WO2023279944A1 - 评估矿物价格的方法和计算机*** - Google Patents

评估矿物价格的方法和计算机*** Download PDF

Info

Publication number
WO2023279944A1
WO2023279944A1 PCT/CN2022/099548 CN2022099548W WO2023279944A1 WO 2023279944 A1 WO2023279944 A1 WO 2023279944A1 CN 2022099548 W CN2022099548 W CN 2022099548W WO 2023279944 A1 WO2023279944 A1 WO 2023279944A1
Authority
WO
WIPO (PCT)
Prior art keywords
mineral
assessed
price
parameter
minerals
Prior art date
Application number
PCT/CN2022/099548
Other languages
English (en)
French (fr)
Inventor
徐青松
李青
Original Assignee
杭州睿胜软件有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 杭州睿胜软件有限公司 filed Critical 杭州睿胜软件有限公司
Publication of WO2023279944A1 publication Critical patent/WO2023279944A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q30/00Commerce
    • G06Q30/02Marketing; Price estimation or determination; Fundraising
    • G06Q30/0278Product appraisal
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/08Learning methods
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/06Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063Operations research, analysis or management
    • G06Q10/0639Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393Score-carding, benchmarking or key performance indicator [KPI] analysis
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/06Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063Operations research, analysis or management
    • G06Q10/0639Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06395Quality analysis or management
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/02Agriculture; Fishing; Forestry; Mining

