CN116663909A - Provider risk identification data processing method and device - Google Patents
Provider risk identification data processing method and device Download PDFInfo
- Publication number
- CN116663909A CN116663909A CN202310756778.4A CN202310756778A CN116663909A CN 116663909 A CN116663909 A CN 116663909A CN 202310756778 A CN202310756778 A CN 202310756778A CN 116663909 A CN116663909 A CN 116663909A
- Authority
- CN
- China
- Prior art keywords
- data
- provider
- cooperation
- dimension
- supplier
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 22
- 238000012545 processing Methods 0.000 claims abstract description 110
- 230000004044 response Effects 0.000 claims abstract description 39
- 238000012216 screening Methods 0.000 claims abstract description 24
- 238000004458 analytical method Methods 0.000 claims description 34
- 238000000034 method Methods 0.000 claims description 30
- 238000012502 risk assessment Methods 0.000 claims description 28
- 238000007726 management method Methods 0.000 claims description 15
- 238000013058 risk prediction model Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000013145 classification model Methods 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000012163 sequencing technique Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 5
- 238000007405 data analysis Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 8
- 230000011218 segmentation Effects 0.000 description 6
- 230000008859 change Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 5
- 230000000977 initiatory effect Effects 0.000 description 4
- 238000013500 data storage Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 238000003058 natural language processing Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000004984 smart glass Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/018—Certifying business or products
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The specification provides a provider risk identification data processing method and device, wherein the provider risk identification data processing method comprises the following steps: determining a set of affiliated suppliers and a set of non-affiliated suppliers in response to the business processing requirements; reading cooperation data corresponding to each cooperation provider in the cooperation provider set, and collecting public data of each non-cooperation provider in the non-cooperation provider set; carrying out cooperative risk prediction on each cooperative supplier in a cooperative risk prediction dimension according to the cooperative data, and screening a first supplier from the cooperative supplier set according to a prediction result; carrying out cooperative risk prediction on each uncooperative provider in a dimension to be cooperative risk prediction according to the public data, and screening a second provider in the uncooperative provider set according to a prediction result; and constructing a supplier set based on the first supplier and the second supplier, and creating and displaying a multi-dimensional supplier portrait according to the attribute data of each supplier in the supplier set.
Description
Technical Field
The present disclosure relates to the field of data processing technologies, and in particular, to a vendor risk identification data processing method and device.
Background
With the development of internet technology, data has become an important component of inter-enterprise communication. And the data is started along with a large amount of information, so that a data analysis platform of an enterprise needs to be capable of realizing the data analysis requirements of different departments, and therefore accurate data service can be provided for a demander. However, in the prior art, most of data analysis platforms used in enterprises are user-oriented, and data services which can be provided by the data analysis platforms are related to user groups based on business requirements; meanwhile, under the condition of facing complex demand, the data service has too simple feedback result, can simply feed back surface conditions, and cannot make auxiliary explanation, so that the service demand cannot be met under the complex demand; there is therefore a need for an effective solution to the above problems.
Disclosure of Invention
In view of this, the present embodiment provides a vendor risk identification data processing method. The present specification also relates to a vendor risk identification data processing apparatus, a computing device, and a computer-readable storage medium, which solve the technical drawbacks existing in the prior art.
According to a first aspect of embodiments of the present specification, there is provided a vendor risk identification data processing method, including:
determining a set of affiliated suppliers and a set of non-affiliated suppliers in response to the business processing requirements;
reading cooperation data corresponding to each cooperation provider in the cooperation provider set, and collecting public data of each non-cooperation provider in the non-cooperation provider set;
carrying out cooperative risk prediction on each cooperative supplier in a cooperative risk prediction dimension according to the cooperative data, and screening a first supplier from the cooperative supplier set according to a prediction result;
carrying out cooperative risk prediction on each uncooperative provider in a dimension to be cooperative risk prediction according to the public data, and screening a second provider in the uncooperative provider set according to a prediction result;
and constructing a supplier set based on the first supplier and the second supplier, and creating and displaying a multi-dimensional supplier portrait according to the attribute data of each supplier in the supplier set.
Optionally, the determining the set of affiliated suppliers and the set of non-affiliated suppliers in response to the business processing requirement includes:
receiving a service processing demand submitted by a service demand party, and determining provider type information according to the service processing demand;
Selecting a partner provider in an initial set of providers in response to the provider type information, constituting the set of partner providers;
and sorting suppliers in the set region according to the supplier type information, and selecting non-cooperative suppliers to form the non-cooperative supplier set according to the sorting result.
Optionally, the reading of the collaboration data corresponding to any one collaboration provider in the collaboration provider set includes:
a business database is determined in response to the business processing requirements, historical supply data of a cooperative supplier associated supply dimension and historical management data of an associated management dimension are read in the business database, and cooperation data corresponding to the cooperative supplier are determined according to the historical supply data and the historical management data;
or,
and responding to the business processing requirements, determining a business database, determining a reference dimension associated with a supply dimension and/or an operation dimension in a plurality of data dimensions contained in the business database, reading historical supply data of a cooperation provider associated with the supply dimension, historical operation data associated with the operation dimension and reference data associated with the reference dimension in the business database, and determining cooperation data corresponding to the cooperation provider according to the historical supply data, the historical operation data and the reference data.
Optionally, the collecting of public data corresponding to any one of the uncooperative suppliers in the uncooperative supplier set includes:
determining judicial dimension, industrial and commercial dimension, supervision dimension, public opinion dimension and weather dimension associated with the uncooperative suppliers in response to the business processing requirements, and acquiring supplier identification information of the uncooperative suppliers;
collecting judicial data in the judicial dimension according to the supplier identification information, collecting industrial and commercial data in the industrial and commercial dimension, collecting supervision data in a supervision dimension, collecting public opinion data in a public opinion dimension, and collecting weather data in a weather dimension;
and determining the public data corresponding to the uncooperative provider according to the judicial data, the industrial and commercial data, the supervision data, the public opinion data and the weather data.
Optionally, the collaborative risk prediction is performed on each collaborative provider in a collaborative risk prediction dimension according to the collaborative data, and the screening of the first provider in the collaborative provider set according to a prediction result includes:
respectively inputting the cooperation data corresponding to each cooperation provider into a risk prediction model for processing, and determining a risk prediction value of a cooperation risk prediction dimension corresponding to each cooperation provider according to a processing result;
And sequencing the risk prediction scores corresponding to each cooperative supplier, and selecting a first set number of cooperative suppliers as the first suppliers according to the sequencing result.
Optionally, determining the risk prediction score of any one of the cooperating suppliers in the set of cooperating suppliers includes:
determining at least two sub-cooperation risk prediction dimensions contained in the cooperation risk prediction dimensions, and determining sub-risk prediction scores corresponding to each sub-cooperation risk prediction dimension according to processing results;
determining a sub-score weight corresponding to each sub-collaboration risk prediction dimension in response to the business processing requirements;
and carrying out weighted summation calculation on the sub-risk prediction scores and sub-score weights corresponding to each sub-cooperation risk prediction dimension, and determining the risk prediction scores corresponding to the cooperation suppliers according to the calculation results.
Optionally, the performing collaborative risk prediction on each uncooperative provider in the dimension to be collaborative risk prediction according to the disclosure data, and screening the second provider in the uncooperative provider set according to the prediction result includes:
determining at least two sub-risk prediction dimensions contained in the risk prediction dimensions to be cooperated, and inputting the public data corresponding to each non-cooperated supplier into a sub-risk prediction model corresponding to each sub-risk prediction dimension to be cooperated for processing respectively;
Determining risk prediction scores of the at least two sub-risk prediction dimensions corresponding to each uncooperative provider according to the processing results;
and sorting the risk prediction scores corresponding to each uncooperative provider, and selecting a second set number of uncooperative providers as the second providers according to the sorting result.
Optionally, the creating and displaying the multidimensional vendor representation according to the attribute data of each vendor in the vendor set includes:
acquiring attribute data of each provider in the provider set, and a multidimensional provider portrait template comprising a risk overview area, a public opinion overview area, a risk analysis area and a basic analysis area;
updating a multi-dimensional provider representation template comprising the risk overview area, the public opinion overview area, the risk analysis area, and the base analysis area based on attribute data of each provider;
and generating and displaying the multi-dimensional provider portrait according to the updating result, wherein the multi-dimensional provider portrait is used for displaying service information of a target provider, and the target provider is selected from the provider set according to a point selection instruction.
Optionally, before the step of reading the collaboration data corresponding to each collaboration provider in the collaboration provider set and collecting the public data of each non-collaboration provider in the non-collaboration provider set is performed, the method further includes:
receiving initial service data, and preprocessing the initial service data to obtain intermediate service data;
classifying the intermediate service data by using a data classification model to obtain class labels corresponding to the intermediate service data;
and selecting a target service database according to the category label, and writing the intermediate data into the target service database.
Optionally, after the step of receiving the initial service data and preprocessing the initial service data to obtain the intermediate service data, the method further includes:
determining an intermediate text corresponding to the intermediate service data, and segmenting the intermediate text into a plurality of word units;
updating a word stock by utilizing the word units, and constructing index information according to a word stock updating result;
correspondingly, the reading the collaboration data corresponding to each collaboration provider in the collaboration provider set includes:
determining a target word unit in response to the service processing requirement, and inquiring the index information based on the target word unit to obtain data address information;
And reading cooperation data corresponding to each cooperation provider in the cooperation provider set in the target service database according to the data address information.
According to a second aspect of embodiments of the present specification, there is provided a vendor risk identification data processing apparatus comprising:
a determining module configured to determine a set of affiliated suppliers and a set of non-affiliated suppliers in response to the business process requirements;
the reading module is configured to read cooperation data corresponding to each cooperation provider in the cooperation provider set and collect public data of each non-cooperation provider in the non-cooperation provider set;
the first screening module is configured to conduct cooperation risk prediction on each cooperation provider in a cooperation risk prediction dimension according to the cooperation data, and screen a first provider in the cooperation provider set according to a prediction result;
a second screening module configured to perform cooperative risk prediction on each uncooperative provider in a dimension to be cooperative risk prediction according to the disclosure data, and screen a second provider from the set of uncooperative providers according to a prediction result;
and the creation module is configured to construct a supplier set based on the first supplier and the second supplier, and create and display a multi-dimensional supplier portrait according to the attribute data of each supplier in the supplier set.
According to a third aspect of embodiments of the present specification, there is provided a computing device comprising:
a memory and a processor;
the memory is for storing computer executable instructions that when executed by the processor implement the steps of a vendor risk identification data processing method.
According to a fourth aspect of embodiments of the present specification, there is provided a computer readable storage medium storing computer executable instructions which, when executed by a processor, implement the steps of the vendor risk identification data processing method.
In order to respond to service processing requirements, feedback is more visual, and multidimensional provider figures of service requirement information can be reflected from multidimensional, a cooperative provider set and an uncooperative provider set can be determined first, and partnerability analysis can be performed on the basis of internal cooperative suppliers and external uncooperative suppliers when new service processing requirements are met. On the basis, the cooperation data of each cooperation provider in the cooperation provider set can be read first, and the public data of the non-cooperation provider in the non-cooperation provider set can be collected. Then, prediction can be performed on the cooperative suppliers in the cooperative risk prediction dimension, namely, cooperative risk prediction is performed on each cooperative supplier in the cooperative risk prediction dimension according to the cooperative data, so that a cooperative supplier with better cooperative prospect is selected from a cooperative supplier set to serve as a first supplier according to a prediction result; meanwhile, prediction is performed on the non-cooperative suppliers in the risk prediction dimension to be cooperated, namely, cooperation risk prediction is performed on each non-cooperative supplier in the risk prediction dimension to be cooperated according to the public data, and the fact that the non-cooperative suppliers with good cooperation prospects are selected from a non-cooperative supplier set to serve as second suppliers according to the prediction results is achieved. In order to facilitate objective analysis of the business demand party initiating the business processing demand, a provider set can be constructed based on the first provider and the second provider, and multidimensional provider portrait display can be constructed based on attribute data of each provider in the set, so that risk analysis conditions of each provider in different dimensions can be represented through multidimensional provider portraits, and the business demand party can be assisted in subsequent decision judgment and other processing.
Drawings
FIG. 1 is a schematic diagram of a method for processing vendor risk identification data according to an embodiment of the present disclosure;
FIG. 2 is a flow chart of a method for processing vendor risk identification data according to an embodiment of the present disclosure;
FIG. 3 is a schematic diagram of a multi-dimensional vendor representation in a vendor risk identification data processing method according to an embodiment of the present disclosure;
FIG. 4 is a schematic diagram of a vendor risk identification data processing device according to an embodiment of the present disclosure;
fig. 5 is a block diagram of a computing device according to an embodiment of the present disclosure.
Detailed Description
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present description. This description may be embodied in many other forms than described herein and similarly generalized by those skilled in the art to whom this disclosure pertains without departing from the spirit of the disclosure and, therefore, this disclosure is not limited by the specific implementations disclosed below.
The terminology used in the one or more embodiments of the specification is for the purpose of describing particular embodiments only and is not intended to be limiting of the one or more embodiments of the specification. As used in this specification, one or more embodiments and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used in one or more embodiments of the present specification refers to and encompasses any or all possible combinations of one or more of the associated listed items.
It should be understood that, although the terms first, second, etc. may be used in one or more embodiments of this specification to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, a first may also be referred to as a second, and similarly, a second may also be referred to as a first, without departing from the scope of one or more embodiments of the present description. The word "if" as used herein may be interpreted as "at … …" or "at … …" or "responsive to a determination", depending on the context.
First, terms related to one or more embodiments of the present specification will be explained.
Natural language processing (Natural Language Processing, NLP) is an important direction in the fields of computer science and artificial intelligence. It is studying various theories and methods that enable effective communication between a person and a computer in natural language.
In the present specification, a vendor risk identification data processing method is provided, and the present specification relates to a vendor risk identification data processing apparatus, a computing device, and a computer-readable storage medium, which are described in detail in the following embodiments one by one.
Referring to the schematic diagram shown in fig. 1, in order to enable feedback of service processing requirements to be more intuitive and enable multi-dimensional provider representations of multi-dimensional response service requirement information to be obtained, a cooperative provider set and an uncooperative provider set can be determined first, so that when new service processing requirements are met, partnerability analysis can be performed on the basis of internal cooperative providers and external uncooperative providers. On the basis, the cooperation data of each cooperation provider in the cooperation provider set can be read first, and the public data of the non-cooperation provider in the non-cooperation provider set can be collected. Then, prediction can be performed on the cooperative suppliers in the cooperative risk prediction dimension, namely, cooperative risk prediction is performed on each cooperative supplier in the cooperative risk prediction dimension according to the cooperative data, so that a cooperative supplier with better cooperative prospect is selected from a cooperative supplier set to serve as a first supplier according to a prediction result; meanwhile, prediction is performed on the non-cooperative suppliers in the risk prediction dimension to be cooperated, namely, cooperation risk prediction is performed on each non-cooperative supplier in the risk prediction dimension to be cooperated according to the public data, and the fact that the non-cooperative suppliers with good cooperation prospects are selected from a non-cooperative supplier set to serve as second suppliers according to the prediction results is achieved. In order to facilitate objective analysis of the business demand party initiating the business processing demand, a provider set can be constructed based on the first provider and the second provider, and multidimensional provider portrait display can be constructed based on attribute data of each provider in the set, so that risk analysis conditions of each provider in different dimensions can be represented through multidimensional provider portraits, and the business demand party can be assisted in subsequent decision judgment and other processing.
Fig. 2 shows a flowchart of a vendor risk identification data processing method according to an embodiment of the present disclosure, which specifically includes the following steps:
step S202, a set of affiliated suppliers and a set of non-affiliated suppliers are determined in response to the business process requirements.
The method for processing the vendor risk identification data provided by the specification can be applied to analysis scenes before any enterprise needs to establish a cooperative relationship with other enterprises, for example, an automobile manufacturer needs to introduce an automobile battery, and when the battery vendor is selected, multidimensional analysis of the battery vendor can be performed through the method for processing the vendor risk identification data provided by the embodiment, so that the automobile manufacturer is assisted in performing bidding operation and the like of the battery vendor according to analysis results.
Specifically, the business processing requirement refers to a requirement submitted by a business requirement department in an enterprise for a certain business task, and the business processing requirement is used for carrying out risk analysis on a provider associated with the business task by the provider risk identification data processing method provided by the embodiment, so as to assist the business requirement department to make a decision; such as an enterprise for an automobile manufacturer, including but not limited to battery provider selection requirements, windshield provider selection requirements, tire provider selection requirements, etc., for assisting the relevant business needs department in analyzing the risk profile of each provider from a multi-dimensional provider representation and for making an explanatory description, assisting the business needs department in making decisions.
Further, the collaboration provider set specifically refers to a set composed of collaboration providers selected from providers having a collaboration relationship with the enterprise under the current business processing requirements; accordingly, the set of uncooperative suppliers specifically refers to a set of uncooperative suppliers selected from suppliers having no cooperative relationship with the enterprise under the current business requirement.
In practical applications, considering that suppliers having a cooperative relationship with an enterprise may also provide commodity supply services corresponding to business processing demands, while uncooperative suppliers may not only provide commodity supply services corresponding to business processing demands, their supply indexes are also very high, so in order to analyze the advantages and disadvantages from each dimension, and comprehensively consider the respective advantages and disadvantages of the cooperative suppliers and uncooperative suppliers, two different sets can be determined in response to the business processing demands, so as to facilitate subsequent risk prediction analysis, and assist business demand departments in making more accurate decisions.
In an alternative embodiment of the present specification, the determining the set of affiliated suppliers and the set of non-affiliated suppliers in response to the business processing requirement includes: receiving a service processing demand submitted by a service demand party, and determining provider type information according to the service processing demand; selecting a partner provider in an initial set of providers in response to the provider type information, constituting the set of partner providers; and sorting suppliers in the set region according to the supplier type information, and selecting non-cooperative suppliers to form the non-cooperative supplier set according to the sorting result.
Specifically, the vendor type information specifically refers to description information of a commodity supply type corresponding to a vendor selected by the service processing requirement, and since different vendors cooperated with different enterprises may provide different commodity supply services, in order to meet the service processing requirement, the vendor type information needs to be determined first. Accordingly, the initial set of suppliers refers specifically to the set of all suppliers that the enterprise collaborates. Accordingly, the set region specifically refers to a region defined by the service demander for the comprehensive requirement of the selected provider, such as asian region, etc., for selecting and ordering only the providers in the region.
Based on the above, after receiving the service processing requirement submitted by the service requiring party, the provider type information can be determined according to the service processing requirement; at this time, a partner provider may be selected from the initial provider set in response to the provider type information, to constitute a partner provider set; meanwhile, suppliers in the set region can be ranked in response to the supplier type information, and non-cooperative suppliers are selected to form a non-cooperative supplier set according to the ranking result.
For example, automobile manufacturer B needs to purchase a batch of automobile batteries, and in order to be able to select a good quality automobile battery provider for cooperation, will initiate a risk prediction analysis before the cooperation of the automobile battery provider. On the basis, according to the analysis requirements of the automobile battery suppliers, the suppliers which can provide the automobile battery supply service are selected from n suppliers which cooperate with the automobile manufacturer B, and it is determined that m (m is less than or equal to n) suppliers can provide the automobile battery supply service, and the suppliers form a supplier set A. Meanwhile, in order to ensure that the automobile battery supply service meets various purchasing demands of the automobile manufacturer B, all automobile battery suppliers in Asian areas can be selected, p automobile battery suppliers are selected from all automobile battery suppliers in the areas to form a supplier set B, and the risk analysis result of each automobile battery supplier is conveniently analyzed on the basis of the two sets so as to facilitate bidding of the automobile manufacturer B.
In summary, by selecting the cooperating supplier set and the non-cooperating supplier set in combination with supplier type information, it is ensured that the analysis result more meets the analysis requirement of the business demander when the risk analysis is performed later, so as to play a role of assisting in decision-making.
Step S204, reading cooperation data corresponding to each cooperation provider in the cooperation provider set, and collecting public data of each non-cooperation provider in the non-cooperation provider set.
Specifically, the collaboration data specifically refers to data that can be read by an enterprise by each collaboration provider in the collaboration provider set, and the portion of data may include data that can be obtained by both in a collaboration state and that is mutually trusted by both, such as supply data of a certain type of commodity, operation data of the provider, and the like. Accordingly, the disclosure data specifically refers to data that each of the non-affiliated suppliers in the set of non-affiliated suppliers can be obtained by the enterprise from the disclosure channel, such as legal information, registered capital data, etc.; the collaboration data is held by the enterprise itself, and the public data can be obtained by the enterprise from other public channels, such as a platform supporting enterprise information query, and the like.
Based on this, in order to be able to analyze each affiliated provider and each non-affiliated provider from the dimension, affiliated data corresponding to each affiliated provider in the affiliated provider set may be read first, and public data of each non-affiliated provider in the non-affiliated provider set may be collected to facilitate subsequent use.
In an optional embodiment of the present disclosure, the reading of collaboration data corresponding to any one collaboration provider in the collaboration provider set includes:
(1) And responding to the business processing requirements to determine a business database, reading historical supply data of the associated supply dimension of the cooperative suppliers and historical management data of the associated management dimension in the business database, and determining the cooperative data corresponding to the cooperative suppliers according to the historical supply data and the historical management data.
Specifically, the business database refers to a database used for storing information related to suppliers in enterprises. Accordingly, the historical supply data specifically refers to supply data of the relevant commodities supplied to the enterprise by the cooperation provider in the supply dimension, wherein relevant information such as the supply quantity, the product type, the supply punctual rate and the like is recorded. Correspondingly, the historical business data specifically refers to business data corresponding to the suppliers in the business dimension, wherein profit information, loss information, business type information and the like of the suppliers are recorded.
Based on the above, in order to fully analyze each cooperation provider based on the existing data of the enterprise, the service database can be determined in response to the service processing requirement, and the historical supply data of the associated supply dimension of the cooperation provider and the historical management data of the associated management dimension are read in the service database, so that the cooperation data corresponding to the cooperation provider can be determined according to the historical supply data and the historical management data, and the risk analysis of the cooperation provider can be conveniently carried out by combining the cooperation data later.
(2) And responding to the business processing requirements, determining a business database, determining a reference dimension associated with a supply dimension and/or an operation dimension in a plurality of data dimensions contained in the business database, reading historical supply data of a cooperation provider associated with the supply dimension, historical operation data associated with the operation dimension and reference data associated with the reference dimension in the business database, and determining cooperation data corresponding to the cooperation provider according to the historical supply data, the historical operation data and the reference data.
In particular, the reference dimension particularly refers to other dimensions associated with the supply dimension and/or the business dimension, such as legal dimensions, and the like. Accordingly, the reference data specifically refers to data associated with a reference dimension, for example, the reference dimension is legal dimension, and the reference data may be legal change data of a provider, employee departure data, and the like.
Based on the above, in order to more comprehensively read the cooperation data on the basis of the requirements of the business demander for ensuring the accuracy of risk analysis, a business database can be determined in response to the business processing requirements, a reference dimension associated with a supply dimension and/or an operation dimension is determined in a plurality of data dimensions contained in the business database, historical supply data of the cooperation provider associated with the supply dimension, historical operation data of the operation dimension and reference data of the associated reference dimension are read in the business database, cooperation data corresponding to the cooperation provider is determined according to the historical supply data, the historical operation data and the reference data, and risk analysis on the cooperation provider is facilitated by combining the cooperation data subsequently.
In an optional embodiment of the present disclosure, the collecting of public data corresponding to any one of the uncooperative suppliers in the uncooperative supplier set includes:
determining judicial dimension, industrial and commercial dimension, supervision dimension, public opinion dimension and weather dimension associated with the uncooperative suppliers in response to the business processing requirements, and acquiring supplier identification information of the uncooperative suppliers; collecting judicial data in the judicial dimension according to the supplier identification information, collecting industrial and commercial data in the industrial and commercial dimension, collecting supervision data in a supervision dimension, collecting public opinion data in a public opinion dimension, and collecting weather data in a weather dimension; and determining the public data corresponding to the uncooperative provider according to the judicial data, the industrial and commercial data, the supervision data, the public opinion data and the weather data.
