Transaction method and system for half-height container

Abstract

The invention provides a transaction method and system for a half-height container, and the method comprises the steps: receiving a box basic feature uploaded by a first transaction end in response to a resale transaction instruction, calling a box basic model and a box basic value according to the box basic feature, and transmitting the box basic model and the box basic value to the first transaction end; receiving a planning trace of the first transaction end for the box basic model based on the transparent image layer, determining a planning area according to the planning trace, associating the actual defect image based on the planning area to obtain a primary evaluation model, and sending the primary evaluation model to the detection end; according to the refrigeration detection requirement of the detection end, dividing the primary evaluation model based on the box body end points to obtain a multi-level function display space, obtaining a multi-level function, and carrying out customized updating on the multi-level function display space to obtain a secondary evaluation model; evaluating the secondary evaluation model to obtain an evaluation coefficient, adjusting the box body basic value according to the evaluation coefficient to obtain a box body recommendation value, and updating the secondary evaluation model based on the box body recommendation value to obtain a comprehensive recommendation model.

Description

Technical Field

[0001] The present invention relates to the technical field of quality inspection, and in particular to a transaction method and system for a half-high container. Background Art

[0002] As the main means of transport in the field of cargo transportation, semi-high containers enable various types of cargo to be transported from one transportation node to another conveniently and quickly, and have become a key component of global trade. As time goes by, users' cargo transportation needs may change. For example, some semi-high containers may no longer be suitable for long-distance transportation due to aging or wear, but can still be used for short-distance or temporary storage. Therefore, many semi-high containers are put back on the market for other users to purchase, thereby meeting the cargo transportation requirements of different users.

[0003] In the current second-hand transactions of semi-high containers, there is a lack of methods for performing automated analysis based on the semi-high container data uploaded by users to generate recommended data and assist users in formulating transaction data based on the recommended data. Summary of the invention

[0004] The embodiment of the present invention provides a semi-high container transaction method and system, which can automatically analyze the semi-high container data uploaded by the user, thereby generating recommended data, and assist the user in formulating transaction data based on the recommended data.

[0005] According to a first aspect of an embodiment of the present invention, a transaction method for a half-high container is provided, comprising responding to a resale transaction instruction, receiving basic characteristics of a container uploaded by a first transaction terminal, retrieving a basic model of a container and a basic value of a container according to the basic characteristics of the container, and sending the result to the first transaction terminal, receiving a planning trace of the basic model of the container by the first transaction terminal based on a transparent layer, determining a planning area according to the planning trace, and obtaining a primary evaluation model based on associating the planning area with an actual defect image, and sending the model to a detection terminal, dividing the primary evaluation model based on the container endpoints according to the refrigeration detection requirements of the detection terminal to obtain a multi-level function display space, obtaining a multi-level function to customize and update the multi-level function display space to obtain a secondary evaluation model, retrieving a comprehensive evaluation model to evaluate the secondary evaluation model to obtain an evaluation coefficient, adjusting the basic value of the container according to the evaluation coefficient to obtain a recommended container value, and updating the secondary evaluation model based on the recommended container value to obtain a comprehensive recommendation model.

[0006] Optionally, in a possible implementation of the first aspect, the response to the resale transaction instruction, receiving the basic characteristics of the container uploaded by the first transaction end, retrieving the basic model of the container and the basic value of the container according to the basic characteristics of the container, and sending them to the first transaction end, includes: calling the attribute entry interface in response to the resale transaction instruction, obtaining the attribute editing data of the semi-high container for sale based on the attribute entry interface, identifying the attribute editing data, obtaining the basic characteristics of the container, extracting resale attribute data according to the basic characteristics of the container, the resale attribute data including the basic model of the container and the basic value of the container, and sending the basic model of the container and the basic value of the container to the first transaction end.

[0007] Optionally, in a possible implementation of the first aspect, the transparent layer-based receiving of planning traces of the box basic model by the first transaction end, determining a planning area according to the planning traces, associating the planning area with an actual defect image to obtain an evaluation model and sending it to the detection end includes: receiving click information of the box basic model by the first transaction end, the click information including outer side click information and / or inner side click information, determining a click surface of the box basic model according to the click information, retrieving a transparent layer corresponding to the click surface and superimposing it on the click surface, obtaining a user's planning action based on the transparent layer, identifying the planning action to obtain a planning trace, determining a planning area corresponding to the click surface according to the planning traces, the planning area including an internal planning area and / or an external planning area, associating the internal planning area and / or the external planning area with the corresponding actual defect image, obtaining an evaluation model and sending it to the detection end.

