtain the risk label corresponding to the enterprise entity.
2. The enterprise investment risk assessment method according to claim 1, wherein said first predetermined rule is: and converting each reference factor in the internal information of the business entity into a digital quantized rule.
3. The enterprise investment risk assessment method according to claim 1 or 2, wherein said second preset rule is: converting each reference factor in the external information of the business entity into a digital quantized rule.
4. The enterprise investment risk assessment method of claim 3, wherein said training of said predetermined enterprise risk assessment model comprises:
crawling news corpora related to a plurality of enterprise entities, extracting other entities related to the plurality of enterprise entities from the news corpora, and respectively constructing relationship networks between the plurality of enterprise entities and the other entities by taking names as nodes and taking the association relationship between the entities as edges;
respectively calculating vector representations of the plurality of enterprise entities according to a relationship network, and generating first feature vectors of the plurality of enterprise entities;
according to a first preset rule, quantifying the internal information of the plurality of enterprise entities to generate a second feature vector;
extracting external information of the enterprise entity from the news corpus, and quantizing the external information of the enterprise entity according to a second preset rule to generate a third feature vector of the enterprise entity;
respectively labeling risk labels for the multiple enterprise entities according to historical risk assessment records, and taking the first characteristic vectors, the second characteristic vectors, the third characteristic vectors and the risk labels of the multiple enterprise entities as sample data;
extracting sample data of a first proportion as a training set and extracting sample data of a second proportion as a verification set;
training a support vector machine by using the training set to obtain the risk assessment model; and
and verifying the accuracy of the risk assessment model by using the verification set, finishing training if the accuracy is greater than or equal to a preset accuracy, or increasing the number of samples and re-executing the training step if the accuracy is less than the preset accuracy.
5. An enterprise investment risk assessment device, characterized in that, the device includes: a memory, a processor, the memory storing an enterprise investment risk assessment program operable on the processor, the program when executed by the processor implementing the steps of:
a1, crawling news corpora of a plurality of different fields related to enterprise entities to be assessed for risks, preprocessing the news corpora, extracting other entities related to the enterprise entities from the preprocessed news corpora, wherein the preprocessing comprises the following steps: unifying the formats of the news corpora into a text format, removing advertisement noise from the news corpora and filtering one or more of dirty words and sensitive words;
a2, constructing a relationship network between the enterprise entity and other entities by taking the name as a node and taking the association relationship between the enterprise entity and other entities as an edge;
a3, calculating the vector representation of the enterprise entity according to a relationship network by adopting a Skip-Gram method, and generating a first characteristic vector of the enterprise entity;
a4, quantifying the internal information of the enterprise entity according to a first preset rule to generate a second feature vector;
a5, extracting external information of the enterprise entity from the news corpus, and quantifying the external information of the enterprise entity according to a second preset rule to generate a third feature vector of the enterprise entity; and
and A6, taking the first characteristic vector, the second characteristic vector, the third characteristic vector and the corresponding risk label as sample data, inputting the sample data into a predetermined enterprise risk evaluation model, and outputting to obtain the risk label corresponding to the enterprise entity.
6. The corporate investment risk assessment apparatus according to claim 5, wherein said first preset rule is: and converting each reference factor in the internal information of the business entity into a digital quantized rule.
7. The enterprise investment risk assessment device according to claim 5 or 6, wherein said second preset rule is: converting each reference factor in the external information of the business entity into a digital quantized rule.
