CN113345080A - Supplier portrait modeling method and system - Google Patents
Supplier portrait modeling method and system Download PDFInfo
- Publication number
- CN113345080A CN113345080A CN202110688987.0A CN202110688987A CN113345080A CN 113345080 A CN113345080 A CN 113345080A CN 202110688987 A CN202110688987 A CN 202110688987A CN 113345080 A CN113345080 A CN 113345080A
- Authority
- CN
- China
- Prior art keywords
- data
- supplier
- unit
- user
- modeling
- 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
- 238000000034 method Methods 0.000 title claims description 22
- 238000011156 evaluation Methods 0.000 claims abstract description 12
- 238000007781 pre-processing Methods 0.000 claims abstract description 12
- 238000011835 investigation Methods 0.000 claims abstract description 10
- 238000004458 analytical method Methods 0.000 claims abstract description 8
- 238000003384 imaging method Methods 0.000 claims abstract description 8
- 230000006399 behavior Effects 0.000 claims abstract description 5
- 238000012545 processing Methods 0.000 claims description 17
- 238000010606 normalization Methods 0.000 claims description 12
- 238000003064 k means clustering Methods 0.000 claims description 9
- 238000012797 qualification Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 230000010354 integration Effects 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 4
- 230000009471 action Effects 0.000 claims description 3
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 210000001520 comb Anatomy 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000003032 molecular docking Methods 0.000 claims description 2
- 238000005192 partition Methods 0.000 claims description 2
- 230000007812 deficiency Effects 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 5
- 230000000694 effects Effects 0.000 description 12
- 238000007405 data analysis Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000002759 z-score normalization Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/211—Schema design and management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Human Resources & Organizations (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Educational Administration (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention comprises a user information collection unit, a service scene determination unit, a basic data acquisition unit, a data preprocessing unit, a modeling unit and an imaging display unit, wherein the user information collection unit acquires effective evaluation data of a supplier based on user transaction history and habits, user historical browsing records and user collection records, the invention utilizes big data and K-means algorithm related technology to carry out comprehensive portrait modeling on the supplier through analysis on historical purchasing data, intuitively and accurately reflects quotation behaviors, bidding habits, supplier performance capability and quality level, and comprehensively constructs risk models of operation risk, financial index, knowledge, legal litigation and other property dimensions by means of credit China, sky eye investigation, enterprise investigation and other third party data to form comprehensive and real supplier portrait, thereby realizing the knowledge of the rights in purchasing games, and the intelligent making and assistant decision of the purchasing strategy are assisted.
Description
Technical Field
The invention relates to the technical field of big data analysis and processing, in particular to a supplier portrait modeling method and a supplier portrait modeling system.
Background
With the rise and development of big data, the dimensionality of the information of the suppliers based on the data sources of external third parties is more and more abundant, and it becomes possible to automatically evaluate the suppliers by digging out the information desired by purchase from various data and by multidimensional evaluation indexes, wherein the overall portrayal of the suppliers by the user portrayal technology is more and more concerned by customers.
The user portrait is one of popular technologies in internet big data at present, is widely applied to various big e-commerce platforms, can determine classification and user models according to user transaction history and habits, and further performs user value mining, service improvement and the like. At present, a purchasing system can inquire and feed back information of a single supplier, but quantitative and effective evaluation of the supplier is difficult to carry out through multi-dimensional information. Management of vendors lacks intuitive, visual management means and methods. By establishing a supplier portrait model, the disordered data can be cleaned and modeled, and further analysis decision is provided.
Disclosure of Invention
Technical problem to be solved
Aiming at the defects of the prior art, the invention provides a supplier portrait modeling method and a supplier portrait modeling system for improving high purchasing efficiency and preventing purchasing risk.
