CN113240446B - Data classification and processing method of artwork estimation system - Google Patents
Data classification and processing method of artwork estimation system Download PDFInfo
- Publication number
- CN113240446B CN113240446B CN202110318403.0A CN202110318403A CN113240446B CN 113240446 B CN113240446 B CN 113240446B CN 202110318403 A CN202110318403 A CN 202110318403A CN 113240446 B CN113240446 B CN 113240446B
- Authority
- CN
- China
- Prior art keywords
- artwork
- auction
- matrix
- price
- estimation
- 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.)
- Active
Links
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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0278—Product appraisal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Mathematical Optimization (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Pure & Applied Mathematics (AREA)
- Library & Information Science (AREA)
- Mathematical Analysis (AREA)
- Strategic Management (AREA)
- Computational Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Computational Linguistics (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Algebra (AREA)
- Software Systems (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a data classification and processing method of an artwork estimation system, which comprises the following steps: step S1: the first data processing module converts the data information; step S2: the second data processing module generates a first estimated bid and a first auction bid interval; step S3: the valuation module generates a second estimated price and a second auction price interval; wherein the character conversion part stores the size, weight, color, age and material information of the artwork in a character database in a byte mode; the picture conversion part stores the pictures of the artwork in a picture database in a pixel value mode; the byte discrimination part generates discrimination bytes by an external input mode, and the discrimination bytes are stored in a discrimination database; the information combining part generates an artwork conversion matrix; and the second data processing module generates a first estimated price and a first auction estimation interval according to the artwork conversion matrix.
Description
Technical Field
The present invention relates generally to the field of valuation calculations, and more particularly to a data classification and processing method for an artwork valuation system.
Background
The artwork valuation refers to the estimation and prediction of the artwork market trading price. Because artwork features are heterogeneous, i.e., each piece of art is unique, and one piece of art may differ significantly from another piece of art, conventional asset assessment methods (e.g., assessment of assets such as real estate, second hand vehicles, etc.) are not fully applicable to artwork valuations. Currently, the methods for estimating the artwork commonly used in the market include the estimation of the artwork by business personnel such as auction houses and galleries according to market transaction experience, and the estimation of the artwork by artwork estimation expert and museum artists according to experience such as the artistic value, historical value and academic value of the artwork. The two common art estimation methods are estimation based on subjective judgment of people, are influenced by personal factors such as experience, learning, preference and the like of estimation people, and are difficult to establish a unified method and a standardized flow.
In this block of artwork estimation using data, there are more academic studies on artwork indexes with Mei Jian and michael-moxidec— Art as an investment and the underperformance of masterpieces, mei, jianping; moses, michael, the American Economic Review; dec 2002;92,5; the paper ProQuest pg.1656 basically confirms that a large idea of data valuation is feasible, and proposes a "repeat transaction model" for price prediction. However, such calculations are particularly demanding in terms of data, requiring artwork to be available for use by repeating the transaction a number of times at the auction. Skate's Art Investment Handbook indicates another possible calculation direction, namely "feature pricing", which refers to price assessment using features of the artwork itself, such as size, material, etc. However, such calculation often cannot guarantee the accuracy. Therefore, the invention provides a data classification and processing method of an artwork evaluation system, so as to at least partially solve the problems.
Disclosure of Invention
In the summary, a series of concepts in simplified form are introduced, which will be further described in detail in the detailed description. The summary of the invention is not intended to define the key features and essential features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter.
In order to at least partially solve the above technical problems, the present invention provides a data classification and processing method of an artwork evaluation system, which includes:
step S1: the first data processing module converts the data information;
step S2: the second data processing module generates a first estimated bid and a first auction bid interval;
step S3: the classification module classifies the levels of the auction companies; the estimation module obtains an estimation calculation formula and data characteristics required by calculation, and generates a second estimated price and a second auction price interval;
the first data processing module comprises a character conversion part, a picture conversion part, a byte discrimination part and an information combination part; the character conversion part stores the size, weight, color, age and material information of the artwork in a character database in a byte mode; the picture conversion part stores the pictures of the artwork in a picture database in a pixel value mode; the byte discrimination part generates discrimination bytes by an external input mode, and the discrimination bytes are stored in a discrimination database; the information combining part invokes the information in the text database, the picture database and the screening database to generate an artwork conversion matrix Tr; the second data processing module generates a first estimated bid and a first auction estimate interval according to the artwork transformation matrix Tr.