Definitions

  • the present disclosure relates to the field of computer technology, and in particular, to methods and computer systems for evaluating mineral prices.
  • a method for estimating a mineral price comprising: using a first inference model trained on a neural network based on an image of the evaluated mineral to identify quality factors of the evaluated mineral; The maximum size MaxSize of the assessed mineral, and obtain the average estimated price per unit size corresponding to the assessed mineral, except for the influence of quality factors, AverageEvaluatePriceperSize; Calculates the EvaluatePrice for the mineral being evaluated.
  • a method for estimating a mineral price comprising: using an inference model trained based on a neural network to identify quality factors of an evaluated mineral based on an image of the evaluated mineral; obtaining the evaluated The maximum size MaxSize of the mineral, and obtain the price estimation function corresponding to the evaluated mineral; and calculate the evaluation price EvaluatePrice of the evaluated mineral according to the quality factor, the maximum size MaxSize and the price estimation function.
  • a computer system for evaluating mineral prices comprising: one or more processors; and one or more memories configured to store a series of computer-readable instructions for execution and computer-accessible data associated with the series of computer-executable instructions, which, when executed by the one or more processors, cause the The computer system performs any of the methods described above.
  • a non-transitory computer-readable storage medium stores a series of computer-executable instructions, when the series of computer-executable instructions The instructions, when executed by one or more computing devices, cause the one or more computing devices to perform any of the methods described above.
  • FIG. 1 is a flowchart schematically illustrating at least a portion of a method of estimating mineral prices according to some embodiments of the present disclosure.
  • Figure 2 is a flow diagram that schematically illustrates at least a portion of a method of estimating mineral prices according to some embodiments of the present disclosure.
  • FIG. 3 is a block diagram schematically illustrating at least a portion of a computer system for estimating mineral prices according to some embodiments of the present disclosure.
  • FIG. 4 is a block diagram schematically illustrating at least a portion of a computer system for estimating mineral prices according to some embodiments of the present disclosure.
  • FIG. 5 is a diagram schematically illustrating mineral sample data applicable to the method for estimating mineral prices according to some embodiments of the present disclosure.
  • mineral in this article refers to minerals with definite morphology, which may also be called mineral specimens, mineral samples, mineral crystals, etc.
  • the inventors of the present application have found after research that the prices of minerals of different types, sizes, and quality levels vary greatly, so the price of minerals can be evaluated by the following three indicators: the category of minerals (different types of minerals) The valuation basis is different), the maximum size of the mineral (the length, width, and maximum size of the mineral), and the quality factor of the mineral.
  • the inventors have found that minerals with bottom rocks are generally more expensive because they are more beautiful; the price of minerals with crystals of small particles is usually lower than that of minerals with large crystals; Among all possible colors, the price of minerals with higher saturation is usually higher; the more obvious the color contrast between the color of the crystal and the color of the bottom rock, the higher the price; the more uniform the color and the less impurities, the more complete the crystal The more unbroken, the higher the price.
  • quality factors are related to whether the mineral includes bedrock, the ratio of the largest crystal size of the mineral to the largest dimension of the mineral being evaluated, the color saturation of the mineral, the color of the crystals of the mineral, and the tint of the color of the bed rock.
  • Parameters can be set separately for these aspects of the quality factor, and each parameter can have a quantitative value to represent different levels of the corresponding aspect, so as to quantify the quality factor of the mineral, which in turn facilitates the assessment of the mineral price.
  • FIG. 1 is a flow diagram that schematically illustrates at least a portion of a method 100 of estimating mineral prices according to some embodiments of the present disclosure.
  • the method 100 includes: identifying a quality factor of the assessed mineral using a first inference model trained based on a neural network based on an image of the assessed mineral (step 110); obtaining a maximum size MaxSize of the assessed mineral, and obtaining The average evaluation price per unit size (step 120) of the mineral corresponding to the evaluation except the influence of the quality factor; Step 130).
  • Method 100 may be performed by an application that provides functionality for users to evaluate mineral prices.
  • the user can input an image showing the mineral to be evaluated into an application program capable of estimating the price of the mineral to estimate the price of the mineral.
  • the image can be previously stored by the user, captured in real time, or downloaded from the Internet.
  • Imagery may include any form of visual representation, such as still images, moving images, and video. Images can be taken with devices including cameras, such as mobile phones, tablet computers, and the like.
  • An application program capable of executing the method 100 may receive an image from a user, and in step 110 use an inference model trained based on a neural network to identify quality factors of minerals in the image.
  • the parameter Matrix, the parameter MaxCrystalRatio, the parameter HighSatuation, the parameter Contract, and the parameter EvenComplete associated with the quality factor can be set.
  • the parameter Matrix indicates whether the assessed mineral includes the bottom rock
  • the parameter MaxCrystalRatio indicates the ratio of the maximum crystal size of the assessed mineral to the maximum size of the assessed mineral
  • the parameter HighSatuation indicates the color saturation of the assessed mineral
  • the parameter Contract Indicating the color contrast between the color of the crystals of the mineral being evaluated and the color of the underlying rock
  • the parameter EvenComplete indicates the uniform integrity of the crystals of the mineral being evaluated.
  • the quality factor index QualityIndex can also be set to quantify the quality factor, wherein the quality factor index QualityIndex can be a function of the parameters Matrix, MaxCrystalRatio, HighSatuation, Contract and EvenComplete.
  • Quantitative values may be set for the aforementioned parameters associated with quality factors to represent different levels of the corresponding quality aspects.
  • the parameter Matrix may have values of 0 and 1, indicating that the mineral does not include the bottom rock and includes the bottom rock, respectively.
  • the parameter MaxCrystalRatio can have values of -1, 0, 1, respectively indicating that the ratio of the maximum crystal size of the mineral to the maximum size of the mineral is less than 1/9, between 1/9 and 1/3 (endpoints may be included), Greater than 1/3.
  • the parameter HighSatuation can have values of -1, 0, and 1, which respectively indicate that the color saturation level of the mineral is poor, medium, and good.
  • the parameter Contract has values of -1, 0, and 1, respectively indicating that the color contrast levels of the mineral crystal color and the bottom rock color are poor, medium, and good.
  • the parameter EvenComplete has values of -1, 0, and 1, respectively indicating that the level of uniformity and completeness of mineral crystals is poor, medium, and good.
  • the quality factor index QualityIndex and the parameters Matrix, MaxCrystalRatio, HighSatuation, Contract and EvenComplete may have the following relationship of formula 1:
  • QualityIndex 2 (Matrix+MaxCrystalRatio/2+HighSatuation/2+Contract/2+ EvenComplete) .
  • using the speculative model to identify the quality factor of the mineral in the image may be, using the speculative model to identify the parameters Matrix, MaxCrystalRatio, HighSatuation, Contract and EvenComplete of the mineral being evaluated, and then according to the quality factor index QualityIndex and the parameters Matrix, The relationship of MaxCrystalRatio, HighSatuation, Contract and EvenComplete (eg, Equation 1) calculates the quality factor index QualityIndex, thereby determining the quality factor of the assessed mineral.
  • Training data can be obtained to establish a training sample set. You can crawl the pictures of all mineral commodities from major mineral sales websites around the world, and mark the values of the mineral parameters Matrix, MaxCrystalRatio, HighSatuation, Contract and EvenComplete for each picture. The marked pictures are formed as training samples (also referred to as training data) in the training sample set. Then use the training sample set to train the neural network based on deep learning to obtain a multi-dimensional classification model, which can output the values of the parameters Matrix, MaxCrystalRatio, HighSatuation, Contract and EvenComplete of the minerals in the image according to the input image. The output accuracy of the multi-dimensional classification model may also be tested by using the test sample set until the training is completed when the output accuracy meets the requirements, so as to obtain the speculative model used in step 110 .
  • the maximum size MaxSize of the assessed mineral is obtained.
  • the maximum size MaxSize can be obtained through various ways, and in one embodiment, it can be obtained from user input.
  • the user may input the size of the mineral to be evaluated (including the maximum size MaxSize) into the application program capable of executing the method 100, so that the application program uses the maximum size MaxSize of the mineral to estimate the price of the mineral.
  • the maximum size MaxSize of the assessed mineral may be identified based on the imagery by a trained inference model.
  • the guessing model used to identify the maximum size MaxSize and the guessing model used in step 110 to identify the parameters Matrix, MaxCrystalRatio, HighSatuation, Contract and EvenComplete may be the same model or a different model.
  • the speculative model can identify the parameters Matrix, MaxCrystalRatio, HighSatuation, Contract, and EvenComplete and the maximum size MaxSize based on the input imagery.
  • Each sample in the training sample set of the speculative model may include a picture of minerals and the values of the parameters Matrix, MaxCrystalRatio, HighSatuation, Contract and EvenComplete of the minerals in the marked picture, and the maximum size MaxSize.
  • the speculative model trained by the neural network based on the training sample set can output the parameters Matrix, MaxCrystalRatio, HighSatuation, Contract, and EvenComplete, as well as the maximum size MaxSize.
  • a training sample set may be separately established for the speculative model used to identify the maximum size MaxSize, and each sample may include a picture of a mineral and the maximum size MaxSize of the mineral in the marked picture.
  • the guessing model trained by the neural network based on the training sample set can identify the maximum size MaxSize of the minerals in the picture.
  • an application capable of performing method 100 may receive an input correction to the identified maximum size, resulting in a maximum size MaxSize of the assessed mineral. For example, after the user inputs an image of a mineral, the application can output information identified based on the image to the user, and the user can check the difference between the maximum size MaxSize of the mineral and the actual maximum size of the mineral. If the discrepancy is large, the user can enter the maximum size MaxSize of the assessed mineral into the application to correct the size identified by the application itself. The application performs subsequent operations based on the size corrected by the user.
  • the average estimated price per unit size corresponding to the evaluated mineral without the influence of the quality factor is obtained.
  • the AverageEvaluatePriceperSize which excludes the influence of the quality factor, may be predetermined before executing the method 100 .
  • the average value per unit size AverageEvaluatePriceperSize that removes the influence of the quality factor can be predetermined for each type of mineral, for example, the average value per unit size set AverageEvaluatePriceperSizeSet is predetermined, which includes N types of minerals that respectively correspond to the N categories of Species i and eliminate the influence of the quality factor
  • the average unit size evaluation AverageEvaluatePriceperSize i corresponding to the mineral category Species i , except for the influence of quality factors is determined according to the following method: obtain multiple samples of minerals belonging to the category Species i ; The actual price of minerals ActualPrice , maximum size MaxSize and quality factor, calculate the unit size evaluation EvaluatePriceperSize of minerals in each sample except for the influence of quality factors; The estimated unit size EvaluatePriceperSize of minerals excluding the influence of the quality factor is averaged to obtain the average estimated price per unit size excluding the influence of the quality factor corresponding to the category Species i .
  • the unit size evaluation EvaluatePriceperSize of the minerals in each sample is calculated without the influence of the quality factor, which can be based on the following formula 2 to proceed:
  • the quality factor index QualityIndex can be calculated according to the relationship between the quality factor index QualityIndex and the parameters Matrix, MaxCrystalRatio, HighSatuation, Contract and EvenComplete (for example, formula 1).
  • step 130 calculate the evaluated price EvaluatePrice of the evaluated mineral according to the quality factor, the maximum size MaxSize and the average estimated price per unit size without the influence of the quality factor AverageEvaluatePriceperSize.
  • a quality factor index, QualityIndex may be used to represent the quality factor of the assessed mineral.
  • the estimated price of the evaluated mineral EvaluatePrice can be calculated according to the following formula 3:
  • the first column is the actual price ActualPrice of the mineral in the sample
  • the second column is the maximum size MaxSize
  • the third column is the unit price PriceperSize calculated by dividing the ActualPrice of the first column by the MaxSize of the second column
  • the fourth column to the first
  • the eight columns are the five parameters Matrix, MaxCrystalRatio, HighSatuation, Contract, and EvenComplete associated with the quality factor
  • the ninth column is the quality factor index QualityIndex representing the quality factor calculated according to formula 1
  • the tenth column is the sample calculated according to formula 2 EvaluatePriceperSize per unit size of minerals in addition to quality factors.
  • the data in the last row of the tenth column (20.72 in the example in Figure 5) is the average estimated price per unit size EvaluatePriceperSize excluding the influence of the quality factor obtained by averaging the unit size assessment EvaluatePriceperSize of the above samples without the influence of the quality factor.
  • the average estimated price is the average estimated price per unit size for the mineral category Species i corresponding to the sample data shown in Fig. 5 excluding the influence of the quality factor.
  • the EvaluatePrice of minerals of this category Species i can be calculated by using Formula 3 according to the average estimated price per unit size except the quality factor in the last row of the tenth column.
  • FIG. 2 is a flow diagram that schematically illustrates at least a portion of a method 200 of estimating mineral prices according to some embodiments of the present disclosure.
