CN113159460A - User data processing method and device, computer equipment and storage medium - Google Patents
User data processing method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN113159460A CN113159460A CN202110565066.5A CN202110565066A CN113159460A CN 113159460 A CN113159460 A CN 113159460A CN 202110565066 A CN202110565066 A CN 202110565066A CN 113159460 A CN113159460 A CN 113159460A
- Authority
- CN
- China
- Prior art keywords
- user
- data
- result
- user data
- real
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title abstract description 6
- 238000012545 processing Methods 0.000 claims abstract description 76
- 238000013507 mapping Methods 0.000 claims abstract description 9
- 238000000034 method Methods 0.000 claims description 51
- 238000004140 cleaning Methods 0.000 claims description 14
- 238000013144 data compression Methods 0.000 claims description 7
- 238000010586 diagram Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 6
- 238000011156 evaluation Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 239000000463 material Substances 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 239000000047 product Substances 0.000 description 3
- 239000008280 blood Substances 0.000 description 2
- 210000004369 blood Anatomy 0.000 description 2
- 238000013145 classification model Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 241000894007 species Species 0.000 description 2
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 description 1
- 241000700605 Viruses Species 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 239000008103 glucose Substances 0.000 description 1
- 230000008821 health effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000012954 risk control Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000009469 supplementation Effects 0.000 description 1
Images
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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06F16/906—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- G06Q40/08—Insurance
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Finance (AREA)
- Databases & Information Systems (AREA)
- Accounting & Taxation (AREA)
- Data Mining & Analysis (AREA)
- Technology Law (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of big data, can be applied to the field of smart cities, and discloses a user data processing method, a user data processing device, computer equipment and a storage medium. The user data processing method can comprise the following steps: receiving and reading user data formed based on an information filling mode, and acquiring offline feature data and real-time feature data which are in one-to-one correspondence with the user data according to the user data; performing feature classification on the current user according to the real-time feature data, the off-line feature data and the user data, and obtaining a user classification result; and acquiring a preset risk prediction result matched with the selection operation information of the current user, and mapping the user classification result and the preset risk prediction result to obtain a risk prediction result of the current user. According to the invention, the risk level of the user can be intelligently and accurately identified by classifying the user through various complex factors, and the user can be accurately analyzed and positioned.
Description
Technical Field
The present invention relates to the technical field of user big data processing, and more particularly, to a method, an apparatus, a computer device, and a storage medium for user data processing.
Background
With the rapid development of national economy, the consumption level of people is continuously improved, and thus a large amount of user data is generated. In order to fully utilize the data to provide better service for the user, the conventional technology largely depends on expert experience and parameters set by human subjectivity to perform data processing and analysis, so that the analysis and positioning of the user are often not accurate enough, the evaluation accuracy of the analysis result obtained based on the conventional technology to the user is lower, the product recommendation is generally not actually required by the user, and the user experience is poor. The reason for this is that the prior art cannot fully utilize the big data of the user, and needs to be improved or optimized urgently.
Disclosure of Invention
In order to solve at least one problem in the prior art, the invention can provide a method, a device, a computer device and a storage medium for processing user data, so as to achieve at least one technical purpose of more fully utilizing user big data, objectively and accurately evaluating user conditions and the like.
To achieve the above technical object, the present invention discloses a method for user data processing, which may include, but is not limited to, at least one of the following steps.
And receiving and reading user data formed based on the information filling mode.
And acquiring offline characteristic data and real-time characteristic data which are in one-to-one correspondence with the user data according to the user data.
And performing feature classification on the current user according to the real-time feature data, the off-line feature data and the user data, and obtaining a user classification result.
And acquiring a preset risk prediction result matched with the selection operation information of the current user.
And mapping the user classification result and the preset risk prediction result to obtain a risk prediction result of the current user.
Further, obtaining a risk prediction result of the current user further includes:
and generating a risk probability result of the current user according to the file uploaded by the user.
And determining the final judgment result of the current user based on the risk probability result and the risk prediction result.
Further, the files uploaded by the user comprise files in a picture format; the generating a risk probability result of the current user according to the file uploaded by the user may include:
and performing text recognition processing on the file in the picture format to extract user condition information.
And predicting the risk probability of the current user by taking the user condition information as a basis to generate a risk probability result of the current user.
Further, after determining the final judgment result of the current user, the method further includes:
and generating a recommendation message according to one or more of the user data, the offline feature data, the real-time feature data, the user classification result, the risk prediction result, the risk probability result and the final judgment result.
And pushing the recommendation message to the current user.
Further, before the feature classification of the current user, the method further includes:
and performing data cleaning processing on the real-time characteristic data, the off-line characteristic data and the user data at least once.
And performing missing value completion processing on the data subjected to the data cleaning processing.
Further, after the missing value completion processing is performed on the data subjected to the data cleansing processing, the method further includes:
and performing data compression processing on the data subjected to missing value completion processing.
Further, the obtaining of the offline feature data and the real-time feature data corresponding to the user data one to one according to the user data includes:
extracting basic parameter information from the user data.
And generating at least one retrieval condition by using the basic parameter information.
And searching a database for storing the feature data through the at least one search condition to obtain offline feature data and real-time feature data which are in one-to-one correspondence with the user data.
In order to achieve the above technical objectives, the present invention can also provide a device for processing user data, where the device for processing user data can include, but is not limited to, a user data acquisition module, a feature data acquisition module, a user feature classification module, and a preset result acquisition module.
And the user data acquisition module can be used for receiving and reading user data formed based on the information filling mode.
And the characteristic data acquisition module is used for acquiring offline characteristic data and real-time characteristic data which are in one-to-one correspondence with the user data according to the user data.
And the user characteristic classification module is used for carrying out characteristic classification on the current user according to the real-time characteristic data, the off-line characteristic data and the user data and obtaining a user classification result.
And the preset result acquisition module is used for acquiring a preset risk prediction result matched with the selection operation information of the current user.
And the prediction result generation module is used for mapping the user classification result and the preset risk prediction result to obtain a risk prediction result of the current user.
To achieve the above technical object, the present invention may also provide a computer device, which includes a memory and a processor, wherein the memory stores computer readable instructions, and the computer readable instructions, when executed by the processor, cause the processor to execute the steps of the method for processing user data in any embodiment of the present invention.
To achieve the above technical object, the present invention can also specifically provide a storage medium storing computer-readable instructions, which when executed by one or more processors, cause the one or more processors to execute the steps of the method for user data processing in any embodiment of the present invention.
The invention has the beneficial effects that:
the invention uses the data filled by the user, the off-line characteristic data and the real-time characteristic data, carries out the big data processing of the user based on the current filling data of the user and the data collected from multiple aspects, and has very large data dimension. According to the invention, based on real-time characteristic data, offline characteristic data and user classification results obtained by the data, the risk level of the user can be intelligently and accurately identified by classifying the user through various complex factors, effective analysis and accurate positioning of each user according to the big data of the user are realized, and the user data can be comprehensively and fully used. Particularly, the corresponding risk prediction results are matched according to the selection operation information of the user and are mapped with the classification results of the user, so that the intelligent and automatic judgment and identification can be carried out according to the current selection operation information of the user in combination with a specific service scene, and the accuracy of data analysis is greatly improved.
The method, the device, the computer equipment and the storage medium for processing the user data can be applied to the field of smart cities, so that the construction of the smart cities is promoted.
Drawings
FIG. 1 is a flow diagram illustrating a process for determining a current user risk prediction in one or more embodiments of the invention.
Fig. 2 shows a flow diagram of a method of user data processing in one or more embodiments of the invention.
FIG. 3 is a flow diagram illustrating a process for determining a final decision result of a current user in one or more embodiments of the invention.
Fig. 4 shows a flow diagram for implementing pushing a message to a current user in one or more embodiments of the invention.
Fig. 5 is a schematic structural diagram of an apparatus for processing user data according to one or more embodiments of the present invention.
FIG. 6 is a block diagram illustrating the internal architecture of a computing device in accordance with one or more embodiments of the invention.
FIG. 7 is a diagram of an environment for implementing a method for user data processing in one or more embodiments of the invention.
Detailed Description
The following explains and explains a method, an apparatus, a computer device, and a storage medium for user data processing in detail, which are provided by the present invention, in conjunction with the drawings of the specification.
As shown in fig. 1, one or more embodiments of the invention can provide a method of user data processing that can include, but is not limited to, one or more of the following.
And step 100, receiving and reading user data formed based on the information filling mode. The invention can provide a human-computer interaction interface for filling information for a user, wherein the filled information can include but is not limited to information submitted for the first time after the user completes filling, information submitted again after the submitted information is modified for one or more times, and the like. Specifically, the invention receives service request transaction information sent by a user through a terminal, and provides an initial application form or an intermediate application form with part of information filled in advance and other forms to be filled in for the user on a man-machine interaction interface of the terminal according to the service request transaction information; after filling the form content, the user can send a submission request through the terminal. The present invention may form structured data, i.e. current user data, based on the content filled in the form.
