CN117391842A - Resource transfer ratio determining method, device, computer equipment and storage medium - Google Patents
Resource transfer ratio determining method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN117391842A CN117391842A CN202311329822.XA CN202311329822A CN117391842A CN 117391842 A CN117391842 A CN 117391842A CN 202311329822 A CN202311329822 A CN 202311329822A CN 117391842 A CN117391842 A CN 117391842A
- Authority
- CN
- China
- Prior art keywords
- value
- determining
- contribution
- service
- user
- 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
- 238000012546 transfer Methods 0.000 title claims abstract description 127
- 238000000034 method Methods 0.000 title claims abstract description 114
- 230000008569 process Effects 0.000 claims description 61
- 230000007774 longterm Effects 0.000 claims description 33
- 238000004590 computer program Methods 0.000 claims description 30
- 238000012549 training Methods 0.000 claims description 21
- 238000012545 processing Methods 0.000 claims description 16
- 230000002787 reinforcement Effects 0.000 claims description 13
- 238000012804 iterative process Methods 0.000 claims description 8
- 239000002131 composite material Substances 0.000 claims description 2
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 230000001419 dependent effect Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 9
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 230000008520 organization Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/092—Reinforcement learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Development Economics (AREA)
- Technology Law (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a method, a device, computer equipment and a storage medium for determining a resource transfer ratio, and relates to the field of artificial intelligence. The method comprises the following steps: determining service value data of the user according to service index data of the user in the historical period; determining a target contribution level of the user according to the service value data; and inputting the target contribution level into the target ratio determination model to obtain a target resource transfer ratio corresponding to the target contribution level output by the target ratio determination model. The method is not dependent on manual subjective adjustment any more, and the determined target resource transfer ratio can be more objective and accurate by determining the model through the target ratio.
Description
Technical Field
The present disclosure relates to the field of artificial intelligence, and in particular, to a method, an apparatus, a computer device, and a storage medium for determining a resource transfer ratio.
Background
With the development of artificial intelligence technology, various service services are introduced in a service organization, and the resource transfer ratio of the service services affects the handling frequency of users on the service services, and further affects the long-term gain of the service services for the service organization, so that it is important to accurately determine the resource transfer ratio.
Currently, the determination of the resource transfer ratio of each service is usually performed manually, and subjective adjustment is performed on the standard resource transfer ratio according to factors such as the service capacity and the service requirement of each user. For example, when the service capability of the user is poor and the service requirement is high, the standard resource transfer ratio is increased.
However, this method can complete the determination of the resource transfer ratio, but has a problem that it is difficult to objectively and accurately determine the resource transfer ratio.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a resource transfer ratio determining method, apparatus, computer device, and storage medium that can objectively and accurately determine a resource transfer ratio.
In a first aspect, the present application provides a method for determining a resource transfer ratio, including:
determining service value data of the user according to service index data of the user in the historical period; the service value data is used for representing at least one of service handling stability and service handling capacity of the user;
determining a target contribution level of the user according to the service value data;
and inputting the target contribution level into the target ratio determination model to obtain a target resource transfer ratio corresponding to the target contribution level output by the target ratio determination model.
In one embodiment, determining a target contribution level of a user according to business value data includes:
according to the service value data, calculating to obtain the comprehensive contribution value grading value of the user;
and determining the target contribution grade according to the comprehensive contribution value grading value.
In one embodiment, the number of service value data is a plurality, and the comprehensive contribution value scoring value of the user is calculated according to the service value data, including:
determining the business value weight corresponding to each business value data;
and carrying out statistical processing on each business value data according to the business value weight to obtain a comprehensive contribution value score.
In one embodiment, determining the target contribution rank from the composite contribution value score value includes:
determining a comprehensive contribution value scoring interval to which the comprehensive contribution value scoring value belongs;
and taking the contribution grade corresponding to the comprehensive contribution value scoring interval as a target contribution grade.
In one embodiment, determining the business value data of the user according to the business index data of the user in the history period includes:
according to the service index data, determining a service index maximum value, a service index minimum value and a service index median in the service index data;
And calculating to obtain service value data according to the service index data, the service index maximum value, the service index minimum value and the service index median.
In one embodiment, the method further comprises:
acquiring sample service value data of each user;
for each user, determining the sample contribution level of the user according to the sample service value data;
and performing reinforcement learning training on the initial ratio determination model based on the contribution level of each sample to obtain a target ratio determination model.
In one embodiment, based on the contribution level of each sample, performing reinforcement learning training on the initial ratio determination model to obtain a target ratio determination model, including:
for one iteration process, inputting each sample contribution level into the intermediate ratio determining model to obtain an intermediate resource transfer ratio corresponding to each sample contribution level output by the intermediate ratio determining model;
determining a reward value corresponding to the current iteration process according to each intermediate resource transfer ratio;
and adjusting the model parameters of the intermediate resource transfer ratio according to the reward value.
In one embodiment, determining the prize value corresponding to the current iterative process according to each intermediate resource transfer ratio includes:
Acquiring a long-term gain contribution value of the current iteration process according to each intermediate resource transfer ratio, and acquiring a short-term gain contribution value of the current iteration process according to each intermediate resource transfer ratio;
and determining a reward value corresponding to the current iteration process according to the long-term gain contribution value, the short-term gain contribution value and the preset value network parameter.
In one embodiment, obtaining the long-term gain contribution value of the current iteration process according to each intermediate resource transfer ratio value includes:
determining satisfaction data corresponding to each sample contribution level according to the intermediate resource transfer ratio corresponding to each sample contribution level;
and determining a long-term gain contribution value of the current iteration process according to the satisfaction data and the service gain contribution value of each user in the historical period.
In one embodiment, obtaining the short-term gain contribution value of the current iteration process according to each intermediate resource transfer ratio value includes:
acquiring user basic information of each user, and inputting the user basic information into a regression model to obtain predicted default probability of each user output by the regression model;
and determining a short-term gain contribution value of the current iteration process according to each predicted default probability and the intermediate resource transfer ratio corresponding to each sample contribution level.
In a second aspect, the present application further provides a resource transfer ratio determining apparatus, including:
the value determining module is used for determining service value data of the user according to the service index data of the user in the historical period; the service value data is used for representing at least one of service handling stability and service handling capacity of the user;
the grade determining module is used for determining the target contribution grade of the user according to the service value data;
and the ratio determining module is used for inputting the target contribution level into the target ratio determining model to obtain a target resource transfer ratio corresponding to the target contribution level output by the target ratio determining model.
In a third aspect, the present application also provides 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:
determining service value data of the user according to service index data of the user in the historical period; the service value data is used for representing at least one of service handling stability and service handling capacity of the user;
determining a target contribution level of the user according to the service value data;
and inputting the target contribution level into the target ratio determination model to obtain a target resource transfer ratio corresponding to the target contribution level output by the target ratio determination model.
In a fourth aspect, the present application also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
determining service value data of the user according to service index data of the user in the historical period; the service value data is used for representing at least one of service handling stability and service handling capacity of the user;
determining a target contribution level of the user according to the service value data;
and inputting the target contribution level into the target ratio determination model to obtain a target resource transfer ratio corresponding to the target contribution level output by the target ratio determination model.
In a fifth aspect, the present application also provides a computer program product comprising a computer program which, when executed by a processor, performs the steps of:
determining service value data of the user according to service index data of the user in the historical period; the service value data is used for representing at least one of service handling stability and service handling capacity of the user;
determining a target contribution level of the user according to the service value data;
and inputting the target contribution level into the target ratio determination model to obtain a target resource transfer ratio corresponding to the target contribution level output by the target ratio determination model.
The method, the device, the computer equipment and the storage medium for determining the resource transfer ratio determine the service value data of the user according to the service index data of the user in the historical period, further determine the target contribution level of the user according to the determined service value data, and finally input the target contribution level into the target ratio determination model to obtain the target resource transfer ratio corresponding to the target contribution level output by the target ratio determination model. Compared with the prior art, the method and the device have the advantages that the target resource transfer ratio is determined through manual subjectivity, the service value data representing the service capacity of the user can be determined more accurately according to the service index data of the user, the target contribution level of the user is further determined, finally, the target resource transfer ratio corresponding to each target contribution level is determined through the target ratio determination model, manual subjectivity adjustment is not relied on, and the determined target resource transfer ratio is objective and accurate through the target ratio determination model.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the related art, the drawings that are required to be used in the embodiments or the related technical descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to the drawings without inventive effort for a person having ordinary skill in the art.
FIG. 1 is an application environment diagram of a method for determining a resource transfer ratio according to the present embodiment;
fig. 2 is a flow chart of a first method for determining a resource transfer ratio according to the present embodiment;
fig. 3 is a schematic flow chart of determining a target contribution level according to the present embodiment;
fig. 4 is a schematic flow chart of a training target ratio determining model according to the present embodiment;
FIG. 5 is a flowchart of determining a prize value according to the present embodiment;
fig. 6 is a flowchart of a second method for determining a resource transfer ratio according to the present embodiment;
fig. 7 is a block diagram of a first resource transfer ratio determining apparatus according to the present embodiment;
fig. 8 is a block diagram of a second resource transfer ratio determining apparatus according to the present embodiment;
fig. 9 is a block diagram of a third resource transfer ratio determining apparatus according to the present embodiment;
fig. 10 is a block diagram of a fourth resource transfer ratio determining apparatus according to the present embodiment;
fig. 11 is an internal structure diagram of a computer device according to the present embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The method for determining the resource transfer ratio provided by the embodiment of the application can be applied to an application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The data storage system may store data that the server 104 needs to process. The data storage system may be integrated on the server 104 or may be located on a cloud or other network server. The server 104 may determine service value data of the user according to service index data of the user in the history period, determine a target contribution level of the user according to the service value data, and finally input the target contribution level into the target ratio determining model to obtain a target resource transfer ratio corresponding to the target contribution level output by the target ratio determining model. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices, and portable wearable devices, where the internet of things devices may be smart speakers, smart televisions, smart air conditioners, smart vehicle devices, and the like. The portable wearable device may be a smart watch, smart bracelet, headset, or the like. The server 104 may be implemented as a stand-alone server or as a server cluster of multiple servers.
In an exemplary embodiment, as shown in fig. 2, a resource transfer ratio determining method is provided, and an example of application of the method to the server 104 in fig. 1 is described, including the following steps S201 to S203. Wherein:
s201, determining service value data of the user according to service index data of the user in the historical period.
The service index data may be index data generated by a user during a service handling process, and optionally, service value data may be calculated based on the service index data. For example, the following traffic index data may be used: the average daily loan, the average information rate and the standard deviation of the loan are determined to obtain the loan business value (namely business value data); the following traffic index data may be used: average daily deposit, average deposit rate, and deposit standard deviation, determining to obtain liability business value (i.e. business value data); the following traffic index data may be used: the intermediate service contribution and the intermediate service transaction times are determined to obtain the intermediate service value (i.e. service value data).
