CN116204888B - Data source fusion evaluation method and system based on privacy calculation - Google Patents
Data source fusion evaluation method and system based on privacy calculation Download PDFInfo
- Publication number
- CN116204888B CN116204888B CN202310219036.8A CN202310219036A CN116204888B CN 116204888 B CN116204888 B CN 116204888B CN 202310219036 A CN202310219036 A CN 202310219036A CN 116204888 B CN116204888 B CN 116204888B
- Authority
- CN
- China
- Prior art keywords
- data sources
- data
- data source
- privacy
- auc
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004364 calculation method Methods 0.000 title claims abstract description 44
- 230000004927 fusion Effects 0.000 title claims abstract description 35
- 238000011156 evaluation Methods 0.000 title claims abstract description 22
- 238000000034 method Methods 0.000 claims abstract description 20
- 238000010801 machine learning Methods 0.000 claims abstract description 16
- 238000012216 screening Methods 0.000 claims abstract description 11
- 238000012549 training Methods 0.000 claims abstract description 8
- 238000013475 authorization Methods 0.000 claims description 18
- 238000011161 development Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/50—Monitoring users, programs or devices to maintain the integrity of platforms, e.g. of processors, firmware or operating systems
- G06F21/57—Certifying or maintaining trusted computer platforms, e.g. secure boots or power-downs, version controls, system software checks, secure updates or assessing vulnerabilities
- G06F21/577—Assessing vulnerabilities and evaluating computer system security
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
- G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Bioethics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a data source fusion evaluation method and a system based on privacy calculation, wherein characteristic data of a plurality of data sources are inquired and obtained, and scores auc of each data source are obtained by training and calculating a machine learning model; ranking the scores auc of the data sources, and screening important data sources which are ranked later but are selected necessarily according to ranking results and the importance of the data sources; acquiring new variables x and labels y of the important data sources in a privacy intersection mode, retraining a machine learning model through the new variables x and the labels y, and calculating new scores auc of the important data sources; the scores auc for each data source are reordered based on the new scores auc, screening out the top N data sources. The method can finish selecting the data sources with sufficient dimensionality and better accuracy performance meeting the data source on the basis of no data source iteration, and finally improves the accuracy of the fusion score.
Description
Technical Field
The invention relates to the technical field of data source fusion scoring, in particular to a data source fusion evaluation method and system based on privacy calculation.
Background
AUC: an index for evaluating the accuracy of the score, which is known as AreaunderCurve, represents a probability value that a classification algorithm ranks positive samples in front of negative samples, and the larger the value is, the more accurate the score is. At present, the fusion scoring based on a plurality of data sources is the key direction of development in the industry (a bank card center, a consumer finance company, a small credit institution and the like), but one technical problem is that the main stream institution is difficult to process at present, because the accuracy of different data sources can be greatly different, how to better model the scoring with high accuracy is a key ring of developing the fusion scoring; for accuracy, most institutions will sort according to auc of each fusion score, and select auc the score with the top ranking as the candidate variable, if the score auc of a certain class of data source is lower, but comes from a certain important dimension, such as one of payment class, SDK class or operator class, according to the conventional screening logic, the score of the class is not necessarily modular, and the invention is intended to provide a new solution.
If auc of a certain data source is lower in the fusion evaluation process, if the data source is directly removed to generate a scoring variable system according to a common processing mode, the method has the advantages of convenience, but has the disadvantages of losing the information of the part of variables, namely sacrificing the diversity of the scoring variable system and being unfavorable for the stability of the subsequent fusion scores; in addition, if a certain data source auc is found to be lower, the data source side iterates further, so that more manpower is consumed to bring about the loss of time cost, and repeated iteration can occur to bring about negative effects on the time point of the final fusion score development online.
Disclosure of Invention
Therefore, the invention provides a data source fusion evaluation method and system based on privacy calculation, which are used for solving the problem of insufficient accuracy of a single data source in the prior art.