  • the method 200 includes: based on the image of the mineral under evaluation, using a neural network-based inference model to identify the quality factor of the mineral under evaluation (step 210); obtaining the maximum size MaxSize of the mineral under evaluation, and obtaining The price estimation function corresponding to the mineral (step 220); and according to the quality factor, the maximum size MaxSize and the price estimation function, calculate the evaluated price EvaluatePrice of the mineral being evaluated (step 230).
  • Step 210 of the method 200 is the same as step 110 of the method 100, and will not be repeated here.
  • Obtaining the maximum size MaxSize of the assessed mineral at step 220 is the same as the operation of obtaining the maximum size MaxSize of the estimated mineral at step 120 , and will not be repeated here.
  • a price estimation function corresponding to the assessed mineral is also obtained.
  • the price estimation function may be predetermined prior to performing method 200 .
  • a price estimation function may be predetermined for each type of mineral, for example, a predetermined price estimation function set including a plurality of price estimation functions respectively corresponding to a plurality of categories of minerals.
  • a price estimation function corresponding to the class of mineral being evaluated may then be selected from the set of price estimation functions according to the class of mineral being evaluated.
  • the price is a function of the maximum size MaxSize and the parameters Matrix, MaxCrystalRatio, HighSatuation, Contract and EvenComplete.
  • the following is an example of how to determine the price estimation function for a mineral whose category is Species i to specifically describe how to determine the price estimation function y i f i (x1, x2, x3, x4, x5, x6).
  • the maximum size MaxSize j the parameters associated with quality factors Matrix j , MaxCrystalRatio j , HighSatuation j , Contract j and EvenComplete j are the influencing factors on the actual price ActualPrice j , which can be used as independent variables of the price estimation function, And the actual price ActualPrice j is used as the dependent variable of the price estimation function. Perform function fitting on these data points (e.g.
  • Two methods 100 and 200 of estimating mineral prices are described above. Any one of the methods 100 and 200 can be used to obtain the evaluated price EvaluatePrice of the mineral being evaluated, and a combination of methods 100 and 200 can be used to obtain the evaluated price EvaluatePrice of the mineral being evaluated. For example, methods 100 and 200 can be used to obtain the first evaluation price EvaluatePrice1 and the second evaluation price EvaluatePrice2 of the evaluated mineral, and then the first evaluation price EvaluatePrice1 and the second evaluation price EvaluatePrice2 are weighted and averaged to obtain the evaluated mineral The final evaluation price of EvaluatePriceFinal.
  • the above-described operations of methods 100 and 200 both require the parameter of the type of mineral.
  • the method 100 according to the category of the mineral to be evaluated, it is necessary to select the average estimated price per unit size AverageEvaluatePriceperSize corresponding to the category of the mineral to be assessed from the average price per unit size set AverageEvaluatePriceperSizeSet except for the influence of the quality factor.
  • the method 200 it is necessary to select a price estimation function corresponding to the assessed mineral category from the set of price estimation functions according to the assessed mineral category.
  • the class of minerals assessed may be obtained from the user.
  • a user may input an assessed mineral category into an application capable of performing methods 100 and/or 200, so that the application uses the assessed mineral category to estimate a price for the mineral.
  • the class of the assessed mineral may be identified based on the imagery by a trained mineral class recognition model.
  • a training sample set may be established, and each sample may include pictures of minerals and the category of minerals in the marked pictures. The training sample set can be used to train the neural network until the output accuracy of the model meets the requirements, so as to obtain the mineral category recognition model.
  • the application may receive input corrections to the identified mineral class, resulting in the assessed mineral class.
  • the application can output the category information identified based on the image to the user, and the user can judge whether the recognition result of the application is correct based on the known information. If incorrect or inaccurate, the user can enter into the app the class of mineral being assessed to correct the app's autonomous identification. The application performs subsequent operations based on the category modified by the user.
  • FIG. 3 is a block diagram schematically illustrating at least a portion of a computer system 300 for estimating mineral prices according to some embodiments of the present disclosure.
  • system 300 may include one or more storage devices 310 , one or more user devices 320 , and one or more computing devices 330 , which may be communicatively connected to each other via a network or bus 340 .
  • One or more storage devices 310 provide storage services for one or more user devices 320 , and one or more computing devices 330 .
  • one or more storage devices 310 are shown in system 300 as a separate block from one or more user devices 320 and one or more computing devices 330, it should be understood that one or more storage devices 310 May actually be stored on any of the other entities 320, 330 included in the system 300.
  • Each of the one or more user devices 320 and the one or more computing devices 330 may be located at different nodes of the network or bus 340 and be capable of communicating directly or indirectly with other nodes of the network or bus 340 .
  • the system 300 may also include other devices not shown in FIG. 3 , where each different device is located at a different node of the network or bus 340 .
  • One or more storage devices 310 may be configured to store any of the above-mentioned data, including but not limited to: images input from users, each training sample set, each neural network model, recognition results, unit size average evaluation set, Data such as price estimation function sets, application files, etc.
  • One or more computing devices 330 may be configured to perform one or more of the above-mentioned methods according to the embodiments, and/or one or more steps in the one or more methods according to the embodiments.
  • One or more user devices 320 may be configured to provide services to the user, for example, receiving imagery from the user and input for modifying the identification results, outputting the identified information and an estimated price of the assessed mineral (including first, second 2 and the final evaluation price), etc.
  • One or more user equipments 320 may also be configured to execute one or more of the above methods according to the embodiments, and/or one or more steps in the one or more methods according to the embodiments.
  • Network or bus 340 may be any wired or wireless network, and may include cables.
  • Network or bus 340 may be part of the Internet, the World Wide Web, a specific intranet, a wide area network or a local area network.
  • Network or bus 340 may utilize standard communication protocols such as Ethernet, WiFi, and HTTP, protocols proprietary to one or more companies, and various combinations of the foregoing.
  • the network or bus 340 may also include, but is not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MCA) bus, an Enhanced ISA (EISA) bus, a Video Electronics Standards Association (VESA) local bus, and a peripheral component interconnect (PCI) bus.
  • ISA Industry Standard Architecture
  • MCA Micro Channel Architecture
  • EISA Enhanced ISA
  • VESA Video Electronics Standards Association
  • PCI peripheral component interconnect
  • Each of the one or more user equipment 320 and the one or more computing devices 330 may be configured similarly to the system 400 shown in FIG. And instruction 421 and data 422.
  • Each of the one or more user devices 320 and the one or more computing devices 330 may be a personal computing device intended for use by a user or a business computing device for use by an All components used in conjunction, such as the central processing unit (CPU), memory for storing data and instructions (e.g., RAM and internal hard drives), such as displays (e.g., monitors with screens, touch screens, projectors, televisions, or operable other devices to display information), mouse, keyboard, touch screen, microphone, speakers, and/or one or more I/O devices such as network interface devices.
  • CPU central processing unit
  • memory for storing data and instructions (e.g., RAM and internal hard drives)
  • displays e.g., monitors with screens, touch screens, projectors, televisions, or operable other devices to display information
  • mouse keyboard, touch screen, microphone, speakers, and/or one
  • One or more user devices 320 may also include one or more cameras for capturing still images or recording video streams, and all components for connecting these elements to each other. While one or more user devices 320 may each comprise a full-sized personal computing device, they may alternatively comprise a mobile computing device capable of wirelessly exchanging data with a server over a network, such as the Internet. One or more user devices 320 may be, for example, a mobile phone, or a device such as a PDA with wireless support, a tablet PC, or a netbook capable of obtaining information via the Internet. In another example, one or more user devices 320 may be a wearable computing system.
  • FIG. 4 is a block diagram schematically illustrating at least a portion of a computer system 400 for estimating mineral prices according to one embodiment of the present disclosure.
  • System 400 includes one or more processors 410, one or more memories 420, and other components (not shown) typically found in a computer or the like.
  • Each of the one or more memories 420 can store content that can be accessed by the one or more processors 410, including instructions 421 that can be executed by the one or more processors 410, and that can be executed by the one or more processors 410.
  • Data 422 retrieved, manipulated or stored.
  • Instructions 421 may be any set of instructions to be executed directly by one or more processors 410, such as machine code, or indirectly, such as a script.
  • the terms “instruction”, “application”, “process”, “step” and “program” are used interchangeably herein.
  • Instructions 421 may be stored in object code format for direct processing by one or more processors 410, or in any other computer language, including scripts or collections of stand-alone source code modules interpreted on demand or compiled ahead of time. Instructions 421 may include instructions that cause, for example, one or more processors 410 to function as various neural networks herein. The function, method and routine of instruction 421 are explained in more detail elsewhere herein.
  • the one or more memories 420 may be any temporary or non-transitory computer-readable storage media capable of storing content accessible by the one or more processors 410, such as hard drives, memory cards, ROM, RAM, DVDs, CDs, USB memory, writable memory and read-only memory, etc.
  • One or more of the one or more memories 420 may comprise a distributed storage system where instructions 421 and/or data 422 may be stored on multiple different storage devices which may be physically located at the same or different geographic locations.
  • One or more of the one or more memories 420 may be connected to the one or more first devices 410 via a network, and/or may be directly connected to or incorporated in any of the one or more processors 410 .
  • One or more processors 410 may retrieve, store or modify data 422 according to instructions 421 .
  • the data 422 stored in the one or more memories 420 may include at least a portion of one or more of the items stored in the one or more storage devices 310 described above.
  • data 422 could also be stored in computer registers (not shown), as tables or XML documents with many different fields and records stored in relational type database.
  • Data 422 may be formatted in any computing device readable format, such as, but not limited to, binary values, ASCII, or Unicode. Additionally, data 422 may include any information sufficient to identify the relevant information, such as numbers, descriptive text, proprietary code, pointers, references to data stored in other storage, such as at other network locations, or used by functions to compute relevant information. data information.
  • the one or more processors 410 may be any conventional processor, such as a commercially available central processing unit (CPU), graphics processing unit (GPU), or the like. Alternatively, one or more processors 410 may also be a dedicated component, such as an application specific integrated circuit (ASIC) or other hardware-based processor. Although not required, one or more processors 410 may include specialized hardware components to more quickly or efficiently perform certain computational processes, such as image processing of imagery and the like.
  • CPU central processing unit
  • GPU graphics processing unit
  • ASIC application specific integrated circuit
  • processors 410 may include specialized hardware components to more quickly or efficiently perform certain computational processes, such as image processing of imagery and the like.
  • system 400 may actually include multiple Multiple processors or memory within a physical enclosure.
  • one of the one or more memories 420 may be a hard drive or other storage medium located in a different housing than that of each of the one or more computing devices (not shown) described above .
  • references to a processor, computer, computing device or memory shall be understood to include references to a collection of processors, computers, computing devices or memory which may or may not operate in parallel.
  • references to "one embodiment” or “some embodiments” means that a feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment, at least some embodiments of the present disclosure.
  • appearances of the phrase “in one embodiment” and “in some embodiments” in various places in this disclosure are not necessarily referring to the same embodiment or embodiments.
  • features, structures or characteristics may be combined in any suitable combination and/or subcombination in one or more embodiments.
  • the word "exemplary” means “serving as an example, instance, or illustration” rather than as a “model” to be exactly reproduced. Any implementation described illustratively herein is not necessarily to be construed as preferred or advantageous over other implementations. Furthermore, the disclosure is not to be bound by any expressed or implied theory presented in the preceding technical field, background, brief summary or detailed description.
  • a component may be, but is not limited to being, a process, object, executable, thread of execution, and/or program running on a processor.
  • a component may be, but is not limited to being, a process, object, executable, thread of execution, and/or program running on a processor.
  • an application running on a server and the server may be a component.
  • One or more components can reside within a process and/or thread of execution and a component can be localized on one computer and/or distributed between two or more computers.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Physics & Mathematics (AREA)
  • Development Economics (AREA)
  • Theoretical Computer Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Physics & Mathematics (AREA)
  • Educational Administration (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Game Theory and Decision Science (AREA)
  • Tourism & Hospitality (AREA)
  • General Health & Medical Sciences (AREA)
  • Operations Research (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Quality & Reliability (AREA)
  • Animal Husbandry (AREA)
  • Data Mining & Analysis (AREA)
  • Primary Health Care (AREA)
  • Marine Sciences & Fisheries (AREA)
  • Mining & Mineral Resources (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Agronomy & Crop Science (AREA)
  • Evolutionary Computation (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