[0008] Optionally, in a possible implementation of the first aspect, the actual defect image corresponding to the association of the internal planning area and / or the external planning area is used to obtain an evaluation model and send it to the detection end, including: responding to the first transaction end's selection information of the internal planning area one by one, receiving the actual defect image and establishing an association with the internal planning area, responding to any selection information of the external planning area by the first transaction end, obtaining a click surface corresponding to the external planning area as a first click surface, counting all external planning areas of the first click surface as associated planning areas, coordinate processing of the first click surface based on the center point of the first click surface, obtaining multiple first coordinate sets corresponding to the associated planning areas, and receiving the The first transaction end uploads an external side image corresponding to the click surface, obtains the box edge in the external side image, cuts the external side image according to the box edge to obtain a box side image, resizes the box side image according to a preset size corresponding to the first click surface to obtain a standard image, coordinates the standard image based on the center point of the standard image, determines the corresponding coordinate set in the standard image according to the first coordinate set to obtain multiple second coordinate sets, batch-cuts the corresponding areas in the standard image according to the second coordinate set as actual defect images, associates the actual defect images with the corresponding external planning areas one by one, obtains an evaluation model and sends it to the detection end.

[0009] Optionally, in a possible implementation of the first aspect, according to the refrigeration detection requirements of the detection end, the primary evaluation model is divided based on the cabinet endpoints to obtain a multi-level function display space, and the multi-level function is obtained to customize and update the multi-level function display space to obtain a secondary evaluation model, including: according to the refrigeration monitoring requirements of the detection end, the sensor layout information uploaded by the detection end is obtained, and the cabinet corner points at corresponding positions are determined as display endpoints based on the sensor layout information. A first-level function display space is constructed at the position of the first evaluation model corresponding to the display endpoint, and the middle position in the length direction of the first evaluation model is determined. The space is expanded to both sides based on the middle position to generate a second-level function display space, and the multi-level function display space includes a first-level function display space and a second-level function display space. The first-level function corresponding to the display endpoint is obtained to update the first-level function display space, and the corresponding second-level function is obtained according to the summary information of multiple first-level functions. The second-level function display space is updated based on the second-level function to obtain a secondary evaluation model.

[0010] Optionally, in a possible implementation of the first aspect, a first-level function corresponding to the display endpoint is obtained to update the first-level function display space, a corresponding second-level function is obtained according to the summary information of multiple first-level functions, the second-level function display space is updated based on the second-level function, and a secondary evaluation model is obtained, including: receiving temperature fluctuation data obtained by each sensor, generating a first-level function corresponding to each display endpoint based on the temperature fluctuation data, and updating the corresponding first-level function display space according to the first-level function; taking the moment of each first-level function as a reference, performing temperature mean processing on multiple first-level functions to obtain summary information corresponding to each moment, generating a corresponding second-level function according to the summary information, updating the second-level function display space based on the second-level function, and obtaining a secondary evaluation model.

[0011] Optionally, in a possible implementation of the first aspect, spatial model parameters of the primary function display space and the secondary function display space are obtained, and the spatial center points of the primary function display space and the secondary function display space are determined; a corresponding initial spatial display surface is established with the spatial center point as the center and the extreme values ​​of the spatial model parameters as the boundaries; the initial spatial display surface includes a first spatial surface and a second spatial surface perpendicular to each other; the first spatial surface or the second spatial surface is selected according to the user's interactive perspective, and the angle of the first spatial surface or the second spatial surface is adjusted; and the corresponding primary function or secondary function is added to the selected and adjusted first spatial surface or the second spatial surface; the browsing data of each user on the primary function display space and the secondary function display space is obtained to generate customized data; after determining that the user chooses to view a new box, a customized browsing video of the new box is generated based on the customized data, so that the user can view the primary function display space and the secondary function display space based on the customized browsing video.

[0012] Optionally, in a possible implementation of the first aspect, the selecting the first spatial plane or the second spatial plane according to the user's perspective, adjusting the angle of the first spatial plane or the second spatial plane, and adding the corresponding primary function or secondary function to the selected and adjusted first spatial plane or second spatial plane include: determining the user's initial interaction perspective, determining one of the first spatial plane or the second spatial plane based on the interaction perspective, the interaction perspective in each direction has a preset first spatial plane or second spatial plane, and displaying the primary function and the secondary function of each primary function display space and the secondary function display space on the corresponding first spatial plane or second spatial plane respectively; if it is determined that the corresponding user adjusts the angle, the primary function and the secondary function are no longer displayed, and the first spatial plane or the second spatial plane is accompanied by an angle adjustment based on the value of the angle adjustment; the primary function and the secondary function are displayed again after the angle adjustment; after it is determined that the angle adjustment reaches a threshold, the first spatial plane or the second spatial plane is switched, and the corresponding primary function or secondary function is added to the selected and adjusted first spatial plane or the second spatial plane.

[0013] Optionally, in a possible implementation of the first aspect, the browsing data of each user on the primary function display space and the secondary function display space are obtained to generate customized data. After determining that the user chooses to view a new box, a customized browsing video of the new box is generated based on the customized data, so that the user can view the primary function display space and the secondary function display space based on the customized browsing video, including: obtaining the first spatial surface or the second spatial surface corresponding to the primary function display space and the secondary function display space corresponding to each box of the historical number viewed by each user, obtaining the dwell time of each first spatial surface or the second spatial surface, obtaining the order of the first spatial surface or the second spatial surface corresponding to each box of the viewing history of each user, generating a corresponding sequential angle node path based on the order and angle of the first spatial surface or the second spatial surface, sorting the boxes based on the viewing time of each box of the historical number, generating a dwell weight for each dwell time based on the sorting, each sequence has a preset dwell weight, and the viewing time corresponding to the dwell weight gradually increases from far to near, performing corresponding automatic data extraction on the new box based on the sequential angle node path, the dwell time, and the dwell weight, and generating a customized browsing video for the new box.

[0014] Optionally, in a possible implementation of the first aspect, the corresponding automatic data extraction of the new box based on the sequential angle node path and the dwell time to generate a customized browsing video of the new box includes: obtaining the number of sequential angle nodes in the sequential angle node path, generating a corresponding dwell time offset value based on the comparison between the number and a preset number, processing the dwell time offset based on the dwell time offset value, and obtaining the browsing sub-time of each sequential angle node in the sequential angle node path; calculating the browsing sub-time of each sequential angle node by the following formula: , in, For the The first spatial surface or the second spatial surface is in the Browsing time from each angle, The box viewed for history is in The first spatial surface or the second spatial surface is in the The dwell time at each angle, The box viewed for history is in The first spatial surface or the second spatial surface is in the The stop weight of the angle, The upper limit value of the box viewed in history. The number of boxes viewed in history. is a constant value, is the number of sequential angle node paths, is the preset quantity, is the quantity weight value.

[0015] Optionally, in a possible implementation of the first aspect, a comprehensive evaluation model is called to evaluate the secondary evaluation model to obtain an evaluation coefficient, and the basic value of the box is adjusted according to the evaluation coefficient to obtain the recommended value of the box, including: calling the comprehensive evaluation model to obtain the fluctuation start data and the fluctuation end data of the first-level function, determining the test fluctuation slope according to the fluctuation start data and the fluctuation end data, obtaining the test fluctuation limit according to the fluctuation end data, obtaining the first-level preset function corresponding to the first-level function, determining the standard fluctuation slope according to the fluctuation start data and the fluctuation end data of the first-level preset function, when the test fluctuation limit reaches the preset standard fluctuation limit, obtaining the ratio information of the test fluctuation slope and the standard fluctuation slope, obtaining the effect evaluation coefficient according to the ratio information, calculating the basic value of the box based on the effect evaluation coefficient, obtaining the first-level effect reduction associated with the first-level function, obtaining the second-level effect reduction according to the sum of multiple first-level effect reductions, and associating the second-level effect reduction with the second-level function.

[0016] Optionally, a comprehensive evaluation model is retrieved to evaluate the secondary evaluation model to obtain an evaluation coefficient, and the basic value of the box is adjusted according to the evaluation coefficient to obtain the recommended value of the box, including: retrieving the comprehensive evaluation model to perform type analysis on the actual defect image to obtain the defect type of the actual defect image, extracting the defect contour in the actual defect image, obtaining the defect area of ​​the defect contour, and obtaining a defect evaluation coefficient according to the ratio of the defect area to the area normalization value, retrieving a preset corresponding table corresponding to the defect type, determining the defect reduction corresponding to the defect evaluation coefficient according to the preset corresponding table, and associating the defect reduction with the planning area one by one, the preset corresponding table including the correspondence between the coefficient interval and the defect reduction, obtaining the total defect reduction according to the sum of the defect reductions, and reducing and adjusting the basic value of the box based on the secondary effect reduction and the total defect reduction to obtain the recommended value of the box.