Wherein the business value data is used to characterize at least one of business handling stability and business handling capacity of the user. Optionally, the number of business value data is a plurality. Such as loan business value, liability business value, intermediate business value, etc.
Optionally, there are various ways to determine the service value data of the user according to the service index data of the user in the history period, which is not limited in this application. One of the alternative implementation manners may be to determine the service value data of the user according to the service index data of the user in the history period by using an efficacy coefficient method. Another alternative implementation manner may be to determine, according to the service indicator data, a service indicator maximum value, a service indicator minimum value, and a service indicator median value in the service indicator data; and calculating to obtain service value data according to the service index data, the service index maximum value, the service index minimum value and the service index median.
Specifically, according to the acquired business index data of the user, a business index maximum value, a business index minimum value and a business index median value of the business index are searched from each business index data, the size relation between each business index data and the business index median value is judged, and when the business index data is larger than the business index median value, the business index data is adjusted according to the following formula (1-1) to obtain a business adjustment score; when the business index data is smaller than the business index median, processing the business index data according to the following formula (1-2) to obtain business adjustment scores; and carrying out average value processing on the basis of all the determined service adjustment scores to obtain service actual scores, and carrying out weighted calculation according to each service actual score so as to determine and obtain each service value data.
Wherein v is k For the service adjustment score, v is the service index data, v max For maximum business index, v mid Is the median value of the business index, v total Is the total score corresponding to the business index data.
Wherein v is k For the service adjustment score, v is the service index data, v min Is minimum value of service index, v mid Is the median value of the business index, v total Is the total score corresponding to the business index data.
S202, determining the target contribution level of the user according to the service value data.
The target contribution level may be a level for characterizing the overall contribution of the user to the service.
Optionally, according to the service value data, determining a service value weight corresponding to each service value data, calculating a weighted sum value between each service value data and each service value weight, determining a contribution level corresponding to a weighted sum section to which the weighted sum value belongs, and taking the contribution level as a target contribution level of the user.
S203, inputting the target contribution level into the target ratio determination model to obtain a target resource transfer ratio corresponding to the target contribution level output by the target ratio determination model.
Wherein the target ratio determination model may be a model for determining a target resource conversion ratio, alternatively the target ratio determination model may be a neural network model. The target resource conversion ratio may be a proportional relationship required for performing resource conversion, such as loan interest rate.
Optionally, the target contribution level is input into a target proportion determining model, and the target proportion determining model analyzes the target contribution level, so as to obtain a target resource transfer ratio corresponding to the target contribution level.
According to the resource transfer ratio determining method, the service value data of the user is determined according to the service index data of the user in the historical period, the target contribution level of the user is further determined according to the determined service value data, and finally the target contribution level is input into the target ratio determining model to obtain the target resource transfer ratio corresponding to the target contribution level output by the target ratio determining model. Compared with the prior art, the method and the device have the advantages that the target resource transfer ratio is determined through manual subjectivity, the service value data representing the service capacity of the user can be determined more accurately according to the service index data of the user, the target contribution level of the user is further determined, finally, the target resource transfer ratio corresponding to each target contribution level is determined through the target ratio determination model, manual subjectivity adjustment is not relied on, and the determined target resource transfer ratio is objective and accurate through the target ratio determination model.
FIG. 3 is a flow diagram of determining a target contribution level in one embodiment. In order to ensure the accuracy of the determined target contribution level, on the basis of the above embodiment, this embodiment provides an alternative way of determining the target contribution level, which includes the following steps:
s301, calculating to obtain the comprehensive contribution value grading value of the user according to the service value data.
Optionally, determining the business value weight corresponding to each business value data, and performing statistical processing on each business value data according to the business value weight to obtain the comprehensive contribution value score.
Specifically, the business value weight corresponding to each business value data is obtained, the business value data and the weighted sum value between the business value weights corresponding to the business value data are calculated, and the weighted sum value is used as the comprehensive contribution value score.
It should be noted that, in this embodiment, the comprehensive contribution value scoring value of the user may be further determined by the following formula (1-3) based on each service index data corresponding to the service value data, a service index weight corresponding to the service index data, and a service value weight corresponding to the service value data.
V＝∑w i (∑w ij V ij ) (1-3)
Wherein V is the total contribution value score value, w i For the business value weight corresponding to the ith business value data, w ij The business index weight of the j business index data corresponding to the i business value data is V ij And j business index data corresponding to the i business value data.
S302, determining a target contribution level according to the comprehensive contribution value grading value.
Optionally, determining a comprehensive contribution value scoring interval to which the comprehensive contribution value scoring value belongs; and taking the contribution grade corresponding to the comprehensive contribution value scoring interval as a target contribution grade.
Specifically, based on the obtained comprehensive contribution value score value, determining a comprehensive contribution value score interval to which the comprehensive contribution value score value belongs, further determining a contribution grade corresponding to the comprehensive contribution value score interval, and taking the contribution grade as a target contribution grade.
According to the method for determining the target contribution level, the comprehensive contribution value of the user is calculated according to the service value data, and the target contribution level is determined according to the comprehensive contribution value, the comprehensive contribution value of the user is determined based on the service value data of the user, and the target contribution level is further determined according to the comprehensive contribution value of the user, so that accuracy and rationality for determining the target contribution level are improved.
FIG. 4 is a flow diagram of training a target ratio determination model in one embodiment. In order to ensure the accuracy of the training of the target ratio determining model, on the basis of the above embodiment, the present embodiment provides an alternative way of training the target ratio determining model, which includes the following steps:
s401, sample service value data of each user is obtained.
The sample service value data may be service value data as a sample.
Optionally, service value data of each user in a preset history period is obtained as sample service value data.
S402 determines, for each user, a sample contribution level of the user from the sample business value data.
Wherein the sample contribution level may be a contribution level as a sample.
Optionally, for each user, the manner of determining the sample contribution level of the user according to the sample service value data is the same as that described in steps S301 to S302 in the foregoing embodiment, which is not described herein in detail.
S403, performing reinforcement learning training on the initial ratio determination model based on the contribution level of each sample to obtain a target ratio determination model.
Wherein the initial ratio determination model may be an untrained ratio determination model.
Optionally, for the first iteration process, inputting each sample contribution level to the initial ratio determining model to obtain an intermediate resource transfer ratio corresponding to each sample contribution level output by the initial ratio determining model, determining a reward value corresponding to the first iteration process according to the intermediate resource transfer ratio, and adjusting the initial ratio determining model according to the reward value to obtain the intermediate ratio determining model. Inputting the contribution levels of the samples into the intermediate ratio determining model for any iteration process except the first iteration process to obtain intermediate resource transfer ratios corresponding to the contribution levels of the samples output by the intermediate ratio determining model; determining a reward value corresponding to the current iteration process according to each intermediate resource transfer ratio; and adjusting the model parameters of the intermediate resource transfer ratio according to the reward value. Stopping reinforcement learning training until the current iteration process reaches the preset iteration times, and taking the intermediate ratio determination model after the last parameter adjustment as a target ratio determination model. The intermediate ratio determining model may be a ratio determining model to be adjusted in the iterative training process. The reward value may be a reward function for adjusting the model parameter.
Specifically, for one iteration process, each sample contribution level can be input into an intermediate ratio determination model, the intermediate ratio determination model analyzes each sample contribution level, so as to obtain an intermediate resource transfer ratio corresponding to each sample contribution level, a loss value of the model is determined by the intermediate ratio in the current iteration process according to each determined intermediate resource transfer ratio, the loss value is taken as a reward value corresponding to the current iteration process, and finally, model parameters of the intermediate resource transfer ratio are adjusted according to the reward value.
According to the training target ratio determining model method, sample service value data of each user are obtained, for each user, sample contribution levels of the user are determined according to the sample service value data, reinforcement learning training is conducted on the initial ratio determining model based on the sample contribution levels, and the target ratio determining model is obtained. According to the method, reinforcement learning training is carried out on the initial ratio determination model in a reinforcement learning training mode, so that a more accurate target ratio determination model can be obtained.
FIG. 5 is a flow chart of determining a prize value in one embodiment. In order to determine the model parameters of the contrast value determination model more accurately through the prize value, on the basis of the above embodiment, this embodiment provides an alternative way of determining the prize value, which includes the following steps:
S501, obtaining a long-term gain contribution value of the current iteration process according to each intermediate resource transfer ratio, and obtaining a short-term gain contribution value of the current iteration process according to each intermediate resource transfer ratio.
The long-term gain contribution value may be a long-term gain contribution degree provided by the user to the service organization. The short-term gain contribution value may be a short-term gain contribution provided by the user to the service facility.
Optionally, the method for obtaining the long-term gain contribution value of the current iterative process according to the intermediate resource transfer ratio may be to determine satisfaction data corresponding to each sample contribution level according to the intermediate resource transfer ratio corresponding to each sample contribution level; and determining a long-term gain contribution value of the current iteration process according to the satisfaction data and the service gain contribution value of each user in the historical period.
Specifically, the total resource limit and approval time of the user are obtained, the satisfaction data corresponding to each user is determined according to the intermediate resource transfer ratio, the total resource limit (such as loan limit) and the approval time through the following formula (1-4), the average satisfaction data corresponding to each sample contribution level is calculated according to the satisfaction data of each user, the average satisfaction data and the service gain contribution value of each user in the historical period, and the long-term gain contribution value of each user in the current iteration process is determined according to the following formula (1-5).
S k ＝a 1 ·r k +a 2 ·c k +a 3 ·t k +a 4 (1-4)
Wherein S is k Satisfaction data for kth user, r k Intermediate resource transfer ratio, a, for kth user 1 For intermediate resource transfer ratioCorresponding weight, c k A is the total resource limit of the kth user 2 Weight corresponding to total amount of resources, t k A is the approval time of the kth user 3 For the corresponding weight of the approval time, a 4 Is a preset random disturbance term.
Wherein Con k,τ+1 For the long-term gain contribution value of kth user in tau+1 period in the current iteration process, con k,τ For the service gain contribution value of the kth user i at tau, namely the segment in the current iteration process, S k,τ User satisfaction data for the kth user during period tau,is the average satisfaction data.
It should be noted that, in the above formula (1-4), the weight a corresponds to the intermediate resource transfer ratio 1 Weight a corresponding to total resource limit 2 Weight a corresponding to approval time 3 And a preset random disturbance term a 4 The determination method of (1) may be that satisfaction data of the users are collected through a Likert scale, and according to the determined satisfaction data of each user, the values of each weight and random disturbance term are obtained through a least square method, namely, the values are shown in the following formulas (1-6).
Wherein S is k Satisfaction data for kth user, r k Intermediate resource transfer ratio, a, for kth user 1 C is the weight corresponding to the intermediate resource transfer ratio k A is the total resource limit of the kth user 2 Weight corresponding to total amount of resources, t k A is the approval time of the kth user 3 For the corresponding weight of the approval time, a 4 Is a pre-preparationAnd setting random disturbance terms.
Optionally, the method for obtaining the short-term gain contribution value of the current iterative process according to the intermediate resource transfer ratio may be to obtain user basic information of each user, and input the user basic information into the regression model to obtain the predicted default probability of each user output by the regression model; and determining a short-term gain contribution value of the current iteration process according to each predicted default probability and the intermediate resource transfer ratio corresponding to each sample contribution level.
The user basic information may be basic information of each dimension of the user acquired from the service mechanism. Alternatively, the user basic information may include personal basic information (including characteristics of age, sex, occupation, education level, marital status, and user contribution level), historical transaction information (including characteristics of loan amount, default amount, and loan interest rate versus reference level), and socioeconomic information (including characteristics of site loss rate, site expansion rate, and site GDP acceleration rate). The regression model may be a selected support vector regression model (Support Vector Regression, SVR).
Specifically, user basic information of each user is obtained, coding processing (such as one-hot coding) is carried out on the user basic information, the user basic information after coding processing is obtained, the user basic information after coding processing is input into a value regression model, and the regression model predicts the user basic information after coding processing through a linear kernel function, so that prediction default probability of each user is obtained.
Obtaining a preset standard resource transfer ratio (such as a deposit basic interest rate), a daily average resource amount (such as a daily average credit amount) of each user and an intermediate resource transfer ratio corresponding to each sample contribution level, and determining to obtain a resource point difference gain value (such as a loan point difference profit) through the following formula (1-7); acquiring the corresponding resource quantity (such as loan quantity) of each user, and determining to acquire a resource loss value (such as loan loss value) according to the corresponding resource quantity of each user and the predicted default probability of each user through the following formula (1-8); and acquiring a preset service mechanism operation expenditure, and determining a short-term gain contribution value of the current iteration process according to the resource point difference gain value, the resource loss value and the difference value (the following formulas 1-9) between the service mechanism operation expenditure.
Inc τ ＝∑ i＝0 M i (r i -r d ) (1-7)
Wherein, inc τ For the resource point difference gain value, M i R is the average daily resource limit of each user i For presetting standard resource transfer ratio, r d Is an intermediate resource transfer ratio.
Wherein Ris τ For the resource loss value, M n L is the resource quantity of each user n The probability of breach is predicted for each user.
P τ ＝Inc τ -Ris τ -Bas τ (1-9)
Wherein P is τ For short-term gain contribution, inc τ As the gain value of the resource point difference, ris τ Bas is a resource loss value τ And (3) operating expenses for the service institutions.
S502, determining a reward value corresponding to the current iteration process according to the long-term gain contribution value, the short-term gain contribution value and the preset value network parameter.
The preset value network parameters may be preset value network model obtaining model parameters. Optionally, the preset value network parameter is used to measure the relative importance between the long-term gain contribution and the short-term gain contribution.The larger the short-term gain contribution value, the more important.
Optionally, the determined long-term gain contribution value, short-term gain contribution value and preset value network parameter are input into the following formulas (1-10), and the corresponding reward value in the iterative process is determined.
Wherein, the reward is a reward value,for presetting value network parameters, P τ For short-term gain contribution, con k，τ Contributing to the long-term gain.
According to the method for determining the rewarding value, the long-term gain contribution value of the current iteration process is obtained according to each intermediate resource transfer ratio, the short-term gain contribution value of the current iteration process is obtained according to each intermediate resource transfer ratio, and finally the rewarding value corresponding to the current iteration process is determined according to the long-term gain contribution value, the short-term gain contribution value and the preset value network parameter. In the process of adjusting model parameters, the method considers the long-term gain contribution value and the short-term gain contribution value, determines more reasonable and accurate rewards values according to the long-term gain contribution value, the short-term gain contribution value and the preset value network parameters, and finally adjusts the model parameters of the model determined by the comparison values more accurately according to the rewards values.
In one embodiment, this embodiment provides an alternative way of determining the resource transfer ratio, and the method is used for a server to be described as an example. As shown in fig. 6, the method includes the steps of:
s601, sample service value data of each user is obtained.
S602, for each user, determining a sample contribution level of the user according to the sample business value data.
S603, for one iteration process, inputting each sample contribution level into the intermediate ratio determining model to obtain an intermediate resource transfer ratio corresponding to each sample contribution level output by the intermediate ratio determining model.
The intermediate ratio determining model may be a model obtained by adjusting model parameters of the initial ratio determining model in the initial iteration process.
S604, determining satisfaction data corresponding to each sample contribution level according to the intermediate resource transfer ratio corresponding to each sample contribution level.
S605, determining a long-term gain contribution value of the current iteration process according to each satisfaction data and the service gain contribution value of each user in the historical period.
S606, obtaining user basic information of each user, and inputting the user basic information into the regression model to obtain the predicted default probability of each user output by the regression model.
S607, determining a short-term gain contribution value of the current iteration process according to each predicted default probability and the intermediate resource transfer ratio corresponding to each sample contribution level.
And S608, determining a reward value corresponding to the current iteration process according to the long-term gain contribution value, the short-term gain contribution value and the preset value network parameter.
S609, according to the rewarding value, the model parameter of the intermediate resource transfer ratio is adjusted.
And S610, when the iteration times reach a preset iteration threshold, finishing reinforcement learning training on the initial ratio determination model to obtain a target ratio determination model.
S611 determines a service index maximum value, a service index minimum value and a service index median value in the service index data according to the service index data.
S612, calculating to obtain service value data according to the service index data, the service index maximum value, the service index minimum value and the service index median.
Wherein the business value data is used to characterize at least one of business handling stability and business handling capacity of the user.
S613 determines a service value weight corresponding to each service value data.
S614, according to the business value weight, each business value data is subjected to statistical processing to obtain a comprehensive contribution value score.
S615 determines a comprehensive contribution value score interval to which the comprehensive contribution value score belongs.
S616 takes the contribution level corresponding to the integrated contribution value scoring interval as the target contribution level.
S617 inputs the target contribution level into the target ratio determination model to obtain a target resource transfer ratio corresponding to the target contribution level output by the target ratio determination model.
It should be noted that, in this embodiment, steps S601 to S610 are processes of reinforcement learning training on the target ratio determining model, and steps S611 to S617 are processes of processing the determined target contribution level through the target ratio determining model to obtain the target resource transfer ratio.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a resource transfer ratio determining device for realizing the above related resource transfer ratio determining method. The implementation of the solution provided by the apparatus is similar to the implementation described in the above method, so the specific limitation in the embodiments of one or more resource transfer ratio determining apparatuses provided below may be referred to the limitation of the resource transfer ratio determining method hereinabove, and will not be described herein.
In an exemplary embodiment, as shown in fig. 7, there is provided a resource transfer ratio determining apparatus 1, including: a value determination module 10, a rank determination module 11, and a ratio determination module 12, wherein:
a value determining module 10, configured to determine service value data of the user according to service index data of the user in the history period; the service value data is used for representing at least one of service handling stability and service handling capacity of the user;
the grade determining module 11 is used for determining a target contribution grade of the user according to the service value data;
the ratio determining module 12 is configured to input the target contribution level into the target ratio determining model, and obtain a target resource transfer ratio corresponding to the target contribution level output by the target ratio determining model.
In one embodiment, as shown in fig. 8, the rank determination module 11 in fig. 7 includes:
a score determining unit 110, configured to calculate and obtain a comprehensive contribution value score value of the user according to the service value data;
the rank determining unit 111 is configured to determine a target contribution rank according to the integrated contribution value score value.
In one embodiment, the score determining unit 110 in fig. 8 includes:
The weight determining subunit is used for determining the business value weight corresponding to each business value data;
and the score determining subunit is used for carrying out statistical processing on each business value data according to the business value weight to obtain a comprehensive contribution value score.
In one embodiment, the rank determination unit 111 in fig. 8 includes:
the interval determining subunit is used for determining the comprehensive contribution value scoring interval to which the comprehensive contribution value scoring value belongs;
and the grade determining subunit is used for taking the contribution grade corresponding to the comprehensive contribution value scoring interval as a target contribution grade.
In one embodiment, as shown in FIG. 9, the value determination module 10 of FIG. 8 includes:
a value determining unit 100, configured to determine, according to the service indicator data, a service indicator maximum value, a service indicator minimum value, and a service indicator median value in the service indicator data;
the value determining unit 101 is configured to calculate and obtain service value data according to the service index data, the service index maximum value, the service index minimum value, and the service index median.
In one embodiment, as shown in fig. 10, the resource transfer ratio determining apparatus 1 in fig. 7 further includes:
a sample data obtaining module 13, configured to obtain sample service value data of each user;
A sample level determining module 14, configured to determine, for each user, a sample contribution level of the user according to the sample service value data;
and the initial model training module 15 is used for performing reinforcement learning training on the initial ratio determination model based on the contribution level of each sample to obtain a target ratio determination model.
In one embodiment, the initial model training module 13 in FIG. 10 includes:
the intermediate ratio determining unit is used for inputting the contribution levels of the samples into the intermediate ratio determining model for one iteration process to obtain intermediate resource transfer ratios corresponding to the contribution levels of the samples output by the intermediate ratio determining model;
the rewarding value determining unit is used for determining a rewarding value corresponding to the current iteration process according to each intermediate resource transfer ratio;
and the parameter adjustment unit is used for adjusting the model parameter of the intermediate resource transfer ratio according to the rewarding value.
In one embodiment, the prize value determining unit includes:
the contribution value determining subunit is used for obtaining a long-term gain contribution value of the current iteration process according to each intermediate resource transfer ratio and obtaining a short-term gain contribution value of the current iteration process according to each intermediate resource transfer ratio;
And the rewarding value determining subunit is used for determining the rewarding value corresponding to the current iteration process according to the long-term gain contribution value, the short-term gain contribution value and the preset value network parameter.
In one embodiment, the contribution value determination subunit comprises:
the satisfaction data sub-component is used for determining satisfaction data corresponding to each sample contribution level according to the intermediate resource transfer ratio corresponding to each sample contribution level;
and the long-term gain determining sub-component is used for determining the long-term gain contribution value of the current iteration process according to the satisfaction data and the service gain contribution value of each user in the historical period.
The breach probability determination sub-assembly is used for acquiring user basic information of each user, inputting the user basic information into the regression model and obtaining the prediction breach probability of each user output by the regression model;
and the short-term gain determining sub-component is used for determining a short-term gain contribution value of the current iteration process according to each predicted default probability and the intermediate resource transfer ratio corresponding to each sample contribution level.
The above-described respective modules in the resource transfer ratio determination apparatus may be implemented in whole or in part by software, hardware, or a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one exemplary embodiment, a computer device is provided, which may be a server, and the internal structure thereof may be as shown in fig. 11. The computer device includes a processor, a memory, an Input/Output interface (I/O) and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used to store target resource transfer ratio data. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication 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 method of determining a resource transfer ratio.
It will be appreciated by those skilled in the art that the structure shown in fig. 11 is merely a block diagram of a portion of the structure associated with the present application and is not limiting of the computer device to which the present application applies, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In one exemplary embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:
determining service value data of the user according to service index data of the user in the historical period; the service value data is used for representing at least one of service handling stability and service handling capacity of the user;
determining a target contribution level of the user according to the service value data;
and inputting the target contribution level into the target ratio determination model to obtain a target resource transfer ratio corresponding to the target contribution level output by the target ratio determination model.
In one embodiment, the processor when executing the computer program further performs the steps of:
According to the service value data, calculating to obtain the comprehensive contribution value grading value of the user;
and determining the target contribution grade according to the comprehensive contribution value grading value.
In one embodiment, the processor when executing the computer program further performs the steps of:
determining the business value weight corresponding to each business value data;
and carrying out statistical processing on each business value data according to the business value weight to obtain a comprehensive contribution value score.
In one embodiment, the processor when executing the computer program further performs the steps of:
determining a comprehensive contribution value scoring interval to which the comprehensive contribution value scoring value belongs;
and taking the contribution grade corresponding to the comprehensive contribution value scoring interval as a target contribution grade.
In one embodiment, the processor when executing the computer program further performs the steps of:
according to the service index data, determining a service index maximum value, a service index minimum value and a service index median in the service index data;
and calculating to obtain service value data according to the service index data, the service index maximum value, the service index minimum value and the service index median.
In one embodiment, the processor when executing the computer program further performs the steps of:
Acquiring sample service value data of each user;
for each user, determining the sample contribution level of the user according to the sample service value data;
and performing reinforcement learning training on the initial ratio determination model based on the contribution level of each sample to obtain a target ratio determination model.
In one embodiment, the processor when executing the computer program further performs the steps of:
for one iteration process, inputting each sample contribution level into the intermediate ratio determining model to obtain an intermediate resource transfer ratio corresponding to each sample contribution level output by the intermediate ratio determining model;
determining a reward value corresponding to the current iteration process according to each intermediate resource transfer ratio;
and adjusting the model parameters of the intermediate resource transfer ratio according to the reward value.
In one embodiment, the processor when executing the computer program further performs the steps of:
acquiring a long-term gain contribution value of the current iteration process according to each intermediate resource transfer ratio, and acquiring a short-term gain contribution value of the current iteration process according to each intermediate resource transfer ratio;
and determining a reward value corresponding to the current iteration process according to the long-term gain contribution value, the short-term gain contribution value and the preset value network parameter.
In one embodiment, the processor when executing the computer program further performs the steps of:
determining satisfaction data corresponding to each sample contribution level according to the intermediate resource transfer ratio corresponding to each sample contribution level;
and determining a long-term gain contribution value of the current iteration process according to the satisfaction data and the service gain contribution value of each user in the historical period.
In one embodiment, the processor when executing the computer program further performs the steps of:
acquiring user basic information of each user, and inputting the user basic information into a regression model to obtain predicted default probability of each user output by the regression model;
and determining a short-term gain contribution value of the current iteration process according to each predicted default probability and the intermediate resource transfer ratio corresponding to each sample contribution level.
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:
determining service value data of the user according to service index data of the user in the historical period; the service value data is used for representing at least one of service handling stability and service handling capacity of the user;
Determining a target contribution level of the user according to the service value data;
and inputting the target contribution level into the target ratio determination model to obtain a target resource transfer ratio corresponding to the target contribution level output by the target ratio determination model.
In one embodiment, a computer program product is provided comprising a computer program which, when executed by a processor, performs the steps of:
determining service value data of the user according to service index data of the user in the historical period; the service value data is used for representing at least one of service handling stability and service handling capacity of the user;
determining a target contribution level of the user according to the service value data;
and inputting the target contribution level into the target ratio determination model to obtain a target resource transfer ratio corresponding to the target contribution level output by the target ratio determination model.
It should be noted that, the data (including, but not limited to, data for analysis, stored data, presented data, etc.) referred to in the present application are all information and data authorized by the user or sufficiently authorized by each party, and the collection, use, and processing of the relevant data are required to meet the relevant regulations.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.
Claims (14)
1. A method for determining a resource transfer ratio, the method comprising:
determining service value data of the user according to service index data of the user in the historical period; the service value data is used for representing at least one of service handling stability and service handling capacity of a user;
determining a target contribution level of the user according to the service value data;
And inputting the target contribution level into a target ratio determination model to obtain a target resource transfer ratio corresponding to the target contribution level output by the target ratio determination model.
2. The method of claim 1, wherein determining the target contribution level of the user based on the business value data comprises:
according to the service value data, calculating to obtain a comprehensive contribution value grading value of the user;
and determining the target contribution grade according to the comprehensive contribution value grading value.
3. The method according to claim 2, wherein the number of the service value data is plural, and the calculating the comprehensive contribution value score value of the user according to the service value data includes:
determining the business value weight corresponding to each business value data;
and carrying out statistical processing on each business value data according to the business value weight to obtain the comprehensive contribution value score.
4. The method of claim 2, wherein said determining said target contribution rank from said composite contribution value score value comprises:
determining a comprehensive contribution value scoring interval to which the comprehensive contribution value scoring value belongs;
And taking the contribution grade corresponding to the comprehensive contribution value scoring interval as the target contribution grade.
5. The method of claim 1, wherein determining the business value data of the user based on the business index data of the user over the historical period of time comprises:
determining a service index maximum value, a service index minimum value and a service index median value in the service index data according to the service index data;
and calculating to obtain the service value data according to the service index data, the service index maximum value, the service index minimum value and the service index median.
6. The method according to claim 1, wherein the method further comprises:
acquiring sample service value data of each user;
for each user, determining a sample contribution level of the user according to the sample service value data;
and performing reinforcement learning training on the initial ratio determination model based on the contribution level of each sample to obtain the target ratio determination model.
7. The method of claim 6, wherein the reinforcement learning training of the initial ratio-determining model based on each of the sample contribution levels to obtain the target ratio-determining model comprises:
For one iteration process, inputting each sample contribution level into an intermediate ratio determination model to obtain an intermediate resource transfer ratio corresponding to each sample contribution level output by the intermediate ratio determination model;
determining a reward value corresponding to the current iterative process according to each intermediate resource transfer ratio;
and determining a model for the target ratio according to the reward value.
8. The method of claim 7, wherein determining the prize value corresponding to the current iterative process based on each of the intermediate resource transfer ratios comprises:
acquiring a long-term gain contribution value of the current iteration process according to each intermediate resource transfer ratio, and acquiring a short-term gain contribution value of the current iteration process according to each intermediate resource transfer ratio;
and determining a reward value corresponding to the current iteration process according to the long-term gain contribution value, the short-term gain contribution value and a preset value network parameter.
9. The method of claim 8, wherein said obtaining the long-term gain contribution of the current iterative process from each of the intermediate resource transfer ratios comprises:
determining satisfaction data corresponding to each sample contribution level according to the intermediate resource transfer ratio corresponding to each sample contribution level;
And determining a long-term gain contribution value of the current iteration process according to each satisfaction data and the service gain contribution value of each user in the historical period.
10. The method of claim 8, wherein said obtaining a short-term gain contribution for a current iterative process from each of said intermediate resource transfer ratios comprises:
acquiring user basic information of each user, and inputting the user basic information into a regression model to obtain predicted default probability of each user output by the regression model;
and determining a short-term gain contribution value of the current iteration process according to each predicted default probability and the intermediate resource transfer ratio corresponding to each sample contribution level.
11. A resource transfer ratio determination apparatus, the apparatus comprising:
the value determining module is used for determining service value data of the user according to the service index data of the user in the historical period; the service value data is used for representing at least one of service handling stability and service handling capacity of a user;
the grade determining module is used for determining the target contribution grade of the user according to the service value data;
And the ratio determining module is used for inputting the target contribution level into a target ratio determining model to obtain a target resource transfer ratio corresponding to the target contribution level output by the target ratio determining model.
12. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 10 when the computer program is executed.
13. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 10.
14. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311329822.XA CN117391842A (en) | 2023-10-13 | 2023-10-13 | Resource transfer ratio determining method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311329822.XA CN117391842A (en) | 2023-10-13 | 2023-10-13 | Resource transfer ratio determining method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117391842A true CN117391842A (en) | 2024-01-12 |
Family
ID=89438429
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311329822.XA Pending CN117391842A (en) | 2023-10-13 | 2023-10-13 | Resource transfer ratio determining method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117391842A (en) |
-
2023
- 2023-10-13 CN CN202311329822.XA patent/CN117391842A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108833458B (en) | Application recommendation method, device, medium and equipment | |
| CN111177473B (en) | Personnel relationship analysis method, device and readable storage medium | |
| CN109784959B (en) | Target user prediction method and device, background server and storage medium | |
| US20200034776A1 (en) | Managing skills as clusters using machine learning and domain knowledge expert | |
| CN105897616B (en) | Resource allocation method and server | |
| CN111340244B (en) | Prediction method, training method, device, server and medium | |
| CN110415036B (en) | User grade determining method, device, computer equipment and storage medium | |
| JP5071851B2 (en) | Prediction device using time information, prediction method, prediction program, and recording medium recording the program | |
| CN115983900A (en) | Method, apparatus, device, medium, and program product for constructing user marketing strategy | |
| Wang et al. | Online Regularization toward Always-Valid High-Dimensional Dynamic Pricing | |
| Almomani et al. | Selecting a good stochastic system for the large number of alternatives | |
| CN109460778B (en) | Activity evaluation method, activity evaluation device, electronic equipment and storage medium | |
| CN116977019A (en) | Merchant recommendation method and device, electronic equipment and storage medium | |
| CN117391842A (en) | Resource transfer ratio determining method, device, computer equipment and storage medium | |
| CN115391666A (en) | Hospital online recommendation method and device, computer equipment and storage medium | |
| EP3901840A1 (en) | Combined prediction system and methods | |
| WO2021129368A1 (en) | Method and apparatus for determining client type | |
| CN114240599A (en) | Loan calculation method and device, computer equipment and storage medium | |
| CN109472454B (en) | Activity evaluation method, activity evaluation device, electronic equipment and storage medium | |
| Rong et al. | Exploring network behavior using cluster analysis | |
| CN109472455B (en) | Activity evaluation method, activity evaluation device, electronic equipment and storage medium | |
| CN116308721B (en) | Information supervision and management method and device, electronic equipment and storage medium | |
| De Mulder et al. | Extending Gaussian process emulation using cluster analysis and artificial neural networks to fit big training sets | |
| Bohlouli et al. | Scalable multi-criteria decision-making: A mapreduce deployed big data approach for skill analytics | |
| US20230259403A1 (en) | Cloud-Based Resource Allocation Using Meters |
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 |