In order to achieve the above object, the present invention provides the following technical solutions:
according to a first aspect of an embodiment of the present invention, a data source fusion evaluation method based on privacy computation is provided, where the method includes:
inquiring to obtain characteristic data of a plurality of data sources, and obtaining scores auc of each data source by training and calculating a machine learning model;
ranking the scores auc of the data sources obtained by calculation, and screening important data sources which are ranked later but are selected necessarily according to ranking results and the importance of the data sources;
acquiring new variables x and labels y of the important data sources through privacy intersection, retraining a machine learning model through the new variables x and the labels y, and calculating new higher scores auc of the important data sources;
the scores auc of the data sources are reordered according to the calculated new scores auc of the important data sources, and the first N data sources comprising the important data sources are screened out through a plurality of iterations according to the ordering result.
Further, screening out important data sources which are selected after sorting but are necessary according to sorting results and by combining importance of all the data sources, wherein the method specifically comprises the following steps:
judging whether the data source is an important data source which is selected necessarily according to the type of the data source, wherein the type of the data source comprises a payment type, an SDK type, an operator type and an Internet type.
Further, obtaining new variables x and labels y of the data sources by privacy intersection on the obtained important data sources specifically includes:
and carrying out privacy intersection on multiple items of data acquired by a single data source to obtain a new input variable x and a new label y.
Further, the querying obtains the characteristic data of a plurality of data sources, which specifically includes:
firstly, confirming whether the authorization of a user side, in particular to the authorization of three-party data meets the reasonable, necessary and minimized principle; and secondly, after confirming that the authorization is correct, starting the inquiry of the data source side.
According to a second aspect of an embodiment of the present invention, there is provided a data source fusion evaluation device based on privacy calculation, the device including:
the data query module is used for querying and acquiring characteristic data of a plurality of data sources;
the calculation engine module is used for obtaining the score auc of each data source through training calculation on the machine learning model;
the sorting module is used for sorting the scores auc of the data sources obtained through calculation, and screening important data sources which are sorted later but are selected necessarily according to sorting results and the importance of the data sources;
the privacy calculation module is used for obtaining new variables x and labels y of the important data sources through a privacy intersection mode, retraining the machine learning model through the new variables x and the labels y, and calculating a new higher score auc of the important data sources;
the ranking module is further configured to reorder the scores auc of the data sources according to the calculated new scores auc of the important data sources, and iterate a plurality of times until the first N data sources including the important data sources are screened out according to the ranking result.
Further, the sorting module is specifically configured to:
judging whether the data source is an important data source which is selected necessarily according to the type of the data source, wherein the type of the data source comprises a payment type, an SDK type, an operator type and an Internet type.
Further, the privacy calculation module is specifically configured to:
and carrying out privacy intersection on multiple items of data acquired by a single data source to obtain a new input variable x and a new label y.
Further, the data query module is specifically configured to:
firstly, confirming whether the authorization of a user side, in particular to the authorization of three-party data meets the reasonable, necessary and minimized principle; and secondly, after confirming that the authorization is correct, starting the inquiry of the data source side.
According to a third aspect of an embodiment of the present invention, there is provided a data source fusion evaluation system based on privacy computation, the system including: a processor and a memory;
the memory is used for storing one or more program instructions;
the processor is configured to execute one or more program instructions to perform the method of any of the above.
According to a fourth aspect of embodiments of the present invention, a computer storage medium is presented, containing one or more program instructions for performing a method as described in any of the above by a privacy calculation based data source fusion assessment system.
The invention has the following advantages:
according to the data source fusion evaluation method and system based on privacy calculation, characteristic data of a plurality of data sources are inquired and obtained, and scores auc of the data sources are obtained by training and calculating a machine learning model; ranking the scores auc of the data sources obtained by calculation, and screening important data sources which are ranked later but are selected necessarily according to ranking results and the importance of the data sources; acquiring new variables x and labels y of the important data sources through privacy intersection, retraining a machine learning model through the new variables x and the labels y, and calculating new higher scores auc of the important data sources; the scores auc of the data sources are reordered according to the calculated new scores auc of the important data sources, and the first N data sources comprising the important data sources are screened out through a plurality of iterations according to the ordering result. The method can finish selecting the data source with sufficient dimensionality and better accuracy performance which meets the data source on the basis of no data source iteration, and finally improves the accuracy of the fusion score.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It will be apparent to those of ordinary skill in the art that the drawings in the following description are exemplary only and that other implementations can be obtained from the extensions of the drawings provided without inventive effort.
FIG. 1 is a flowchart of a data source fusion evaluation method based on privacy computation according to an embodiment of the present invention;
fig. 2 is a flowchart of an implementation of a data source fusion evaluation method based on privacy calculation according to an embodiment of the present invention.
Detailed Description
Other advantages and advantages of the present invention will become apparent to those skilled in the art from the following detailed description, which, by way of illustration, is to be read in connection with certain specific embodiments, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1 and fig. 2, an embodiment of the present invention proposes a data source fusion evaluation method based on privacy calculation, where the method includes:
s100, inquiring to obtain characteristic data of a plurality of data sources, and obtaining scores auc of each data source by training and calculating a machine learning model.
Firstly, the modeled data needs to confirm the authorization of a user side, in particular whether the authorization of the three-party data meets the reasonable, necessary and minimized principle; and secondly, after confirming that the authorization is correct, starting the inquiry of the data source side.
Each data source score auc is calculated by the calculation engine to provide a basis for determining which data source scores can be ultimately modeled for subsequent evaluation.
And S200, sorting the scores auc of the data sources obtained through calculation, and screening important data sources which are sorted later but are selected necessarily according to sorting results and the importance of the data sources.
Specifically, whether the important data source is necessary to be selected is judged according to the type of the data source, wherein the type of the data source comprises a payment type, an SDK type, an operator type and an Internet type. Such as payment, SDK, or carrier, and culls such sources if auc is low.
By ordering the data sources auc calculated by the calculation engine, the top ranked data sources are found, typically the number of data sources for which the fusion score is not excessive, typically less than 4, in view of the cost of the data, and there is an explicit requirement for the type of data source, such as for example 4 data sources, typically comprising various categories such as payment, operator, SDK, internet, etc., if auc of one data source is ordered relatively later, such as auc, the fifth data source is ordered, but in view of the consideration of the type of data source such data sources must be taken into account, at this point the following privacy calculations will be initiated.
S300, acquiring new variables x and labels y of the important data sources through a privacy intersection mode, retraining a machine learning model through the new variables x and the labels y, and calculating new higher scores auc of the important data sources.
The variable x and the tag y include an input variable x and a tag y. In this embodiment, x is mainly variable required for risk modeling, such as internet behavior data, account conditions, historical repayment performances, and the like, y is mainly a tag that a user has mob3-5 overdue for more than 30 days, and data sources, such as three major operators, have x and y related to the user and need to be indirectly linked and acquired through a privacy calculation mode.
In order to reduce the cost, a single data source is selected for privacy intersection. And carrying out privacy intersection on multiple items of data acquired by a single data source to obtain a new input variable x and a new label y. For example, the data source of the communication hospital gathers three networks of data, and obtains the variable x and the label y through privacy intersection.
Acquiring new variables through privacy calculations may promote auc. The more variables, and with labels y, the promotion auc is achieved.
S400, according to the calculated new scores auc of the important data sources, the scores auc of the data sources are ranked again, and a plurality of iterations are performed until the first N data sources comprising the important data sources are screened out according to the ranking result.
The method comprises the steps of acquiring an x variable of an important data source in a privacy intersection mode, acquiring y common to industries, completing privacy modeling, normally completing the model of the important data source through a modeling module in a privacy calculation module, and calculating auc by iterative scoring after modeling, so that a new auc score enters a certain position of the first 4 bits to serve as a target for iteration termination, thereby completing a final target of the method.
Corresponding to the above embodiment 1, this embodiment proposes a data source fusion evaluation device based on privacy calculation, which includes:
the data query module is used for querying and acquiring characteristic data of a plurality of data sources;
the calculation engine module is used for obtaining the score auc of each data source through training calculation on the machine learning model;
the sorting module is used for sorting the scores auc of the data sources obtained through calculation, and screening important data sources which are sorted later but are selected necessarily according to sorting results and the importance of the data sources;
the privacy calculation module is used for obtaining new variables x and labels y of the important data sources through a privacy intersection mode, retraining the machine learning model through the new variables x and the labels y, and calculating a new higher score auc of the important data sources;
the ranking module is further configured to reorder the scores auc of the data sources according to the calculated new scores auc of the important data sources, and iterate a plurality of times until the first N data sources including the important data sources are screened out according to the ranking result.
Further, the sorting module is specifically configured to:
judging whether the data source is an important data source which is selected necessarily according to the type of the data source, wherein the type of the data source comprises a payment type, an SDK type, an operator type and an Internet type.
Further, the privacy calculation module is specifically configured to:
and carrying out privacy intersection on multiple items of data acquired by a single data source to obtain a new input variable x and a new label y.
Further, the data query module is specifically configured to:
firstly, confirming whether the authorization of a user side, in particular to the authorization of three-party data meets the reasonable, necessary and minimized principle; and secondly, after confirming that the authorization is correct, starting the inquiry of the data source side.
The functions performed by each component in the data source fusion evaluation system based on privacy calculation provided in the embodiment of the present invention are described in detail in the above embodiment 1, so that redundant description is omitted here.
Corresponding to the above embodiment, an embodiment of the present invention proposes a data source fusion evaluation system based on privacy calculation, the system including: a processor and a memory;
the memory is used for storing one or more program instructions;
the processor is configured to execute one or more program instructions to perform the method as described in the above embodiments.
In correspondence with the above-described embodiments, the present embodiment proposes a computer storage medium containing one or more program instructions for performing the method of the above-described embodiments by a data source fusion evaluation system based on privacy calculations.
While the invention has been described in detail in the foregoing general description and specific examples, it will be apparent to those skilled in the art that modifications and improvements can be made thereto. Accordingly, such modifications or improvements may be made without departing from the spirit of the invention and are intended to be within the scope of the invention as claimed.
Claims (8)
1. A data source fusion evaluation method based on privacy computation, the method comprising:
inquiring to obtain characteristic data of a plurality of data sources, and obtaining scores auc of each data source by training and calculating a machine learning model;
ranking the scores auc of the data sources obtained by calculation, and screening important data sources which are ranked later but are selected necessarily according to ranking results and the importance of the data sources; the method specifically comprises the following steps: judging whether the data source is an important data source which is necessary to be selected according to the type of the data source, wherein the type of the data source comprises a payment class, an SDK class, an operator class and an Internet class;
acquiring new variables x and labels y of the important data sources through privacy intersection, retraining a machine learning model through the new variables x and the labels y, and calculating new higher scores auc of the important data sources;
the scores auc of the data sources are reordered according to the calculated new scores auc of the important data sources, and the first N data sources comprising the important data sources are screened out through a plurality of iterations according to the ordering result.
2. The method for evaluating the fusion of the data sources based on the privacy calculation according to claim 1, wherein the method for acquiring the new variable x and the tag y of the data source by the important data source through the privacy intersection is characterized by comprising the following steps:
and carrying out privacy intersection on multiple items of data acquired by a single data source to obtain a new input variable x and a new label y.
3. The method for evaluating fusion of data sources based on privacy calculation according to claim 1, wherein querying obtains feature data of a plurality of data sources, specifically comprising:
firstly, confirming the authorization of a user side, and judging whether the authorization of the three-party data meets the reasonable, necessary and minimized principle or not; and secondly, after confirming that the authorization is correct, starting the inquiry of the data source side.
4. A data source fusion evaluation device based on privacy computation, the device comprising:
the data query module is used for querying and acquiring characteristic data of a plurality of data sources;
the calculation engine module is used for obtaining the score auc of each data source through training calculation on the machine learning model;
the sorting module is used for sorting the scores auc of the data sources obtained through calculation, and screening important data sources which are sorted later but are selected necessarily according to sorting results and the importance of the data sources; the ordering module is specifically used for: judging whether the data source is an important data source which is necessary to be selected according to the type of the data source, wherein the type of the data source comprises a payment class, an SDK class, an operator class and an Internet class;
the privacy calculation module is used for obtaining new variables x and labels y of the important data sources through a privacy intersection mode, retraining the machine learning model through the new variables x and the labels y, and calculating a new higher score auc of the important data sources;
the ranking module is further configured to reorder the scores auc of the data sources according to the calculated new scores auc of the important data sources, and iterate a plurality of times until the first N data sources including the important data sources are screened out according to the ranking result.
5. The data source fusion evaluation device based on privacy calculation according to claim 4, wherein the privacy calculation module is specifically configured to:
and carrying out privacy intersection on multiple items of data acquired by a single data source to obtain a new input variable x and a new label y.
6. The data source fusion evaluation device based on privacy calculation according to claim 4, wherein the data query module is specifically configured to:
firstly, confirming the authorization of a user side, and judging whether the authorization of the three-party data meets the reasonable, necessary and minimized principle or not; and secondly, after confirming that the authorization is correct, starting the inquiry of the data source side.
7. A data source fusion evaluation system based on privacy calculations, the system comprising: a processor and a memory;
the memory is used for storing one or more program instructions;
the processor being operative to execute one or more program instructions for performing the method as claimed in any one of claims 1-3.
8. A computer storage medium having one or more program instructions embodied therein for performing the method of any of claims 1-3 by a privacy computation based data source fusion assessment system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310219036.8A CN116204888B (en) | 2023-03-01 | 2023-03-01 | Data source fusion evaluation method and system based on privacy calculation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310219036.8A CN116204888B (en) | 2023-03-01 | 2023-03-01 | Data source fusion evaluation method and system based on privacy calculation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116204888A CN116204888A (en) | 2023-06-02 |
| CN116204888B true CN116204888B (en) | 2023-10-27 |
Family
ID=86517136
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310219036.8A Active CN116204888B (en) | 2023-03-01 | 2023-03-01 | Data source fusion evaluation method and system based on privacy calculation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116204888B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113919432A (en) * | 2021-10-19 | 2022-01-11 | 南京星云数字技术有限公司 | Classification model construction method, data classification method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108090208A (en) * | 2017-12-29 | 2018-05-29 | 广东欧珀移动通信有限公司 | Fused data processing method and processing device |
-
2023
- 2023-03-01 CN CN202310219036.8A patent/CN116204888B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113919432A (en) * | 2021-10-19 | 2022-01-11 | 南京星云数字技术有限公司 | Classification model construction method, data classification method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116204888A (en) | 2023-06-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tsiptsis et al. | Data mining techniques in CRM: inside customer segmentation | |
| CN110263821B (en) | Training of transaction feature generation model, and method and device for generating transaction features | |
| CN109739844B (en) | Data classification method based on attenuation weight | |
| CN110428322A (en) | A kind of adaptation method and device of business datum | |
| CN109684627A (en) | A kind of file classification method and device | |
| US7398227B2 (en) | Methods, systems, and computer for managing purchasing data | |
| US20170278013A1 (en) | Stereoscopic learning for classification | |
| CN118363932B (en) | Unmanned aerial vehicle-based intelligent patrol method and system | |
| CN114830164A (en) | Method and system for detecting reasons for additional deposit notification using machine learning | |
| CN114118816B (en) | Risk assessment method, apparatus, device and computer storage medium | |
| US20230099627A1 (en) | Machine learning model for predicting an action | |
| AU2021258019A1 (en) | Utilizing machine learning models to generate initiative plans | |
| CN116204888B (en) | Data source fusion evaluation method and system based on privacy calculation | |
| CN112506907A (en) | Engineering machinery marketing strategy pushing method, system and device based on big data | |
| CN111311420A (en) | Business data pushing method and device | |
| US20230027530A1 (en) | Artificial intelligence (ai) engine assisted creation of production descriptions | |
| Yang et al. | Sequential clustering and classification approach to analyze sales performance of retail stores based on point-of-sale data | |
| CN115796183A (en) | Data field unified standard naming method and device | |
| KR102415644B1 (en) | Smart customs declaration item classification system and method | |
| CN114443803A (en) | Text information mining method and device, electronic equipment and storage medium | |
| CN116954591B (en) | Generalized linear model training method, device, equipment and medium in banking field | |
| US20230289804A1 (en) | Method for scoring events from multiple heterogeneous input streams with low latency, using machine learning | |
| Karnila et al. | MARKET BASKET ANALYSIS ON TRANSACTION DATA USING THE APRIORI ALGORITHM | |
| CN113420214B (en) | Electronic transaction object recommendation method, device and equipment | |
| CN112396513B (en) | Data processing method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |