CN113689124A - Internet rental bicycle demand characteristic evaluation method and storage medium - Google Patents

Internet rental bicycle demand characteristic evaluation method and storage medium Download PDF

Info

Publication number
CN113689124A
CN113689124A CN202110986179.2A CN202110986179A CN113689124A CN 113689124 A CN113689124 A CN 113689124A CN 202110986179 A CN202110986179 A CN 202110986179A CN 113689124 A CN113689124 A CN 113689124A
Authority
CN
China
Prior art keywords
borrowing
returning
time
bicycle
data
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110986179.2A
Other languages
Chinese (zh)
Inventor
顾天奇
王波
金仁熙
庄楚天
张琪峰
郑栋
高欣
金文刚
杨溪清
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.)
CCDI Suzhou Exploration and Design Consultant Co Ltd
Original Assignee
CCDI Suzhou Exploration and Design Consultant Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by CCDI Suzhou Exploration and Design Consultant Co Ltd filed Critical CCDI Suzhou Exploration and Design Consultant Co Ltd
Priority to CN202110986179.2A priority Critical patent/CN113689124A/en
Publication of CN113689124A publication Critical patent/CN113689124A/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
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06315—Needs-based resource requirements planning or analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0645—Rental transactions; Leasing transactions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/40—Business processes related to the transportation industry

Landscapes

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

Abstract

The application provides a method for evaluating demand characteristics of Internet rented bicycles and a storage medium, wherein the method comprises the following steps: calculating a borrowing and returning normalization index of a station or an area according to the user use data; constructing a clustering analysis model according to the borrowing and returning normalization index, and carrying out clustering analysis; and classifying the sites or the regions according to the using modes according to the clustering analysis result. According to the method and the device, the clustering analysis is carried out based on the normalization index of the user borrowing and returning data, the use characteristics of the vehicle are represented, and the discreteness error caused by the fact that NAB data are used in the conventional technology is avoided. Preferably, since the user usage data is based on continuous time and includes real-time borrowing and returning data, errors in conventional methods in which borrowing and returning cancel each other out can be avoided.

Description

Internet rental bicycle demand characteristic evaluation method and storage medium
Technical Field
The invention relates to a use requirement characteristic evaluation technology of an internet rental bicycle, in particular to a method and a storage medium for evaluating the use requirement characteristic of the internet rental bicycle.
Background
At present, no widely accepted analysis and evaluation method exists for the use demand characteristics of Internet renting bicycles (including public bicycles, shared bicycles, electric bicycles and the like). For a public bicycle which is one of network rental (electric) bicycles, researchers and operators can observe the borrowing and returning condition of the current station vehicle by calling the number of available bike posts (for example, if the station has 20 bike posts, the station can borrow 6 vehicles, and the NAB is 6/20) so as to calculate the use demand. The method is generally performed in units of a certain site.
The existing analysis method has the following problems:
firstly, most of NAB data are static data, and based on discrete time stamps, errors can be brought, and the real requirements are covered: usually, a vehicle pile feeds back a group of NAB data at intervals, and if the borrowing and returning behaviors exist in the time period, the number of borrowed vehicles and the number of returned vehicles are mutually offset, namely the NAB data at the previous time is equal to the NAB data at the next time. For the NAB observer, the usage demand of the bicycle is 0, but the real demand of both the borrowing and returning is not 0.
Secondly, the NAB data-based feature evaluation method is difficult to eliminate the operation scheduling error: for network rental (electric) bikes, operators typically perform manual dispatch to transport the bikes to areas where demand is high but where supply is low (e.g., public bikes are transported to public bikes around rail stations in the morning); or conversely, too many vehicles are transported away from a certain place to make room for the user to return to the vehicle. If the NAB data is directly observed, the borrowed vehicle number generated by scheduling is easily classified into the real requirement, so that a large error is generated. However, the synchronous prompting of the NAB data when dispatching the vehicle requires more advanced data coordination capability, and has great difficulty at present.
And thirdly, the user use data is lack of effective mining: the conventional demand evaluation technology has less mining on the use data (car borrowing and returning data) of the user, and the use characteristics of the user are not easy to discover.
And fourthly, a demand characteristic evaluation method aiming at the pile-free travel modes of the shared bicycle, the electric bicycle and the like is lacked: the conventional evaluation method mainly aims at the public bicycles with piles, and analyzes the public bicycles with piles by taking a certain station as a unit. For the existing rapidly developed shared bicycle and electric bicycle without piles, the evaluation and analysis of the demand characteristics cannot be carried out because NAB data does not exist.
Disclosure of Invention
The invention aims to provide an internet renting bicycle demand characteristic evaluation method and a storage medium, which are used for carrying out clustering by constructing normalized bicycle borrowing and returning data vectors on the basis of user use data (bicycle borrowing and returning data), so that demand characteristics of internet renting bicycle sites/areas are analyzed, and the purpose of classifying the time-varying characteristics of the use demands of the internet renting bicycles is realized.
The following presents a simplified summary of one or more aspects in order to provide a basic understanding of such aspects. This summary is not an extensive overview of all contemplated aspects, and is intended to neither identify key or critical elements of all aspects nor delineate the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a prelude to the more detailed description that is presented later.
According to one aspect of the invention, the method for evaluating the requirement characteristics of the Internet rented bicycles comprises the following steps:
calculating a borrowing and returning normalization index of a station or an area according to the user use data;
constructing a clustering analysis model according to the borrowing and returning normalization index, and carrying out clustering analysis;
and classifying the sites or the regions according to the using modes according to the clustering analysis result.
In one embodiment, the user usage data is based on a continuous time.
In one embodiment, the user usage data includes real-time vehicle borrowing data and real-time vehicle returning data.
In one embodiment, the loan-return normalization index is calculated by a daily real-time loan amount FI and a daily real-time loan amount FO, and the daily real-time loan amount FI and the daily real-time loan amount FO are averaged over a plurality of days.
In one embodiment, for a particular site or area m, the daily real-time departure amount FI is represented as a vector FIm：
FIm＝[fim，0，fim，1，fim，2，...，fim，t，...，fim，23]，
Wherein, fim，tThe average vehicle returning amount in the tth hour is represented by t, the t represents the time sequence of 24 hours in the whole day, and t is more than or equal to 0 and less than or equal to 23;
fim，tcalculated from the following formula:
Figure BDA0003230772040000031
wherein, fim，t，iThe number of returned vehicles in the tth hour on the jth day is k, which represents the number of days, and k is 22.
In one embodiment, the daily real-time loan amount FO is expressed as a vector FO for a particular station or zone mm：
FOm＝[fom，0，fOm，1，fom，2，...，fim，t，...fom，23]，
Wherein, fom，tIs the average vehicle borrowing in the t hourQuantity, t represents a time series of 24 hours throughout the day, t is 0 ≦ 23;
in the formula fom，tCalculated from the following formula:
Figure BDA0003230772040000041
wherein, fom，t，iThe number of borrowed vehicles on the jth day and the tth hour is k, which represents the number of days, and k is 22.
In one embodiment, the time-varying car borrowing and returning conditions for a particular station or area m over a period of time are represented by a vector FmRepresents:
Fm＝[fim，0，fom，0，fim，1，fom，1，fim，2，fom，2，...，fim，23，fom，23]
to FmNormalization is performed, and all values are divided by the maximum value f of the 48 valuesmaxObtaining the normalized index NF of borrowing and returning carm：
NFm＝[fim，0/fmax，fom，0/fmax，fim，1/fmax，fom，1/fmax，...，fim，23/fmax，fom，23/fmax]。
In one embodiment, the clustering analysis employs a k-means clustering method.
In one embodiment, the usage patterns include a combination of one or more of a borrow and balance double peak pattern, a borrow and balance single peak pattern, a borrow and balance unbalanced double peak pattern, and a borrow and balance unbalanced single peak pattern.
According to another aspect of the present invention, there is further provided a readable storage medium, wherein the storage medium stores a program, and when the program is executed by a processor, the method for evaluating demand characteristics of an internet rental bicycle is implemented as described in any one of the above embodiments.
The embodiment of the invention has the beneficial effects that: normalization indexes based on user borrowing and returning data are used for clustering analysis and representing use characteristics of vehicles, and discreteness errors caused by using NAB data in the conventional technology are avoided. Preferably, since the user usage data is based on continuous time and includes real-time borrowing and returning data, errors caused by mutual cancellation of the borrowing and returning in the conventional method can be avoided.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
The above features and advantages of the present disclosure will be better understood upon reading the detailed description of embodiments of the disclosure in conjunction with the following drawings. In the drawings, components are not necessarily drawn to scale, and components having similar relative characteristics or features may have the same or similar reference numerals.
FIG. 1 is a flow chart of an embodiment of the present application;
FIG. 2 is a graph of demand characteristics by balancing double peak mode;
FIG. 3 is a graph of demand characteristics for a double peak by return imbalance mode;
FIG. 4 is a graph of demand characteristics for a single peak mode with disequilibrium.
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments. It is noted that the aspects described below in connection with the figures and the specific embodiments are only exemplary and should not be construed as imposing any limitation on the scope of the present invention.
As shown in fig. 1, an embodiment of the present application provides an internet rental bicycle demand characteristic evaluation method, including the following steps:
s100, calculating a borrowing and returning normalization index of a station or an area according to the user use data;
s200, constructing a clustering analysis model according to the borrowing and returning normalization index, and carrying out clustering analysis;
and S300, classifying the sites or the regions according to the use mode according to the clustering analysis result.
Unlike NAB data used in the prior art, the present method uses user usage data for usage demand analysis evaluation. Since the user usage data is based on continuous time, real-time borrowing and returning data is included and used as a normalization index for cluster analysis.
In step S100, the user usage data may be collected from card swiping or bank payment code scanning data, a single data field generally includes the time and place of the user' S car borrowing and returning, and the basic information (gender, age, etc.) of the user, and is provided by the operator or the industry governing department, and the data size of one month is within about 10G. This part is a field work, which is usually performed by a project team or a research and development team and a project consignor (an operator or an industry director).
And after the user use data is obtained, data cleaning is needed to be carried out, and invalid data is removed. For time section data and space data, the required sites/areas are screened out by screening in conventional database software and GIS software, for example, the sites/areas are distinguished according to working days and non-working days, and the sites/areas are distinguished according to certain specific areas (such as the periphery of a railway station and certain specific administrative regions). This part of the content is a job, and is usually done independently by a project group or a development team.
In the method, the user use data is based on continuous time and comprises real-time vehicle borrowing data and real-time vehicle returning data, so that the error that the vehicle borrowing and the vehicle returning are mutually offset in the conventional method can be avoided. In addition, due to the fact that the special label is arranged on the scheduling behavior in the use data, the scheduling behavior can be easily screened out, and therefore the fact that the scheduling behavior influences real requirements is avoided.
Specifically, the normalization index of the car borrowing and returning is calculated by the daily real-time car returning amount FI (the station or regional parking is increased) and the daily real-time car borrowing amount FO (the station or regional parking is decreased), and the daily real-time car returning amount FI and the daily real-time car borrowing amount FO are averaged for a plurality of days, so that the average value is more accurate.
For example, for a particular station or area m, the daily real-time return amount FI is represented as a vector FIm：
FIm＝[fim，0，fim，1，fim，2，...，fim，t，...，fim，23]，
Wherein, fim，tThe average vehicle returning amount in the tth hour is represented by t, the t represents the time sequence of 24 hours in the whole day, and t is more than or equal to 0 and less than or equal to 23;
fim，tcalculated from the following formula:
Figure BDA0003230772040000071
wherein, fim，t，iThe number of returning vehicles in the tth hour on the jth day is k, which represents the number of days, and if 30 days are considered in units of months and 8 weekends are removed, the total number of valid days is 22, so that k is equal to 22 and j is not less than 1 and not more than 22.
For a particular station or area m, the daily real-time loan amount FO is expressed as a vector FOm：
FOm＝[fom，0，fom，1，fom，2，...，fim，t，...fom，23]，
Wherein, fom，tThe average vehicle borrowing amount in the tth hour is represented by t, the t represents the time sequence of 24 hours in the whole day, and t is more than or equal to 0 and less than or equal to 23;
in the formula fom，tCalculated from the following formula:
Figure BDA0003230772040000072
wherein, fom，t，iThe number of borrowed vehicles on the jth day and the tth hour is k, which represents the number of days, and k is 22.
The time-varying car borrowing and returning situation of a specific station or area m within a certain time is represented by a vector FmRepresents:
Fm＝[fim，0，fom，0，fim，1，fom，1，fim，2，fom，2，...，fim，23，fom，23]
this is a set of 48 values of one-dimensional vectors, normalized to Fm, all values divided by the maximum value f of the 48 valuesmaxObtaining the normalized index NF of borrowing and returning carm：
NFm＝[fim，0/fmax，fom，0/fmax，fim，1/fmax，fom，1/fmax，...，fim，23/fmax，fom，23/fmax]The index can represent the car borrowing and returning conditions of all stations/regions at the same latitude.
In step S200, clustering analysis may be performed on each site/region by using k-means clusters with better universality, and verification may be performed by using a contour coefficient (silouette coefficients).
The usage pattern in step S300 includes one or more combinations of a borrowing and balancing double peak pattern, a borrowing and balancing single peak pattern, a borrowing and balancing double peak pattern, and a borrowing and balancing single peak pattern. After clustering is finished, drawing can be performed according to clustering results to form a type drawing of demand evaluation, and the type drawing is connected with an operator or an industry department of charge to provide related results for optimizing the operation scheduling of the Internet renting bicycles (electric bicycles).
Fig. 1 shows a demand characteristic diagram of a typical double-peak internet rental bicycle (electric bicycle) station/area with basically balanced bicycle borrowing and returning (dark color in the figure is the returning and light color is the borrowing). The clustering is provided with a borrowing and returning peak respectively in the morning and at night, and the number of the borrowing and returning peaks is basically the same. The clustering usually occurs in a conventional area, the dispatching pressure of the vehicle borrowing and returning is not large, and the self-adaption can be basically realized.
Fig. 2 shows a typical demand characteristic diagram of a station/area for internet renting bicycles (electric bicycles) with unbalanced bicycle borrowing and returning and double peaks (dark color in the figure is for returning bicycles and light color is for borrowing bicycles). The cluster has two peak car usage, but the station/area has more cars changed, few cars borrowed in the early peak, and the opposite is true in the late peak. The clustering usually occurs in the periphery of the track station, the business district, the dispatching pressure of the borrowing and returning vehicles is large, and the clustering can be jointly dispatched with other unbalanced double peak stations/areas.
Fig. 3 shows a demand characteristic diagram (dark color is for returning bicycles and light color is for returning bicycles) of a typical type of internet rental bicycle (electric bicycle) stations/areas with unbalanced bicycle borrowing and returning, and only 1 vehicle peak is in the cluster in the evening, and the bicycle borrowing and returning are in an unbalanced state. The clustering usually occurs in the periphery of schools, the dispatching pressure of the borrowing and returning of the vehicles is large, and the vehicles are usually required to be dispatched separately.
The demand characteristic diagram of the balance single peak mode of the borrowing and returning vehicles is similar to that in fig. 3, the difference lies in that the number of the borrowing and returning vehicles is basically the same, and the description is omitted.
The method in the embodiment of the present application may also be stored in a readable storage medium in the form of software. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially implemented or a part contributing to the prior art may be embodied in the form of a software product stored in a storage medium, and including several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: u disk, removable hard disk, read only memory, magnetic or optical disk, etc. Thus, embodiments of the invention are not limited to any specific combination of hardware and software.
The above description is only a preferred example of the present application and should not be taken as limiting the present application, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present application should be included in the scope of the present application.

