CN112950335A - Online trading platform for photo building sample pictures based on big data - Google Patents
Online trading platform for photo building sample pictures based on big data Download PDFInfo
- Publication number
- CN112950335A CN112950335A CN202110394184.4A CN202110394184A CN112950335A CN 112950335 A CN112950335 A CN 112950335A CN 202110394184 A CN202110394184 A CN 202110394184A CN 112950335 A CN112950335 A CN 112950335A
- Authority
- CN
- China
- Prior art keywords
- sample
- photo
- type
- buyer
- module
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0621—Item configuration or customization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0641—Shopping interfaces
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an online transaction platform based on big data, in particular to an online transaction platform based on big data for photo buildings, which comprises a buyer module, a seller module, an intention type pushing module, an intention sample selection module and a sample disassembling and matching module, wherein the buyer module and the seller module are used for registering and registering the information of a buyer and a seller; the intention type pushing module pushes intention type samples according to the relevant operation of the buyer on the platform, and divides the big data photo building samples for one time, so that the selection range is reduced, and the efficiency is improved; the sample piece disassembling and matching module is used for matching the intention sample piece selected by the buyer with the form requirement, the difficulty degree of posture, the information of the buyer and the professional degree of a photographer subordinate to the seller to obtain a matching degree result, and the buyer and the seller can make a decision on whether to trade.
Description
Technical Field
The invention relates to the technical field of online trading platforms, in particular to a movie building sample film online trading platform based on big data.
Background
The phenomenon exists in the current trading process of the photo building sample, namely, a client is required to select a photo by visiting the gate, the client is not required to select the photo on line, the phenomenon is that the style is different due to the difference of style types, compositions, designs and clothes props of the photo building sample, the photo building party can only provide a scheme for the photo building sample according to some brief and abstract descriptions of the client, a model in the sample provided by the photo building terminal for the photo building sample often has superior physical conditions, professional postures and expressive force after professional training, and the photography techniques of photographers in the photo building are also different; at this time, the following two phenomena occur: one is as follows: the type scheme provided by the studio and the type desired by the customer in advance can be selected in a short time because of wrong understanding in communication, and the studio can not avoid the situation again if all matching schemes are sent to the customer for selection, which leads to the reduction of the operation efficiency of the studio and the longer time of the customer, and the second problem is that: the final effect graph of the studio is different from the effect supposed by the buyer, namely, the effect of the client is far from that of the sample, so that the phenomenon that the evaluation of the studio is reduced after the emotion of the buyer is dissatisfied is caused, the buyer experiences poor purchasing experience, and the seller suffers credit loss.
Based on the above problems, it is urgently needed to provide a movie building sample online transaction platform based on big data, which intelligently defines region types according to browsing operations of buyers in the platform through an intention type pushing module and a sample disassembling and matching module, so that the time for the buyers to screen the intention types is reduced, the time loss caused by errors in communication understanding between two parties is reduced, and the efficiency of the two parties is improved; according to the sample piece disassembling and matching module, the sample piece is disassembled, meanwhile, the self demand and the self condition of the buyer are intelligently matched with the intention sample piece, the final customer effect is pre-judged in advance, the buyer makes a transaction decision based on the pre-judged result, the phenomenon that the buyer is unsatisfied is reduced, the number of times of cooperation of both parties is increased, and meanwhile the operation efficiency and the credit value of the studio party are increased.
Disclosure of Invention
The invention aims to provide a large data-based online trading platform for photo building samples, which aims to solve the problems in the background art.
In order to solve the technical problems, the invention provides the following technical scheme:
a movie building sample online transaction platform based on big data comprises a buyer module, a seller module, an intention type pushing module, an intention sample selecting module and a sample disassembling and matching module; the buyer module and the seller module are used for inputting the information of the buyer and the seller to be stored into the platform for registration; the intention type pushing module is used for screening intention type plates of buyers for the photo building sample plates with big data; the intention sample selecting module is used for buyer to select intention in the gallery after the type plate screening of the big data photo building sample; and the sample disassembling and matching module is used for performing final matching on the buyer and the seller. After the buyers register and register respective information input platforms, the intention type pushing module pushes intention types to the buyers, the intention type photo floor samples are sent to the intention sample selecting module, the buyers select final intention samples in the intention sample selecting module, the intention sample selecting module sends the intention samples finally selected by the buyers to the sample disassembling and matching module for final sample disassembling and matching, and the sample disassembling and matching module feeds back the final matching degree value of the intention samples to the buyers and the sellers as a reference for the two parties to determine whether to cooperate or not.