本公开涉及评估矿物价格的方法,包括:根据所评估的矿物的影像,使用基于神经网络训练的第一推测模型,识别所评估的矿物的质量因素;获取所评估的矿物的最大尺寸MaxSize,并获取与所评估的矿物对应的除却质量因素影响的单位尺寸平均估价AverageEvaluatePriceperSize;以及根据所述质量因素、最大尺寸MaxSize以及除却质量因素影响的单位尺寸平均估价AverageEvaluatePriceperSize,计算所评估的矿物的评估价格EvaluatePrice。本公开还涉及评估矿物价格的计算机***。

Description

评估矿物价格的方法和计算机*** 技术领域
本公开涉及计算机技术领域,尤其涉及评估矿物价格的方法和计算机***。
背景技术
在计算机技术领域中,存在多种用于识别对象的应用程序。这些应用程序通常接收来自用户的影像(包括静态图像、动态图像、以及视频等),并基于由人工智能技术建立的对象识别模型对影像中的待识别对象进行识别。
发明内容
本公开的一个目的是提供评估矿物价格的方法和计算机***。
根据本公开的第一方面,提供了一种评估矿物价格的方法,包括:根据所评估的矿物的影像,使用基于神经网络训练的第一推测模型,识别所评估的矿物的质量因素;获取所评估的矿物的最大尺寸MaxSize,并获取与所评估的矿物对应的除却质量因素影响的单位尺寸平均估价AverageEvaluatePriceperSize;以及根据所述质量因素、最大尺寸MaxSize以及除却质量因素影响的单位尺寸平均估价AverageEvaluatePriceperSize,计算所评估的矿物的评估价格EvaluatePrice。
根据本公开的第二方面,提供了一种评估矿物价格的方法,包括:根据所评估的矿物的影像,使用基于神经网络训练的推测模型,识别所评估的矿物的质量因素;获取所评估的矿物的最大尺寸MaxSize,并获取与所评估的矿物对应的价格估算函数;以及根据所述质量因素、最大尺寸MaxSize以及价格估算函数,计算所评估的矿物的评估价格EvaluatePrice。
根据本公开的第三方面,提供了一种评估矿物价格的计算机***,包括:一个或多个处理器;以及一个或多个存储器,所述一个或多个存储器被配置为存储一系列计算机可执行的指令以及与所述一系列计算机可执行的指令相关联的计算机可访问的数据,其中,当所述一系列计算机可执行的指令被所 述一个或多个处理器执行时,使得所述计算机***进行如上所述的任一方法。
根据本公开的第四方面,提供了一种非临时性计算机可读存储介质,所述非临时性计算机可读存储介质上存储有一系列计算机可执行的指令,当所述一系列计算机可执行的指令被一个或多个计算装置执行时,使得所述一个或多个计算装置进行如上所述的任一方法。
通过以下参照附图对本公开的示例性实施例的详细描述,本公开的其它特征及其优点将会变得清楚。
附图说明
构成说明书的一部分的附图描述了本公开的实施例,并且连同说明书一起用于解释本公开的原理。
参照附图,根据下面的详细描述,可以更加清楚地理解本公开,其中:
图1是示意性地示出根据本公开一些实施例的评估矿物价格的方法的至少一部分的流程图。
图2是示意性地示出根据本公开一些实施例的评估矿物价格的方法的至少一部分的流程图。
图3是示意性地示出根据本公开一些实施例的评估矿物价格的计算机***的至少一部分的结构图。
图4是示意性地示出根据本公开一些实施例的评估矿物价格的计算机***的至少一部分的结构图。
图5是示意性地示出适用于根据本公开一些实施例的评估矿物价格的方法的矿物样本数据的示意图。
注意,在以下说明的实施方式中,有时在不同的附图之间共同使用同一附图标记来表示相同部分或具有相同功能的部分,而省略其重复说明。在本说明书中,使用相似的标号和字母表示类似项,因此,一旦某一项在一个附图中被定义,则在随后的附图中不需要对其进行进一步讨论。
具体实施方式
以下将参照附图来详细描述本公开的各种示例性实施例。应注意到:除非另外具体说明,否则在这些实施例中阐述的部件和步骤的相对布置、数字表达式和数值不限制本公开的范围。在下面描述中,为了更好地解释本公开,阐述了许多细节,然而可以理解的是,在没有这些细节的情况下也可以实践本公开。
以下对至少一个示例性实施例的描述实际上仅仅是说明性的,决不作为对本公开及其应用或使用的任何限制。在这里示出和讨论的所有示例中,任何具体值应被解释为仅仅是示例性的,而不是作为限制。
对于相关领域普通技术人员已知的技术、方法和设备可能不作详细讨论,但在适当情况下,所述技术、方法和设备应当被视为说明书的一部分。
由于矿物可供人学习、研究、观赏的特性,不少爱好者进行矿物收藏。因此,可以结合人工智能技术,提供对矿物的识别或者对矿物的价格进行评估的应用程序。本文所称“矿物”,是指具有确定形貌的矿物,也可被称为矿物标本、矿物样本、矿物晶体等。
影响矿物的价格的因素是多种多样的。本申请的发明人经研究后发现,不同种类、不同尺寸、以及不同质量等级的矿物的价格差异较大,因此可以通过如下三个指标来评估矿物的价格:矿物的类别(不同类别的矿物的估值基础不同)、矿物的最大尺寸(矿物的长、宽、高中的最大尺寸)、以及矿物的质量因素。而质量因素方面,发明人发现,具有底岩的矿物因为较为美观通常其价格也较高;全是小颗粒的晶体的矿物的价格通常低于具有大尺寸晶体的矿物;在某类矿物具备的所有可能颜色中,较高饱和度的矿物其价格通常也较高;晶体的颜色和底岩的颜色的色彩对比度越明显其价格通常越高;颜色越均匀、杂质越少,晶体越完整、越没有破损,其价格通常越高。因此,本公开提出,质量因素与该矿物是否包括底岩、矿物的最大晶体尺寸与所评估的矿物的最大尺寸之比、矿物的颜色饱和度、矿物的晶体的颜色和底岩的颜色的色彩对比度、以及矿物的晶体的均匀完整度等方面相关联。可以为质量因素的这些方面分别设置参数,每个参数可以具有量化值以代表相应方面的不同等级,从而对矿物的质量因素进行 量化,进而有利于矿物价格的评估。
图1是示意性地示出根据本公开一些实施例的评估矿物价格的方法100的至少一部分的流程图。方法100包括:根据所评估的矿物的影像,使用基于神经网络训练的第一推测模型,识别所评估的矿物的质量因素(步骤110);获取所评估的矿物的最大尺寸MaxSize,并获取与所评估的矿物对应的除却质量因素影响的单位尺寸平均估价AverageEvaluatePriceperSize(步骤120);以及根据质量因素、最大尺寸MaxSize以及除却质量因素影响的单位尺寸平均估价AverageEvaluatePriceperSize,计算所评估的矿物的评估价格EvaluatePrice(步骤130)。方法100可以由为用户提供评估矿物价格的功能的应用程序来执行。
用户可以将能够呈现所评估的矿物的影像输入到可以进行评估矿物价格的应用程序,来评估该矿物的价格。该影像可以是用户先前存储的、实时拍摄的、或者从网络上下载的。影像可以包括任何形式的视觉呈现,例如静态图像、动态图像、以及视频等。影像可以利用包括摄像头的设备进行拍摄,如手机、平板电脑等。
能够执行方法100的应用程序可以接收来自用户的影像,并在步骤110中使用基于神经网络训练的推测模型对影像中的矿物的质量因素进行识别。可以设置与质量因素相关联的参数Matrix、参数MaxCrystalRatio、参数HighSatuation、参数Contract、以及参数EvenComplete。其中,参数Matrix指示所评估的矿物是否包括底岩,参数MaxCrystalRatio指示所评估的矿物的最大晶体尺寸与所评估的矿物的最大尺寸之比,参数HighSatuation指示所评估的矿物的颜色饱和度,参数Contract指示所评估的矿物的晶体的颜色和底岩的颜色的色彩对比度,参数EvenComplete指示所评估的矿物的晶体的均匀完整度。还可以设置质量因素指数QualityIndex以对质量因素进行量化,其中,质量因素指数QualityIndex可以为参数Matrix、MaxCrystalRatio、HighSatuation、Contract和EvenComplete的函数。
可以为上述与质量因素相关联的参数设置量化值,以代表相应质量方面的不同等级。在一个实施例中,参数Matrix可以具有0、1的取值,分别指示矿物不包括底岩、包括底岩。参数MaxCrystalRatio可以具有-1、0、1的取值,分别指示矿物的最大晶体尺寸与矿物的最大尺寸之比小于1/9、在1/9和1/3之间(可以包括端点值)、大于1/3。参数HighSatuation可以具有-1、0、1的取值,分别指示矿物的颜色饱和度的等级为差、中、好。参数Contract具有-1、0、1的取值,分别指示矿物的晶体的颜色和底岩的颜色的色彩对比度的等级为差、中、好。参数EvenComplete具有-1、0、1的取值,分别指示矿物的晶体的均匀完整度的等级为差、中、好。在该实施例中,质量因素指数QualityIndex与参数Matrix、MaxCrystalRatio、HighSatuation、Contract和EvenComplete可以具有如下的公式1的关系:
公式1:QualityIndex=2 (Matrix+MaxCrystalRatio/2+HighSatuation/2+Contract/2+ EvenComplete)
在步骤110,使用推测模型对影像中的矿物的质量因素进行识别可以是,使用推测模型识别出所评估的矿物的参数Matrix、MaxCrystalRatio、HighSatuation、Contract和EvenComplete,然后根据质量因素指数QualityIndex与参数Matrix、MaxCrystalRatio、HighSatuation、Contract和EvenComplete的关系(例如公式1)计算出质量因素指数QualityIndex,从而确定所评估的矿物的质量因素。
推测模型是基于神经网络预先训练的。可以获取训练数据以建立训练样本集。可以从全球各大矿物售卖网站爬取所有矿物商品的图片,并为每张图片标注其中的矿物的参数Matrix、MaxCrystalRatio、HighSatuation、Contract和EvenComplete的值。标注后的图片形成为训练样本集中的训练样本(也可称为训练数据)。然后使用训练样本集,基于深度学习对神经网络进行训练,以得到一个多维度分类模型,其可以根据输入的影像输出影像中的矿物的参数Matrix、MaxCrystalRatio、HighSatuation、Contract和EvenComplete的值。还可以使用测试样本集对该多维度分类模型的输出准确度进行测试,直到输出准确度满足要求时训练完成,从而得到步骤110 中使用的推测模型。
在步骤120,获取所评估的矿物的最大尺寸MaxSize。最大尺寸MaxSize的获取可以通过多种途径,在一个实施例中,可以获取自用户的输入。用户可以向能够执行方法100的应用程序输入所评估的矿物的尺寸(包括最大尺寸MaxSize),以便于应用程序使用所评估的矿物的最大尺寸MaxSize来对该矿物的价格进行评估。在一个实施例中,可以通过已训练的推测模型来基于影像识别所评估的矿物的最大尺寸MaxSize。