Claims (10)

1. An Internet rental bicycle demand characteristic evaluation method is characterized by comprising the following steps:
calculating a borrowing and returning normalization index of a station or an area according to the user use data;
constructing a clustering analysis model according to the borrowing and returning normalization index, and carrying out clustering analysis;
and classifying the sites or the regions according to the using modes according to the clustering analysis result.
2. The internet rental bicycle demand characteristic evaluation method of claim 1, wherein the user usage data is based on continuous time.
3. The internet rental bicycle demand characteristic evaluation method of claim 2, wherein the user usage data includes real-time borrowing data and real-time returning data.
4. The internet bicycle rental demand characteristic evaluation method according to claim 3, wherein the bicycle borrowing and returning normalization index is calculated by a daily real-time bicycle return amount FI and a daily real-time bicycle borrowing amount FO, and the daily real-time bicycle return amount FI and the daily real-time bicycle borrowing amount FO are averaged over a plurality of days.
5. The Internet rental bicycle demand characteristic evaluation method of claim 4, wherein the daily real-time return bicycle amount FI is represented as a vector FI for a specific station or area mm：
FIm＝[fim，0，fim，1，fim，2，...，fim，t，...，fim，23]，
Wherein, fim，tThe average vehicle returning amount in the tth hour is represented by t, the t represents the time sequence of 24 hours in the whole day, and t is more than or equal to 0 and less than or equal to 23;
fim，tcalculated from the following formula:
Figure FDA0003230772030000011
wherein，fim，t，iThe number of returned vehicles in the tth hour on the jth day is k, which represents the number of days, and k is 22.
6. The internet rental bicycle demand characteristic evaluation method of claim 5, wherein the daily live loan amount FO is expressed as a vector FO for a specific station or area mm：
FOm＝[fom，0，fom，1，fom，2，...，fim，t，...fom，23]，
Wherein, fom，tThe average vehicle borrowing amount in the tth hour is represented by t, the t represents the time sequence of 24 hours in the whole day, and t is more than or equal to 0 and less than or equal to 23;
in the formula fom，tCalculated from the following formula:
Figure FDA0003230772030000021
wherein, fom，t，iThe number of borrowed vehicles on the jth day and the tth hour is k, which represents the number of days, and k is 22.
7. The method for evaluating demand characteristics of bicycles leased on internet as claimed in claim 6, wherein the time-varying returning of bicycles at a specific station or area m is represented by a vector FmRepresents:
Fm＝[fim，0，fom，0，fim，1，fom，1，fim，2，fom，2，...，fim，23，fom，23]
to FmNormalization is performed, and all values are divided by the maximum value f of the 48 valuesmaxObtaining the normalized index NF of borrowing and returning carm：
NFm＝[fim，0/fmax，fom，0/fmax，fim，1/fmax，fom，1/fmax，...，fim，23/fmax，fom，23/fmax]。
8. The internet rental bicycle demand characteristic evaluation method of claim 1, wherein the clustering analysis adopts a k-means clustering method.
9. The internet rental bicycle demand characteristic evaluation method of claim 1, wherein the usage patterns include one or more combinations of a borrowing and returning balanced double peak pattern, a borrowing and returning balanced single peak pattern, a borrowing and returning unbalanced double peak pattern, and a borrowing and returning unbalanced single peak pattern.
10. A readable storage medium, wherein the storage medium stores thereon a program that, when executed by a processor, implements the internet rental bicycle demand characteristic evaluation method according to any one of claims 1 to 9.
CN202110986179.2A 2021-08-26 2021-08-26 Internet rental bicycle demand characteristic evaluation method and storage medium Pending CN113689124A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110986179.2A CN113689124A (en) 2021-08-26 2021-08-26 Internet rental bicycle demand characteristic evaluation method and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110986179.2A CN113689124A (en) 2021-08-26 2021-08-26 Internet rental bicycle demand characteristic evaluation method and storage medium

Publications (1)

Publication Number Publication Date
CN113689124A true CN113689124A (en) 2021-11-23

Family

ID=78582792

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110986179.2A Pending CN113689124A (en) 2021-08-26 2021-08-26 Internet rental bicycle demand characteristic evaluation method and storage medium

Country Status (1)

Country Link
CN (1) CN113689124A (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104636828A (en) * 2015-02-02 2015-05-20 西南交通大学 Public bicycle station supply and demand prediction method based on Markov chain
CN106296350A (en) * 2016-08-04 2017-01-04 杭州电子科技大学 A kind of visual analyzing city public bicycle system borrows the method for also pattern
CN108470033A (en) * 2018-02-01 2018-08-31 杭州电子科技大学 A kind of city public bicycle system borrows the visual analysis method of also pattern
CN109583491A (en) * 2018-11-23 2019-04-05 温州职业技术学院 A kind of shared bicycle intelligent dispatching method
US20190228661A1 (en) * 2016-09-29 2019-07-25 Tomtom Traffic B.V. Methods and Systems for Generating Parking Related Data
CN110929783A (en) * 2019-11-21 2020-03-27 同济大学 Land use attribute classification method of rented and returned data based on shared object

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104636828A (en) * 2015-02-02 2015-05-20 西南交通大学 Public bicycle station supply and demand prediction method based on Markov chain
CN106296350A (en) * 2016-08-04 2017-01-04 杭州电子科技大学 A kind of visual analyzing city public bicycle system borrows the method for also pattern
US20190228661A1 (en) * 2016-09-29 2019-07-25 Tomtom Traffic B.V. Methods and Systems for Generating Parking Related Data
CN108470033A (en) * 2018-02-01 2018-08-31 杭州电子科技大学 A kind of city public bicycle system borrows the visual analysis method of also pattern
CN109583491A (en) * 2018-11-23 2019-04-05 温州职业技术学院 A kind of shared bicycle intelligent dispatching method
CN110929783A (en) * 2019-11-21 2020-03-27 同济大学 Land use attribute classification method of rented and returned data based on shared object

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
徐瑗瑗;顾天奇;: "基于二重拆分模型的新建轨道交通对公共自行车时空需求的影响", 江苏城市规划, no. 2020, pages 17 - 25 *

Similar Documents

Publication Publication Date Title
Abowd The effect of wage bargains on the stock market value of the firm
CN104303199B (en) The system and method with presenting are analyzed for used car pricing data
CN103440557B (en) A kind of group merges account and the generation method and system of consolidated accounts
US20030061064A1 (en) Method for obtaining and allocating investment income based on the capitalization of intellectual property
US20030093289A1 (en) Reporting and collecting rent payment history
CN107944665A (en) A kind of Engineering Project Information Management System and method
CN103236014A (en) Method for flexibly defining payment and ownership formulas of enterprise annuity account management system
CN111798057A (en) Charging station site selection method based on fuzzy level profit analysis
Stern Services in the international economy
CN113689124A (en) Internet rental bicycle demand characteristic evaluation method and storage medium
CN116681450B (en) Customer credit evaluation method and system supporting intelligent fee-forcing
JP2004288058A (en) Management accounting information processing system, equipment thereof, method therefor, and computer program therefor
CN114416686B (en) Vehicle equipment fingerprint CARID identification system and identification method
CN115827798A (en) Bill management method established based on industry characteristics
Chakraborty et al. Predictive models to measure the impact of fiber-optic broadband speeds on local towns and communities
Barcaroli et al. Optimal sampling design for household finance surveys using administrative income data
CN1049236A (en) The tracking of ticket operating position and system
CN112529712A (en) Modeling method and system for user operation analysis RFM
JP5228134B1 (en) Expense management support system for vehicle, expense management support method, information processing apparatus, and computer program
JP2000137746A (en) Real estate investment index system
McCarthy European integration, urban economic change, and public policy responses
Приймачук Internal transfer prices as a tool for financial management of a company
TW200411457A (en) Notes receivable management system and method
Tindale Impact Fees-Issues
CN116266330A (en) Novel accounting and billing system and method with information enabling function

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