CN108537460A - Consumer's risk prediction technique and system - Google Patents
Consumer's risk prediction technique and system Download PDFInfo
- Publication number
- CN108537460A CN108537460A CN201810347191.7A CN201810347191A CN108537460A CN 108537460 A CN108537460 A CN 108537460A CN 201810347191 A CN201810347191 A CN 201810347191A CN 108537460 A CN108537460 A CN 108537460A
- Authority
- CN
- China
- Prior art keywords
- prediction
- user
- information
- prediction model
- index
- 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
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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Technology Law (AREA)
- Finance (AREA)
- Educational Administration (AREA)
- Accounting & Taxation (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides a kind of consumer's risk prediction techniques and system, this method to include：Scorecard is obtained according to a plurality of index；Prediction model is built online according to scorecard and indicator conditions, different prediction models is built according to different types of user, and same type of user builds at least one prediction model；Optimal prediction model；Set the use ratio of each prediction model for predicting same type of user；The index computation rule of the index value of each index of setup algorithm；It brings user information into index computation rule and obtains index value, corresponding prediction model is brought into according to obtained index value obtains prediction result, the product for meeting prediction result is matched according to prediction result and product information, prediction result accuracy of the present invention is high, and prediction model adjustment is more convenient, it can be quickly that user matches suitable product and percent of pass is high, reduce the financial risks of cooperative institution, improve the efficiency of user terminal and mechanism end.
Description
Technical field
The invention belongs to internet information processing technology fields, and in particular to a kind of consumer's risk prediction technique and system.
Background technology
Existing internet finance all can carry out risk assessment to reduce financial risks to user.It is most of to have pattern
There is no systematization, and existing system is not adapted dynamically prediction model, can not flexibly build model, test model.From
When user information obtains the index value of index, need by index computation rule, existing model needs more in index computation rule
It is more time-consuming when changing, and model adjustment is cumbersome.
Invention content
The present invention be to solve the above-mentioned problems and carry out, and it is an object of the present invention to provide a kind of modeling efficiency is high, accuracy rate height,
Prediction model can be dynamically adjusted, the consumer's risk prediction technique and system of suitable product are quickly matched for user.
The present invention provides a kind of consumer's risk prediction techniques, which is characterized in that includes the following steps：According to a plurality of index
Scorecard is obtained based on pre-defined rule；
Prediction model is built online according to scorecard and indicator conditions, and different predictions is built according to different types of user
Model, same type of user build at least one prediction model；
Optimal prediction model：Influence of the indicator conditions different in prediction model to prediction model is tested, according to each index
Influence of the condition to prediction model adjusts prediction model；
Set the use ratio of each prediction model for predicting same type of user；
The index computation rule of the index value of each index of setup algorithm；
It brings user information into index computation rule and obtains index value, corresponding prediction mould is brought into according to obtained index value
Type obtains prediction result, and the product for meeting prediction result is matched according to prediction result and product information.
Further, it in consumer's risk prediction technique provided by the invention, can also have the feature that：Wherein, if
When determining the use ratio of each prediction model for predicting same type of user, by each prediction model to same user information
Prediction result be compared, the use ratio of each prediction model is determined according to comparison result.
Further, it in consumer's risk prediction technique provided by the invention, can also have the feature that：Wherein, it obtains
To after prediction result, prediction result is shown.
Further, it in consumer's risk prediction technique provided by the invention, can also have the feature that：Wherein, will
Prediction result is shown when showing in the form of pie chart, block diagram, linear graph or table.
Further, it in consumer's risk prediction technique provided by the invention, can also have the feature that：Wherein, institute
Stating product information includes：Name of product, product issue, product interest rate, air control condition and product icon.
Further, it in consumer's risk prediction technique provided by the invention, can also have the feature that：Wherein, it fills out
The user information write includes：Personal information, electric business purchase information, collage-credit data, liability information, is believed using equipment job information
Breath.
Further, it in consumer's risk prediction technique provided by the invention, can also have the feature that：The scoring
Card includes：Personal information scorecard, job information scorecard, electric business information scorecard, reference information scorecard, liability information are commented
Divide card, operator's informaiton scorecard.
The present invention also provides a kind of consumer's risk forecasting systems, which is characterized in that includes：
Input module, for inputting user information, product information, the type for selecting user；
Model construction module, for building prediction model online；
Memory module, for storing product information, prediction model；
Index computing module is based on pre-defined rule according to the user information of input and calculates each index value；
Prediction module selects suitable prediction model, the finger that the index computing module is obtained according to the type of user
Scale value brings the prediction model into and obtains prediction result；And
Matching module, for being the suitable product of user's matching according to prediction result and product information.
