CN110782277A - Resource processing method, resource processing device, computer equipment and storage medium - Google Patents

Resource processing method, resource processing device, computer equipment and storage medium Download PDF

Info

Publication number
CN110782277A
CN110782277A CN201910969537.1A CN201910969537A CN110782277A CN 110782277 A CN110782277 A CN 110782277A CN 201910969537 A CN201910969537 A CN 201910969537A CN 110782277 A CN110782277 A CN 110782277A
Authority
CN
China
Prior art keywords
resource
target
historical
prediction model
vector
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
Application number
CN201910969537.1A
Other languages
Chinese (zh)
Inventor
覃德
颜健
张小云
梁树峰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Weikun Shanghai Technology Service Co Ltd
Original Assignee
Lujiazui Shanghai International Financial Assets Market Ltd By Share Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Lujiazui Shanghai International Financial Assets Market Ltd By Share Ltd filed Critical Lujiazui Shanghai International Financial Assets Market Ltd By Share Ltd
Priority to CN201910969537.1A priority Critical patent/CN110782277A/en
Publication of CN110782277A publication Critical patent/CN110782277A/en
Pending legal-status Critical Current

Links

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
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
    • G06Q30/0224—Discounts or incentives, e.g. coupons or rebates based on user history
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
    • G06Q30/0222—During e-commerce, i.e. online transactions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
    • G06Q30/0236—Incentive or reward received by requiring registration or ID from user
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
    • G06Q30/0239—Online discounts or incentives
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14—Network analysis or design
    • H04L41/147—Network analysis or design for predicting network behaviour
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L63/00—Network architectures or network communication protocols for network security
    • H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
    • H04L63/0815—Network architectures or network communication protocols for network security for authentication of entities providing single-sign-on or federations
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L63/00—Network architectures or network communication protocols for network security
    • H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
    • H04L63/0876—Network architectures or network communication protocols for network security for authentication of entities based on the identity of the terminal or configuration, e.g. MAC address, hardware or software configuration or device fingerprint

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Hardware Design (AREA)
  • Computer Security & Cryptography (AREA)
  • Software Systems (AREA)
  • Power Engineering (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Mathematical Physics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application relates to machine learning and provides a resource processing method, a resource processing device, a computer device and a storage medium. The method comprises the following steps: detecting whether the user identification is associated with the resource storage account identification, and acquiring login information corresponding to the user identification when the user identification is associated with the resource storage account identification; verifying the login information, and acquiring corresponding behavior data and basic data according to the user identification when the login information passes verification; performing dimensionality reduction on the behavior data and the basic data to obtain dimensionality-reduced features and corresponding feature importance, determining and extracting target features according to the feature importance, and encoding the target features to obtain target feature vectors; inputting the target characteristic vector into a trained resource usage prediction model to obtain a prediction result vector; and obtaining a resource prediction use result according to the prediction result vector, obtaining a target resource value according to the resource prediction use result, and transferring the target resource value to a terminal corresponding to the user identifier. By adopting the method, the pressure of the server can be reduced, and resources are saved.

Description

Resource processing method, resource processing device, computer equipment and storage medium
Technical Field
The present application relates to the field of internet technologies, and in particular, to a resource processing method and apparatus, a computer device, and a storage medium.
Background
With the rapid development of internet technology, websites generally transfer initial resources to users, and the positivity of users in using websites is improved. Currently, the website is used to directly issue initial resources to the user's hands when each user is successfully registered. However, this approach may result in a large number of "wool parties" to acquire the initial resources, may cause server stress in a short time, and may waste a large amount of resources.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a resource processing method, device, computer device, and storage medium capable of reducing server stress and node resources.
A method of resource processing, the method comprising:
detecting whether the user identification is associated with the resource storage account identification, and acquiring login information corresponding to the user identification when the user identification is associated with the resource storage account identification;
verifying the login information, and acquiring corresponding behavior data and basic data according to the user identification when the login information passes verification;
performing dimensionality reduction on the behavior data and the basic data to obtain dimensionality-reduced features and corresponding feature importance, determining target features according to the feature importance, and encoding the target features to obtain target feature vectors;
inputting the target characteristic vector into a trained resource usage prediction model to obtain a prediction result vector;
and obtaining a resource prediction use result according to the prediction result vector, obtaining a target resource value according to the resource prediction use result, and transferring the target resource value to a terminal corresponding to the user identifier.
In one embodiment, before detecting whether the user identifier is associated with the resource storage account identifier, and when the user identifier is associated with the resource storage account identifier, acquiring login information corresponding to the user identifier, the method further includes:
receiving an identification verification instruction, wherein the identification verification instruction carries a resource storage account identification, and sending a verification request to a resource storage server according to the identification verification instruction, and the resource storage server is used for verifying the resource storage account identification to generate verification passing information;
and acquiring verification passing information of the resource storage account identifier returned by the resource storage server, acquiring a user identifier according to the verification passing information of the resource storage account identifier, and associating the user identifier with the resource storage account identifier.
In one embodiment, obtaining a resource predicted use result according to the prediction result vector, obtaining a target resource value according to the resource predicted use result, and transferring the target resource value to a terminal corresponding to the user identifier includes:
and acquiring a corresponding key according to the target resource value, encrypting the target resource value by using the key to obtain an encrypted target resource value, and transferring the encrypted target resource value to a terminal corresponding to the user identifier.
In one embodiment, the step of generating the trained resource usage prediction model comprises:
acquiring historical behavior data and historical basic data corresponding to historical user identification, and performing feature selection according to the historical behavior data and the historical basic data to obtain initial features;
performing feature screening on the initial features according to the importance and the missing rate of the initial features to obtain target historical features, acquiring target historical data corresponding to the target historical features, and preprocessing the target historical data to obtain target historical feature vectors;
acquiring a historical resource use value corresponding to a historical user identifier, and coding the historical resource use value to obtain a historical result vector;
and taking the target historical characteristic vector as input, taking the historical result vector as a label, and training by using a machine learning algorithm model to obtain a trained resource use prediction model.
In one embodiment, the training using the machine learning algorithm model with the target historical feature vector as input and the historical result vector as a label to obtain the trained resource usage prediction model comprises:
inputting the target historical characteristic vector and the historical result vector into a logistic regression algorithm model for training to obtain a first resource use prediction model;
inputting the target historical characteristic vector and the historical result vector into a decision tree model for training to obtain a second resource use prediction model;
inputting the target historical characteristic vector and the historical result vector into a neural network model for training to obtain a third resource use prediction model;
the trained resource usage prediction model is derived from the first resource usage prediction model, the second resource usage prediction model, and the third resource usage prediction model.
In one embodiment, after the target historical feature vector is used as an input, the historical result vector is used as a label, and the machine learning algorithm model is used for training to obtain the trained resource usage prediction model, the method further includes:
and calling an importance interface to obtain the feature importance corresponding to the target historical feature, and returning the target historical feature and the feature importance to the target terminal for displaying.
In one embodiment, after the target historical feature vector is used as an input, the historical result vector is used as a label, and the machine learning algorithm model is used for training to obtain the trained resource usage prediction model, the method further includes:
the resource usage prediction model file in the preset file format is obtained, the resource usage prediction model file in the preset file format is converted into a resource usage prediction model file in a target file format, and the resource usage prediction model file in the target file format is loaded to obtain a resource usage prediction model.
An apparatus for resource handling, the apparatus comprising:
the system comprises an association detection module, a resource storage account identification and a login information acquisition module, wherein the association detection module is used for detecting whether the user identification is associated with the resource storage account identification or not, and acquiring login information corresponding to the user identification when the user identification is associated with the resource storage account identification;
the data acquisition module is used for verifying login information, and acquiring corresponding behavior data and basic data according to the user identification when the login information passes verification;
the characteristic extraction module is used for reducing the dimensions of the behavior data and the basic data to obtain the reduced-dimension characteristics and the corresponding characteristic importance, determining the target characteristics according to the characteristic importance and coding the target characteristics to obtain target characteristic vectors;
the prediction module is used for inputting the target characteristic vector into the trained resource use prediction model to obtain a prediction result vector;
and the resource transfer module is used for obtaining a resource prediction use result according to the prediction result vector, obtaining a target resource value according to the resource prediction use result, and transferring the target resource value to the terminal corresponding to the user identifier.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
detecting whether the user identification is associated with the resource storage account identification, and acquiring login information corresponding to the user identification when the user identification is associated with the resource storage account identification;
verifying the login information, and acquiring corresponding behavior data and basic data according to the user identification when the login information passes verification;
performing dimensionality reduction on the behavior data and the basic data to obtain dimensionality-reduced features and corresponding feature importance, determining target features according to the feature importance, and encoding the target features to obtain target feature vectors;
inputting the target characteristic vector into a trained resource usage prediction model to obtain a prediction result vector;
and obtaining a resource prediction use result according to the prediction result vector, obtaining a target resource value according to the resource prediction use result, and transferring the target resource value to a terminal corresponding to the user identifier.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
detecting whether the user identification is associated with the resource storage account identification, and acquiring login information corresponding to the user identification when the user identification is associated with the resource storage account identification;
verifying the login information, and acquiring corresponding behavior data and basic data according to the user identification when the login information passes verification;
performing dimensionality reduction on the behavior data and the basic data to obtain dimensionality-reduced features and corresponding feature importance, determining target features according to the feature importance, and encoding the target features to obtain target feature vectors;
inputting the target characteristic vector into a trained resource usage prediction model to obtain a prediction result vector;
and obtaining a resource prediction use result according to the prediction result vector, obtaining a target resource value according to the resource prediction use result, and transferring the target resource value to a terminal corresponding to the user identifier.
According to the resource processing method, the resource processing device, the computer equipment and the storage medium, when the user is associated with the resource storage account identifier, the behavior data and the basic data of the user are obtained, the resource use condition of the user is predicted according to the behavior data and the basic data by using the resource use prediction model, and when the prediction result is the resource use, the target resource value is transferred to the terminal corresponding to the user identifier, so that the server pressure can be relieved. And resources are only transferred to users using the resources, so that resource waste can be avoided, the resource utilization rate is improved, and the resources are saved.
Drawings
FIG. 1 is a diagram of an application scenario of a resource handling method in one embodiment;
FIG. 2 is a flow diagram illustrating a method for resource handling in one embodiment;
FIG. 3 is a schematic diagram of a process for associating resource storage account identifiers in one embodiment;
FIG. 4 is a schematic flow diagram of training a resource usage prediction model in one embodiment;
FIG. 5 is a flow diagram illustrating selection of a resource usage prediction model in one embodiment;
FIG. 6 is a graphical illustration of feature importance in one embodiment;
FIG. 7 is a block diagram showing the structure of a resource processing apparatus according to one embodiment;
FIG. 8 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The resource processing method provided by the application can be applied to the application environment shown in fig. 1. Wherein the terminal 102 and the server 104 communicate via a network. The server 104 detects whether the user identifier is associated with the resource storage account identifier, and when the user identifier is associated with the resource storage account identifier, the server 104 acquires login information corresponding to the user identifier; the server 104 verifies the login information, and when the login information passes the verification, corresponding behavior data and basic data are obtained according to the user identification; the server 104 performs dimensionality reduction on the behavior data and the basic data to obtain dimensionality-reduced features and corresponding feature importance, determines target features according to the feature importance, and encodes the target features to obtain target feature vectors; the server 104 inputs the target characteristic vector into the trained resource use prediction model to obtain a prediction result vector; the server 104 obtains a resource predicted use result according to the prediction result vector, obtains a target resource value according to the resource predicted use result, and transfers the target resource value to the terminal 102 corresponding to the user identifier. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented by an independent server or a server cluster formed by a plurality of servers.
In one embodiment, as shown in fig. 2, a resource processing method is provided, which is described by taking the application of the method to the server in fig. 1 as an example, and includes the following steps:
s202, whether the user identification is associated with the resource storage account identification or not is detected, and when the user identification is associated with the resource storage account identification, login information corresponding to the user identification is obtained.
The user identifier is used to uniquely identify the user, and may be a number, a character string, or the like. The resource storage account identification refers to a resource storage account for uniquely identifying the user, and the resource storage account can be a bank card account or the like. The login information refers to information related to the login of the user, and includes IP address information, login device information, login area information, and the like.
Specifically, the server detects whether the user identifier is associated with the resource storage account identifier, for example, the corresponding associated resource storage account identifier may be searched in a preset association data table according to the user identifier, and when the resource storage account identifier can be searched, it is indicated that the user identifier is associated with the resource storage account identifier. At this time, the server acquires login information corresponding to the user identifier.
And S204, verifying the login information, and acquiring corresponding behavior data and basic data according to the user identification when the login information passes verification.
The behavior data refers to a behavior data basis generated in a website by a user corresponding to the user identifier, and may include login times, released resource values, resource browsing times and the like within a target time. The basic data refers to the basic information data of the user with the user identification, and comprises the gender, the identity card area, the age, whether to recommend the user, the safe resource classification, the mobile phone identification attribution, the resource area corresponding to the associated resource storage account identification and the like.
Specifically, the server verifies the login information, matches the login information with data recorded in a login information database in advance, and if the matching is consistent, the login information passes the verification. And when the matching is inconsistent, a prompt of 'login failure and inconsistent login information' is returned to the terminal corresponding to the user identifier. And when the login information passes the verification, the server acquires corresponding behavior data and basic data according to the user identification. The behavioral data and the underlying data may be looked up from databases and logs.
S206, reducing the dimensions of the behavior data and the basic data to obtain the features after dimension reduction and the corresponding feature importance, determining the target features according to the feature importance, and coding the target features to obtain target feature vectors.
The target characteristics refer to user data characteristics extracted from the behavior data and the basic data, and may include characteristics such as age, gender, access times, registration time, identity area, mobile phone identifier attribution, resource score and resource use richness. And the resource prediction use result is obtained according to the model.
Specifically, the server first preprocesses the behavior data and the basic data, including missing value processing, deduplication, format processing, and the like. And then, performing dimensionality reduction on the behavior data and the basic data to obtain dimensionality-reduced features and corresponding feature importance, and determining target features according to the feature importance. In the dimension reduction, PCA (principal component analysis algorithm), LDA (document theme generation model) chi-square detection, information gain, correlation coefficient algorithm, and the like may be used. And then coding the target feature to obtain a target feature vector. Different target features have different encoding modes, for example, One-hot-encoding (One-hot encoding, mainly using a bit state register to encode each state) is used for encoding the features without weight information, such as gender features. The mobile phone identifier attribution is characterized by having a grade weight, and is converted into a corresponding grade by using Label encoding. For example, Guangzhou, Shanghai, Beijing, a first-line city, may be coded as level 1, etc. And then, the coded target features form a target feature vector. In one embodiment, the obtained target feature vector is subjected to normalization processing to obtain a normalized target feature vector.
And S208, inputting the target characteristic vector into the trained resource use prediction model to obtain a prediction result vector.
The resource usage prediction model is obtained by performing a large amount of training by using a machine learning algorithm according to historical behavior data, historical basic data and corresponding historical resource usage. The predicted result vector is used for representing a predicted result vector of the resource used by the user, and the result of the resource used by the user comprises a predicted used resource and a predicted unused resource.
Specifically, the server inputs the target feature vector into a trained resource usage prediction model for prediction, and a prediction result vector is obtained.
S210, obtaining a resource prediction use result according to the prediction result vector, obtaining a target resource value according to the resource prediction use result, and transferring the target resource value to a terminal corresponding to the user identifier.
The target resource value refers to a resource value which needs to be issued to a terminal corresponding to the user identifier, and the resource refers to various virtual value articles in the internet, and the virtual value articles can be used and have a certain value. Such as investment coupons, red packs, vouchers, and the like.
Specifically, the server obtains the resource prediction use result from the prediction result vector according to the relationship between the prediction result vector and the resource prediction result, that is, when the prediction result is the prediction use resource, the target resource value is obtained, and the target resource value is transferred to the terminal corresponding to the user identifier. And when the prediction result is that the resources are not used, not processing.
In the embodiment, when the user associates the resource storage account identifier, the behavior data and the basic data of the user are acquired, the resource use condition of the user is predicted according to the behavior data and the basic data use resource use prediction model, when the prediction result is resource use, the target resource value is transferred to the terminal corresponding to the user, the server pressure can be reduced, and when the prediction result is resource use, the target resource value is transferred to the terminal corresponding to the user, resource waste can be avoided, and resources are saved.
In an embodiment, as shown in fig. 3, before step S202, that is, before detecting whether the user identifier is associated with the resource storage account identifier, and when the user identifier is associated with the resource storage account identifier, acquiring login information corresponding to the user identifier, the method further includes the steps of:
s304, receiving an identification verification instruction, wherein the identification verification instruction carries a resource storage account identification, and sending a verification request to a resource storage server according to the identification verification instruction, and the resource storage server is used for verifying the resource storage account identification to generate verification passing information.
The resource storage server refers to a server storing a large amount of resources, such as a bank server. The resource storage server is used for verifying the resource storage account identification to generate verification passing information.
Specifically, the server receives an identifier verification instruction, the identifier verification instruction carries a resource storage account identifier, and sends a verification request to the resource storage server according to the identifier verification instruction, and the resource storage server is used for verifying the resource storage account identifier to generate verification passing information.
S306, obtaining the verification passing information of the resource storage account identifier returned by the resource storage server, obtaining the user identifier according to the verification passing information of the resource storage account identifier, and associating the user identifier with the resource storage account identifier.
Wherein, the verification passing information refers to the information obtained after the resource storage account identification is verified,
specifically, the server obtains the verification passing information of the resource storage account identifier returned by the resource storage server, obtains the user identifier according to the verification passing information of the resource storage account identifier, and associates the user identifier with the resource storage account identifier.
In one embodiment, the server acquires registration information corresponding to the user identifier, real-name authentication information corresponding to the user identifier and resource transaction password information corresponding to the user identifier, and stores the user identifier, the registration information, the real-name authentication information, the resource transaction password information and the resource storage account identifier in a database in an associated manner.
In the embodiment, the resource storage account identifier which passes the verification is associated with the user identifier in advance, so that the accuracy of association of the resource storage account identifier and the user identifier is ensured, and the subsequent use is facilitated.
In one embodiment, step S210, obtaining a resource predicted use result according to the predicted result vector, obtaining a target resource value according to the resource predicted use result, and transferring the target resource value to the terminal corresponding to the user identifier, includes the steps of:
and acquiring a corresponding key according to the target resource value, encrypting the target resource value by using the key to obtain an encrypted target resource value, and transferring the encrypted target resource value to a terminal corresponding to the user identifier.
Specifically, the server acquires a key corresponding to the target resource value after acquiring the target resource value, the key may be a transaction password of a user, the key is used to encrypt the target resource value to obtain an encrypted target resource value, the encrypted target resource value is transferred to a terminal corresponding to a user identifier, and when the terminal corresponding to the user identifier receives the encrypted target resource value, the terminal receives a key input by the user and decrypts the key to obtain the target resource value. The safety of the target resource value in the transmission process is ensured.
In one embodiment, as shown in FIG. 4, the step of generating the trained resource usage prediction model comprises:
s402, obtaining historical behavior data and historical basic data corresponding to the historical user identification, and performing feature selection according to the historical behavior data and the historical basic data to obtain initial features.
The historical behavior data and the historical basic data refer to behavior data and basic data of a user when resources are issued through historical manual auditing. Feature selection refers to the possibility of selecting matching features from the initial features of the historical behavioral data and the historical base data using a feature selection algorithm. The feature selection algorithm may be a method using chi-square test, correlation coefficient method and tree model based feature selection.
Specifically, the server obtains historical behavior data and historical basic data corresponding to the historical user identification, and performs feature selection according to the historical behavior data and the historical basic data to obtain initial features.
S404, performing feature screening on the initial features according to the importance and the missing rate of the initial features to obtain target historical features, obtaining target historical data corresponding to the target historical features, and preprocessing the target historical data to obtain target historical feature vectors.
The importance and the missing rate of the initial features refer to the analysis of corresponding data by using an EDA (exploratory data analysis) method, the statistics and the distribution of taxonomic fields and the occupation ratio of missing values. The characteristic screening means that the required characteristics are screened from the initial characteristics. Preprocessing the target historical data refers to encoding the target historical data and performing data standardization.