Further, the picture conversion part comprises an image segmentation unit, an image recognition comparison unit and an image marking unit; the image segmentation unit segments an image of an artwork, and the image segmentation unit generates a characteristic pixel matrix Q (Q 1 q 2 q 3 ....q n ) In the matrix, q 1 、q 2 、q 3 Recursively to q n Are pixel values of the image;
the identification comparison unit acquires artwork information from the Internet in real time and generates an existing artwork estimation matrix S c And the information file doc to be called c The subscript c represents the number of the existing artwork, and the subscripts c=1, 2, 3 are sequentially incremented until n; the existing artwork estimation matrix is S c (M c N c ) In the matrix, M c To initially identify the pixel matrix, N c As the characteristic pixel matrix, the initial identification pixel matrix is M c (m c1 m c2 m c3 ) In the matrix, m c1 、m c2 、m c3 Are identifiable pixel values; pixel value m c1 、m c2 、m c3 Are all set by people, and the characteristic pixel matrix is N c (n c1 n c2 n c3 ....n cn ) In the matrix, n c1 n c2 n c3 Recursively to n cn All are feature pixel values; information file doc to be called c The method comprises the steps of including an original price for corresponding artwork and an original auction valuation interval;
the image marking unit uses the characteristic pixel matrix Q and the initial identification pixel matrix M c In comparison, when there is an initial identification pixel matrix M j Subscript j is any number of 1, 2, 3..n, matrix M j The value m of (a) j1 m j2 m j3 When the image marking units are in the characteristic pixel matrix Q, the image marking units divide the characteristic pixel matrix Q and the characteristic pixel matrix N j Comparing, the image marking unit generates an identification parameter k according to the comparison result j 。
Further, the image marking unit records the number numQ of pixel values in the characteristic pixel matrix Q, and the image marking unit records the characteristic pixel matrix N j The number numN of the same feature pixel values present in the feature pixel matrix Q, the identification parameter k j ＝numN/numQ。
Further, the byte discriminating part comprises an external information input device, and the external information input device acquires the byte quantity of the artwork to be supplemented; the byte discrimination part generates an artwork integrity evaluation value Inte, wherein the integrity evaluation value Inte=byte 0/byte1; in the formula, byte0 is the byte quantity of the artwork which needs to be supplemented, and byte1 is the existing byte quantity of the artwork.
Further, the artwork transformation matrix is Tr (k j IntE), the second data processing module stores the original price of the artwork and the original auction estimation interval; first pre-estimated price sal1=k j SAL 0 Inte; first auction estimate interval Δsal1=k j ΔSAL 0 The method comprises the steps of carrying out a first treatment on the surface of the Wherein k is j To identify parameters, SAL 0 To make original price of artwork, ΔSAL 0 An original auction rating interval for the artwork; inte is the integrity evaluation value.
Further, the classification module classifies the levels according to the number of the auction companies meeting the judgment standard, and the higher the number of the auction companies meeting the judgment standard is, the higher the level is; influence factor F OI The larger.
Further, the judgment criteria include:
market value judgment criteria, when the total amount of the auction company's deals is greater than or equal to seven turns of the total amount of the market, the auction company satisfies the market value judgment criteria;
the method comprises the steps of collecting capacity judgment standards of works, and setting the judgment standards of collecting capacity of the auction companies when the upper shooting amount of the auction companies exceeds 50% of the same period;
a capability judging standard package for converting the collected beats into sales when the up-beat amount of the auction company exceeds 50% of the same period of the same line, wherein the auction company meets the judging standard of the capability for converting the collected beats into sales;
the average price judgment standard, when the average price of the auction company exceeds the same period of 50%, the auction company meets the average price judgment standard;
and when the auction company meets the judgment standard of successful sales capacity and the past 5 years have a record of accomplishment and the past 6 auction seasons have a record of continuous auction, the auction company meets the judgment standard of successful sales capacity and the continuous collection work.
Further, the estimation module calculates a weight value by using a cauchy function, and the calculation formula is as follows:
wherein α, β, a, b are parameters to be determined, c is an acceptable level value, d is a value of the highest level, c=m is set, the value of the lowest level is 1, f (1) =0.01, f (d) =1, f (m) =n, and the weight value of each level is calculated according to formula (1) by assigning the parameters to be determined α, β, a, b, m, n respectively.
Further, the estimation module establishes a mathematical model quantity relation by using multiple regression analysis;
and (3) establishing a linear model: ln (P) =α+β 1 ln(x) (2)；
Wherein P is a dependent variable, x is an independent variable, alpha, beta 1 Is a coefficient to be determined. The independent variables include: trade price rp, size m, subject f, and auction company level a for similar works; a linear model is built according to the transaction price rp, the size m, the subject f and the auction company level a of the similar works:
ln(P)＝α+β 1 lnrp+β 2 lnm+β 3 lnf+β 4 lna (3)；
wherein P is a dependent variable, alpha, beta 1 、β 2 、β 3 、β 4 Is a coefficient to be determined.
Further, the valuation module determines that the price influencing factors include a similar work trade price rp and a size m; the estimation module sets the influence factors as i respectively 1 、i 2 And a calculation formula (4) is obtained:
in the method, in the process of the invention,trade price average for similar works,/->And alpha is a coefficient to be determined, which is the average size number.
The second estimated trading value is P=EXP [ ln (P)]+F OI SAL1；
Second auction valuation interval P r The calculation formula of (2) is as follows: p (P) r ＝P±σ+F OI Δsal1, where σ is the float calculated at a confidence level of 90%, σ= (1-90)％)P，F OI SAL1 is the first estimated auction price, and ΔSAL1 is the first auction price range, as an impact factor.
Compared with the prior art, the invention has the beneficial effects that: the invention provides a data classification and processing method of an artwork estimation system, which comprises the following steps: step S1: the first data processing module converts the data information; step S2: the second data processing module generates a first estimated bid and a first auction bid interval; step S3: the classification module classifies the levels of the auction companies; the estimation module obtains an estimation calculation formula and data characteristics required by calculation, and generates a second estimated auction price and a second auction price interval; the first data processing module comprises a character conversion part, a picture conversion part, a byte discrimination part and an information combination part; the character conversion part stores the size, weight, color, age and material information of the artwork in a character database in a byte mode; the picture conversion part stores the pictures of the artwork in a picture database in a pixel value mode; the byte discrimination part generates discrimination bytes by an external input mode, and the discrimination bytes are stored in a discrimination database; the information combining part invokes the information in the text database, the picture database and the screening database to generate an artwork conversion matrix Tr; the second data processing module generates a first estimated bid and a first auction estimate interval according to the artwork transformation matrix Tr. The artwork estimation can be performed more accurately.
Drawings
In order that the advantages of the invention will be readily understood, a more particular description of the invention briefly described above will be rendered by reference to specific embodiments that are illustrated in the appended drawings. Understanding that these drawings depict only typical embodiments of the invention and are not therefore to be considered to be limiting of its scope, the invention will be described and explained with additional specificity and detail through the use of the accompanying drawings.
Fig. 1 is a schematic diagram of steps of a data classification and processing method of an artwork evaluation system according to an embodiment of the present invention.
Detailed Description
In the following description, numerous specific details are set forth in order to provide a more thorough understanding of the present invention. It will be apparent, however, to one skilled in the art that embodiments of the invention may be practiced without one or more of these details. In other instances, well-known features have not been described in detail in order to avoid obscuring the embodiments of the invention.
In the following description, a detailed structure will be presented for a thorough understanding of embodiments of the present invention. It will be apparent that embodiments of the invention may be practiced without limitation to the specific details that are familiar to those skilled in the art. Preferred embodiments of the present invention are described in detail below, however, the present invention may have other embodiments in addition to these detailed descriptions.
In the description of the present invention, the terms "inside", "outside", "longitudinal", "transverse", "upper", "lower", "top", "bottom", and the like refer to the orientation or positional relationship based on that shown in the drawings, only for convenience in describing the present invention, and do not require that the present invention must be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention.
Referring to fig. 1, the invention provides a data classification and processing method of an artwork estimation system, which comprises the following steps:
step S1: the first data processing module converts the data information;
step S2: the second data processing module generates a first estimated bid and a first auction bid interval;
step S3: the classification module classifies the levels of the auction companies; the estimation module obtains an estimation calculation formula and data characteristics required by calculation, and generates a second estimated price and a second auction price interval;
the first data processing module comprises a character conversion part, a picture conversion part, a byte discrimination part and an information combination part; the character conversion part stores the size, weight, color, age and material information of the artwork in a character database in a byte mode; the picture conversion part stores the pictures of the artwork in a picture database in a pixel value mode; the byte discrimination part generates discrimination bytes by an external input mode, and the discrimination bytes are stored in a discrimination database; the information combining part invokes the information in the text database, the picture database and the screening database to generate an artwork conversion matrix Tr; the second data processing module generates a first estimated bid and a first auction estimate interval according to the artwork transformation matrix Tr.
Specifically, the picture conversion part comprises an image segmentation unit, an image recognition comparison unit and an image marking unit; the image segmentation unit segments an image of an artwork, and the image segmentation unit generates a characteristic pixel matrix Q (Q 1 q 2 q 3 ....q n ) In the matrix, q 1 、q 2 、q 3 Recursively to q n Are pixel values of the image;
the identification comparison unit acquires artwork information from the Internet in real time and generates an existing artwork estimation matrix S c And the information file doc to be called c The subscript c represents the number of the existing artwork, and the subscripts c=1, 2, 3 are sequentially incremented until n; the existing artwork estimation matrix is S c (M c N c ) In the matrix, M c To initially identify the pixel matrix, N c As the characteristic pixel matrix, the initial identification pixel matrix is M c (m c1 m c2 m c3 ) In the matrix, m c1 、m c2 、m c3 Are identifiable pixel values; pixel value m c1 、m c2 、m c3 Are all set by people, and the characteristic pixel matrix is N c (n c1 n c2 n c3 ....n cn ) In the matrix, n c1 n c2 n c3 Recursively to n cn All are feature pixel values; information file doc to be called c The method comprises the steps of including an original price for corresponding artwork and an original auction valuation interval;
the image marking unit marks the characteristic pixel matrix Q and the initial recognitionPixel matrix M c In comparison, when there is an initial identification pixel matrix M j Subscript j is any number of 1, 2, 3..n, matrix M j The value m of (a) j1 m j2 m j3 When the image marking units are in the characteristic pixel matrix Q, the image marking units divide the characteristic pixel matrix Q and the characteristic pixel matrix N j Comparing, the image marking unit generates an identification parameter k according to the comparison result j 。
The image marking unit records the number numQ of pixel values in the characteristic pixel matrix Q, and the image marking unit records the characteristic pixel matrix N j The number numN of the same feature pixel values present in the feature pixel matrix Q, the identification parameter k j =numn/numQ. The byte discriminating part comprises an external information input device, and the external information input device acquires the byte quantity of the artwork to be supplemented; the byte discrimination part generates an artwork integrity evaluation value Inte, wherein the integrity evaluation value Inte=byte 0/byte1; in the formula, byte0 is the byte quantity of the artwork which needs to be supplemented, and byte1 is the existing byte quantity of the artwork. Artwork transformation matrix Tr (k) j IntE), the second data processing module stores the original price of the artwork and the original auction estimation interval; first pre-estimated price sal1=k j SAL 0 Inte; first auction estimate interval Δsal1=k j ΔSAL 0 The method comprises the steps of carrying out a first treatment on the surface of the Wherein k is j To identify parameters, SAL 0 To make original price of artwork, ΔSAL 0 An original auction rating interval for the artwork; inte is the integrity evaluation value.
Specifically, when the original currency of the price is non-RMB, the original currency is converted into the RMB price, and the intermediate exchange rate is the intermediate exchange rate of the RMB exchanged by the currency in the month where the auction time is obtained; taking dollars as an example, the formula is P rmb ＝EX t *P USD Wherein EX is t The method comprises the steps of obtaining the dollar RMB exchange intermediate exchange rate of the month where the auction time is; when the currency of the auction valuation interval is non-RMB, the non-RMB is converted into the RMB price, and the intermediate exchange rate is the intermediate of the RMB exchanged with the currency of the month in which the auction time is obtainedExchange rate.
Specifically, the classification module classifies the levels according to the number of auction companies meeting the judgment standard, wherein the higher the number of auction companies meeting the judgment standard is, the higher the level is; influence factor F OI The larger.
Specifically, the judgment criteria include:
market value judgment criteria, when the total amount of the auction company's deals is greater than or equal to seven turns of the total amount of the market, the auction company satisfies the market value judgment criteria;
the method comprises the steps of collecting capacity judgment standards of works, and setting the judgment standards of collecting capacity of the auction companies when the upper shooting amount of the auction companies exceeds 50% of the same period;
a capability judging standard package for converting the collected beats into sales when the up-beat amount of the auction company exceeds 50% of the same period of the same line, wherein the auction company meets the judging standard of the capability for converting the collected beats into sales;
the average price judgment standard, when the average price of the auction company exceeds the same period of 50%, the auction company meets the average price judgment standard;
and when the auction company meets the judgment standard of successful sales capacity and the past 5 years have a record of accomplishment and the past 6 auction seasons have a record of continuous auction, the auction company meets the judgment standard of successful sales capacity and the continuous collection work.
Specifically, in the present invention, the size is converted into a size area; considering the habit of painting and calligraphy category, the size area is converted into square ruler number. The calculation formula is (length cm. Wide cm) ×0.0009=square.
Specifically, the estimation module calculates a weight value by using a cauchy function, and the calculation formula is as follows:
where a, β, a, b are undetermined parameters, c is an acceptable level value, d is the highest level value,
setting c=m, the numerical value of the lowest level is 1, f (1) =0.01, f (d) =1, f (m) =n, and calculating the weight value of each level according to the formula (1) by respectively assigning the parameters alpha, beta, a, b, m and n to be determined.
In some embodiments of the present invention, the auction companies are sequentially divided into seven levels of auction companies a, B, C, D, E, F, G (7,6,5,4,3,2,1), wherein the class a auction company satisfies 5 judgment standards, the class B auction company satisfies 4 judgment standards, the class C auction company satisfies 3 judgment standards, the class D auction company satisfies 2 judgment standards, the class E auction company satisfies 1 judgment standard, the class F auction company satisfies 0 judgment standard, and the class G auction company is an auction company that does not play in the middle or does not play in the province.
In some embodiments of the present invention, the values d=7, m=4, n=0.7 at the highest level, the undetermined parameters α= 4.8003, β=0.7788, a=0.5372, b= -0.04532, respectively, are calculated by formula (1), and the calculation results are: A. b, C, D, E, F, G corresponds to (1,0.92,0.82,0.70,0.51,0.24,0.01).
The estimation module uses multiple regression analysis to establish a mathematical model quantity relation;
and (3) establishing a linear model: ln (P) =α+β 1 ln(x) (2)；
Wherein P is a dependent variable, x is an independent variable, alpha, beta 1 Is a coefficient to be determined. The independent variables include: trade price rp, size m, subject f, and auction company level a for similar works; a linear model is built according to the transaction price rp, the size m, the subject f and the auction company level a of the similar works:
ln(P)＝α+β 1 lnrp+β 2 lnm+β 3 lnf+β 4 lna (3)；
wherein P is a dependent variable, alpha, beta 1 、β 2 、β 3 、β 4 Is a coefficient to be determined.
Specifically, the valuation module determines that the price influencing factors include a similar work trade price rp and a size m; the estimation module sets the influence factors as i respectively 1 、i 2 And a calculation formula (4) is obtained:
in the method, in the process of the invention,trade price average for similar works,/->And alpha is a coefficient to be determined, which is the average size number.
The second estimated trading value is P=EXP [ ln (P)]+F OI SAL1；
Second auction valuation interval P r The calculation formula of (2) is as follows: p (P) r ＝P±σ+F OI Δsal1, where σ is the float value calculated at 90% confidence level, σ= (1-90%) P, F OI SAL1 is the first estimated auction price, and ΔSAL1 is the first auction price range, as an impact factor.
In some embodiments of the invention, a piece of artwork original transaction data missing filtering field S 1 Supplementary related information is required. Set S 1 Is the value n by retrieving all the matches S in the database 1 Data of =n, and these data are packed into an appropriate data set.
In some embodiments of the invention, four items of size, subject matter, creation year and mounting are taken as dimensions respectively, a data set meeting the conditions is screened out, the estimated target size is 4.5 square, the mountain and water are estimated, the creation year is 1962, and the mounting is a vertical shaft; the specific screening steps are as follows:
1. screening works with 3-6 flat rules, and reserving the works;
2. screening mountain and water materials, and reserving the mountain and water materials;
3. during the screening years 1960-1970, the screening period remained;
4. screening and mounting the steel plates to be vertical shafts, and keeping the steel plates.
The filtered data is the appropriate data set that can be calculated.
Specifically, after finding the appropriate dataset, the so-calculated price influencing factors i should be included in the collection at this time 1 ,i 2 And an artist constant α. As some artist constant α= -1.164, i 1 ＝0.991,i 2 =0.857, the average number of trade prices for similar works is 10,000, flat rule 4.5, substituted into formula Ln (P) = -1.164+0.991×ln (10,000) +0.857×ln (4.5) =9.127+1.289-1.164= 9.252;
the artwork estimation price is EXP (9.252) =10425.
Unless defined otherwise, technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein is for the purpose of describing particular implementations only and is not intended to be limiting of the invention. Terms such as "component" as used herein may refer to either a single part or a combination of parts. Terms such as "mounted," "disposed," and the like as used herein may refer to one component being directly attached to another component or to one component being attached to another component through an intermediary. Features described herein in one embodiment may be applied to another embodiment alone or in combination with other features unless the features are not applicable or otherwise indicated in the other embodiment.
The present invention has been described in terms of the above embodiments, but it should be understood that the above embodiments are for purposes of illustration and description only and are not intended to limit the invention to the embodiments described. Those skilled in the art will appreciate that many variations and modifications are possible in light of the teachings of the invention, which variations and modifications are within the scope of the invention as claimed.
Claims (5)
1. The data classification and processing method of the artwork estimation system is characterized by comprising the following steps:
step S1: the first data processing module converts the data information;
step S2: the second data processing module generates a first estimated bid and a first auction bid interval;
step S3: the classification module classifies the levels of the auction companies; the estimation module obtains an estimation calculation formula and data characteristics required by calculation, and generates a second estimated price and a second auction price interval;
the first data processing module comprises a character conversion part, a picture conversion part, a byte discrimination part and an information combination part; the character conversion part stores the size, weight, color, age and material information of the artwork in a character database in a byte mode; the picture conversion part stores the pictures of the artwork in a picture database in a pixel value mode; the byte discrimination part generates discrimination bytes by an external input mode, and the discrimination bytes are stored in a discrimination database; the information combining part invokes the information in the text database, the picture database and the screening database to generate an artwork conversion matrix Tr; the second data processing module generates a first estimated price and a first auction estimation interval according to the artwork conversion matrix Tr;
the picture conversion part comprises an image segmentation unit, an image recognition comparison unit and an image marking unit; the image segmentation unit segments an image of an artwork, and the image segmentation unit generates a characteristic pixel matrix Q (Q 1 q 2 q 3 ....q n ) In the matrix, q 1 、q 2 、q 3 Recursively to q n Are pixel values of the image;
the identification comparison unit acquires artwork information from the Internet in real time and generates an existing artwork estimation matrix Sc and an information file doc to be called c The subscript c represents the number of the existing artwork, and the subscripts c=1, 2, 3 are sequentially incremented until k; the existing artwork estimation matrix is S c (M c N c ) In the matrix, M c To initially identify the pixel matrix, N c As the characteristic pixel matrix, the initial identification pixel matrix is M c (m c1 m c2 m c3 ) In the matrix, the number of the cells in the matrix,m c1 、m c2 、m c3 are identifiable pixel values; pixel value m c1 、m c2 、m c3 Are all set by people, and the characteristic pixel matrix is N c (n c1 n c2 n c3 ....n cn ) In the matrix, n c1 n c2 n c3 Recursively to n cn All are feature pixel values; information file doc to be called c The method comprises the steps of including an original price for corresponding artwork and an original auction valuation interval;
the image marking unit uses the characteristic pixel matrix Q and the initial identification pixel matrix M c In comparison, when there is an initial identification pixel matrix M j Subscript j is any number of 1, 2, 3..n, matrix M j The value m of (a) j1 m j2 m j3 When the image marking units are in the characteristic pixel matrix Q, the image marking units divide the characteristic pixel matrix Q and the characteristic pixel matrix N j Comparing, the image marking unit generates an identification parameter k according to the comparison result j ；
The image marking unit records the number numQ of pixel values in the characteristic pixel matrix Q, and the image marking unit records the characteristic pixel matrix N j The number numN of the same feature pixel values present in the feature pixel matrix Q, the identification parameter k j ＝numN/numQ；
The byte discriminating part comprises an external information input device, and the external information input device acquires the byte quantity of the artwork to be supplemented; the byte discrimination part generates an artwork integrity evaluation value Inte, wherein the integrity evaluation value Inte=byte 0/byte1; in the formula, byte0 is the byte quantity of the artwork to be supplemented, and byte1 is the existing byte quantity of the artwork;
artwork transformation matrix Tr (k) j IntE), the second data processing module stores the original price of the artwork and the original auction estimation interval; first pre-estimated price sal1=k j SAL 0 Inte; first auction estimate interval Δsal1=k j ΔSAL 0 The method comprises the steps of carrying out a first treatment on the surface of the Wherein k is j To identify parameters, SAL 0 To make original price of artwork, ΔSAL 0 An original auction rating interval for the artwork; inte is the integrity evaluation value.
2. The data classification and processing method of an artwork evaluation system according to claim 1, wherein the classification module classifies the levels according to the number of auction companies satisfying the judgment criteria, the greater the number of auction companies satisfying the judgment criteria, the higher the level thereof; influence factor F OI The larger.
3. The method for classifying and processing data of an artwork evaluation system according to claim 2, wherein the judgment criteria include:
market value judgment criteria, when the total amount of the auction company's deals is greater than or equal to seven turns of the total amount of the market, the auction company satisfies the market value judgment criteria;
the method comprises the steps of collecting capacity judgment standards of works, and setting the judgment standards of collecting capacity of the auction companies when the upper shooting amount of the auction companies exceeds 50% of the same period;
converting the acquired beats into sales capacity judgment standards, wherein when the up-take amount of the auction company exceeds 50% of the same period, the auction company meets the judgment standards of the capacity of converting the acquired beats into sales;
the average price judgment standard, when the average price of the auction company exceeds the same period of 50%, the auction company meets the average price judgment standard;
and when the auction company meets the judgment standard of successful sales capacity and the past 5 years have a record of accomplishment and the past 6 auction seasons have a record of continuous auction, the auction company meets the judgment standard of successful sales capacity and the continuous collection work.
4. The method of claim 3, wherein the valuation module builds a linear model based on the transaction price rp, the size m, the subject f, and the auction company level a of the similar works:
ln(P)＝α+β 1 ln rp+β 2 ln m+β 3 ln f+β 4 ln a (1)；
wherein P is a dependent variable, alpha, beta 1 、β 2 、β 3 、β 4 Is a coefficient to be determined.
5. The method of claim 4, wherein the valuation module determines that the price influencing factors include a similar work trade price rp and a size m; the estimation module sets the influence factors as i respectively 1 、i 2 And a calculation formula (2) is obtained:
in the method, in the process of the invention,trade price average for similar works,/->Is the average size number, alpha is the coefficient to be determined; the second estimated trading value is P=EXP [ ln (P)]+F OI SAL1；
Second auction valuation interval P r The calculation formula of (2) is as follows: p (P) r ＝P±σ+F OI Δsal1, where σ is the float value calculated at 90% confidence level, σ= (1-90%) P, F OI SAL1 is the first estimated auction price, and ΔSAL1 is the first auction price range, as an impact factor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110318403.0A CN113240446B (en) | 2021-03-25 | 2021-03-25 | Data classification and processing method of artwork estimation system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110318403.0A CN113240446B (en) | 2021-03-25 | 2021-03-25 | Data classification and processing method of artwork estimation system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113240446A CN113240446A (en) | 2021-08-10 |
| CN113240446B true CN113240446B (en) | 2023-09-29 |
Family
ID=77130488
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110318403.0A Active CN113240446B (en) | 2021-03-25 | 2021-03-25 | Data classification and processing method of artwork estimation system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113240446B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105631486A (en) * | 2014-10-27 | 2016-06-01 | 深圳Tcl数字技术有限公司 | image character recognition method and device |
| CN108334906A (en) * | 2018-02-08 | 2018-07-27 | 杭州华选信息科技有限公司 | A kind of finance pawns the guaranty automatic identification appraisal procedure and device of service |
| CN108647987A (en) * | 2018-04-03 | 2018-10-12 | 云南网星大数据科技股份有限公司 | House valuation of assets method |
| CN109766898A (en) * | 2018-12-26 | 2019-05-17 | 平安科技（深圳）有限公司 | Image character recognition method, device, computer equipment and storage medium |
-
2021
- 2021-03-25 CN CN202110318403.0A patent/CN113240446B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105631486A (en) * | 2014-10-27 | 2016-06-01 | 深圳Tcl数字技术有限公司 | image character recognition method and device |
| CN108334906A (en) * | 2018-02-08 | 2018-07-27 | 杭州华选信息科技有限公司 | A kind of finance pawns the guaranty automatic identification appraisal procedure and device of service |
| CN108647987A (en) * | 2018-04-03 | 2018-10-12 | 云南网星大数据科技股份有限公司 | House valuation of assets method |
| CN109766898A (en) * | 2018-12-26 | 2019-05-17 | 平安科技（深圳）有限公司 | Image character recognition method, device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113240446A (en) | 2021-08-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105760957B (en) | A kind of Forecasting Methodology of the soft customer revenue of security | |
| Dascal et al. | An analysis of EU wine trade: A gravity model approach | |
| Spathis et al. | Detecting falsified financial statements: a comparative study using multicriteria analysis and multivariate statistical techniques | |
| US6141648A (en) | Method for estimating the price per square foot value of real property | |
| US6834266B2 (en) | Methods for estimating the seasonality of groups of similar items of commerce data sets based on historical sales data values and associated error information | |
| KR20010103784A (en) | Valuation prediction models in situations with missing inputs | |
| US20070299683A1 (en) | Method of Repeatedly Securitizing Intellectual Property Assets and Facilitating Investments Therein | |
| KR100746107B1 (en) | Cross correlation tool for automated portfolio descriptive statistics | |
| KR20010102452A (en) | Methods and systems for finding value and reducing risk | |
| WO2004061714A1 (en) | Technique evaluating device, technique evaluating program, and technique evaluating method | |
| KR20030004316A (en) | Methods and apparatus for simulating competitive bidding yield | |
| KR20010109302A (en) | Methods and systems for efficiently sampling portfolios for optimal underwriting | |
| KR20010108282A (en) | Methods and systems for optimizing return and present value | |
| Weissova et al. | Rating as a useful tool for credit risk measurement | |
| Trujillo | Patterns in a complex system: an empirical study of valuation in business bankruptcy cases | |
| CN115409364A (en) | Data security risk assessment method based on data analysis | |
| CN111105311A (en) | Dynamic credit rating method and device for bond body | |
| CN107133862A (en) | Dynamic produces the method and system of the detailed transaction payment experience of enhancing credit evaluation | |
| US6289321B1 (en) | Device to detect stock names having the highest current value and its methods for use | |
| CN105427171A (en) | Data processing method of Internet lending platform rating | |
| CN113240446B (en) | Data classification and processing method of artwork estimation system | |
| CN113239313B (en) | Image recognition processing method of artwork estimation system | |
| Kolácek et al. | Assessment of scoring models using information value | |
| JP2002358397A (en) | Management method for time series data, information disclosing device and recording means | |
| CN113139830A (en) | Estimation calculation method of artwork estimation system |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |