WO2019192262A1 - 一种评价商户的经营状况的方法、装置及设备 - Google Patents

一种评价商户的经营状况的方法、装置及设备 Download PDF

Info

Publication number
WO2019192262A1
WO2019192262A1 PCT/CN2019/073934 CN2019073934W WO2019192262A1 WO 2019192262 A1 WO2019192262 A1 WO 2019192262A1 CN 2019073934 W CN2019073934 W CN 2019073934W WO 2019192262 A1 WO2019192262 A1 WO 2019192262A1
Authority
WO
WIPO (PCT)
Prior art keywords
merchant
time interval
value
sequence
indicator
Prior art date
Application number
PCT/CN2019/073934
Other languages
English (en)
French (fr)
Inventor
郑霖
陈帅
朱江
陈弢
Original Assignee
阿里巴巴集团控股有限公司
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 阿里巴巴集团控股有限公司 filed Critical 阿里巴巴集团控股有限公司
Publication of WO2019192262A1 publication Critical patent/WO2019192262A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q10/00Administration; Management
    • G06Q10/06Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063Operations research, analysis or management
    • G06Q10/0639Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393Score-carding, benchmarking or key performance indicator [KPI] analysis
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00Commerce
    • G06Q30/02Marketing; Price estimation or determination; Fundraising
    • G06Q30/0282Rating or review of business operators or products
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00Commerce
    • G06Q30/02Marketing; Price estimation or determination; Fundraising
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00Commerce
    • G06Q30/02Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201Market modelling; Market analysis; Collecting market data

Definitions

  • the present specification relates to the field of information technology, and in particular, to a method, device and device for evaluating a business condition of a merchant.
  • the evaluation of the business conditions of merchants is an important part of the management of merchants.
  • a plurality of business indicators (such as transaction volume, turnover, user praise, etc.) of the merchant can be analyzed to comprehensively evaluate the business status of the merchant.
  • the business metric of the merchant is analyzed by the value of the business indicator of the merchant at each specified time interval (such as daily, monthly or quarterly) (this article) It is called the indicator value) for statistics, and calculates the variance of the indicator values of the merchants in each specified time interval. It is generally believed that the smaller the variance, the less likely the indicator value of the merchant to fluctuate, which means that the better the business situation of the merchant, the higher the evaluation of the merchant; the larger the variance, the more likely the indicator value of the merchant is likely to occur. Fluctuation also indicates that the worse the business conditions of the merchants, the lower the evaluation of the merchants.
  • the embodiments of the present specification provide a method, device, and device for evaluating a business condition of a merchant, so as to solve the problem that the accuracy of evaluating the business condition of the merchant existing in the prior art is not high.
  • the business status of the merchant is evaluated.
  • the sorting module sorts the actual index values of the merchants in each first time interval according to the chronological order of the first time intervals, and obtains a sequence of index values
  • a prediction module according to the sequence of indicator values, predicting a predicted indicator value of the merchant in a second time interval; the second time interval is a time interval after all the first time intervals;
  • Comparing a module comparing actual value and predicted indicator value of the merchant in the second time interval
  • the evaluation module evaluates the business status of the merchant based on the comparison result.
  • An apparatus for evaluating a business condition of a merchant including one or more processors and a memory, the memory stores a program, and is configured to perform the following steps by the one or more processors:
  • the business status of the merchant is evaluated.
  • the actual operating index values of the merchants to be evaluated in each first time interval form an index value according to the chronological order of the first time intervals. And then predicting, by the sequence of indicator values, the predicted indicator value of the merchant during a second time interval, wherein the second time interval is a time interval after all the first time intervals.
  • the business status of the merchant can be evaluated by comparing the actual index value and the predicted index value of the merchant in the second time interval.
  • This specification considers that the trend of the trend of the indicator value of the merchant in each specified time interval is stronger (that is, the more accurate the future indicator value of the merchant based on the past indicator value of the merchant), indicating that the business condition of the merchant is better.
  • the regularity of the trend of the indicator value of the merchant in each specified time interval can be analyzed, and the evaluation of the business condition of the merchant can be realized accordingly. In this way, it is possible to avoid good merchants who will adopt a personalized business strategy (for example, merchants whose business value has increased suddenly during the period due to regular marketing activities, and, for example, business indicators during this period due to regular business closures. The merchants whose value suddenly dropped were misjudged as merchants with poor business conditions, thereby improving the accuracy of evaluating the business conditions of the merchants.
  • Figure 1 is a trend chart of the trading volume of merchant A in each month of 2016;
  • FIG. 2 is a flow chart of a method for evaluating a business condition of a merchant according to an embodiment of the present disclosure
  • Figure 3 is a graphical representation of the trend of the actual transaction volume for each month of 2017 and the trend of the forecasted transaction volume for each month of 2017 predicted by the time series forecasting model;
  • FIG. 4 is a schematic diagram of an apparatus for evaluating a business condition of a merchant provided by an embodiment of the present specification
  • FIG. 5 is a schematic diagram of an apparatus for evaluating a business condition of a merchant according to an embodiment of the present specification.
  • the value of the business index of a merchant within each specified time interval is less likely to fluctuate, indicating that the business condition of the merchant is better.
  • the variance of the business indicator value of the merchant in each specified time interval can be calculated to measure the fluctuation degree of the business indicator value of the merchant within each specified time interval, and then the business condition of the merchant is evaluated accordingly.
  • some well-operated merchants will adopt a personalized business strategy, such as regular marketing activities (such as participating in double 11 marketing activities each year) or regular closing (such as one out of business in February each year). month).
  • a personalized business strategy may result in a sudden increase in the value of the indicator for these merchants during a specific time interval (such as a sudden increase in the volume of transactions in November) or a sudden drop (such as a volume of 0 in February), resulting in
  • the variance of the indicator values of these excellent merchants at each specified time interval is large.
  • the existing evaluation methods for the business conditions of good merchants have great limitations, and it is easy to misjudge some good merchants as merchants with poor business conditions. That is to say, the existing method of evaluating the business status of the merchant is not accurate.
  • Figure 1 is a trend chart of the trading volume of merchant A in each month of 2016. As shown in Figure 1, Merchant A will temporarily close down in February of each year, resulting in the transaction volume of Merchant A in February of each year is 0, and Merchant A will participate in the double 11 marketing activities of the e-commerce platform in November each year, resulting in merchants. A has seen a sudden increase in trading volume in November each year. Obviously, although the transaction volume of merchant A in February and November of each year will be abnormal, this abnormality is caused by the personalized business strategy of merchant A, which is normal. This does not mean the operation of merchant A. The situation is poor.
  • this specification considers that the trend of the trend of the indicator value of the merchant in each specified time interval is stronger (that is, the more accurate the future indicator value of the merchant based on the past indicator value of the merchant), indicating that the business situation of the merchant is more it is good.
  • the present invention proposes the following technical solution: according to the chronological order of the first time intervals, the actual operating index values of the merchants to be evaluated in each first time interval form a sequence of index values, and then according to the index values. a sequence predicting a predicted indicator value of the merchant during a second time interval, wherein the second time interval is a time interval after all the first time intervals by comparing actual conditions of the merchant within the second time interval.
  • the indicator value and the predicted indicator value can be used to evaluate the business status of the merchant.
  • the regularity of the trend of the indicator value of the merchant in each specified time interval can be analyzed, and the evaluation of the business condition of the merchant can be realized accordingly.
  • the good merchants who adopt the personalized business strategy will not be misjudged as the merchants with poor business conditions, and the accuracy of evaluating the business conditions of the merchants will be improved.
  • FIG. 2 is a flow chart of a method for evaluating a business condition of a merchant provided by an embodiment of the present specification, including the following steps:
  • S200 Acquire an actual indicator value of the merchant to be evaluated in each first time interval.
  • each of the first time intervals may be each specified time interval within a specified period, wherein the specified period and the specified time interval may be specified as needed.
  • the specified period may be the whole year of 2016 (ie, January 1, 2016 to December 31, 2016), and the specified time interval may be one month, then each first time interval is actually Months of 2016 (ie January, February, ..., December).
  • the actual indicator value of the merchant in each first time interval refers to the indicator value of the merchants that have been counted in each first time interval.
  • the indicator value is a value of a business indicator of the merchant.
  • business indicators for a business such as transaction volume, turnover, or user praise.
  • the indicator value in the embodiment of the present specification generally refers to the value of a business indicator, that is, the method flow shown in FIG. 2 is generally for an operational indicator, if it is required for the merchant.
  • a plurality of business indicators are analyzed to comprehensively evaluate the business conditions of the merchants, and the method flow shown in Figure 2 can be performed for each business indicator.
  • the actual indicator value of the merchant in each month of 2016 may be the actual transaction volume of the merchant in each month of 2016 (the number of sold items), as shown in Table 1.
  • S202 Sort the actual index values of the merchants in each first time interval according to the chronological order of the first time intervals to obtain a sequence of index values.
  • each of the first time intervals has a chronological order. For example, if 12 months in 2016 are used as the first time interval, there is a chronological order from January to December.
  • the order of the actual index values in the sequence of index values is the chronological order of the first time intervals. Taking Table 1 as an example, the index value sequence is (150, 200, 220, 180, 165, 135, 159, 180, 189, 165, 260, 175).
  • S204 Predict the predicted indicator value of the merchant in the second time interval according to the sequence of indicator values.
  • the sequence of indicator values continues to extend backwards, that is, the predicted indicator value of the merchant in subsequent time intervals is predicted.
  • the subsequent time interval refers to the time interval after all the first time intervals, which is referred to herein as the second time interval. It should be noted that the second time interval is generally equal to the first time interval. For example, assuming that each of the first time intervals is a month in 2016, the second time interval is any month after December 2016 (eg, September 2017).
  • the time series prediction method or the machine learning method may be specifically used to predict the predicted indicator value of the merchant in the second time interval.
  • the time series prediction model may be determined according to the sequence of index values; and the indicator value of the merchant in the second time interval is predicted by the time series prediction model, and the merchant is obtained in the second time interval. The predicted indicator value.
  • time series prediction models Common methods for determining time series prediction models include Autoregressive Integrated Moving Average (ARIMA), Vector Autoregressive Method, and Threshold autoregressive Method.
  • ARIMA Autoregressive Integrated Moving Average
  • Vector Autoregressive Method Vector Autoregressive Method
  • Threshold Autoregressive Method the obtained time series prediction models are ARIMA model and vector self. Regression model, threshold autoregressive model. The following uses the ARIMA model as an example.
  • the index value may be The sequence performs data smoothing processing (such as log smoothing), and the ARIMA model is determined using the sequence of index values after data smoothing.
  • the step of determining the ARIMA model is: determining whether the index value sequence has stationarity; if yes, calculating an autocorrelation coefficient AC and a partial autocorrelation coefficient PAC corresponding to the index value sequence, according to the The AC and PAC corresponding to the index value sequence are determined by the autoregressive integral moving average ARIMA model; otherwise, the index value sequence is subjected to at least one differential operation, so that the index value sequence has stationarity, and the index value after the smoothness is calculated
  • the AC and PAC corresponding to the sequence determine the ARIMA model according to the number of times of performing the difference operation and the AC and PAC corresponding to the sequence of the indicator values after the smoothing.
  • the ARIMA model is a common time series prediction model, and the use of a time series (the sequence of indicator values is a time series) determines the ARIMA model as a prerequisite for the stability of the time series. It is possible to determine whether the time series is stationary by performing a unit root test on the time series. If the time series is not stationary, then the time series needs to be differentially operated to make the time series stable, and then the ARIMA model is determined using the smoothed time series. Among them, what is the smoothness of the time series and how to judge whether the time series has smoothness is well known to those skilled in the art, and will not be described again.
  • the ARIMA model is usually expressed as ARIMA (p, d, q), and p, d, q are the model parameters of the ARIMA model.
  • the process of determining the ARIMA model according to the index value sequence is to determine the model parameters according to the index value sequence. process. Wherein p and q are determined by analyzing AC and PAC corresponding to the sequence of index values, and d is the number of times of performing differential operations on the sequence of index values (if there is no need to perform differential operation on the sequence of index values) , then d is 0).
  • each second time interval may be more than one.
  • each first time interval is a month in 2016, each second time interval may be a month in 2017.
  • the ARIMA model determined according to the sequence of index values may predict predicted value of the merchant for a plurality of second time intervals.
  • S206 Compare the actual indicator value and the predicted indicator value of the merchant in the second time interval.
  • each first time interval is usually a specified time interval within a specified period of history.
  • the second time interval may be historical, and the time interval after all the first time intervals may also be the time interval after the current time point (ie, the future time interval).
  • the execution of the method may be temporarily suspended after the step S204 is performed, until the actual indicator value of the merchant in the second time interval is obtained. Proceed to step S206.
  • comparing the actual index value and the predicted index value of the merchant in the second time interval actually determining the actual index value and the predictive index of the merchant in the second time interval.
  • the proximity of the value The closer the actual index value of the merchant in the second time interval is to the predicted index value, the higher the evaluation of the business status of the merchant.
  • the score corresponding to the merchant is determined to be used to represent the business status of the merchant; the higher the score corresponding to the merchant (ie, the higher the evaluation of the business status of the merchant), indicating that the merchant The better the business situation.
  • the actual indicator value and the predicted indicator value of the merchant in the second time interval may be compared in the following manner:
  • the business status of the merchant can be evaluated in the following manner:
  • the actual value of the merchant in each second time interval may also be used to determine the actuality of the merchant in each second time interval.
  • a first curve of a change trend of the index value and determining, according to the predicted index value of the merchant in each second time interval, a trend for characterizing the trend of the predictor value of the merchant in each second time interval a second curve; comparing the first curve and the second curve. The more similar the first curve is to the second curve, the higher the evaluation of the business status of the merchant (ie, the higher the score corresponding to the merchant).
  • Figure 3 is a graph showing the trend of the actual transaction volume for each month of 2017 and the trend of the forecasted transaction volume for each month of 2017 predicted by the time series prediction model.
  • the black dot is the forecasted trading volume for each month of 2017.
  • the dashed line that is, the second curve
  • each black dot represents the trend of each forecasted trading volume;
  • the white point is the middle of 2017.
  • the actual transaction volume of the month, the solid line connecting the white points (ie the first curve) represents the trend of the actual transaction volume.
  • the actual business index values of the merchants to be evaluated in each first time interval form a sequence of index values, and then according to the And a sequence of indicator values predicting a predicted indicator value of the merchant during a second time interval, wherein the second time interval is a time interval after all the first time intervals.
  • the business status of the merchant can be evaluated by comparing the actual index value and the predicted index value of the merchant in the second time interval.
  • This specification considers that the trend of the trend of the indicator value of the merchant in each specified time interval is stronger (that is, the more accurate the future indicator value of the merchant based on the past indicator value of the merchant), indicating that the business condition of the merchant is better.
  • the regularity of the trend of the indicator value of the merchant in each specified time interval can be analyzed, and the evaluation of the business condition of the merchant can be realized accordingly. In this way, it is possible to avoid good merchants who will adopt a personalized business strategy (for example, merchants whose business value has increased suddenly during the period due to regular marketing activities, and, for example, business indicators during this period due to regular business closures. The merchants whose value suddenly dropped were misjudged as merchants with poor business conditions, thereby improving the accuracy of evaluating the business conditions of the merchants.
  • the embodiment of the present specification further provides a device for analyzing the business indicators of the merchant, as shown in FIG. 4, including:
  • the obtaining module 401 is configured to obtain actual indicator values of the merchants to be evaluated in each first time interval;
  • the sorting module 402 sorts the actual index values of the merchants in each first time interval according to the chronological order of the first time intervals to obtain a sequence of index values;
  • the prediction module 403 is configured to predict, according to the sequence of indicator values, a predicted indicator value of the merchant in a second time interval; the second time interval is a time interval after all the first time intervals;
  • the comparing module 404 compares the actual index value and the predicted index value of the merchant in the second time interval
  • the evaluation module 405 evaluates the business status of the merchant based on the comparison result.
  • the prediction module 403 according to the sequence of index values, determining a time series prediction model, and predicting, by the time series prediction model, an indicator value of the merchant in a second time interval, to obtain that the merchant is in the second The value of the predictor within the time interval.
  • the prediction module 403 determines whether the index value sequence has stationarity; if yes, calculates an autocorrelation coefficient AC and a partial autocorrelation coefficient PAC corresponding to the index value sequence, and according to the AC and PAC corresponding to the index value sequence Determining an autoregressive integral moving average ARIMA model; otherwise, performing at least one differential operation on the sequence of index values to make the index value sequence have stationarity, and calculating AC and PAC corresponding to the sequence of the indicator values after smoothing, according to The number of differential operations is performed, and the ARIMA model is determined based on the AC and PAC corresponding to the sequence of the index values after the smoothing.
  • the number of the second time intervals is more than one
  • the comparing module 404 calculates, for each second time interval, an absolute value of a difference between the actual index value and the predicted index value of the merchant in the second time interval; and calculating the absolute value and the merchant in the first The ratio of the actual index values in the two time intervals is used as the difference characterization value corresponding to the second time interval.
  • the evaluation module 405 selects a difference characterization value that is greater than a specified threshold from the difference characterization values respectively calculated for each second time interval; and the maximum value in the selected difference characterization value and/or the number of the selected difference characterization values, Evaluating the business status of the merchant; the smaller the maximum value, the higher the evaluation of the business status of the merchant; the smaller the quantity, the higher the evaluation of the business status of the merchant.
  • the embodiment of the present specification further provides a device for evaluating the business status of the merchant.
  • the device includes one or more processors and a memory.
  • the memory stores a program and is configured to perform the following steps by the one or more processors:
  • the business status of the merchant is evaluated.
  • PLD Programmable Logic Device
  • FPGA Field Programmable Gate Array
  • HDL Hardware Description Language
  • the controller can be implemented in any suitable manner, for example, the controller can take the form of, for example, a microprocessor or processor and a computer readable medium storing computer readable program code (eg, software or firmware) executable by the (micro)processor.
  • computer readable program code eg, software or firmware
  • examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, The Microchip PIC18F26K20 and the Silicone Labs C8051F320, the memory controller can also be implemented as part of the memory's control logic.
  • the controller can be logically programmed by means of logic gates, switches, ASICs, programmable logic controllers, and embedding.
  • Such a controller can therefore be considered a hardware component, and the means for implementing various functions included therein can also be considered as a structure within the hardware component.
  • a device for implementing various functions can be considered as a software module that can be both a method of implementation and a structure within a hardware component.
  • the system, device, module or unit illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product having a certain function.
  • a typical implementation device is a computer.
  • the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital character assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device. Or a combination of any of these devices.
  • embodiments of the present invention can 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 a combination of software and hardware. Moreover, the invention can 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, etc.) including computer usable program code.
  • computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
  • the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
  • the apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
  • the instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.
  • a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
  • processors CPUs
  • input/output interfaces network interfaces
  • memory volatile and non-volatile memory
  • the memory may include non-persistent memory, random access memory (RAM), and/or non-volatile memory in a computer readable medium, such as read only memory (ROM) or flash memory.
  • RAM random access memory
  • ROM read only memory
  • Memory is an example of a computer readable medium.
  • Computer readable media includes both permanent and non-persistent, removable and non-removable media.
  • Information storage can be implemented by any method or technology.
  • the information can be computer readable instructions, data structures, modules of programs, or other data.
  • Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory. (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technology, compact disk read only memory (CD-ROM), multi-character versatile disc (DVD) or other optical storage
  • PRAM phase change memory
  • SRAM static random access memory
  • DRAM dynamic random access memory
  • RAM random access memory
  • ROM read only memory
  • EEPROM electrically erasable programmable read only memory
  • flash memory or other memory technology
  • compact disk read only memory CD-ROM
  • DVD multi-character versatile disc
  • program modules include routines, programs, objects, components, data structures, and the like that perform particular tasks or implement particular abstract data types.
  • the present specification can also be practiced in distributed computing environments where tasks are performed by remote processing devices that are connected through a communication network.
  • program modules can be located in both local and remote computer storage media including storage devices.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Development Economics (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Game Theory and Decision Science (AREA)
  • Theoretical Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Educational Administration (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Data Mining & Analysis (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种评价商户的经营状况的方法、装置及设备。按照各第一时间间隔的时间先后顺序,将待评价的商户在各第一时间间隔内的实际经营指标值形成指标值序列,然后根据所述指标值序列,预测所述商户在第二时间间隔内的预测指标值,其中所述第二时间间隔是所有第一时间间隔之后的时间间隔。通过比较所述商户在所述第二时间间隔内的实际指标值和预测指标值,可以对所述商户的经营状况进行评价。

Description

一种评价商户的经营状况的方法、装置及设备 技术领域
本说明书涉及信息技术领域,尤其涉及一种评价商户的经营状况的方法、装置及设备。
背景技术
众所周知,对商户的经营状况进行评价,是商户管理工作的重要内容。通常地,可对商户的多项经营指标(如交易量、营业额、用户好评数等)进行分析,以便对商户的经营状况进行综合评价。
具体地,针对每项经营指标,对商户的该项经营指标进行分析的方式为,对商户在每个指定时间间隔内(如每天、每月或每季度)的该项经营指标的值(本文将之称为指标值)进行统计,并计算商户在各指定时间间隔内的指标值的方差。通常认为,方差越小,表明商户的指标值越不容易发生波动,也就表明商户的经营状况越好,因此,对商户的评价就越高;方差越大,表明商户的指标值越容易发生波动,也就表明商户的经营状况越差,因此,对商户的评价就越低。
基于现有技术,需要一种更为准确的评价商户的经营状况的方法。
发明内容
本说明书实施例提供一种评价商户的经营状况的方法、装置及设备,以解决现有技术中存在的对商户的经营状况进行评价的准确性不高的问题。
为解决上述技术问题,本说明书实施例是这样实现的:
本说明书实施例提供的一种评价商户的经营状况的方法,包括:
获取待评价的商户在各第一时间间隔内的实际指标值;
按照各第一时间间隔的时间先后顺序,对所述商户在各第一时间间隔内的实际指标值进行排序,得到指标值序列;
根据所述指标值序列,预测所述商户在第二时间间隔内的预测指标值;所述第二时间间隔是所有第一时间间隔之后的时间间隔;
比较所述商户在所述第二时间间隔内的实际指标值和预测指标值;
根据比较结果,对所述商户的经营状况进行评价。
本说明书实施例提供的一种评价商户的经营状况的装置,包括:
获取模块,获取待评价的商户在各第一时间间隔内的实际指标值;
排序模块,按照各第一时间间隔的时间先后顺序,对所述商户在各第一时间间隔内的实际指标值进行排序,得到指标值序列;
预测模块,根据所述指标值序列,预测所述商户在第二时间间隔内的预测指标值;所述第二时间间隔是所有第一时间间隔之后的时间间隔;
比较模块,比较所述商户在所述第二时间间隔内的实际指标值和预测指标值;
评价模块,根据比较结果,对所述商户的经营状况进行评价。
本说明书实施例提供的一种评价商户的经营状况的设备,包括一个或多个处理器及存储器,所述存储器存储有程序,并且被配置成由所述一个或多个处理器执行以下步骤:
获取待评价的商户在各第一时间间隔内的实际指标值;
按照各第一时间间隔的时间先后顺序,对所述商户在各第一时间间隔内的实际指标值进行排序,得到指标值序列;
根据所述指标值序列,预测所述商户在第二时间间隔内的预测指标值;所述第二时间间隔是所有第一时间间隔之后的时间间隔;
比较所述商户在所述第二时间间隔内的实际指标值和预测指标值;
根据比较结果,对所述商户的经营状况进行评价。
由以上本说明书实施例提供的技术方案可见,在本说明书实施例中,按照各第一时间间隔的时间先后顺序,将待评价的商户在各第一时间间隔内的实际经营指标值形成指标值序列,然后根据所述指标值序列,预测所述商户在第二时间间隔内的预测指标值,其中所述第二时间间隔是所有第一时间间隔之后的时间间隔。通过比较所述商户在所述第二时间间隔内的实际指标值和预测指标值,可以对所述商户的经营状况进行评价。本说明书认为,商户在各指定时间间隔内的指标值的变化趋势呈现出的规律性越强(即根据商户过去的指标值预测的商户未来的指标值越准确),说明商户的经营状况越好。而通过本说明书实施例,可以分析出所述商户在各指定时间间隔内的指标值的变化趋势呈 现出的规律性的强弱,并据此实现对所述商户的经营状况的评价。如此,就可以避免将采取个性化经营策略的优良商户(例如,因定期举办营销活动而导致在此期间的经营指标值突增的商户,又如,因定期歇业而导致在此期间的经营指标值突降的商户)误判为经营状况不佳的商户,从而提升了对商户的经营状况进行评价的准确性。
附图说明
为了更清楚地说明本说明书实施例或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本说明书中记载的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动性的前提下,还可以根据这些附图获得其他的附图。
图1是商户A在2016年中各月的交易量的变化趋势图;
图2是本说明实施例提供的一种评价商户的经营状况的方法流程图;
图3是2017年中各月的实际交易量的变化趋势和时序预测模型预测的2017年中各月的预测交易量的变化趋势示意图;
图4是本说明书实施例提供的一种评价商户的经营状况的装置示意图;
图5是本说明书实施例提供的一种评价商户的经营状况的设备示意图。
具体实施方式
在现有技术中,通常认为一个商户在各指定时间间隔内的经营指标值越不容易发生波动,说明该商户的经营状况就越好。基于此,可以计算商户在各指定时间间隔内的经营指标值的方差,来衡量商户在各指定时间间隔内的经营指标值的波动程度,进而据此评价商户的经营状况。
实践中,有些经营状况良好的商户(本文称之为优良商户)会采用个性化的经营策略,比如定期进行营销活动(如每年参加双11营销活动)或定期歇业(如于每年2月份歇业一个月)。个性化的经营策略可能会导致这些商户在特定的时间间隔内的指标值会出现突增(如每年11月的交易量突增)或突降(如每年2月份的交易量为0),导致这些优良商户在各指定时间间隔内的指标值的方差较大。然而,仅因为这些优良商户在各指定时间间隔内的指标值的方差较大,就将这些优良商户评价为经营状况不佳的商户,显然是不合理的。可见,现有的对优良商户的经营状况的评价方法具有很大的局限 性,容易将一些优良商户误判为经营状况不佳的商户。也就是说,现有的评价商户的经营状况的方法的准确性不高。
图1是商户A在2016年中各月的交易量的变化趋势图。如图1所示,商户A在每年的2月会暂时歇业,导致商户A在每年的2月份的交易量为0,商户A在每年11月会参加电商平台的双11营销活动,导致商户A在每年11月的交易量出现突增。显然,虽然商户A在每年2月和每年11月的交易量都会出现异常,但是这种异常是由于商户A的个性化的经营策略导致的,是正常情况,这并不意味着商户A的经营状况较差。
而本说明书认为,商户在各指定时间间隔内的指标值的变化趋势呈现出的规律性越强(即根据商户过去的指标值预测的商户未来的指标值越准确),说明商户的经营状况越好。
基于此,本发明提出了如下技术方案:按照各第一时间间隔的时间先后顺序,将待评价的商户在各第一时间间隔内的实际经营指标值形成指标值序列,然后根据所述指标值序列,预测所述商户在第二时间间隔内的预测指标值,其中所述第二时间间隔是所有第一时间间隔之后的时间间隔,通过比较所述商户在所述第二时间间隔内的实际指标值和预测指标值,可以对所述商户的经营状况进行评价。
这样一来,可以分析出所述商户在各指定时间间隔内的指标值的变化趋势呈现出的规律性的强弱,并据此实现对所述商户的经营状况的评价。通过这样的评价方式,不会将采用个性化经营策略的优良商户误判为经营状况不佳的商户,也就提升了对商户的经营状况进行评价的准确性。
继续参见图1。在本说明书实施例中,倘若商户A在2017年中各月的交易量的变化趋势也呈现出如图1所示的规律性(即2月交易量为0,11月的交易量突增,其他月的交易量波动不大),那么说明商户A的经营状况良好,对商户A的经营状况的评价就会较高。
为了使本技术领域的人员更好地理解本说明书中的技术方案,下面将结合本说明书一个或多个实施例中的附图,对本说明书实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例仅仅是本说明书一部分实施例,而不是全部的实施例。通过本说明书实施例,本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例,都应当属于本说明书保护的范围。
以下结合附图,详细说明本说明书各实施例提供的技术方案。
图2是本说明书实施例提供的一种评价商户的经营状况的方法流程图,包括以下步骤:
S200:获取待评价的商户在各第一时间间隔内的实际指标值。
在本说明书实施例中,各第一时间间隔可以是指定期间内的各指定时间间隔,其中,所述指定期间和所述指定时间间隔皆可以根据需要指定。例如,所述指定期间可以是2016年全年(即2016年1月1日至2016年12月31日),所述指定时间间隔可以是1个月,那么,各第一时间间隔实际上是2016年中的各月(即1月、2月、……、12月)。
商户在各第一时间间隔内的实际指标值是指已经统计到的商户在各第一时间间隔内的指标值。其中,所述指标值是商户的经营指标的值。商户的经营指标可以有多种,如交易量、营业额或用户好评数。需要说明的是,本说明书实施例中的指标值通常是指一项经营指标的值,也就是说,图2所示的方法流程通常是针对一项经营指标而言的,若需要对商户的多项经营指标进行分析以便对商户的经营状况进行综合评价,则可以针对每项经营指标,执行一次图2所示的方法流程。
沿用上例,商户在2016年中各月的实际指标值具体可以是商户在2016年中每个月的实际交易量(卖出的商品件数),如表1所示。
月份 1 2 3 4 5 6 7 8 9 10 11 12
实际交易量 150 200 220 180 165 135 159 180 189 165 260 175
表1
S202:按照各第一时间间隔的时间先后顺序,对所述商户在各第一时间间隔内的实际指标值进行排序,得到指标值序列。
在本说明书实施例中,各第一时间间隔存在时间先后顺序。例如,假设将2016年中的12个月作为各第一时间间隔,则1~12月存在时间先后顺序。所述指标值序列中各实际指标值的排列顺序,即是各第一时间间隔的时间先后顺序。以表1为例,所述指标值序列是(150,200,220,180,165,135,159,180,189,165,260,175)。
S204:根据所述指标值序列,预测所述商户在第二时间间隔内的预测指标值。
在本说明书实施例中,由于所述指标值序列中的各实际指标值是按时间先后顺序排列的,可以反映出所述商户在各第一时间间隔内的实际交易量的变化趋势,因此可以根据此变化趋势,将所述指标值序列继续向后延伸,也即预测所述商户在后续的时间间隔 内的预测指标值。
其中,后续的时间间隔是指所有第一时间间隔之后的时间间隔,本文称之为第二时间间隔。需要说明的是,所述第二时间间隔通常等于所述第一时间间隔。例如,假设各第一时间间隔为2016年中的各月,那么所述第二时间间隔即是2016年12月之后的任何月份(如2017年9月)。
在本说明书实施例中,具体可以采用时间序列预测方法或机器学习的方法,预测所述商户在第二时间间隔内的预测指标值。例如,可以根据所述指标值序列,确定时序预测模型;通过所述时序预测模型,对所述商户在第二时间间隔内的指标值进行预测,得到所述商户在所述第二时间间隔内的预测指标值。
常见的确定时序预测模型的方法有自回归积分滑动平均法(Autoregressive Integrated Moving Average,ARIMA)、向量自回归法、门限自回归法等,相应地,得到的时序预测模型分别为ARIMA模型、向量自回归模型、门限自回归模型。后文以ARIMA模型为例说明。
在本说明书实施例中,若所述指标值序列中的各实际指标值之间差距过大(如有的实际指标值为1000,有的实际指标值为1),则可以对所述指标值序列进行数据平滑处理(如log平滑),使用数据平滑处理后的所述指标值序列确定ARIMA模型。
在本说明书实施例中,确定ARIMA模型的步骤为:判断所述指标值序列是否具有平稳性;若是,则计算所述指标值序列对应的自相关系数AC和偏自相关系数PAC,根据所述指标值序列对应的AC和PAC,确定自回归积分滑动平均ARIMA模型;否则,对所述指标值序列进行至少一次差分运算,使得所述指标值序列具有平稳性,计算平稳后的所述指标值序列对应的AC和PAC,根据进行差分运算的次数,以及根据平稳后的所述指标值序列对应的AC和PAC,确定ARIMA模型。
众所周知,ARIMA模型是一种常见的时序预测模型,而使用时间序列(所述指标值序列就是一种时间序列)确定ARIMA模型的前提是时间序列具有平稳性。可以通过对时间序列进行单位根检验的方式,判断时间序列是否具有平稳性。若时间序列不具有平稳性,则需要对时间序列进行差分运算,使得时间序列具有平稳性,然后使用平稳后的时间序列继续确定ARIMA模型。其中,何为时间序列的平稳性以及如何判断时间序列是否具有平稳性是为本领域技术人员所熟知的,不再赘述。
ARIMA模型通常表达为ARIMA(p,d,q),p、d、q即是ARIMA模型的模型参 数,根据所述指标值序列确定ARIMA模型的过程即是根据所述指标值序列确定模型参数的过程。其中,p和q是通过对所述指标值序列对应的AC和PAC进行分析而确定的,d是对所述指标值序列进行差分运算的次数(若不需要对所述指标值序列进行差分运算,则d为0)。
需要说明的是,所述第二时间间隔的数量可以是不止一个。例如,假设各第一时间间隔为2016年中的各月,那么各第二时间间隔可以为2017年中的各月。根据所述指标值序列确定的ARIMA模型可以预测所述商户在多个第二时间间隔内的预测指标值。
S206:比较所述商户在所述第二时间间隔内的实际指标值和预测指标值。
S208:根据比较结果,对所述商户的经营状况进行评价。
值得强调的是,各第一时间间隔通常是历史上的一段指定期间内的各指定时间间隔。而第二时间间隔可以是历史上的,且在所有第一时间间隔之后的时间间隔,也可以是当前时间点之后的时间间隔(即未来的时间间隔)。
当第二时间间隔是未来的时间间隔时,可以在执行完步骤S204之后,暂时中止本方法的执行,待到获取到所述商户在所述第二时间间隔内的实际指标值时,方可继续执行步骤S206。
在本说明书实施例中,比较所述商户在所述第二时间间隔内的实际指标值和预测指标值,实际上是确定所述商户在所述第二时间间隔内的实际指标值和预测指标值的接近程度。所述商户在第二时间间隔内的实际指标值与预测指标值越接近,对所述商户的经营状况评价越高。具体地,可以针对每个商户,根据比较结果,确定该商户对应的评分,用于表征商户的经营状况;该商户对应的评分越高(即对商户的经营状况评价越高),表明该商户的经营状况越好。
本领域技术人员在理解了上述思想之后,很容易想到各种方式,对所述商户在所述第二时间间隔内的实际指标值和预测指标值进行比较,并根据比较结果对商户的经营状况进行评价。这些方式都应在本申请文件所要求的保护范围之内。
具体地,当所述第二时间间隔的数量为不止一个时,可以采用如下方式对所述商户在所述第二时间间隔内的实际指标值和预测指标值进行比较:
针对每个第二时间间隔,计算所述商户在该第二时间间隔内的实际指标值和预测指标值的差的绝对值;计算该绝对值与所述商户在该第二时间间隔内的实际指标值的比值,作为该第二时间间隔对应的差距表征值。
基于此比较方式,可以采用如下方式对所述商户的经营状况进行评价:
从针对各第二时间间隔分别计算的差距表征值中选择大于指定阈值的差距表征值;根据选择的差距表征值中的最大值和/或选择的差距表征值的数量,评价所述商户的经营状况;所述最大值越小,对商户的经营状况评价越高;所述数量越少,对所述商户的经营状况评价越高。
此外,当所述第二时间间隔的数量为不止一个时,也可以根据所述商户在各第二时间间隔内的实际指标值,确定用于表征所述商户在各第二时间间隔内的实际指标值的变化趋势的第一曲线,以及,根据所述商户在各第二时间间隔内的预测指标值,确定用于表征所述商户在各第二时间间隔内的预测指标值的变化趋势的第二曲线;比较所述第一曲线和所述第二曲线。所述第一曲线与所述第二曲线越相似,对所述商户的经营状况评价越高(即所述商户对应的评分越高)。
举例来说,假设使用表1所示的交易量序列确定时序预测模型,并通过确定的时序预测模型预测2017年中各月的预测交易量。图3是2017年中各月的实际交易量的变化趋势和时序预测模型预测的2017年中各月的预测交易量的变化趋势示意图。如图3所示,黑点是2017年中各月的预测交易量,各黑点连接而成的虚线(即第二曲线)表征了各预测交易量的变化趋势;白点是2017年中各月的实际交易量,各白点连接而成的实线(即第一曲线)表征了各实际交易量的变化趋势。可以看到,2017年中各月的预测交易量的变化趋势与2017年中各月的实际交易量的变化趋势非常相似(也即所述商户在各指定时间间隔中的交易量的变化趋势具有较强的规律性),所述商户的经营状况良好,因此对所述商户的评价较高。
通过图2所示的评价商户的经营状况的方法,按照各第一时间间隔的时间先后顺序,将待评价的商户在各第一时间间隔内的实际经营指标值形成指标值序列,然后根据所述指标值序列,预测所述商户在第二时间间隔内的预测指标值,其中所述第二时间间隔是所有第一时间间隔之后的时间间隔。通过比较所述商户在所述第二时间间隔内的实际指标值和预测指标值,可以对所述商户的经营状况进行评价。本说明书认为,商户在各指定时间间隔内的指标值的变化趋势呈现出的规律性越强(即根据商户过去的指标值预测的商户未来的指标值越准确),说明商户的经营状况越好。而通过本说明书实施例,可以分析出所述商户在各指定时间间隔内的指标值的变化趋势呈现出的规律性的强弱,并据此实现对所述商户的经营状况的评价。如此,就可以避免将采取个性化经营策略的优良商户(例如,因定期举办营销活动而导致在此期间的经营指标值突增的商户,又如, 因定期歇业而导致在此期间的经营指标值突降的商户)误判为经营状况不佳的商户,从而提升了对商户的经营状况进行评价的准确性。
基于图2所示的分析商户的经营指标方法,本说明书实施例还对应提供了一种分析商户的经营指标的装置,如图4所示,包括:
获取模块401,获取待评价的商户在各第一时间间隔内的实际指标值;
排序模块402,按照各第一时间间隔的时间先后顺序,对所述商户在各第一时间间隔内的实际指标值进行排序,得到指标值序列;
预测模块403,根据所述指标值序列,预测所述商户在第二时间间隔内的预测指标值;所述第二时间间隔是所有第一时间间隔之后的时间间隔;
比较模块404,比较所述商户在所述第二时间间隔内的实际指标值和预测指标值;
评价模块405,根据比较结果,对所述商户的经营状况进行评价。
所述预测模块403,根据所述指标值序列,确定时序预测模型;通过所述时序预测模型,对所述商户在第二时间间隔内的指标值进行预测,得到所述商户在所述第二时间间隔内的预测指标值。
所述预测模块403,判断所述指标值序列是否具有平稳性;若是,则计算所述指标值序列对应的自相关系数AC和偏自相关系数PAC,根据所述指标值序列对应的AC和PAC,确定自回归积分滑动平均ARIMA模型;否则,对所述指标值序列进行至少一次差分运算,使得所述指标值序列具有平稳性,计算平稳后的所述指标值序列对应的AC和PAC,根据进行差分运算的次数,以及根据平稳后的所述指标值序列对应的AC和PAC,确定ARIMA模型。
所述评价模块405,所述商户在第二时间间隔内的实际指标值与预测指标值越接近,对所述商户的经营状况评价越高。
所述第二时间间隔的数量为不止一个;
所述比较模块404,针对每个第二时间间隔,计算所述商户在该第二时间间隔内的实际指标值和预测指标值的差的绝对值;计算该绝对值与所述商户在该第二时间间隔内的实际指标值的比值,作为该第二时间间隔对应的差距表征值。
所述评价模块405,从针对各第二时间间隔分别计算的差距表征值中选择大于指定阈值的差距表征值;根据选择的差距表征值中的最大值和/或选择的差距表征值的数量, 评价所述商户的经营状况;所述最大值越小,对商户的经营状况评价越高;所述数量越少,对所述商户的经营状况评价越高。
基于图2所示的评价商户的经营状况的方法,本说明书实施例还对应提供了一种评价商户的经营状况的设备,如图5所示,该设备包括一个或多个处理器及存储器,所述存储器存储有程序,并且被配置成由所述一个或多个处理器执行以下步骤:
获取待评价的商户在各第一时间间隔内的实际指标值;
按照各第一时间间隔的时间先后顺序,对所述商户在各第一时间间隔内的实际指标值进行排序,得到指标值序列;
根据所述指标值序列,预测所述商户在第二时间间隔内的预测指标值;所述第二时间间隔是所有第一时间间隔之后的时间间隔;
比较所述商户在所述第二时间间隔内的实际指标值和预测指标值;
根据比较结果,对所述商户的经营状况进行评价。
本说明书中的各个实施例均采用递进的方式描述,各个实施例之间相同相似的部分互相参见即可,每个实施例重点说明的都是与其他实施例的不同之处。尤其,对于图5所示的设备而言,由于其基本相似于方法实施例,所以描述的比较简单,相关之处参见方法实施例的部分说明即可。
在20世纪90年代,对于一个技术的改进可以很明显地区分是硬件上的改进(例如,对二极管、晶体管、开关等电路结构的改进)还是软件上的改进(对于方法流程的改进)。然而,随着技术的发展,当今的很多方法流程的改进已经可以视为硬件电路结构的直接改进。设计人员几乎都通过将改进的方法流程编程到硬件电路中来得到相应的硬件电路结构。因此,不能说一个方法流程的改进就不能用硬件实体模块来实现。例如,可编程逻辑器件(Programmable Logic Device,PLD)(例如现场可编程门阵列(Field Programmable Gate Array,FPGA))就是这样一种集成电路,其逻辑功能由用户对器件编程来确定。由设计人员自行编程来把一个数字符系统“集成”在一片PLD上,而不需要请芯片制造厂商来设计和制作专用的集成电路芯片。而且,如今,取代手工地制作集成电路芯片,这种编程也多半改用“逻辑编译器(logic compiler)”软件来实现,它与程序开发撰写时所用的软件编译器相类似,而要编译之前的原始代码也得用特定的编程语言来撰写,此称之为硬件描述语言(Hardware Description Language,HDL),而HDL也并非仅有一种,而是有许多种,如ABEL(Advanced Boolean Expression Language)、 AHDL(Altera Hardware Description Language)、Confluence、CUPL(Cornell University Programming Language)、HDCal、JHDL(Java Hardware Description Language)、Lava、Lola、MyHDL、PALASM、RHDL(Ruby Hardware Description Language)等,目前最普遍使用的是VHDL(Very-High-Speed Integrated Circuit Hardware Description Language)与Verilog。本领域技术人员也应该清楚,只需要将方法流程用上述几种硬件描述语言稍作逻辑编程并编程到集成电路中,就可以很容易得到实现该逻辑方法流程的硬件电路。
控制器可以按任何适当的方式实现,例如,控制器可以采取例如微处理器或处理器以及存储可由该(微)处理器执行的计算机可读程序代码(例如软件或固件)的计算机可读介质、逻辑门、开关、专用集成电路(Application Specific Integrated Circuit,ASIC)、可编程逻辑控制器和嵌入微控制器的形式,控制器的例子包括但不限于以下微控制器:ARC 625D、Atmel AT91SAM、Microchip PIC18F26K20以及Silicone Labs C8051F320,存储器控制器还可以被实现为存储器的控制逻辑的一部分。本领域技术人员也知道,除了以纯计算机可读程序代码方式实现控制器以外,完全可以通过将方法步骤进行逻辑编程来使得控制器以逻辑门、开关、专用集成电路、可编程逻辑控制器和嵌入微控制器等的形式来实现相同功能。因此这种控制器可以被认为是一种硬件部件,而对其内包括的用于实现各种功能的装置也可以视为硬件部件内的结构。或者甚至,可以将用于实现各种功能的装置视为既可以是实现方法的软件模块又可以是硬件部件内的结构。
上述实施例阐明的系统、装置、模块或单元,具体可以由计算机芯片或实体实现,或者由具有某种功能的产品来实现。一种典型的实现设备为计算机。具体的,计算机例如可以为个人计算机、膝上型计算机、蜂窝电话、相机电话、智能电话、个人数字符助理、媒体播放器、导航设备、电子邮件设备、游戏控制台、平板计算机、可穿戴设备或者这些设备中的任何设备的组合。
为了描述的方便,描述以上装置时以功能分为各种单元分别描述。当然,在实施本说明书时可以把各单元的功能在同一个或多个软件和/或硬件中实现。
本领域内的技术人员应明白,本发明的实施例可提供为方法、系统、或计算机程序产品。因此,本发明可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且,本发明可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本发明是参照根据本发明实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器,使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中,使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品,该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上,使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理,从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
在一个典型的配置中,计算设备包括一个或多个处理器(CPU)、输入/输出接口、网络接口和内存。
内存可能包括计算机可读介质中的非永久性存储器,随机存取存储器(RAM)和/或非易失性内存等形式,如只读存储器(ROM)或闪存(flash RAM)。内存是计算机可读介质的示例。
计算机可读介质包括永久性和非永久性、可移动和非可移动媒体可以由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机的存储介质的例子包括,但不限于相变内存(PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体或其他内存技术、只读光盘只读存储器(CD-ROM)、数字符多功能光盘(DVD)或其他光学存储、磁盒式磁带,磁带磁磁盘存储或其他磁性存储设备或任何其他非传输介质,可用于存储可以被计算设备访问的信息。按照本文中的界定,计算机可读介质不包括暂存电脑可读媒体(transitory media),如调制的数据信号和载波。
还需要说明的是,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、商品或者设备不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、商品或者设备所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括所述要素的过程、方法、商品或者设备中还存在另外的相同要素。
本说明书可以在由计算机执行的计算机可执行指令的一般上下文中描述,例如程序模块。一般地,程序模块包括执行特定任务或实现特定抽象数据类型的例程、程序、对象、组件、数据结构等等。也可以在分布式计算环境中实践本说明书,在这些分布式计算环境中,由通过通信网络而被连接的远程处理设备来执行任务。在分布式计算环境中,程序模块可以位于包括存储设备在内的本地和远程计算机存储介质中。
以上所述仅为本说明书的实施例而已,并不用于限制本说明书。对于本领域技术人员来说,本说明书可以有各种更改和变化。凡在本说明书的精神和原理之内所作的任何修改、等同替换、改进等,均应包含在本说明书的权利要求范围之内。

