CN110688463A - Enterprise list processing method and device - Google Patents
Enterprise list processing method and deviceDownload PDFInfo
- Publication number
- CN110688463A CN110688463ACN201910964776.8ACN201910964776ACN110688463ACN 110688463 ACN110688463 ACN 110688463ACN 201910964776 ACN201910964776 ACN 201910964776ACN 110688463 ACN110688463 ACN 110688463A
- Authority
- CN
- China
- Prior art keywords
- enterprise
- news
- list
- information
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06F16/3332—Query translation
- G06F16/3334—Selection or weighting of terms from queries, including natural language queries
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Description
[ technical field ] A method for producing a semiconductor device
The present disclosure relates to the field of data processing technologies, and in particular, to a method and an apparatus for processing an enterprise list.
[ background of the invention ]
The enterprise list is a common enterprise information management tool, and generally all enterprises meeting a certain standard are listed based on the standard, so that the enterprise list is convenient for others to inquire and use. In the data information era, the enterprise list is stored in the form of electronic information, and the enterprise list can be dynamically updated according to the operation condition of related enterprises, so that the reliability of the enterprise list is improved.
In the related art, the update of the enterprise list depends on the comprehensive analysis of the historical data, so that the processing of the enterprise list is delayed. For risk sensitive enterprise lists, such as enterprise white lists with good credit set by financial institutions, timely updating is needed to prevent enterprises from cheating the financial institutions of funds and causing losses to the financial institutions by utilizing gaps of updating of the enterprise white lists after the enterprises encounter sudden crisis. Therefore, a technical scheme capable of timely processing the enterprise list is needed.
[ summary of the invention ]
The embodiments of the present specification aim to solve at least one of the technical problems in the related art to some extent.
Therefore, a first object of the embodiments of the present specification is to provide a method for processing an enterprise list, so as to generate a news tag corresponding to each enterprise according to news information related to each enterprise. And judging whether the enterprises meet preset conditions or not according to the news labels, determining the enterprises meeting the preset conditions as risk enterprises, and processing the enterprise list in time.
A second object of the embodiments of the present specification is to provide an apparatus for processing a business list.
A third object of embodiments of the present specification is to propose a computer apparatus.
A fourth object of embodiments of the present specification is to propose a non-transitory computer-readable storage medium.
To achieve the above object, an embodiment of a first aspect of an embodiment of the present specification provides a method for processing an enterprise list, including: acquiring a first enterprise list to be processed; wherein the first list of businesses comprises names of a plurality of businesses; respectively acquiring news information related to each enterprise; screening the news information, and respectively generating a news label corresponding to each enterprise according to the screened news information; respectively judging whether the news tags corresponding to the enterprises comprise preset tags or not; if the news tag corresponding to the enterprise comprises the preset tag, determining that the enterprise meets a preset condition; and determining the enterprises meeting the preset conditions in the first enterprise list as risk enterprises.
Compared with the prior art, the embodiment of the specification respectively generates the news label corresponding to each enterprise according to the news information related to each enterprise. And judging whether the enterprises meet preset conditions or not according to the news labels, determining the enterprises meeting the preset conditions as risk enterprises, and processing the enterprise list in time.
In addition, the method for processing the enterprise list in the embodiment of the present specification further has the following additional technical features:
optionally, the first business list corresponds to a first business category, and the filtering the news information includes: judging whether the news information comprises the industry professional wordings; the industry specialty terms are determined from the first industry category; and if not, deleting the news information which does not comprise the industry professional terms.
Optionally, the generating, according to the screened news information, a news tag corresponding to each enterprise respectively includes: segmenting the screened news information, and generating a plurality of keywords corresponding to the news information according to a segmentation result; clustering the keywords, and generating the news labels corresponding to the enterprises according to clustering results.
Optionally, after the generating the news tag corresponding to the enterprise according to the clustering result, the method further includes: generating a weight corresponding to each news label according to a clustering result; and generating the portrait corresponding to the enterprise according to the news tag and the weight corresponding to the news tag.
Optionally, before the determining, in the first business list, the business meeting the preset condition as an inauguration business, the method further includes: acquiring the stock right information of the enterprise which does not accord with the preset condition; determining the related enterprises which do not meet the preset conditions according to the stock right information; judging whether the associated enterprise is located in a second enterprise list corresponding to a second industry type or not according to the second industry type corresponding to the associated enterprise; if not, determining that the enterprise meets the preset conditions.
Optionally, after the determining, in the first business list, the business meeting the preset condition as an inauguration business, the method further includes: and deleting the risk enterprises from the first enterprise list.
Optionally, before the obtaining the first to-be-processed business list, the method further includes: acquiring the business information and the operation information of the enterprise from a plurality of data sources; according to the business information and the operation information, performing risk assessment on the enterprise; and if the risk score of the enterprise is smaller than or equal to a preset threshold value, adding the enterprise into the first enterprise list.
An embodiment of a second aspect of the present specification provides an apparatus for processing an enterprise list, including: the first acquisition module is used for acquiring a first enterprise list to be processed; wherein the first list of businesses comprises names of a plurality of businesses; the second acquisition module is used for respectively acquiring news information related to each enterprise; the screening module is used for screening the news information; the generating module is used for respectively generating a news label corresponding to each enterprise according to the screened news information; the first judging module is used for respectively judging whether the news tags corresponding to the enterprises comprise preset tags or not; the first determining module is used for determining that the enterprise meets a preset condition when the first judging module determines that the news tag corresponding to the enterprise comprises the preset tag; and the second determining module is used for determining the enterprises meeting the preset conditions in the first enterprise list as risk enterprises.
In addition, the processing apparatus for the enterprise list according to the embodiment of the present specification further has the following additional technical features:
optionally, the first business list corresponds to a first business category, and the filtering module includes: the judging submodule is used for judging whether the news information comprises the industry professional wording; the industry specialty terms are determined from the first industry category; and the deleting submodule is used for deleting the news information which does not include the industry professional wording when the judging submodule determines that the news information does not include the industry professional wording.