Specifically, the vendor identification information specifically refers to unique identification information corresponding to the uncooperative vendor; correspondingly, the judicial data specifically refers to related data of the judicial cases associated with the uncooperative suppliers; the business data specifically refers to related data of non-cooperative supplier stockholder change or enterprise name change; the supervision data specifically refers to the relevant data of the non-cooperative suppliers which are punished by the supervision department; the public opinion data specifically refers to related data of public opinion information of persons in an uncooperative provider or an enterprise; weather data specifically refers to data related to weather influences of uncooperative suppliers.
Based on the above, when the public data collection is performed on the uncooperative suppliers, in order to accurately analyze the suppliers, the judicial dimension, the industrial and commercial dimension, the supervision dimension, the public opinion dimension and the weather dimension associated with the uncooperative suppliers can be determined in response to the service processing requirements, and the supplier identification information of the uncooperative suppliers can be obtained; thereafter, judicial data can be collected in a judicial dimension according to the supplier identification information, business data can be collected in a business dimension, supervisory data can be collected in a supervisory dimension, public opinion data can be collected in a public opinion dimension, and weather data can be collected in a weather dimension; according to judicial data, industrial and commercial data, supervision data, public opinion data and weather data, public data corresponding to uncooperative suppliers are determined, more data dimensions are covered, and therefore risk analysis accuracy is guaranteed in an analysis processing stage.
In an optional embodiment of the present disclosure, before the step of reading the collaboration data corresponding to each collaboration provider in the collaboration provider set and collecting the public data of each non-collaboration provider in the non-collaboration provider set is performed, the method further includes:
receiving initial service data, and preprocessing the initial service data to obtain intermediate service data; classifying the intermediate service data by using a data classification model to obtain class labels corresponding to the intermediate service data; and selecting a target service database according to the category label, and writing the intermediate data into the target service database.
In practical application, when an enterprise creates a data analysis platform supporting multiple demand parties, the existing data needs to be integrated to support the data service level of the data analysis platform to be higher, so that the enterprise needs to support the import of structured data and unstructured data, and is convenient for the operation of each demand party. On the basis, in order to support subsequent analysis and use, null values can be automatically deleted through a big data technology, average values can be automatically filled and the like, so that the preprocessing operation of data can be completed under the condition that manual participation is not needed after the source data is loaded to a data analysis platform. After that, the preprocessed data can be classified by combining with a preset data classification model, so that the data are respectively marked with different labels, and the data can be conveniently written into different data storage spaces by combining with category labels, so that the use in an analysis stage is supported.
It should be noted that, if the data size is large, the data classification model may not cover all the dimensions of the data classification processing, but in order to avoid the influence on the data classification result, the data classification model may be trained in a self-supervision manner, so that the data classification model may automatically learn the classification capability, and ensure to cover a wider classification dimension, thereby implementing the accurate classification labeling of different data, and automatically completing the data classification and database dropping operation.
In an optional embodiment of the present disclosure, after the step of receiving the initial service data and preprocessing the initial service data to obtain the intermediate service data, the method further includes:
determining an intermediate text corresponding to the intermediate service data, and segmenting the intermediate text into a plurality of word units; updating a word stock by utilizing the word units, and constructing index information according to a word stock updating result; correspondingly, the reading the collaboration data corresponding to each collaboration provider in the collaboration provider set includes: determining a target word unit in response to the service processing requirement, and inquiring the index information based on the target word unit to obtain data address information; and reading cooperation data corresponding to each cooperation provider in the cooperation provider set in the target service database according to the data address information.
Specifically, the intermediate text specifically refers to text content generated according to intermediate service data or text content extracted from the intermediate service data; correspondingly, the word unit specifically refers to a word unit obtained after word segmentation processing is performed on the intermediate text and is used for updating a word stock, wherein the word segmentation processing can be completed through an IK word segmentation device. Correspondingly, the word library specifically refers to a word unit database for storing an intermediate text word segmentation structure corresponding to all intermediate service data, so that the mapping relation between the word segmentation and a data storage address, namely index information, is established, the word in the word library can be conveniently and firstly located according to the front-end query requirement in the query stage, and then the data storage address corresponding to the hit word can be read, so that the cooperation data of the cooperation provider can be read from the service database.
Based on the method, before the data is written into the database, the query result can be fed back for supporting quick searching of the data and any data which can be carried out on the supporting front section, the intermediate text corresponding to the intermediate service data can be determined first, and the intermediate text is segmented into a plurality of word units; and updating the word stock by utilizing a plurality of word units, and constructing index information according to the word stock updating result.
Further, in the data reading stage, a target word unit can be determined in response to the service processing requirement, and the index information is queried based on the target word unit, so that data address information is obtained; and finally, the cooperation data corresponding to each cooperation provider in the cooperation provider set can be read from the target service database according to the data address information, so that the subsequent use is convenient.
And S206, carrying out cooperation risk prediction on each cooperation provider in a cooperation risk prediction dimension according to the cooperation data, and screening a first provider in the cooperation provider set according to a prediction result.
Specifically, the collaborative risk prediction dimension specifically refers to a dimension covered by the comprehensive collaborative data for performing risk prediction on each collaborative provider, and correspondingly, the first provider specifically refers to a provider with lower risk screened from the collaborative provider set according to a risk prediction result of each collaborative provider.
Based on the method, in order to facilitate the business demand side to select a proper supplier as an alternative according to the self demand, collaborative risk prediction can be performed on each collaborative supplier in a collaborative risk prediction dimension according to collaborative data, so that risk prediction is completed in a plurality of dimensions related to the data, and therefore a first supplier is screened from a collaborative supplier set according to a prediction result, and further analysis of a multi-dimensional supplier portrait can be conveniently constructed later.
In practical application, when the first provider is selected, a collaborative filtering algorithm may be used to implement provider recommendation, so that the first provider is selected according to the recommendation result, for example, collaborative filtering based on a model may be modeled by using a machine learning idea, and the existing partial sparse data is used to predict the scoring relation between blank providers and data, so as to find the provider with higher score to push as the first provider.
In an optional embodiment of the present disclosure, the performing, according to the collaboration data, collaboration risk prediction on each collaboration provider in a collaboration risk prediction dimension, and screening, according to a prediction result, a first provider from the collaboration provider set includes:
respectively inputting the cooperation data corresponding to each cooperation provider into a risk prediction model for processing, and determining a risk prediction value of a cooperation risk prediction dimension corresponding to each cooperation provider according to a processing result; and sequencing the risk prediction scores corresponding to each cooperative supplier, and selecting a first set number of cooperative suppliers as the first suppliers according to the sequencing result.
Specifically, the risk prediction model is a model capable of scoring the synthetic suppliers based on the cooperation data, and the risk prediction model can be trained by adopting a large number of positive and negative samples in a training stage to obtain a risk prediction model with higher fitting and higher prediction precision, so that accurate scoring in the cooperation risk prediction dimension is realized. Accordingly, the risk prediction score specifically refers to a score representing the risk of the cooperation provider, and the higher the risk prediction score is, the higher the risk is. Correspondingly, the first set number specifically refers to a value set according to actual requirements, such as 5, 10, etc.
Based on the above, when the first suppliers are screened, the cooperation data corresponding to each cooperation supplier can be respectively input into a risk prediction model for processing, and the risk prediction value of the cooperation risk prediction dimension corresponding to each cooperation supplier is determined according to the processing result; and then, sorting the risk prediction scores corresponding to the cooperative suppliers, so as to select a first set number of cooperative suppliers as the first supplier according to the sorting result.
In an optional embodiment of the present disclosure, determining the risk prediction score of any one of the collaboration providers in the collaboration provider set includes:
determining at least two sub-cooperation risk prediction dimensions contained in the cooperation risk prediction dimensions, and determining sub-risk prediction scores corresponding to each sub-cooperation risk prediction dimension according to processing results; determining a sub-score weight corresponding to each sub-collaboration risk prediction dimension in response to the business processing requirements; and carrying out weighted summation calculation on the sub-risk prediction scores and sub-score weights corresponding to each sub-cooperation risk prediction dimension, and determining the risk prediction scores corresponding to the cooperation suppliers according to the calculation results.
