CN114519461A - Transaction time prediction method and device - Google Patents

Transaction time prediction method and device Download PDF

Info

Publication number
CN114519461A
CN114519461A CN202210132185.6A CN202210132185A CN114519461A CN 114519461 A CN114519461 A CN 114519461A CN 202210132185 A CN202210132185 A CN 202210132185A CN 114519461 A CN114519461 A CN 114519461A
Authority
CN
China
Prior art keywords
transaction
time
time interval
sequence
transaction time
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210132185.6A
Other languages
Chinese (zh)
Inventor
刘乙赛
罗涛
施佳子
于海燕
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Industrial and Commercial Bank of China Ltd ICBC
Original Assignee
Industrial and Commercial Bank of China Ltd ICBC
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Industrial and Commercial Bank of China Ltd ICBC filed Critical Industrial and Commercial Bank of China Ltd ICBC
Priority to CN202210132185.6A priority Critical patent/CN114519461A/en
Publication of CN114519461A publication Critical patent/CN114519461A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • 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
    • 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
    • G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Development Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Technology Law (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Biology (AREA)
  • Game Theory and Decision Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The embodiment of the invention discloses a transaction time prediction method and a device, which can be used in the financial field or other technical fields, and the method comprises the following steps: acquiring transaction time sequence data of a target transaction type of a client; generating a transaction time interval sequence according to the transaction time sequence data; inputting the transaction time interval sequence into a preset prediction model to obtain a time interval of the next transaction of the target transaction type by the client, which is output by the prediction model, and further determining the time of the next transaction of the target transaction type by the client according to the time interval and the transaction time sequence data, wherein the prediction model is obtained by training according to a prophet model. The invention realizes the beneficial effect of accurately predicting the time of the next target transaction type transaction of the client.

Description

Transaction time prediction method and device
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a transaction time prediction method and a device.
Background
Every day, thousands of customers carry out transactions such as transfer, payment and the like through banks. It is very meaningful if the transaction rules of the client can be mined from massive bank transaction data, and the client is reminded or recommended appropriately.
At present, in the aspect of time sequence prediction, more mature algorithms exist. For example: a recurrent neural network RNN, a long and short memory network LSTM, linear regression, an ARMA model and the like. However, from the analysis of data level, the operation of the customer through the bank is usually not continuous, the generated time sequence is usually sparse, and the period is generally about 20-40 days, taking the electricity charge as an example, so the machine learning method is not suitable for the prediction problem of bank transaction. Therefore, the prior art lacks a scheme for predicting the transaction time of sparse banking transactions.
Disclosure of Invention
The present invention provides a method and an apparatus for predicting transaction time to solve at least one technical problem in the background art.
In order to achieve the above object, according to one aspect of the present invention, there is provided a transaction time prediction method including:
acquiring transaction time sequence data of a target transaction type of a client;
generating a transaction time interval sequence according to the transaction time sequence data;
inputting the transaction time interval sequence into a preset prediction model to obtain a time interval of the next transaction of the target transaction type by the client, which is output by the prediction model, and further determining the time of the next transaction of the target transaction type by the client according to the time interval and the transaction time sequence data, wherein the prediction model is obtained by training according to a prophet model.
Optionally, the transaction time prediction method further includes:
acquiring a training sample set, wherein training data in the training sample set is a transaction time interval sequence used for model training;
and training the prophet model according to the training sample set to obtain the prediction model.
Optionally, the generating a transaction time interval sequence according to the transaction timing data includes:
generating a transaction time sequence according to the transaction time sequence data;
and generating the transaction time interval sequence by calculating the time difference between any two adjacent items in the transaction time sequence.
Optionally, before the inputting the sequence of transaction time intervals into a preset prediction model, the method further includes:
and if the data in the trading time interval sequence meet the Gaussian distribution, removing the data which is more than N times of the standard deviation of the data in the trading time interval sequence, wherein N is more than 0.
Optionally, the determining, according to the time interval and the transaction timing data, the time when the customer performs the next transaction of the target transaction type specifically includes:
determining the transaction time of the last transaction in the transaction time sequence data;
and determining the time of the customer for the next transaction of the target transaction type according to the transaction time and the time interval.
Optionally, the prophet model includes: the system comprises a trend model and a holiday model, wherein the trend model adopts a piecewise linear function.
In order to achieve the above object, according to another aspect of the present invention, there is provided a transaction time prediction apparatus, comprising:
the transaction time sequence data acquisition unit is used for acquiring the transaction time sequence data of the target transaction type of the client;
the transaction time interval sequence generating unit is used for generating a transaction time interval sequence according to the transaction time sequence data;
and the prediction unit is used for inputting the transaction time interval sequence into a preset prediction model to obtain the time interval of the next transaction of the target transaction type by the client output by the prediction model, and further determining the time of the next transaction of the target transaction type by the client according to the time interval and the transaction time sequence data, wherein the prediction model is obtained by training according to a prophet model.
To achieve the above object, according to another aspect of the present invention, there is also provided a computer device including a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the above transaction time prediction method when executing the computer program.
To achieve the above object, according to another aspect of the present invention, there is also provided a computer readable storage medium having stored thereon a computer program/instructions which, when executed by a processor, implement the steps of the above-described transaction time prediction method.
To achieve the above object, according to another aspect of the present invention, there is also provided a computer program product comprising computer program/instructions which, when executed by a processor, implement the steps of the above-mentioned transaction time prediction method.
The invention has the beneficial effects that:
according to the embodiment of the invention, the prediction model is trained through the prophet model, and the time of the next target transaction type transaction of the client is predicted according to the prediction model, so that the beneficial effect of accurately and efficiently predicting the time of the next target transaction type transaction of the client is realized.
Drawings
In order to more clearly illustrate the embodiments or technical solutions of the present invention, the drawings used in the embodiments or technical solutions in the prior art are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts. In the drawings:
FIG. 1 is a first flowchart of a transaction time prediction method according to an embodiment of the present invention;
FIG. 2 is a second flowchart of a transaction time prediction method according to an embodiment of the present invention;
FIG. 3 is a third flowchart of a transaction time prediction method according to an embodiment of the present invention;
FIG. 4 is a fourth flowchart of a transaction time prediction method according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of transaction timing data according to an embodiment of the invention;
FIG. 6 is a schematic diagram of transaction interval data according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of outlier removal according to an embodiment of the present invention;
FIG. 8 is a graph illustrating predicted results according to an embodiment of the present invention;
fig. 9 is a block diagram showing the construction of a transaction time prediction apparatus according to an embodiment of the present invention;
FIG. 10 is a schematic diagram of a computer apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. 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.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
It should be noted that the terms "comprises" and "comprising," and any variations thereof, in the description and claims of the present invention and the above-described drawings, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict. The present invention will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
It should be noted that, in the technical solution of the present application, the acquisition, storage, use, processing, etc. of data all conform to the relevant regulations of the national laws and regulations.
It should be noted that the transaction time prediction method and apparatus of the present invention can be applied to the financial field, and can also be applied to other technical fields.
Fig. 1 is a first flowchart of a transaction time prediction method according to an embodiment of the present invention, and as shown in fig. 1, the transaction time prediction method according to an embodiment of the present invention includes steps S101 to S103.
Step S101, transaction time sequence data of the target transaction type of the client is obtained.
In one embodiment of the invention, the invention can obtain historical transaction data of the customer from a bank database, and the historical transaction data is usually recorded only when the customer generates an operation, so that the data needs to be processed firstly. Firstly, screening transaction data in a database according to a client id and a transaction type; second, because we need to predict the time the customer is doing the transaction rather than the specific amount, we need to mark the time the customer is doing the transaction with a "1"; finally, the time series needs to be filled up, and the time points where no transaction occurs are marked with "0". This results in transaction timing data for a particular user, a particular transaction type, which can be used for analysis. The visualization results may be as shown in fig. 5.
In one embodiment of the present invention, the target transaction type may be various, for example, water fee, electricity fee, gas fee, super consumer, and the like.
And step S102, generating a transaction time interval sequence according to the transaction time sequence data.
The transaction time series data obtained by the method cannot meet the input format of the prophet model, is not in a common time series data form, is difficult to model, and needs to be processed in a series of ways.
The sparse data conversion method adopted by the method is a phase-by-phase difference method, that is, time point information of behaviors generated by a user is not used as time sequence data, but time intervals generated by two behaviors are used as time sequence data, and the obtained transaction time interval data is shown in fig. 6.
Step S103, inputting the transaction time interval sequence into a preset prediction model, obtaining the time interval of the next transaction of the target transaction type by the customer output by the prediction model, and further determining the time of the next transaction of the target transaction type by the customer according to the time interval and the transaction time sequence data, wherein the prediction model is obtained by training according to a prophet model.
In an embodiment of the present invention, the time interval in this step may be a time interval, and the time interval includes a time interval minimum value and a time interval maximum value. Similarly, the time for the client to perform the next transaction of the target transaction type determined in this step may also be a time interval, where the time interval includes a minimum time value and a maximum time value.
Aiming at the characteristics of transaction data of bank customers, the current popular time sequence prediction method cannot predict correctly, and in order to meet the timeliness and universality of the problem and predict the time generated by the next transaction of the customer more accurately, the transaction data of the customer is converted into a time sequence data format and predicted by adopting a prophet algorithm, so that the beneficial effect of accurately and efficiently predicting the time of the next target transaction type transaction of the customer is realized.
As shown in fig. 2, in an embodiment of the present invention, the prediction model in step S103 is specifically obtained by training in step S201 and step S202.
Step S201, a training sample set is obtained, where training data in the training sample set is a transaction time interval sequence for model training.
In one embodiment of the invention, the trading time interval sequence used for model training comprises N data, the first N-1 data are put into the model for training when training is carried out, and the Nth data are used for verifying the difference between the predicted result and the true value of the model.
And S202, training the prophet model according to the training sample set to obtain the prediction model.
In one embodiment of the invention, the prophet model comprises: the system comprises a trend model and a holiday model, wherein the trend model adopts a piecewise linear function.
The method adopts the prophet model for prediction, considers the influence of holidays on user behaviors besides the trend of time series data, and has the following corresponding formula:
y＝g(t)+h(t)
the trend model g (t) adopts a piecewise linear function, namely a linear function related to the time t, and the formula can be as follows:
g(t)＝(k+α(t)Tδ)t+m+α(t)Tγ
wherein, α is a group of vectors with length of total length of time sequence data, when current time point is greater than i, α isiAnd is 1, otherwise 0, k represents the growth rate, m represents the offset, and δ is the rate of change of each change point. Gamma is the negative of the product of the current time point and the current rate of change.
The model of the holiday and festival,
Figure BDA0003503085190000061
wherein D is a time set corresponding to the holidays.
The prophet model is continuously trained according to the training sample set, parameters of the prophet model are optimized, the prediction accuracy of the prophet model finally reaches a preset value, and the prophet model at the moment is stored as the prediction model in the step S103. In the present invention, parameters of the prophet model include: a trend term variable point parameter and a holiday term parameter.
In an embodiment of the present invention, after the prediction model is trained, the prediction accuracy of the prediction model is verified, as shown in fig. 8, the predicted value and the true value of the prediction model of the present invention are relatively close, which can show that the prediction model of the present invention can relatively accurately predict the customer transaction time of the bank.
As shown in fig. 3, in an embodiment of the present invention, the step S102 of generating the transaction time interval sequence according to the transaction timing data specifically includes a step S301 and a step S302.
Step S301, generating a transaction time sequence according to the transaction time sequence data.
Step S302, the trading time interval sequence is generated by calculating the time difference between any two adjacent items in the trading time sequence.
In one embodiment of the invention, the invention adopts a phase-by-phase difference method, and takes the time interval of two transactions as time sequence data to generate a transaction time interval sequence.
In an embodiment of the present invention, before inputting the sequence of transaction time intervals into the preset predictive model in step S103, the method further includes:
and if the data in the trading time interval sequence meet the Gaussian distribution, removing the data which is more than N times of the standard deviation of the data in the trading time interval sequence, wherein N is more than 0.
In one embodiment of the invention, N is equal to 3.
In an embodiment of the present invention, due to a customer misoperation or the like, a phenomenon of data missing and wrong recording may occur, so that an abnormal value that is too large or too small appears in an obtained time sequence, and model training is affected, so that the abnormal value can be eliminated through gaussian distribution in the present invention, as shown in fig. 7. Specifically, the invention can calculate the standard deviation of each item of data in the transaction time interval sequence
Figure BDA0003503085190000071
Mean value of and will
Figure BDA0003503085190000072
And removing the other data. FIG. 7 shows data that produces an exception and labels the exception point.
As shown in fig. 4, in an embodiment of the present invention, the determining, according to the time interval and the transaction timing data in step S103, the time when the customer performs the next transaction of the target transaction type specifically includes step S401 and step S402.
Step S401, determining the transaction time of the last transaction in the transaction time series data.
In an embodiment of the present invention, this step queries the transaction time of the last transaction from the transaction timing data.
Step S402, determining the time of the customer for the next transaction of the target transaction type according to the transaction time and the time interval.
In an embodiment of the present invention, this step specifically adds the time interval to the transaction time to obtain the time when the customer conducts the next transaction of the target transaction type.
The embodiment shows that the main innovation point of the invention is to provide a data processing mode aiming at the characteristics of bank customer transaction data and predict by utilizing prophet combination trend and holiday information. The method predicts the time interval of the next possible transaction behavior of the client through the steps of data processing, model construction, model fitting and the like, is convenient for workers to remind the client or reasonably recommend the client, and has important significance.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
Based on the same inventive concept, the embodiment of the present invention further provides a transaction time prediction apparatus, which can be used to implement the transaction time prediction method described in the above embodiment, as described in the following embodiment. Because the principle of the transaction time prediction device for solving the problem is similar to the transaction time prediction method, the embodiment of the transaction time prediction device can be referred to the embodiment of the transaction time prediction method, and repeated parts are not described again. As used hereinafter, the term "unit" or "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
Fig. 9 is a block diagram showing a configuration of a transaction time prediction apparatus according to an embodiment of the present invention, and as shown in fig. 9, in an embodiment of the present invention, the transaction time prediction apparatus includes:
a transaction timing data acquisition unit 1 for acquiring transaction timing data of a target transaction type of a customer;
the transaction time interval sequence generating unit 2 is used for generating a transaction time interval sequence according to the transaction time sequence data;
and the prediction unit 3 is configured to input the transaction time interval sequence into a preset prediction model, obtain a time interval of the next transaction of the target transaction type performed by the customer and output by the prediction model, and further determine, according to the time interval and the transaction timing data, a time of the next transaction of the target transaction type performed by the customer, where the prediction model is obtained by training according to a prophet model.
In one embodiment of the present invention, the transaction time prediction apparatus of the present invention further includes:
the training sample set acquisition unit is used for acquiring a training sample set, wherein training data in the training sample set is a transaction time interval sequence used for model training;
and the model training unit is used for training the prophet model according to the training sample set to obtain the prediction model.
In an embodiment of the present invention, the transaction time interval sequence generating unit 2 specifically includes:
the transaction time sequence generating module is used for generating a transaction time sequence according to the transaction time sequence data;
and the time difference calculating module is used for generating the transaction time interval sequence by calculating the time difference between any two adjacent items in the transaction time sequence.
In one embodiment of the present invention, the transaction time prediction apparatus of the present invention further includes:
and the abnormal value removing unit is used for removing data which is more than N times of the standard deviation of each item of data in the trading time interval sequence if each item of data in the trading time interval sequence meets Gaussian distribution, wherein N is more than 0.
In an embodiment of the present invention, the prediction unit 3 specifically includes:
the last transaction time determining module is used for determining the transaction time of the last transaction in the transaction time sequence data;
and the next transaction time determining module is used for determining the time of the next transaction of the target transaction type by the client according to the transaction time and the time interval.
To achieve the above object, according to another aspect of the present application, there is also provided a computer apparatus. As shown in fig. 10, the computer device comprises a memory, a processor, a communication interface and a communication bus, wherein a computer program that can be run on the processor is stored in the memory, and the steps of the method of the embodiment are realized when the processor executes the computer program.
The processor may be a Central Processing Unit (CPU). The Processor may also be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, or a combination thereof.
The memory, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs, non-transitory computer executable programs, and units, such as the corresponding program units in the above-described method embodiments of the present invention. The processor executes various functional applications of the processor and the processing of the work data by executing the non-transitory software programs, instructions and modules stored in the memory, that is, the method in the above method embodiment is realized.
The memory may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created by the processor, and the like. Further, the memory may include high speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory optionally includes memory located remotely from the processor, and such remote memory may be coupled to the processor via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The one or more units are stored in the memory and when executed by the processor perform the method of the above embodiments.
The specific details of the computer device may be understood by referring to the corresponding related descriptions and effects in the above embodiments, and are not described herein again.
In order to achieve the above object, according to another aspect of the present application, there is also provided a computer-readable storage medium storing a computer program which, when executed in a computer processor, implements the steps in the above-described transaction time prediction method. It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory (Flash Memory), a Hard Disk (Hard Disk Drive, abbreviated as HDD) or a Solid State Drive (SSD), etc.; the storage medium may also comprise a combination of memories of the kind described above.
To achieve the above object, according to another aspect of the present application, there is also provided a computer program product comprising computer program/instructions which, when executed by a processor, implement the steps of the above-mentioned transaction time prediction method.
It will be apparent to those skilled in the art that the modules or steps of the present invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and they may alternatively be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, or fabricated separately as individual integrated circuit modules, or fabricated as a single integrated circuit module from multiple modules or steps. Thus, the present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (10)

1. A transaction time prediction method, comprising:
acquiring transaction time sequence data of a target transaction type of a client;
generating a transaction time interval sequence according to the transaction time sequence data;
inputting the transaction time interval sequence into a preset prediction model to obtain a time interval of the next transaction of the target transaction type by the client, which is output by the prediction model, and further determining the time of the next transaction of the target transaction type by the client according to the time interval and the transaction time sequence data, wherein the prediction model is obtained by training according to a prophet model.
2. The transaction time prediction method of claim 1, further comprising:
acquiring a training sample set, wherein training data in the training sample set is a transaction time interval sequence used for model training;
and training the prophet model according to the training sample set to obtain the prediction model.
3. The method of claim 1, wherein generating a sequence of transaction time intervals from the transaction timing data comprises:
generating a transaction time sequence according to the transaction time sequence data;
and generating the transaction time interval sequence by calculating the time difference between any two adjacent items in the transaction time sequence.
4. The transaction time prediction method of claim 1, wherein prior to said inputting the sequence of transaction time intervals into a preset prediction model, further comprising:
and if the data in the trading time interval sequence meet the Gaussian distribution, removing the data which is more than N times of the standard deviation of the data in the trading time interval sequence, wherein N is more than 0.
5. The method for predicting transaction time according to claim 1, wherein the determining the time for the customer to perform the next transaction of the target transaction type according to the time interval and the transaction timing data specifically comprises:
determining the transaction time of the last transaction in the transaction time sequence data;
and determining the time of the customer for the next transaction of the target transaction type according to the transaction time and the time interval.
6. The method of predicting transaction time according to claim 1 or 2, wherein the prophet model comprises: the system comprises a trend model and a holiday model, wherein the trend model adopts a piecewise linear function.
7. A transaction time prediction apparatus, comprising:
the transaction time sequence data acquisition unit is used for acquiring the transaction time sequence data of the target transaction type of the client;
the transaction time interval sequence generating unit is used for generating a transaction time interval sequence according to the transaction time sequence data;
and the prediction unit is used for inputting the transaction time interval sequence into a preset prediction model to obtain the time interval of the next transaction of the target transaction type by the client output by the prediction model, and further determining the time of the next transaction of the target transaction type by the client according to the time interval and the transaction time sequence data, wherein the prediction model is obtained by training according to a prophet model.
8. 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 6 are implemented when the computer program is executed by the processor.
9. A computer-readable storage medium, on which a computer program/instructions are stored, characterized in that the computer program/instructions, when executed by a processor, implement the steps of the method of any one of claims 1 to 6.
10. A computer program product comprising computer program/instructions, characterized in that the computer program/instructions, when executed by a processor, implement the steps of the method of any one of claims 1 to 6.
CN202210132185.6A 2022-02-14 2022-02-14 Transaction time prediction method and device Pending CN114519461A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210132185.6A CN114519461A (en) 2022-02-14 2022-02-14 Transaction time prediction method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210132185.6A CN114519461A (en) 2022-02-14 2022-02-14 Transaction time prediction method and device

Publications (1)

Publication Number Publication Date
CN114519461A true CN114519461A (en) 2022-05-20

Family

ID=81596940

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210132185.6A Pending CN114519461A (en) 2022-02-14 2022-02-14 Transaction time prediction method and device

Country Status (1)

Country Link
CN (1) CN114519461A (en)

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108416619A (en) * 2018-02-08 2018-08-17 深圳市喂车科技有限公司 A kind of consumption interval time prediction technique, device and readable storage medium storing program for executing
CN110415119A (en) * 2019-07-30 2019-11-05 中国工商银行股份有限公司 Model training, bill business prediction technique, device, storage medium and equipment
CN110990174A (en) * 2019-10-25 2020-04-10 苏州浪潮智能科技有限公司 Method, device and medium for predicting SSD available time based on Prophet model
CN111274531A (en) * 2020-01-19 2020-06-12 苏宁云计算有限公司 Commodity sales amount prediction method, commodity sales amount prediction device, computer equipment and storage medium
CN111709754A (en) * 2020-06-12 2020-09-25 中国建设银行股份有限公司 User behavior feature extraction method, device, equipment and system
CN112085497A (en) * 2020-08-28 2020-12-15 银清科技有限公司 User account data processing method and device
CN112150214A (en) * 2020-10-20 2020-12-29 腾讯科技（深圳）有限公司 Data prediction method and device and computer readable storage medium
CN112364975A (en) * 2020-10-14 2021-02-12 山东大学 Terminal operation state prediction method and system based on graph neural network
CN113010260A (en) * 2020-09-29 2021-06-22 证通股份有限公司 Elastic expansion method and system for container quantity
CN113139835A (en) * 2021-04-29 2021-07-20 北京深演智能科技股份有限公司 Data processing method, data processing device, nonvolatile storage medium and processor

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108416619A (en) * 2018-02-08 2018-08-17 深圳市喂车科技有限公司 A kind of consumption interval time prediction technique, device and readable storage medium storing program for executing
CN110415119A (en) * 2019-07-30 2019-11-05 中国工商银行股份有限公司 Model training, bill business prediction technique, device, storage medium and equipment
CN110990174A (en) * 2019-10-25 2020-04-10 苏州浪潮智能科技有限公司 Method, device and medium for predicting SSD available time based on Prophet model
CN111274531A (en) * 2020-01-19 2020-06-12 苏宁云计算有限公司 Commodity sales amount prediction method, commodity sales amount prediction device, computer equipment and storage medium
CN111709754A (en) * 2020-06-12 2020-09-25 中国建设银行股份有限公司 User behavior feature extraction method, device, equipment and system
CN112085497A (en) * 2020-08-28 2020-12-15 银清科技有限公司 User account data processing method and device
CN113010260A (en) * 2020-09-29 2021-06-22 证通股份有限公司 Elastic expansion method and system for container quantity
CN112364975A (en) * 2020-10-14 2021-02-12 山东大学 Terminal operation state prediction method and system based on graph neural network
CN112150214A (en) * 2020-10-20 2020-12-29 腾讯科技（深圳）有限公司 Data prediction method and device and computer readable storage medium
CN113139835A (en) * 2021-04-29 2021-07-20 北京深演智能科技股份有限公司 Data processing method, data processing device, nonvolatile storage medium and processor

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
刘卓军;李晓明;: "基于时间序列建模和控制图的异常交易检测方法", 数学的实践与认识, no. 10, 23 May 2013 (2013-05-23), pages 91 - 98 *

Similar Documents

Publication Publication Date Title
US11876374B2 (en) System and method for optimal control of energy storage system
Janardhanan et al. CPU workload forecasting of machines in data centers using LSTM recurrent neural networks and ARIMA models
CN105205297B (en) Service prediction method and system based on time sequence
CN107092974A (en) Dispense pressure prediction method and device
CN113205227B (en) Vehicle line optimization method and device
CN111143989A (en) Frequency adjustment amount calculation method, module, system, storage medium, and device
JP2017021772A (en) Copula-theory based feature selection
CN112468312A (en) Network flow prediction method, communication equipment and storage medium
Nugaliyadde et al. Predicting electricity consumption using deep recurrent neural networks
CN109992866A (en) Training method, device, readable medium and the electronic equipment of load forecasting model
CN110634061A (en) Capital demand prediction method and device and terminal equipment
Reis et al. A scalable load forecasting system for low voltage grids
CN114519461A (en) Transaction time prediction method and device
CN110826196B (en) Industrial equipment operation data processing method and device
Chen et al. A novel interval estimation framework for wind power forecasting using multi-objective gradient descent optimization
CN108471362B (en) Resource allocation prediction technique and device
Botman et al. A scalable method for probabilistic short-term forecasting of individual households consumption in low voltage grids
CN117371493A (en) Data prediction method, system, terminal and storage medium based on multi-scale TCN
CN110543973A (en) data prediction method, data prediction result adjusting method, device and equipment
CN116893891A (en) Thread scheduling management method, device, equipment and storage medium
CN116646923A (en) Method, device, terminal and storage medium for predicting medium and long term power load
CN111861544A (en) Participant account liquidity prediction method and device
Nazirova et al. Comparative analysis of the calculation of electricity losses in 10-6-0.4 kV distribution networks
Lieskovska et al. Traffic Flow Prediction in Urban Networks: Integrating Sequential Neural Network Architectures.
Tang et al. Forecasting Network Traffic at Large Time Scales by Using Dual-Related Method

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