Optionally, the generating module includes: the word segmentation submodule is used for segmenting the screened news information; the first generation submodule is used for generating a plurality of keywords corresponding to the news information according to the word segmentation result; the clustering submodule is used for clustering the plurality of keywords; and the second generation submodule is used for generating the news label corresponding to the enterprise according to the clustering result.
Optionally, the generating module further includes: the third generation submodule is used for generating the weight corresponding to each news label according to the clustering result; and the fourth generation submodule is used for generating the portrait corresponding to the enterprise according to the news tag and the weight corresponding to the news tag.
Optionally, the apparatus further comprises: the third acquisition module is used for acquiring the share right information of the enterprise which does not accord with the preset condition; a third determining module, configured to determine, according to the stock right information, an associated enterprise of the enterprise that does not meet the preset condition; the second judging module is used for judging whether the associated enterprise is located in a second enterprise list corresponding to a second industry type according to the second industry type corresponding to the associated enterprise; a fourth determining module, configured to determine that the enterprise meets the preset condition when the second determining module determines that the associated enterprise is located in a second enterprise list corresponding to the second industry category.
Optionally, the apparatus further comprises: and the deleting module is used for deleting the risk enterprises from the first enterprise list.
Optionally, the apparatus further comprises: the fourth acquisition module is used for acquiring the business information and the operation information of the enterprise from a plurality of data sources; the evaluation module is used for carrying out risk evaluation on the enterprise according to the business information and the operation information; and the adding module is used for adding the enterprise into the first enterprise list when the risk score of the enterprise is less than or equal to a preset threshold value.
A third aspect of embodiments herein provides a computer device, comprising a memory and a processor; the memory having stored thereon a computer program executable by the processor; the processor executes the computer program to perform the method for processing the enterprise list according to the foregoing method embodiment.
A fourth aspect of the embodiments of the present specification proposes a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method for processing the enterprise list according to the foregoing method embodiments.
Additional aspects and advantages of embodiments of the present description will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of embodiments of the present description.
[ description of the drawings ]
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present disclosure, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without any creative effort.
Fig. 1 is a schematic flowchart illustrating a method for processing an enterprise list according to an embodiment of the present disclosure;
FIG. 2 is a flowchart illustrating another method for processing a business listing according to an embodiment of the present disclosure;
FIG. 3 is a flowchart illustrating a method for processing a business listing according to an embodiment of the present disclosure;
fig. 4 is a flowchart illustrating a method for processing a business list according to an embodiment of the present disclosure;
FIG. 5 is a flowchart of an example of a method for processing a business listing provided by an embodiment of the present specification;
fig. 6 is a schematic structural diagram of a device for processing an enterprise list according to an embodiment of the present disclosure;
FIG. 7 is a block diagram of another apparatus for processing a business listing according to an embodiment of the present disclosure;
FIG. 8 is a schematic structural diagram of another apparatus for processing a business list according to an embodiment of the present disclosure; and
fig. 9 is a schematic structural diagram of another apparatus for processing an enterprise list according to an embodiment of the present disclosure.
[ detailed description ] embodiments
Reference will now be made in detail to embodiments of the present specification, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary and intended to be illustrative of the present specification embodiments and should not be construed as limiting the present specification embodiments.
The following describes a method for processing an enterprise list and an apparatus thereof according to an embodiment of the present specification with reference to the drawings.
As can be seen from the above description of the prior art, in the related art, the update of the business list relies on the comprehensive analysis of the historical data, so that there is a delay in the processing of the business list.
To solve this problem, an embodiment of the present specification provides a method for processing an enterprise list, where a news tag corresponding to each enterprise is generated according to news information related to each enterprise. And judging whether the enterprises meet preset conditions or not according to the news label, determining the enterprises meeting the preset conditions in the first enterprise list as risk enterprises, and processing the enterprise list in time.
Fig. 1 is a flowchart illustrating a method for processing an enterprise list according to an embodiment of the present disclosure. As shown in fig. 1, the method comprises the steps of:
step S101, a first enterprise list to be processed is obtained.
The first business list comprises names of a plurality of businesses.
It can be understood that, in the processing method of the enterprise list provided in the embodiment of the present disclosure, after the first enterprise list is generated, the first enterprise list is processed in time, so as to update the first enterprise list in time.
Step S102, news information related to each enterprise is respectively obtained.
The news information refers to information that is exploded in a short time, and may specifically refer to information about an emergency. It can be understood that the information of the emergency is spread quickly on the internet, and the processing method of the enterprise list provided by the embodiment of the present disclosure can search news information related to each enterprise in the first enterprise list on the whole network, and perform corresponding processing on the first enterprise list in time according to the news information.
It should be understood that the first business list includes names of multiple businesses, and each business name is an identifier of a corresponding business, so in this embodiment of the present disclosure, the name of a business may be understood as a name of a business entity, and the handling of the business names in the first business list is essentially the handling of the businesses in the first business list.
When the news information related to each enterprise is acquired, searching can be performed according to the name of the enterprise to acquire the news information related to the enterprise.
It should be noted that, when the first business list is processed, each business in the first business list needs to be processed separately. Therefore, it is necessary to determine whether an enterprise is an inauguration enterprise according to news information related to each enterprise.
And S103, screening the news information, and respectively generating a news label corresponding to each enterprise according to the screened news information.
It can be understood that when acquiring news information related to an enterprise, the enterprise name is used as a keyword to search, and all news information including the enterprise name can be searched. However, among these news information, some news information is not useful for the processing of the first business list. For example, the first enterprise list is a white list of good-credit enterprises, including national enterprises, central enterprises, and listed enterprises with credit endorsements, and 500 strong commercial enterprises operating stably can be used as a loan reference list of the financial institution. If the news information is a sudden departure of a certain high-level management of the enterprise, the message has no influence on the credit status of the enterprise and on whether the financial institution credits the enterprise. For such news messages, the corresponding news tags do not need to be generated, and the news messages can be deleted in a screening mode.
The screened news information is usually a segment of characters, and needs to be further processed, the characters are refined, and key information in the news information is grasped to be used as a trigger signal for processing the first enterprise list.
In order to catch up the key information in the news information, the processing method of the enterprise list provided in the embodiment of the present specification generates a news tag corresponding to the news information, and displays the key information in the news information in the form of the news tag.
And step S104, respectively judging whether the news labels corresponding to each enterprise comprise preset labels.
Step S105, if the news tag corresponding to the enterprise comprises a preset tag, determining that the enterprise meets the preset condition.
The enterprise meeting the preset condition is the trigger condition for processing the enterprise list.
It can be understood that the news tag is used for displaying key information in the news information in a tag form, and in order to improve the processing efficiency of the enterprise list, the embodiment of the specification uses the preset tag as a trigger signal for processing the enterprise list.
In other words, if the news tag includes the preset tag, it is indicated that the key information in the news information satisfies the trigger condition for processing the enterprise list, and the enterprise list needs to be processed. If the news tag does not include the preset tag, it is indicated that the key information in the news information has no influence on the enterprise list.
It should be particularly noted that, in the method for processing an enterprise list provided in the embodiment of the present specification, whether the news tag includes a preset tag includes not only text matching but also semantic matching. It can be understood that, since the news tag is generated according to the news information, the news tag may not be completely consistent with the preset tag in terms of text, but has similar semantics, when the semantic similarity between a certain news tag and the preset tag exceeds a preset threshold, for example, 90%, semantic matching between the news tag and the preset tag is determined, that is, the news tag includes the preset tag.
And step S106, determining enterprises meeting preset conditions in the first enterprise list as risk enterprises.
It should be noted that in the embodiment of the present specification, a mode of determining an enterprise meeting a preset condition in the first enterprise list as an enterprise at risk is adopted to implement processing on the first enterprise list. In fact, different processing modes can be adopted for different types of enterprise lists. For the enterprise white list with higher risk sensitivity, the enterprise with the risk is directly determined as the risk enterprise, so that the enterprise can be quickly and effectively prevented from cheating the fund of the financial institution, and the risk of the financial institution is reduced.
In order to more clearly illustrate how the processing method of the business list provided in the embodiment of the present disclosure processes the business list according to the news tag, the following examples are provided.
The above-mentioned white list of the enterprise is taken as an example to explain, and the preset label is high liability. If the news label corresponding to the news information is performance increase and market expansion, the enterprise list does not need to be processed, and the enterprise is continuously kept in the enterprise white list. And if the news label corresponding to the news information is high liability and debt disputes including a preset label, the enterprise list needs to be processed, and the enterprise is determined as an inauguration enterprise to mark if the enterprise does not meet the requirement of good credit in the enterprise white list.
To sum up, the method for processing an enterprise list provided in the embodiment of the present specification obtains a first enterprise list to be processed, and respectively obtains news information related to each enterprise. And screening the news information, and respectively generating a news label corresponding to each enterprise according to the screened news information. And respectively judging whether the news labels corresponding to the enterprises comprise preset labels or not, and if the news labels corresponding to the enterprises comprise the preset labels, determining that the enterprises meet preset conditions. And determining the enterprises meeting the preset conditions in the first enterprise list as risk enterprises.
In the foregoing embodiment, after a business is determined to be an inauguration business, the business may be flagged, but the name of the inauguration business is still stored in the first business list.
In order to optimize the first enterprise list, reduce the data volume of the first enterprise list, and reduce the workload of subsequent data processing, a possible implementation manner is that, in step S106, after determining an enterprise meeting a preset condition in the first enterprise list as an inauguration enterprise, the method further includes:
and step S107, deleting the risk enterprises from the first enterprise list.
In order to enable the business lists provided by the embodiments of the present specification to be provided to customers of different industry categories, the business lists provided by the embodiments of the present specification may correspond to a certain industry category. Specifically, the enterprise list may be refined, and enterprises belonging to the same industry category are set in the same enterprise list, so as to obtain a plurality of enterprise lists corresponding to different industry categories respectively.
In order to set enterprises of different industry categories in different enterprise lists, the embodiment of the specification further provides another processing method of the enterprise lists. Fig. 2 is a schematic flowchart of another method for processing a business list according to an embodiment of the present disclosure, where as shown in fig. 2, the method includes:
step S201, a first enterprise list to be processed is obtained.
Wherein the first business list corresponds to a first business category.
Step S202, news information related to each enterprise is acquired, respectively.
Step S203, judging whether the news information includes industry professional terms.
Wherein the industry specialty is determined from the first industry category.
And step S204, if not, deleting the news information which does not comprise the industry professional term.
It should be noted that although the white list of businesses is provided to the financial institution for determining the risk of the business, the risk factors are different for different business categories of businesses. For example, for a manufacturing enterprise, the supply chain is critical to the enterprise, and once a problem occurs in the supply chain, the normal operation of the entire enterprise will become a problem. For internet enterprises, user traffic is the key of the enterprises, and once the number of users drops down on a large scale, the development of the enterprises can be stagnated or even shut down.
The embodiment of the specification sets corresponding industry professional terms for enterprises of different industry types. The industry specials corresponding to each industry category relate to the operating mode of the enterprise in that industry category and may affect the operating condition of the enterprise.
It can be understood that the quantity of news information related to enterprises obtained from the whole network search is huge, and in order to reduce the data processing amount in the subsequent steps and improve the accuracy of the generated news tags, only the news information including the professional terms of the industry can be processed in the next step to generate the corresponding news tags.
And S205, respectively generating news labels corresponding to each enterprise according to the screened news information.
Step S206, whether the news labels corresponding to each enterprise comprise preset labels or not is judged respectively.
Step S207, if the news tag corresponding to the enterprise includes a preset tag, it is determined that the enterprise meets a preset condition.
And step S208, determining the enterprises meeting the preset conditions in the first enterprise list as risk enterprises.
And step S209, deleting the risk enterprises from the first enterprise list.
Therefore, the correspondence between the enterprise list and the industry category is realized, and the enterprise list is more refined.
In addition, the corresponding enterprise lists are set for the enterprises of different industry categories, and the situation that the related enterprises are located in different enterprise lists may occur. Such as: when the parent company is a manufacturing enterprise and the subsidiary company is a sales enterprise, it is likely that the parent company cheats the funds of the financial institution on the behalf of the subsidiary company when the parent company encounters a sudden crisis, and risks are brought to the financial institution.
Therefore, in order to avoid the above situation, in the embodiment of the present specification, before deleting the enterprise meeting the preset condition from the first enterprise list, a recheck needs to be performed on the enterprise not meeting the preset condition.
Specifically, the stock right information of the enterprises which do not accord with the preset conditions is obtained, and the related enterprises of the enterprises which do not accord with the preset conditions are determined according to the stock right information. And judging whether the associated enterprise is located in a second enterprise list corresponding to the second industry type according to the second industry type corresponding to the associated enterprise. If not, determining that the enterprise meets the preset conditions.
It is understood that, for the first business list and the second business list, the determination of whether the business meets the preset condition is synchronous and repeated. Once a certain enterprise meets the preset conditions, all related enterprises of the enterprise are affected and deleted from the corresponding enterprise list.
It should be noted that, for the enterprises having the stock right association, the enterprises may also be located in the same enterprise list, that is, the first enterprise list and the second enterprise list are the same enterprise list. And deleting the share right associated enterprises in the enterprise list once a certain enterprise meets the preset conditions.
In addition, in order to generate a news tag corresponding to each enterprise according to news information, another method for processing an enterprise list is also provided in the embodiments of the present specification. Fig. 3 is a flowchart illustrating a method for processing a business list according to an embodiment of the present disclosure. As shown in fig. 3, the method includes:
step S301, a first enterprise list to be processed is obtained.
The first business list comprises names of a plurality of businesses.
Step S302, news information related to each enterprise is acquired, respectively.
Step S303, the news information is filtered.
And step S304, performing word segmentation on the screened news information, and generating a plurality of keywords corresponding to the news information according to word segmentation results.
Step S305, clustering the plurality of keywords, and generating news labels corresponding to enterprises according to clustering results.
Based on the foregoing description, it can be known that the screened news information is usually a segment of text, and the news tag is a refinement of the text, which shows key information in the news information.
In order to refine key information in news information, in the embodiment of the present specification, a plurality of keywords corresponding to the news information are generated by segmenting the screened news information. The determination of the keywords may be implemented according to various natural semantic recognition modes such as word frequency statistics, which is not limited in the embodiments of this specification.
After the keywords are determined, a plurality of words with similar word senses exist among the keywords, so that the keywords can be clustered to avoid a large number of words with similar word senses in the news label, and the news label is generated according to a clustering result to reduce subsequent data processing amount.
Further, in the process of generating the news tag, the keywords are clustered, and the number of the keywords corresponding to different clustering clusters in the clustering result reflects the description of the image of the enterprise in the news information.
Therefore, after the news tags corresponding to the enterprises are generated according to the clustering result, the weight corresponding to each news tag can be generated according to the clustering result, wherein the weight corresponding to the news tag is related to the number of the keywords corresponding to the news tag. And generating the portrait corresponding to the enterprise according to the news label and the weight corresponding to the news label.
In the embodiment of the present invention, since news information related to a business is continuously acquired, news tags and drawings are also continuously generated, and the drawings of the business are statistically analyzed, thereby generating a change situation of the business.
Step S306, respectively judging whether the news labels corresponding to each enterprise comprise preset labels.
Step S307, if the news tag corresponding to the enterprise includes a preset tag, determining that the enterprise meets a preset condition.
Step S308, determining the enterprises meeting the preset conditions in the first enterprise list as risk enterprises.
And step S309, deleting the risk enterprises from the first enterprise list.
Therefore, the news label corresponding to each enterprise is generated according to the news information.
The foregoing description of the method for processing an enterprise list is to process an existing enterprise list after the enterprise list is generated, and the first enterprise list in this embodiment of the present description may be generated by the following steps, that is, before acquiring the first enterprise list to be processed, the method further includes:
step S11, business information and business information of the enterprise are obtained from a plurality of data sources.
And step S12, performing risk assessment on the enterprise according to the business information and the operation information.
Step S13, if the risk score of the enterprise is less than or equal to the preset threshold, adding the enterprise into the first enterprise list.
It should be understood that the first business list in the embodiment of the present disclosure is a white list of good-credit businesses, and to add to the first business list, businesses whose risk scores are less than or equal to a preset threshold value through risk assessment may be added to the first business list.
In order to objectively and comprehensively evaluate the risk of an enterprise, it is necessary to obtain the business information and the operation information of the enterprise from a plurality of data sources, for example, obtain the related information of the enterprise from a financial office, obtain the related filing information of the enterprise from a public security organization, and obtain the risk information of the enterprise from an enterprise information query website. The information is summarized and cross-validated, so that the accuracy of risk assessment can be improved.
It should be noted that different risk assessment models are required to be used for risk assessment for different types of enterprises, and especially for financial-like enterprises, a variety of specialized assessment models such as a general scoring model, a P2P risk model, a petty loan model, and the like can be used.
In order to more clearly illustrate how the embodiment of the present specification generates the first business list and processes the first business list, the embodiment of the present specification further provides another processing method of the business list. Fig. 4 is a flowchart illustrating a method for processing a business list according to an embodiment of the present disclosure. As shown in fig. 4, the method includes:
step S401, business information and operation information of enterprises are obtained from a plurality of data sources.
And S402, performing risk assessment on the enterprise according to the industrial and commercial information and the operation information.
Step S403, if the risk score of the enterprise is less than or equal to the preset threshold, adding the enterprise into the first enterprise list.
Step S404, a first enterprise list to be processed is obtained.
Wherein the first business list corresponds to a first business category.
Step S405, news information related to each enterprise is acquired, respectively.
Step S406, judging whether the news information includes industry professional terms.
Wherein the industry specialty is determined from the first industry category.
And step S407, if not, deleting the news information which does not comprise the industry professional term.
Step S408, performing word segmentation on the screened news information, and generating a plurality of keywords corresponding to the news information according to word segmentation results.
And step S409, clustering the keywords, and generating news labels corresponding to enterprises according to clustering results.
Step S410, respectively determining whether the news tags corresponding to each enterprise include a preset tag.
Step S411, if the news tag corresponding to the enterprise includes a preset tag, determining that the enterprise meets a preset condition.
Step S412, acquiring the share right information of the enterprises which do not meet the preset conditions.
Step S413, according to the equity information, determining the related enterprises that do not meet the preset condition.
Step S414, according to the second industry category corresponding to the associated enterprise, determining whether the associated enterprise is located in a second enterprise list corresponding to the second industry category.
Step S415, if not, determining that the enterprise meets the preset condition.
Step S416, determining the enterprises in the first enterprise list that meet the preset conditions as risk enterprises.
And step S417, deleting the risk enterprises from the first enterprise list.
It should be noted that the explanation of the foregoing embodiment also applies to steps S401 to S416, and is not repeated here.
Therefore, the first enterprise list is generated according to the business information and the operation information of the enterprises, and then the first enterprise list is processed in time according to the news information related to each enterprise.
In order to more clearly describe the steps of the method for processing the enterprise list provided in the embodiments of the present disclosure, the following description is made by way of example.
Fig. 5 is a flowchart of an example of a method for processing a business list according to an embodiment of the present disclosure. As shown in fig. 5, the related information of the enterprise is obtained from a plurality of channels such as a financial office, a public security organization, an enterprise information query website, and the like, and the business information and the operation information of the enterprise are obtained after the information is collected. And performing risk assessment on the enterprise according to the business information and the operation information of the enterprise, and if the risk score of the enterprise meets the requirement, adding the enterprise into a first enterprise list corresponding to the first enterprise category according to the first enterprise category where the enterprise is located.
When an emergency occurs, news information related to an enterprise is obtained in time, and the news information is extracted to generate a news label. And if the news label comprises a preset label, the enterprise is indicated to have a larger risk, the enterprise is determined to be an inauguration enterprise, and the enterprise is deleted from the first enterprise list. In addition, for the enterprises remaining in the first enterprise list, it is necessary to determine whether the corresponding share rights associated enterprises are at a greater risk, specifically by checking whether the share rights associated enterprises are located in the corresponding second enterprise list. If the equity associated business has been deleted from the second business list, the business is also deleted from the first business list.
In order to implement the foregoing embodiment, an embodiment of the present specification further provides a device for processing an enterprise list. Fig. 6 is a schematic structural diagram of an apparatus for processing an enterprise list according to an embodiment of the present disclosure, as shown in fig. 6, the apparatus includes: the system comprises a first obtainingmodule 510, a second obtainingmodule 520, ascreening module 530, agenerating module 540, afirst judging module 550, a first determiningmodule 560 and a second determiningmodule 570.
The first obtainingmodule 510 is configured to obtain a first enterprise list to be processed.
The first business list comprises names of a plurality of businesses.
A second obtainingmodule 520, configured to obtain news information related to each enterprise, respectively.
And afiltering module 530, configured to filter the news information.
And thegenerating module 540 is configured to generate a news tag corresponding to each enterprise according to the screened news information.
The first determiningmodule 550 is configured to determine whether the news tag corresponding to each enterprise includes a preset tag.
The first determiningmodule 560 is configured to determine that the enterprise meets the preset condition when the first determiningmodule 550 determines that the news tag corresponding to the enterprise includes a preset tag.
And the second determiningmodule 570 is configured to determine, as the risk enterprise, an enterprise in the first enterprise list that meets the preset condition.
Further, in order to optimize the first enterprise list, a possible implementation manner is that the apparatus further includes: a delete module 580 for deleting the at-risk business from the first list of businesses.
It should be noted that the explanation of the embodiment of the method for processing an enterprise list is also applicable to the apparatus for processing an enterprise list of the embodiment, and details are not repeated here.
To sum up, the processing apparatus for an enterprise list provided in the embodiment of the present specification obtains a first enterprise list to be processed, and respectively obtains news information related to each enterprise. And screening the news information, and respectively generating a news label corresponding to each enterprise according to the screened news information. And respectively judging whether the news labels corresponding to the enterprises comprise preset labels or not, and if the news labels corresponding to the enterprises comprise the preset labels, determining that the enterprises meet preset conditions. And determining the enterprises meeting the preset conditions in the first enterprise list as risk enterprises.
In order to implement the foregoing embodiment, another apparatus for processing an enterprise list is further provided in this embodiment of the present specification. Fig. 7 is a schematic structural diagram of another apparatus for processing a business list according to an embodiment of the present disclosure. As shown in fig. 7, the apparatus includes: the system comprises a first obtaining module 610, a second obtaining module 620, a screening module 630, a generating module 640, a first judging module 650, a first determining module 660, a second determining module 670 and a deleting module 680.
The first obtaining module 610 is configured to obtain a first enterprise list to be processed.
The first business list comprises names of a plurality of businesses.
And a second obtaining module 620, configured to obtain news information related to each enterprise, respectively.
And a filtering module 630, configured to filter the news information.
And a generating module 640, configured to generate, according to the screened news information, a news tag corresponding to each enterprise respectively.
The first determining module 650 is configured to determine whether the news tag corresponding to each enterprise includes a preset tag.
The first determining module 660 is configured to determine that the enterprise meets the preset condition when the first determining module 650 determines that the news tag corresponding to the enterprise includes a preset tag.
And the second determining module 670 is configured to determine, as an inauguration enterprise, an enterprise in the first enterprise list that meets the preset condition.
A delete module 680 configured to delete the inauguration enterprises from the first enterprise list.
Wherein, the screening module 630 includes: the determining sub-module 631 is configured to determine whether the news information includes industry vocabularies. Wherein the industry specialty is determined from the first industry category. The delete sub-module 632 is configured to delete the news information that does not include the industry vocabularies when the judging sub-module 631 determines that the news information does not include the industry vocabularies.
Further, in order to perform a rechecking operation on an enterprise that does not meet the preset condition, a possible implementation manner is that the apparatus further includes: the third obtaining module 690 is configured to obtain the equity information of the enterprise that does not meet the preset condition. A third determining module 6100, configured to determine, according to the equity information, an associated enterprise of the enterprise that does not meet the preset condition. The second determining module 6110 is configured to determine, according to the second industry category corresponding to the associated enterprise, whether the associated enterprise is located in a second enterprise list corresponding to the second industry category. The fourth determining module 6120 is configured to determine that the enterprise meets the preset condition when the second determining module 6110 determines that the associated enterprise is located in the second enterprise list corresponding to the second industry category.
It should be noted that the explanation of the embodiment of the method for processing an enterprise list is also applicable to the apparatus for processing an enterprise list of the embodiment, and details are not repeated here.
Therefore, the correspondence between the enterprise list and the industry category is realized, and the enterprise list is more refined.
In order to implement the foregoing embodiment, the present specification further provides another apparatus for processing an enterprise list. Fig. 8 is a schematic structural diagram of another apparatus for processing an enterprise list according to an embodiment of the present disclosure. As shown in fig. 8, the apparatus includes: a first obtainingmodule 710, a second obtainingmodule 720, ascreening module 730, agenerating module 740, afirst judging module 750, a first determiningmodule 760, a second determiningmodule 770, and a deletingmodule 780.
The first obtainingmodule 710 is configured to obtain a first enterprise list to be processed.
The first business list comprises names of a plurality of businesses.
A second obtainingmodule 720, configured to obtain news information related to each enterprise respectively.
And thescreening module 730 is used for screening the news information.
And agenerating module 740, configured to generate, according to the screened news information, a news tag corresponding to each enterprise respectively.
The first determiningmodule 750 is configured to determine whether the news tag corresponding to each enterprise includes a preset tag.
The first determiningmodule 760 is configured to determine that the enterprise meets the preset condition when the first determiningmodule 750 determines that the news tag corresponding to the enterprise includes a preset tag.
The second determiningmodule 770 is configured to determine, as an inauguration enterprise, an enterprise in the first enterprise list that meets the preset condition.
Adeletion module 780 configured to delete the inauguration enterprises from the first enterprise list.
Wherein, thegenerating module 740 comprises: and theword segmentation sub-module 741 is used for segmenting the screened news information. Thefirst generating sub-module 742 is configured to generate a plurality of keywords corresponding to the news information according to the word segmentation result. Aclustering submodule 743 is used for clustering the plurality of keywords. And thesecond generation submodule 744 is used for generating a news tag corresponding to the enterprise according to the clustering result.
Further, in order to generate a representation corresponding to an enterprise, in one possible implementation, thegenerating module 740 further includes: and thethird generation submodule 744 is configured to generate a weight corresponding to each news tag according to the clustering result. The fourth generating submodule 745 is configured to generate the portrait corresponding to the enterprise according to the news tag and the weight corresponding to the news tag.
It should be noted that the explanation of the embodiment of the method for processing an enterprise list is also applicable to the apparatus for processing an enterprise list of the embodiment, and details are not repeated here.
Therefore, the news label corresponding to each enterprise is generated according to the news information.
In order to implement the foregoing embodiment, the embodiment of this specification further provides another apparatus for processing an enterprise list. Fig. 9 is a schematic structural diagram of another apparatus for processing an enterprise list according to an embodiment of the present disclosure. As shown in fig. 9, the apparatus includes: the system comprises a fourth obtainingmodule 810, an evaluatingmodule 820, an addingmodule 830, a first obtainingmodule 840, a second obtainingmodule 850, ascreening module 860, agenerating module 870, afirst judging module 880, a first determiningmodule 890, a third obtainingmodule 8100, a third determiningmodule 8110, asecond judging module 8120, a fourth determiningmodule 8130, a second determiningmodule 8140 and a deletingmodule 8150.
And a fourth obtainingmodule 810, configured to obtain the business information and the business information of the enterprise from multiple data sources.
And theevaluation module 820 is used for carrying out risk evaluation on the enterprise according to the industrial and commercial information and the operation information.
And an addingmodule 830, configured to add the enterprise to the first enterprise list when the risk score of the enterprise is less than or equal to a preset threshold.
The first obtainingmodule 840 is configured to obtain a first enterprise list to be processed.
The first business list comprises names of a plurality of businesses.
A second obtainingmodule 850, configured to obtain news information related to each enterprise, respectively.
And thescreening module 860 is used for screening the news information.
Thegenerating module 870 is configured to generate a news tag corresponding to each enterprise according to the screened news information.
The first determiningmodule 880 is configured to determine whether the news tag corresponding to each enterprise includes a preset tag.
A first determiningmodule 890, configured to determine that the enterprise meets the preset condition when the first determiningmodule 880 determines that the news tag corresponding to the enterprise includes the preset tag.
And a third obtainingmodule 8100, configured to obtain the right-to-stock information of the enterprise that does not meet the preset condition.
And a third determiningmodule 8110, configured to determine, according to the equity information, a related enterprise of the enterprise that does not meet the preset condition.
The second determiningmodule 8120 is configured to determine whether the associated enterprise is located in a second enterprise list corresponding to a second industry category according to the second industry category corresponding to the associated enterprise.
A fourth determiningmodule 8130, configured to determine that the enterprise meets the preset condition when the second determiningmodule 8120 determines that the associated enterprise is located in the second enterprise list corresponding to the second industry category.
And a second determiningmodule 8140, configured to determine, as an inauguration enterprise, an enterprise in the first enterprise list that meets a preset condition.
Adeletion module 8150 for deleting the inauguration enterprises from the first enterprise list.
Wherein thescreening module 860 includes: and thejudgment submodule 861 is used for judging whether the news information comprises professional terms or not. Wherein the industry specialty is determined from the first industry category. A deletion sub-module 862 for deleting the news information not including the industry specialty when thejudgment sub-module 861 determines that the news information does not include the industry specialty.
Thegeneration module 870 includes: and aword segmentation submodule 871, configured to segment words of the screened news information. Thefirst generating sub-module 872 is configured to generate a plurality of keywords corresponding to the news information according to the word segmentation result. And aclustering submodule 873 for clustering the plurality of keywords. Thesecond generating sub-module 874 is configured to generate a news tag corresponding to the enterprise according to the clustering result.
It should be noted that the explanation of the embodiment of the method for processing an enterprise list is also applicable to the apparatus for processing an enterprise list of the embodiment, and details are not repeated here.
Therefore, the first enterprise list is generated according to the business information and the operation information of the enterprises, and news processing is carried out on the first enterprise list according to the news information related to each enterprise.
In order to implement the foregoing embodiments, the present specification further provides a computer device, including a memory and a processor; the memory having stored thereon a computer program executable by the processor; when the processor runs the computer program, the method for processing the enterprise list according to the foregoing method embodiment is performed.
In order to implement the above embodiments, embodiments further propose a non-transitory computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method of processing the enterprise list as described in the aforementioned method embodiments.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the embodiments herein, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
In the embodiments of the present specification, unless otherwise specifically stated or limited, the terms "mounted," "connected," and "fixed" are to be construed broadly, e.g., as meaning fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; they may be directly connected or indirectly connected through intervening media, or they may be connected internally or in any other suitable relationship, unless expressly stated otherwise. Specific meanings of the above terms in the embodiments of the present specification can be understood by those of ordinary skill in the art according to specific situations.
In embodiments of the present specification, unless explicitly stated or limited otherwise, a first feature may be "on" or "under" a second feature in direct contact with the first and second features, or in indirect contact with the first and second features through intervening media. Also, a first feature "on," "over," and "above" a second feature may be directly or diagonally above the second feature, or may simply indicate that the first feature is at a higher level than the second feature. A first feature being "under," "below," and "beneath" a second feature may be directly under or obliquely under the first feature, or may simply mean that the first feature is at a lesser elevation than the second feature.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of an embodiment of the specification. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (16)
1. A method for processing a business list comprises the following steps:
acquiring a first enterprise list to be processed; wherein the first list of businesses comprises names of a plurality of businesses;
respectively acquiring news information related to each enterprise;
screening the news information, and respectively generating a news label corresponding to each enterprise according to the screened news information;
respectively judging whether the news tags corresponding to the enterprises comprise preset tags or not;
if the news tag corresponding to the enterprise comprises the preset tag, determining that the enterprise meets a preset condition; and
and determining the enterprises meeting the preset conditions in the first enterprise list as risk enterprises.
2. The method of claim 1, the first business list corresponding to a first business category, the filtering the news information comprising:
judging whether the news information comprises the industry professional wordings; the industry specialty terms are determined from the first industry category;
and if not, deleting the news information which does not comprise the industry professional terms.
3. The method of claim 1, wherein the generating a news tag corresponding to each of the businesses respectively according to the filtered news information comprises:
segmenting the screened news information, and generating a plurality of keywords corresponding to the news information according to a segmentation result;
clustering the keywords, and generating the news labels corresponding to the enterprises according to clustering results.
4. The method of claim 3, after the generating the news tag corresponding to the business according to the clustering result, further comprising:
generating a weight corresponding to each news label according to a clustering result;
and generating the portrait corresponding to the enterprise according to the news tag and the weight corresponding to the news tag.
5. The method of claim 2, further comprising, before said determining said businesses in said first list of businesses that meet said predetermined criteria as inauguration businesses:
acquiring the stock right information of the enterprise which does not accord with the preset condition;
determining the related enterprises which do not meet the preset conditions according to the stock right information;
judging whether the associated enterprise is located in a second enterprise list corresponding to a second industry type or not according to the second industry type corresponding to the associated enterprise;
if not, determining that the enterprise meets the preset conditions.
6. The method of claim 1, after said determining said businesses in said first list that meet said predetermined condition as inauguration businesses, further comprising:
and deleting the risk enterprises from the first enterprise list.
7. The method of any of claims 1-6, further comprising, prior to the obtaining the first roster of businesses to be processed:
acquiring the business information and the operation information of the enterprise from a plurality of data sources;
according to the business information and the operation information, performing risk assessment on the enterprise;
and if the risk score of the enterprise is smaller than or equal to a preset threshold value, adding the enterprise into the first enterprise list.
8. An apparatus for processing a business list, comprising:
the first acquisition module is used for acquiring a first enterprise list to be processed;
wherein the first list of businesses comprises names of a plurality of businesses;
the second acquisition module is used for respectively acquiring news information related to each enterprise;
the screening module is used for screening the news information;
the generating module is used for respectively generating a news label corresponding to each enterprise according to the screened news information;
the first judging module is used for respectively judging whether the news tags corresponding to the enterprises comprise preset tags or not;
the first determining module is used for determining that the enterprise meets a preset condition when the first judging module determines that the news tag corresponding to the enterprise comprises the preset tag; and
and the second determining module is used for determining the enterprises meeting the preset conditions in the first enterprise list as risk enterprises.
9. The apparatus of claim 8, the first list of businesses corresponding to a first business category, the filtering module comprising:
the judging submodule is used for judging whether the news information comprises the industry professional wording; the industry specialty terms are determined from the first industry category;
and the deleting submodule is used for deleting the news information which does not include the industry professional wording when the judging submodule determines that the news information does not include the industry professional wording.
10. The apparatus of claim 8, the generating module comprising:
the word segmentation submodule is used for segmenting the screened news information;
the first generation submodule is used for generating a plurality of keywords corresponding to the news information according to the word segmentation result;
the clustering submodule is used for clustering the plurality of keywords;
and the second generation submodule is used for generating the news label corresponding to the enterprise according to the clustering result.
11. The apparatus of claim 10, the generating module further comprising:
the third generation submodule is used for generating the weight corresponding to each news label according to the clustering result;
and the fourth generation submodule is used for generating the portrait corresponding to the enterprise according to the news tag and the weight corresponding to the news tag.