8. A computer-readable storage medium, wherein the computer-readable storage medium has stored thereon a corporate investment risk assessment program, which when executed by a processor, implements the steps of the corporate investment risk assessment method according to any one of claims 1 to 4.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711141730.3A CN107909274B (en) | 2017-11-17 | 2017-11-17 | Enterprise investment risk assessment method and device and storage medium |
PCT/CN2018/076169 WO2019095572A1 (en) | 2017-11-17 | 2018-02-10 | Enterprise investment risk assessment method, device, and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711141730.3A CN107909274B (en) | 2017-11-17 | 2017-11-17 | Enterprise investment risk assessment method and device and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107909274A CN107909274A (en) | 2018-04-13 |
CN107909274B true CN107909274B (en) | 2023-02-28 |
Family
ID=61845968
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711141730.3A Active CN107909274B (en) | 2017-11-17 | 2017-11-17 | Enterprise investment risk assessment method and device and storage medium |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN107909274B (en) |
WO (1) | WO2019095572A1 (en) |
Families Citing this family (47)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109087163B (en) * | 2018-07-06 | 2021-07-09 | 创新先进技术有限公司 | Credit assessment method and device |
CN108985638B (en) * | 2018-07-25 | 2020-07-24 | 腾讯科技(深圳)有限公司 | User investment risk assessment method and device and storage medium |
CN109345089A (en) * | 2018-09-13 | 2019-02-15 | 杭州索骥数据科技有限公司 | Enterprise development state evaluating method and system based on big data |
CN109299362B (en) * | 2018-09-21 | 2023-04-14 | 平安科技(深圳)有限公司 | Similar enterprise recommendation method and device, computer equipment and storage medium |
CN109597894B (en) * | 2018-09-30 | 2023-10-03 | 创新先进技术有限公司 | Correlation model generation method and device, and data correlation method and device |
CN109523117A (en) * | 2018-10-11 | 2019-03-26 | 平安科技(深圳)有限公司 | Risk Forecast Method, device, computer equipment and storage medium |
CN109214904A (en) * | 2018-10-11 | 2019-01-15 | 平安科技(深圳)有限公司 | Acquisition methods, device, computer equipment and the storage medium of financial fraud clue |
CN109472485A (en) * | 2018-11-01 | 2019-03-15 | 成都数联铭品科技有限公司 | Enterprise breaks one's promise Risk of Communication inquiry system and method |
CN109523153A (en) * | 2018-11-12 | 2019-03-26 | 平安科技(深圳)有限公司 | Acquisition methods, device, computer equipment and the storage medium of illegal fund collection enterprise |
CN109543985A (en) * | 2018-11-15 | 2019-03-29 | 李志东 | Business risk appraisal procedure, system and medium |
CN109657917B (en) * | 2018-11-19 | 2022-04-29 | 平安科技(深圳)有限公司 | Risk early warning method and device for evaluation object, computer equipment and storage medium |
CN109558592A (en) * | 2018-11-29 | 2019-04-02 | 上海点融信息科技有限责任公司 | The method and apparatus of customer Credit Risk assessment information is obtained based on artificial intelligence |
CN109670837A (en) * | 2018-11-30 | 2019-04-23 | 平安科技(深圳)有限公司 | Recognition methods, device, computer equipment and the storage medium of bond default risk |
CN109740865A (en) * | 2018-12-13 | 2019-05-10 | 平安科技(深圳)有限公司 | Methods of risk assessment, system, equipment and storage medium |
CN109359901A (en) * | 2018-12-13 | 2019-02-19 | 泰康保险集团股份有限公司 | Method and device, medium and electronic equipment are determined based on the business risk of block chain |
KR102202139B1 (en) * | 2018-12-17 | 2021-01-12 | 지속가능발전소 주식회사 | Method for analyzing risk of cooperrator supply chain, computer readable medium for performing the method |
CN109800976A (en) * | 2019-01-07 | 2019-05-24 | 平安科技(深圳)有限公司 | Investment decision methods, device, computer equipment and storage medium |
CN109829640A (en) * | 2019-01-23 | 2019-05-31 | 平安科技(深圳)有限公司 | Recognition methods, device, computer equipment and the storage medium of enterprise's default risk |
CN110033120A (en) * | 2019-03-06 | 2019-07-19 | 阿里巴巴集团控股有限公司 | For providing the method and device that risk profile energizes service for trade company |
CN110009229A (en) * | 2019-04-04 | 2019-07-12 | 泰康保险集团股份有限公司 | Supply chain management method, device, storage medium and equipment based on block chain |
CN110188980A (en) * | 2019-04-15 | 2019-08-30 | 深圳壹账通智能科技有限公司 | Business risk methods of marking, device, computer equipment and storage medium |
CN110443459A (en) * | 2019-07-05 | 2019-11-12 | 深圳壹账通智能科技有限公司 | Warning information method for pushing, device, computer equipment and storage medium |
CN110533528A (en) * | 2019-08-30 | 2019-12-03 | 北京市天元网络技术股份有限公司 | Assess the method and apparatus of business standing |
CN110532357B (en) * | 2019-09-04 | 2024-03-12 | 深圳前海微众银行股份有限公司 | ESG scoring system generation method, device, equipment and readable storage medium |
CN111104442A (en) * | 2019-11-06 | 2020-05-05 | 杭州绿程网络科技有限公司 | Preprocessing method for enterprise comprehensive data |
CN111291932A (en) * | 2020-02-12 | 2020-06-16 | 徐佳慧 | Investment and financing relation network link prediction method, device and equipment |
CN111340246A (en) * | 2020-02-26 | 2020-06-26 | 未来地图(深圳)智能科技有限公司 | Processing method and device for enterprise intelligent decision analysis and computer equipment |
CN111311105A (en) * | 2020-02-28 | 2020-06-19 | 深圳前海微众银行股份有限公司 | Combined product scoring method, device, equipment and readable storage medium |
CN111459961A (en) * | 2020-03-31 | 2020-07-28 | 深圳前海微众银行股份有限公司 | Method, device and equipment for updating service data and storage medium |
CN113592519A (en) * | 2020-04-30 | 2021-11-02 | 景德镇陶瓷大学 | Marketing data analysis and evaluation system beneficial to enterprise development |
CN111353728A (en) * | 2020-05-06 | 2020-06-30 | 支付宝(杭州)信息技术有限公司 | Risk analysis method and system |
CN111951079B (en) * | 2020-08-14 | 2024-04-02 | 国网数字科技控股有限公司 | Credit rating method and device based on knowledge graph and electronic equipment |
CN113743111A (en) * | 2020-08-25 | 2021-12-03 | 国家计算机网络与信息安全管理中心 | Financial risk prediction method and device based on text pre-training and multi-task learning |
CN112016850A (en) * | 2020-09-14 | 2020-12-01 | 支付宝(杭州)信息技术有限公司 | Service evaluation method and device |
CN112418320B (en) * | 2020-11-24 | 2024-01-19 | 杭州未名信科科技有限公司 | Enterprise association relation identification method, device and storage medium |
CN113837517A (en) * | 2020-12-01 | 2021-12-24 | 北京沃东天骏信息技术有限公司 | Event triggering method and device, medium and electronic equipment |
CN112365194A (en) * | 2020-12-01 | 2021-02-12 | 未鲲(上海)科技服务有限公司 | Enterprise data processing method, device, equipment and computer storage medium |
CN112598496B (en) * | 2020-12-15 | 2024-04-30 | 深圳前海微众银行股份有限公司 | Wind control blacklist setting method and device, terminal equipment and readable storage medium |
CN112579773A (en) * | 2020-12-16 | 2021-03-30 | 中国建设银行股份有限公司 | Risk event grading method and device |
CN112732804B (en) * | 2020-12-23 | 2024-04-26 | 北京金堤征信服务有限公司 | Cooperative data evaluation method and device, electronic equipment and readable storage medium |
CN112613762B (en) * | 2020-12-25 | 2024-04-16 | 北京知因智慧科技有限公司 | Group rating method and device based on knowledge graph and electronic equipment |
CN112598302B (en) * | 2020-12-25 | 2024-03-26 | 北京知因智慧科技有限公司 | Enterprise data evaluation method, device and server |
CN112884496B (en) * | 2021-05-06 | 2021-08-20 | 达而观数据(成都)有限公司 | Method, device and computer storage medium for calculating enterprise credit factor score |
CN113283806A (en) * | 2021-06-22 | 2021-08-20 | 中国平安财产保险股份有限公司 | Enterprise information evaluation method and device, computer equipment and storage medium |
CN113506173A (en) * | 2021-08-06 | 2021-10-15 | 国网电子商务有限公司 | Credit risk assessment method and related equipment thereof |