Claims (13)

  1. 一种评价商户的经营状况的方法,包括:
    获取待评价的商户在各第一时间间隔内的实际指标值;
    按照各第一时间间隔的时间先后顺序,对所述商户在各第一时间间隔内的实际指标值进行排序,得到指标值序列;
    根据所述指标值序列,预测所述商户在第二时间间隔内的预测指标值;所述第二时间间隔是所有第一时间间隔之后的时间间隔;
    比较所述商户在所述第二时间间隔内的实际指标值和预测指标值;
    根据比较结果,对所述商户的经营状况进行评价。
  2. 如权利要求1所述的方法,根据所述指标值序列,预测所述商户在第二时间间隔内的预测指标值,具体包括:
    根据所述指标值序列,确定时序预测模型;
    通过所述时序预测模型,对所述商户在第二时间间隔内的指标值进行预测,得到所述商户在所述第二时间间隔内的预测指标值。
  3. 如权利要求2所述的方法,根据所述指标值序列,确定时序预测模型,具体包括:
    判断所述指标值序列是否具有平稳性;
    若是,则计算所述指标值序列对应的自相关系数AC和偏自相关系数PAC,根据所述指标值序列对应的AC和PAC,确定自回归积分滑动平均ARIMA模型;
    否则,对所述指标值序列进行至少一次差分运算,使得所述指标值序列具有平稳性,计算平稳后的所述指标值序列对应的AC和PAC,根据进行差分运算的次数,以及根据平稳后的所述指标值序列对应的AC和PAC,确定ARIMA模型。
  4. 如权利要求1所述的方法,根据比较结果,对所述商户的经营状况进行评价,具体包括:
    所述商户在第二时间间隔内的实际指标值与预测指标值越接近,对所述商户的经营状况评价越高。
  5. 如权利要求1所述的方法,所述第二时间间隔的数量为不止一个;
    比较所述商户在所述第二时间间隔内的实际指标值和预测指标值,具体包括:
    针对每个第二时间间隔,计算所述商户在该第二时间间隔内的实际指标值和预测指标值的差的绝对值;
    计算该绝对值与所述商户在该第二时间间隔内的实际指标值的比值,作为该第二时 间间隔对应的差距表征值。
  6. 如权利要求5所述的方法,根据比较结果,对所述商户的经营状况进行评价,具体包括:
    从针对各第二时间间隔分别计算的差距表征值中选择大于指定阈值的差距表征值;
    根据选择的差距表征值中的最大值和/或选择的差距表征值的数量,评价所述商户的经营状况;所述最大值越小,对商户的经营状况评价越高;所述数量越少,对所述商户的经营状况评价越高。
  7. 一种评价商户的经营状况的装置,包括:
    获取模块,获取待评价的商户在各第一时间间隔内的实际指标值;
    排序模块,按照各第一时间间隔的时间先后顺序,对所述商户在各第一时间间隔内的实际指标值进行排序,得到指标值序列;
    预测模块,根据所述指标值序列,预测所述商户在第二时间间隔内的预测指标值;所述第二时间间隔是所有第一时间间隔之后的时间间隔;
    比较模块,比较所述商户在所述第二时间间隔内的实际指标值和预测指标值;
    评价模块,根据比较结果,对所述商户的经营状况进行评价。
  8. 如权利要求7所述的装置,所述预测模块,根据所述指标值序列,确定时序预测模型;通过所述时序预测模型,对所述商户在第二时间间隔内的指标值进行预测,得到所述商户在所述第二时间间隔内的预测指标值。
  9. 如权利要求8所述的装置,所述预测模块,判断所述指标值序列是否具有平稳性;若是,则计算所述指标值序列对应的自相关系数AC和偏自相关系数PAC,根据所述指标值序列对应的AC和PAC,确定自回归积分滑动平均ARIMA模型;否则,对所述指标值序列进行至少一次差分运算,使得所述指标值序列具有平稳性,计算平稳后的所述指标值序列对应的AC和PAC,根据进行差分运算的次数,以及根据平稳后的所述指标值序列对应的AC和PAC,确定ARIMA模型。
  10. 如权利要求7所述的装置,所述评价模块,所述商户在第二时间间隔内的实际指标值与预测指标值越接近,对所述商户的经营状况评价越高。
  11. 如权利要求7所述的装置,所述第二时间间隔的数量为不止一个;
    所述比较模块,针对每个第二时间间隔,计算所述商户在该第二时间间隔内的实际指标值和预测指标值的差的绝对值;计算该绝对值与所述商户在该第二时间间隔内的实际指标值的比值,作为该第二时间间隔对应的差距表征值。
  12. 如权利要求11所述的装置,所述评价模块,从针对各第二时间间隔分别计算 的差距表征值中选择大于指定阈值的差距表征值;根据选择的差距表征值中的最大值和/或选择的差距表征值的数量,评价所述商户的经营状况;所述最大值越小,对商户的经营状况评价越高;所述数量越少,对所述商户的经营状况评价越高。
  13. 一种评价商户的经营状况的设备,包括一个或多个处理器及存储器,所述存储器存储有程序,并且被配置成由所述一个或多个处理器执行以下步骤:
    获取待评价的商户在各第一时间间隔内的实际指标值;
    按照各第一时间间隔的时间先后顺序,对所述商户在各第一时间间隔内的实际指标值进行排序,得到指标值序列;
    根据所述指标值序列,预测所述商户在第二时间间隔内的预测指标值;所述第二时间间隔是所有第一时间间隔之后的时间间隔;
    比较所述商户在所述第二时间间隔内的实际指标值和预测指标值;
    根据比较结果,对所述商户的经营状况进行评价。
PCT/CN2019/073934 2018-04-02 2019-01-30 一种评价商户的经营状况的方法、装置及设备 WO2019192262A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810282041.2A CN108805385A (zh) 2018-04-02 2018-04-02 一种评价商户的经营状况的方法、装置及设备
CN201810282041.2 2018-04-02

Publications (1)

Publication Number Publication Date
WO2019192262A1 true WO2019192262A1 (zh) 2019-10-10

Family

ID=64094741

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/073934 WO2019192262A1 (zh) 2018-04-02 2019-01-30 一种评价商户的经营状况的方法、装置及设备

Country Status (3)

Country Link
CN (1) CN108805385A (zh)
TW (1) TW201942835A (zh)
WO (1) WO2019192262A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108805385A (zh) * 2018-04-02 2018-11-13 阿里巴巴集团控股有限公司 一种评价商户的经营状况的方法、装置及设备
CN111914060B (zh) * 2020-06-28 2021-02-26 杭州电子科技大学 一种基于在线点评数据的商户多视图特征提取及模型构建方法

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106204086A (zh) * 2015-05-06 2016-12-07 阿里巴巴集团控股有限公司 商品销量的预警方法和装置
CN107292649A (zh) * 2016-04-01 2017-10-24 阿里巴巴集团控股有限公司 业务预测数据校正的方法和装置
CN107767659A (zh) * 2017-10-13 2018-03-06 东南大学 基于arima模型的共享单车吸引量和发生量预测方法
CN108805385A (zh) * 2018-04-02 2018-11-13 阿里巴巴集团控股有限公司 一种评价商户的经营状况的方法、装置及设备

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106204086A (zh) * 2015-05-06 2016-12-07 阿里巴巴集团控股有限公司 商品销量的预警方法和装置
CN107292649A (zh) * 2016-04-01 2017-10-24 阿里巴巴集团控股有限公司 业务预测数据校正的方法和装置
CN107767659A (zh) * 2017-10-13 2018-03-06 东南大学 基于arima模型的共享单车吸引量和发生量预测方法
CN108805385A (zh) * 2018-04-02 2018-11-13 阿里巴巴集团控股有限公司 一种评价商户的经营状况的方法、装置及设备

Also Published As

Publication number Publication date
CN108805385A (zh) 2018-11-13
TW201942835A (zh) 2019-11-01

Similar Documents

Publication Publication Date Title
CN109063886B (zh) 一种异常检测方法、装置以及设备
TWI769190B (zh) 風險管控方法及裝置
WO2019196552A1 (zh) 保险欺诈识别的数据处理方法、装置、设备及服务器
TW202008237A (zh) 針對新場景的預測模型訓練方法及裝置
CN109242519B (zh) 一种异常行为识别方法、装置和设备
TW201928841A (zh) 訓練風控模型和風控的方法、裝置及設備
CN110472802B (zh) 一种数据特征评估方法、装置及设备
CN108596410B (zh) 一种风控事件自动处理方法及装置
US11182804B2 (en) Segment valuation in a digital medium environment
CN111967940B (zh) 一种订单量异常检测方法及装置
WO2021120845A1 (zh) 一种同质风险单位特征集合生成方法、装置、设备及介质
WO2019192262A1 (zh) 一种评价商户的经营状况的方法、装置及设备
WO2024113932A1 (zh) 一种模型优化的方法、装置、设备及存储介质
US20230334370A1 (en) Model gradient determining methods, apparatuses, devices, and media based on federated learning
CN112926636A (zh) 牵引变流器柜体温度异常检测方法和装置
US20200065837A1 (en) Systems and methods for use in evaluating aggregate merchant sets
CN110688433A (zh) 一种基于路径的特征生成方法及装置
JP6729703B2 (ja) 情報提示方法、装置、及びプログラム
Robinson Automated analysis of simulation output data
CN110458581B (zh) 商户业务周转异常的识别方法及装置
WO2020225902A1 (ja) 検知装置、検知方法および検知プログラム
CN108470242B (zh) 风险管控方法、装置、及服务器
Nahm Nonparametric quantile regression analysis of R&D-sales relationship for Korean firms
CN115456801A (zh) 个人信用的人工智能大数据风控系统、方法和存储介质
US20130030863A1 (en) Trend-based target setting for process control

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19781236

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19781236

Country of ref document: EP

Kind code of ref document: A1