12. The apparatus of claim 9, the apparatus further comprising:
the third acquisition module is used for acquiring the share right information of the enterprise which does not accord with the preset condition;
a third determining module, configured to determine, according to the stock right information, an associated enterprise of the enterprise that does not meet the preset condition;
the second judging module is used for judging whether the associated enterprise is located in a second enterprise list corresponding to a second industry type according to the second industry type corresponding to the associated enterprise;
a fourth determining module, configured to determine that the enterprise meets the preset condition when the second determining module determines that the associated enterprise is located in a second enterprise list corresponding to the second industry category.
13. The apparatus of claim 8, further comprising:
and the deleting module is used for deleting the risk enterprises from the first enterprise list.
14. The apparatus of any one of claims 8-13, further comprising:
the fourth acquisition module is used for acquiring the business information and the operation information of the enterprise from a plurality of data sources;
the evaluation module is used for carrying out risk evaluation on the enterprise according to the business information and the operation information;
and the adding module is used for adding the enterprise into the first enterprise list when the risk score of the enterprise is less than or equal to a preset threshold value.
15. A computer device comprising a memory and a processor; the memory having stored thereon a computer program executable by the processor; the processor, when executing the computer program, performs the method of processing a business listing according to any of claims 1-7.
16. A non-transitory computer-readable storage medium, having stored thereon a computer program which, when executed by a processor, implements a method of processing a list of businesses as claimed in any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910964776.8ACN110688463A (en) | 2019-10-11 | 2019-10-11 | Enterprise list processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910964776.8ACN110688463A (en) | 2019-10-11 | 2019-10-11 | Enterprise list processing method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110688463Atrue CN110688463A (en) | 2020-01-14 |
Family
ID=69112184
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910964776.8APendingCN110688463A (en) | 2019-10-11 | 2019-10-11 | Enterprise list processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110688463A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111914064A (en)* | 2020-07-29 | 2020-11-10 | 王嘉兴 | Text mining method, device, equipment and medium |
| CN112749742A (en)* | 2020-12-30 | 2021-05-04 | 北京知因智慧科技有限公司 | Source risk score quantification method and device and electronic equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| 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 |
| 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 |
| TW201917664A (en)* | 2017-10-19 | 2019-05-01 | 李智婷 | Shared watch list system using Blockchain |
| CN110033171A (en)* | 2019-03-19 | 2019-07-19 | 阿里巴巴集团控股有限公司 | A kind of method, system platform and medium identifying financial company's risk |
| CN110175784A (en)* | 2019-05-30 | 2019-08-27 | 杭州一骑轻尘信息技术有限公司 | Auto metal halide lamp risk control method, apparatus and system |
- 2019
- 2019-10-11CNCN201910964776.8Apatent/CN110688463A/enactivePending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW201917664A (en)* | 2017-10-19 | 2019-05-01 | 李智婷 | Shared watch list system using Blockchain |
| 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 |
| 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 |
| 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 |
| CN110033171A (en)* | 2019-03-19 | 2019-07-19 | 阿里巴巴集团控股有限公司 | A kind of method, system platform and medium identifying financial company's risk |
| CN110175784A (en)* | 2019-05-30 | 2019-08-27 | 杭州一骑轻尘信息技术有限公司 | Auto metal halide lamp risk control method, apparatus and system |
Non-Patent Citations (1)
| Title |
|---|
| 魏国雄: "《信贷风险管理》", 31 October 2008, 北京：中国金融出版社* |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111914064A (en)* | 2020-07-29 | 2020-11-10 | 王嘉兴 | Text mining method, device, equipment and medium |
| CN112749742A (en)* | 2020-12-30 | 2021-05-04 | 北京知因智慧科技有限公司 | Source risk score quantification method and device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11663254B2 (en) | System and engine for seeded clustering of news events | |
| US11645321B2 (en) | Calculating relationship strength using an activity-based distributed graph | |
| JP5575902B2 (en) | Information retrieval based on query semantic patterns | |
| KR101231560B1 (en) | Method and system for discovery and modification of data clusters and synonyms | |
| US20170177733A1 (en) | Tenantization of search result ranking | |
| WO2021098648A1 (en) | Text recommendation method, apparatus and device, and medium | |
| US20160085742A1 (en) | Automated collective term and phrase index | |
| WO2018195105A1 (en) | Document similarity analysis | |
| WO2009009192A2 (en) | Adaptive archive data management | |
| US20170270439A1 (en) | System and method to present a summarized task view in a case management system | |
| WO2012129149A2 (en) | Aggregating search results based on associating data instances with knowledge base entities | |
| CN111881283B (en) | Business keyword library creation method, intelligent chat guiding method and device | |
| JP2018538603A (en) | Identify query patterns and related total statistics between search queries | |
| US11226972B2 (en) | Ranking collections of document passages associated with an entity name by relevance to a query | |
| US20130246463A1 (en) | Prediction and isolation of patterns across datasets | |
| US12112133B2 (en) | Multi-model approach to natural language processing and recommendation generation | |
| CN111930967B (en) | Data query method and device based on knowledge graph and storage medium | |
| CN113239295A (en) | Search method, search device, electronic equipment and storage medium | |
| CA2956627A1 (en) | System and engine for seeded clustering of news events | |
| CN114461783A (en) | Keyword generating method, apparatus, computer equipment, storage medium and product | |
| CN110688463A (en) | Enterprise list processing method and device | |
| US9336280B2 (en) | Method for entity-driven alerts based on disambiguated features | |
| CN115994534A (en) | Method, device, equipment and storage medium for mining hot words in government affairs scene | |
| CN115239214A (en) | Enterprise evaluation processing method and device and electronic equipment | |
| CN113177116B (en) | Information display method and device, electronic equipment, storage medium and program product |
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 | ||
| RJ01 | Rejection of invention patent application after publication | Application publication date:20200114 | |
| RJ01 | Rejection of invention patent application after publication |