In particular, the sub-collaborative risk prediction dimension refers to a prediction dimension of a data dimension related to the associated collaborative data, for example, the collaborative data is determined by the historical business data and the historical supply data, and the sub-collaborative risk prediction dimension may be a business risk prediction dimension and a supply risk prediction dimension. Correspondingly, the sub-risk prediction score specifically refers to a prediction score corresponding to each dimension, and the sub-score weight is a weight corresponding to each dimension, and is set by the service demand party according to the actual service demand.
Based on the above, in order to determine the risk prediction score in combination with the requirements sent by the business requirements, at least two sub-cooperation risk prediction dimensions included in the cooperation risk prediction dimensions can be determined, and the sub-risk prediction score corresponding to each sub-cooperation risk prediction dimension is determined according to the processing result; at this time, weights can be introduced, namely, sub-score weights corresponding to each sub-cooperation risk prediction dimension are determined in response to service processing requirements; and carrying out weighted summation calculation on the sub-risk prediction scores and sub-score weights corresponding to each sub-cooperation risk prediction dimension, and determining the risk prediction scores corresponding to the cooperation suppliers according to the calculation results.
Along the above example, after the m car battery suppliers with the cooperative relationship are confirmed, in order to facilitate risk analysis by the business demand party, the operation data (liability information, profit information, etc.) and the supply data (supply timing rate, supply quantity, etc.) corresponding to each car electric car supplier in the m car battery suppliers can be collected, then the score corresponding to each car battery supplier in the supply dimension and the operation dimension is obtained by inputting the operation data and the supply data into a preset risk prediction model for scoring, and at this time, different weights are set for each dimension in combination with the focus focused by the business demand party; and then a weighted summation mode can be adopted to obtain the corresponding total risk prediction value of each automobile battery provider. And then, sorting the m total risk prediction values, and selecting Top10 as a provider to be selected, so as to facilitate the construction of multi-dimensional provider figures for the 10 providers respectively, and facilitate risk analysis of business demanders.
In summary, by determining the risk prediction score by adopting a weighted summation mode, the risk prediction score can be ensured to be influenced by the appeal of the service demander, so that the analysis result is ensured to be more accurate.
And step S208, carrying out cooperative risk prediction on each non-cooperative supplier in the dimension to be cooperative risk prediction according to the public data, and screening a second supplier from the non-cooperative supplier set according to the prediction result.
Specifically, the dimension to be cooperated risk prediction specifically refers to a dimension covered by comprehensive disclosure data for risk prediction of each non-cooperated provider, and correspondingly, the second provider refers to a provider with lower risk screened from the non-cooperated provider set according to a risk prediction result of each non-cooperated provider.
Based on the method, in order to facilitate the business demand side to select a proper supplier as an alternative according to the self demand, collaborative risk prediction can be performed on each uncooperative supplier in a dimension to be collaborative risk prediction according to the public data, so that risk prediction can be completed in a plurality of dimensions related to the data, and a second supplier is screened from a set of uncooperative suppliers according to a prediction result, so that further analysis of a multi-dimensional supplier portrait constructed later is facilitated.
In an optional embodiment of the present disclosure, the performing, according to the disclosure data, collaborative risk prediction on each uncooperative provider in a dimension to be collaborative risk prediction, and screening, according to a prediction result, a second provider in the uncooperative provider set includes:
determining at least two sub-risk prediction dimensions contained in the risk prediction dimensions to be cooperated, and inputting the public data corresponding to each non-cooperated supplier into a sub-risk prediction model corresponding to each sub-risk prediction dimension to be cooperated for processing respectively; determining risk prediction scores of the at least two sub-risk prediction dimensions corresponding to each uncooperative provider according to the processing results; and sorting the risk prediction scores corresponding to each uncooperative provider, and selecting a second set number of uncooperative providers as the second providers according to the sorting result.
It should be noted that, in this embodiment, the description of screening the second provider based on the disclosure data is similar to the description of screening the first provider, and the same or corresponding description may be referred to the same or corresponding description in the above embodiment, which is not repeated here.
Based on the above, when screening the second suppliers, at least two sub-risk prediction dimensions to be cooperated, which are included in the risk prediction dimensions to be cooperated, can be determined, and the public data corresponding to each non-cooperated supplier is input into the sub-risk prediction model corresponding to each sub-risk prediction dimension to be cooperated for processing respectively; determining risk prediction scores of at least two sub-risk prediction dimensions to be cooperated corresponding to each non-cooperated provider according to the processing result; and sorting the risk prediction scores corresponding to the non-cooperative suppliers, namely selecting a second set number of non-cooperative suppliers as the second suppliers according to the sorting result.
Along the above example, after determining p car battery suppliers which have no cooperative relationship and have better public praise, in order to facilitate risk analysis by a business demand party, judicial data (related to judicial cases, trade contract disputes and the like), business data (enterprise legal change information, enterprise name change information and the like), supervision data (supervision department reward and punishment information and the like), public opinion data (enterprise or related personnel public opinion information) and weather data (regional weather environment information and the like) corresponding to each car electric car supplier in the p car battery suppliers can be adopted, and then the judicial data, the business data, the supervision data, the public opinion data and the weather data are input into a preset risk prediction model to be scored, so that scores respectively corresponding to each car battery supplier in judicial dimensions, business dimensions, supervision dimensions, public opinion dimensions and weather dimensions are obtained, and at the moment, different weights are set for each dimension in combination with the focused key points of the business demand party; and then a weighted summation mode can be adopted to obtain the corresponding total risk prediction value of each automobile battery provider. And then, sorting the p risk prediction scores, and selecting Top10 as a provider to be selected, so as to facilitate the construction of multi-dimensional provider figures for the 10 providers respectively, and facilitate risk analysis of business demanders.
Step S210, a provider set is built based on the first provider and the second provider, and a multi-dimensional provider portrait is created and displayed according to attribute data of each provider in the provider set.
Specifically, the vendor set refers to a set formed by the first vendor and the second vendor, and the corresponding multidimensional vendor representation specifically refers to a representation for displaying risk analysis results of each vendor from multiple dimensions, such as displaying information of the number of products supplied by the vendor, information of other vendors having a cooperative relationship with the vendor, information of excessive risk of products supplied, and the like, which is not limited in this embodiment.
In an optional embodiment of the disclosure, the creating and displaying a multidimensional vendor representation according to the attribute data of each vendor in the vendor set includes:
acquiring attribute data of each provider in the provider set, and a multidimensional provider portrait template comprising a risk overview area, a public opinion overview area, a risk analysis area and a basic analysis area; updating a multi-dimensional provider representation template comprising the risk overview area, the public opinion overview area, the risk analysis area, and the base analysis area based on attribute data of each provider; and generating and displaying the multi-dimensional provider portrait according to the updating result, wherein the multi-dimensional provider portrait is used for displaying service information of a target provider, and the target provider is selected from the provider set according to a point selection instruction.
Specifically, the risk overview area is specifically an area for displaying information of risk prediction results obtained by a provider after prediction in different risk dimensions. The public opinion overview area specifically refers to an area for displaying information of public opinion prediction results obtained by suppliers after prediction in different public opinion dimensions. The risk analysis area specifically refers to an area in which interpretation information generated after risk analysis is performed in different dimensions for a provider is displayed. The basic analysis area specifically refers to an area for displaying analysis information generated by analyzing basic information of suppliers in different dimensions. Correspondingly, the multi-dimensional vendor portrait template specifically refers to a template for displaying vendor data, in which tables, bar charts, graphs, ring charts and the like can be set in the template for recording data in different dimensions, and the setting of the template can be set according to actual requirements, and the embodiment is not limited in any way.
Based on the above, after the provider set is formed, attribute data of each provider in the provider set and a multi-dimensional provider portrait template comprising a risk overview area, a public opinion overview area, a risk analysis area and a basic analysis area can be obtained; at this time, a multi-dimensional provider portrait template including a risk overview area, a public opinion overview area, a risk analysis area, and a basic analysis area may be updated based on attribute data of each provider; updating data into a template is achieved, and therefore a multi-dimensional provider portrait is generated and displayed according to an updating result, wherein the multi-dimensional provider portrait is used for displaying service information of a target provider, and the target provider is selected according to a selection instruction in a provider set, namely, a service demander can click different providers, and therefore the multi-dimensional provider portrait with the same structure and different data content of the different providers is seen.
Along the above example, after 20 car battery suppliers are screened, attribute data of each car battery supplier can be extracted, and a supplier portrait template is rendered by the attribute data, so that a supplier portrait as shown in fig. 3 can be obtained, wherein 9 areas are included, and each area is used for displaying different information. If the areas 1, 2 and 3 are used for displaying public opinion news, negative news and active news quantity of related suppliers, the area 4 is used for displaying the number of suppliers of public opinion, the areas 5 and 7 are used for constructing risk category distribution and company distribution through bar charts, the area 6 is used for analyzing public opinion keywords to form keyword word clouds, the area 8 is used for displaying the sequence trend of the number of public opinion according to date and time, the area 9 is used for displaying detailed description of risk events and supporting clicking information and then jumping to a specific information display page.
In order to respond to service processing requirements, feedback is more visual, and multidimensional provider figures of service requirement information can be reflected from multidimensional, a cooperative provider set and an uncooperative provider set can be determined first, and partnerability analysis can be performed on the basis of internal cooperative suppliers and external uncooperative suppliers when new service processing requirements are met. On the basis, the cooperation data of each cooperation provider in the cooperation provider set can be read first, and the public data of the non-cooperation provider in the non-cooperation provider set can be collected. Then, prediction can be performed on the cooperative suppliers in the cooperative risk prediction dimension, namely, cooperative risk prediction is performed on each cooperative supplier in the cooperative risk prediction dimension according to the cooperative data, so that a cooperative supplier with better cooperative prospect is selected from a cooperative supplier set to serve as a first supplier according to a prediction result; meanwhile, prediction is performed on the non-cooperative suppliers in the risk prediction dimension to be cooperated, namely, cooperation risk prediction is performed on each non-cooperative supplier in the risk prediction dimension to be cooperated according to the public data, and the fact that the non-cooperative suppliers with good cooperation prospects are selected from a non-cooperative supplier set to serve as second suppliers according to the prediction results is achieved. In order to facilitate objective analysis of the business demand party initiating the business processing demand, a provider set can be constructed based on the first provider and the second provider, and multidimensional provider portrait display can be constructed based on attribute data of each provider in the set, so that risk analysis conditions of each provider in different dimensions can be represented through multidimensional provider portraits, and the business demand party can be assisted in subsequent decision judgment and other processing.
Corresponding to the above method embodiments, the present disclosure further provides an embodiment of a vendor risk identification data processing device, and fig. 4 is a schematic structural diagram of a vendor risk identification data processing device according to an embodiment of the present disclosure. As shown in fig. 4, the apparatus includes:
a determining module 402 configured to determine a set of affiliated suppliers and a set of non-affiliated suppliers in response to the business processing requirements;
a reading module 404 configured to read collaboration data corresponding to each collaboration provider in the collaboration provider set, and collect public data of each non-collaboration provider in the non-collaboration provider set;
a first screening module 406 configured to perform collaborative risk prediction in a collaborative risk prediction dimension for each collaborative provider according to the collaborative data, and screen a first provider from the set of collaborative providers according to a prediction result;
a second screening module 408 configured to perform collaborative risk prediction in a dimension to be collaborative risk prediction for each uncooperative provider according to the disclosure data, and screen a second provider from the set of uncooperative providers according to a prediction result;
a creation module 410 configured to construct a set of suppliers based on the first and second suppliers, create and present a multi-dimensional supplier representation from attribute data of each supplier in the set of suppliers.
In an alternative embodiment, the determining module 402 is further configured to:
receiving a service processing demand submitted by a service demand party, and determining provider type information according to the service processing demand; selecting a partner provider in an initial set of providers in response to the provider type information, constituting the set of partner providers; and sorting suppliers in the set region according to the supplier type information, and selecting non-cooperative suppliers to form the non-cooperative supplier set according to the sorting result.
In an optional embodiment, the reading of the collaboration data corresponding to any one collaboration provider in the collaboration provider set includes:
a business database is determined in response to the business processing requirements, historical supply data of a cooperative supplier associated supply dimension and historical management data of an associated management dimension are read in the business database, and cooperation data corresponding to the cooperative supplier are determined according to the historical supply data and the historical management data; or, determining a business database in response to the business processing requirement, determining a reference dimension associated with a supply dimension and/or an operation dimension in a plurality of data dimensions contained in the business database, reading historical supply data of a cooperation provider associated with the supply dimension, historical operation data of the operation dimension and reference data of the reference dimension in the business database, and determining cooperation data corresponding to the cooperation provider according to the historical supply data, the historical operation data and the reference data.
In an optional embodiment, the collecting of public data corresponding to any one of the uncooperative suppliers in the uncooperative supplier set includes:
determining judicial dimension, industrial and commercial dimension, supervision dimension, public opinion dimension and weather dimension associated with the uncooperative suppliers in response to the business processing requirements, and acquiring supplier identification information of the uncooperative suppliers; collecting judicial data in the judicial dimension according to the supplier identification information, collecting industrial and commercial data in the industrial and commercial dimension, collecting supervision data in a supervision dimension, collecting public opinion data in a public opinion dimension, and collecting weather data in a weather dimension; and determining the public data corresponding to the uncooperative provider according to the judicial data, the industrial and commercial data, the supervision data, the public opinion data and the weather data.
In an alternative embodiment, the first filtering module 406 is further configured to:
respectively inputting the cooperation data corresponding to each cooperation provider into a risk prediction model for processing, and determining a risk prediction value of a cooperation risk prediction dimension corresponding to each cooperation provider according to a processing result; and sequencing the risk prediction scores corresponding to each cooperative supplier, and selecting a first set number of cooperative suppliers as the first suppliers according to the sequencing result.
In an alternative embodiment, the determining of the risk prediction score of any one of the cooperating suppliers in the set of cooperating suppliers includes:
determining at least two sub-cooperation risk prediction dimensions contained in the cooperation risk prediction dimensions, and determining sub-risk prediction scores corresponding to each sub-cooperation risk prediction dimension according to processing results; determining a sub-score weight corresponding to each sub-collaboration risk prediction dimension in response to the business processing requirements; and carrying out weighted summation calculation on the sub-risk prediction scores and sub-score weights corresponding to each sub-cooperation risk prediction dimension, and determining the risk prediction scores corresponding to the cooperation suppliers according to the calculation results.
In an alternative embodiment, the second screening module 408 is further configured to:
determining at least two sub-risk prediction dimensions contained in the risk prediction dimensions to be cooperated, and inputting the public data corresponding to each non-cooperated supplier into a sub-risk prediction model corresponding to each sub-risk prediction dimension to be cooperated for processing respectively; determining risk prediction scores of the at least two sub-risk prediction dimensions corresponding to each uncooperative provider according to the processing results; and sorting the risk prediction scores corresponding to each uncooperative provider, and selecting a second set number of uncooperative providers as the second providers according to the sorting result.
In an alternative embodiment, the creation module 410 is further configured to:
acquiring attribute data of each provider in the provider set, and a multidimensional provider portrait template comprising a risk overview area, a public opinion overview area, a risk analysis area and a basic analysis area; updating a multi-dimensional provider representation template comprising the risk overview area, the public opinion overview area, the risk analysis area, and the base analysis area based on attribute data of each provider; and generating and displaying the multi-dimensional provider portrait according to the updating result, wherein the multi-dimensional provider portrait is used for displaying service information of a target provider, and the target provider is selected from the provider set according to a point selection instruction.
In an alternative embodiment, the apparatus further comprises:
the data preprocessing module is configured to receive initial service data and preprocess the initial service data to obtain intermediate service data; classifying the intermediate service data by using a data classification model to obtain class labels corresponding to the intermediate service data; and selecting a target service database according to the category label, and writing the intermediate data into the target service database.
In an alternative embodiment, the apparatus further comprises:
the word segmentation module is configured to determine an intermediate text corresponding to the intermediate service data and segment the intermediate text into a plurality of word units; updating a word stock by utilizing the word units, and constructing index information according to a word stock updating result;
accordingly, the read module 404 is further configured to:
determining a target word unit in response to the service processing requirement, and inquiring the index information based on the target word unit to obtain data address information; and reading cooperation data corresponding to each cooperation provider in the cooperation provider set in the target service database according to the data address information.
In order to respond to service processing requirements, feedback is more intuitive, and multidimensional provider figures of service requirement information can be reflected from multidimensional, a cooperative provider set and an uncooperative provider set can be determined first, and partnerability analysis can be performed on the basis of internal cooperative providers and external uncooperative providers when new service processing requirements are met. On the basis, the cooperation data of each cooperation provider in the cooperation provider set can be read first, and the public data of the non-cooperation provider in the non-cooperation provider set can be collected. Then, prediction can be performed on the cooperative suppliers in the cooperative risk prediction dimension, namely, cooperative risk prediction is performed on each cooperative supplier in the cooperative risk prediction dimension according to the cooperative data, so that a cooperative supplier with better cooperative prospect is selected from a cooperative supplier set to serve as a first supplier according to a prediction result; meanwhile, prediction is performed on the non-cooperative suppliers in the risk prediction dimension to be cooperated, namely, cooperation risk prediction is performed on each non-cooperative supplier in the risk prediction dimension to be cooperated according to the public data, and the fact that the non-cooperative suppliers with good cooperation prospects are selected from a non-cooperative supplier set to serve as second suppliers according to the prediction results is achieved. In order to facilitate objective analysis of the business demand party initiating the business processing demand, a provider set can be constructed based on the first provider and the second provider, and multidimensional provider portrait display can be constructed based on attribute data of each provider in the set, so that risk analysis conditions of each provider in different dimensions can be represented through multidimensional provider portraits, and the business demand party can be assisted in subsequent decision judgment and other processing.
The above is a schematic solution of a vendor risk identification data processing apparatus of the present embodiment. It should be noted that, the technical solution of the vendor risk identification data processing device and the technical solution of the vendor risk identification data processing method belong to the same concept, and details of the technical solution of the vendor risk identification data processing device, which are not described in detail, can be referred to the description of the technical solution of the vendor risk identification data processing method.
Fig. 5 illustrates a block diagram of a computing device 500 provided in accordance with an embodiment of the present specification. The components of the computing device 500 include, but are not limited to, a memory 510 and a processor 520. Processor 520 is coupled to memory 510 via bus 530 and database 550 is used to hold data.
Computing device 500 also includes access device 540, access device 540 enabling computing device 500 to communicate via one or more networks 560. Examples of such networks include public switched telephone networks (PSTN, public Switched Telephone Network), local area networks (LAN, local Area Network), wide area networks (WAN, wide Area Network), personal area networks (PAN, personal Area Network), or combinations of communication networks such as the internet. The access device 540 may include one or more of any type of network interface, wired or wireless (e.g., network interface card (NIC, network interface controller)), such as an IEEE802.11 wireless local area network (WLAN, wireless Local Area Network) wireless interface, a worldwide interoperability for microwave access (Wi-MAX, worldwide Interoperability for Microwave Access) interface, an ethernet interface, a universal serial bus (USB, universal Serial Bus) interface, a cellular network interface, a bluetooth interface, a near field communication (NFC, near Field Communication) interface, and so forth.
In one embodiment of the application, the above-described components of computing device 500, as well as other components not shown in FIG. 5, may also be connected to each other, such as by a bus. It should be understood that the block diagram of the computing device illustrated in FIG. 5 is for exemplary purposes only and is not intended to limit the scope of the present application. Those skilled in the art may add or replace other components as desired.
Computing device 500 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., tablet, personal digital assistant, laptop, notebook, netbook, etc.), mobile phone (e.g., smart phone), wearable computing device (e.g., smart watch, smart glasses, etc.), or other type of mobile device, or a stationary computing device such as a desktop computer or personal computer (PC, personal Computer). Computing device 800 may also be a mobile or stationary server.
Wherein the processor 520 is configured to implement the steps of the vendor risk identification data processing method when executing computer executable instructions.
The foregoing is a schematic illustration of a computing device of this embodiment. It should be noted that, the technical solution of the computing device and the technical solution of the foregoing vendor risk identification data processing method belong to the same concept, and details of the technical solution of the computing device, which are not described in detail, can be referred to the description of the technical solution of the foregoing vendor risk identification data processing method.
An embodiment of the present specification also provides a computer-readable storage medium storing computer instructions that, when executed by a processor, are for use in a vendor risk identification data processing method.
The above is an exemplary version of a computer-readable storage medium of the present embodiment. It should be noted that, the technical solution of the storage medium and the technical solution of the foregoing vendor risk identification data processing method belong to the same concept, and details of the technical solution of the storage medium, which are not described in detail, can be referred to the description of the technical solution of the foregoing vendor risk identification data processing method.
The foregoing describes specific embodiments of the present disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The computer instructions include computer program code that may be in source code form, object code form, executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth. It should be noted that the content of the computer readable medium can be increased or decreased appropriately according to the requirements of the patent practice, for example, in some areas, according to the patent practice, the computer readable medium does not include an electric carrier signal and a telecommunication signal.
It should be noted that, for the sake of simplicity of description, the foregoing method embodiments are all expressed as a series of combinations of actions, but it should be understood by those skilled in the art that the present description is not limited by the order of actions described, as some steps may be performed in other order or simultaneously in accordance with the present description. Further, those skilled in the art will appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily all necessary in the specification.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to the related descriptions of other embodiments.
The preferred embodiments of the present specification disclosed above are merely used to help clarify the present specification. Alternative embodiments are not intended to be exhaustive or to limit the invention to the precise form disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the disclosure and the practical application, to thereby enable others skilled in the art to best understand and utilize the disclosure. This specification is to be limited only by the claims and the full scope and equivalents thereof.
Claims (13)
1. A vendor risk identification data processing method, comprising:
determining a set of affiliated suppliers and a set of non-affiliated suppliers in response to the business processing requirements;
reading cooperation data corresponding to each cooperation provider in the cooperation provider set, and collecting public data of each non-cooperation provider in the non-cooperation provider set;
carrying out cooperative risk prediction on each cooperative supplier in a cooperative risk prediction dimension according to the cooperative data, and screening a first supplier from the cooperative supplier set according to a prediction result;
Carrying out cooperative risk prediction on each uncooperative provider in a dimension to be cooperative risk prediction according to the public data, and screening a second provider in the uncooperative provider set according to a prediction result;
and constructing a supplier set based on the first supplier and the second supplier, and creating and displaying a multi-dimensional supplier portrait according to the attribute data of each supplier in the supplier set.
2. The method of claim 1, wherein the determining the set of affiliated suppliers and the set of non-affiliated suppliers in response to the business process requirements comprises:
receiving a service processing demand submitted by a service demand party, and determining provider type information according to the service processing demand;
selecting a partner provider in an initial set of providers in response to the provider type information, constituting the set of partner providers;
and sorting suppliers in the set region according to the supplier type information, and selecting non-cooperative suppliers to form the non-cooperative supplier set according to the sorting result.
3. The method of claim 1, wherein the reading of collaboration data corresponding to any one of the collaboration providers in the collaboration provider set comprises:
A business database is determined in response to the business processing requirements, historical supply data of a cooperative supplier associated supply dimension and historical management data of an associated management dimension are read in the business database, and cooperation data corresponding to the cooperative supplier are determined according to the historical supply data and the historical management data;
or,
and responding to the business processing requirements, determining a business database, determining a reference dimension associated with a supply dimension and/or an operation dimension in a plurality of data dimensions contained in the business database, reading historical supply data of a cooperation provider associated with the supply dimension, historical operation data associated with the operation dimension and reference data associated with the reference dimension in the business database, and determining cooperation data corresponding to the cooperation provider according to the historical supply data, the historical operation data and the reference data.
4. The method of claim 1, wherein the collection of public data corresponding to any one of the set of uncooperative suppliers comprises:
determining judicial dimension, industrial and commercial dimension, supervision dimension, public opinion dimension and weather dimension associated with the uncooperative suppliers in response to the business processing requirements, and acquiring supplier identification information of the uncooperative suppliers;
Collecting judicial data in the judicial dimension according to the supplier identification information, collecting industrial and commercial data in the industrial and commercial dimension, collecting supervision data in a supervision dimension, collecting public opinion data in a public opinion dimension, and collecting weather data in a weather dimension;
and determining the public data corresponding to the uncooperative provider according to the judicial data, the industrial and commercial data, the supervision data, the public opinion data and the weather data.
5. The method of claim 1, wherein said performing a collaborative risk prediction in a collaborative risk prediction dimension for each collaborative provider based on the collaborative data, screening a first provider in the set of collaborative providers based on a prediction result, comprises:
respectively inputting the cooperation data corresponding to each cooperation provider into a risk prediction model for processing, and determining a risk prediction value of a cooperation risk prediction dimension corresponding to each cooperation provider according to a processing result;
and sequencing the risk prediction scores corresponding to each cooperative supplier, and selecting a first set number of cooperative suppliers as the first suppliers according to the sequencing result.
6. The method of claim 5, wherein determining the risk prediction score for any one of the set of cooperating suppliers comprises:
Determining at least two sub-cooperation risk prediction dimensions contained in the cooperation risk prediction dimensions, and determining sub-risk prediction scores corresponding to each sub-cooperation risk prediction dimension according to processing results;
determining a sub-score weight corresponding to each sub-collaboration risk prediction dimension in response to the business processing requirements;
and carrying out weighted summation calculation on the sub-risk prediction scores and sub-score weights corresponding to each sub-cooperation risk prediction dimension, and determining the risk prediction scores corresponding to the cooperation suppliers according to the calculation results.
7. The method of claim 1, wherein said collaborative risk prediction in a dimension to be collaborative risk prediction for each uncooperative provider based on the published data, screening a second provider in the set of uncooperative providers based on prediction results, comprises:
determining at least two sub-risk prediction dimensions contained in the risk prediction dimensions to be cooperated, and inputting the public data corresponding to each non-cooperated supplier into a sub-risk prediction model corresponding to each sub-risk prediction dimension to be cooperated for processing respectively;
determining risk prediction scores of the at least two sub-risk prediction dimensions corresponding to each uncooperative provider according to the processing results;
And sorting the risk prediction scores corresponding to each uncooperative provider, and selecting a second set number of uncooperative providers as the second providers according to the sorting result.
8. The method of claim 1, wherein creating and exposing a multi-dimensional vendor representation from the attribute data of each vendor in the set of vendors comprises:
acquiring attribute data of each provider in the provider set, and a multidimensional provider portrait template comprising a risk overview area, a public opinion overview area, a risk analysis area and a basic analysis area;
updating a multi-dimensional provider representation template comprising the risk overview area, the public opinion overview area, the risk analysis area, and the base analysis area based on attribute data of each provider;
and generating and displaying the multi-dimensional provider portrait according to the updating result, wherein the multi-dimensional provider portrait is used for displaying service information of a target provider, and the target provider is selected from the provider set according to a point selection instruction.
9. The method of claim 1, wherein the step of reading collaboration data corresponding to each collaboration provider in the set of collaboration providers and collecting public data for each non-collaboration provider in the set of non-collaboration providers is performed further comprises:
Receiving initial service data, and preprocessing the initial service data to obtain intermediate service data;
classifying the intermediate service data by using a data classification model to obtain class labels corresponding to the intermediate service data;
and selecting a target service database according to the category label, and writing the intermediate data into the target service database.
10. The method of claim 9, wherein said receiving initial traffic data and preprocessing said initial traffic data, after said obtaining intermediate traffic data step is performed, further comprises:
determining an intermediate text corresponding to the intermediate service data, and segmenting the intermediate text into a plurality of word units;
updating a word stock by utilizing the word units, and constructing index information according to a word stock updating result;
correspondingly, the reading the collaboration data corresponding to each collaboration provider in the collaboration provider set includes:
determining a target word unit in response to the service processing requirement, and inquiring the index information based on the target word unit to obtain data address information;
and reading cooperation data corresponding to each cooperation provider in the cooperation provider set in the target service database according to the data address information.
11. A vendor risk identification data processing device, comprising:
a determining module configured to determine a set of affiliated suppliers and a set of non-affiliated suppliers in response to the business process requirements;
the reading module is configured to read cooperation data corresponding to each cooperation provider in the cooperation provider set and collect public data of each non-cooperation provider in the non-cooperation provider set;
the first screening module is configured to conduct cooperation risk prediction on each cooperation provider in a cooperation risk prediction dimension according to the cooperation data, and screen a first provider in the cooperation provider set according to a prediction result;
a second screening module configured to perform cooperative risk prediction on each uncooperative provider in a dimension to be cooperative risk prediction according to the disclosure data, and screen a second provider from the set of uncooperative providers according to a prediction result;
and the creation module is configured to construct a supplier set based on the first supplier and the second supplier, and create and display a multi-dimensional supplier portrait according to the attribute data of each supplier in the supplier set.
12. A computing device comprising a memory and a processor; the memory is configured to store computer executable instructions and the processor is configured to execute the computer executable instructions to implement the steps of the method of any one of claims 1 to 10.
13. A computer readable storage medium storing computer instructions which, when executed by a processor, implement the steps of the method of any one of claims 1 to 10.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310756778.4A CN116663909A (en) | 2023-06-26 | 2023-06-26 | Provider risk identification data processing method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310756778.4A CN116663909A (en) | 2023-06-26 | 2023-06-26 | Provider risk identification data processing method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116663909A true CN116663909A (en) | 2023-08-29 |
Family
ID=87727984
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310756778.4A Pending CN116663909A (en) | 2023-06-26 | 2023-06-26 | Provider risk identification data processing method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116663909A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117557073A (en) * | 2024-01-11 | 2024-02-13 | 云南建投物流有限公司 | Full life cycle provider service management method and system |
CN118246773A (en) * | 2024-05-29 | 2024-06-25 | 南京基石数据技术有限责任公司 | Method for processing data of station link in data |
-
2023
- 2023-06-26 CN CN202310756778.4A patent/CN116663909A/en active Pending
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117557073A (en) * | 2024-01-11 | 2024-02-13 | 云南建投物流有限公司 | Full life cycle provider service management method and system |
CN117557073B (en) * | 2024-01-11 | 2024-04-02 | 云南建投物流有限公司 | Full life cycle provider service management method and system |
CN118246773A (en) * | 2024-05-29 | 2024-06-25 | 南京基石数据技术有限责任公司 | Method for processing data of station link in data |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Saura et al. | Setting B2B digital marketing in artificial intelligence-based CRMs: A review and directions for future research | |
Shao et al. | IoT data visualization for business intelligence in corporate finance | |
CN108229590B (en) | Method and device for acquiring multi-label user portrait | |
CN110070391B (en) | Data processing method and device, computer readable medium and electronic equipment | |
Cheung et al. | A multi-perspective knowledge-based system for customer service management | |
CN116663909A (en) | Provider risk identification data processing method and device | |
CN111047412A (en) | Big data electricity merchant operation platform | |
CN112256762A (en) | Enterprise portrait method, system, equipment and medium based on industrial map | |
CN114862506B (en) | Financial product recommendation method based on deep reinforcement learning | |
CN115809376A (en) | Intelligent recommendation method based on big teaching data | |
US11551187B2 (en) | Machine-learning creation of job posting content | |
CN115829683A (en) | Power integration commodity recommendation method and system based on inverse reward learning optimization | |
KR102523050B1 (en) | Method for providing subscription economy based rental price comparison service | |
CN112464106B (en) | Object recommendation method and device | |
CN117746546A (en) | Service business handling method and system based on number calling device | |
CN112767114A (en) | Enterprise diversified decision method and device, electronic equipment and storage medium | |
KR101853555B1 (en) | SW Market Information Service System | |
CN115982391A (en) | Information processing method and device | |
CN112860878A (en) | Service data recommendation method, storage medium and equipment | |
US11270253B2 (en) | Cognitive procurement | |
Upreti et al. | Artificial intelligence and its effect on employment and skilling | |
US20030046204A1 (en) | Method and system for assessing and improving individual customer profitability for a profit-making organization | |
Mekhanikov | Artificial intelligence in marketing theory and marketing practice: practical recommendations for companies on the best way to implement or develop AI | |
Park et al. | Analysis of Brand Effects in Data-Driven Design Based on Online Reviews | |
Gončarovs et al. | Using data analytics for continuous improvement of CRM processes: case of financial institution |
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 |