In some application scenarios of the present invention, the transaction-requesting service may be an application request service. The form to be filled in is an application request form. The information to be filled in the form includes, but is not limited to, the name, age, identification number, mobile phone number, driver's license number, address, income, physical condition, height, weight, marital-related condition, family-related condition, asset-related condition, tax-related condition, credit-related condition, historical insurance condition, personal or family disease history, blood type, constellation and the like of the user.
And 200, acquiring offline feature data and real-time feature data which are in one-to-one correspondence with the user data according to the user data. The off-line characteristic data and the real-time characteristic data are data which are widely collected in advance, the off-line characteristic data are used for representing the characteristics of a user which are relatively stable and unchangeable for a long time, the real-time characteristic data can be used for representing the behavior characteristics of the user within a current set time period, and the off-line characteristic data and the real-time characteristic data of each user are stored in a specified database.
Specifically, some embodiments of the present invention, obtaining the offline feature data and the real-time feature data corresponding to the user data one to one according to the user data includes: extracting basic parameter information from the user data, wherein the basic parameter information can be used for representing the identity of the current user, and the basic parameter information comprises at least one of the name, the identity card number, the mobile phone number, the driving license number, fingerprint information, face identification information and iris identification information of the user; generating one or more retrieval conditions by using the basic parameter information, wherein the retrieval conditions can be a complex retrieval formula or a series of character strings or binary codes, for example, namely the retrieval conditions can include but are not limited to coding expressions, character string expressions or combinations thereof; and searching the database for storing the characteristic data through at least one search condition to obtain the offline characteristic data and the real-time characteristic data which are matched with the basic parameter information, namely obtaining the offline characteristic data and the real-time characteristic data which are in one-to-one correspondence with the current user data. According to the invention, the offline characteristic data and the real-time characteristic data of the current user can be accurately and quickly matched based on the information filled by the user, so that accurate data is provided for the next big data processing process of the user; particularly, when a plurality of user related data are processed simultaneously, the data retrieval efficiency of the current user can be obviously improved.
In some application scenarios of the present invention, for example, in a user insurance application scenario, the offline feature data may include, but is not limited to, basic information of an applicant, historical insurance application information of the applicant, historical insurance exposure information of an insurance application organization, historical claim settlement information of a seller corresponding to an insurance policy, health activity information of the applicant, keyword search records of the insurance field of the applicant on the internet, and the like, and the real-time feature data may include, but is not limited to, information of records of dangerous species that a user attempts to apply insurance in six months, information of changes of the amount of insurance application in the last five insurance applications, information of communication times with a seller in the last three months, and the like.
As shown in FIG. 2, some preferred embodiments of the present invention include steps 201-203 to pre-process the obtained data. Step 201, performing data cleaning processing on the real-time characteristic data, the offline characteristic data and the user data at least once to remove data which do not meet requirements, such as redundant data and data obviously exceeding a set threshold value, in the data, so as to improve the rationality and accuracy of a subsequent judgment process. Step 202, missing value completion processing is performed on the data subjected to the data cleaning processing so as to complete the missing value in the current data. In some embodiments of the present invention, the missing value completion processing may adopt an intermediate value filling manner or perform filling by matching, from a cloud, related data of a user with a higher similarity to the current user. In step 203, data compression processing is performed on the data subjected to missing value completion processing, so as to reduce the pressure of the server for performing data processing, increase the data loading speed of the server memory, and increase the data processing speed.
And step 300, performing feature classification on the current user according to the real-time feature data, the offline feature data and the user data, and obtaining a user classification result. Some embodiments of the invention may use a trained classification model including, but not limited to, at least one of an LR model, an XGBoost model to rapidly classify a current user based on real-time feature data, offline feature data, and user data. The present invention can output the range value corresponding to the current user by using the classification model, i.e. the user classification result can be, for example, a range value.
In a user insurance application scene, if the selected operation information is 100 thousands of insurance application amount, the preset risk prediction result may include high risk, high and medium risk, medium and low risk, and if the selected operation information is 5 thousands of insurance application amount, the preset risk prediction result may include high risk and low risk.
And 500, mapping the user classification result with a preset risk prediction result to obtain a risk prediction result of the current user. Specifically, the method and the device can label the user according to the range value representing the classification result of the user, wherein the specific content of the label is the preset risk prediction result. For example, if the corresponding label is high risk when the range value is S1, the risk prediction result of the current user is specifically high risk; if the label corresponding to the range value S2 is low risk, the risk prediction result of the current user is specifically low risk.
Under the condition of user insurance, for different dangerous situations selected by the current user, the same user classification result of the invention can map different risk prediction results. Therefore, the data processing mode of the invention is more reasonable, and the insurance risk of the user can be more accurately evaluated.
And step 600, generating a risk probability result of the current user according to the file uploaded by the user. The process of uploading the file can be carried out in the step of filling out information by the user or separately.
Further, the files uploaded by the user include files in a picture format; for the uploaded file in the picture format, in some embodiments of the present invention, generating a risk probability result of the current user according to the file uploaded by the user may include: performing text recognition processing on the file in the picture format to extract user condition information, for example, performing high-precision recognition on characters in the picture file by using an image text detection algorithm such as FOTS or PSENet; and predicting the risk probability of the current user according to the user condition information to generate a risk probability result of the current user, for example, predicting the risk probability by using at least one model of GBDT + LR, LightGBM and gcForest which are trained. The risk probability result of the present invention can be a specific value, such as any value between 0-100%. The invention can realize the visualized judgment of the user condition through the risk prediction result and realize the quantitative judgment of the user condition through the risk probability result.
Under the user insurance application scene, the basic score of the user can be increased or decreased through the trained model based on the user condition information. For example, the basic score of the user is set to 50%, and if the identified user condition information includes that the fixed asset amount exceeds five million, the score is reduced by 15% and becomes 35%, and if the identified user condition information also includes that the health notification information is a virus carrier, the score is increased by 30% and becomes 65%. In some embodiments of the present invention, the files uploaded by the user may include, but are not limited to, asset certification files, credit certification files, relevant diagnosis non-sensitive information reports, and the like, and the extracted user situation information may include, but is not limited to, asset certification validity information, asset amount, credit, physical examination letter information, health notification information, blood glucose value, relevant modification record information, and the like.
The invention comprehensively considers the unnecessary material information of the user and realizes the auxiliary control of the risk. By means of a text recognition technology, a machine learning technology and the like, the risk probability of the current user can be determined by fully utilizing unnecessary information related materials uploaded by the user. Under the condition of underwriting wind control, the invention can effectively avoid the condition that the user is refused to be guaranteed due to the operation of false report or false report and the like which are carried out because of lack of related insurance basic knowledge and insurance law common knowledge by adopting the auxiliary risk control means, and can also effectively avoid the condition that the user is directly refused to be guaranteed due to the condition that the user is re-insured or re-insured with other dangerous species and the like after completing corresponding data supplement and modification.
As shown in fig. 3, one or more embodiments of the present invention further include the steps of generating a final judgment result and outputting the final judgment result, which may be output to the user terminal.
And 700, determining the final judgment result of the current user based on the risk probability result and the risk prediction result. And the final judgment result is used for representing the comprehensive risk evaluation result of the current user. Under the user insurance application scene, the risk comprehensive assessment result can comprise passing and not passing, namely underwriting, and not passing or refusing. In specific implementation, the user can view the displayed final judgment result on the human-computer interaction interface operated previously, for example, the result may be that the underwriting passes (underwriting) or that the underwriting does not pass (refusing). For example, if the risk prediction result is medium risk and the risk probability result is 35%, the risk comprehensive evaluation result is pass; for example, if the risk prediction result is high risk and the risk probability result is 51%, the risk comprehensive evaluation result is failure; for example, if the risk prediction result is low risk and the risk probability result is 58%, the risk comprehensive assessment result is pass. It should be understood that if the risk prediction result is too different from the risk probability result, for example, the risk prediction result is a high risk and the risk probability result is 8%, the data source may be checked according to actual conditions or a worker may be notified to perform manual evaluation and judgment separately. Therefore, under the wind control scene of the underwriting, the method and the device can comprehensively judge the risk level and the risk probability of the current user, and synthesize the two results to give the final accurate judgment, namely underwriting or refusing to ensure, so that the user experience is very good.
As shown in fig. 4, one or more embodiments of the present invention include the following steps for generating and pushing recommendation messages.
And 800, generating a recommendation message according to one or more of the user data, the offline feature data, the real-time feature data, the user classification result, the risk prediction result, the risk probability result and the final judgment result, and pushing the recommendation message to the current user. Some embodiments of the present invention can generate the recommendation message by data analysis, for example, the recommendation message can be automatically generated by data processing and analysis by using algorithms such as Word2vec and Item2 vec. The invention can intelligently recommend acceptable products or services for the user based on the user data and the related information of risk prediction, and can recommend and provide an acceptable and reasonable insurance plan scheme for the user on the premise of assuming insurance expense, insurance payment frequency, specific insurance coverage and the like in the insurance application scene. Therefore, the method and the device can push the recommendation messages matched with the requirements of different users to avoid the disturbance of useless recommendation messages to the users, thereby greatly improving the satisfaction degree of the users and improving the user experience, and have very large market potential. The invention can realize the pushing of the insurance plans of thousands of people under the insurance application scene, for example, a part of short-term insurance experience plans are provided for potential new users, and long-term auxiliary insurance plans are provided for old users.
Therefore, the method and the device can also push the recommendation message matched with the user requirement for the user, and avoid the disturbance of useless recommendation message to the user, thereby greatly improving the user satisfaction degree, further improving the user experience, and having huge market potential and wide market prospect.
As shown in fig. 5, the present invention can provide a user data processing apparatus according to one or more embodiments based on the same technical concept as the user data processing method. Further, the device for processing user data may include, but is not limited to, a user data acquisition module, a feature data acquisition module, a user feature classification module, a preset result acquisition module, a predicted result generation module, a risk probability determination module, a final result determination module, and a recommendation message pushing module.
The user data acquisition module can be used for receiving and reading user data formed based on the information filling mode.
The characteristic data acquisition module can be used for acquiring offline characteristic data and real-time characteristic data which are in one-to-one correspondence with the user data according to the user data. More specifically, the feature data acquisition module is configured to extract basic parameter information from the user data, generate at least one search condition using the basic parameter information, and search the database for storing the feature data through the at least one search condition to obtain offline feature data and real-time feature data corresponding to the acquired current user data one to one.
The device for processing user data of some embodiments of the present invention can further include a data cleaning module, a data repairing module, a data compressing module, and the like.
The data cleaning module is used for performing data cleaning processing on the real-time characteristic data, the off-line characteristic data and the user data at least once.
And the data repairing module is used for performing missing value completion processing on the data subjected to the data cleaning processing.
And the data compression module is used for performing data compression processing on the data subjected to missing value completion processing.
The user characteristic classification module can be used for carrying out characteristic classification on the current user according to the real-time characteristic data, the off-line characteristic data and the user data, and obtaining a user classification result.
The preset result obtaining module can be used for obtaining a preset risk prediction result matched with the selection operation information of the current user.
The prediction result generation module can be used for mapping the user classification result with a preset risk prediction result to obtain a risk prediction result of the current user.
And the risk probability determination module is used for generating a risk probability result of the current user according to the file uploaded by the user. Specifically, the files uploaded by the user include files in a picture format; the risk probability determination module can be used for carrying out text recognition processing on the file in the picture format so as to extract user condition information; the risk probability determination module is used for predicting the risk probability of the current user according to the current user condition information so as to generate a risk probability result of the current user.
And the final result determining module is used for jointly determining the final judgment result of the current user based on the risk probability result and the risk prediction result. The method can process the big data of the user based on the current reported data of the user and data collected from multiple aspects, has very large data dimension, can intelligently and accurately identify the risk level of the user by classifying the user through multiple complex factors, and realizes effective analysis and accurate positioning of each user according to the big data of the user, thereby being capable of comprehensively and fully using the user data. Particularly, the invention can also be combined with specific service scenes and intelligently and automatically judge and identify according to the current selection condition of the user, thereby greatly improving the accuracy of data analysis. The invention can realize the visualized judgment of the user condition through the risk prediction result and realize the quantitative judgment of the user condition through the risk probability result. Under the wind control scene of the underwriting, the method and the device can comprehensively judge the risk level and the risk probability of the current user, and synthesize the two results to give final accurate judgment, namely underwriting or refusing to ensure, so that the user experience is very good. The method and the device can also push the recommendation message matched with the user requirement for the user, and avoid the disturbance of useless recommendation message to the user, thereby greatly improving the user satisfaction, further improving the user experience, and having great market potential.
The recommendation message pushing module is used for generating a recommendation message according to one or more of the user data, the offline feature data, the real-time feature data, the user classification result, the risk prediction result, the risk probability result and the final judgment result, and is also used for pushing the recommendation message to the current user. The method and the system intelligently recommend acceptable products or services for the user based on the user data and the relevant risk prediction information, and under the insurance application scene, the method and the system can recommend and provide an acceptable and reasonable insurance plan scheme for the user on the premise of assuming insurance expense, insurance payment frequency, specific insurance coverage and the like. Therefore, the method and the device can push the recommendation messages matched with the requirements of different users to avoid the disturbance of useless recommendation messages to the users, thereby greatly improving the satisfaction degree of the users and improving the user experience, and have very large market potential. The invention can realize the pushing of the insurance plans of thousands of people under the insurance application scene, for example, a part of short-term insurance experience plans are provided for potential new users, and long-term auxiliary insurance plans are provided for old users.
As shown in fig. 6, one or more embodiments of the invention can provide a computer device that can include a memory and a processor, the memory having stored therein computer-readable instructions that, when executed by the processor, cause the processor to perform the steps of the method of user data processing in any of the embodiments of the invention. The method of user data processing may include, but is not limited to, at least one of the following: and step 100, receiving and reading user data formed based on the information filling mode. And 200, acquiring offline feature data and real-time feature data which are in one-to-one correspondence with the user data according to the user data. Specifically, some embodiments of the present invention, obtaining the offline feature data and the real-time feature data corresponding to the user data one to one according to the user data includes: extracting basic parameter information from the user data, and generating at least one retrieval condition by using the basic parameter information; and searching the database for storing the characteristic data through at least one search condition to obtain the off-line characteristic data and the real-time characteristic data which are in one-to-one correspondence with the user data. Some preferred embodiments of the present invention include steps 201-203. Step 201, performing data cleaning processing on the real-time characteristic data, the off-line characteristic data and the user data at least once; step 202, performing missing value completion processing on the data subjected to the data cleaning processing; step 203, performing data compression processing on the data subjected to missing value completion processing. And step 300, performing feature classification on the current user according to the real-time feature data, the offline feature data and the user data, and obtaining a user classification result. And 400, acquiring a preset risk prediction result matched with the selection operation information of the current user. And 500, mapping the user classification result with a preset risk prediction result to obtain a risk prediction result of the current user. And step 600, generating a risk probability result of the current user according to the file uploaded by the user. Further, the files uploaded by the user include files in a picture format; for the uploaded files in the picture format, the method for generating the risk probability result of the current user according to the files uploaded by the user comprises the following steps: performing text recognition processing on the file in the picture format to extract user condition information; and predicting the risk probability of the current user by taking the user condition information as a basis to generate a risk probability result of the current user. And 700, determining the final judgment result of the current user based on the risk probability result and the risk prediction result. Step 800, generating a recommendation message according to one or more of the user data, the offline feature data, the real-time feature data, the user classification result, the risk prediction result, the risk probability result and the final judgment result, and pushing the recommendation message to the current user.
As shown in fig. 6, one or more embodiments of the invention can also provide a storage medium storing computer-readable instructions which, when executed by one or more processors, cause the one or more processors to perform the steps of the method of user data processing in any of the embodiments of the invention. The method of user data processing may include, but is not limited to, at least one of the following: and step 100, receiving and reading user data formed based on the information filling mode. And 200, acquiring offline feature data and real-time feature data which are in one-to-one correspondence with the user data according to the user data. Specifically, some embodiments of the present invention, obtaining the offline feature data and the real-time feature data corresponding to the user data one to one according to the user data includes: extracting basic parameter information from the user data, and generating at least one retrieval condition by using the basic parameter information; and searching the database for storing the characteristic data through at least one search condition to obtain the off-line characteristic data and the real-time characteristic data which are in one-to-one correspondence with the user data. Some preferred embodiments of the present invention include steps 201-203. Step 201, performing data cleaning processing on the real-time characteristic data, the off-line characteristic data and the user data at least once; step 202, performing missing value completion processing on the data subjected to the data cleaning processing; step 203, performing data compression processing on the data subjected to missing value completion processing. And step 300, performing feature classification on the current user according to the real-time feature data, the offline feature data and the user data, and obtaining a user classification result. And 400, acquiring a preset risk prediction result matched with the selection operation information of the current user. And 500, mapping the user classification result with a preset risk prediction result to obtain a risk prediction result of the current user. And step 600, generating a risk probability result of the current user according to the file uploaded by the user. Further, the files uploaded by the user include files in a picture format; for the uploaded files in the picture format, the method for generating the risk probability result of the current user according to the files uploaded by the user comprises the following steps: performing text recognition processing on the file in the picture format to extract user condition information; and predicting the risk probability of the current user by taking the user condition information as a basis to generate a risk probability result of the current user. And 700, determining the final judgment result of the current user based on the risk probability result and the risk prediction result. Step 800, generating a recommendation message according to one or more of the user data, the offline feature data, the real-time feature data, the user classification result, the risk prediction result, the risk probability result and the final judgment result, and pushing the recommendation message to the current user.
It should be understood that the method, the apparatus, the computer device and the storage medium for processing user data provided by the technical solution of the present invention can be applied to the field of smart cities, thereby promoting the construction of smart cities.
It should be noted that, as shown in fig. 7, the terminal and the computer device may be a smart phone, a tablet computer, a notebook computer, a desktop computer, and the like, but are not limited thereto. The computer device and the terminal may be connected through bluetooth, USB (Universal Serial Bus), or other communication connection methods, which is not limited herein. The computer device includes a processor, a non-volatile storage medium, a memory, and a network interface that may be connected by a system bus. The non-volatile storage medium of the computer device stores an operating system, a database and computer readable instructions, the database can store control information sequences, and the computer readable instructions can enable the processor to realize a user data processing method when being executed by the processor. The processor of the computer device is used for providing calculation and control capability and supporting the operation of the whole computer device. The memory of the computer device may have stored therein computer readable instructions that, when executed by the processor, may cause the processor to perform a method of user data processing. The network interface of the computer device is used for connecting and communicating with the terminal. It will be appreciated by those skilled in the art that the configurations shown in the figures are block diagrams of only some of the configurations relevant to the present application, and do not constitute a limitation on the computing devices to which the present application may be applied, and that a particular computing device may include more or less components than those shown in the figures, or may combine certain components, or have a different arrangement of components.
The logic and/or steps represented in the flowcharts or otherwise described herein, such as an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable storage medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable storage medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer cartridge (magnetic device), a Random Access Memory (RAM), a Read-Only Memory (ROM), an Erasable Programmable Read-Only Memory (EPROM-Only Memory, or flash Memory), an optical fiber device, and a portable Compact Disc Read-Only Memory (CDROM). Additionally, the computer-readable storage medium may even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic Gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic Gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
In the description herein, references to the description of the term "the present embodiment," "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and simplifications made in the spirit of the present invention are intended to be included in the scope of the present invention.
Claims (10)
1. A method of user data processing, comprising:
receiving and reading user data formed based on the information filling mode;
acquiring offline feature data and real-time feature data which are in one-to-one correspondence with the user data according to the user data;
performing feature classification on the current user according to the real-time feature data, the offline feature data and the user data, and obtaining a user classification result;
acquiring a preset risk prediction result matched with the selection operation information of the current user;
and mapping the user classification result and the preset risk prediction result to obtain a risk prediction result of the current user.
2. The method of claim 1, wherein obtaining the risk prediction result of the current user further comprises:
generating a risk probability result of the current user according to the file uploaded by the user;
and determining the final judgment result of the current user based on the risk probability result and the risk prediction result.
3. The method of claim 2, wherein the files uploaded by the user comprise files in a picture format; the generating of the risk probability result of the current user according to the file uploaded by the user comprises the following steps:
performing text recognition processing on the file in the picture format to extract user condition information;
and predicting the risk probability of the current user by taking the user condition information as a basis to generate a risk probability result of the current user.
4. The method according to claim 2, wherein the determining the final determination result of the current user further comprises:
and generating a recommendation message according to one or more of the user data, the offline feature data, the real-time feature data, the user classification result, the risk prediction result, the risk probability result and the final judgment result, and pushing the recommendation message to the current user.
5. The method of claim 1, wherein the classifying the current user further comprises:
performing data cleaning processing on the real-time characteristic data, the off-line characteristic data and the user data at least once;
and performing missing value completion processing on the data subjected to the data cleaning processing.
6. The method according to claim 5, wherein the performing missing value completion processing on the data subjected to the data cleansing processing further comprises:
and performing data compression processing on the data subjected to missing value completion processing.
7. The method according to claim 1, wherein the obtaining of the offline feature data and the real-time feature data corresponding to the user data one to one according to the user data comprises:
extracting basic parameter information from the user data;
generating at least one retrieval condition by using the basic parameter information;
and searching a database for storing the feature data through the at least one search condition to obtain offline feature data and real-time feature data which are in one-to-one correspondence with the user data.
8. An apparatus for user data processing, comprising:
the user data acquisition module is used for receiving and reading user data formed based on the information filling mode;
the characteristic data acquisition module is used for acquiring offline characteristic data and real-time characteristic data which are in one-to-one correspondence with the user data according to the user data;
the user characteristic classification module is used for carrying out characteristic classification on the current user according to the real-time characteristic data, the off-line characteristic data and the user data and obtaining a user classification result;
the preset result acquisition module is used for acquiring a preset risk prediction result matched with the selection operation information of the current user;
and the prediction result generation module is used for mapping the user classification result and the preset risk prediction result to obtain a risk prediction result of the current user.
9. A computer device comprising a memory and a processor, the memory having stored therein computer-readable instructions which, when executed by the processor, cause the processor to carry out the steps of the method of user data processing according to any one of claims 1 to 7.
10. A storage medium having computer-readable instructions stored thereon, which, when executed by one or more processors, cause the one or more processors to perform the steps of the method of user data processing according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110565066.5A CN113159460A (en) | 2021-05-24 | 2021-05-24 | User data processing method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110565066.5A CN113159460A (en) | 2021-05-24 | 2021-05-24 | User data processing method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113159460A true CN113159460A (en) | 2021-07-23 |
Family
ID=76877087
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110565066.5A Pending CN113159460A (en) | 2021-05-24 | 2021-05-24 | User data processing method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113159460A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112037039A (en) * | 2020-09-02 | 2020-12-04 | 中国银行股份有限公司 | Loan assessment method and device |
| CN112199575A (en) * | 2020-10-09 | 2021-01-08 | 深圳壹账通智能科技有限公司 | Virtual bank account opening method, device, equipment and computer storage medium |
| CN112529716A (en) * | 2020-12-07 | 2021-03-19 | 平安科技（深圳）有限公司 | Quota prediction method, device and computer readable storage medium |
-
2021
- 2021-05-24 CN CN202110565066.5A patent/CN113159460A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112037039A (en) * | 2020-09-02 | 2020-12-04 | 中国银行股份有限公司 | Loan assessment method and device |
| CN112199575A (en) * | 2020-10-09 | 2021-01-08 | 深圳壹账通智能科技有限公司 | Virtual bank account opening method, device, equipment and computer storage medium |
| CN112529716A (en) * | 2020-12-07 | 2021-03-19 | 平安科技（深圳）有限公司 | Quota prediction method, device and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110070391B (en) | Data processing method and device, computer readable medium and electronic equipment | |
| US20240153079A1 (en) | System to collect and identify medical conditions from images and expert knowledge | |
| CN109829629B (en) | Risk analysis report generation method, apparatus, computer device and storage medium | |
| CN111861768B (en) | Service processing method and device based on artificial intelligence, computer equipment and medium | |
| CN110910257A (en) | Information prediction method, information prediction device, electronic equipment and computer readable medium | |
| CN114334169B (en) | Medical object category decision method and device, electronic equipment and storage medium | |
| CN113435998B (en) | Loan overdue prediction method and device, electronic equipment and storage medium | |
| CN110781380A (en) | Information pushing method and device, computer equipment and storage medium | |
| CN111696656B (en) | Doctor evaluation method and device of Internet medical platform | |
| CN111190946A (en) | Report generation method and device, computer equipment and storage medium | |
| CN112201359A (en) | Artificial intelligence-based critical illness inquiry data identification method and device | |
| CN113707296B (en) | Medical scheme data processing method, device, equipment and storage medium | |
| CN114756669A (en) | Intelligent analysis method and device for problem intention, electronic equipment and storage medium | |
| CN114372532A (en) | Method, device, equipment, medium and product for determining label marking quality | |
| CN113707304A (en) | Triage data processing method, device, equipment and storage medium | |
| CN113298495A (en) | Resume screening method, resume screening device, terminal device and storage medium | |
| CN112634017A (en) | Remote card opening activation method and device, electronic equipment and computer storage medium | |
| CN111784506A (en) | Overdue risk control method, device and readable storage medium | |
| CN116863116A (en) | Image recognition method, device, equipment and medium based on artificial intelligence | |
| CN113159460A (en) | User data processing method and device, computer equipment and storage medium | |
| CN112084408B (en) | List data screening method, device, computer equipment and storage medium | |
| CN113902576A (en) | Deep learning-based information pushing method and device, electronic equipment and medium | |
| CN113870983A (en) | Social health transfer method, device, computer equipment and storage medium | |
| Mahalle et al. | Data Acquisition and Preparation | |
| CN113688854A (en) | Data processing method and device and computing equipment |
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: 20210723 |