(II) technical scheme
In order to achieve the purpose, the invention provides the following technical scheme: a supplier portrait modeling system comprises a user information collection unit, a business scene determination unit, a basic data acquisition unit, a data preprocessing unit, a modeling unit and an imaging display unit, wherein the user information collection unit acquires effective evaluation data of a supplier based on user transaction history and habits, user history browsing records and user collection records, the business scene determination unit determines a business scene in which a supplier label attribute is used according to the requirement of a life cycle of a purchasing process on the supplier management, the basic data acquisition unit combs an existing internal database list of the supplier, acquires supplier registration, qualification prequalification and supplier evaluation from a company internal related system, and acquires the business license, type test report content, performance content, company qualification and other qualification content of the supplier, and penalizes, The method comprises the steps of establishing a basic database and sorting, analyzing and recombining data, wherein when missing values and repeated values exist in the obtained data, the data are preprocessed before the data are used by a data preprocessing unit, business label attributes are dynamically divided by a modeling unit according to historical data of a purchasing platform and external data by adopting a K-means clustering algorithm, so that comprehensive and accurate supplier information is provided for users, the obtained supplier big data are subjected to data cleaning by an imaging display unit, the follow-up data for identification can be ensured to fully express a business knowledge system of a supplier, and then the supplier attributes are identified through links of information integration, analysis and the like, and the labels are defined.
In order to improve the effect of acquiring data by a basic data unit, the invention has the improvement that the basic data acquisition unit adopts a Restful interface style, uses a standard HTTP request mode, and performs data timing extraction and butt joint with a national enterprise credit information public system, a Chinese referee document network and the like.
In order to improve the use effect of the data preprocessing unit, the invention improves that the data preprocessing unit comprises a data filtering unit and a data optimizing unit, the data filtering unit comprises a repeated data removing unit and a missing value processing unit, and the data optimizing unit comprises an attribute coding unit, a data standardization processing unit and a data regularization processing unit.
In order to improve the completion effect of the missing value, the missing value processing unit comprises a mean value interpolation module, a similar mean value interpolation module, a modeling prediction module, a high-dimensional mapping module, a multiple interpolation module, a compressed sensing module, a matrix completion module and a manual interpolation module.
In order to improve the encoding effect of the attribute encoding unit, the invention improves that the attribute encoding unit comprises a characteristic dualization and a one-hot encoding, the characteristic dualization is to convert the attribute of a numerical type into the attribute of a Boolean value, a threshold value is set as a separation point for dividing the attribute value into 0 and 1, the one-hot encoding adopts an N-bit state register to encode N possible values, each state is represented by an independent register, and only one of the states is effective at any time.
In order to improve the optimization effect on the data, the invention improves that the data normalization scales the attributes of the samples to a certain specified range, the data regularization processing unit scales a certain norm of the samples to a bit 1, the regularization process is specific to a single sample, and the samples are scaled to a unit norm for each sample.
In order to improve the modeling effect, the invention improves the method that the K-means clustering algorithm takes K points in a data set as the center for clustering and classifies the objects closest to the K points. And gradually updating the value of each clustering center by an iterative method.
A vendor representation modeling method, comprising the steps of:
establishing a tag data source, and acquiring effective evaluation data of a supplier based on transaction history and habits of a user, historical browsing records of the user and collection records of the user;
setting a label rule model, performing comprehensive portrait modeling on a supplier through analysis of historical purchasing data, visually and accurately reflecting quotation behaviors, bidding habits, supplier performance capability and quality level, and comprehensively constructing a risk model of dimensions such as operational risk, financial indexes, intellectual property rights, legal action and the like by means of third-party data such as credit China, sky eye investigation, enterprise investigation and the like;
calculating labels, namely dynamically dividing service label attributes by adopting a K-means clustering algorithm according to historical data and external data of the purchasing platform so as to provide comprehensive and accurate supplier information for users;
and step four, displaying and applying labels, namely dividing the suppliers into primary adaptive suppliers, relationship growth suppliers, relationship maturity suppliers and strategy stable suppliers by matching the rule model established in the step two with the supplier information calculated in the step three.
(III) advantageous effects
Compared with the prior art, the invention provides a supplier portrait modeling method and a supplier portrait modeling system, which have the following beneficial effects:
the invention utilizes big data and K-means algorithm correlation technology, analyzes historical purchasing data, carries out comprehensive portrait modeling on a supplier, intuitively and accurately reflects quotation behaviors, bidding habits, supplier performance capability and quality level, comprehensively constructs a risk model with operation risk, financial index, intellectual property, legal litigation and other dimensions by means of credit China, sky eye investigation, enterprise investigation and other third party data, forms comprehensive and real supplier portrait, realizes the knowledge in purchasing game, and assists intelligent formulation and auxiliary decision making of purchasing strategies.
Drawings
FIG. 1 is a schematic representation of the steps of the present invention;
FIG. 2 is a schematic diagram of the system of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-2, the present invention is a supplier portrait modeling system, which includes a user information collection unit, a business scenario determination unit, a basic data acquisition unit, a data preprocessing unit, a modeling unit, and an imaging display unit, wherein the user information collection unit acquires effective evaluation data of a supplier based on user transaction history and habits, user's historical browsing records, and user's collection records, the business scenario determination unit determines a business scenario in which a supplier label attribute has been used according to a need of a supplier management in a lifecycle of a purchasing process, the basic data acquisition unit combs an existing internal database list of the supplier, acquires supplier registration, qualification prequalification and supplier evaluation from an internal related system of a company, and acquires business license, type test report content, business license performance content, image data of the supplier, and the like, The system comprises a modeling unit, a data integration unit, an imaging display unit, a data analysis unit and a data analysis unit, wherein the modeling unit is used for dynamically dividing service label attributes according to historical data of a purchasing platform and external data by adopting a K-means clustering algorithm when the obtained data has missing values and repeated values, so as to provide comprehensive and accurate supplier information for users, the imaging display unit is used for cleaning the obtained supplier big data, so that the follow-up data for identification can fully express a service knowledge system of a supplier, and then the supplier attributes are identified through links of information integration, analysis and the like, so as to define labels.
In this embodiment, the basic data acquisition unit adopts a Restful interface style, performs data timing extraction and docking with a national enterprise credit information public system, a chinese referee document network and the like by using a standard HTTP request mode, realizes real-time data acquisition of a data provider according to a business algorithm model rule, establishes a business relationship with internal data, and provides objective data support for a provider portrait, thereby improving the data acquisition effect of the basic data unit.
In this embodiment, the data preprocessing unit includes a data filtering unit and a data optimizing unit, the data filtering unit includes a repeated data removing unit and a missing value processing unit, the data optimizing unit includes an attribute encoding unit, a data normalization processing unit and a data regularization processing unit, the collected basic information of the enterprise is integrated by the data optimizing unit, and the repeated data removing unit removes redundant repeated data in time, so that the use effect of the data preprocessing unit is improved.
In this embodiment, the missing value processing unit includes a mean interpolation module, a homogeneous mean interpolation module, a modeling prediction module, a high-dimensional mapping module, a multiple interpolation module, a compressed sensing module, a matrix completion module, and a manual interpolation module, where when the mean interpolation module is used, if the distance of a sample attribute is measurable, the mean value of the effective values of the attribute is used to interpolate a missing value, and if the distance is not measurable, the mode of the effective values of the attribute is used to interpolate the missing value; classifying samples, interpolating a missing value by using the mean value of the samples in the class, classifying the samples by using a homogeneous mean value interpolation module, and interpolating the missing value by using the mean value of the samples in the class; the modeling prediction module predicts the missing attributes as prediction targets, divides the data set into two types according to whether the missing values of the specific attributes exist or not, and predicts the missing values of the data set to be predicted by utilizing the existing machine learning algorithm; and the high-dimensional mapping module maps the attributes to a high-dimensional space and adopts a one-hot code encoding (one-hot) technology. Expanding the attribute value containing K discrete value ranges into K +1 attribute values, and if the attribute value is missing, setting the expanded K +1 attribute value as 1; the multiple interpolation module considers that the value to be interpolated is random, practically, the value to be interpolated is usually estimated, different noises are added to form a plurality of groups of selectable interpolation values, the most suitable interpolation is selected according to a certain selection basis, and the interpolation processing only supplements unknown values with subjective estimation values of people and does not necessarily completely accord with objective facts.
In this embodiment, the attribute encoding unit includes a feature binarization and a one-hot encoding, where the feature binarization is to convert a numerical attribute into a boolean attribute, and set a threshold as a partition point for dividing attribute values into 0 and 1, and the one-hot encoding employs an N-bit state register to encode N possible values, each state is represented by an independent register, and only one of the states is available at any time; one-hot encoding can handle non-numerical attributes; features are expanded to a certain extent; the coded attribute is sparse, and a large number of zero components exist, so that the coding effect of the attribute coding unit is improved.
In this embodiment, the data normalization scales the attribute of the sample to a certain specified range, the data normalization processing unit scales a certain norm of the sample to bit 1, the regularization process is for a single sample, the sample is scaled to a unit norm for each sample, and the data normalization requires that the sample has zero mean and unit variance based on some algorithms; the effect when different properties of the sample have different magnitudes needs to be eliminated: the difference of the orders of magnitude leads to the property with larger orders of magnitude to occupy the dominant position; the difference in order of magnitude will result in a slower iterative convergence rate; the algorithm relying on the sample distance is very sensitive to the magnitude of the data;
min-max normalization: for each attribute, let minA and maxA be the minimum and maximum values of attribute A, respectively, and map an original value x of A to a value x' in the interval [0,1] by min-max normalization, which is expressed by: new data = (original data-min)/(max-min)
z-score standardization (normalization): the normalization of the data is performed based on the mean and standard deviation (mean) of the raw data. The original value x of A is normalized to x' using z-score. The z-score normalization method is applicable to cases where the maximum and minimum values of attribute A are unknown, or where there is outlier data that is out of range. New data = (raw data-mean)/standard deviation, both mean and standard deviation defined on a sample set, not on a single sample. Normalization is for a certain property and requires the use of the value of all samples on that property.
In this embodiment, the K-means clustering algorithm performs clustering with K points in the data set as the center, and classifies the objects closest to them. And the values of all the clustering centers are updated successively by an iterative method, so that the modeling effect is improved.
A vendor representation modeling method, comprising the steps of:
establishing a tag data source, and acquiring effective evaluation data of a supplier based on transaction history and habits of a user, historical browsing records of the user and collection records of the user;
setting a label rule model, performing comprehensive portrait modeling on a supplier through analysis of historical purchasing data, visually and accurately reflecting quotation behaviors, bidding habits, supplier performance capability and quality level, and comprehensively constructing a risk model of dimensions such as operational risk, financial indexes, intellectual property rights, legal action and the like by means of third-party data such as credit China, sky eye investigation, enterprise investigation and the like;
calculating labels, namely dynamically dividing service label attributes by adopting a K-means clustering algorithm according to historical data and external data of the purchasing platform so as to provide comprehensive and accurate supplier information for users;
and step four, displaying and applying labels, namely dividing the suppliers into primary adaptive suppliers, relationship growth suppliers, relationship maturity suppliers and strategy stable suppliers by matching the rule model established in the step two with the supplier information calculated in the step three.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (8)
1. A supplier pictorial modeling system is characterized by comprising a user information collection unit, a business scene determination unit, a basic data acquisition unit, a data preprocessing unit, a modeling unit and an imaging display unit, wherein the user information collection unit acquires effective evaluation data of a supplier based on user transaction history and habits, user historical browsing records and user collection records, the business scene determination unit determines business scenes in which the label attribute of the supplier is used according to the requirements of the life cycle of a purchasing process on the management of the supplier, the basic data acquisition unit combs the existing internal database list of the supplier, acquires the registration, qualification prequalification and evaluation of the supplier from an internal related system of a company, and acquires the qualification contents such as the business license, the type test report content, the performance content and the qualification of the company of the supplier, the method comprises the steps of establishing a basic database, sorting, analyzing and recombining data, carrying out data preprocessing before use when missing values and repeated values exist in the obtained data by a data preprocessing unit, dynamically dividing service label attributes by a modeling unit according to historical data of a purchasing platform and external data by adopting a K-means clustering algorithm so as to provide comprehensive and accurate supplier information for a user, carrying out data cleaning on the obtained supplier big data by an imaging display unit, ensuring that the subsequent data for identification can fully express a service knowledge system of the supplier, identifying the supplier attributes through links of information integration, analysis and the like, and defining labels.
2. The supplier portrait modeling system according to claim 1, wherein the basic data acquisition unit adopts Restful interface style, and uses standard HTTP request mode to perform data timing extraction and docking with national enterprise credit information public system, chinese referee document network, etc.
3. The supplier imagery modeling system of claim 1, wherein the data pre-processing unit comprises a data filtering unit and a data optimization unit, the data filtering unit comprises a repeated data removal unit and a missing value processing unit, and the data optimization unit comprises an attribute encoding unit, a data normalization processing unit and a data regularization processing unit.
4. The supplier image modeling system of claim 3, wherein the deficiency value processing unit comprises a mean interpolation module, a homogeneous mean interpolation module, a modeling prediction module, a high-dimensional mapping module, a multiple interpolation module, a compressive sensing module, a matrix completion module, and a manual interpolation module.
5. The vendor representation system of claim 3, wherein the attribute encoding unit comprises a feature binarization for converting a numeric attribute into a Boolean attribute, and a one-hot encoding for setting a threshold as a partition point dividing the attribute values into 0 and 1, wherein the one-hot encoding uses N-bit status registers to encode N possible values, each status being represented by a separate register and only one of the statuses being valid at any time.
6. A vendor imagery modeling system according to claim 3, wherein said data normalization scales the attributes of the samples to a specified range, said data regularization processing unit scales a norm of the samples to bit 1, and the regularization process is for a single sample, scaling the sample to a unit norm for each sample.
7. The vendor imagery modeling system of claim 1, wherein said K-means clustering algorithm clusters K points in the data set as a center, classifies objects closest to them, and updates the value of each cluster center successively by an iterative method.
8. A supplier portrait modeling method is characterized by comprising the following steps:
establishing a tag data source, and acquiring effective evaluation data of a supplier based on transaction history and habits of a user, historical browsing records of the user and collection records of the user;
setting a label rule model, performing comprehensive portrait modeling on a supplier through analysis of historical purchasing data, visually and accurately reflecting quotation behaviors, bidding habits, supplier performance capability and quality level, and comprehensively constructing a risk model of dimensions such as operational risk, financial indexes, intellectual property rights, legal action and the like by means of third-party data such as credit China, sky eye investigation, enterprise investigation and the like;
calculating labels, namely dynamically dividing service label attributes by adopting a K-means clustering algorithm according to historical data and external data of the purchasing platform so as to provide comprehensive and accurate supplier information for users;
and step four, displaying and applying labels, namely dividing the suppliers into primary adaptive suppliers, relationship growth suppliers, relationship maturity suppliers and strategy stable suppliers by matching the rule model established in the step two with the supplier information calculated in the step three.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110688987.0A CN113345080A (en) | 2021-06-22 | 2021-06-22 | Supplier portrait modeling method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110688987.0A CN113345080A (en) | 2021-06-22 | 2021-06-22 | Supplier portrait modeling method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113345080A true CN113345080A (en) | 2021-09-03 |
Family
ID=77478455
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110688987.0A Pending CN113345080A (en) | 2021-06-22 | 2021-06-22 | Supplier portrait modeling method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113345080A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114184232A (en) * | 2021-12-10 | 2022-03-15 | 重庆大学 | Multi-parameter integrated monitoring system for power transmission line |
| CN114219114A (en) * | 2021-12-24 | 2022-03-22 | 南京莫愁智慧信息科技有限公司 | Reservation big data-based tourism passenger flow management and control method and cloud service platform |
| CN114254916A (en) * | 2021-12-20 | 2022-03-29 | 国网江苏省电力有限公司物资分公司 | Multi-dimensional supplier risk real-time early warning method with power grid service characteristics |
| CN114444381A (en) * | 2021-12-30 | 2022-05-06 | 南京诺源医疗器械有限公司 | Control method and system suitable for light source |
| CN115080698A (en) * | 2022-07-01 | 2022-09-20 | 公诚管理咨询有限公司 | Bidding analysis method, system, equipment and storage medium based on big data |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110675011A (en) * | 2019-06-21 | 2020-01-10 | 广东电网物资有限公司 | Imaging method and use method of supplier portrait of material equipment in power industry |
| CN111600919A (en) * | 2019-02-21 | 2020-08-28 | 北京金睛云华科技有限公司 | Web detection method and device based on artificial intelligence |
| CN111861716A (en) * | 2020-07-23 | 2020-10-30 | 北京睿知图远科技有限公司 | Method for generating monitoring early warning level in credit based on software system |
| CN112434884A (en) * | 2020-12-12 | 2021-03-02 | 广东电力信息科技有限公司 | Method and device for establishing supplier classified portrait |
| CN112948667A (en) * | 2021-02-03 | 2021-06-11 | 北京优易惠技术有限公司 | Supplier recommendation system and method based on bidding |
| CN112990973A (en) * | 2021-03-22 | 2021-06-18 | 山东顺能网络科技有限公司 | Online shop portrait construction method and system |
-
2021
- 2021-06-22 CN CN202110688987.0A patent/CN113345080A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111600919A (en) * | 2019-02-21 | 2020-08-28 | 北京金睛云华科技有限公司 | Web detection method and device based on artificial intelligence |
| CN110675011A (en) * | 2019-06-21 | 2020-01-10 | 广东电网物资有限公司 | Imaging method and use method of supplier portrait of material equipment in power industry |
| CN111861716A (en) * | 2020-07-23 | 2020-10-30 | 北京睿知图远科技有限公司 | Method for generating monitoring early warning level in credit based on software system |
| CN112434884A (en) * | 2020-12-12 | 2021-03-02 | 广东电力信息科技有限公司 | Method and device for establishing supplier classified portrait |
| CN112948667A (en) * | 2021-02-03 | 2021-06-11 | 北京优易惠技术有限公司 | Supplier recommendation system and method based on bidding |
| CN112990973A (en) * | 2021-03-22 | 2021-06-18 | 山东顺能网络科技有限公司 | Online shop portrait construction method and system |
Non-Patent Citations (2)
| Title |
|---|
| 吴奭登: "基于大数据分析的电力企业供应商信用风险管理研究", 《现代信息科技》 * |
| 孙云飞: "浅谈大型国企集中采购下的供应商精准画像策略", 《中国物流与采购》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114184232A (en) * | 2021-12-10 | 2022-03-15 | 重庆大学 | Multi-parameter integrated monitoring system for power transmission line |
| CN114254916A (en) * | 2021-12-20 | 2022-03-29 | 国网江苏省电力有限公司物资分公司 | Multi-dimensional supplier risk real-time early warning method with power grid service characteristics |
| CN114219114A (en) * | 2021-12-24 | 2022-03-22 | 南京莫愁智慧信息科技有限公司 | Reservation big data-based tourism passenger flow management and control method and cloud service platform |
| CN114219114B (en) * | 2021-12-24 | 2022-08-26 | 南京莫愁智慧信息科技有限公司 | Reservation big data-based tourism passenger flow management and control method and cloud service platform |
| CN114444381A (en) * | 2021-12-30 | 2022-05-06 | 南京诺源医疗器械有限公司 | Control method and system suitable for light source |
| CN115080698A (en) * | 2022-07-01 | 2022-09-20 | 公诚管理咨询有限公司 | Bidding analysis method, system, equipment and storage medium based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113345080A (en) | Supplier portrait modeling method and system | |
| US20230306449A1 (en) | Pre-processing financial market data prior to machine learning training | |
| CN110738527A (en) | feature importance ranking method, device, equipment and storage medium | |
| CN112700324A (en) | User loan default prediction method based on combination of Catboost and restricted Boltzmann machine | |
| CN112270596A (en) | Risk control system and method based on user portrait construction | |
| CN112395487A (en) | Information recommendation method and device, computer-readable storage medium and electronic equipment | |
| CN113469730A (en) | Customer repurchase prediction method and device based on RF-LightGBM fusion model under non-contract scene | |
| CN112541111A (en) | Commodity retrieval and commodity recommendation system based on decentralized big data retrieval market | |
| CN113313538A (en) | User consumption capacity prediction method and device, electronic equipment and storage medium | |
| CN115526652A (en) | Client loss early warning method and system based on machine learning | |
| CN113139769A (en) | Purchasing method and device based on artificial intelligence, computer equipment and storage medium | |
| CN115545886A (en) | Overdue risk identification method, overdue risk identification device, overdue risk identification equipment and storage medium | |
| CN114997916A (en) | Prediction method, system, electronic device and storage medium of potential user | |
| CN116862626B (en) | Multi-mode commodity alignment method | |
| CN113450141A (en) | Intelligent prediction method and device based on electricity selling quantity characteristics of large-power customer groups | |
| CN113468203B (en) | Financial user image drawing method based on recurrent neural network and attention mechanism | |
| CN116012086A (en) | Commodity price estimating method, commodity price estimating device, electronic equipment and storage medium | |
| CN115034762A (en) | Post recommendation method and device, storage medium, electronic equipment and product | |
| CN114626940A (en) | Data analysis method and device and electronic equipment | |
| CN117194966A (en) | Training method and related device for object classification model | |
| CN113837843A (en) | Product recommendation method, device, medium and electronic equipment | |
| US11004156B2 (en) | Method and system for predicting and indexing probability of financial stress | |
| CN113034264A (en) | Method and device for establishing customer loss early warning model, terminal equipment and medium | |
| CN108280531B (en) | Student class score ranking prediction method based on Lasso regression | |
| CN117009921B (en) | Optimized data processing method and system of data fusion engine |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210903 |