CN110764902A - Virtual resource allocation method and device based on AI (Artificial Intelligence), computer equipment and storage medium - Google Patents
Virtual resource allocation method and device based on AI (Artificial Intelligence), computer equipment and storage medium Download PDFInfo
- Publication number
- CN110764902A CN110764902A CN201910883397.6A CN201910883397A CN110764902A CN 110764902 A CN110764902 A CN 110764902A CN 201910883397 A CN201910883397 A CN 201910883397A CN 110764902 A CN110764902 A CN 110764902A
- Authority
- CN
- China
- Prior art keywords
- virtual resource
- allocation
- target
- resource allocation
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 64
- 238000013473 artificial intelligence Methods 0.000 title description 13
- 238000012549 training Methods 0.000 claims abstract description 49
- 238000007781 pre-processing Methods 0.000 claims abstract description 12
- 238000012545 processing Methods 0.000 claims description 20
- 238000012795 verification Methods 0.000 claims description 19
- 238000010606 normalization Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 7
- 238000007477 logistic regression Methods 0.000 claims description 4
- 238000003062 neural network model Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 23
- 238000004140 cleaning Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5077—Logical partitioning of resources; Management or configuration of virtualized resources
-
- 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
-
- 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
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Theoretical Computer Science (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Software Systems (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- Technology Law (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a virtual resource allocation method based on AI, comprising the following steps: acquiring a target virtual resource allocation rule which is issued in advance from a virtual resource allocation rule database, and acquiring an allocation time period corresponding to the target virtual resource allocation rule; acquiring user characteristics and virtual resource consumption data corresponding to each user history in a distribution time period from a sample database, and preprocessing the user characteristics and the virtual resource consumption data to obtain a standardized sample data set; training according to a standardized sample data set to obtain a virtual resource consumption prediction model; predicting virtual resource prediction consumption data of the target user in the allocation time period through a virtual resource consumption prediction model according to the current user characteristics of the target user; matching the virtual resource predicted consumption data with a target virtual resource allocation rule; and pushing the target virtual resource allocation rule to a target user corresponding to the matched virtual resource prediction consumption data. The invention can accurately push the relevant information of the cashback activity to the user.
Description
Technical Field
The present invention relates to the field of computer processing technologies, and in particular, to a virtual resource allocation method and apparatus based on AI, a computer device, and a storage medium.
Background
Currently, financial products are increasingly competitive. To attract users, large banks have successively pushed out various virtual resource allocation rules, such as pushing out various cashback activities. In the prior art, a way for a bank to push cashback activities to a user is generally that the user simply classifies lines and then sends corresponding cashback activities to all users of corresponding classes in a group. For example, given that a credit card consumption cashback activity is going to be brought online, existing methods classify users by attributes such as age or income and push the rules of the cashback activity to a specific category of people to encourage these users to consume. The push sending method has the disadvantages that a single variable is used for simply dividing a user group, comprehensive consideration is not carried out on multi-dimensional characteristic data of the user, the cashback activity rule can be pushed to the user with low relevance degree, the pushing accuracy is low, and the user experience is reduced.
Disclosure of Invention
In view of the foregoing deficiencies of the prior art, an object of the present invention is to provide a virtual resource allocation method and apparatus, a computer device, and a storage medium based on AI, so as to improve accurate pushing of virtual resource allocation rules and provide better user experience.
In order to achieve the above object, the present invention provides a virtual resource allocation method based on AI, which includes a push process, where the push process includes the following steps:
acquiring a target virtual resource allocation rule which is issued in advance from a virtual resource allocation rule database, and acquiring an allocation time period corresponding to the target virtual resource allocation rule;
acquiring user characteristics and virtual resource consumption data corresponding to each training user history in the distribution time period from a sample database, and preprocessing the user characteristics and the virtual resource consumption data to obtain a standardized sample data set;
training according to the standardized sample data set to obtain a virtual resource consumption prediction model;
predicting virtual resource prediction consumption data of each target user in the allocation time period through the virtual resource consumption prediction model according to the current user characteristics of each target user;
matching the virtual resource predicted consumption data of each target user with a target virtual resource allocation rule;
and pushing the target virtual resource allocation rule to a target user corresponding to the matched virtual resource prediction consumption data.
In one embodiment of the invention, the preprocessing includes data cleaning processing, digitizing processing, and normalization processing.