CN113673870B (en) * | 2021-08-23 | 2024-04-30 | 杭州安恒信息技术股份有限公司 | Enterprise data analysis method and related components |
CN114168757B (en) * | 2022-02-11 | 2022-04-29 | 子长科技(北京)有限公司 | Company event risk prediction method, device, storage medium and electronic equipment |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103942718A (en) * | 2014-04-14 | 2014-07-23 | 中国人民银行征信中心 | Enterprise credit information collection and integration method |
CN105528465A (en) * | 2016-02-03 | 2016-04-27 | 天弘基金管理有限公司 | Credit status assessment method and device |
CN105740335A (en) * | 2016-01-22 | 2016-07-06 | 山东合天智汇信息技术有限公司 | Titan-based enterprise information analysis platform and construction method thereof |
CN105913195A (en) * | 2016-04-29 | 2016-08-31 | 浙江汇信科技有限公司 | All-industry data based enterprise's financial risk scoring method |
CN105975491A (en) * | 2016-04-26 | 2016-09-28 | 重庆誉存企业信用管理有限公司 | Enterprise news analysis method and system |
CN106203808A (en) * | 2016-07-01 | 2016-12-07 | 中国民生银行股份有限公司 | Enterprise Credit Risk Evaluation method and apparatus |
CN106447066A (en) * | 2016-06-01 | 2017-02-22 | 上海坤士合生信息科技有限公司 | Big data feature extraction method and device |
CN106934712A (en) * | 2017-03-16 | 2017-07-07 | 深圳微众税银信息服务有限公司 | A kind of enterprise's representation data processing method and system |
CN107301493A (en) * | 2017-05-19 | 2017-10-27 | 四川新网银行股份有限公司 | A kind of mutual golden business ratings model based on deep neural network |
Family Cites Families (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040215551A1 (en) * | 2001-11-28 | 2004-10-28 | Eder Jeff S. | Value and risk management system for multi-enterprise organization |
JP2005516308A (en) * | 2002-01-31 | 2005-06-02 | シーベリ アナリティック エルエルシー | Risk model and method for business enterprise |
US20070208600A1 (en) * | 2006-03-01 | 2007-09-06 | Babus Steven A | Method and apparatus for pre-emptive operational risk management and risk discovery |
JP6009864B2 (en) * | 2011-09-21 | 2016-10-19 | 典秀 野田 | Company evaluation system, company evaluation method and company evaluation program |
US9087088B1 (en) * | 2012-11-13 | 2015-07-21 | American Express Travel Related Services Company, Inc. | Systems and methods for dynamic construction of entity graphs |
CA2905996C (en) * | 2013-03-13 | 2022-07-19 | Guardian Analytics, Inc. | Fraud detection and analysis |
CA2851464A1 (en) * | 2013-05-02 | 2014-11-02 | Alla KRAMSKAIA | A system and method using multi-dimensional rating to determine an entity's future commercial viability |
CN106445988A (en) * | 2016-06-01 | 2017-02-22 | 上海坤士合生信息科技有限公司 | Intelligent big data processing method and system |
CN106126614A (en) * | 2016-06-21 | 2016-11-16 | 山东合天智汇信息技术有限公司 | A kind of method and system reviewing Liang Ge enterprise multi-layer associated path |
CN107133732A (en) * | 2017-04-27 | 2017-09-05 | 青岛格兰德信用管理咨询有限公司 | The relation loop method for digging analyzed based on big data and its application |
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 |
CN107220237A (en) * | 2017-05-24 | 2017-09-29 | 南京大学 | A kind of method of business entity's Relation extraction based on convolutional neural networks |
CN107229756A (en) * | 2017-06-30 | 2017-10-03 | 山东合天智汇信息技术有限公司 | A kind of design method and system directly perceived for showing business connection collection of illustrative plates |
-
2017
- 2017-11-17 CN CN201711141730.3A patent/CN107909274B/en active Active
-
2018
- 2018-02-10 WO PCT/CN2018/076169 patent/WO2019095572A1/en active Application Filing
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103942718A (en) * | 2014-04-14 | 2014-07-23 | 中国人民银行征信中心 | Enterprise credit information collection and integration method |
CN105740335A (en) * | 2016-01-22 | 2016-07-06 | 山东合天智汇信息技术有限公司 | Titan-based enterprise information analysis platform and construction method thereof |
CN105528465A (en) * | 2016-02-03 | 2016-04-27 | 天弘基金管理有限公司 | Credit status assessment method and device |
CN105975491A (en) * | 2016-04-26 | 2016-09-28 | 重庆誉存企业信用管理有限公司 | Enterprise news analysis method and system |
CN105913195A (en) * | 2016-04-29 | 2016-08-31 | 浙江汇信科技有限公司 | All-industry data based enterprise's financial risk scoring method |
CN106447066A (en) * | 2016-06-01 | 2017-02-22 | 上海坤士合生信息科技有限公司 | Big data feature extraction method and device |
CN106203808A (en) * | 2016-07-01 | 2016-12-07 | 中国民生银行股份有限公司 | Enterprise Credit Risk Evaluation method and apparatus |
CN106934712A (en) * | 2017-03-16 | 2017-07-07 | 深圳微众税银信息服务有限公司 | A kind of enterprise's representation data processing method and system |
CN107301493A (en) * | 2017-05-19 | 2017-10-27 | 四川新网银行股份有限公司 | A kind of mutual golden business ratings model based on deep neural network |
Non-Patent Citations (2)
Title |
---|
中国信用风险预警模型及实证研究——基于企业关联关系和信贷行为的视角;刘堃 等;《财经研究》;20090703;第35卷(第7期);17-23 * |
基于灰色综合关联分析的企业集团信用风险研究;余步雷;《中国博士学位论文全文数据库经济与管理科学辑》;20160315(第03期);J152-12 * |
Also Published As
Publication number | Publication date |
---|---|
CN107909274A (en) | 2018-04-13 |
WO2019095572A1 (en) | 2019-05-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107909274B (en) | Enterprise investment risk assessment method and device and storage medium | |
CN107945024B (en) | Method for identifying internet financial loan enterprise operation abnormity, terminal equipment and storage medium | |
CN111401777B (en) | Enterprise risk assessment method, enterprise risk assessment device, terminal equipment and storage medium | |
Spilnyk et al. | Accounting and financial reporting system in the digital economy | |
CN109274843B (en) | Key prediction method, device and computer readable storage medium | |
CN111125343A (en) | Text analysis method and device suitable for human-sentry matching recommendation system | |
CN111639480A (en) | Text labeling method based on artificial intelligence, electronic device and storage medium | |
CN114265967B (en) | Sensitive data security level marking method and device | |
CN110765101B (en) | Label generation method and device, computer readable storage medium and server | |
CN115936895A (en) | Risk assessment method, device and equipment based on artificial intelligence and storage medium | |
CN113177700A (en) | Risk assessment method, system, electronic equipment and storage medium | |
CN112734569A (en) | Stock risk prediction method and system based on user portrait and knowledge graph | |
US11461616B2 (en) | Method and system for analyzing documents | |
CN117033431A (en) | Work order processing method, device, electronic equipment and medium | |
CN116450723A (en) | Data extraction method, device, computer equipment and storage medium | |
CN115409104A (en) | Method, apparatus, device, medium and program product for identifying object type | |
CN114493853A (en) | Credit rating evaluation method, credit rating evaluation device, electronic device and storage medium | |
CN112069807A (en) | Text data theme extraction method and device, computer equipment and storage medium | |
CN111179076A (en) | IT system intelligent management method, IT system intelligent management device and computer readable storage medium | |
US11875374B2 (en) | Automated auditing and recommendation systems and methods | |
CN117273968A (en) | Accounting document generation method of cross-business line product and related equipment thereof | |
CN116757851A (en) | Data configuration method, device, equipment and storage medium based on artificial intelligence | |
CN117788051A (en) | Customer preference analysis method, device, equipment and medium based on artificial intelligence | |
CN118037455A (en) | Financial data prediction method, device, equipment and storage medium thereof | |
CN117853247A (en) | Product recommendation method, device, equipment and storage medium based on artificial intelligence |
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 |