Further, it in consumer's risk forecasting system provided by the invention, can also have the feature that：Consumer's risk
Forecasting system also includes：Display module, for showing prediction result and the matched product of user.
Advantages of the present invention is as follows：
According to consumer's risk prediction technique according to the present invention, since scorecard is to build to obtain by a plurality of index, in advance
Surveying model is built online according to scorecard and at least one indicator conditions, and the index meter of the index value of setup algorithm index is passed through
Rule is calculated, after user information input, carries out index value calculating, then bringing corresponding prediction model into according to class of subscriber carries out
Prediction result is obtained after calculating, is matched according to prediction result and product information, elects suitable product for user, simultaneously
The user for meeting institutional risk grade is filtered out for cooperative institution, whole process usage time is short, improves user experience, drop
The financial risks of Di Liao cooperative institutions improves the efficiency of user terminal and client；Prediction model is built online, and is supported
Line is debugged, and is optimized to model according to result, and according to the test result of different test models, and use ratio is carried out to model
Configuration, therefore prediction model prediction accuracy is high, and adjust more convenient；Index computation rule when index parameter value is more
After changing, the prediction result of prediction model is also accordingly changed, therefore it is more convenient to change index computation rule.
Consumer's risk forecasting system provided by the invention, prediction result accuracy is high, and prediction model adjustment is more convenient,
It can be quickly that user matches suitable product and percent of pass is high, reduce the financial risks of cooperative institution, improve user terminal and machine
The efficiency at structure end.
Description of the drawings
Fig. 1 is the flow chart of consumer's risk prediction technique in the present invention；
Fig. 2 is the schematic diagram of consumer's risk forecasting system in the present invention.
Specific implementation mode
It is real below in order to make the technical means, the creative features, the aims and the efficiencies achieved by the present invention be easy to understand
Example combination attached drawing is applied to be specifically addressed consumer's risk prediction technique of the present invention and system.
As shown in Figure 1, consumer's risk prediction technique comprises the steps of：
Step S1 obtains scorecard according to a plurality of index based on pre-defined rule.In the present embodiment, scorecard includes individual
Information scorecard, job information scorecard, electric business information scorecard, reference information scorecard, liability information scorecard, operator
Information scorecard.
Scorecard calculating process is exemplified below：
Index：Age, the place where his residence is registered, work city, monthly income etc., time limit, interest rate, expense etc..
Indicator rule：Regular 1 (the age>20)；Regular 2 (monthly incomes>2000)……
Scorecard computation rule：
Scorecard 1：Regular 1==ture scores 10；
Regular 2=true scores 10；
.....。
Scorecard 1 is scored at as the sum of every regular score.
In the present embodiment, index includes：Personal essential information class index, job information class index, electric business info class refer to
Mark, reference class index, debt class index, facility information class index etc..The index of these classifications is specially：Month telephone expenses maximum value,
Mobile phone charge minimum value, the mobile phone set meal amount of consumption, client Alipay class APP quantity, customer bank class APP quantity, client's browsing
Device class APP quantity, client electric business class APP quantity, client financing class APP quantity, client borrow or lend money class APP quantity, Taobao month consumption
Volume average value, Taobao month amount of consumption maximum value, Taobao month amount of consumption minimum value, common reserve fund information etc. are numerous to list herein.
Step S2 builds prediction model online according to scorecard and indicator conditions, not according to different types of user structure
Same prediction model, same type of user build at least one prediction model.Same type user builds at least one pre-
Model is surveyed, same user information can be predicted using all prediction models under the user type, then more each mould
The prediction result of type.
In the present embodiment, user type includes：Personal user, enterprise customer.
Model construction is illustrated：
Model 1：
Regular 1==true-->Time limit=3-->Scorecard 1>60-->Interest rate=0.01, expense=20.
Regular 1==false-->Time limit=0 ... interest rate=0, expense=0.
Different user types build scorecard used when model or indicator conditions are different, and same user type structure is not
With used in model scorecard or indicator conditions it is also different.
Step S3, optimal prediction model：Influence of the indicator conditions different in prediction model to prediction model is tested, according to
Influence of each indicator conditions to prediction model adjusts prediction model.
Such as in model 1：
Regular 1==true-->Time limit=3-->Scorecard 1>60-->Interest rate=0.01, expense=20.By the value in time limit
After being modified or deleting this indicator conditions of time limit, brought into the different model 1 of duration value with the same user information, point
Prediction result is not obtained, to obtain influence of this indicator conditions of time limit to the prediction result of test model.Further, according to
The influence of indicator conditions adjusts prediction model, to debug out the optimal models for meeting business scenario.
Step S4 sets the use ratio of each prediction model for predicting same type of user.Due to same type
The prediction model of user is at least one, therefore, when in use, sets the use ratio of each prediction model.For example, one
The prediction model of type of user has 3, and the use ratio of setting model 1 is 30%, and the use ratio of model 2 is 20%, model 2
Use ratio be 50%, if then there is 10 users to carry out risk profiles, have 3 users and predicted using model 1,
2 users predict that 5 users are predicted using model 3 using model 2.Setting is for predicting same type of user
Each prediction model use ratio when, each prediction model is compared the prediction result of same user information, according to
Comparison result determines the use ratio of each prediction model.
Step S5, the index computation rule of the index value of each index of setup algorithm.By the finger by setting in user information
Mark computation rule calculates the index value of user.Such as in scorecard calculating, the regular 1 (age in indicator rule>20), according to
The data provided in user information use the index value that the age is obtained according to the index computation rule at age.
Step S6 brings user information into index computation rule and obtains index value, brought into accordingly according to obtained index value
Prediction model obtain prediction result, the product for meeting prediction result is matched according to prediction result and product information.To side
Just user selects suitable product, while also being filtered out for Products Information Releasing mechanism and meeting institutional risk grade, improves production
The conversion ratio of product improves the working efficiency of cooperative institution.
Index value is brought into prediction model, the calculating process of prediction model is identical as program when structure prediction model.Example
Such as：This index of has age in scorecard structure, uses according to the data provided in user information and calculates rule according to the index at age
The index value 21 for then obtaining the age calculates scorecard first when bringing this index value in prediction model into, and in scorecard
The rule of the index at age is the age>20, eligible, therefore, regular (age)==ture scores 10 are other in scorecard
Indicator rule is identical.
The user type that the prediction model that selection is predicted selects when being then according to user's input information determines.Such as：
When user inputs user information, selection is personal user, then when being predicted with prediction model, then can use personal user
Corresponding multiple prediction models, which prediction model under the personal user of selection, then according to the use of each prediction model ratio
Example is configured.
In the present embodiment, the user information filled in includes：Personal information, job information, electric business purchase information, reference number
According to, liability information, use facility information.Wherein, personal information includes the essential informations such as name, age.
In the present embodiment, product information includes：Name of product, product issue, product interest rate, air control condition and production
Product icon.
In the present embodiment, after obtaining prediction result, prediction result is shown.Cake is used when prediction result is shown
Figure, block diagram, linear graph or table form be shown.User can be seen that the product for oneself meeting which cooperative institution.
As shown in Fig. 2, consumer's risk forecasting system 200 includes input module 210, model construction module 220, memory module
230, index computing module 240, prediction module 250 and matching module 260.
Input module 210 is used to input user information, product information, the type for selecting user.
Model construction module 220 changes prediction model for building prediction model online.
Memory module 230 is for storing product information, prediction model.
Index computing module 240 is used to be based on pre-defined rule according to the user information of input to calculate each index value.
Prediction module 250 is used to select suitable prediction model according to the type of user, and index computing module 240 is obtained
Index value bring prediction model into and obtain prediction result.
Matching module 260 is used to according to prediction result and product information be the suitable product of user's matching.
In the present embodiment, consumer's risk forecasting system 200 further includes display module 270, and display module 270 is for showing
Prediction result and the matched product of user.
In the present embodiment, consumer's risk forecasting system includes 7 servers, user terminal, mechanism ends, and 7 servers are equal
6.5 systems of centos, 4 core 8G are installed.User terminal and mechanism end are as input module and display module.User terminal is for filling in
User information simultaneously selects user type, and mechanism end is used for release product information.User terminal, mechanism end and two first servers and
Four third server communication connections.Two first servers are used to collect the production of the information and cooperative institution's publication of user's submission
Product information.One second server is used as model construction, model modification and debugging.Another 4 third servers and two first
Server and a second server connection.Third server obtains the user information of two first servers, cooperative institution's hair
The prediction model of cloth product information, second server is brought into suitable according to user information parameter value according to user type
Prediction model is calculated, and the product for meeting user is matched according to prediction result and product information.When third server process
The mode of off-line calculation can be used.Obtained result is sent to user terminal, mechanism end by third server, and user passes through user terminal
It is known that meeting the product of oneself, mechanism is known that the user for meeting institutional risk by mechanism end.
