CN108334906B - Automatic collateral identification and evaluation method and device for financial book service - Google Patents
Automatic collateral identification and evaluation method and device for financial book service Download PDFInfo
- Publication number
- CN108334906B CN108334906B CN201810128431.4A CN201810128431A CN108334906B CN 108334906 B CN108334906 B CN 108334906B CN 201810128431 A CN201810128431 A CN 201810128431A CN 108334906 B CN108334906 B CN 108334906B
- Authority
- CN
- China
- Prior art keywords
- mortgage
- ginseng
- value
- damage
- unit
- 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.)
- Expired - Fee Related
Links
- 238000011156 evaluation Methods 0.000 title claims description 32
- 238000000034 method Methods 0.000 claims abstract description 19
- 235000008434 ginseng Nutrition 0.000 claims description 46
- 241000208340 Araliaceae Species 0.000 claims description 36
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 36
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 36
- 208000035126 Facies Diseases 0.000 claims description 25
- 238000010606 normalization Methods 0.000 claims description 12
- 240000004371 Panax ginseng Species 0.000 claims description 10
- 235000002789 Panax ginseng Nutrition 0.000 claims description 10
- 238000001514 detection method Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 239000000463 material Substances 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 description 10
- 239000010985 leather Substances 0.000 description 6
- 238000011161 development Methods 0.000 description 5
- 238000000605 extraction Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 241001093575 Alma Species 0.000 description 2
- 230000004075 alteration Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000007635 classification algorithm Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000003708 edge detection Methods 0.000 description 2
- 238000012854 evaluation process Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000010422 painting Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- 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
- 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
Abstract
The invention discloses a method and a device for automatically identifying and evaluating book mortgage, which comprise the following steps: obtaining an original image of the mortgage; identifying and determining damage of the mortgage in the original image of the mortgage; searching for item phase values, transaction dates and transaction prices of m reference mortgages which are the same as the mortgage objects in class and are closest to the items; an estimate V of the collateral is calculated. The invention adopts a mode of automatic machine valuation to replace manual valuation, and has the advantages of objective and fair valuation, unified standard, real-time performance and high efficiency.
Description
Technical Field
The invention relates to the field of article identification and evaluation, in particular to a method and a device for automatically identifying and evaluating a book mortgage.
Background
The book-awarding industry has a great significance as a long-history industry in the economic development history of China, develops from the earliest folk loan mode to the present and relates to various economic fields, and mortgages are expanded from folk goods (such as famous watches, famous bags, jewelry, cameras, fur, calligraphy and painting, antiques and the like) to automobiles, house products, securities, business rights, equities and the like. The book becomes an important way for individuals to develop financing in emergency and small and medium enterprises, and solves the urgent need of many enterprises and individuals. With the continuous development of information technology, the continuance industry has realized the informatization management of links such as daily approval, collection, redemption, continuance, absolute and the like, which greatly reduces the waste of labor resources and improves the management efficiency of the continuance company.
However, in the civil classics, at the most critical justice stage, the traditional method is mainly adopted, namely, the classicisors are mainly used for manually identifying and evaluating the mortgage. The manual mode has the following disadvantages: firstly, the quality of the classics is uneven, and excellent classics are rare; secondly, the manual mode has strong subjectivity, and unified and standard standardized mortgage identification and evaluation cannot be realized; thirdly, the more intense the current counterfeiting behavior, the more false the counterfeiting technology can be, and even the highly experienced classicism can avoid the misjudgment; finally, manual methods are inefficient and do not meet the growing demand of the increasingly strong classic industry.
The mortgage identification and evaluation is a basic guarantee for the health development of the mortgage industry, so that the mortgage industry needs an objective and impartial, unified-standard, real-time and efficient mortgage identification and evaluation technology to assist or even replace a manual mode, and the development of the mortgage industry is greatly promoted.
Disclosure of Invention
The invention provides a method and a device for automatically identifying and evaluating a classic mortgage, which adopt a mode of automatically evaluating a value by a machine instead of manually evaluating the value and have the advantages of objective and fair evaluation, unified standard, real-time performance and high efficiency.
The invention relates to an automatic identification and evaluation method for a pawn mortgage, which is characterized by comprising the following steps:
step 10, shooting images of the mortgage to obtain original images of the mortgage;
step 20, identifying and damage-fixing the mortgage in the original mortgage image, wherein the step 20 specifically comprises the following steps:
step 201, normalizing the original images of the mortgages to obtain standard images of the mortgages;
step 202, identifying the mortgage in the standard mortgage image to obtain a mortgage image;
step 203, respectively matching the mortgage images with articles in a preset article library to determine the articles of the mortgage;
step 204, carrying out damage detection on the mortgage image, and determining the facies value S of the mortgageBook (I)；
Step 30, searching item phase values, transaction dates and transaction prices of m reference mortgages which have the same item class as the mortgages and are closest to the item phase in a preset reference valuation library according to the item class and the item phase value of the mortgages; the preset reference valuation library stores the types, the item phase values, the transaction dates and the transaction prices of the already-delivered mortgage materials, wherein m is an integer larger than or equal to 0, if m is larger than 0, the step 40 is carried out, and if m is equal to 0, the step 50 is carried out;
step 40, calculating an estimated value V of the mortgage by using a formula (I); wherein S isGinseng 1，SGinseng 2，……，SGinseng radix (radix Ginseng, rhizoma Dioscoreae, radix Ginseng, rhizoma Dioscoreae, etc.)Is the facies value, T, of the m reference mortgagesGinseng 1，TGinseng 2，……，TGinseng radix (radix Ginseng, rhizoma Dioscoreae, radix Ginseng, rhizoma Dioscoreae, etc.)Is the time difference, V, between the date of the deal and the current date of the m reference mortgagesGinseng 1，VGinseng 2，……，VGinseng radix (radix Ginseng, rhizoma Dioscoreae, radix Ginseng, rhizoma Dioscoreae, etc.)Is the bargaining price of the m reference mortgages, i is an integer which is more than or equal to 1 and less than or equal to m, and alpha is a weight factor;
step 50, judging whether the mortgage is a consumable product or not according to the type of the mortgage, if so, entering step 501, and if not, entering step 502;
step 501, inquiring the current selling price V of the article type of the mortgage articleSaleInquiring the sold time T of the mortgageSaleAnd service life TLongevityDetermining the value S of the mortgageBook (I)Calculating the estimated value V of the collated object by using a formula (II) according to the corresponding item phase factor eta, wherein beta is the residual value of the item type of the collated object;
step 502, inquiring the current selling price V of the type of the mortgage objectSaleDetermining the value S of the mortgageBook (I)And (3) calculating the estimated value V of the mortgage by using a formula (III) according to the corresponding facies factor eta.
V＝VSale(1-ηSBook (I)) (formula three)
Preferably, step 204 is to perform damage detection on the mortgage image and determine the facies value S of the mortgageBook (I)The method specifically comprises the following steps:
step 2041, detecting a damage area in the mortgage image, and determining the position, size and damage type of the damage area;
step 2042, according to the type of the mortgage, searching a reference position damage rating value S which is the same as the mortgage in type and has the same or the closest damage area position in a preset reference damage rating libraryReference positionSearching for a reference size damage assessment value S which is the same as the mortgage in type and has the same or the closest damage area sizeGinseng sizeAnd searching for a reference type damage rating value S which is the same as the collateral article and has the same damage type or is closest to the damage typeGinseng (Panax ginseng C.A.)；
Step 2043, calculating the value S of the mortgage object by formula (IV)Book (I)；
SBook (I)＝aSReference position+bSGinseng size+cSGinseng (Panax ginseng C.A.)(formula four)
Wherein a, b and c are loss coefficients respectively, and a + b + c is 1.
Preferably, the category includes a variety, and the category further includes at least one of a brand, a series, and a model.
Preferably, the phase factor η is predetermined, and one phase factor η corresponds to one phase value range.
The invention relates to an automatic identification and evaluation device for a classic mortgage, which is characterized by comprising an image capturing unit, an identification and damage assessment unit, a searching unit, a first evaluation unit, a consumable judgment unit, a second evaluation unit and a third evaluation unit, wherein:
the image capturing unit is used for shooting images of the mortgage to obtain original images of the mortgage;
the identification loss assessment unit is used for identifying and assessing loss of the mortgage in the original mortgage image, and comprises a normalization unit, an identification unit, a category determination unit and a facies determination unit, wherein:
the normalization unit is used for performing normalization processing on the original images of the mortgages to obtain standard images of the mortgages;
the identification unit is used for identifying the mortgage in the mortgage standard image to obtain a mortgage image;
the category determining unit is used for respectively matching the mortgage object image with articles in a preset category library and determining the category of the mortgage object; and
a facies determining unit for detecting damage of the mortgage image and determining the facies value S of the mortgageBook (I)；
The searching unit is used for searching the item phase value, the closing date and the closing price of m reference mortgages which have the same item class as the mortgages and are closest to the item phase in a preset reference valuation library according to the item class and the item phase value of the mortgages; the preset reference valuation library stores the types, the item phase values, the transaction dates and the transaction prices of the already-delivered mortgage materials, and m is an integer greater than or equal to 0;
a first estimation unit for calculating an estimation value V of the mortgage by using a formula (one) when m is larger than 0; wherein S isGinseng 1，SGinseng 2，……，SGinseng radix (radix Ginseng, rhizoma Dioscoreae, radix Ginseng, rhizoma Dioscoreae, etc.)Is the facies value, T, of the m reference mortgagesGinseng 1，TGinseng 2，……，TGinseng radix (radix Ginseng, rhizoma Dioscoreae, radix Ginseng, rhizoma Dioscoreae, etc.)Is the time difference, V, between the date of the deal and the current date of the m reference mortgagesGinseng 1，VGinseng 2，……，VGinseng radix (radix Ginseng, rhizoma Dioscoreae, radix Ginseng, rhizoma Dioscoreae, etc.)Is the bargaining price of the m reference mortgages, i is an integer which is more than or equal to 1 and less than or equal to m, and alpha is a weight factor;
a consumable judgment unit, configured to judge whether the mortgage is a consumable according to the category of the mortgage when m is 0;
a second valuation unit for inquiring the current selling price V of the article class of the collated object when m is equal to 0 and the collated object is a consumable articleSaleInquiring the sold time T of the mortgageSaleAnd service life TLongevityDetermining the value S of the mortgageBook (I)Calculating the estimated value V of the collated object by using a formula (II) according to the corresponding item phase factor eta, wherein beta is the residual value of the item type of the collated object;
a third valuation unit for inquiring the current selling price V of the article class of the collated object when m is equal to 0 and the collated object is not a consumable articleSaleDetermining the value S of the mortgageBook (I)And (3) calculating the estimated value V of the mortgage by using a formula (III) according to the corresponding facies factor eta.
V＝VSale(1-ηSBook (I)) (formula three)
Preferably, the phase determining unit specifically includes:
the damage detection unit is used for detecting a damaged area in the mortgage image and determining the position, the size and the damage type of the damaged area;
a damage value searching unit, configured to search, according to the category of the mortgage, a reference position damage value S that is the same as or closest to the category of the mortgage and has the same damage area position in a preset reference damage libraryReference positionSearching for a reference size damage assessment value S which is the same as the mortgage in type and has the same or the closest damage area sizeGinseng sizeAnd searching for a reference type damage rating value S which is the same as the collateral article and has the same damage type or is closest to the damage typeGinseng (Panax ginseng C.A.)；
A quality value calculating unit for calculating the quality value S of the mortgage object by using a formula (IV)Book (I)；
SBook (I)＝aSReference position+bSGinseng size+cSGinseng (Panax ginseng C.A.)(formula four)
Wherein a, b and c are loss coefficients respectively, and a + b + c is 1.
Preferably, the category includes a variety, and the category further includes at least one of a brand, a series, and a model.
Preferably, the phase factor η is predetermined, and one phase factor η corresponds to one phase value range.
The computer-readable storage medium of the present invention stores computer-executable instructions that cause a computer to perform any of the methods described above.
Compared with the prior art, the method and the device for automatically identifying and evaluating the book mortgage, provided by the invention, have the advantages that firstly, the manual valuation mode is replaced by the automatic valuation of the machine, so that the problems in the prior art are solved, the technical blank is filled, and the development of the book mortgage industry is greatly promoted; secondly, the phase value of the mortgage is accurately detected through an image processing technology and is accurately calculated through stored big data, and the accuracy and the precision of the mortgage are far superior to those of a manual estimation mode; finally, the estimation of the collateral object in the invention is obtained by adopting big data accurate calculation on the basis of fully considering the product phase and the natural loss, and the accuracy and precision of the estimation also far exceed the manual estimation mode.
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, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a flow chart of a method for automatic identification and evaluation of a book mortgage according to the present invention;
FIG. 2 is a block diagram of an automatic identification and evaluation device for mortgage according to the present invention.
Detailed Description
Example one
FIG. 1 is a flow chart of the automatic identification and evaluation method of the book mortgage of the present invention, as shown in FIG. 1, the method includes the following steps:
and step 10, shooting the images of the mortgage to obtain the original images of the mortgage. High-definition images of the mortgage can be shot by adopting the high-definition camera so as to obtain better image quality.
And 20, identifying and determining loss of the mortgage in the original mortgage image.
Wherein the step 20 specifically comprises the following steps:
step 201, performing normalization processing on the original images of the mortgages to obtain standard images of the mortgages.
And (3) carrying out normalization processing on the original images of the mortgages, such as color, size, brightness and the like by adopting an image processing technology so as to obtain standard images of the mortgages. The standard images of the mortgages can be enhanced, so that the mortgages can be accurately identified and the accuracy of damage assessment on the damage is improved.
Step 202, identifying the mortgage in the standard mortgage image to obtain a mortgage image.
An edge detection technique may be employed to obtain a mortgage image.
And step 203, respectively matching the mortgage object image with the objects in a preset object class library, and determining the object class of the mortgage object.
The category of the mortgage can be determined by respectively matching the image of the mortgage with the items in a preset category library by adopting an image recognition technology, such as an image feature matching algorithm based on an SIFT operator, an image feature matching algorithm based on an SURF operator, an image classification algorithm based on a convolutional neural network, an image matching algorithm based on global and local feature fusion, an image matching algorithm based on texture features and a neural network, and the like.
The category includes items such as leather bags, fur, jewelry, watches, cameras, etc., and at least one of brand, serial, and model, such as SPEEDY, NEVERFULL, ARTSY, NOE, ALMA serial under LV (LOUIS vision) brand, such as model M40156 of LV, etc., identified by image recognition technology.
The preset item library includes images of items of various items and all models of items of respective series of respective brands of one item. For example, the preset product library includes full-series full-model images of various brands.
Step 204, carrying out damage detection on the mortgage image, and determining the facies value S of the mortgageBook (I). The method specifically comprises the following steps:
step 2041, detecting a damage area in the mortgage image, and determining the position, size and damage type of the damage area.
The parameters of the damaged area of the mortgage image, such as the position, size and damage type of the damaged area, including a damaged area, a surface defect area, a surface scratch area, a stain area, etc., can be extracted by using algorithms such as closed edge extraction, gradient extraction, etc.
Step 2042, according to the type of the mortgage, searching a reference position damage rating value S which is the same as the mortgage in type and has the same or the closest damage area position in a preset reference damage rating libraryReference positionSearching for a reference size damage assessment value S which is the same as the mortgage in type and has the same or the closest damage area sizeGinseng sizeAnd searching for a reference type damage rating value S which is the same as the collateral article and has the same damage type or is closest to the damage typeGinseng (Panax ginseng C.A.)。
Taking the surface scratch of the leather bag as an example, reference pictures and reference damage values of different scratch degrees of leather bags of various brands, various types and various models are stored in a preset reference damage library and are used as damage templates of different grades of scratches. And comparing the position and the size of the damage area identified by the current collateral with the reference picture of the damage assessment template, and referring to the reference damage assessment value in which reference template when the similarity of the position and the size of the damage area identified by the current collateral is highest with which reference template. For example, for a surface scratch of a series of LV bags of a certain model, according to parameters such as the position and the size of the surface scratch, a reference position damage value S which is the same as or closest to the position of the scratch of the same type of LV bag is searched from a preset reference damage libraryReference positionAnd searching for the reference size damage of the same LV bag, which is the same as or closest to the scratch in sizeValue SGinseng sizeAnd finding a reference type damage rating S for the same LV bag for the surface scratchGinseng (Panax ginseng C.A.)。
Step 2043, calculating the value S of the mortgage object by formula (IV)Book (I)；
SBook (I)＝aSReference position+bSGinseng size+cSGinseng (Panax ginseng C.A.)(formula four)
Wherein a, b and c are loss coefficients respectively, and a + b + c is 1.
In general, the type of damage, the damage position, and the damage size have different weights for determining the damage assessment value, and different values of a, b, and c may be set according to different categories empirically. In addition, the phase value SBook (I)Can be expressed in percent, and the product phase value SBook (I)The larger the damage of the collateral, the worse the phase.
Step 30, searching item phase values, transaction dates and transaction prices of m reference mortgages which have the same item class as the mortgages and are closest to the item phase in a preset reference valuation library according to the item class and the item phase value of the mortgages; the preset reference valuation library stores the types, the item phase values, the transaction dates and the transaction prices of the already-delivered mortgage materials, wherein m is an integer larger than or equal to 0, if m is larger than 0, the step 40 is carried out, and if m is equal to 0, the step 50 is carried out;
if the pre-set reference valuation library stores the referred transaction prices, the valuation method can be generally implemented in step 40 by referring to the transaction prices of already committed mortgages with the same product class and similar products, and if the referenceable transaction prices are not stored, the valuation of the mortgages needs to be accurately calculated, and the calculation method is implemented in step 50.
Step 40, calculating an estimated value V of the mortgage by using a formula (I); wherein S isGinseng 1，SGinseng 2，……，SGinseng radix (radix Ginseng, rhizoma Dioscoreae, radix Ginseng, rhizoma Dioscoreae, etc.)Is the facies value, T, of the m reference mortgagesGinseng 1，TGinseng 2，……，TGinseng radix (radix Ginseng, rhizoma Dioscoreae, radix Ginseng, rhizoma Dioscoreae, etc.)Is the day of the deal of the m reference mortgagesTime difference between date and current date, VGinseng 1，VGinseng 2，……，VGinseng radix (radix Ginseng, rhizoma Dioscoreae, radix Ginseng, rhizoma Dioscoreae, etc.)Is the bargaining price of the m reference mortgages, i is an integer which is more than or equal to 1 and less than or equal to m, and alpha is a weight factor;
under the condition of the same phase value, the transaction price of the reference mortgage with smaller time difference can accurately estimate the estimated value of the mortgage, under the condition of the same time difference, the transaction price of the reference mortgage with closer phase value can accurately estimate the estimated value of the mortgage, the phase value and the time difference have different influences on the estimated value of the mortgage, and the phase value and the time difference are comprehensively considered. Alpha is a weighting factor, alpha values of different categories are different, and the alpha values can be set according to experience.
Step 50, judging whether the mortgage is a consumable product or not according to the type of the mortgage, if so, entering step 501, and if not, entering step 502;
for the situation that the evaluation value of the mortgage is required to be accurately calculated without a referenceable transaction price, firstly, whether the type of the mortgage is a consumable or not needs to be judged, if the mortgage is a consumable, such as a purse, fur, a camera, a watch and the like, in addition to the value loss caused by damage, the natural loss caused by the limited service life needs to be considered, and if the mortgage is a non-consumable, such as antique, the value loss caused by the damage needs to be considered generally.
Step 501, inquiring the current selling price V of the article type of the mortgage articleSaleInquiring the sold time T of the mortgageSaleAnd service life TLongevityDetermining the value S of the mortgageBook (I)Calculating the estimated value V of the collated object by using a formula (II) according to the corresponding item phase factor eta, wherein beta is the residual value of the item type of the collated object;
if the collateral is still sold, the current selling price of the collateral can be inquired, if the collateral is sold, the selling price of the collateral at the time of sale can be inquired as the current selling price, and the sold time of the collateral can be inquired, wherein the selling time can be counted by year, month or day. For consumables, the life of the collateral also needs to be queried. By passing
Calculating the natural breakage rate of the collateral object by eta SBook (I)Calculating the damage rate, eta S, of the collateral due to damageBook (I)Should be less than or equal to 1. The phase factor eta is preset, and for one class, one phase factor eta corresponds to one phase value range. For example, for a purse, when 0 ≦ SBook (I)When the concentration is less than or equal to 5 percent, eta can be set to be 0.8, when
When η is 1, when
In the process, eta can be set to be 1, and the like, so that a higher estimated value can be ensured when the damage is smaller, and the estimated value is rapidly reduced when the damage is larger, thereby accurately simulating a real manual evaluation process. Beta is the residual value of the type of the collateral, and beta is obtained according to experience.
Step 502, inquiring the current selling price V of the type of the mortgage objectSaleDetermining the value S of the mortgageBook (I)And (3) calculating the estimated value V of the mortgage by using a formula (III) according to the corresponding facies factor eta.
V＝VSale(1-ηSBook (I)) (formula three)
As described above, the non-consumable product generally only needs to consider the value loss due to the damage.
In the invention, a preset product class library, a preset reference damage assessment library and a preset reference evaluation library all store a large amount of data. After the estimates V of the mortgage are obtained in the above manner, the estimates V of the mortgage are stored in a preset reference estimate database to expand the preset reference estimate database. In addition, the preset product class library and the preset reference damage assessment library can be continuously updated and supplemented.
Example two
As shown in fig. 2, the present invention further provides an automatic identification and evaluation device for book mortgages, which is characterized in that the device comprises:
and the image capturing unit is used for shooting the images of the mortgages and obtaining the original images of the mortgages. The image capturing unit can adopt a high-definition camera, so that a high-definition image of the mortgage can be shot to obtain better image quality.
An identifying and damage-fixing unit, configured to identify and fix damage to the mortgage in the original mortgage image, where the identifying and damage-fixing unit includes:
and the normalization unit is used for performing normalization processing on the original images of the mortgages to obtain the standard images of the mortgages. The normalization unit performs normalization processing on the original images of the mortgages by adopting an image processing technology, such as color, size, brightness and the like, so as to obtain standard images of the mortgages. The standard images of the mortgages can be enhanced, so that the mortgages can be accurately identified and the accuracy of damage assessment on the damage is improved.
And the identification unit is used for identifying the mortgage in the mortgage standard image to obtain a mortgage image. The recognition unit may use an edge detection technique to obtain the mortgage image.
And the category determining unit is used for respectively matching the mortgage object image with the articles in a preset category library and determining the categories of the mortgage objects. The category of the mortgage can be determined by respectively matching the image of the mortgage with the items in a preset category library by adopting an image recognition technology, such as an image feature matching algorithm based on an SIFT operator, an image feature matching algorithm based on an SURF operator, an image classification algorithm based on a convolutional neural network, an image matching algorithm based on global and local feature fusion, an image matching algorithm based on texture features and a neural network, and the like. The category includes items such as leather bags, fur, jewelry, watches, cameras, etc., and at least one of brand, serial, and model, such as SPEEDY, NEVERFULL, ARTSY, NOE, ALMA serial under LV (LOUIS vision) brand, such as model M40156 of LV, etc., identified by image recognition technology. The preset item library includes images of items of various items and all models of items of respective series of respective brands of one item. For example, the preset product library includes full-series full-model images of various brands.
A facies determining unit for detecting damage of the mortgage image and determining the facies value S of the mortgageBook (I). The quality phase determining unit comprises a damage detecting unit, a loss assessment value searching unit and a quality phase value calculating unit, wherein:
and the damage detection unit is used for detecting a damaged area in the mortgage image and determining the position, the size and the damage type of the damaged area. The damage detection unit may extract parameters of a damaged area of the collateral image, such as a position, a size, and a damage type of the damaged area, using algorithms such as closed edge extraction and gradient extraction, where the damaged area includes a damaged area, a surface defect area, a surface scratch area, a dirt area, and the like.
A damage value searching unit, configured to search, according to the category of the mortgage, a reference position damage value S that is the same as or closest to the category of the mortgage and has the same damage area position in a preset reference damage libraryReference positionSearching for a reference size damage assessment value S which is the same as the mortgage in type and has the same or the closest damage area sizeGinseng sizeAnd searching for a reference type damage rating value S which is the same as the collateral article and has the same damage type or is closest to the damage typeGinseng (Panax ginseng C.A.). Taking a leather handbag with a scratched surface as an example, the preset reference damage assessment library is storedReference pictures and reference damage values of different scratch degrees of the leather bags of various brands and various models are stored and used as damage assessment templates of scratches of different grades. And comparing the position and the size of the damage area identified by the current collateral with the reference picture of the damage assessment template, and referring to the reference damage assessment value in which reference template when the similarity of the position and the size of the damage area identified by the current collateral is highest with which reference template. For example, for a surface scratch of a series of LV bags of a certain model, according to parameters such as the position and the size of the surface scratch, a reference position damage value S which is the same as or closest to the position of the scratch of the same type of LV bag is searched from a preset reference damage libraryReference positionAnd searching a reference size damage assessment value S which is the same as or closest to the size of the scratch and is of the same LV bagGinseng sizeAnd finding a reference type damage rating S for the same LV bag for the surface scratchGinseng (Panax ginseng C.A.)。
A quality value calculating unit for calculating the quality value S of the mortgage object by using a formula (IV)Book (I)；
SBook (I)＝aSReference position+bSGinseng size+cSGinseng (Panax ginseng C.A.)(formula four)
Wherein a, b and c are loss coefficients respectively, and a + b + c is 1. In general, the type of damage, the damage position, and the damage size have different weights for determining the damage assessment value, and different values of a, b, and c may be set according to different categories empirically. In addition, the phase value SBook (I)Can be expressed in percent, and the product phase value SBook (I)The larger the damage of the collateral, the worse the phase.
The searching unit is used for searching the item phase value, the closing date and the closing price of m reference mortgages which have the same item class as the mortgages and are closest to the item phase in a preset reference valuation library according to the item class and the item phase value of the mortgages; the preset reference valuation library stores the types, the item phase values, the transaction dates and the transaction prices of the already-delivered mortgage materials, and m is an integer greater than or equal to 0. If the reference valuation library which is preset stores the referred transaction prices, the valuation can be generally carried out by referring to the transaction prices of the already committed mortgages with the same product class and similar products, the valuation method is realized in a first valuation unit, if the reference transaction prices are not stored, the valuation of the mortgages needs to be accurately calculated, and the calculation method is realized in a second valuation unit or a third valuation unit.
A first estimation unit for calculating an estimation value V of the mortgage by using a formula (one) when m is larger than 0; wherein S isGinseng 1，SGinseng 2，……，SGinseng radix (radix Ginseng, rhizoma Dioscoreae, radix Ginseng, rhizoma Dioscoreae, etc.)Is the facies value, T, of the m reference mortgagesGinseng 1，TGinseng 2，……，TGinseng radix (radix Ginseng, rhizoma Dioscoreae, radix Ginseng, rhizoma Dioscoreae, etc.)Is the time difference, V, between the date of the deal and the current date of the m reference mortgagesGinseng 1，VGinseng 2，……，VGinseng radix (radix Ginseng, rhizoma Dioscoreae, radix Ginseng, rhizoma Dioscoreae, etc.)Is the bargaining price of the m reference mortgages, i is an integer which is more than or equal to 1 and less than or equal to m, and alpha is a weight factor;
under the condition of the same phase value, the transaction price of the reference mortgage with smaller time difference can accurately estimate the estimated value of the mortgage, under the condition of the same time difference, the transaction price of the reference mortgage with closer phase value can accurately estimate the estimated value of the mortgage, the phase value and the time difference have different influences on the estimated value of the mortgage, and the phase value and the time difference are comprehensively considered. Alpha is a weighting factor, alpha values of different categories are different, and the alpha values can be set according to experience.
And the consumable judgment unit is used for judging whether the mortgage is a consumable or not according to the category of the mortgage when m is 0. For the situation that the evaluation value of the mortgage is required to be accurately calculated without a referenceable transaction price, firstly, whether the type of the mortgage is a consumable or not needs to be judged, if the mortgage is a consumable, such as a purse, fur, a camera, a watch and the like, in addition to the value loss caused by damage, the natural loss caused by the limited service life needs to be considered, and if the mortgage is a non-consumable, such as antique, the value loss caused by the damage needs to be considered generally.
A second valuation unit for inquiring the current selling price V of the article class of the collated object when m is equal to 0 and the collated object is a consumable articleSaleInquiring the sold time T of the mortgageSaleAnd service life TLongevityDetermining the value S of the mortgageBook (I)Calculating the estimated value V of the collated object by using a formula (II) according to the corresponding item phase factor eta, wherein beta is the residual value of the item type of the collated object;
if the collateral is still sold, the current selling price of the collateral can be inquired, if the collateral is sold, the selling price of the collateral at the time of sale can be inquired as the current selling price, and the sold time of the collateral can be inquired, wherein the selling time can be counted by year, month or day. For consumables, the life of the collateral also needs to be queried. By passing
Calculating the natural breakage rate of the collateral object by eta SBook (I)Calculating the damage rate, eta S, of the collateral due to damageBook (I)Should be less than or equal to 1. The phase factor eta is preset, and for one class, one phase factor eta corresponds to one phase value range. For example, for a purse, when 0 ≦ SBook (I)When the concentration is less than or equal to 5 percent, eta can be set to be 0.8, when
When η is 1, when
When the damage is small, the higher estimation value can be ensured, and when the damage is large, the estimation value is quickAnd the real manual evaluation process can be accurately simulated. Beta is the residual value of the type of the collateral, and beta is obtained according to experience.
A third valuation unit for inquiring the current selling price V of the article class of the collated object when m is equal to 0 and the collated object is not a consumable articleSaleDetermining the value S of the mortgageBook (I)And (3) calculating the estimated value V of the mortgage by using a formula (III) according to the corresponding facies factor eta.
V＝VSale(1-ηSBook (I)) (formula three)
As described above, the non-consumable product generally only needs to consider the value loss due to the damage.
In the invention, a preset product class library, a preset reference damage assessment library and a preset reference evaluation library all store a large amount of data. After the estimates V of the mortgage are obtained in the above manner, the estimates V of the mortgage are stored in a preset reference estimate database to expand the preset reference estimate database. In addition, the preset product class library and the preset reference damage assessment library can be continuously updated and supplemented.
Furthermore, the present invention also provides a computer-readable storage medium storing computer-executable instructions, which cause a computer to execute the method according to the present invention.
It should be understood that the above-mentioned embodiments are merely preferred examples of the present invention, and not restrictive, but rather, all the changes, substitutions, alterations and modifications that come within the spirit and scope of the invention as described above may be made by those skilled in the art, and all the changes, substitutions, alterations and modifications that fall within the scope of the appended claims should be construed as being included in the present invention.
Claims (9)
1. An automatic identification and evaluation method for a book mortgage, which is characterized by comprising the following steps:
step 10, shooting images of the mortgage to obtain original images of the mortgage;
step 20, identifying and damage-fixing the mortgage in the original mortgage image, wherein the step 20 specifically comprises the following steps:
step 201, normalizing the original images of the mortgages to obtain standard images of the mortgages;
step 202, identifying the mortgage in the standard mortgage image to obtain a mortgage image;
step 203, respectively matching the mortgage images with articles in a preset article library to determine the articles of the mortgage;
step 204, carrying out damage detection on the mortgage image, and determining the facies value S of the mortgageBook (I)；
Step 30, searching item phase values, transaction dates and transaction prices of m reference mortgages which have the same item class as the mortgages and are closest to the item phase in a preset reference valuation library according to the item class and the item phase value of the mortgages; the preset reference valuation library stores the types, the item phase values, the transaction dates and the transaction prices of the already-delivered mortgage materials, wherein m is an integer larger than or equal to 0, if m is larger than 0, the step 40 is carried out, and if m is equal to 0, the step 50 is carried out;
step 40, calculating an estimated value V of the mortgage by using a formula (I); wherein S isGinseng 1，SGinseng 2，……，SGinseng radix (radix Ginseng, rhizoma Dioscoreae, radix Ginseng, rhizoma Dioscoreae, etc.)Is the facies value, T, of the m reference mortgagesGinseng 1，TGinseng 2，……，TGinseng radix (radix Ginseng, rhizoma Dioscoreae, radix Ginseng, rhizoma Dioscoreae, etc.)Is the time difference, V, between the date of the deal and the current date of the m reference mortgagesGinseng 1，VGinseng 2，……，VGinseng radix (radix Ginseng, rhizoma Dioscoreae, radix Ginseng, rhizoma Dioscoreae, etc.)Is the bargaining price of the m reference mortgages, i is an integer which is more than or equal to 1 and less than or equal to m, and alpha is a weight factor;
step 50, judging whether the mortgage is a consumable product or not according to the type of the mortgage, if so, entering step 501, and if not, entering step 502;
step 501, inquiring the current selling price V of the article type of the mortgage articleSaleInquiring the sold time T of the mortgageSaleAnd service life TLongevityDetermining the value S of the mortgageBook (I)Calculating the estimated value V of the collated object by using a formula (II) according to the corresponding item phase factor eta, wherein beta is the residual value of the item type of the collated object;
step 502, inquiring the current selling price V of the type of the mortgage objectSaleDetermining the value S of the mortgageBook (I)Calculating the estimated value V of the mortgage by using a formula (III) according to the corresponding facies factor eta
V＝VSale(1-ηSBook (I)) (formula three).
2. The automatic pawn mortgage identification and evaluation method according to claim 1, wherein: step 204, carrying out damage detection on the mortgage image, and determining the facies value S of the mortgageBook (I)The method specifically comprises the following steps:
step 2041, detecting a damage area in the mortgage image, and determining the position, size and damage type of the damage area;
step 2042, according to the type of the mortgage, searching a reference position damage rating value S which is the same as the mortgage in type and has the same or the closest damage area position in a preset reference damage rating libraryReference positionSearching for a reference size damage assessment value S which is the same as the mortgage in type and has the same or the closest damage area sizeGinseng sizeAnd searching for a reference type damage rating value S which is the same as the collateral article and has the same damage type or is closest to the damage typeGinseng (Panax ginseng C.A.)；
Step 2043, calculating the value S of the mortgage object by formula (IV)Book (I)；
SBook (I)＝aSReference position+bSGinseng size+cSGinseng (Panax ginseng C.A.)(formula four)
Wherein a, b and c are loss coefficients respectively, and a + b + c is 1.
3. The automatic pawn mortgage identification and evaluation method according to claim 1, wherein: the categories comprise varieties and at least one of brands, series and models.
4. The automatic pawn mortgage identification and evaluation method according to claim 1, wherein: the phase factor eta is preset, and one phase factor eta corresponds to one phase value range.
5. An automatic identification and evaluation device for classical mortgage, which is characterized by comprising an image capturing unit, an identification and damage assessment unit, a searching unit, a first evaluation unit, a consumable judgment unit, a second evaluation unit and a third evaluation unit, wherein:
the image capturing unit is used for shooting images of the mortgage to obtain original images of the mortgage;
the identification loss assessment unit is used for identifying and assessing loss of the mortgage in the original mortgage image, and comprises a normalization unit, an identification unit, a category determination unit and a facies determination unit, wherein:
the normalization unit is used for performing normalization processing on the original images of the mortgages to obtain standard images of the mortgages;
the identification unit is used for identifying the mortgage in the mortgage standard image to obtain a mortgage image;
the category determining unit is used for respectively matching the mortgage object image with articles in a preset category library and determining the category of the mortgage object; and
a facies determining unit for detecting damage of the mortgage image and determining the facies value S of the mortgageBook (I)；
The searching unit is used for searching the item phase value, the closing date and the closing price of m reference mortgages which have the same item class as the mortgages and are closest to the item phase in a preset reference valuation library according to the item class and the item phase value of the mortgages; the preset reference valuation library stores the types, the item phase values, the transaction dates and the transaction prices of the already-delivered mortgage materials, and m is an integer greater than or equal to 0;
a first estimation unit for calculating an estimation value V of the mortgage by using a formula (one) when m is larger than 0; wherein S isGinseng 1，SGinseng 2，……，SGinseng radix (radix Ginseng, rhizoma Dioscoreae, radix Ginseng, rhizoma Dioscoreae, etc.)Is the facies value, T, of the m reference mortgagesGinseng 1，TGinseng 2，……，TGinseng radix (radix Ginseng, rhizoma Dioscoreae, radix Ginseng, rhizoma Dioscoreae, etc.)Is the time difference, V, between the date of the deal and the current date of the m reference mortgagesGinseng 1，VGinseng 2，……，VGinseng radix (radix Ginseng, rhizoma Dioscoreae, radix Ginseng, rhizoma Dioscoreae, etc.)Is the bargaining price of the m reference mortgages, i is an integer which is more than or equal to 1 and less than or equal to m, and alpha is a weight factor;
a consumable judgment unit, configured to judge whether the mortgage is a consumable according to the category of the mortgage when m is 0;
a second valuation unit for inquiring the current selling price V of the article class of the collated object when m is equal to 0 and the collated object is a consumable articleSaleInquiring the sold time T of the mortgageSaleAnd service life TLongevityDetermining the value S of the mortgageBook (I)Calculating the estimated value V of the collated object by using a formula (II) according to the corresponding item phase factor eta, wherein beta is the residual value of the item type of the collated object;
a third evaluation unit for evaluating the value of the first,when m is equal to 0 and the mortgage is not a consumable, inquiring the current selling price V of the article class where the mortgage is locatedSaleDetermining the value S of the mortgageBook (I)Calculating the estimated value V of the mortgage by using a formula (III) according to the corresponding facies factor eta
V＝VSale(1-ηSBook (I)) (formula three).
6. The automatic identification and evaluation device of pawn mortgage as claimed in claim 5, wherein the quality determination unit comprises:
the damage detection unit is used for detecting a damaged area in the mortgage image and determining the position, the size and the damage type of the damaged area;
a damage value searching unit, configured to search, according to the category of the mortgage, a reference position damage value S that is the same as or closest to the category of the mortgage and has the same damage area position in a preset reference damage libraryReference positionSearching for a reference size damage assessment value S which is the same as the mortgage in type and has the same or the closest damage area sizeGinseng sizeAnd searching for a reference type damage rating value S which is the same as the collateral article and has the same damage type or is closest to the damage typeGinseng (Panax ginseng C.A.)；
A quality value calculating unit for calculating the quality value S of the mortgage object by using a formula (IV)Book (I)；
SBook (I)＝aSReference position+bSGinseng size+cSGinseng (Panax ginseng C.A.)(formula four)
Wherein a, b and c are loss coefficients respectively, and a + b + c is 1.
7. The automatic collateral mortgage identification and evaluation device of claim 5, wherein: the categories comprise varieties and at least one of brands, series and models.
8. The automatic collateral mortgage identification and evaluation device of claim 5, wherein: the phase factor eta is preset, and one phase factor eta corresponds to one phase value range.
9. A computer-readable storage medium storing computer-executable instructions for causing a computer to perform the method of any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810128431.4A CN108334906B (en) | 2018-02-08 | 2018-02-08 | Automatic collateral identification and evaluation method and device for financial book service |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810128431.4A CN108334906B (en) | 2018-02-08 | 2018-02-08 | Automatic collateral identification and evaluation method and device for financial book service |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108334906A CN108334906A (en) | 2018-07-27 |
| CN108334906B true CN108334906B (en) | 2021-02-23 |
Family
ID=62928354
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810128431.4A Expired - Fee Related CN108334906B (en) | 2018-02-08 | 2018-02-08 | Automatic collateral identification and evaluation method and device for financial book service |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108334906B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110263201B (en) * | 2019-06-25 | 2022-03-11 | 吴昶炜 | Electronic product category identification and defect identification method and application thereof |
| CN113537256A (en) * | 2020-03-29 | 2021-10-22 | 袁艳荣 | Big data identification system for residual value analysis |
| CN112365441B (en) * | 2020-10-12 | 2022-06-14 | 深圳市对庄科技有限公司 | Information processing method and device for jadeite evaluation |
| CN112348670A (en) * | 2020-11-09 | 2021-02-09 | 上海欧冶金融信息服务股份有限公司 | System and method for interchanging and sharing of mortgage and credit for financial products |
| CN112381589A (en) * | 2020-12-04 | 2021-02-19 | 南京浪脆电子商务有限公司 | Intelligent commodity evaluation management system of commodity transaction platform based on cloud computing |
| CN113239313B (en) * | 2021-03-24 | 2023-05-23 | 深圳市雅昌艺术网股份有限公司 | Image recognition processing method of artwork estimation system |
| CN113239323B (en) * | 2021-03-24 | 2023-01-17 | 深圳市雅昌艺术网股份有限公司 | Artwork valuation system and valuation method based on transaction data |
| CN113240446B (en) * | 2021-03-25 | 2023-09-29 | 深圳市雅昌艺术网股份有限公司 | Data classification and processing method of artwork estimation system |
| CN113139830A (en) * | 2021-03-25 | 2021-07-20 | 深圳市雅昌艺术网股份有限公司 | Estimation calculation method of artwork estimation system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105512680A (en) * | 2015-12-02 | 2016-04-20 | 北京航空航天大学 | Multi-view SAR image target recognition method based on depth neural network |
| CN106447434A (en) * | 2016-09-14 | 2017-02-22 | 全联征信有限公司 | Personal credit ecological platform |
| CN106600422A (en) * | 2016-11-24 | 2017-04-26 | 中国平安财产保险股份有限公司 | Car insurance intelligent loss assessment method and system |
| CN106803205A (en) * | 2016-12-27 | 2017-06-06 | 北京量子保科技有限公司 | A kind of system and method for insuring from kinetonucleus compensation |
| CN107358596A (en) * | 2017-04-11 | 2017-11-17 | 阿里巴巴集团控股有限公司 | A kind of car damage identification method based on image, device, electronic equipment and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002183504A (en) * | 2000-06-27 | 2002-06-28 | Tadashi Goino | Auction method, auction system and server |
-
2018
- 2018-02-08 CN CN201810128431.4A patent/CN108334906B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105512680A (en) * | 2015-12-02 | 2016-04-20 | 北京航空航天大学 | Multi-view SAR image target recognition method based on depth neural network |
| CN106447434A (en) * | 2016-09-14 | 2017-02-22 | 全联征信有限公司 | Personal credit ecological platform |
| CN106600422A (en) * | 2016-11-24 | 2017-04-26 | 中国平安财产保险股份有限公司 | Car insurance intelligent loss assessment method and system |
| CN106803205A (en) * | 2016-12-27 | 2017-06-06 | 北京量子保科技有限公司 | A kind of system and method for insuring from kinetonucleus compensation |
| CN107358596A (en) * | 2017-04-11 | 2017-11-17 | 阿里巴巴集团控股有限公司 | A kind of car damage identification method based on image, device, electronic equipment and system |
Non-Patent Citations (1)
| Title |
|---|
| A Method for Evaluating Residential Value Based on Value Engineering Theory;Yang Dong ET AL;《2009 International Conference on Information Management, Innovation Management and Industrial Engineering》;20091227;第1-5页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108334906A (en) | 2018-07-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108334906B (en) | Automatic collateral identification and evaluation method and device for financial book service | |
| US20240087102A1 (en) | Automatic Image Based Object Damage Assessment | |
| KR101678970B1 (en) | Method for appraising item | |
| US10467662B2 (en) | Apparatus for appraising article | |
| US10373262B1 (en) | Image processing system for vehicle damage | |
| US20210042797A1 (en) | Autonomous Article Grading | |
| US10380696B1 (en) | Image processing system for vehicle damage | |
| CN110263821B (en) | Training of transaction feature generation model, and method and device for generating transaction features | |
| AU2018101523A4 (en) | A personal credit scoring model based on machine learning method | |
| CN106776897A (en) | A kind of user's portrait label determines method and device | |
| CN108985285B (en) | Commodity patent acquisition method and system based on machine identification | |
| Choudhury et al. | A machine learning approach to identify potential customer based on purchase behavior | |
| CN113506173A (en) | Credit risk assessment method and related equipment thereof | |
| Al Imran et al. | Predicting the return of orders in the e-tail industry accompanying with model interpretation | |
| Aisen et al. | Credit contraction and international trade: evidence from chilean exporters | |
| CN106127606B (en) | Method and device for processing oil and gas index data in exploration and development project | |
| Agarwal et al. | A comparative study of supervised machine learning algorithms for fruit prediction | |
| Priya et al. | A graph theoretical approach for identifying fraudulent transactions in circular trading | |
| Velmurugan et al. | Supply chain financial risk management using business intelligence | |
| CN115187387B (en) | Identification method and equipment for risk merchant | |
| Aravapalli | An automatic inspection approach for remanufacturing components using object detection | |
| Afrinanda et al. | Comparison of Machine Learning Algorithm Models in Bitcoin Price Sentiment Analysis | |
| CN113282886B (en) | Bank loan default judgment method based on logistic regression | |
| Hasugian | Testing the C45 Algorithm with Rapid Miner for Stock Selection (Case Study: Toko Usaha Muda) | |
| Singhal et al. | Digispectra: Techno-Archaeo Toolkit |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20190423 Address after: Room B8406-03, 4th floor, 818 Huayuan Road, Xiangcheng District, Suzhou City, Jiangsu Province Applicant after: SUZHOU QIXIAN INTELLIGENT TECHNOLOGY Co.,Ltd. Address before: 310051 Room 125, Building No. 88, Jiangling Road, Xixing Street, Binjiang District, Hangzhou City, Zhejiang Province Applicant before: HANGZHOU HUAXUAN INFORMATION TECHNOLOGY Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210129 Address after: 100089 209-089, 2nd floor, building 6, yard 1, shangdishi street, Haidian District, Beijing Applicant after: Beijing XINCHE Technology Co.,Ltd. Address before: Room b8406-03, 4th floor, 818 Huayuan Road, Xiangcheng District, Suzhou City, Jiangsu Province Applicant before: SUZHOU QIXIAN INTELLIGENT TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210223 |