Further, the specific working process of the intention type pushing module comprises the following steps: collecting browsing time mark T of certain type of photo building sampleoiThe number of times of clicking a certain type of photo building sample is marked as MoiAnd the click times of the photo building samples of a certain type are marked as KoiAccording to the formula:
wherein y is1、y2、y3、y4、x1、x2、x3、x4Is a correlation coefficient, HoiThe buyer attention value is expressed as the type of the first oi type of the photo building samples, oi is {1,2,3 … }, and the intelligent pushing module pushes H of different types of photo building samplesoiFeeding values back to the platform end and the seller end; h is to beoiThe first three values are labeled as strong attention values VoiThe oi-1, 2,3 platform end and the seller end push related types of photo-building samples to the buyer according to the strong attention value of the buyer, and the buyer performs intention selection; h of photo building sample pictures of different types is pushed by intention type pushing moduleoiThe value is fed back to the platform end and the seller end, and the process is beneficial to finding potential interest and hobbies of the buyerThe demands can be more accurately positioned, and the respective operating efficiency of both buyers and sellers is improved.
The method for collecting the browsing time of a certain type of photo building sample pictures comprises the following specific working processes: the method comprises the steps of presetting a period of acquisition time, classifying the types of samples browsed in the period of time to obtain the average browsing time of the samples of different typesmi is the type of the mi type of the photo studio swatch, and mi is {1,2,3 … };respectively representing the average browsing time of the buyer to the first type, the second type and the third type of photo building samples; when the browsing time of a certain type of photo building sample exceeds the average browsing time of the type of photo building sample, recording the browsing abnormal situation of the type of photo building sample as the browsing abnormal situation of the type of photo building sample, storing the browsing abnormal time of the photo building sample and marking the abnormal times of the photo building sample, when the abnormal times exceed a preset value, averaging and storing the abnormal browsing time of the type of photo building sample, and covering the average browsing time of the original type of photo building sample by the average value of the stored browsing abnormal time of the certain type of photo building sample; when the times of abnormal browsing time does not reach a preset value, discarding the data; the collecting process is beneficial to eliminating the situation that a buyer stays in a sample page in the browsing process but does not actually look up the sample in an interest mode, and the obtained related browsing time is more targeted, so that the intelligent pushing result is more accurate.
The method for collecting the click amplification times of a certain type of photo building sample comprises the following specific processes: includes collecting times of conventional amplification marked as d, times of amplification exceeding common amplification dhAccording to the formula:
M=d×BI+dh×BH
m represents the number of clicks on a type of photo floor swatch by a buyer, where BI、BHTo presetA percentage value of BI<BH(ii) a The acquisition process can enable the acquired click amplification times to be more closely related to the interest degree of the buyer in the type of sample.
The method for collecting the click times of a certain type of photo building sample pictures comprises the following specific working processes: collecting the times of clicking a certain type of photo building sample at a time, marking as i, reversing to repeatedly click the type of photo building sample, marking as f, and collecting the times of the type of photo building sample n; setting a weight A for the times of clicking a certain type of photo building sample once, setting a weight B for the times of repeatedly clicking the type of photo building sample backwards and setting a weight C for the times of collecting the type of photo building sample, according to the formula:
k is expressed as the number of clicks of a buyer on a certain type of photo floor swatch, and A is<B<C, the collection process enables the final buyer to pay attention to the value HoiAnd more accurate.
Further, the specific working process of the sample wafer disassembling and matching module comprises: when the platform locks the intention sample of the buyer, the sample is analyzed in a disassembling proportion, and the data obtained by the main analysis has a shape requirement proportion coefficient g of the sample model1Fraction g of difficulty of sample posture2And the corresponding difficulty degree demand score S, storing the data in a sample disassembling and matching module, simultaneously extracting the height, weight, shoulder width, three-dimensional and other sizes provided when the buyer side registers information, performing score judgment with an intention sample in the module according to a preset certain shape difference standard to obtain a buyer shape matching score Q, obtaining the professional value E of a photographer according to the transfer rate, the good rate and the order taking rate of previous sample works of the information of the subordinate photographers which can be provided by each photo building party, and performing fitting and matching to obtain the final matching degree R according to a formula:
R=Q×g1+S+E
and transmitting the data to the buyer and the seller as a reference basis for whether the buyer and the seller select the transaction.