In an embodiment of the present invention, the step of training to obtain the virtual resource consumption prediction model according to the normalized sample data set includes:
dividing the standardized sample data set into a training set and a verification set according to a preset proportion;
training parameters of the virtual resource consumption prediction model based on the training set;
and verifying the virtual resource consumption prediction model based on the verification set, and finishing training if the verification is passed.
In one embodiment of the present invention, the virtual resource consumption prediction model is a logistic regression model or a neural network model.
In one embodiment of the invention, the user characteristics include age, gender, income, industry of interest, job title, academic calendar, and/or home condition.
In an embodiment of the present invention, after reaching an allocation time period corresponding to the target virtual resource allocation rule, the method further includes an allocation process, where the allocation process includes the following steps:
acquiring virtual resource actual consumption data matched with the target virtual resource allocation rule in the allocation time period, and taking an account corresponding to the virtual resource actual consumption data as an account to be allocated;
acquiring virtual resource pre-allocation data corresponding to each account to be allocated according to the target virtual resource allocation rule;
and allocating corresponding virtual resources to each account to be allocated based on the virtual resource pre-allocation data.
In an embodiment of the present invention, the step of allocating, based on the virtual resource pre-allocation data, corresponding virtual resources to each account to be allocated specifically includes:
and extracting a plurality of accounts to be allocated, detecting whether virtual resource actual consumption data and virtual resource pre-allocation data corresponding to the extracted accounts to be allocated are matched with the target virtual resource allocation rule or not, if so, allocating corresponding virtual resources to each account to be allocated based on the virtual resource pre-allocation data, otherwise, sending allocation exception notification information and the virtual resource actual consumption data and the virtual resource pre-allocation data corresponding to the unmatched accounts to be allocated to the administrator terminal, and ending the process.
In order to achieve the above object, the present invention further provides an AI-based virtual resource allocation apparatus, including a push part, the push part including:
the rule obtaining module is used for obtaining a target virtual resource distribution rule which is issued in advance from a virtual resource distribution rule database and obtaining a distribution time period corresponding to the target virtual resource distribution rule;
the sample processing module is used for acquiring user characteristics and virtual resource consumption data corresponding to the distribution time period of each training user history from a sample database, and preprocessing the user characteristics and the virtual resource consumption data to obtain a standardized sample data set;
the model training module is used for training according to the standardized sample data set to obtain a virtual resource consumption prediction model;
the prediction module is used for predicting virtual resource prediction consumption data of each target user in the distribution time period through the virtual resource consumption prediction model according to the current user characteristics of each target user;
the matching module is used for matching the virtual resource predicted consumption data with a target virtual resource allocation rule;
and the pushing module is used for pushing the target virtual resource allocation rule to a target user corresponding to the matched virtual resource prediction consumption data.
In one embodiment of the invention, the preprocessing includes data cleaning processing, digitizing processing, and normalization processing.
In one embodiment of the invention, the model training module comprises:
the sample dividing unit is used for dividing the standardized sample data set into a training set and a verification set according to a preset proportion;
a training unit for training parameters of the virtual resource consumption prediction model based on the training set;
and the verification unit is used for verifying the virtual resource consumption prediction model based on the verification set, and if the verification passes, finishing the training.
In one embodiment of the present invention, the virtual resource consumption prediction model is a logistic regression model or a neural network model.
In one embodiment of the invention, the user characteristics include age, gender, income, industry of interest, job title, academic calendar, and/or home condition.
In one embodiment of the invention, the apparatus further comprises an assignment section comprising the steps of:
the account to be allocated determining module is used for acquiring virtual resource actual consumption data matched with the target virtual resource allocation rule in the allocation time period, and taking an account corresponding to the virtual resource actual consumption data as an account to be allocated;
the pre-allocation data acquisition module is used for acquiring virtual resource pre-allocation data corresponding to each account to be allocated according to the target virtual resource allocation rule;
and the allocation module is used for allocating corresponding virtual resources to each account to be allocated based on the virtual resource pre-allocation data.
In an embodiment of the present invention, the allocation module is specifically configured to:
and extracting a plurality of accounts to be allocated, detecting whether virtual resource actual consumption data and virtual resource pre-allocation data corresponding to the extracted accounts to be allocated are matched with the target virtual resource allocation rule or not, if so, allocating corresponding virtual resources to each account to be allocated based on the virtual resource pre-allocation data, otherwise, sending allocation exception notification information and the virtual resource actual consumption data and the virtual resource pre-allocation data corresponding to the unmatched accounts to be allocated to the administrator terminal, and ending the process.
In order to achieve the above object, the present invention also provides a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the aforementioned method when executing the computer program.
In order to achieve the above object, the present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the aforementioned method.
Through the technical scheme, the invention has the following beneficial effects:
according to the method and the device, the target virtual resource allocation rule is pushed to the target user corresponding to the virtual resource prediction consumption data matched with the rule, so that the disturbance to the user with low relevance is avoided, the target virtual resource allocation rule is accurately pushed, and the user experience is improved. In addition, the invention can also automatically realize the virtual resource allocation operation of the consumption records to be allocated, automatically identify the abnormity in the allocation process and provide corresponding processing, and reduce the manual workload, thereby reducing the error rate, releasing the time of related personnel, leading the personnel to use more time for more valuable work and reducing the inefficient repetitive work.
Drawings
FIG. 1 is a flowchart illustrating a pushing process of the AI-based virtual resource allocation method according to the present invention;
FIG. 2 is a flowchart illustrating an allocation process of the AI-based virtual resource allocation method according to the present invention;
FIG. 3 is a block diagram illustrating an AI-based virtual resource allocation apparatus according to the present invention;
fig. 4 is a hardware architecture diagram of the computer apparatus of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention 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 invention and are not intended to limit the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example one
The embodiment provides a virtual resource allocation method based on AI, which includes a push process and an allocation process, where the push process is shown in fig. 1 and includes the following steps:
s11, obtaining the target virtual resource allocation rule issued in advance from the virtual resource allocation rule database, and obtaining the allocation time period corresponding to the target virtual resource allocation rule. The virtual resource allocation rule may be, for example, a cashback rule of a cashback activity of a credit card to be online, and an allocation time period corresponding to the target virtual resource allocation rule is an activity time period of the cashback activity. In daily life, banks are often brought online with cashback activities of various rules in order to attract consumer consumption. For example, the cashback rule for a cashback activity is: during the activity period (such as 9 months 1-9 months 30 days in the current year), if the total consumption amount of the appointed credit card reaches a certain amount (such as 20000 yuan), 1% of the total consumption amount is returned.
And S12, acquiring user characteristics and virtual resource consumption data corresponding to each training user history in the distribution time period from a preset sample database, and preprocessing to obtain a standardized sample data set.
Assuming that the target virtual resource allocation rule is the above-mentioned cashback activity a, the step may acquire, from the sample database, user characteristics and virtual resource consumption data corresponding to each training user between 9 months 1 day and 9 months 30 days of the previous two years. The user characteristics may include name, account, phone number, age, gender, income, industry, job title, academic calendar, and/or housing status, among others. The virtual resource consumption data may be a credit card consumption amount.
In this embodiment, the preprocessing includes a data cleaning process, a digitizing process, and a normalizing process.
The cleaning treatment comprises the steps of deleting the characteristics which are not related to the consumption capacity in the user characteristics, such as unique identifications of names, accounts, mobile phone numbers and the like; in addition, the method can also comprise deleting samples with virtual resource consumption data lower than a preset threshold, and it can be understood that less virtual resource consumption data cannot reflect the real behavior habits of users, and even can have negative influence on the whole analysis and modeling.
The numerical processing means that non-numerical features among the user features are expressed as numerical features, for example, regarding the sex feature, the numerical feature is expressed as 1 when the sex is male, and the numerical feature is expressed as 0 when the sex is female; for the affiliated industry, the jobs, the academic calendar, the housing conditions and the like, clustering can be performed according to a preset rule, and different categories are represented by different numbers.
The normalization process refers to adjusting all the features in the user features into the same dimension. The normalization processing is performed because the magnitude of each feature in the user features is greatly different, for example, the income may be tens of thousands or hundreds of thousands, the age is only dozens, when the model is trained subsequently, the calculation of the large number is very time-consuming, and the calculation result is also abnormally large. In addition, the weight distribution is also uneven, generally, the weight obtained by a large number is possibly larger, however, the large number is probably not the most critical factor for determining the prediction result, and the result becomes the most important factor because the numerical value is large, so that the prediction is not accurate, and therefore, the normalization processing is used for adjusting, all the features are changed into the range of 0 to 1, and the dimension and the adjustment direction are unified. The process of normalizing the user characteristics specifically comprises the following steps: firstly, acquiring the mean value and standard deviation of all user characteristics; and then, subtracting the mean value from each user characteristic value, and dividing the mean value by the standard deviation to obtain a normalization result.
And S13, training according to the standardized sample data set to obtain a virtual resource consumption prediction model.
In the training process, firstly, the standardized sample data set is divided into a training set and a verification set according to a predetermined proportion, for example, 70% of the standardized sample data set is selected as the training set, and the rest 30% of the sample data set is selected as the verification set. And then, training parameters of the virtual resource consumption prediction model based on a training set, and preferably performing iterative training by adopting a gradient descent algorithm. Specifically, the value of the loss function of the virtual resource consumption prediction model during the K-th iterative training is calculated, and then the K + 1-th iterative training is performed by using a gradient descent algorithm according to the value of the loss function of the K-th iterative training until the value of the loss function of the virtual resource consumption prediction model meets the preset requirement. And finally, verifying indexes such as accuracy of the virtual resource consumption prediction model based on the verification sample set, ending training if the verification is passed, and increasing the number of the training sets for retraining if the verification is not passed.
And S14, predicting virtual resource predicted consumption data of each target user in the distribution time period through the virtual resource consumption prediction model according to the current user characteristics of each target user. Specifically, the current user characteristics of a target user are obtained from a user database; and then inputting the user characteristics of the target user into the trained virtual resource consumption prediction model, so as to predict and obtain the virtual resource prediction consumption data of the target user in the allocation time period.
And S15, matching the virtual resource predicted consumption data of each target user with the target virtual resource allocation rule, and extracting the matched virtual resource predicted consumption data. For example, if the target virtual resource allocation rule is the cashback rule of the a cashback activity, if it is predicted that the consumption amount of the credit card of the X user between 9 month 1 day and 9 month 30 day of the year will reach 20000 yuan, the consumption amount is considered to match the cashback rule of the a cashback activity, otherwise, the consumption amount is not matched.
And S16, pushing the target virtual resource allocation rule to the target user corresponding to the matched virtual resource predicted consumption data. For example, if the target virtual resource allocation rule is the cashback rule of the cashback activity a, if it is predicted that the consumption amount of the credit card of the X user between 9 month 1 day and 9 month 30 day of the year will reach 20000 yuan, the cashback rule of the cashback activity a is pushed to the X user, and the pushing and sending mode may be a form of a short message, an email or a WeChat.
Through the steps S11-S16, the target virtual resource allocation rule can be pushed accurately, disturbance to the user with low relevance degree is avoided, and user experience is improved.
After the allocation time period corresponding to the target virtual resource allocation rule is reached, the method of this embodiment further includes an allocation process, as shown in fig. 2, where the allocation process includes the following steps:
and S21, acquiring virtual resource actual consumption data matched with the target virtual resource allocation rule in the allocation time period, and taking an account corresponding to the virtual resource actual consumption data as an account to be allocated. For example, assuming that the target virtual resource allocation rule is the cashback rule of the cashback activity a, consumption data of which the actual total consumption amount of the target credit card account reaches 20000 yuan between 1 day of 9 month and 30 days of 9 month in the current year is collected, and the account of which the actual total consumption amount reaches 20000 yuan is taken as the account to be allocated.
And S22, acquiring virtual resource pre-allocation data corresponding to each account to be allocated according to the target virtual resource allocation rule. Assuming that the target virtual resource allocation rule is the cashback rule of the cashback activity A, the activity stipulates that if the total actual consumption amount between 9 month 1 day and 9 month 30 day of the current year reaches 20000 yuan, the cashback amount is 1 yuan, and if the total actual consumption amount between 9 month 1 day and 9 month 30 day of the current year reaches 28000 yuan, the cashback amount is 280 yuan, at this time, the account of the Y user is the account to be allocated, and the virtual resource pre-allocation data corresponding to the account is 280 yuan.
And S23, allocating corresponding virtual resources to each account to be allocated based on the virtual resource pre-allocation data. For example, assuming that the virtual resource pre-allocation data corresponding to an account is 280, 280 elements are allocated to the account.
In this embodiment, step S23 specifically includes: extracting a plurality of (for example, randomly extracting 100) accounts to be allocated, detecting whether virtual resource actual consumption data corresponding to the extracted accounts to be allocated and virtual resource pre-allocation data are matched with a target virtual resource allocation rule, if so, allocating corresponding virtual resources to each account to be allocated based on the virtual resource pre-allocation data, otherwise, sending allocation exception notification information, and virtual resource actual consumption data and virtual resource pre-allocation data corresponding to the unmatched accounts to be allocated to an administrator terminal, so that the administrator performs manual processing, and ending the process.
Through the above steps S21-S23, an automatic dispensing operation is realized, and further, an abnormal condition can be automatically recognized and a warning can be provided.
Example two
The present embodiment provides an AI-based virtual resource allocation apparatus 10, including a push part 11, as shown in fig. 3, where the push part 11 includes:
a rule obtaining module 111, configured to obtain a target virtual resource allocation rule to be issued from a virtual resource allocation rule database, and obtain an allocation time period corresponding to the target virtual resource allocation rule;
the sample processing module 112 is configured to obtain, from a sample database, user characteristics and virtual resource consumption data corresponding to each training user history in the allocation time period, and perform preprocessing to obtain a standardized sample data set;
a model training module 113, configured to train according to the standardized sample data set to obtain a virtual resource consumption prediction model;
the prediction module 114 is configured to predict, according to the current user characteristics of each target user, virtual resource prediction consumption data of each target user in the allocation time period through the virtual resource consumption prediction model;
a matching module 115, configured to match the virtual resource predicted consumption data with a target virtual resource allocation rule;
and a pushing module 116, configured to push the target virtual resource allocation rule to a target user corresponding to the matched virtual resource consumption prediction data.
In this embodiment, the preprocessing includes data cleaning, digitizing, and normalizing. The cleaning treatment refers to deleting the characteristics which are not related to the consumption capability in the user characteristics, such as names, accounts and mobile phone numbers; meanwhile, deleting the samples with the virtual resource consumption data lower than the preset threshold value, so that the fact that less virtual resource consumption data cannot reflect the real behavior habits of the user and even can generate negative effects on the whole analysis and modeling can be understood, in order to avoid the problem, the data need to be cleaned, wherein the threshold value is determined according to specific needs, and the threshold value can be properly adjusted according to the subsequent prediction effect.
The numerical processing means that non-numerical features among the user features are expressed as numerical features, for example, regarding the sex feature, the numerical feature is expressed as 1 when the sex is male, and the numerical feature is expressed as 0 when the sex is female; the related industries, the jobs, the academic calendars and the housing conditions can be clustered according to a preset rule, and different categories are represented by different numbers.
The normalization process refers to adjusting all the features in the user features into the same dimension. The normalization processing is performed because the magnitude of each feature in the user features is greatly different, for example, the income may be tens of thousands or hundreds of thousands, the age is only dozens, when the model is trained subsequently, the calculation of the large number is very time-consuming, and the calculation result is also abnormally large. In addition, the weight distribution is also uneven, generally, the weight obtained by a large number is possibly larger, however, the large number is probably not the most critical factor for determining the prediction result, and the result becomes the most important factor because the numerical value is large, so that the prediction is not accurate, and therefore, the normalization processing is used for adjusting, all the features are changed into the range of 0 to 1, and the dimension and the adjustment direction are unified. The process of normalizing the user characteristics specifically comprises the following steps: firstly, acquiring the mean value and standard deviation of all user characteristics; and then, subtracting the mean value from each user characteristic value, and dividing the mean value by the standard deviation to obtain a normalization result.
In this embodiment, the model training module 113 includes:
the sample dividing unit is used for dividing the standardized sample data set into a training set and a verification set according to a preset proportion;
a training unit for training parameters of the virtual resource consumption prediction model based on the training set;
and the verification unit is used for verifying the virtual resource consumption prediction model based on the verification set, and if the verification passes, finishing the training.
In this embodiment, the virtual resource consumption prediction model is a logistic regression model or a neural network model.
In this embodiment, the user characteristics include age, gender, income, industry of interest, job title, academic calendar, and/or home condition.
In this embodiment, the apparatus 10 further comprises an assignment segment 12, the assignment segment 12 comprising the steps of:
the account to be allocated determining module 121 is configured to acquire virtual resource actual consumption data matched with the target virtual resource allocation rule in the allocation time period, and use an account corresponding to the virtual resource actual consumption data as an account to be allocated;
a pre-allocation data obtaining module 122, configured to obtain, according to the target virtual resource allocation rule, virtual resource pre-allocation data corresponding to each account to be allocated;
the allocating module 123 is configured to allocate, based on the virtual resource pre-allocation data, corresponding virtual resources to each account to be allocated.
In this embodiment, the allocating module 123 is specifically configured to:
and extracting a plurality of accounts to be allocated, detecting whether virtual resource actual consumption data and virtual resource pre-allocation data corresponding to the extracted accounts to be allocated are matched with the target virtual resource allocation rule or not, if so, allocating corresponding virtual resources to each account to be allocated based on the virtual resource pre-allocation data, otherwise, sending allocation exception notification information and the virtual resource actual consumption data and the virtual resource pre-allocation data corresponding to the unmatched accounts to be allocated to the administrator terminal, and ending the process.