Specifically, feature screening is carried out on the initial features according to the importance of the initial features and the loss rate, target historical features are obtained by sequentially selecting the initial features from the initial features according to the importance of the initial features from high to low and the loss rate from small to large, target historical data corresponding to the target historical features are obtained, the target historical data are coded, and the coded target historical data are subjected to data standardization processing to obtain target historical feature vectors.
S406, obtaining a historical resource use value corresponding to the historical user identifier, and coding the historical resource use value to obtain a historical result vector.
The historical resource usage value refers to a numerical value of the resource used by the historical user.
Specifically, the server obtains historical resource usage values corresponding to the historical user identifiers, encodes the historical resource usage values, and performs data standardization to obtain historical result vectors.
And S408, training by using a machine learning algorithm model by using the target historical characteristic vector as input and the historical result vector as a label to obtain a trained resource use prediction model.
Specifically, a target historical feature vector is used as input, a historical result vector is used as a label, a machine learning algorithm model is used for training, and when a preset training completion condition is reached, a trained resource usage prediction model is obtained. The machine learning algorithm may be an xgboost (extreme Gradient Boosting) algorithm, a logistic regression algorithm, a support vector machine algorithm, a neural network algorithm, and the like, and the training completion condition includes that the value of the cost function reaches a maximum value or reaches a maximum iteration number.
In one embodiment, a large amount of historical behavior data, historical basic data and corresponding historical resource use values are obtained as sample data, and a resource use prediction model is trained by using a cross-validation method.
In the above embodiment, the resource usage prediction model is obtained by training in advance using a machine learning algorithm based on historical data, and the prediction efficiency can be improved by using the model directly in prediction.
In one embodiment, as shown in fig. 5, in step S408, that is, taking the target historical feature vector as an input and the historical result vector as a label, training the target historical feature vector by using a machine learning algorithm model to obtain a trained resource usage prediction model, includes the steps of:
s502, inputting the target historical characteristic vector and the historical result vector into a logistic regression algorithm model for training to obtain a first resource use prediction model.
Among them, Logistic regression (Logistic) is a linear regression analysis model, and is commonly used in the fields of data mining, automatic disease diagnosis, economic prediction, and the like. For example, risk factors causing diseases are studied, and the probability of occurrence of diseases is predicted from the risk factors.
Specifically, the server inputs the target historical feature vector and the historical result vector into a logistic regression algorithm model for training, and when the value of the cost function reaches a preset threshold value or reaches the maximum iteration number, a first resource usage prediction model is obtained. The activation function of the logistic regression algorithm model uses a sigmoid function.
S504, inputting the target historical characteristic vector and the historical result vector into a decision tree model for training to obtain a second resource use prediction model.
The decision tree model is an XGboost model, which is a lifting tree model and is a strong classifier obtained by integrating a plurality of tree models.
Specifically, the server inputs a target historical feature vector and a historical result vector into the XGboost model for training, and when the value of the cost function reaches a preset threshold value or reaches the maximum iteration number, a second resource use prediction model is obtained.
S506, inputting the target historical characteristic vector and the historical result vector into a neural network model for training to obtain a third resource use prediction model.
The neural network model can be a BP neural network model, and is a multilayer feedforward neural network trained according to an error back propagation algorithm.
Specifically, the server inputs the same target historical feature vector and historical result vector into a BP neural network model for training, an S-shaped function is used for activating the function, and when the training reaches the maximum iteration or the error between the training and a label is smaller than a preset threshold value, the training is completed to obtain a third resource use prediction model.
S508, obtaining the trained resource usage prediction model from the first resource usage prediction model, the second resource usage prediction model and the third resource usage prediction model.
Specifically, test sample data including a test feature vector and a test result vector are obtained, the test data is used for testing the first resource usage prediction model, the second resource usage prediction model and the third resource usage prediction model, and a test result is obtained, wherein the test result includes operation speed, occupied storage space, test accuracy and the like. And selecting a resource use prediction model corresponding to the optimal result as a trained resource use prediction model according to the test result.
In the above embodiment, different resource usage prediction models are obtained by training using different machine learning algorithms, the obtained resource usage prediction models are tested, and the optimal resource usage prediction model is selected as the trained resource usage prediction model according to the test result, so that the accuracy, efficiency and the like of prediction can be improved.
In one embodiment, after step S408, that is, after training the target historical feature vector as an input and the historical result vector as a label by using the machine learning algorithm model to obtain the trained resource usage prediction model, the method further includes the steps of:
and calling an importance interface to obtain the feature importance corresponding to the target historical feature, and returning the target historical feature and the feature importance to the target terminal for displaying.
The importance level is used to indicate the importance level of the target history feature.
Specifically, the server calls an importance interface to obtain a feature importance corresponding to the target historical feature, and returns the target historical feature and the corresponding feature importance to the target terminal for display. In a specific embodiment, after the investment platform trains to obtain the resource usage prediction model, the target historical characteristics and the corresponding characteristic importance degrees are obtained as shown in fig. 6, wherein the importance degree of the age characteristic is the highest, and other characteristics are sequentially reduced.
In one embodiment, after step S408, after taking the target historical feature vector as an input and the historical result vector as a label, and training the target historical feature vector using the machine learning algorithm model to obtain a trained resource usage prediction model, the method further includes the steps of:
the resource usage prediction model file in the preset file format is obtained, the resource usage prediction model file in the preset file format is converted into a resource usage prediction model file in a target file format, and the resource usage prediction model file in the target file format is loaded to obtain a resource usage prediction model.
The preset file format refers to an inherent file format when training is completed. The target file format refers to a file format of a common format
Specifically, because the inherent file format cannot be analyzed by the server, when model deployment is required, the server needs to acquire a resource usage prediction model file in a preset file format, convert the resource usage prediction model file in the preset file format into a resource usage prediction model file in a target file format, and then load the resource usage prediction model file in the target file format to obtain a deployed resource usage prediction model, so that resource usage prediction can be directly performed. Model deployment is performed by using the resource usage prediction model file in the target file format, so that deployment efficiency can be improved.
In a specific embodiment, currently, most investment platforms adopt an undifferentiated marketing mode, that is, users bound with bank cards issue investment tickets uniformly, and such a wide-range networking mode can cause a large number of wool parties (who specially select marketing activities of internet companies and exchange high rewards for low cost or even zero cost) to acquire the investment tickets, which causes that the pressure of an investment platform server is too high in a short time. And the undifferentiated marketing wastes a large amount of investment coupons of the website and resources.
When the investment platform needs to issue the investment ticket, the investment platform server detects whether the user identification in the database is associated with the bank card account, and when the user identification is associated with the bank card account, the IP address information, the login equipment information and the login area information corresponding to the user identification are obtained. And verifying whether the IP address information, the login equipment information and the login area information are consistent with the verification information stored in the verification database, and if so, passing the verification. And when the login information of the investment platform server passes the verification, acquiring corresponding behavior data and basic data according to the user identification. Performing dimensionality reduction on the behavior data and the basic data to obtain dimensionality-reduced features and corresponding feature importance, determining and extracting investment features according to the feature importance, and coding the investment features to obtain investment feature vectors; inputting the investment characteristic vector into a trained investment coupon use prediction model to obtain a prediction result vector; and obtaining the predicted use result of the investment ticket according to the prediction result vector, obtaining the investment ticket to be issued according to the predicted use result of the resource, and issuing the investment ticket to the terminal corresponding to the user identifier.
It should be understood that although the various steps in the flow charts of fig. 2-5 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-5 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 7, there is provided a resource processing apparatus 700, including: an association detection module 702, a data acquisition module 704, a feature extraction module 706, a prediction module 708, and a resource transfer module 710, wherein:
the association detection module 702 is configured to detect whether the user identifier is associated with the resource storage account identifier, and when the user identifier is associated with the resource storage account identifier, obtain login information corresponding to the user identifier;
the data acquisition module 704 is used for verifying the login information, and acquiring corresponding behavior data and basic data according to the user identification when the login information passes the verification;
the feature extraction module 706 is configured to perform dimension reduction on the behavior data and the basic data to obtain a feature after dimension reduction and a corresponding feature importance, determine a target feature according to the feature importance, and encode the target feature to obtain a target feature vector;
a prediction module 708, configured to input the target feature vector into the trained resource usage prediction model to obtain a prediction result vector;
and the resource transfer module 710 is configured to obtain a resource predicted usage result according to the prediction result vector, obtain a target resource value according to the resource predicted usage result, and transfer the target resource value to the terminal corresponding to the user identifier.
In one embodiment, the resource processing apparatus 700 further includes:
the verification module is used for receiving an identifier verification instruction, the identifier verification instruction carries a resource storage account identifier, a verification request is sent to the resource storage server according to the identifier verification instruction, and the resource storage server is used for verifying the resource storage account identifier to generate verification passing information;
and the association module is used for acquiring the verification passing information of the resource storage account identifier returned by the resource storage server, acquiring the user identifier according to the verification passing information of the resource storage account identifier, and associating the user identifier with the resource storage account identifier.
In an embodiment, the resource transfer module 710 is further configured to obtain a corresponding key according to the target resource value, encrypt the target resource value using the key to obtain an encrypted target resource value, and transfer the encrypted target resource value to the terminal corresponding to the user identifier.
In one embodiment, the resource processing apparatus 700 further includes:
the historical data acquisition module is used for acquiring historical behavior data and historical basic data corresponding to the historical user identification, and performing feature selection according to the historical behavior data and the historical basic data to obtain initial features;
the historical feature extraction module is used for carrying out feature screening on the initial features according to the importance and the missing rate of the initial features to obtain target historical features, obtaining target historical data corresponding to the target historical features, and preprocessing the target historical data to obtain target historical feature vectors;
the historical result acquisition module is used for acquiring historical resource use values corresponding to the historical user identifiers and coding the historical resource use values to obtain historical result vectors;
and the training module is used for training by using a machine learning algorithm model by taking the target historical characteristic vector as input and the historical result vector as a label to obtain a trained resource use prediction model.
In one embodiment, the training module is further to: inputting the target historical characteristic vector and the historical result vector into a logistic regression algorithm model for training to obtain a first resource use prediction model; inputting the target historical characteristic vector and the historical result vector into a decision tree model for training to obtain a second resource use prediction model; inputting the target historical characteristic vector and the historical result vector into a neural network model for training to obtain a third resource use prediction model; the trained resource usage prediction model is derived from the first resource usage prediction model, the second resource usage prediction model, and the third resource usage prediction model.
In one embodiment, the training module is further configured to call an importance interface, obtain a feature importance corresponding to the target historical feature, and return the target historical feature and the feature importance to the target terminal for display.
In one embodiment, the resource processing apparatus 700 further includes:
the model loading module is used for acquiring the resource usage prediction model file in the preset file format, converting the resource usage prediction model file in the preset file format into the resource usage prediction model file in the target file format, and loading the resource usage prediction model file in the target file format to obtain the resource usage prediction model.
For the specific limitation of the resource processing device, reference may be made to the above limitation of the resource processing method, which is not described herein again. The modules in the resource processing device can be wholly or partially implemented by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 8. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing behavior data, basic data and the like. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a resource handling method.
Those skilled in the art will appreciate that the architecture shown in fig. 8 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, there is provided a computer device comprising a memory storing a computer program and a processor implementing the following steps when the processor executes the computer program: detecting whether the user identification is associated with the resource storage account identification, and acquiring login information corresponding to the user identification when the user identification is associated with the resource storage account identification; verifying the login information, and acquiring corresponding behavior data and basic data according to the user identification when the login information passes verification; performing dimensionality reduction on the behavior data and the basic data to obtain dimensionality-reduced features and corresponding feature importance, determining target features according to the feature importance, and encoding the target features to obtain target feature vectors; inputting the target characteristic vector into a trained resource usage prediction model to obtain a prediction result vector; and obtaining a resource prediction use result according to the prediction result vector, obtaining a target resource value according to the resource prediction use result, and transferring the target resource value to a terminal corresponding to the user identifier.
In one embodiment, the processor, when executing the computer program, further performs the steps of: receiving an identification verification instruction, wherein the identification verification instruction carries a resource storage account identification, and sending a verification request to a resource storage server according to the identification verification instruction, and the resource storage server is used for verifying the resource storage account identification to generate verification passing information; and acquiring verification passing information of the resource storage account identifier returned by the resource storage server, acquiring a user identifier according to the verification passing information of the resource storage account identifier, and associating the user identifier with the resource storage account identifier.
In one embodiment, the processor, when executing the computer program, further performs the steps of: and acquiring a corresponding key according to the target resource value, encrypting the target resource value by using the key to obtain an encrypted target resource value, and transferring the encrypted target resource value to a terminal corresponding to the user identifier.
In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring historical behavior data and historical basic data corresponding to historical user identification, and performing feature selection according to the historical behavior data and the historical basic data to obtain initial features; performing feature screening on the initial features according to the importance and the missing rate of the initial features to obtain target historical features, acquiring target historical data corresponding to the target historical features, and preprocessing the target historical data to obtain target historical feature vectors; acquiring a historical resource use value corresponding to a historical user identifier, and coding the historical resource use value to obtain a historical result vector; and taking the target historical characteristic vector as input, taking the historical result vector as a label, and training by using a machine learning algorithm model to obtain a trained resource use prediction model.
In one embodiment, the processor, when executing the computer program, further performs the steps of: inputting the target historical characteristic vector and the historical result vector into a logistic regression algorithm model for training to obtain a first resource use prediction model; inputting the target historical characteristic vector and the historical result vector into a decision tree model for training to obtain a second resource use prediction model; inputting the target historical characteristic vector and the historical result vector into a neural network model for training to obtain a third resource use prediction model; the trained resource usage prediction model is derived from the first resource usage prediction model, the second resource usage prediction model, and the third resource usage prediction model.
In one embodiment, the processor, when executing the computer program, further performs the steps of: and calling an importance interface to obtain the feature importance corresponding to the target historical feature, and returning the target historical feature and the feature importance to the target terminal for displaying.
In one embodiment, the processor, when executing the computer program, further performs the steps of: the resource usage prediction model file in the preset file format is obtained, the resource usage prediction model file in the preset file format is converted into a resource usage prediction model file in a target file format, and the resource usage prediction model file in the target file format is loaded to obtain a resource usage prediction model.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of: detecting whether the user identification is associated with the resource storage account identification, and acquiring login information corresponding to the user identification when the user identification is associated with the resource storage account identification; verifying the login information, and acquiring corresponding behavior data and basic data according to the user identification when the login information passes verification; performing dimensionality reduction on the behavior data and the basic data to obtain dimensionality-reduced features and corresponding feature importance, determining target features according to the feature importance, and encoding the target features to obtain target feature vectors; inputting the target characteristic vector into a trained resource usage prediction model to obtain a prediction result vector; and obtaining a resource prediction use result according to the prediction result vector, obtaining a target resource value according to the resource prediction use result, and transferring the target resource value to a terminal corresponding to the user identifier.
In one embodiment, the computer program when executed by the processor further performs the steps of: receiving an identification verification instruction, wherein the identification verification instruction carries a resource storage account identification, and sending a verification request to a resource storage server according to the identification verification instruction, and the resource storage server is used for verifying the resource storage account identification to generate verification passing information; and acquiring verification passing information of the resource storage account identifier returned by the resource storage server, acquiring a user identifier according to the verification passing information of the resource storage account identifier, and associating the user identifier with the resource storage account identifier.
In one embodiment, the computer program when executed by the processor further performs the steps of: and acquiring a corresponding key according to the target resource value, encrypting the target resource value by using the key to obtain an encrypted target resource value, and transferring the encrypted target resource value to a terminal corresponding to the user identifier.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring historical behavior data and historical basic data corresponding to historical user identification, and performing feature selection according to the historical behavior data and the historical basic data to obtain initial features; performing feature screening on the initial features according to the importance and the missing rate of the initial features to obtain target historical features, acquiring target historical data corresponding to the target historical features, and preprocessing the target historical data to obtain target historical feature vectors; acquiring a historical resource use value corresponding to a historical user identifier, and coding the historical resource use value to obtain a historical result vector; and taking the target historical characteristic vector as input, taking the historical result vector as a label, and training by using a machine learning algorithm model to obtain a trained resource use prediction model.
In one embodiment, the computer program when executed by the processor further performs the steps of: inputting the target historical characteristic vector and the historical result vector into a logistic regression algorithm model for training to obtain a first resource use prediction model; inputting the target historical characteristic vector and the historical result vector into a decision tree model for training to obtain a second resource use prediction model; inputting the target historical characteristic vector and the historical result vector into a neural network model for training to obtain a third resource use prediction model; the trained resource usage prediction model is derived from the first resource usage prediction model, the second resource usage prediction model, and the third resource usage prediction model.
In one embodiment, the computer program when executed by the processor further performs the steps of: and calling an importance interface to obtain the feature importance corresponding to the target historical feature, and returning the target historical feature and the feature importance to the target terminal for displaying.
In one embodiment, the computer program when executed by the processor further performs the steps of: the resource usage prediction model file in the preset file format is obtained, the resource usage prediction model file in the preset file format is converted into a resource usage prediction model file in a target file format, and the resource usage prediction model file in the target file format is loaded to obtain a resource usage prediction model.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims (10)

1. A method of resource processing, the method comprising:
detecting whether a user identifier is associated with a resource storage account identifier, and acquiring login information corresponding to the user identifier when the user identifier is associated with the resource storage account identifier;
verifying the login information, and acquiring corresponding behavior data and basic data according to the user identification when the login information passes the verification;
performing dimensionality reduction on the behavior data and the basic data to obtain dimensionality-reduced features and corresponding feature importance, determining target features according to the feature importance, and encoding the target features to obtain target feature vectors;
inputting the target characteristic vector into a trained resource usage prediction model to obtain a prediction result vector;
and obtaining a resource prediction use result according to the prediction result vector, obtaining a target resource value according to the resource prediction use result, and transferring the target resource value to a terminal corresponding to the user identifier.
2. The method according to claim 1, before the detecting whether the user identifier is associated with a resource storage account identifier, and when the user identifier is associated with the resource storage account identifier, acquiring login information corresponding to the user identifier, further comprising:
receiving an identifier verification instruction, wherein the identifier verification instruction carries a resource storage account identifier, and sending a verification request to a resource storage server according to the identifier verification instruction, wherein the resource storage server is used for verifying the resource storage account identifier to generate verification passing information;
and acquiring verification passing information of the resource storage account identifier returned by the resource storage server, acquiring the user identifier according to the verification passing information of the resource storage account identifier, and associating the user identifier with the resource storage account identifier.
3. The method according to claim 1, wherein the obtaining a resource predicted usage result according to the prediction result vector, obtaining a target resource value according to the resource predicted usage result, and transferring the target resource value to a terminal corresponding to the user identifier includes:
and acquiring a corresponding key according to the target resource value, encrypting the target resource value by using the key to obtain an encrypted target resource value, and transferring the encrypted target resource value to a terminal corresponding to the user identifier.
4. The method of claim 1, wherein the step of generating the trained resource usage prediction model comprises:
acquiring historical behavior data and historical basic data corresponding to historical user identification, and performing feature selection according to the historical behavior data and the historical basic data to obtain initial features;
performing feature screening on the initial features according to the importance and the missing rate of the initial features to obtain target historical features, acquiring target historical data corresponding to the target historical features, and preprocessing the target historical data to obtain target historical feature vectors;
acquiring a historical resource use value corresponding to the historical user identifier, and coding the historical resource use value to obtain a historical result vector;
and taking the target historical characteristic vector as input, taking the historical result vector as a label, and training by using a machine learning algorithm model to obtain the trained resource use prediction model.
5. The method of claim 4, wherein the training using the target historical feature vector as an input and the historical result vector as a label using a machine learning algorithm model to obtain the trained resource usage prediction model comprises:
inputting the target historical characteristic vector and the historical result vector into a logistic regression algorithm model for training to obtain a first resource use prediction model;
inputting the target historical characteristic vector and the historical result vector into a decision tree model for training to obtain a second resource use prediction model;
inputting the target historical characteristic vector and the historical result vector into a neural network model for training to obtain a third resource use prediction model;
deriving the trained resource usage prediction model from the first, second, and third resource usage prediction models.
6. The method of claim 4, wherein after the training using the machine learning algorithm model with the target historical feature vector as input and the historical result vector as a label to obtain the trained resource usage prediction model, further comprising:
and calling an importance interface to obtain the feature importance corresponding to the target historical feature, and returning the target historical feature and the feature importance to a target terminal for displaying.
7. The method of claim 4, wherein after the training using the machine learning algorithm model with the target historical feature vector as input and the historical result vector as a label to obtain the trained resource usage prediction model, further comprising:
the resource usage prediction model file in the preset file format is obtained, the resource usage prediction model file in the preset file format is converted into a resource usage prediction model file in a target file format, and the resource usage prediction model file in the target file format is loaded to obtain a resource usage prediction model.
8. An apparatus for resource handling, the apparatus comprising:
the system comprises an association detection module, a resource storage account identification and a login information acquisition module, wherein the association detection module is used for detecting whether a user identification is associated with the resource storage account identification or not, and acquiring login information corresponding to the user identification when the user identification is associated with the resource storage account identification;
the data acquisition module is used for verifying the login information, and acquiring corresponding behavior data and basic data according to the user identification when the login information passes the verification;
the characteristic extraction module is used for reducing the dimensions of the behavior data and the basic data to obtain the reduced-dimension characteristics and the corresponding characteristic importance, determining target characteristics according to the characteristic importance and coding the target characteristics to obtain target characteristic vectors;
the prediction module is used for inputting the target characteristic vector into a trained resource use prediction model to obtain a prediction result vector;
and the resource transfer module is used for obtaining a resource prediction use result according to the prediction result vector, obtaining a target resource value according to the resource prediction use result, and transferring the target resource value to the terminal corresponding to the user identifier.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
CN201910969537.1A 2019-10-12 2019-10-12 Resource processing method, resource processing device, computer equipment and storage medium Pending CN110782277A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910969537.1A CN110782277A (en) 2019-10-12 2019-10-12 Resource processing method, resource processing device, computer equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910969537.1A CN110782277A (en) 2019-10-12 2019-10-12 Resource processing method, resource processing device, computer equipment and storage medium

Publications (1)

Publication Number Publication Date
CN110782277A true CN110782277A (en) 2020-02-11

Family

ID=69385213

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910969537.1A Pending CN110782277A (en) 2019-10-12 2019-10-12 Resource processing method, resource processing device, computer equipment and storage medium

Country Status (1)

Country Link
CN (1) CN110782277A (en)

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111510473A (en) * 2020-03-13 2020-08-07 北京三快在线科技有限公司 Access request processing method and device, electronic equipment and computer readable medium
CN111628912A (en) * 2020-05-28 2020-09-04 深圳华锐金融技术股份有限公司 Resource-related data processing method and device, computer equipment and storage medium
CN111672130A (en) * 2020-06-03 2020-09-18 西安万像电子科技有限公司 Game player identity authentication method, authentication device and cloud game system
CN111681041A (en) * 2020-05-26 2020-09-18 深圳市元征科技股份有限公司 Electronic coupon issuing method and device, electronic equipment and storage medium
CN111966921A (en) * 2020-08-18 2020-11-20 中国银行股份有限公司 Community identification method and system based on user scene
CN112381234A (en) * 2020-11-09 2021-02-19 北京达佳互联信息技术有限公司 Resource distribution method, device, equipment and computer readable storage medium
CN112561082A (en) * 2020-12-22 2021-03-26 北京百度网讯科技有限公司 Method, device, equipment and storage medium for generating model
CN113328908A (en) * 2021-05-10 2021-08-31 广东电网有限责任公司广州供电局 Abnormal data detection method and device, computer equipment and storage medium
CN113761335A (en) * 2020-11-19 2021-12-07 北京沃东天骏信息技术有限公司 Resource processing method and device
CN113807858A (en) * 2021-09-23 2021-12-17 未鲲(上海)科技服务有限公司 Data processing method based on decision tree model and related equipment
CN115147020A (en) * 2022-09-02 2022-10-04 深圳装速配科技有限公司 Decoration data processing method, device, equipment and storage medium

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102999848A (en) * 2011-09-08 2013-03-27 阿里巴巴集团控股有限公司 Method and equipment for issuing electronic discount coupons
CN107301562A (en) * 2017-05-16 2017-10-27 重庆邮电大学 A kind of O2O reward vouchers use big data Forecasting Methodology
CN107578281A (en) * 2017-08-31 2018-01-12 湖南大学 User preferential certificate behavior prediction method and model building method under e-commerce environment
CN108154288A (en) * 2017-12-07 2018-06-12 北京三快在线科技有限公司 New user subsidizes computational methods, device, electronic equipment and the storage medium of strategy
CN108876436A (en) * 2018-05-25 2018-11-23 广东工业大学 A kind of electric business discount coupon based on integrated model uses probability forecasting method
CN109509033A (en) * 2018-12-14 2019-03-22 重庆邮电大学 A kind of user buying behavior big data prediction technique under consumer finance scene
CN109670847A (en) * 2017-10-17 2019-04-23 腾讯科技（深圳）有限公司 The distribution method and device of resource
CN109961191A (en) * 2019-04-03 2019-07-02 北京奇艺世纪科技有限公司 A kind of discount coupon distribution method and device
CN110111090A (en) * 2019-03-26 2019-08-09 口口相传(北京)网络技术有限公司 A kind of distribution method and device of electronics red packet

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102999848A (en) * 2011-09-08 2013-03-27 阿里巴巴集团控股有限公司 Method and equipment for issuing electronic discount coupons
CN107301562A (en) * 2017-05-16 2017-10-27 重庆邮电大学 A kind of O2O reward vouchers use big data Forecasting Methodology
CN107578281A (en) * 2017-08-31 2018-01-12 湖南大学 User preferential certificate behavior prediction method and model building method under e-commerce environment
CN109670847A (en) * 2017-10-17 2019-04-23 腾讯科技（深圳）有限公司 The distribution method and device of resource
CN108154288A (en) * 2017-12-07 2018-06-12 北京三快在线科技有限公司 New user subsidizes computational methods, device, electronic equipment and the storage medium of strategy
CN108876436A (en) * 2018-05-25 2018-11-23 广东工业大学 A kind of electric business discount coupon based on integrated model uses probability forecasting method
CN109509033A (en) * 2018-12-14 2019-03-22 重庆邮电大学 A kind of user buying behavior big data prediction technique under consumer finance scene
CN110111090A (en) * 2019-03-26 2019-08-09 口口相传(北京)网络技术有限公司 A kind of distribution method and device of electronics red packet
CN109961191A (en) * 2019-04-03 2019-07-02 北京奇艺世纪科技有限公司 A kind of discount coupon distribution method and device

Cited By (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111510473B (en) * 2020-03-13 2022-07-19 北京三快在线科技有限公司 Access request processing method and device, electronic equipment and computer readable medium
CN111510473A (en) * 2020-03-13 2020-08-07 北京三快在线科技有限公司 Access request processing method and device, electronic equipment and computer readable medium
CN111681041A (en) * 2020-05-26 2020-09-18 深圳市元征科技股份有限公司 Electronic coupon issuing method and device, electronic equipment and storage medium
CN111628912A (en) * 2020-05-28 2020-09-04 深圳华锐金融技术股份有限公司 Resource-related data processing method and device, computer equipment and storage medium
CN111628912B (en) * 2020-05-28 2021-08-03 深圳华锐金融技术股份有限公司 Resource-related data processing method and device, computer equipment and storage medium
CN111672130A (en) * 2020-06-03 2020-09-18 西安万像电子科技有限公司 Game player identity authentication method, authentication device and cloud game system
CN111966921A (en) * 2020-08-18 2020-11-20 中国银行股份有限公司 Community identification method and system based on user scene
CN112381234A (en) * 2020-11-09 2021-02-19 北京达佳互联信息技术有限公司 Resource distribution method, device, equipment and computer readable storage medium
CN112381234B (en) * 2020-11-09 2024-05-14 北京达佳互联信息技术有限公司 Resource distribution method, device, equipment and computer readable storage medium
CN113761335A (en) * 2020-11-19 2021-12-07 北京沃东天骏信息技术有限公司 Resource processing method and device
CN112561082A (en) * 2020-12-22 2021-03-26 北京百度网讯科技有限公司 Method, device, equipment and storage medium for generating model
CN113328908A (en) * 2021-05-10 2021-08-31 广东电网有限责任公司广州供电局 Abnormal data detection method and device, computer equipment and storage medium
CN113807858B (en) * 2021-09-23 2024-04-26 中科软科技股份有限公司 Data processing method and related equipment based on decision tree model
CN113807858A (en) * 2021-09-23 2021-12-17 未鲲(上海)科技服务有限公司 Data processing method based on decision tree model and related equipment
CN115147020A (en) * 2022-09-02 2022-10-04 深圳装速配科技有限公司 Decoration data processing method, device, equipment and storage medium
CN115147020B (en) * 2022-09-02 2023-01-06 深圳装速配科技有限公司 Decoration data processing method, device, equipment and storage medium

Similar Documents

Publication Publication Date Title
CN110782277A (en) Resource processing method, resource processing device, computer equipment and storage medium
CN108876133B (en) Risk assessment processing method, device, server and medium based on business information
CN108898418B (en) User account detection method, device, computer equipment and storage medium
CN108769026B (en) User account detection system and method
CN111176990B (en) Test data generation method and device based on data decision, and computer equipment
CN109816200B (en) Task pushing method, device, computer equipment and storage medium
CN111275448A (en) Face data processing method and device and computer equipment
CN110912712A (en) Service operation risk authentication method and system based on block chain
CN108334625B (en) User information processing method and device, computer equipment and storage medium
CN111324802A (en) Data auditing method and device based on identity recognition and computer equipment
CN112231224A (en) Business system testing method, device, equipment and medium based on artificial intelligence
CN109460541B (en) Vocabulary relation labeling method and device, computer equipment and storage medium
CN112017024A (en) Credit risk assessment method, system, computer device and storage medium
CN110750750A (en) Webpage generation method and device, computer equipment and storage medium
CN111124421B (en) Abnormal contract data detection method and device for blockchain intelligent contract
CN110223075B (en) Identity authentication method and device, computer equipment and storage medium
CN111222919A (en) Business data pushing method and device, computer equipment and storage medium
CN111125748A (en) Judgment method and device for unauthorized query, computer equipment and storage medium
CN108304289B (en) Terminal fingerprint test method and device, computer equipment and storage medium
CN113268328A (en) Batch processing method and device, computer equipment and storage medium
CN112632504A (en) Webpage access method, device, system, computer equipment and storage medium
CN110460585B (en) Equipment identity identification method and device, computer equipment and storage medium
CN110716930A (en) Numerical value transfer method, device, computer equipment and storage medium
CN110674847A (en) Card classification storage method and device, computer equipment and storage medium
CN110599271A (en) Bill detection method and device, computer equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
TA01 Transfer of patent application right

Effective date of registration: 20200212

Address after: 200120 floor 15, 1333 Lujiazui Ring Road, free trade Experimental Zone, Pudong New Area, Shanghai

Applicant after: Weikun (Shanghai) Technology Service Co.,Ltd.

Address before: 13th Floor, 1333 Lujiazui Ring Road, Shanghai Free Trade Pilot Area, 200120

Applicant before: SHANGHAI LUJIAZUI INTERNATIONAL FINANCIAL ASSETS TRANSACTION MARKET CO.,LTD.

TA01 Transfer of patent application right
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

Application publication date: 20200211

RJ01 Rejection of invention patent application after publication