Figure requirement proportion coefficient g of sample model1The specific process of obtaining comprises: disassembling the piece on the sampleAdding image processing software into the matching module, extracting square pixels of regions with different attributes in the sample, and determining figure shape requirement proportion coefficient g by the proportion of figures1。
Ratio coefficient g of sample posture difficulty2The specific process of confirmation of (2) includes: the method comprises the steps of pre-storing and importing a human body conventional action image in the module, extracting people in a sample when an intention sample is locked, comparing the people with the pre-stored image to coincide, calculating the cosine similarity of an included angle of a limb part which does not coincide according to a rectangular coordinate system of an area part, respectively making a limb of the conventional action and a limb of the intention sample as a triangle side a and a triangle side b, wherein the included angle between the two sides is theta, forming a triangle, and according to a formula:
cosθ=(a^2+b^2+c^2)/(2*a*b)
the cosine value cos theta of the included angle is used as a difficulty degree confirmation standard of the sample posture, when cos theta is greater than 0, the more similar the description is, namely the difficulty is smaller, when cos theta is less than 0, the more dissimilar the description is, namely the difficulty is larger, the value of cos theta is used as an interval distribution, a score judgment standard is given to the value of cos theta, a score S is obtained according to the confirmation of the difficulty degree, the matching process is favorable for realizing an intelligent matching process, the final guest effect is pre-judged in advance, and a buyer is allowed to make a transaction decision based on a pre-judgment result.
Compared with the prior art, the invention has the following beneficial effects: according to the method, the area types are intelligently defined according to the browsing operation of the buyer in the platform through the intention type pushing module, the time for the buyer to screen the intention types is reduced, the time loss caused by errors in communication understanding of the two parties is reduced, the intelligent pushing is more accurate and efficient, and the efficiency of the two parties is improved; according to the sample piece disassembling and matching module, the sample piece is disassembled, meanwhile, the demands and the conditions of the buyer are intelligently matched with the intention sample piece, the final customer effect is pre-judged in advance, the buyer can make a transaction decision based on the pre-judged result, the phenomenon that the buyer is dissatisfied is reduced, the satisfaction degrees of both sides of the buyer and the seller are improved, and the operation efficiency and the credit value of the studio are improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a system diagram of a big data-based photo studio dailies online transaction platform of the present invention;
FIG. 2 is a diagram of steps of a method for collecting browsing time of a certain type of photo building samples in an online trading platform for photo building samples based on big data according to the present invention;
FIG. 3 is a diagram of the steps of the method for collecting the number of times of click amplification of a certain type of photo building samples in the big data based photo building sample online transaction platform according to the present invention;
FIG. 4 is a diagram of the method steps for collecting the number of clicks of a certain type of photo building swatch in the big data based photo building swatch online transaction platform according to the present invention;
FIG. 5 is a concrete work flow of a sample disassembling and matching module of the online trading platform for photo building samples based on big data according to the present invention;
FIG. 6 is a figure-shape requirement proportion coefficient g of a model collected in a sample of an online trading platform for photo building samples based on big data1A diagram of method steps of;
FIG. 7 is a proportion coefficient g of the sample posture difficulty of the big data-based online trading platform for photo building samples2And their scores;
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-7, the present invention provides the following technical solutions:
a movie building sample online transaction platform based on big data comprises a buyer module, a seller module, an intention type pushing module, an intention sample selection module and a sample disassembling and matching module, wherein the buyer module and the seller module are used for inputting information of a buyer and a seller to be stored into the platform for registration; the intention type pushing module is used for screening intention type plates of buyers for the photo building sample plates with big data; the intention sample selecting module is used for buyer to select intention in the gallery after the type plate screening of the big data photo building sample; the sample disassembling and matching module is used for carrying out final matching on the buyer and the seller. After the buyers register and register the respective information input platforms, the intention type pushing module pushes intention types to the buyers, the intention type photo-building samples are sent to the intention sample selecting module, the buyers select final intention samples in the intention sample selecting module, the intention sample selecting module sends the intention samples finally selected by the buyers to the sample disassembling and matching module for final sample disassembling and matching, and the sample disassembling and matching module feeds back the final matching degree value to the buyers and the sellers as a reference for the two parties to determine whether to cooperate or not.
The specific working process of the intention type pushing module is as follows:
collecting browsing time mark T of certain type of photo building sampleoi;
The number of times of click amplification for collecting a certain type of photo studio samples is marked as Moi;
The click times for collecting the photo building sample is marked as Koi;
According to the formula:
obtaining buyer attention value H for certain type of photo building sampleoi;
H of photo building sample pictures of different types is pushed by intention type pushing moduleoiFeeding values back to the platform end and the seller end; the process is beneficial to discovering the potential interests and hobbies of the buyers, can more accurately position the hobbies and requirements of the buyers, and improves the respective operating efficiency of the buyers and the sellers.
The method for acquiring the browsing time of the photo building sample pictures of a certain type comprises the following specific processes:
presetting a period of acquisition time, and classifying the types of the samples browsed in the period of time;
obtaining average browsing time of different types of samplesmi is the type of the mi type of the photo studio, mi is {1,2,3 … },representing an average viewing time for a first type of photo floor swatch;
when the browsing time of a certain type of photo studio prints exceeds the average browsing time of the type of photo studio prints, namely abnormal browsing time W>Average browsing time TmiRecording the abnormal browsing condition of the photo building sample, storing the abnormal browsing time and marking the abnormal times;
when the abnormal times exceed 5 times, the average value of the abnormal browsing time W of the type of photo building sample is marked as PmiAnd storing, namely, covering the average browsing time of the original type of photo building sample by the stored average value of the browsing abnormal time of the type of photo building sample, namely Tmi=Pmi;
When the frequency of the abnormal browsing time does not reach 5 times, discarding the previously stored abnormal browsing time W; the collecting process is beneficial to eliminating the situation that a buyer stays in a sample page in the browsing process but does not actually look up the sample in an interest mode, and the obtained related browsing time is more targeted, so that the intelligent pushing result is more accurate.
The specific process of the method for collecting the click amplification times of a certain type of photo studio prints is as follows:
collecting the times of conventional amplification and marking as d;
number of times d that the acquisition magnification exceeds the normal magnificationh;
According to the formula:
M=d×BI+dh×BH
obtaining the click amplification times of a certain type of photo building sample, wherein BI、BHIs a preset percentage value and satisfies BI<BH(ii) a The acquisition process can enable the acquired click amplification times to be more closely related to the interest degree of the buyer in the type of sample.
The specific working process of the method for collecting the sample click times of a certain type of photo studio samples is as follows:
collecting the times of clicking a certain type of photo building sample film at a time and marking as i;
collecting the times of repeatedly clicking the type of photo building sample film in a reverse mode and marking as f;
the times of collecting the photo building sample pictures of the type are marked as n;
setting a weight A for the times of clicking a certain type of photo building sample once, setting a weight B for the times of repeatedly clicking the photo building sample backwards, setting a weight C for the times of collecting the photo building sample of the type, wherein A < B < C,
according to the formula:
K=A×i+B×f+C×n
obtaining the sample click times K of a certain type of photo building sample; this collection process enables the final buyer's attention value HoiAnd more accurate.
The specific working process of the sample disassembling and matching module is as follows:
the buyer selects an intention sample in the intention sample selection module;
the sample piece disassembling matching module carries out a disassembling proportion analysis on the sample piece, and the data obtained by the main analysis has a body shape requirement proportion coefficient g of the sample piece model1Fraction g of difficulty of sample posture2The corresponding gesture difficulty degree demand score S is stored in a sample wafer disassembling and matching module;
extracting all sizes of height, weight, shoulder width, three-dimension and the like provided when the buyer side registration information is extracted, and performing score evaluation with the intention sample in the module according to a certain shape difference standard set in advance to obtain a buyer shape matching score Q;
obtaining the professional degree value E of the photographers according to the reprinting rate, the good appraisal rate and the order acceptance rate of the original sample works of the information of subordinate photographers which can be provided by each video building, carrying out fitting matching to obtain the final matching degree R according to a formula:
R=Q×g1+S+E
and transmitting the data value R to the buyer and the seller, and using the data value R as a reference for whether the buyer and the seller select the transaction according to the height of the data value R.
Figure requirement proportion coefficient g of sample model1The specific process of obtaining is as follows:
the sample disassembling and matching module comprises image processing software and is used for extracting square pixels of areas with different attributes in the sample;
determining figure shape requirement proportion coefficient g by the proportion of figure in the sample picture1。
Ratio coefficient g of sample posture difficulty2The specific process of (2) is as follows:
pre-storing and importing a human body conventional action image in a sample disassembling and matching module;
when the intention sample sheet is locked, the characters in the sample sheet are extracted and compared with the pre-stored image to be superposed, a rectangular coordinate system of the limb part which is not superposed at the region part is established to carry out the calculation of the cosine similarity of the included angle, and the limb of the conventional action and the limb of the intention sample sheet are respectively taken as the sides of the triangleAnd edgeThe included angle between the two is theta to form a triangle;
according to the formula:
obtaining a cosine value cos theta of an included angle, wherein the value range of the cosine value cos theta is [ -1,1], the cosine value cos theta is used as a difficulty level confirmation standard of the sample posture, when cos theta is greater than 0, the more similar description is, namely the difficulty level is smaller, and when cos theta is less than 0, the more dissimilar description is, namely the difficulty level is larger;
taking the value range [ -1,1] of cos theta as an equal-difference interval distribution, and giving a score evaluation standard to each interval, for example, assigning the interval [ -1, -0.5] with a score 60, assigning the interval [ -0.5,0] with a score 70, and so on, and obtaining a corresponding assigned score S according to the interval where the cos theta is located.
Compared with the prior art, the invention has the following beneficial effects: according to the method, the area types are intelligently defined according to the browsing operation of the buyer in the platform through the intention type pushing module, the time for the buyer to screen the intention types is reduced, the time loss caused by errors in communication understanding of the two parties is reduced, the intelligent pushing is more accurate and efficient, and the efficiency of the two parties is improved; according to the sample piece disassembling and matching module, the sample piece is disassembled, meanwhile, the demands and the conditions of the buyer are intelligently matched with the intention sample piece, the final customer effect is pre-judged in advance, the buyer can make a transaction decision based on the pre-judged result, the phenomenon that the buyer is dissatisfied is reduced, the satisfaction degrees of both sides of the buyer and the seller are improved, and the operation efficiency and the credit value of the studio are improved.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. The utility model provides a building sample piece online transaction platform based on big data which characterized in that: the system comprises a buyer module, a seller module, an intention type pushing module, an intention sample selecting module and a sample disassembling and matching module:
the buyer module is used for inputting personal information of a buyer for registering, registering and sending to the platform for storage;
the seller module is used for inputting relevant information of a seller, registering and registering the information of the past works of subordinate photographers including a movie building, and sending the information to the platform for storage;
the intention type pushing module is used for screening intention type plates of buyers for the photo building sample pieces with big data;
the intention sample selecting module is used for buyer to select intention in the gallery after the big data photo building sample is subjected to type plate screening;
and the sample disassembling and matching module is used for performing final matching on the buyer and the seller.
2. The big-data-based on-line trading platform for photo building samples according to claim 1, wherein: the specific working process of the intention type pushing module comprises the following steps: collecting browsing time mark T of certain type of photo building sampleoiThe number of times of clicking a certain type of photo building sample is marked as MoiAnd the click times of the photo building samples of a certain type are marked as KoiAccording to the formula:
wherein y is1、y2、y3、y4、x1、x2、x3、x4Is a correlation coefficient, HoiThe buyer attention value is expressed as the type of the first type of the photo building samples, wherein oi is {1,2,3 … }, and the intelligent pushing module pushes H of different types of photo building samplesoiFeeding values back to the platform end and the seller end; h is to beoiThe first three values are labeled as strong attention values VoiAnd the oi & lt1, 2,3 & gt platform end and the seller end push related type photo and building samples to the buyer according to the strong attention value of the buyer, and the buyer performs intention selection.
3. The big-data-based on-line trading platform for photo building samples according to claim 2, wherein: the method for collecting the browsing time of the photo building sample pictures of a certain type comprises the following specific working processes: the method comprises the steps of presetting a period of acquisition time, classifying the types of samples browsed in the period of time to obtain the average browsing time of the samples of different typesmi is the type of the mi type of the photo studio swatch, and mi is {1,2,3 … };respectively representing the average browsing time of the buyer to the first type, the second type and the third type of photo building samples; when the browsing time of a certain type of photo building sample exceeds the average browsing time of the type of photo building sample, recording the browsing abnormal situation of the type of photo building sample as the browsing abnormal situation of the type of photo building sample, storing the browsing abnormal time of the photo building sample and marking the abnormal times of the photo building sample, when the abnormal times exceed a preset value, averaging and storing the abnormal browsing time of the type of photo building sample, and covering the average browsing time of the original type of photo building sample by the average value of the stored browsing abnormal time of the certain type of photo building sample; when abnormal browsing time occursAnd when the number does not reach the preset value, discarding the data.
4. The big-data-based on-line trading platform for photo building samples according to claim 2, wherein: the method for collecting the click amplification times of a certain type of photo building sample pictures comprises the following specific processes: includes collecting times of conventional amplification marked as d, times of amplification exceeding common amplification dhAccording to the formula:
M=d×BI+dh×BH
m represents the number of clicks on a type of photo floor swatch by a buyer, where BI、BHIs a preset percentage value and satisfies BI<BH。
5. The big-data-based on-line trading platform for photo building samples according to claim 2, wherein: the method for collecting the click times of the photo building samples of a certain type comprises the following specific working processes: collecting the times of clicking a certain type of photo building sample at a time, marking as i, reversing to repeatedly click the type of photo building sample, marking as f, and collecting the times of the type of photo building sample n; setting a weight A for the times of clicking a certain type of photo building sample once, setting a weight B for the times of repeatedly clicking the type of photo building sample backwards and setting a weight C for the times of collecting the type of photo building sample, according to the formula:
K=A×i+B×f+C×n
k is expressed as the number of clicks of the buyer on a certain type of photo floor swatch, and A < B < C.
6. The big-data-based on-line trading platform for photo building samples according to claim 1, wherein: matching module is disassembled to the sample, its concrete working process: includes locking the buyer's intention sample on the platform, carrying out a disassembly proportion analysis on the sample, and obtaining the data with the figure requirement proportion coefficient g of the sample model1Fraction g of difficulty of sample posture2And corresponding difficultiesThe method comprises the following steps of firstly storing data with an easy degree demand score S in a sample disassembling and matching module, simultaneously extracting various sizes of height, weight, shoulder width, three dimensions and the like provided when information is registered at a buyer end, carrying out score judgment on the data and an intention sample in the module according to a certain shape difference standard set in advance to obtain a buyer shape matching score Q, obtaining a professional degree value E of a photographer according to the transfer rate, the good rate and the order receiving rate of previous sample works of the information of subordinate photographers which can be provided by each studio side, and carrying out fitting matching to obtain a final matching degree R according to a formula:
R=Q×g1+S+E
and transmitting the data to the buyer and the seller as a reference basis for whether the buyer and the seller select the transaction.
7. The big-data-based photo building sample film online transaction platform according to claim 6, wherein: the figure requirement proportion coefficient g of the sample model1The specific process of obtaining comprises: adding image processing software into the sample disassembling and matching module, extracting square pixels of areas with different attributes in the sample, and determining the figure shape requirement proportion coefficient g by the proportion of figures1。
8. The big-data-based photo building sample film online transaction platform according to claim 6, wherein: the proportion coefficient g of the sample posture difficulty degree2The specific process of (1) is as follows: the method comprises the steps of pre-storing and importing a human body conventional action image in a module, extracting people in a sample when an intention sample is locked, comparing the people with the pre-stored image to coincide the people, calculating the cosine similarity of an included angle of a limb part which does not coincide according to a rectangular coordinate system of an area part, respectively making a limb of the conventional action and a limb of the intention sample into a side a and a side b of a triangle, wherein the included angle between the two sides is theta, forming the triangle, and according to a formula:
cosθ=(a^2+b^2+c^2)/(2*a*b)
the cosine value cos theta of the included angle is used as a difficulty level confirmation standard of the sample posture, when cos theta is larger than 0, the more similar the description is, that is, the difficulty level is smaller, when cos theta is smaller than 0, the more dissimilar the description is, that is, the difficulty level is larger, the value of cos theta is used as a section distribution, a score judgment standard is given to the section distribution, and the score S is obtained according to the difficulty level confirmation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110394184.4A CN112950335B (en) | 2021-04-13 | 2021-04-13 | Online trading platform for photo building sample pictures based on big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110394184.4A CN112950335B (en) | 2021-04-13 | 2021-04-13 | Online trading platform for photo building sample pictures based on big data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112950335A true CN112950335A (en) | 2021-06-11 |
CN112950335B CN112950335B (en) | 2023-04-07 |
Family
ID=76232404
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110394184.4A Active CN112950335B (en) | 2021-04-13 | 2021-04-13 | Online trading platform for photo building sample pictures based on big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112950335B (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104517223A (en) * | 2014-12-15 | 2015-04-15 | 小米科技有限责任公司 | Commodity information recommending method and device |
CN105259730A (en) * | 2015-08-27 | 2016-01-20 | 孙健 | U-shaped soft light shadowless studio system |
CN106651536A (en) * | 2016-12-30 | 2017-05-10 | 安徽迅迪网络营销策划有限公司 | Photographer online management system based on wedding photography platform |
CN106779964A (en) * | 2016-12-30 | 2017-05-31 | 安徽迅迪网络营销策划有限公司 | A kind of online wedding photo website user integral management system |
CN107316232A (en) * | 2017-07-07 | 2017-11-03 | 苏州丞相文化科技有限公司 | A kind of photography service website operation system |
CN109040849A (en) * | 2018-07-20 | 2018-12-18 | 广州虎牙信息科技有限公司 | A kind of live streaming platform exchange method, device, equipment and storage medium |
CN109064277A (en) * | 2018-07-25 | 2018-12-21 | 北京小米移动软件有限公司 | merchandise display method and device |
-
2021
- 2021-04-13 CN CN202110394184.4A patent/CN112950335B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104517223A (en) * | 2014-12-15 | 2015-04-15 | 小米科技有限责任公司 | Commodity information recommending method and device |
CN105259730A (en) * | 2015-08-27 | 2016-01-20 | 孙健 | U-shaped soft light shadowless studio system |
CN106651536A (en) * | 2016-12-30 | 2017-05-10 | 安徽迅迪网络营销策划有限公司 | Photographer online management system based on wedding photography platform |
CN106779964A (en) * | 2016-12-30 | 2017-05-31 | 安徽迅迪网络营销策划有限公司 | A kind of online wedding photo website user integral management system |
CN107316232A (en) * | 2017-07-07 | 2017-11-03 | 苏州丞相文化科技有限公司 | A kind of photography service website operation system |
CN109040849A (en) * | 2018-07-20 | 2018-12-18 | 广州虎牙信息科技有限公司 | A kind of live streaming platform exchange method, device, equipment and storage medium |
CN109064277A (en) * | 2018-07-25 | 2018-12-21 | 北京小米移动软件有限公司 | merchandise display method and device |
Also Published As
Publication number | Publication date |
---|---|
CN112950335B (en) | 2023-04-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
AU2014354947B2 (en) | Preferred image retrieval | |
KR101800831B1 (en) | Real Estate Trade Matching and Management System | |
US6958821B1 (en) | Analyzing images to determine third party product materials corresponding to the analyzed images | |
US6785421B1 (en) | Analyzing images to determine if one or more sets of materials correspond to the analyzed images | |
CN102714689B (en) | The method and system of color is determined from image | |
US20040165786A1 (en) | System and method for converting whiteboard content into an electronic document | |
US20050104901A1 (en) | System and method for whiteboard scanning to obtain a high resolution image | |
CN103324759B (en) | A kind of ceramic tile intelligent identification equipment | |
CN103975342A (en) | Systems and methods for mobile image capture and processing | |
TW200829855A (en) | Systems and methods for object dimension estimation | |
CN102016882A (en) | Method, system, and computer program for identification and sharing of digital images with face signatures | |
KR20160016961A (en) | Evaluating image sharpness | |
EP1016038A4 (en) | Method and apparatus for performing global image alignment using any local match measure | |
US20230099352A1 (en) | Apparatus and method of converting digital images to three-dimensional construction images | |
JP2010130695A (en) | Method and system for aligning sequence of images | |
CN101755267A (en) | Compositional balance and color driven content retrieval | |
US20190114795A1 (en) | Reassembling and Repairing Torn Image Pieces | |
JP2019096222A (en) | Image processor, method for processing image, and computer program | |
CN113396424A (en) | System and method for automated material extraction | |
CN112950335B (en) | Online trading platform for photo building sample pictures based on big data | |
JP7451170B2 (en) | Information processing device, information processing method and program | |
Nafchi et al. | Deviation based pooling strategies for full reference image quality assessment | |
JP4738871B2 (en) | Rug manufacturing method and rug providing method | |
US20230230112A1 (en) | Information processing apparatus, operation method of information processing apparatus, operation program of information processing apparatus, and information management system | |
CN109447957A (en) | One kind transmitting matched image duplication based on key point and pastes detection method |
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 |