EXAMPLE III
The present invention also provides a computer device, such as a smart phone, a tablet computer, a notebook computer, a desktop computer, a rack server, a blade server, a tower server or a rack server (including an independent server or a server cluster composed of a plurality of servers) capable of executing programs, and the like. The computer device 20 of the present embodiment includes at least, but is not limited to: a memory 21, a processor 22, which may be communicatively coupled to each other via a system bus, as shown in FIG. 4. It is noted that fig. 4 only shows the computer device 20 with components 21-22, but it is to be understood that not all shown components are required to be implemented, and that more or fewer components may be implemented instead.
In the present embodiment, the memory 21 (i.e., a readable storage medium) includes a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, and the like. In some embodiments, the storage 21 may be an internal storage unit of the computer device 20, such as a hard disk or a memory of the computer device 20. In other embodiments, the memory 21 may also be an external storage device of the computer device 20, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), or the like, provided on the computer device 20. Of course, the memory 21 may also include both internal and external storage devices of the computer device 20. In this embodiment, the memory 21 is generally used for storing an operating system and various application software installed in the computer device 20, such as the program codes of the virtual resource allocation apparatus 10 in the second embodiment. Further, the memory 21 may also be used to temporarily store various types of data that have been output or are to be output.
Processor 22 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor 22 is typically used to control the overall operation of the computer device 20. In this embodiment, the processor 22 is configured to execute the program code stored in the memory 21 or process data, for example, execute the virtual resource allocation apparatus 10, so as to implement the virtual resource allocation method according to the first embodiment.
Example four
The present invention also provides a computer-readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, a server, an App application mall, etc., on which a computer program is stored, which when executed by a processor implements corresponding functions. The computer-readable storage medium of this embodiment is used for storing the virtual resource allocation apparatus 10, and when executed by a processor, implements the virtual resource allocation method of the first embodiment.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A virtual resource allocation method based on AI is characterized by comprising a pushing process, wherein the pushing process comprises the following steps:
acquiring a target virtual resource allocation rule which is issued in advance from a virtual resource allocation rule database, and acquiring an allocation time period corresponding to the target virtual resource allocation rule;
acquiring user characteristics and virtual resource consumption data corresponding to each training user history in the distribution time period from a sample database, and preprocessing the user characteristics and the virtual resource consumption data to obtain a standardized sample data set;
training according to the standardized sample data set to obtain a virtual resource consumption prediction model;
predicting virtual resource prediction consumption data of each target user in the allocation time period through the virtual resource consumption prediction model according to the current user characteristics of each target user;
matching the virtual resource predicted consumption data of each target user with the target virtual resource allocation rule;
and pushing the target virtual resource allocation rule to a target user corresponding to the matched virtual resource prediction consumption data.
2. The AI-based virtual resource allocation method according to claim 1, wherein the preprocessing includes a data cleansing process, a numeralization process, and a normalization process.
3. The AI-based virtual resource allocation method according to claim 1, wherein the step of training a virtual resource consumption prediction model based on the normalized set of sample data comprises:
dividing the standardized sample data set into a training set and a verification set according to a preset proportion;
training parameters of the virtual resource consumption prediction model based on the training set;
and verifying the virtual resource consumption prediction model based on the verification set, and finishing training if the verification is passed.
4. The AI-based virtual resource allocation method according to claim 1, wherein the virtual resource consumption prediction model is a logistic regression model or a neural network model.
5. The AI-based virtual resource allocation method according to claim 1, wherein the user characteristics include age, gender, income, industry of interest, job title, academic calendar, and/or home status.
6. The AI-based virtual resource allocation method according to claim 1, wherein after reaching an allocation time period corresponding to the target virtual resource allocation rule, the method further comprises an allocation procedure, the allocation procedure comprising the steps of:
acquiring virtual resource actual consumption data matched with the target virtual resource allocation rule in the allocation time period, and taking an account corresponding to the virtual resource actual consumption data as an account to be allocated;
acquiring virtual resource pre-allocation data corresponding to each account to be allocated according to the target virtual resource allocation rule;
and allocating corresponding virtual resources to each account to be allocated based on the virtual resource pre-allocation data.
7. The AI-based virtual resource allocation method according to claim 6, wherein the step of allocating corresponding virtual resources to each account to be allocated based on the virtual resource pre-allocation data further comprises:
and extracting a plurality of accounts to be allocated, detecting whether virtual resource actual consumption data and virtual resource pre-allocation data corresponding to the extracted accounts to be allocated are matched with the target virtual resource allocation rule or not, if so, allocating corresponding virtual resources to each account to be allocated based on the virtual resource pre-allocation data, otherwise, sending allocation exception notification information and the virtual resource actual consumption data and the virtual resource pre-allocation data corresponding to the unmatched accounts to be allocated to the administrator terminal, and ending the process.
8. An AI-based virtual resource allocation apparatus comprising a push section, the push section comprising:
the rule obtaining module is used for obtaining a target virtual resource distribution rule which is issued in advance from a virtual resource distribution rule database and obtaining a distribution time period corresponding to the target virtual resource distribution rule;
the sample processing module is used for acquiring user characteristics and virtual resource consumption data corresponding to the distribution time period of each training user history from a sample database, and preprocessing the user characteristics and the virtual resource consumption data to obtain a standardized sample data set;
the model training module is used for training according to the standardized sample data set to obtain a virtual resource consumption prediction model;
the prediction module is used for predicting virtual resource prediction consumption data of each target user in the distribution time period through the virtual resource consumption prediction model according to the current user characteristics of each target user;
the matching module is used for matching the virtual resource prediction consumption data of each target user with a target virtual resource allocation rule;
and the pushing module is used for pushing the target virtual resource allocation rule to a target user corresponding to the matched virtual resource prediction consumption data.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method of any of claims 1 to 7 are implemented by the processor 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.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910883397.6A CN110764902A (en) | 2019-09-18 | 2019-09-18 | Virtual resource allocation method and device based on AI (Artificial Intelligence), computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910883397.6A CN110764902A (en) | 2019-09-18 | 2019-09-18 | Virtual resource allocation method and device based on AI (Artificial Intelligence), computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110764902A true CN110764902A (en) | 2020-02-07 |
Family
ID=69330165
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910883397.6A Pending CN110764902A (en) | 2019-09-18 | 2019-09-18 | Virtual resource allocation method and device based on AI (Artificial Intelligence), computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110764902A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112101720A (en) * | 2020-08-10 | 2020-12-18 | 北京思特奇信息技术股份有限公司 | Method and system for allocating group resources |
| CN112418654A (en) * | 2020-11-19 | 2021-02-26 | 百度在线网络技术（北京）有限公司 | Resource allocation method and device, electronic equipment and storage medium |
| CN113159829A (en) * | 2021-03-19 | 2021-07-23 | 北京京东拓先科技有限公司 | Virtual asset allocation method and device and electronic equipment |
| CN113822722A (en) * | 2021-09-28 | 2021-12-21 | 北京沃东天骏信息技术有限公司 | Virtual resource distribution control method and device and server |
| CN114531287A (en) * | 2022-02-17 | 2022-05-24 | 恒安嘉新（北京）科技股份公司 | Method, device, equipment and medium for detecting virtual resource acquisition behavior |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020152116A1 (en) * | 2001-01-30 | 2002-10-17 | Yan Kent J. | Method and system for generating fixed and/or dynamic rebates in credit card type transactions |
| CN108564458A (en) * | 2018-01-09 | 2018-09-21 | 秒钱（北京）信息服务有限公司 | A kind of consumption predictions method and system based on Monte Carlo simulation |
| CA3011592A1 (en) * | 2018-07-16 | 2018-11-12 | Banque Nationale Du Canada | System and method for managing a retail rewards program |
| CN109214585A (en) * | 2018-09-25 | 2019-01-15 | 平安科技（深圳）有限公司 | Customer consumption prediction technique, device, electronic equipment and storage medium |
| CN110020914A (en) * | 2019-03-05 | 2019-07-16 | 泉州市优拓信息技术有限公司 | A kind of consumption circulating system |
| CN110246037A (en) * | 2019-04-19 | 2019-09-17 | 阿里巴巴集团控股有限公司 | Transaction feature prediction technique, device, server and readable storage medium storing program for executing |
-
2019
- 2019-09-18 CN CN201910883397.6A patent/CN110764902A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020152116A1 (en) * | 2001-01-30 | 2002-10-17 | Yan Kent J. | Method and system for generating fixed and/or dynamic rebates in credit card type transactions |
| CN108564458A (en) * | 2018-01-09 | 2018-09-21 | 秒钱（北京）信息服务有限公司 | A kind of consumption predictions method and system based on Monte Carlo simulation |
| CA3011592A1 (en) * | 2018-07-16 | 2018-11-12 | Banque Nationale Du Canada | System and method for managing a retail rewards program |
| CN109214585A (en) * | 2018-09-25 | 2019-01-15 | 平安科技（深圳）有限公司 | Customer consumption prediction technique, device, electronic equipment and storage medium |
| CN110020914A (en) * | 2019-03-05 | 2019-07-16 | 泉州市优拓信息技术有限公司 | A kind of consumption circulating system |
| CN110246037A (en) * | 2019-04-19 | 2019-09-17 | 阿里巴巴集团控股有限公司 | Transaction feature prediction technique, device, server and readable storage medium storing program for executing |
Non-Patent Citations (1)
| Title |
|---|
| 王延荣 等: "《市场营销学》", 31 August 2005, 河南人民出版社, pages: 44 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112101720A (en) * | 2020-08-10 | 2020-12-18 | 北京思特奇信息技术股份有限公司 | Method and system for allocating group resources |
| CN112101720B (en) * | 2020-08-10 | 2024-04-02 | 北京思特奇信息技术股份有限公司 | Method and system for distributing group resources |
| CN112418654A (en) * | 2020-11-19 | 2021-02-26 | 百度在线网络技术（北京）有限公司 | Resource allocation method and device, electronic equipment and storage medium |
| CN112418654B (en) * | 2020-11-19 | 2024-04-09 | 百度在线网络技术（北京）有限公司 | Resource allocation method and device, electronic equipment and storage medium |
| CN113159829A (en) * | 2021-03-19 | 2021-07-23 | 北京京东拓先科技有限公司 | Virtual asset allocation method and device and electronic equipment |
| CN113822722A (en) * | 2021-09-28 | 2021-12-21 | 北京沃东天骏信息技术有限公司 | Virtual resource distribution control method and device and server |
| CN114531287A (en) * | 2022-02-17 | 2022-05-24 | 恒安嘉新（北京）科技股份公司 | Method, device, equipment and medium for detecting virtual resource acquisition behavior |
| CN114531287B (en) * | 2022-02-17 | 2024-06-11 | 恒安嘉新（北京）科技股份公司 | Method, device, equipment and medium for detecting virtual resource acquisition behavior |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110764902A (en) | Virtual resource allocation method and device based on AI (Artificial Intelligence), computer equipment and storage medium | |
| CN107040397B (en) | Service parameter acquisition method and device | |
| CN110288193B (en) | Task monitoring processing method and device, computer equipment and storage medium | |
| CN111192144A (en) | Financial data prediction method, device, equipment and storage medium | |
| CN113626241B (en) | Abnormality processing method, device, equipment and storage medium for application program | |
| CN109754290B (en) | Game data processing method and device | |
| CN111881158A (en) | Management report data processing method and device, computer system and readable storage medium | |
| CN112598513B (en) | Method and device for identifying stockholder risk transaction behaviors | |
| CN110751376B (en) | Work order distribution scheduling method and device, computer equipment and storage medium | |
| CN115879017A (en) | Automatic classification and grading method and device for power sensitive data and storage medium | |
| CN115545886A (en) | Overdue risk identification method, overdue risk identification device, overdue risk identification equipment and storage medium | |
| CN115936895A (en) | Risk assessment method, device and equipment based on artificial intelligence and storage medium | |
| CN107871213B (en) | Transaction behavior evaluation method, device, server and storage medium | |
| CN113554301A (en) | Production plan scheduling method and system | |
| CN111738868A (en) | Anti-money laundering anti-terrorist financing risk monitoring method, device, computer equipment and storage medium | |
| CN116187675A (en) | Task allocation method, device, equipment and storage medium | |
| CN112712270B (en) | Information processing method, device, equipment and storage medium | |
| CN114881761A (en) | Determination method of similar sample and determination method of credit limit | |
| CN115907898A (en) | Method for recommending financial products to reinsurance client and related equipment | |
| CN112529319A (en) | Grading method and device based on multi-dimensional features, computer equipment and storage medium | |
| CN113987351A (en) | Artificial intelligence based intelligent recommendation method and device, electronic equipment and medium | |
| CN112686702A (en) | Wool party identification method and device, computer equipment and storage medium | |
| CN113450208A (en) | Loan risk change early warning and model training method and device | |
| US20240037586A1 (en) | Influence scoring for segment analysis systems and methods | |
| CN107678841B (en) | Method and device for controlling underwriting processing, computer equipment and storage medium |
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 |