应当理解,用于识别最大尺寸MaxSize的推测模型,与步骤110中使用的用于识别参数Matrix、MaxCrystalRatio、HighSatuation、Contract和EvenComplete的推测模型,可以是同一个模型也可以是不同的模型。在是同一个模型的示例中,该推测模型可以基于输入的影像识别出参数Matrix、MaxCrystalRatio、HighSatuation、Contract和EvenComplete以及最大尺寸MaxSize。该推测模型的训练样本集中的每个样本可以包括矿物的图片和所标注的图片中的矿物的参数Matrix、MaxCrystalRatio、HighSatuation、Contract和EvenComplete的值以及最大尺寸MaxSize。基于该训练样本集对神经网络训练出来的推测模型,既可以输出参数Matrix、MaxCrystalRatio、HighSatuation、Contract和EvenComplete,也可以输出最大尺寸MaxSize。在不是同一个模型的示例中,可以为用于识别最大尺寸MaxSize的推测模型单独建立训练样本集,其中的每个样本可以包括矿物的图片和所标注的图片中的矿物的最大尺寸MaxSize。基于该训练样本集对神经网络训练出来的推测模型可以识别图片中的矿物的最大尺寸MaxSize。
由于影像对矿物的拍摄角度以及拍摄距离等因素,基于影像对其中的矿物的尺寸的识别可能是不准确的。在一个实施例中,能够执行方法100的应用程序可以接收输入的对所识别的最大尺寸的修正,从而得到所评估的矿物的最大尺寸MaxSize。例如,在用户输入了矿物的影像之后,应用程序可以将基于影像识别出的信息输出给用户,用户可以检查其中的矿物的最大尺寸MaxSize与矿物的实际最大尺寸的差异。如果差异较大,用户 可以向应用程序输入所评估的矿物的最大尺寸MaxSize以对应用程序自主识别的尺寸进行修正。应用程序以经用户修正后的尺寸为基础进行后续的操作。
在步骤120,还获取与所评估的矿物对应的除却质量因素影响的单位尺寸平均估价AverageEvaluatePriceperSize。除却质量因素影响的单位尺寸平均估价AverageEvaluatePriceperSize可以是在执行方法100之前预先确定的。可以为每个种类的矿物预先确定除却质量因素影响的单位尺寸平均估价AverageEvaluatePriceperSize,例如,预先确定单位尺寸平均估价集AverageEvaluatePriceperSizeSet,其包括与矿物的N个类别Species i分别对应的N个除却质量因素影响的单位尺寸平均估价AverageEvaluatePriceperSize i,其中,i=1,2,…,N。然后可以根据所评估的矿物的类别,从AverageEvaluatePriceperSizeSet中选择与所评估的矿物的类别对应的除却质量因素影响的单位尺寸平均估价AverageEvaluatePriceperSize。
单位尺寸平均估价集AverageEvaluatePriceperSizeSet中的与矿物的类别Species i对应的除却质量因素影响的单位尺寸平均估价AverageEvaluatePriceperSize i根据如下方法确定:获取属于类别Species i的矿物的多个样本;根据每个样本中的矿物的实际价格ActualPrice、最大尺寸MaxSize和质量因素,计算每个样本中的矿物的除却质量因素影响的单位尺寸估价EvaluatePriceperSize;以及将属于类别Species i的矿物的多个样本中的每个样本中的矿物的除却质量因素影响的单位尺寸估价EvaluatePriceperSize进行平均,以得到与类别Species i对应的除却质量因素影响的单位尺寸平均估价AverageEvaluatePriceperSize i
在一个实施例中,根据每个样本中的矿物的实际价格ActualPrice、最大尺寸MaxSize和质量因素,来计算每个样本中的矿物的除却质量因素影响的单位尺寸估价EvaluatePriceperSize,可以根据如下的公式2来进行:
公式2:EvaluatePriceperSize=ActualPrice/MaxSize/QualityIndex。
其中,可以根据质量因素指数QualityIndex与参数Matrix、 MaxCrystalRatio、HighSatuation、Contract和EvenComplete的关系(例如公式1),来计算质量因素指数QualityIndex。
在步骤130,根据质量因素、最大尺寸MaxSize以及除却质量因素影响的单位尺寸平均估价AverageEvaluatePriceperSize,计算所评估的矿物的评估价格EvaluatePrice。在一个实施例中,可以使用质量因素指数QualityIndex来代表所评估的矿物的质量因素。例如,在质量因素指数QualityIndex具有如公式1所示的计算关系的示例中,可以根据如下的公式3来计算所评估的矿物的评估价格EvaluatePrice:
公式3:EvaluatePrice=AverageEvaluatePriceperSize*MaxSize*QualityIndex。
参考图5所示的矿物样本数据,这些数据对应同一个类别的矿物,例如Species i。第一列为样本中的矿物的实际价格ActualPrice,第二列为最大尺寸MaxSize,第三列为用第一列的ActualPrice除以第二列的MaxSize计算出来的尺寸单价PriceperSize,第四列至第八列分别为质量因素相关联的五个参数Matrix、MaxCrystalRatio、HighSatuation、Contract和EvenComplete,第九列为根据公式1计算的代表质量因素的质量因素指数QualityIndex,第十列为根据公式2计算的样本中的矿物除却质量因素影响的单位尺寸估价EvaluatePriceperSize。第十列的最后一行的数据(在图5的示例中为20.72)为将上面的各个样本的除却质量因素影响的单位尺寸估价EvaluatePriceperSize进行平均得到的除却质量因素影响的单位尺寸平均估价AverageEvaluatePriceperSize,该平均估价为针对图5所示的样本数据所对应的矿物类别Species i的除却质量因素影响的单位尺寸平均估价AverageEvaluatePriceperSize。之后可以根据第十列的最后一行的除却质量因素影响的单位尺寸平均估价AverageEvaluatePriceperSize,使用公式3来计算这种类别Species i的矿物的评估价格EvaluatePrice。
图2是示意性地示出根据本公开一些实施例的评估矿物价格的方法200的至少一部分的流程图。方法200包括:根据所评估的矿物的影像,使用基于神经网络训练的推测模型,识别所评估的矿物的质量因素(步骤 210);获取所评估的矿物的最大尺寸MaxSize,并获取与所评估的矿物对应的价格估算函数(步骤220);以及根据质量因素、最大尺寸MaxSize以及价格估算函数,计算所评估的矿物的评估价格EvaluatePrice(步骤230)。
方法200的步骤210同方法100的步骤110,此处不再赘述。在步骤220获取所评估的矿物的最大尺寸MaxSize,与在步骤120获取所评估的矿物的最大尺寸MaxSize的操作相同,此处也不再赘述。
在步骤220,还获取与所评估的矿物对应的价格估算函数。价格估算函数可以是在执行方法200之前预先确定的。可以为每个种类的矿物预先确定价格估算函数,例如,预先确定价格估算函数集,其包括与矿物的多个类别分别对应的多个价格估算函数。然后可以根据所评估的矿物的类别,从价格估算函数集中选择与所评估的矿物的类别对应的价格估算函数。
价格估算函数集中的与矿物的类别Species i(其中,i=1,2,…,N)对应的价格估算函数y i=f i(x1,x2,x3,x4,x5,x6)根据如下方法确定:获取属于类别Species i的矿物的多个样本;以及根据属于类别Species i的矿物的多个样本中的每个样本中的矿物的实际价格ActualPrice、最大尺寸MaxSize以及参数Matrix、MaxCrystalRatio、HighSatuation、Contract和EvenComplete,拟合出针对类别Species i的矿物的价格估算函数y i=f i(x1,x2,x3,x4,x5,x6)。在价格估算函数中价格为最大尺寸MaxSize、以及参数Matrix、MaxCrystalRatio、HighSatuation、Contract和EvenComplete的函数。
下面以为类别为Species i的矿物确定价格估算函数为例来具体说明如何确定价格估算函数y i=f i(x1,x2,x3,x4,x5,x6)。可以从各大矿物售卖网站爬取类别为Species i的矿物的商品信息共M条,每条信息包含有该矿物商品的实际价格ActualPrice j、最大尺寸MaxSize j、与质量因素相关联的参数Matrix j、MaxCrystalRatio j、HighSatuation j、Contract j和EvenComplete j这些数据,其中,j=1,2,…,M。在这些数据中,最大尺寸MaxSize j、与质量因素相关联的参数Matrix j、MaxCrystalRatio j、HighSatuation j、Contract j 和EvenComplete j作为对实际价格ActualPrice j的影响因素,可以作为价格估算函数的自变量,而实际价格ActualPrice j作为价格估算函数的因变量。对这些数据点进行函数拟合(例如通过Matlab),拟合出价格估算函数y i=f i(x1,x2,x3,x4,x5,x6),其中y表示矿物的实际价格,x1至x6分别表示上述最大尺寸MaxSize j至EvenComplete j的6个对实际价格的影响因素。
以上描述了两种评估矿物价格的方法100和200。可以使用方法100和200中的任意一种来得到所评估的矿物的评估价格EvaluatePrice,也可以使用方法100和200的结合来得到所评估的矿物的评估价格EvaluatePrice。例如,可以分别使用方法100和200得到所评估的矿物的第一评估价格EvaluatePrice1和第二评估价格EvaluatePrice2,然后将第一评估价格EvaluatePrice1和第二评估价格EvaluatePrice2进行加权平均,从而得到所评估的矿物的最终评估价格EvaluatePriceFinal。
以上描述的方法100和200的操作过程均需要矿物的类别这个参数。例如,在方法100中,需要根据所评估的矿物的类别,从预先确定单位尺寸平均估价集AverageEvaluatePriceperSizeSet中选择与所评估的矿物的类别对应的除却质量因素影响的单位尺寸平均估价AverageEvaluatePriceperSize。在方法200中,需要根据所评估的矿物的类别,从价格估算函数集中选择与所评估的矿物的类别对应的价格估算函数。获得所评估的矿物的类别可以通过多种途径。在一个实施例中,可以从用户处获得所评估的矿物的类别。用户可以向能够执行方法100和/或200的应用程序输入所评估的矿物的类别,以便于应用程序使用所评估的矿物的类别来对该矿物的价格进行评估。在一个实施例中,可以通过已训练的矿物类别识别模型来基于影像识别所评估的矿物的类别。可以建立训练样本集,其中的每个样本可以包括矿物的图片和所标注的图片中的矿物的类别。可以使用该训练样本集来对神经网络进行训练,直到模型的输出准确率满足要求,从而得到矿物类别识别模型。在一个实施例中,应用程序可以接收输入的对所识别的矿物类别的修正,从而得到所评估的矿物的类别。例如,在用户输入了矿物的影像之后,应用程序可以将基于影像识别出的类 别信息输出给用户,用户可以根据其已知的信息判断应用程序的识别结果是否正确。如果不正确或不准确,用户可以向应用程序输入所评估的矿物的类别,以对应用程序自主识别的结果进行修正。应用程序以经用户修正后的类别为基础进行后续的操作。
图3是示意性地示出根据本公开一些实施例的评估矿物价格的计算机***300的至少一部分的结构图。本领域技术人员可以理解,***300只是一个示例,不应将其视为限制本公开的范围或本文所描述的特征。在该示例中,***300可以包括一个或多个存储装置310、一个或多个用户设备320、以及一个或多个计算装置330,其可以通过网络或总线340互相通信连接。一个或多个存储装置310为一个或多个用户设备320、以及一个或多个计算装置330提供存储服务。虽然一个或多个存储装置310在***300中以独立于一个或多个用户设备320、以及一个或多个计算装置330之外的单独的框示出,应当理解,一个或多个存储装置310可以实际存储在***300所包括的其他实体320、330中的任何一个上。一个或多个用户设备320以及一个或多个计算装置330中的每一个可以位于网络或总线340的不同节点处,并且能够直接地或间接地与网络或总线340的其他节点通信。本领域技术人员可以理解,***300还可以包括图3未示出的其他装置,其中每个不同的装置均位于网络或总线340的不同节点处。
一个或多个存储装置310可以被配置为存储上文所述的任何数据,包括但不限于:从用户输入的影像、各训练样本集、各神经网络模型、识别结果、单位尺寸平均估价集、价格估算函数集、应用程序的文件等数据。一个或多个计算装置330可以被配置为执行上述根据实施例的方法中的一个或多个,和/或一个或多个根据实施例的方法中的一个或多个步骤。一个或多个用户设备320可以被配置为为用户提供服务,例如,从用户接收影像和用于修正识别结果的输入,输出识别出的信息以及所评估的矿物的评估价格(包括第一、第二和最终评估价格)等。一个或多个用户设备320还可以被配置为执行上述根据实施例的方法中的一个或多个,和/或一个或多个根据实施例的方法中的一个或多个步骤。
网络或总线340可以是任何有线或无线的网络,也可以包括线缆。网络或总线340可以是互联网、万维网、特定内联网、广域网或局域网的一部分。网络或总线340可以利用诸如以太网、WiFi和HTTP等标准通信协议、对于一个或多个公司来说是专有的协议、以及前述协议的各种组合。网络或总线340还可以包括但不限于工业标准体系结构(ISA)总线、微通道架构(MCA)总线、增强型ISA(EISA)总线、视频电子标准协会(VESA)本地总线、和***部件互连(PCI)总线。
一个或多个用户设备320和一个或多个计算装置330中的每一个可以被配置为与图4所示的***400类似,即具有一个或多个处理器410、一个或多个存储器420、以及指令421和数据422。一个或多个用户设备320和一个或多个计算装置330中的每一个可以是意在由用户使用的个人计算装置或者由企业使用的商业计算机装置,并且具有通常与个人计算装置或商业计算机装置结合使用的所有组件,诸如中央处理单元(CPU)、存储数据和指令的存储器(例如,RAM和内部硬盘驱动器)、诸如显示器(例如,具有屏幕的监视器、触摸屏、投影仪、电视或可操作来显示信息的其他装置)、鼠标、键盘、触摸屏、麦克风、扬声器、和/或网络接口装置等的一个或多个I/O设备。
一个或多个用户设备320还可以包括用于捕获静态图像或记录视频流的一个或多个相机、以及用于将这些元件彼此连接的所有组件。虽然一个或多个用户设备320可以各自包括全尺寸的个人计算装置,但是它们可能可选地包括能够通过诸如互联网等网络与服务器无线地交换数据的移动计算装置。举例来说,一个或多个用户设备320可以是移动电话,或者是诸如带无线支持的PDA、平板PC或能够经由互联网获得信息的上网本等装置。在另一个示例中,一个或多个用户设备320可以是可穿戴式计算***。
图4是示意性地示出根据本公开的一个实施例的评估矿物价格的计算机***400的至少一部分的结构图。***400包括一个或多个处理器410、一个或多个存储器420、以及通常存在于计算机等装置中的其他组件(未示出)。一个或多个存储器420中的每一个可以存储可由一个或多个处理 器410访问的内容,包括可以由一个或多个处理器410执行的指令421、以及可以由一个或多个处理器410来检索、操纵或存储的数据422。
指令421可以是将由一个或多个处理器410直接地执行的任何指令集,诸如机器代码,或者间接地执行的任何指令集,诸如脚本。本文中的术语“指令”、“应用”、“过程”、“步骤”和“程序”在本文中可以互换使用。指令421可以存储为目标代码格式以便由一个或多个处理器410直接处理,或者存储为任何其他计算机语言,包括按需解释或提前编译的独立源代码模块的脚本或集合。指令421可以包括引起诸如一个或多个处理器410来充当本文中的各神经网络的指令。本文其他部分更加详细地解释了指令421的功能、方法和例程。
一个或多个存储器420可以是能够存储可由一个或多个处理器410访问的内容的任何临时性或非临时性计算机可读存储介质,诸如硬盘驱动器、存储卡、ROM、RAM、DVD、CD、USB存储器、能写存储器和只读存储器等。一个或多个存储器420中的一个或多个可以包括分布式存储***,其中指令421和/或数据422可以存储在可以物理地位于相同或不同的地理位置处的多个不同的存储装置上。一个或多个存储器420中的一个或多个可以经由网络连接至一个或多个第一装置410,和/或可以直接地连接至或并入一个或多个处理器410中的任何一个中。
一个或多个处理器410可以根据指令421来检索、存储或修改数据422。存储在一个或多个存储器420中的数据422可以包括上文所述的一个或多个存储装置310中存储的各项中一项或多项的至少部分。举例来说,虽然本文所描述的主题不受任何特定数据结构限制,但是数据422还可能存储在计算机寄存器(未示出)中,作为具有许多不同的字段和记录的表格或XML文档存储在关系型数据库中。数据422可以被格式化为任何计算装置可读格式,诸如但不限于二进制值、ASCII或统一代码。此外,数据422可以包括足以识别相关信息的任何信息,诸如编号、描述性文本、专有代码、指针、对存储在诸如其他网络位置处等其他存储器中的数据的引用或者被函数用于计算相关数据的信息。
一个或多个处理器410可以是任何常规处理器,诸如市场上可购得的中央处理单元(CPU)、图形处理单元(GPU)等。可替换地,一个或多个处理器410还可以是专用组件,诸如专用集成电路(ASIC)或其他基于硬件的处理器。虽然不是必需的,但是一个或多个处理器410可以包括专门的硬件组件来更快或更有效地执行特定的计算过程,诸如对影像进行图像处理等。
虽然图4中示意性地将一个或多个处理器410以及一个或多个存储器420示出在同一个框内,但是***400可以实际上包括可能存在于同一个物理壳体内或不同的多个物理壳体内的多个处理器或存储器。例如,一个或多个存储器420中的一个可以是位于与上文所述的一个或多个计算装置(未示出)中的每一个的壳体不同的壳体中的硬盘驱动器或其他存储介质。因此,引用处理器、计算机、计算装置或存储器应被理解成包括引用可能并行操作或可能非并行操作的处理器、计算机、计算装置或存储器的集合。
在说明书及权利要求中的词语“A或B”包括“A和B”以及“A或B”,而不是排他地仅包括“A”或者仅包括“B”,除非另有特别说明。
在本公开中,对“一个实施例”、“一些实施例”的提及意味着结合该实施例描述的特征、结构或特性包含在本公开的至少一个实施例、至少一些实施例中。因此,短语“在一个实施例中”、“在一些实施例中”在本公开的各处的出现未必是指同一个或同一些实施例。此外,在一个或多个实施例中,可以任何合适的组合和/或子组合来组合特征、结构或特性。
如在此所使用的,词语“示例性的”意指“用作示例、实例或说明”,而不是作为将被精确复制的“模型”。在此示例性描述的任意实现方式并不一定要被解释为比其它实现方式优选的或有利的。而且,本公开不受在上述技术领域、背景技术、发明内容或具体实施方式中所给出的任何所表述的或所暗示的理论所限定。
另外,仅仅为了参考的目的,还可以在下面描述中使用某种术语,并且因而并非意图限定。例如,除非上下文明确指出,否则涉及结构或元件的词语“第一”、“第二”和其它此类数字词语并没有暗示顺序或次序。 还应理解,“包括/包含”一词在本文中使用时,说明存在所指出的特征、整体、步骤、操作、单元和/或组件,但是并不排除存在或增加一个或多个其它特征、整体、步骤、操作、单元和/或组件以及/或者它们的组合。
在本公开中,术语“部件”和“***”意图是涉及一个与计算机有关的实体,或者硬件、硬件和软件的组合、软件、或执行中的软件。例如,一个部件可以是,但是不局限于,在处理器上运行的进程、对象、可执行态、执行线程、和/或程序等。通过举例说明,在一个服务器上运行的应用程序和所述服务器两者都可以是一个部件。一个或多个部件可以存在于一个执行的进程和/或线程的内部,并且一个部件可以被定位于一台计算机上和/或被分布在两台或更多计算机之间。
本领域技术人员应当意识到,在上述操作之间的边界仅仅是说明性的。多个操作可以结合成单个操作,单个操作可以分布于附加的操作中,并且操作可以在时间上至少部分重叠地执行。而且,另选的实施例可以包括特定操作的多个实例,并且在其他各种实施例中可以改变操作顺序。但是,其它的修改、变化和替换同样是可能的。因此,本说明书和附图应当被看作是说明性的,而非限制性的。
虽然已经通过示例对本公开的一些特定实施例进行了详细说明,但是本领域的技术人员应该理解,以上示例仅是为了进行说明,而不是为了限制本公开的范围。在此公开的各实施例可以任意组合,而不脱离本公开的精神和范围。本领域的技术人员还应理解,可以对实施例进行多种修改而不脱离本公开的范围和精神。本公开的范围由所附权利要求来限定。

Claims (25)

  1. 一种评估矿物价格的方法,包括:
    根据所评估的矿物的影像,使用基于神经网络训练的第一推测模型,识别所评估的矿物的质量因素;
    获取所评估的矿物的最大尺寸MaxSize,并获取与所评估的矿物对应的除却质量因素影响的单位尺寸平均估价AverageEvaluatePriceperSize;以及
    根据所述质量因素、最大尺寸MaxSize以及除却质量因素影响的单位尺寸平均估价AverageEvaluatePriceperSize,计算所评估的矿物的评估价格EvaluatePrice。
  2. 根据权利要求1所述的方法,其中,所述质量因素与第一参数至第五参数相关联,其中,
    所述第一参数Matrix指示所评估的矿物是否包括底岩;
    所述第二参数MaxCrystalRatio指示所评估的矿物的最大晶体尺寸与所评估的矿物的最大尺寸之比;
    所述第三参数HighSatuation指示所评估的矿物的颜色饱和度;
    所述第四参数Contract指示所评估的矿物的晶体的颜色和底岩的颜色的色彩对比度;以及
    所述第五参数EvenComplete指示所评估的矿物的晶体的均匀完整度。
  3. 根据权利要求2所述的方法,其中,识别所评估的矿物的质量因素包括:
    使用所述第一推测模型,识别所评估的矿物的第一参数至第五参数;以及
    根据识别出的第一参数至第五参数,确定所述质量因素。
  4. 根据权利要求3所述的方法,其中,所述第一推测模型通过如下方法得到:
    建立训练样本集,所述训练样本集包括多个样本,每个样本包括矿物 的影像和标注的与该影像中的矿物对应的第一参数Matrix、第二参数MaxCrystalRatio、第三参数HighSatuation、第四参数Contract和第五参数EvenComplete;以及
    使用所述训练样本集对神经网络进行训练,以得到所述第一推测模型。
  5. 根据权利要求2所述的方法,其中,
    所述第一参数Matrix具有0或1的取值,分别指示所评估的矿物不包括底岩或包括底岩;
    所述第二参数MaxCrystalRatio具有-1、0或1的取值,分别指示所评估的矿物的最大晶体尺寸与所评估的矿物的最大尺寸之比小于1/9、在1/9和1/3之间或大于1/3;
    所述第三参数HighSatuation具有-1、0或1的取值,分别指示所评估的矿物的颜色饱和度的等级为差、中或好;
    所述第四参数Contract具有-1、0或1的取值,分别指示所评估的矿物的晶体的颜色和底岩的颜色的色彩对比度的等级为差、中或好;以及
    所述第五参数EvenComplete具有-1、0或1的取值,分别指示所评估的矿物的晶体的均匀完整度的等级为差、中或好。
  6. 根据权利要求5所述的方法,其中,
    识别所评估的矿物的质量因素包括通过如下公式计算所评估的矿物的质量因素指数QualityIndex:
    QualityIndex=2 (Matrix+MaxCrystalRatio/2+HighSatuation/2+Contract/2+EvenComplete);以及
    根据如下公式计算所评估的矿物的评估价格EvaluatePrice:
    EvaluatePrice=AverageEvaluatePriceperSize*MaxSize*QualityIndex。
  7. 根据权利要求1所述的方法,其中,获取所评估的矿物的最大尺寸MaxSize包括:
    根据所述影像,使用基于神经网络训练的第二推测模型,识别所述影像中的矿物的最大尺寸,从而得到所评估的矿物的最大尺寸MaxSize。
  8. 根据权利要求7所述的方法,还包括:
    接收输入的对所识别的最大尺寸的修正,从而得到所评估的矿物的最大尺寸MaxSize。
  9. 根据权利要求7所述的方法,其中,所述第一推测模型和所述第二推测模型为同一个模型。
  10. 根据权利要求1所述的方法,其中,获取与所评估的矿物对应的除却质量因素影响的单位尺寸平均估价AverageEvaluatePriceperSize包括:
    预先确定单位尺寸平均估价集AverageEvaluatePriceperSizeSet,所述单位尺寸平均估价集AverageEvaluatePriceperSizeSet包括与矿物的多个类别Species i分别对应的多个除却质量因素影响的单位尺寸平均估价AverageEvaluatePriceperSize i,其中,i=1,2,…,N;以及
    根据所评估的矿物的类别,从所述单位尺寸平均估价集AverageEvaluatePriceperSizeSet中选择与所评估的矿物的类别对应的除却质量因素影响的单位尺寸平均估价AverageEvaluatePriceperSize。
  11. 根据权利要求10所述的方法,所述单位尺寸平均估价集AverageEvaluatePriceperSizeSet中的与矿物的类别Species i对应的除却质量因素影响的单位尺寸平均估价AverageEvaluatePriceperSize i根据如下方法确定:
    获取属于类别Species i的矿物的多个样本;
    根据每个样本中的矿物的实际价格ActualPrice、最大尺寸MaxSize和质量因素,计算每个样本中的矿物的除却质量因素影响的单位尺寸估价EvaluatePriceperSize;以及
    将属于类别Species i的矿物的多个样本中的每个样本中的矿物的除却质量因素影响的单位尺寸估价EvaluatePriceperSize进行平均,以得到与类别Species i对应的除却质量因素影响的单位尺寸平均估价AverageEvaluatePriceperSize i
  12. 根据权利要求1所述的方法,还包括:
    获取与所评估的矿物对应的价格估算函数;
    根据所述质量因素、最大尺寸MaxSize以及价格估算函数,计算所评估的矿物的第二评估价格EvaluatePrice2;以及
    将所述评估价格EvaluatePrice和所述第二评估价格EvaluatePrice2进行加权平均,以得到所评估的矿物的最终评估价格EvaluatePriceFinal。
  13. 根据权利要求12所述的方法,其中,获取与所评估的矿物对应的价格估算函数包括:
    预先确定价格估算函数集,所述价格估算函数集包括与矿物的多个类别分别对应的多个价格估算函数;以及
    根据所评估的矿物的类别,从所述价格估算函数集中选择与所评估的矿物的类别对应的价格估算函数。
  14. 根据权利要求13所述的方法,所述价格估算函数集中的与矿物的类别Species i对应的价格估算函数根据如下方法确定:
    获取属于类别Species i的矿物的多个样本;以及
    根据属于类别Species i的矿物的多个样本中的每个样本中的矿物的实际价格ActualPrice、最大尺寸MaxSize和质量因素,拟合出针对类别Species i的矿物的价格估算函数,在所述价格估算函数中价格为最大尺寸MaxSize和质量因素的函数。
  15. 一种评估矿物价格的方法,包括:
    根据所评估的矿物的影像,使用基于神经网络训练的推测模型,识别所评估的矿物的质量因素;
    获取所评估的矿物的最大尺寸MaxSize,并获取与所评估的矿物对应的价格估算函数;以及
    根据所述质量因素、最大尺寸MaxSize以及价格估算函数,计算所评估的矿物的评估价格EvaluatePrice。
  16. 根据权利要求15所述的方法,其中,所述质量因素与第一参数至第五参数相关联,其中,
    所述第一参数Matrix指示所评估的矿物是否包括底岩;
    所述第二参数MaxCrystalRatio指示所评估的矿物的最大晶体尺寸与 所评估的矿物的最大尺寸之比;
    所述第三参数HighSatuation指示所评估的矿物的颜色饱和度;
    所述第四参数Contract指示所评估的矿物的晶体的颜色和底岩的颜色的色彩对比度;以及
    所述第五参数EvenComplete指示所评估的矿物的晶体的均匀完整度。
  17. 根据权利要求16所述的方法,其中,识别所评估的矿物的质量因素包括:
    使用所述推测模型,识别所评估的矿物的第一参数至第五参数;以及
    根据识别出的第一参数至第五参数,确定所述质量因素。
  18. 根据权利要求17所述的方法,其中,所述推测模型通过如下方法得到:
    建立训练样本集,所述训练样本集包括多个样本,每个样本包括矿物的影像和标注的与该影像中的矿物对应的第一参数Matrix、第二参数MaxCrystalRatio、第三参数HighSatuation、第四参数Contract和第五参数EvenComplete;以及
    使用所述训练样本集对神经网络进行训练,以得到所述推测模型。
  19. 根据权利要求16所述的方法,其中,
    所述第一参数Matrix具有0或1的取值,分别指示所评估的矿物不包括底岩或包括底岩;
    所述第二参数MaxCrystalRatio具有-1、0或1的取值,分别指示所评估的矿物的最大晶体尺寸与所评估的矿物的最大尺寸之比小于1/9、在1/9和1/3之间或大于1/3;
    所述第三参数HighSatuation具有-1、0或1的取值,分别指示所评估的矿物的颜色饱和度的等级为差、中或好;
    所述第四参数Contract具有-1、0或1的取值,分别指示所评估的矿物的晶体的颜色和底岩的颜色的色彩对比度的等级为差、中或好;以及
    所述第五参数EvenComplete具有-1、0或1的取值,分别指示所评估的矿物的晶体的均匀完整度的等级为差、中或好。
  20. 根据权利要求15所述的方法,其中,获取所评估的矿物的最大尺寸MaxSize包括:
    根据所述影像,使用所述推测模型,识别所述影像中的矿物的最大尺寸,从而得到所评估的矿物的最大尺寸MaxSize。
  21. 根据权利要求20所述的方法,还包括:
    接收输入的对所识别的最大尺寸的修正,从而得到所评估的矿物的最大尺寸MaxSize。
  22. 根据权利要求16所述的方法,其中,获取与所评估的矿物对应的价格估算函数包括:
    预先确定价格估算函数集,所述价格估算函数集包括与矿物的多个类别分别对应的多个价格估算函数;以及
    根据所评估的矿物的类别,从所述价格估算函数集中选择与所评估的矿物的类别对应的价格估算函数。
  23. 根据权利要求22所述的方法,所述价格估算函数集中的与矿物的类别Species i对应的价格估算函数根据如下方法确定:
    获取属于类别Species i的矿物的多个样本;以及
    根据属于类别Species i的矿物的多个样本中的每个样本中的矿物的实际价格ActualPrice、最大尺寸MaxSize和第一参数至第五参数,拟合出针对类别Species i的矿物的价格估算函数,在所述价格估算函数中价格为最大尺寸MaxSize和第一参数至第五参数的函数。
  24. 一种评估矿物价格的计算机***,包括:
    一个或多个处理器;以及
    一个或多个存储器,所述一个或多个存储器被配置为存储一系列计算机可执行的指令以及与所述一系列计算机可执行的指令相关联的计算机可访问的数据,
    其中,当所述一系列计算机可执行的指令被所述一个或多个处理器执行时,使得所述计算机***进行如权利要求1-23中任一项所述的方法。
  25. 一种非临时性计算机可读存储介质,其特征在于,所述非临时性计 算机可读存储介质上存储有一系列计算机可执行的指令,当所述一系列计算机可执行的指令被一个或多个计算机***执行时,使得所述一个或多个计算机***进行如权利要求1-23中任一项所述的方法。
PCT/CN2022/099548 2021-07-09 2022-06-17 评估矿物价格的方法和计算机*** WO2023279944A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110777039.4 2021-07-09
CN202110777039.4A CN113435942A (zh) 2021-07-09 2021-07-09 评估矿物价格的方法和计算机***

Publications (1)

Publication Number Publication Date
WO2023279944A1 true WO2023279944A1 (zh) 2023-01-12

Family

ID=77759738

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/099548 WO2023279944A1 (zh) 2021-07-09 2022-06-17 评估矿物价格的方法和计算机***

Country Status (2)

Country Link
CN (1) CN113435942A (zh)
WO (1) WO2023279944A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113435942A (zh) * 2021-07-09 2021-09-24 杭州睿胜软件有限公司 评估矿物价格的方法和计算机***

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130339255A1 (en) * 2012-06-19 2013-12-19 Fannie Mae Automated valuation model with comparative value histories
CN107292660A (zh) * 2017-05-22 2017-10-24 北京速信科技有限公司 一种基于大数据的珠宝艺术品价值评估方法及***
CN108734520A (zh) * 2018-05-24 2018-11-02 哈工大机器人(合肥)国际创新研究院 一种基于机器学习的玉石价格评估方法及装置
CN110852795A (zh) * 2019-10-30 2020-02-28 中国科学院自动化研究所南京人工智能芯片创新研究院 一种基于计算机视觉的手机估价***及其估价方法
CN112365441A (zh) * 2020-10-12 2021-02-12 深圳市对庄科技有限公司 一种用于翡翠评估的信息处理方法及装置
CN113435942A (zh) * 2021-07-09 2021-09-24 杭州睿胜软件有限公司 评估矿物价格的方法和计算机***

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2008045613A2 (en) * 2006-10-11 2008-04-17 Rosy Blue Dmcc Diamond valuation method, apparatus and computer readable medium product
CN112116398A (zh) * 2020-09-27 2020-12-22 广州华多网络科技有限公司 一种宝石估价方法及相关设备

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130339255A1 (en) * 2012-06-19 2013-12-19 Fannie Mae Automated valuation model with comparative value histories
CN107292660A (zh) * 2017-05-22 2017-10-24 北京速信科技有限公司 一种基于大数据的珠宝艺术品价值评估方法及***
CN108734520A (zh) * 2018-05-24 2018-11-02 哈工大机器人(合肥)国际创新研究院 一种基于机器学习的玉石价格评估方法及装置
CN110852795A (zh) * 2019-10-30 2020-02-28 中国科学院自动化研究所南京人工智能芯片创新研究院 一种基于计算机视觉的手机估价***及其估价方法
CN112365441A (zh) * 2020-10-12 2021-02-12 深圳市对庄科技有限公司 一种用于翡翠评估的信息处理方法及装置
CN113435942A (zh) * 2021-07-09 2021-09-24 杭州睿胜软件有限公司 评估矿物价格的方法和计算机***

Also Published As

Publication number Publication date
CN113435942A (zh) 2021-09-24

Similar Documents

Publication Publication Date Title
TWI753044B (zh) 影片資料的推薦方法和裝置
Perez-Ortiz et al. A practical guide and software for analysing pairwise comparison experiments
US20190266434A1 (en) Method and device for extracting information from pie chart
JP5476236B2 (ja) コーディネート推薦装置、コーディネート推薦方法及びそのプログラム
JP6216024B1 (ja) 学習済モデル生成方法及び信号データ判別装置
US9569498B2 (en) Using image features to extract viewports from images
CN108846066B (zh) 一种可视化的数据分析方法及***
US11853368B2 (en) Method and system for identifying and displaying an object
TWI722325B (zh) 對待評估樣本進行分類的方法、裝置、電腦可讀儲存介質及計算設備
CN108876756A (zh) 图像相似性的度量方法和装置
WO2023279944A1 (zh) 评估矿物价格的方法和计算机***
CN111597933A (zh) 人脸识别方法和装置
TWI803243B (zh) 圖像擴增方法、電腦設備及儲存介質
Qureshi et al. A comprehensive performance evaluation of objective quality metrics for contrast enhancement techniques
CN108369647B (zh) 基于图像的质量控制
CN111753729B (zh) 一种假脸检测方法、装置、电子设备及存储介质
CN112348615B (zh) 用于审核信息的方法和装置
CN105913427B (zh) 一种基于机器学习的噪声图像显著性检测方法
CN112035605A (zh) 题目推荐方法、装置、设备及存储介质
Ahmed et al. BIQ2021: a large-scale blind image quality assessment database
Patil et al. Survey on approaches used for image quality assessment
Khanzadi et al. A novel metric for digital image quality assessment using entropy-based image complexity
US20190149878A1 (en) Determining and correlating visual context on a user device with user behavior using digital content on the user device
CN112580674A (zh) 一种图片识别方法、计算机设备、存储介质
Zhou et al. No-reference image quality assessment via multi-order perception similarity

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22836698

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE