CN104537071A - Benefit analysis method and system for parking lot - Google Patents

Benefit analysis method and system for parking lot Download PDF

Info

Publication number
CN104537071A
CN104537071A CN201410842323.5A CN201410842323A CN104537071A CN 104537071 A CN104537071 A CN 104537071A CN 201410842323 A CN201410842323 A CN 201410842323A CN 104537071 A CN104537071 A CN 104537071A
Authority
CN
China
Prior art keywords
data
factor
parking lot
training
influence
Prior art date
Application number
CN201410842323.5A
Other languages
Chinese (zh)
Inventor
唐健
陈毅林
黄佳欢
Original Assignee
深圳市科漫达智能管理科技有限公司
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 深圳市科漫达智能管理科技有限公司 filed Critical 深圳市科漫达智能管理科技有限公司
Priority to CN201410842323.5A priority Critical patent/CN104537071A/en
Publication of CN104537071A publication Critical patent/CN104537071A/en

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06QDATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00Commerce, e.g. shopping or e-commerce
    • G06Q30/02Marketing, e.g. market research and analysis, surveying, promotions, advertising, buyer profiling, customer management or rewards; Price estimation or determination
    • G06Q30/0201Market data gathering, market analysis or market modelling

Abstract

The invention discloses a benefit analysis method and system for a parking lot. The method comprises the steps that training set data of the parking lot are acquired; classification attribute data in the training set data are converted into numeric attribute data; a model for the converted training set data is constructed by utilizing a numerical prediction algorithm, so a benefit model is obtained. In this way, an analyzer can find the relation between benefits of the parking lot and all factors in the impact factors conveniently through the benefit model, and the purpose of improving working efficiency by automatically analyzing the relation between benefit values of the parking lot and all the factors in the impact factors is achieved.