The above embodiment is the preferred case of the present invention, is not intended to limit protection scope of the present invention.
Claims (9)
1. a kind of consumer's risk prediction technique, which is characterized in that include the following steps：
Scorecard is obtained based on pre-defined rule according to a plurality of index；
Prediction model is built online according to scorecard and indicator conditions, and different prediction moulds is built according to different types of user
Type, same type of user build at least one prediction model；
Optimal prediction model：Influence of the indicator conditions different in prediction model to prediction model is tested, according to each indicator conditions
Influence to prediction model adjusts prediction model；
Set the use ratio of each prediction model for predicting same type of user；
The index computation rule of the index value of each index of setup algorithm；
It brings user information into index computation rule and obtains index value, bringing corresponding prediction model into according to obtained index value obtains
To prediction result, the product for meeting prediction result is matched according to prediction result and product information.
2. consumer's risk prediction technique according to claim 1, it is characterised in that：
Wherein, when setting the use ratio of each prediction model for predicting same type of user, by each prediction model pair
The prediction result of same user information is compared, and the use ratio of each prediction model is determined according to comparison result.
3. consumer's risk prediction technique according to claim 1, it is characterised in that：
Wherein, after obtaining prediction result, prediction result is shown.
4. consumer's risk prediction technique according to claim 3, it is characterised in that：
Wherein, it is shown in the form of pie chart, block diagram, linear graph or table when prediction result being shown.
5. consumer's risk prediction technique according to claim 1, it is characterised in that：
Wherein, the product information includes：Name of product, product issue, product interest rate, air control condition and product icon.
6. consumer's risk prediction technique according to claim 1, it is characterised in that：
Wherein, the user information filled in includes：Personal information, job information, electric business purchase information, collage-credit data, liability information,
Use facility information.
7. consumer's risk prediction technique according to claim 1, it is characterised in that：
Wherein, the scorecard includes：Personal information scorecard, job information scorecard, electric business information scorecard, reference information
Scorecard, liability information scorecard, operator's informaiton scorecard.
8. a kind of consumer's risk forecasting system, which is characterized in that include：
Input module, for inputting user information, product information, the type for selecting user；
Model construction module, for building prediction model online；
Memory module, for storing product information, prediction model；
Index computing module is based on pre-defined rule according to the user information of input and calculates each index value；
Prediction module selects suitable prediction model, the index value that the index computing module is obtained according to the type of user
It brings the prediction model into and obtains prediction result；And
Matching module, for being the suitable product of user's matching according to prediction result and product information.
9. consumer's risk forecasting system according to claim 8, which is characterized in that also include：
Display module, for showing prediction result and the matched product of user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810347191.7A CN108537460A (en) | 2018-04-18 | 2018-04-18 | Consumer's risk prediction technique and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810347191.7A CN108537460A (en) | 2018-04-18 | 2018-04-18 | Consumer's risk prediction technique and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108537460A true CN108537460A (en) | 2018-09-14 |
Family
ID=63481407
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810347191.7A Pending CN108537460A (en) | 2018-04-18 | 2018-04-18 | Consumer's risk prediction technique and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108537460A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110222962A (en) * | 2019-05-24 | 2019-09-10 | 东方银谷(北京)科技发展有限公司 | Data configuration method and device for financial business risk control |
| CN110717821A (en) * | 2019-09-09 | 2020-01-21 | 上海凯京信达科技集团有限公司 | Vehicle loan assessment method and device, computer storage medium and electronic equipment |
| CN112085596A (en) * | 2020-09-27 | 2020-12-15 | 中国建设银行股份有限公司 | Method and device for determining user risk level information |
| CN112150277A (en) * | 2020-09-30 | 2020-12-29 | 中国银行股份有限公司 | Service data processing method, device, readable medium and equipment |
| CN112561685A (en) * | 2020-12-15 | 2021-03-26 | 建信金融科技有限责任公司 | Client classification method and device |
| CN112579047A (en) * | 2020-12-15 | 2021-03-30 | 安徽兆尹信息科技股份有限公司 | Model configuration method and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105590261A (en) * | 2014-12-31 | 2016-05-18 | 中国银联股份有限公司 | Merchant risk estimation method and system |
| CN106503873A (en) * | 2016-11-30 | 2017-03-15 | 腾云天宇科技（北京）有限公司 | A kind of prediction user follows treaty method, device and the computing device of probability |
| CN107436866A (en) * | 2016-05-25 | 2017-12-05 | 阿里巴巴集团控股有限公司 | The recommendation method and device of finance product |
| CN107730154A (en) * | 2017-11-23 | 2018-02-23 | 安趣盈（上海）投资咨询有限公司 | Based on the parallel air control application method of more machine learning models and system |
-
2018
- 2018-04-18 CN CN201810347191.7A patent/CN108537460A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105590261A (en) * | 2014-12-31 | 2016-05-18 | 中国银联股份有限公司 | Merchant risk estimation method and system |
| CN107436866A (en) * | 2016-05-25 | 2017-12-05 | 阿里巴巴集团控股有限公司 | The recommendation method and device of finance product |
| CN106503873A (en) * | 2016-11-30 | 2017-03-15 | 腾云天宇科技（北京）有限公司 | A kind of prediction user follows treaty method, device and the computing device of probability |
| CN107730154A (en) * | 2017-11-23 | 2018-02-23 | 安趣盈（上海）投资咨询有限公司 | Based on the parallel air control application method of more machine learning models and system |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110222962A (en) * | 2019-05-24 | 2019-09-10 | 东方银谷(北京)科技发展有限公司 | Data configuration method and device for financial business risk control |
| CN110717821A (en) * | 2019-09-09 | 2020-01-21 | 上海凯京信达科技集团有限公司 | Vehicle loan assessment method and device, computer storage medium and electronic equipment |
| CN112085596A (en) * | 2020-09-27 | 2020-12-15 | 中国建设银行股份有限公司 | Method and device for determining user risk level information |
| CN112150277A (en) * | 2020-09-30 | 2020-12-29 | 中国银行股份有限公司 | Service data processing method, device, readable medium and equipment |
| CN112150277B (en) * | 2020-09-30 | 2023-09-12 | 中国银行股份有限公司 | Service data processing method, device, readable medium and equipment |
| CN112561685A (en) * | 2020-12-15 | 2021-03-26 | 建信金融科技有限责任公司 | Client classification method and device |
| CN112579047A (en) * | 2020-12-15 | 2021-03-30 | 安徽兆尹信息科技股份有限公司 | Model configuration method and storage medium |
| CN112561685B (en) * | 2020-12-15 | 2023-10-17 | 建信金融科技有限责任公司 | Customer classification method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108537460A (en) | Consumer's risk prediction technique and system | |
| CN110033252A (en) | A kind of channel of disbursement recommended method and device | |
| CN107305679A (en) | Product data method of adjustment and device, a key method of adjustment and device | |
| CN106327196A (en) | Payment threshold acquisition method and device | |
| CN110111090A (en) | A kind of distribution method and device of electronics red packet | |
| CN110363661A (en) | Bank liquidity prediction technique and device | |
| US20190205978A1 (en) | Centralized model for lending risk management system | |
| CN110930038A (en) | Loan demand identification method, loan demand identification device, loan demand identification terminal and loan demand identification storage medium | |
| CN110135711A (en) | A kind of information management method and device | |
| CN110400184A (en) | Method and apparatus for generating information | |
| CN109034493A (en) | A kind of account balance prediction technique and device | |
| KR102092461B1 (en) | Method for providing investment success rate | |
| JP2016110610A (en) | Management support program | |
| CN113158124A (en) | Data processing method and device based on artificial intelligence and storage medium | |
| CN108985595A (en) | The move transaction service evaluation method and device mutually commented based on counterparty | |
| JP2017084229A (en) | Investment simulation device and method | |
| KR101927273B1 (en) | Risk value evaluating system for unclaimed construction and risk value evaluating apparatus for unclaimed construction | |
| CN110245985A (en) | A kind of information processing method and device | |
| JP2020035417A (en) | Banking business support system, banking business support method and banking business support program | |
| CN114581069A (en) | Minimum bill amount charging method and system based on API call amount | |
| Anfuso et al. | A sound Basel III compliant framework for backtesting credit exposure models | |
| CN111178744A (en) | Distribution method, device, equipment and storage medium | |
| CN111429251A (en) | Method and device for processing data under multiple modes | |
| CN112785451B (en) | Quantitative analysis method and device for oil and gas exploration effect | |
| TWI785419B (en) | Asset and liability simulation analysis system and method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 200433 room 8, 14 building, 18 Government Road, Yangpu District, Shanghai. Applicant after: Xin Yong computing power information technology (Shanghai) Co., Ltd. Address before: 200433 room 8, 14 building, 18 Government Road, Yangpu District, Shanghai. Applicant before: Shanghai Rong Jia Financial Information Service Co., Ltd. |
|
| 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: 20180914 |