CN114004694A - Public opinion information-based enterprise risk early warning method, equipment and medium - Google Patents
Public opinion information-based enterprise risk early warning method, equipment and medium Download PDFInfo
- Publication number
- CN114004694A CN114004694A CN202111425172.XA CN202111425172A CN114004694A CN 114004694 A CN114004694 A CN 114004694A CN 202111425172 A CN202111425172 A CN 202111425172A CN 114004694 A CN114004694 A CN 114004694A
- Authority
- CN
- China
- Prior art keywords
- public opinion
- opinion information
- information
- enterprise
- public
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 230000008451 emotion Effects 0.000 claims abstract description 78
- 238000004458 analytical method Methods 0.000 claims abstract description 62
- 230000009193 crawling Effects 0.000 claims abstract description 37
- 238000003860 storage Methods 0.000 claims description 13
- 238000005516 engineering process Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 8
- 238000013507 mapping Methods 0.000 claims description 6
- 230000002996 emotional effect Effects 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 2
- 230000000505 pernicious effect Effects 0.000 claims description 2
- 239000000126 substance Substances 0.000 claims 1
- 230000010354 integration Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 12
- 238000004590 computer program Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002441 reversible effect Effects 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 238000012550 audit Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000005180 public health Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
- G06F16/353—Clustering; Classification into predefined classes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/374—Thesaurus
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Artificial Intelligence (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Technology Law (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses a public opinion information-based enterprise risk early warning method, equipment and a medium, which are used for solving the technical problem that the existing bank cannot acquire enterprise risk information in time. The method comprises the following steps: crawling public opinion information related to enterprise operation and storing the public opinion information in a database; acquiring a plurality of predetermined emotion words related to enterprise operation, adding the emotion words to an emotion word dictionary, and constructing a positive and negative emotion analysis model of the text; public opinion information in the database is analyzed to obtain an analysis result; if the public opinion information is determined to be negative information, determining keywords to determine the category corresponding to the public opinion information; and setting the category as a label of the public sentiment information so as to push the public sentiment information to a bank system with enterprise authority corresponding to the public sentiment information. The method obtains available enterprise public opinion information through the method, determines the business situation of the enterprise through integration and analysis, and pushes the negative information of the enterprise to related banks in time so as to provide reference for the loan work of the banks.
Description
Technical Field
The application relates to the technical field of risk monitoring, in particular to a public opinion information-based enterprise risk early warning method, equipment and medium.
Background
Under the strong support of the country, the independent entrepreneurship is selected by more and more young people by virtue of the characteristics of high degree of freedom and strong work acceptance, and is becoming a new popular trend. However, due to the public health emergencies and various natural disasters caused by climate change in recent years, the management and production of small and medium-sized enterprises face huge challenges. Meanwhile, many large enterprises also have unstable conditions such as business conditions and personnel structures due to internal factors.
At present, a bank mainly evaluates the capital capacity of an enterprise according to annual reports or quarterly financial reports of the enterprise, however, the financial reports do not have strong timeliness and cannot well cope with emergency situations. The bank can hardly receive the report of the media at the first time, so that the real-time condition of the enterprise can not be known in time. At this time, if the bank does not know the operation condition of the enterprise, the bank can not timely withdraw the money because the money is easily issued to the enterprise with unstable operation because the enterprise is not operated well and cannot be crisis steadily because only the good performance condition of the enterprise is considered without multiple audits.
Disclosure of Invention
The embodiment of the application provides a public opinion information-based enterprise risk early warning method, equipment and a medium, which are used for solving the technical problem that money cannot be timely withdrawn due to the fact that an existing bank cannot timely acquire the operation condition of an enterprise and easily deposits the money to the enterprise with poor operation.
On one hand, the embodiment of the application provides an enterprise risk early warning method based on public opinion information, which comprises the following steps: crawling public opinion information related to enterprise operation according to preset crawling rules, and storing the public opinion information into a database; acquiring a plurality of predetermined emotion words related to enterprise operation, and adding the emotion words to an emotion word dictionary to construct a positive and negative emotion analysis model of the text; analyzing the public sentiment information in the database according to the sentiment words in the positive and negative sentiment analysis model of the text to obtain an analysis result; if the public opinion information is determined to be negative information according to the analysis result, determining keywords matched with a preset category keyword dictionary in the public opinion information, and determining a category corresponding to the public opinion information according to the keywords; and setting the category as the label of the public opinion information so as to push the public opinion information with the label to a bank system with enterprise authority corresponding to the public opinion information.
In an implementation manner of the present application, the analyzing public sentiment information in the database according to the sentiment words in the text positive and negative sentiment analysis model to obtain an analysis result specifically includes: traversing the public opinion information, and determining public opinion vocabularies in the public opinion information and sentences where the public opinion vocabularies are located; the public sentiment words are matched with the sentiment words in the text positive and negative sentiment analysis model; if the sentence in which the public opinion vocabulary is located comprises a preset word, determining the positive and negative directions of the sentence in which the public opinion vocabulary is located according to the public opinion vocabulary and the preset word; if the sentence in which the public opinion vocabulary is located does not comprise the preset word, determining the positive and negative directions of the sentence in which the public opinion vocabulary is located according to the public opinion vocabulary; and counting the number of positive sentences and negative sentences in the public opinion information to determine the positive direction and the negative direction of the public opinion information.
In an implementation manner of the present application, after crawling public opinion information related to enterprise operation, the method further includes: determining an information source of the public opinion information, and determining a publisher of the public opinion information according to the information source; wherein the publisher comprises: a person or a medium; crawling basic information and the pernicious information of the publisher from a network through a crawler technology to determine the authority degree of the publisher; and determining the authenticity of the public opinion information according to the authority degree of the publisher.
In an implementation manner of the present application, after crawling public opinion information related to enterprise operation, the method further includes: acquiring the crawled public opinion information from the database, and deleting all blank spaces in the public opinion information; determining the title of the public opinion information and an enterprise corresponding to the public opinion information; establishing a mapping relation between the short names of the enterprises and the full names of the enterprises through a distributed processing technology; according to the title and the short name or the full name of the enterprise, null filling and repeated value filtering are carried out on the public opinion information; unifying the filtered public opinion information into a preset format.
In an implementation manner of the present application, before the obtaining of a plurality of predetermined emotion words related to enterprise operation, the method further includes: acquiring historical risk early warning information of a plurality of enterprises from the database; and determining a plurality of emotion words related to enterprise operation from the plurality of historical risk early warning information through a text recognition technology, and storing the emotion words in a database.
In an implementation manner of the present application, before adding the emotion words to the emotion word dictionary, the method further includes: setting files corresponding to the emotion words into a text txt format, and setting the txt format files into one word in each line.
In one implementation manner of the present application, after the setting the category as the label of the public opinion information, the method further includes: according to the enterprise corresponding to the public opinion information, crawling a registration address and an actual address of the enterprise from a network to determine a geographical position range of the enterprise intention loan; determining a bank which has the authority to apply for loan in the geographic position range according to the scale of the enterprise; and pushing the public opinion information with the label and the full name of the enterprise corresponding to the public opinion information to all banks having the authority to apply for loan in the geographical location range.
In an implementation manner of the present application, after determining that the public opinion information is negative information according to the analysis result, the method further includes: determining the category of the public opinion information according to a plurality of keywords describing risks, and creating a category keyword dictionary; wherein the category keyword dictionary comprises: the corresponding relation between the keywords and the categories; traversing all sentences related to the keywords in the public opinion information; wherein the keywords are keywords in the category keyword dictionary; and determining the category corresponding to the public opinion information according to the keywords contained in the sentence of the public opinion information.
On the other hand, this application embodiment still provides an enterprise risk early warning equipment based on public sentiment information, and equipment includes: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to: crawling public opinion information related to enterprise operation according to preset crawling rules, and storing the public opinion information into a database; acquiring a plurality of predetermined emotion words related to enterprise operation, and adding the emotion words to an emotion word dictionary to construct a positive and negative emotion analysis model of the text; analyzing the public sentiment information in the database according to the sentiment words in the positive and negative sentiment analysis model of the text to obtain an analysis result; if the public opinion information is determined to be negative information according to the analysis result, determining keywords matched with a preset category keyword dictionary in the public opinion information, and determining a category corresponding to the public opinion information according to the keywords; and setting the category as the label of the public opinion information so as to push the public opinion information with the label to a bank system with enterprise authority corresponding to the public opinion information.
In another aspect, an embodiment of the present application further provides a non-volatile computer storage medium storing computer-executable instructions, where the computer-executable instructions are configured to: crawling public opinion information related to enterprise operation according to preset crawling rules, and storing the public opinion information into a database; acquiring a plurality of predetermined emotion words related to enterprise operation, and adding the emotion words to an emotion word dictionary to construct a positive and negative emotion analysis model of the text; analyzing the public sentiment information in the database according to the sentiment words in the positive and negative sentiment analysis model of the text to obtain an analysis result; if the public opinion information is determined to be negative information according to the analysis result, determining keywords matched with a preset category keyword dictionary in the public opinion information, and determining a category corresponding to the public opinion information according to the keywords; and setting the category as the label of the public opinion information so as to push the public opinion information with the label to a bank system with enterprise authority corresponding to the public opinion information.
The embodiment of the application provides an enterprise risk early warning method, equipment and medium based on public opinion information, which at least have the following beneficial effects: public opinion information related to enterprise operation is crawled from a network and is analyzed and processed, so that the effective utilization of the public opinion information is realized; by establishing a text positive and negative emotion analysis model, public opinion information is comprehensively analyzed, the positive and negative directions of the public opinion information and category labels corresponding to the public opinion information are determined and pushed to relevant banks, valuable references can be provided for the banks, and the situation that money cannot be timely withdrawn due to the fact that the existing banks cannot timely know the actual operation condition of an enterprise and pay for the enterprise with a risk easily is avoided.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 is a flowchart of an enterprise risk early warning method based on public opinion information according to an embodiment of the present application;
fig. 2 is a crawled public opinion information provided by an embodiment of the present application;
fig. 3 is a diagram illustrating mapping relationships between enterprise acronyms and enterprise suffixes according to an embodiment of the disclosure;
fig. 4 is a diagram illustrating public opinion information categories according to an embodiment of the present application;
fig. 5 is a schematic internal structure diagram of an enterprise risk early warning device based on public opinion information according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail and completely with reference to the following specific embodiments of the present application and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The embodiment of the application provides a public opinion information-based enterprise risk early warning method, equipment and a medium, and public opinion information related to enterprise operation is crawled from a network and is analyzed and processed, so that the public opinion information is effectively utilized; by establishing a text positive and negative emotion analysis model, comprehensive analysis is carried out on the public opinion information, the positive and negative directions of the public opinion information and the category labels corresponding to the public opinion information are determined and pushed to related banks, and valuable references can be provided for the banks. The technical problem that money cannot be timely withdrawn due to the fact that an existing bank cannot timely acquire the operation condition of an enterprise and easily deposits money to the enterprise with poor operation is solved.
The technical solutions proposed in the embodiments of the present application are described in detail below with reference to the accompanying drawings.
Fig. 1 is a flowchart of an enterprise risk early warning method based on public opinion information according to an embodiment of the present application. As shown in fig. 1, the public opinion information-based enterprise risk early warning method provided in the embodiment of the present application mainly includes the following steps:
step 101: and crawling public opinion information related to enterprise operation through preset crawling rules, and storing the public opinion information in a database.
The server searches websites, webpages or platforms related to enterprise operation from a search engine, takes the websites, webpages or platforms as a target data source, determines a crawling rule preset according to the actual requirement of a user, and then establishes a related crawling task. And the server crawls public opinion information related to enterprise operation in the media reports from a target data source through a crawler technology according to the specific crawling task.
It should be noted that the public opinion information obtained in the present application includes information such as an enterprise name, a release time, a news title, and a news text. The target data source in the embodiment of the application includes, but is not limited to, news related to enterprise business issued by current mainstream financial websites and financial websites. The preset crawling rule in the embodiment of the application is as follows: the method comprises the steps of crawling titles and related enterprises in media reports, crawling a data source of current public opinion information, namely media for publishing the current public opinion information, and continuing crawling publishing time, keywords in texts and categories of the current public opinion information.
As shown in fig. 2, the server in this embodiment of the present application is public opinion information crawled on a webpage of a certain news, the information source of the public opinion information is a certain commercial news, the release event is 22 o 22/15/10/2021, and the news title is CEO unload | (company a)! The lower left corner of fig. 2 includes news text and the lower right corner of fig. 2 includes a stock procurement calendar. After crawling public opinion information, the server stores the public opinion information into a database.
In one embodiment of the application, public opinion information related to enterprise operation crawled by a crawler comprises information sources. After crawling public opinion information related to enterprise operation, a server determines the information source of the public opinion information through the crawled data, determines that a publisher of the public opinion information is a person or a medium according to the information source, and then crawls basic information and disciplined information of the public opinion information publisher from a network through a crawler technology. When the publisher is a media, the server determines the scale, creation time and the behavior information of illegal discipline such as false news, malicious assassault and the like of the current media, and judges the authority degree of the current media according to the behavior information; when the publisher is an individual, the server acquires the identity information of the publisher and the information published by the publisher in history, and accordingly determines the authority degree of the publisher for publishing the information. Therefore, the server can determine the authenticity of the current public opinion information according to the authority degree of the publisher. Therefore, the authenticity of the crawled public opinion information related to enterprise operation can be further judged, and the actual operation condition of the enterprise can be determined.
In one embodiment of the application, after crawling public opinion information related to enterprise operation, a server acquires a plurality of crawled public opinion information from a database, and deletes all blank spaces in titles and texts in the public opinion information for subsequent analysis. The server finds the title of the public sentiment information and the enterprise corresponding to the public sentiment information according to the crawled public sentiment information, and establishes a mapping relation between the short names of the enterprises and the full names of the enterprises through a distributed processing technology, so that a plurality of public sentiment information can be compared according to the short names or the full names of the enterprises. The server fills public opinion information with vacant contents according to preset filling rules; the server deletes and filters the repeated public opinion information of the same kind of label in the same enterprise, and if the repeated public opinion information of the same kind of label in the same enterprise comprises important non-repeated content, the server combines the repeated public opinion information into one piece of data, so that the waste of a database storage space is avoided, and the workload of processing the public opinion information by a text positive and negative emotion analysis model is reduced. In addition, the server unifies the data in the filtered public opinion information into a preset standard format, so that a plurality of public opinion information can be visually compared, the public opinion information which is still repeated after the unified format is filtered again, and the storage pressure of the database is further reduced.
As shown in fig. 3, the mapping relationship between the enterprise abbreviation and the enterprise full name is divided into two types, the first type is a listed company, for example, the enterprise abbreviation a is a listed company, and then the enterprise full name corresponding to a is an a-holding group stock limited company; and the second is a non-listed company, for example, the enterprise abbreviation B is a non-listed company, and then the enterprise corresponding to B is named B limited company. Through the mapping relation, no matter whether the public opinion information is called enterprise for short or enterprise full name, the server can unify the public opinion information crawled by the embodiment of the application.
Step 102: the method comprises the steps of obtaining a plurality of predetermined emotion words related to enterprise operation, and adding the emotion words to an emotion word dictionary to construct a text positive and negative emotion analysis model.
The server acquires a plurality of predetermined emotion words related to enterprise operation from the database, expands an emotion word dictionary by adding the emotion words into the emotion word dictionary, and establishes a text positive and negative emotion analysis model. Therefore, the emotion word dictionary of the text positive and negative emotion analysis model is enriched, and the positive and negative emotion analysis model analysis public opinion information accuracy is improved.
In an embodiment of the application, before obtaining a plurality of predetermined emotion words related to enterprise operation, a server obtains historical risk early warning information of a plurality of enterprises from a database, obtains the emotion words related to enterprise operation in the historical risk early warning information through a text recognition technology, and then stores the obtained emotion words in the database for subsequent use.
In an embodiment of the application, before adding a plurality of obtained emotion words to an emotion word dictionary, a server needs to store a plurality of emotion words in one file, and since the emotion word importing emotion word dictionary only supports a file importing txt format, the server needs to set the file to txt format, and set the txt format file to be one word per line, so that the emotion word dictionary is expanded.
Step 103: and analyzing the public sentiment information in the database according to the sentiment words in the positive and negative sentiment analysis model of the text to obtain an analysis result.
The server comprehensively analyzes the public opinion information crawled from the database according to a plurality of emotional words and other words in the emotional word dictionary of the text positive and negative emotion analysis model, and obtains the analysis result of the public opinion information.
It should be noted that the emotion word dictionary in the embodiment of the present application includes not only the imported emotion words but also the adjectives describing the positive or negative direction of the public opinion information.
Specifically, the server traverses the public opinion information, determines the public opinion words matched with the emotional words in the text positive and negative emotion analysis model in the public opinion information and the sentences in which the public opinion words are located, and judges whether the sentences in which the public opinion words are located include preset words or not. It should be noted that the preset word in the embodiment of the present application refers to an intensity adverb having a modification effect on an emotion word or a fixed phrase having a semantic reversal effect on an emotion word.
If the sentence in which the public opinion vocabulary is located comprises the preset word, the server finally determines the positive direction and the negative direction of the sentence in which the public opinion vocabulary is located according to the positive direction and the negative direction of the public opinion vocabulary and the strengthening effect or the semantic reversal effect of the preset word on the public opinion vocabulary. If the public sentiment words do not include the preset words, the server can determine the positive direction and the negative direction of the current sentence where the public sentiment words are located only according to the positive direction and the negative direction of the public sentiment words.
After the positive and negative directions of the public sentiment words and the sentences in which the public sentiment words are located are determined, the service needs to respectively count the quantity of the positive sentences and the negative sentences in the current public sentiment information, and then the positive and negative directions of the current public sentiment information are determined together according to the positive sentences and the negative sentences.
Step 104: and if the public opinion information is determined to be negative information according to the analysis result, determining keywords matched with a preset category keyword dictionary in the public opinion information, and determining the category corresponding to the public opinion information according to the keywords.
If the server determines that the current public opinion information is negative information according to the analysis result of the text positive and negative emotion analysis model, the server can continuously traverse the public opinion information to determine keywords matched with a preset category keyword dictionary in the public opinion information, and determines the category corresponding to the public opinion information according to the matched keywords.
In an embodiment of the application, after determining that the public opinion information is negative information according to the analysis result, the server determines categories of the public opinion information corresponding to a plurality of keywords according to a plurality of keywords describing risks related to enterprise management, so as to establish a category keyword dictionary. It should be noted that the keyword dictionary in the embodiment of the present application includes a correspondence between a keyword and a category.
The server traverses the public opinion information, determines all sentences related to the keywords in the category keyword dictionary in the public opinion information, and then determines the category corresponding to the current public opinion information according to the determined keywords in each sentence.
Step 105: and setting the category as a label of the public sentiment information so as to push the public sentiment information with the label to a bank system with the enterprise authority corresponding to the public sentiment information.
The server sets the determined category of the public sentiment information as a label of the public sentiment information, and marks the risk early warning of which category the public sentiment information belongs to in a brief way through the label. The server determines a bank with the current enterprise rights through an enterprise corresponding to the public opinion information, and then pushes the negative public opinion information with a label to all bank systems with the current enterprise rights, so that the bank can acquire the actual operation conditions of the enterprise or huge internal personnel changes in time, timely and valuable references are provided for the loan work of the bank, and the situation that money cannot be timely withdrawn due to the fact that the bank easily issues the money to the enterprise which is unstable due to untimely information acquisition is avoided.
As shown in fig. 4, the public opinion information crawled by the server includes enterprise names and specific public opinion information texts, when the public opinion information is negative information, the server traverses the public opinion information to determine keywords in the public opinion information, and determines categories corresponding to the keywords from a category keyword dictionary, thereby setting the categories as labels of the public opinion information, so that when the server sends the public opinion information to a bank system, the bank can directly make clear of the categories of the public opinion information according to the labels of the public opinion information, thereby improving the identification efficiency of the bank system.
In one embodiment of the application, after setting the category as a tag of public opinion information, the server can crawl a registered address, an actual address and the scale of an enterprise of the enterprise from a network according to a corresponding enterprise name in the public opinion information; determining the geographical position range of the enterprise intention loan according to the registered address and the actual address of the enterprise; then determining a bank which has the authority to apply for loan in the current geographic position range according to the scale of the enterprise; and finally, the server pushes the negative public opinion information with the label and the full name of the enterprise corresponding to the public opinion information to all banks in the current geographical position range, wherein the enterprise has the authority to apply for loan. Therefore, the enterprise can be prevented from applying for loans to banks which do not cooperate before, and the banks which do not cooperate cannot timely know the public opinion information of the enterprise due to no authority, so that the benefits of other banks in the current geographic position range are protected. It should be noted that the public opinion information of the enterprise is not directly pushed to all banks, so as to prevent useless information pushing and waste of resources of other banks and time of corresponding staff.
The above is the method embodiment proposed by the present application. Based on the same inventive concept, the embodiment of the application further provides public opinion information-based enterprise risk early warning equipment, and the structure of the equipment is shown in fig. 5.
Fig. 5 is a schematic internal structure diagram of an enterprise risk early warning device based on public opinion information according to an embodiment of the present application. As shown in fig. 5, the apparatus includes at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to: crawling public opinion information related to enterprise operation according to preset crawling rules, and storing the public opinion information into a database; acquiring a plurality of predetermined emotion words related to enterprise operation, and adding the emotion words to an emotion word dictionary to construct a positive and negative emotion analysis model of the text; analyzing public sentiment information in a database according to the sentiment words in the positive and negative sentiment analysis model of the text to obtain an analysis result; if the public opinion information is determined to be negative information according to the analysis result, determining keywords matched with a preset category keyword dictionary in the public opinion information, and determining a category corresponding to the public opinion information according to the keywords; and setting the category as a label of the public sentiment information so as to push the public sentiment information with the label to a bank system with the enterprise authority corresponding to the public sentiment information.
An embodiment of the present application further provides a non-volatile computer storage medium, in which computer-executable instructions are stored, and the computer-executable instructions are configured to: crawling public opinion information related to enterprise operation according to preset crawling rules, and storing the public opinion information into a database; acquiring a plurality of predetermined emotion words related to enterprise operation, and adding the emotion words to an emotion word dictionary to construct a positive and negative emotion analysis model of the text; analyzing public sentiment information in a database according to the sentiment words in the positive and negative sentiment analysis model of the text to obtain an analysis result; if the public opinion information is determined to be negative information according to the analysis result, determining keywords matched with a preset category keyword dictionary in the public opinion information, and determining a category corresponding to the public opinion information according to the keywords; and setting the category as a label of the public sentiment information so as to push the public sentiment information with the label to a bank system with the enterprise authority corresponding to the public sentiment information.
The embodiments in the present application are described in a progressive manner, and the same and similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the device and media embodiments, the description is relatively simple as it is substantially similar to the method embodiments, and reference may be made to some descriptions of the method embodiments for relevant points.
The device and the medium provided by the embodiment of the application correspond to the method one to one, so the device and the medium also have the similar beneficial technical effects as the corresponding method, and the beneficial technical effects of the method are explained in detail above, so the beneficial technical effects of the device and the medium are not repeated herein.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus 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, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. A public opinion information-based enterprise risk early warning method is characterized by comprising the following steps:
crawling public opinion information related to enterprise operation according to preset crawling rules, and storing the public opinion information into a database;
acquiring a plurality of predetermined emotion words related to enterprise operation, and adding the emotion words to an emotion word dictionary to construct a positive and negative emotion analysis model of the text;
analyzing the public sentiment information in the database according to the sentiment words in the positive and negative sentiment analysis model of the text to obtain an analysis result;
if the public opinion information is determined to be negative information according to the analysis result, determining keywords matched with a preset category keyword dictionary in the public opinion information, and determining a category corresponding to the public opinion information according to the keywords;
and setting the category as the label of the public opinion information so as to push the public opinion information with the label to a bank system with enterprise authority corresponding to the public opinion information.
2. The method as claimed in claim 1, wherein the analyzing the public sentiment information in the database according to the sentiment words in the text positive and negative sentiment analysis model to obtain the analysis result specifically comprises:
traversing the public opinion information, and determining public opinion vocabularies in the public opinion information and sentences where the public opinion vocabularies are located; the public sentiment words are matched with the sentiment words in the text positive and negative sentiment analysis model;
if the sentence in which the public opinion vocabulary is located comprises a preset word, determining the positive and negative directions of the sentence in which the public opinion vocabulary is located according to the public opinion vocabulary and the preset word;
if the sentence in which the public opinion vocabulary is located does not comprise the preset word, determining the positive and negative directions of the sentence in which the public opinion vocabulary is located according to the public opinion vocabulary;
and counting the number of positive sentences and negative sentences in the public opinion information to determine the positive direction and the negative direction of the public opinion information.
3. The public opinion information based enterprise risk early warning method as claimed in claim 1, wherein after crawling the public opinion information related to enterprise operation, the method further comprises:
determining an information source of the public opinion information, and determining a publisher of the public opinion information according to the information source; wherein the publisher comprises: a person or a medium;
crawling basic information and the pernicious information of the publisher from a network through a crawler technology to determine the authority degree of the publisher;
and determining the authenticity of the public opinion information according to the authority degree of the publisher.
4. The public opinion information based enterprise risk early warning method as claimed in claim 1, wherein after crawling the public opinion information related to enterprise operation, the method further comprises:
acquiring the crawled public opinion information from the database, and deleting all blank spaces in the public opinion information;
determining the title of the public opinion information and an enterprise corresponding to the public opinion information;
establishing a mapping relation between the short names of the enterprises and the full names of the enterprises through a distributed processing technology;
according to the title and the short name or the full name of the enterprise, null filling and repeated value filtering are carried out on the public opinion information;
unifying the filtered public opinion information into a preset format.
5. The method for enterprise risk early warning based on public opinion information according to claim 1, wherein before obtaining a plurality of predetermined emotional words related to enterprise operation, the method further comprises:
acquiring historical risk early warning information of a plurality of enterprises from the database;
and determining a plurality of emotion words related to enterprise operation from the plurality of historical risk early warning information through a text recognition technology, and storing the emotion words in a database.
6. The public opinion information based enterprise risk early warning method as claimed in claim 1, wherein the adding of the emotion words to the emotion word dictionary is preceded by:
setting files corresponding to the emotion words into a text txt format, and setting the txt format files into one word in each line.
7. A public opinion information based enterprise risk early warning method as claimed in claim 1, wherein after the setting of the category as the label of the public opinion information, the method further comprises:
according to the enterprise corresponding to the public opinion information, crawling a registration address and an actual address of the enterprise from a network to determine a geographical position range of the enterprise intention loan;
determining a bank which has the authority to apply for loan in the geographic position range according to the scale of the enterprise;
and pushing the public opinion information with the label and the full name of the enterprise corresponding to the public opinion information to all banks having the authority to apply for loan in the geographical location range.
8. The method as claimed in claim 1, wherein after determining that the public opinion information is negative information according to the analysis result, the method further comprises:
determining the category of the public opinion information according to a plurality of keywords describing risks, and creating a category keyword dictionary; wherein the category keyword dictionary comprises: the corresponding relation between the keywords and the categories;
traversing all sentences related to the keywords in the public opinion information; wherein the keywords are keywords in the category keyword dictionary;
and determining the category corresponding to the public opinion information according to the keywords contained in the sentence of the public opinion information.
9. The utility model provides an enterprise risk early warning equipment based on public opinion information which characterized in that, equipment includes:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to:
crawling public opinion information related to enterprise operation according to preset crawling rules, and storing the public opinion information into a database;
acquiring a plurality of predetermined emotion words related to enterprise operation, and adding the emotion words to an emotion word dictionary to construct a positive and negative emotion analysis model of the text;
analyzing the public sentiment information in the database according to the sentiment words in the positive and negative sentiment analysis model of the text to obtain an analysis result;
if the public opinion information is determined to be negative information according to the analysis result, determining keywords matched with a preset category keyword dictionary in the public opinion information, and determining a category corresponding to the public opinion information according to the keywords;
and setting the category as the label of the public opinion information so as to push the public opinion information with the label to a bank system with enterprise authority corresponding to the public opinion information.