Description

Parking lot income analysis method and system
Technical field
The present invention relates to data mining technology field, particularly relate to a kind of parking lot income analysis method and system.
Background technology
Usually, parking lot management person wishes through parking lot form, not only can see the management state in parking lot, can see again and be hidden in parking lot report data useful information behind, such as parking lot financial value and affect situation of Profit factor of influence in relation between each factor, then improve the financial value in parking lot further by these relation informations.But in the method for the relation in existing excavation parking data in parking lot financial value and factor of influence between each factor, need manually in person to analyze report data, such mode is lost time, inefficiency.
Summary of the invention
In view of this, the invention provides a kind of parking lot income analysis method and system, to reach the relation in automatic analysis parking lot financial value and factor of influence between each factor, and then the object of increasing work efficiency.
For solving the problems of the technologies described above, the invention provides a kind of parking lot income analysis method, comprising:
Obtain parking lot training set data;
The data of categorical attribute in described training set data are converted to the data of numerical attribute;
Utilize numerical prediction algorithm, model is built to the training set data after conversion, obtains earnings pattern, so that analyst finds out the relation in parking lot income and described factor of influence between each factor by described earnings pattern;
Wherein, described training set data comprises: the financial value of numerical attribute and the factor of influence of categorical attribute, and described factor of influence at least comprises: parking area mark, supplementary service mark, expenses standard mark, type of vehicle mark and car owner's relevant information.
In said method, preferably, after obtaining earnings pattern, also comprise:
Described earnings pattern is shown, so that analyst finds out the relation in parking lot income and described factor of influence between each factor by described earnings pattern with graphical format.
In said method, preferably, after obtaining earnings pattern, also comprise:
Utilize earnings pattern described in test set data test, until the result precision of described earnings pattern reaches default accuracy lower limit.
In said method, preferably, after obtaining earnings pattern, also comprise:
Determine factor of influence to be predicted;
Described factor of influence to be predicted is substituted into described earnings pattern, obtains predicting financial value.
In said method, preferably, described prediction financial value shows with report form.
In said method, preferably, when described numerical prediction algorithm is linear regression algorithm, by following steps, model is built to the training set data after conversion, obtains earnings pattern:
Using described financial value as dependent variable, in described factor of influence, each factor is as independent variable, utilizes linear regression algorithm, and build the linear representation between each factor in described financial value and described factor of influence, the linear representation obtained is earnings pattern.
In said method, preferably, by before in described training set data, the data of categorical attribute are converted to the data of numerical attribute, also comprise:
Determine the redundant data in described training set data;
Delete described redundant data, to realize operating the dimensionality reduction of described training set data.
In said method, preferably, by before in described training set data, the data of categorical attribute are converted to the data of numerical attribute, also comprise:
Determine the exceptional value in described training set data and/or isolated point;
Delete described exceptional value and/or isolated point, to realize operating the denoising of described training set data.
Present invention also offers a kind of parking lot income analysis system, comprising:
Data capture unit, for obtaining parking lot training set data;
Converting unit, for being converted to the data of numerical attribute by the data of categorical attribute in described training set data;
Model construction unit, for utilizing numerical prediction algorithm, building model to the training set data after conversion, obtaining earnings pattern, so that analyst finds out the relation in parking lot income and described factor of influence between each factor by described earnings pattern;
Wherein, described training set data comprises: the financial value of numerical attribute and the factor of influence of categorical attribute, and described factor of influence at least comprises: parking area mark, supplementary service mark, expenses standard mark, type of vehicle mark and car owner's relevant information.
In said system, preferably, also comprise:
Display unit, for showing described earnings pattern with graphical format, so that analyst finds out the relation in parking lot income and described factor of influence between each factor by described earnings pattern.
Above in the income analysis method and system of parking lot provided by the invention, first obtain the parking lot training set data comprising financial value and factor of influence, then the data of categorical attribute in training set data are converted to the data of numerical attribute, to adapt to the demand of follow-up modeling, finally recycle numerical prediction algorithm, model is built to the training set data after conversion, obtain earnings pattern, by this earnings pattern, analyst can find out the relation in middle financial value and factor of influence between each factor, and the reasonable proposal providing raising parking lot income makes a policy for managerial personnel, to improve the income in parking lot, foregoing provides a kind of full automatic income analysis technical scheme based on parking lot training set data, reaches the relation between each factor in automatic analysis parking lot financial value and factor of influence, and then the object of increasing work efficiency.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only embodiments of the invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to the accompanying drawing provided.
Fig. 1 is the process flow diagram of a kind of parking lot of the present invention income analysis embodiment of the method 1;
Fig. 2 is the process flow diagram of a kind of parking lot of the present invention income analysis embodiment of the method 2;
Fig. 3 is a kind of process flow diagram of a kind of parking lot of the present invention income analysis embodiment of the method 3;
Fig. 4 is the another kind of process flow diagram of a kind of parking lot of the present invention income analysis embodiment of the method 3;
Fig. 5 is the structured flowchart of a kind of parking lot of the present invention income analysis system embodiment 1.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
Core of the present invention is to provide a kind of parking lot income analysis method and system, to reach the relation that automatic analysis obtains in parking lot financial value and factor of influence between each factor, and then the object of increasing work efficiency.
In order to make those skilled in the art person understand the present invention program better, below in conjunction with the drawings and specific embodiments, the present invention is described in further detail.
With reference to figure 1, show the process flow diagram of a kind of parking lot of the present invention income analysis embodiment of the method 1, the method can comprise the steps:
Step S100, acquisition parking lot training set data;
Wherein, described training set data comprises: the financial value of numerical attribute and the factor of influence of categorical attribute, and described factor of influence at least comprises: parking area mark, supplementary service mark, expenses standard mark, type of vehicle mark and car owner's relevant information;
It should be noted that, parking data in the present invention can relate to three data sets: parking lot training set data, test set data and inspection set data, wherein, parking lot training set data and test set data adopt the method for division to take from identical parking data collection usually, and inspection set data are from different parking data environment.
In the present invention, the historical data mainly for parking lot is analyzed, and using the additional function of analytical approach provided by the invention as parking lot form, namely expands based on managing system of car parking report capability, increases parking lot income analysis system;
Wherein, parking area mark and supplementary service mark are referred to as car park areas mark, and car park areas mark, as a broad concept, can be subdivided into following two aspects: region, parking lot, mainly refer to the overall situation in this region, corresponding parking area mark; The Additional Services place of region, parking lot, such as supermarket, market, diet StoreFront etc., corresponding supplementary service mark;
Certainly, factor of influence is except above-mentioned three kinds of factors, can also be that other affects the factor of parking lot financial value, such as a series of factor such as parking lot hardware facility and environment, time marking, favor information, wherein, time marking comprises ordinary times mark and holiday time mark, and the present embodiment is only illustrate for several factors that influence degree in practical application is higher, the factor that can have influence on parking lot financial value is not limited to any, as long as can be introduced;
Step S101, the data of categorical attribute in described training set data are converted to the data of numerical attribute;
Consider in parking data to there is a large amount of categorical attributes, as parking lot title, region, type of vehicle, brand etc., parking lot income is numerical attribute, and numerical analysis is compared and is conducive to improving analysis speed and efficiency, see with this angle, can first be changed data attribute by vanning or MDL technology, again the data of categorical attribute in described parking data are converted to the data of numerical attribute, make data enter model as input variable, and then use numerical prediction algorithm to set up earnings pattern.
Step S102, utilize numerical prediction algorithm, model is built to the training set data after conversion, obtains earnings pattern, so that the relation in customer analysis parking lot income and described factor of influence between each factor.
Understand the relation between parking lot income and single factor of influence by earnings pattern, what parameter represented each factor affects intensity, and is converted to intelligible rule format and feeds back to system user, after namely obtaining earnings pattern, also comprises:
Described earnings pattern is shown with graphical format, macroscopic view as parking lot income embodies, and predict the financial value in parking lot in future time section, so that analyst finds out the relation in parking lot income and described factor of influence between each factor by earnings pattern, and the reasonable proposal providing raising parking lot income makes a policy for managerial personnel.Here it should be noted that, the dependent variable due to earnings pattern is numbered type, therefore is generally the tendency removing to describe numerical value with curve map;
The display mode of above-mentioned employing curve map, the historical yield situation for the ease of representing parking lot more intuitively and future trend, this only just gives an example, certainly, also can adopt the display mode of bar chart, just take the tendency of the easier description income intuitively of curve map, in fact, as long as show in directly perceived, simple mode, the visual patterns such as such as rule, decision tree or figure, just can adopt.
In the present invention, consider to use simple and the most conventional linear regression algorithm, build the model between parking lot income and correlation factor, particularly, by following steps, model is built to the training set data after conversion, obtain earnings pattern:
Using described financial value as dependent variable, the data that in described factor of influence, each factor pair is answered are as independent variable, utilize linear regression algorithm, build the linear representation between each factor in described financial value and described factor of influence, the linear representation obtained is earnings pattern.
In order to ensure accuracy and the versatility of earnings pattern, after obtaining above-mentioned earnings pattern, also need to utilize test data set constantly to revise parameter in earnings pattern, until earnings pattern performance is good, particularly, after obtaining earnings pattern, also comprise:
Utilize earnings pattern described in test set data test, until the result precision of described earnings pattern reaches default accuracy lower limit;
And, inspection set data can also be utilized to produce earnings forecast value as the input of earnings pattern, according to the performance of error judgment model under other data environments between model prediction financial value and actual gain value, when error is in setting range, this error can be ignored, show that earnings pattern performance is good, otherwise, then need to rethink utilize other algorithms build model;
Wherein, training dataset and test data set are extracted from same data centralization by leaving-one method usually, and check data collection is then take from different pieces of information collection.Because in actual applications, earnings pattern is concentrated may show instability in different pieces of information, or even diametrically opposite assay, only have by constantly changing and correction model, constantly test and feed back, could produce healthy and strong model, this process may produce the situation of overfitting, need to utilize check data the set pair analysis model to test, avoid the risk of overfitting;
For the earnings pattern obtained in above-mentioned steps S102, its accuracy is an ideal value, and without the inspection of check data collection, at this moment, by check data collection, can test to final mask, avoid model depending on unduly data set;
The result precision of earnings pattern described above reaches default accuracy lower limit, can think that now earnings pattern performance is good, consider and need to ensure there is higher accuracy, this default accuracy lower limit is preferably 95%, certainly, in actual applications, for different user groups, it is also different to the requirement of result precision, can be set here by those skilled in the art according to concrete condition.
Managing system of car parking, as the soft service in parking lot, is rapidly developed in recent years.The application of relevant new technology is served easily for parking lot management person provides on the one hand, improves the competitive level of industry on the other hand.Large data technique flourish, makes industry smell boundless vital force.From form and the pattern of parking lot service, no longer rest on traditional mode, channel and Internet resources form, but round the embody rule launched to consume the thing connectionization of serving as theme, centered by excavation that self-oriented, business-like " on line+line under " serves.For parking lot Report Forms Service, supvr wishes the management state being not only parking lot seen, more wishes to see to be hidden in data useful information behind, wishes the income promoting parking lot by these information further, but, really provide the product of this function also few at present.
The present invention is intended to the Reports module expanding parking management system, by the related algorithm of Data Mining, for parking data, build the mathematical model of parking lot income and the relative influence factor, excavate and be hidden in data business rule behind, understand the realistic meaning of analytical model in conjunction with business, for parking lot management person provides more reasonably improvement strategy, improve the income in parking lot.
By obtaining earnings pattern in the income analysis method of above parking lot provided by the invention, user can obtain the relation in parking lot income and described factor of influence between each factor easily; Foregoing provides a kind of full automatic income analysis technical scheme based on parking lot training set data, reaches the relation that automatic analysis obtains in parking lot financial value and factor of influence between each factor, and then the object of increasing work efficiency.
With reference to figure 2, show the process flow diagram of a kind of parking lot of the present invention income analysis embodiment of the method 2, the method can comprise the steps: after obtaining earnings pattern, also comprises:
Step S200, determine factor of influence to be predicted; Wherein, factor of influence to be predicted preferably affects the larger factor of intensity to financial value;
Step S201, described factor of influence to be predicted is substituted into described earnings pattern, obtain predicting financial value.Particularly, using the parking data in following certain period as the input value of factor of influence in earnings pattern, the financial value of this time period is predicted.
In the present invention, described prediction financial value shows with report form, and namely parking data is after earnings pattern process, and the prediction financial value obtained represents with the form of form;
Give an example, predict the situation of Profit in parking lot November, obtain predicting financial value, such as this prediction financial value is 100,000, when obtaining the actual gain value in November, is such as 80,000, and then comparing 100,000 and 80,000, to obtain relative error be 20%; The users such as such as parking lot management person can for the gap between prediction financial value and actual gain value, utilize earnings pattern, analyze the concrete reason causing this gap, and then provide specific aim strategy and suggestion for parking lot operator, as changed parking fee collective system strategy, arranging the related hardware facility in parking lot, or consider that parking lot and periphery commercial circle are carried out binding and served.
What parking lot management person wanted is result, and does not mind the production process of result, and the readability of the result link that to be whole analytical approach final.First combination model result and business are analyzed, and consider secondly, show result, can adopt rule in Reports module with intuitive manner, or bar graph form to describe whether same reality.
With reference to figure 3, show a kind of process flow diagram of a kind of parking lot of the present invention income analysis embodiment of the method 3, by before the data of categorical attribute are converted to the data of numerical attribute in described parking data, also comprise:
Step S300, the redundant data determined in described training set data;
Particularly, determine the degree of correlation between each dependent variable by Linear correlative analysis, determine the redundant data in parking data;
Step S301, delete described redundant data, to realize operating the dimensionality reduction of described training set data.
Wherein, dimensionality reduction refers to the quantity reducing and enter the factor of influence in model construction stage, because some factor correlativity is higher, there will be overlapping phenomenon to the impact of financial value, needs the factor removing this part;
Because in the form of parking lot, data are lengthy and jumbled, a lot of data dimension is useless in system, if accounts information, holder name and numbering can not, as the factor affecting parking lot income, in fact also be all like this.In addition, may there is correlativity in the some effects factor, affects the foundation of model.By dimensionality reduction, factor of influence is simplified more, reduce the risk of model overfitting.
Even if carried out dimensionality reduction operation, data have also needed further process, and denoising process clears data exceptional value in record and isolated point, eliminates the abnormal operation because human factor causes and the junk data that causes;
With reference to figure 4, show the another kind of process flow diagram of a kind of parking lot of the present invention income analysis embodiment of the method 3, by before the data of categorical attribute are converted to the data of numerical attribute in described training set data, also comprise:
Step S400, determine exceptional value in described training set data and/or isolated point;
Step S401, delete described exceptional value and/or isolated point, to realize operating the denoising of described training set data.
Wherein, denoising refers to remove the noise spot in data, more namely because faulty operation is preserved or very special data, because these data are special case, if do not removed, can bring very large impact to the accuracy of model;
In the present invention, principal component analysis (PCA) (principle components analysis) is adopted to the historical data of managing system of car parking, select to affect the maximum dimension of variance as master variable, residue dimension can be considered to delete selectively or retain, utilize the clustering algorithms such as k-means to carry out simple filtration to data, delete the data that performance is abnormal.
To sum up, in the present invention, the present embodiment carries out dimensionality reduction for the redundant data in parking data and denoising two step removes pre-service, certainly, preferably, all performs dimensionality reduction operation and denoising operation, with the accuracy making earnings pattern reach fully high in analytic process.
Corresponding with a kind of parking lot of the invention described above income analysis embodiment of the method 1, the present invention also provides a kind of parking lot income analysis system embodiment 1, and with reference to figure 5, this parking lot income analysis system 500 can comprise:
Data capture unit 501, for obtaining parking lot training set data;
Wherein, described training set data comprises: the financial value of numerical attribute and the factor of influence of categorical attribute, and described factor of influence at least comprises: parking area mark, supplementary service mark, expenses standard mark, time marking, type of vehicle mark and car owner's relevant information;
Converting unit 502, for being converted to the data of numerical attribute by the data of categorical attribute in described training set data;
Model construction unit 503, for utilizing numerical prediction algorithm, building model to the training set data after conversion, obtaining earnings pattern, so that the relation in customer analysis parking lot income and described factor of influence between each factor.
Preferably, parking lot income analysis system 500 also comprises:
Display unit, for showing described earnings pattern with graphical format, so that analyst finds out the relation in parking lot income and described factor of influence between each factor by described earnings pattern, and so that analyst understands the situation of Profit in the time in the past section of parking lot intuitively, and provide the earnings forecast value in following a period of time.
To sum up, the present invention carries out modeling mainly for the historical data in parking lot, excavate the key factor affecting parking lot income, thus provide specific aim strategy and suggestion for parking lot operator, as changed parking fee collective system strategy, arranging the related hardware facility in parking lot, or consider that parking lot and periphery commercial circle are carried out binding and served.Using the additional function of this analysis system as parking lot form, by pre-service, dimensionality reduction, denoising and conversion are carried out to data, utilize the model between data mining related algorithm structure parking lot income and factor of influence, process and extract the management tactics of rationality, carrying out decision analysis for parking lot operator.
It should be noted that, each embodiment in this instructions all adopts the mode of going forward one by one to describe, and what each embodiment stressed is the difference with other embodiment, between each embodiment identical similar part mutually see.For system class embodiment, due to itself and embodiment of the method basic simlarity, so describe fairly simple, relevant part illustrates see the part of embodiment of the method.
Above parking lot provided by the present invention income analysis method and system are described in detail.Apply specific case herein to set forth principle of the present invention and embodiment, the explanation of above embodiment just understands method of the present invention and core concept thereof for helping.It should be pointed out that for those skilled in the art, under the premise without departing from the principles of the invention, can also carry out some improvement and modification to the present invention, these improve and modify and also fall in the protection domain of the claims in the present invention.

Claims (10)

1. a parking lot income analysis method, is characterized in that, comprising:
Obtain parking lot training set data;
The data of categorical attribute in described training set data are converted to the data of numerical attribute;
Utilize numerical prediction algorithm, model is built to the training set data after conversion, obtains earnings pattern, so that analyst finds out the relation in parking lot income and described factor of influence between each factor by described earnings pattern;
Wherein, described training set data comprises: the financial value of numerical attribute and the factor of influence of categorical attribute, and described factor of influence at least comprises: parking area mark, supplementary service mark, expenses standard mark, type of vehicle mark and car owner's relevant information.
2. the method for claim 1, is characterized in that, after obtaining earnings pattern, also comprises:
Described earnings pattern is shown, so that analyst finds out the relation in parking lot income and described factor of influence between each factor by described earnings pattern with graphical format.
3. the method for claim 1, is characterized in that, after obtaining earnings pattern, also comprises:
Utilize earnings pattern described in test set data test, until the result precision of described earnings pattern reaches default accuracy lower limit.
4. the method for claim 1, is characterized in that, after obtaining earnings pattern, also comprises:
Determine factor of influence to be predicted;
Described factor of influence to be predicted is substituted into described earnings pattern, obtains predicting financial value.
5. method as claimed in claim 4, it is characterized in that, described prediction financial value shows with report form.
6. the method for claim 1, is characterized in that, when described numerical prediction algorithm is linear regression algorithm, builds model, obtain earnings pattern by following steps to the training set data after conversion:
Using described financial value as dependent variable, in described factor of influence, each factor is as independent variable, utilizes linear regression algorithm, and build the linear representation between each factor in described financial value and described factor of influence, the linear representation obtained is earnings pattern.
7. the method for claim 1, is characterized in that, by before in described training set data, the data of categorical attribute are converted to the data of numerical attribute, also comprises:
Determine the redundant data in described training set data;
Delete described redundant data, to realize operating the dimensionality reduction of described training set data.
8. the method for claim 1, is characterized in that, by before in described training set data, the data of categorical attribute are converted to the data of numerical attribute, also comprises:
Determine the exceptional value in described training set data and/or isolated point;
Delete described exceptional value and/or isolated point, to realize operating the denoising of described training set data.
9. a parking lot income analysis system, is characterized in that, comprising:
Data capture unit, for obtaining parking lot training set data;
Converting unit, for being converted to the data of numerical attribute by the data of categorical attribute in described training set data;
Model construction unit, for utilizing numerical prediction algorithm, building model to the training set data after conversion, obtaining earnings pattern, so that analyst finds out the relation in parking lot income and described factor of influence between each factor by described earnings pattern;
Wherein, described training set data comprises: the financial value of numerical attribute and the factor of influence of categorical attribute, and described factor of influence at least comprises: parking area mark, supplementary service mark, expenses standard mark, type of vehicle mark and car owner's relevant information.
10. system as claimed in claim 9, is characterized in that, also comprise:
Display unit, for showing described earnings pattern with graphical format, so that analyst finds out the relation in parking lot income and described factor of influence between each factor by described earnings pattern.
CN201410842323.5A 2014-12-30 2014-12-30 Benefit analysis method and system for parking lot CN104537071A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201410842323.5A CN104537071A (en) 2014-12-30 2014-12-30 Benefit analysis method and system for parking lot

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201410842323.5A CN104537071A (en) 2014-12-30 2014-12-30 Benefit analysis method and system for parking lot

Publications (1)

Publication Number Publication Date
CN104537071A true CN104537071A (en) 2015-04-22

Family

ID=52852599

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201410842323.5A CN104537071A (en) 2014-12-30 2014-12-30 Benefit analysis method and system for parking lot

Country Status (1)

Country Link
CN (1) CN104537071A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107067801A (en) * 2017-03-08 2017-08-18 深圳市科漫达智能管理科技有限公司 A kind of abnormality eliminating method and device based on parking data

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102110265A (en) * 2009-12-23 2011-06-29 深圳市腾讯计算机系统有限公司 Network advertisement effect estimating method and network advertisement effect estimating system
US20120296701A1 (en) * 2008-07-14 2012-11-22 Wahrheit, Llc System and method for generating recommendations
CN103426103A (en) * 2013-08-02 2013-12-04 苏州两江科技有限公司 Supermarket market value map construction method
CN103578057A (en) * 2012-08-10 2014-02-12 北京奥齐都市网络科技有限公司 Real estate value estimation method based on artificial neural network statistic model

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120296701A1 (en) * 2008-07-14 2012-11-22 Wahrheit, Llc System and method for generating recommendations
CN102110265A (en) * 2009-12-23 2011-06-29 深圳市腾讯计算机系统有限公司 Network advertisement effect estimating method and network advertisement effect estimating system
CN103578057A (en) * 2012-08-10 2014-02-12 北京奥齐都市网络科技有限公司 Real estate value estimation method based on artificial neural network statistic model
CN103426103A (en) * 2013-08-02 2013-12-04 苏州两江科技有限公司 Supermarket market value map construction method

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107067801A (en) * 2017-03-08 2017-08-18 深圳市科漫达智能管理科技有限公司 A kind of abnormality eliminating method and device based on parking data

Similar Documents

Publication Publication Date Title
Daraio et al. Efficiency and effectiveness in the urban public transport sector: A critical review with directions for future research
US20170329462A1 (en) Graphical user interface for static and adaptive thresholds
US20190147363A1 (en) Adaptive key performance indicator thresholds updated using training data
CN106651424B (en) Power user portrait establishing and analyzing method based on big data technology
Roxas et al. Institutional environment, managerial attitudes and environmental sustainability orientation of small firms
Becker et al. Offshoring and the onshore composition of tasks and skills
Gereffi Global value chains in a post-Washington Consensus world
Rajeev et al. Evolution of sustainability in supply chain management: A literature review
Thomson ‘But does sustainability need capitalism or an integrated report’a commentary on ‘The International Integrated Reporting Council: A story of failure’by Flower, J.
Chen et al. Understanding the relationships between environmental management practices and financial performances of multinational construction firms
Amores-Salvadó et al. Green corporate image: moderating the connection between environmental product innovation and firm performance
CN103218719B (en) A kind of e-commerce website air navigation aid and system
CN103390066B (en) A kind of database overall automation optimizes prior-warning device and disposal route thereof
Schaltegger et al. Expanding material flow cost accounting. Framework, review and potentials
US7640196B2 (en) Method of making capital investment decisions concerning locations for business operations and/or facilities
Figge et al. Value drivers of corporate eco-efficiency: Management accounting information for the efficient use of environmental resources
Acquaye et al. A quantitative model for environmentally sustainable supply chain performance measurement
US10482093B2 (en) Data mining method
Bartelsman et al. Measuring and analyzing cross-country differences in firm dynamics
Möller et al. The sustainability balanced scorecard as a framework for eco‐efficiency analysis
Brown et al. Triple bottom line: a business metaphor for a social construct
Spedding et al. Application of discrete event simulation to the activity based costing of manufacturing systems
US8095417B2 (en) Key performance indicator scorecard editor
Wang et al. Using adaptive network-based fuzzy inference system to forecast automobile sales
Warr et al. Useful work and information as drivers of economic growth

Legal Events

Date Code Title Description
PB01 Publication
SE01 Entry into force of request for substantive examination
C10 Entry into substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20150422

RJ01 Rejection of invention patent application after publication