10. A non-transitory computer storage medium storing computer-executable instructions, the computer-executable instructions configured to:
crawling public opinion information related to enterprise operation according to preset crawling rules, and storing the public opinion information into a database;
acquiring a plurality of predetermined emotion words related to enterprise operation, and adding the emotion words to an emotion word dictionary to construct a positive and negative emotion analysis model of the text;
analyzing the public sentiment information in the database according to the sentiment words in the positive and negative sentiment analysis model of the text to obtain an analysis result;
if the public opinion information is determined to be negative information according to the analysis result, determining keywords matched with a preset category keyword dictionary in the public opinion information, and determining a category corresponding to the public opinion information according to the keywords;
and setting the category as the label of the public opinion information so as to push the public opinion information with the label to a bank system with enterprise authority corresponding to the public opinion information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111425172.XA CN114004694A (en) | 2021-11-26 | 2021-11-26 | Public opinion information-based enterprise risk early warning method, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111425172.XA CN114004694A (en) | 2021-11-26 | 2021-11-26 | Public opinion information-based enterprise risk early warning method, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114004694A true CN114004694A (en) | 2022-02-01 |
Family
ID=79930518
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111425172.XA Withdrawn CN114004694A (en) | 2021-11-26 | 2021-11-26 | Public opinion information-based enterprise risk early warning method, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114004694A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112732997A (en) * | 2021-01-14 | 2021-04-30 | 上海尧信惠达信息科技有限公司 | Automatic enterprise public opinion monitoring method, system, storage medium and electronic equipment |
| CN114998004A (en) * | 2022-08-08 | 2022-09-02 | 成都运荔枝科技有限公司 | Method and system based on enterprise financial loan wind control |
| CN115357688A (en) * | 2022-10-12 | 2022-11-18 | 北京金堤科技有限公司 | Enterprise list information acquisition method and device, storage medium and electronic equipment |
| CN117314621A (en) * | 2023-09-26 | 2023-12-29 | 山东浪潮爱购云链信息科技有限公司 | Enterprise liability monitoring method, equipment and medium |
-
2021
- 2021-11-26 CN CN202111425172.XA patent/CN114004694A/en not_active Withdrawn
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112732997A (en) * | 2021-01-14 | 2021-04-30 | 上海尧信惠达信息科技有限公司 | Automatic enterprise public opinion monitoring method, system, storage medium and electronic equipment |
| CN114998004A (en) * | 2022-08-08 | 2022-09-02 | 成都运荔枝科技有限公司 | Method and system based on enterprise financial loan wind control |
| CN115357688A (en) * | 2022-10-12 | 2022-11-18 | 北京金堤科技有限公司 | Enterprise list information acquisition method and device, storage medium and electronic equipment |
| CN115357688B (en) * | 2022-10-12 | 2023-02-21 | 北京金堤科技有限公司 | Enterprise list information acquisition method and device, storage medium and electronic equipment |
| CN117314621A (en) * | 2023-09-26 | 2023-12-29 | 山东浪潮爱购云链信息科技有限公司 | Enterprise liability monitoring method, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114004694A (en) | Public opinion information-based enterprise risk early warning method, equipment and medium | |
| WO2019200752A1 (en) | Semantic understanding-based point of interest query method, device and computing apparatus | |
| EP1899855B1 (en) | System and method of making unstructured data available to structured data analysis tools | |
| CN110196848B (en) | Cleaning and duplicate removal method and system for public resource transaction data | |
| CN111967761A (en) | Monitoring and early warning method and device based on knowledge graph and electronic equipment | |
| CN106991090B (en) | Public opinion event entity analysis method and device | |
| CN113360676A (en) | Method and device for determining potential relation of enterprise based on knowledge graph | |
| CN111985201B (en) | Data processing rule generation method and device and electronic equipment | |
| CN112241458B (en) | Text knowledge structuring processing method, device, equipment and readable storage medium | |
| CN110851611A (en) | Hidden danger data knowledge graph construction method, device, equipment and medium | |
| CN110109870A (en) | A kind of mass data quick retrieval system based on Solr | |
| CN102063460A (en) | Information processing method and device | |
| CN114297204A (en) | Data storage and retrieval method and device for heterogeneous data source | |
| CN117033744A (en) | Data query method and device, storage medium and electronic equipment | |
| CN112069808A (en) | Financing wind control method and device, computer equipment and storage medium | |
| CN110941952A (en) | Method and device for perfecting audit analysis model | |
| CN111078867A (en) | Text classification method and device | |
| CN111191007A (en) | Article keyword filtering method and device based on block chain and medium | |
| KR20100136438A (en) | Method and apparutus for automatic contents generation | |
| CN111428037B (en) | Method for analyzing matching performance of behavior policy | |
| CN113722278A (en) | PDF file-based method, device and medium for extracting knowledge elements | |
| CN113450197A (en) | Hanging account self-balancing result checking method and device | |
| CN113723047A (en) | Map construction method, device and medium based on legal document | |
| CN115049372B (en) | Method, apparatus and medium for constructing digital infrastructure for human resource information | |
| CN110851431A (en) | Data processing method and device for data center station |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20220201 |
|
| WW01 | Invention patent application withdrawn after publication |