[0017] According to a second aspect of an embodiment of the present invention, a trading system for a half-high container is provided, comprising: a feature acquisition module for responding to a resale transaction instruction, receiving basic features of a container uploaded by a first transaction terminal, retrieving a basic model of a container and a basic value of a container according to the basic features of the container, and sending the results to the first transaction terminal; a region association module for receiving planning traces of the basic model of the container by the first transaction terminal based on a transparent layer, determining a planning region according to the planning traces, and obtaining a primary evaluation model based on the association of the planning region with an actual defect image, and sending the model to a detection terminal; a customized update module for dividing the primary evaluation model based on the container endpoints according to the refrigeration detection requirements of the detection terminal to obtain a multi-level function display space, obtaining a multi-level function to customize and update the multi-level function display space, and obtaining a secondary evaluation model; a model generation module for retrieving a comprehensive evaluation model to evaluate the secondary evaluation model, and obtaining an evaluation coefficient; adjusting the basic value of the container according to the evaluation coefficient to obtain a recommended value of the container; and updating the secondary evaluation model based on the recommended value of the container to obtain a comprehensive recommendation model.

[0018] The beneficial effects of the present invention are as follows: 1. The present invention can determine the basic model and basic value of the half-high container for sale based on the basic features of the container uploaded by the user, update the appearance data of the basic model of the container to obtain a primary evaluation model, then update the data corresponding to the refrigeration effect of the primary evaluation model to obtain a secondary evaluation model, and finally evaluate the secondary evaluation model to obtain an evaluation coefficient, adjust the basic value of the container based on the evaluation coefficient to obtain a recommended value of the container, and update the secondary evaluation model based on the recommended value of the container to obtain a comprehensive recommendation model. The embodiment of the present invention performs automatic analysis based on the half-high container data uploaded by the user, thereby generating recommended data, and assists the user in formulating transaction data based on the recommended data.

[0019] 2. The present invention can obtain the corresponding click surface according to the external planning area information selected by the first transaction end, and use the click surface as the first click surface, count all the external planning areas of the first click surface as the associated planning area, and process the external side image corresponding to the associated planning area through coordinate processing and size adjustment to obtain a standard image, coordinate processing is performed based on the center point of the standard image to determine the corresponding coordinate set, and the corresponding areas in the standard image are batch-intercepted according to the second coordinate set as actual defect images, and the actual defect images obtained by batch processing are associated one-to-one with the external planning areas, thereby obtaining an evaluation model. The embodiment of the present invention improves the update speed of the external appearance data in the box basic model by batch-intercepting the corresponding areas in the standard image as actual defect images, and associating the actual defect images obtained by batch processing with the external planning areas one-to-one, thereby quickly obtaining an evaluation model.

[0020] 3. According to the refrigeration monitoring requirements of the detection end, the present invention obtains the sensor layout information uploaded by the detection end, determines the corner point of the box at the corresponding position as the display endpoint based on the sensor layout information, constructs a first-level function display space at the position of the first evaluation model corresponding to the display endpoint, determines the middle position in the length direction of the first evaluation model, and uses the middle position as a reference to expand the space to both sides to generate a second-level function display space. The multi-level function display space includes a first-level function display space and a second-level function display space. The first-level function corresponding to the display endpoint is obtained to update the first-level function display space, and the corresponding second-level function is obtained according to the summary information of multiple first-level functions. The second-level function display space is updated based on the second-level function to obtain a secondary evaluation model. The present invention displays the functions corresponding to each display endpoint by generating a first-level function display space, and displays the second-level function obtained from the summary information of the first-level function by generating a second-level function display space, thereby updating the refrigeration effect in the first evaluation model, so that users can clearly see the refrigeration effect of the half-high container for sale when viewing the model.

[0021] 4. The present invention can obtain the spatial model parameters of the primary function display space and the secondary function display space, and determine their spatial center points. According to the spatial center points and extreme values, the mutually perpendicular first spatial plane and the second spatial plane are established as the initial spatial display plane. The first spatial plane or the second spatial plane is selected and adjusted according to the user's interactive perspective, and the corresponding primary function and secondary function are added to the adjusted first spatial plane or the second spatial plane. The browsing data of each user for the primary function display space and the secondary function display space is obtained and converted into customized data. When the user views a new box, a customized browsing video of the new box is generated based on these customized data. The present invention can generate customized display angles and display content according to the user's interactive behavior and personalized browsing data, thereby improving the user's interactivity. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a flow chart of a transaction method for a half-high container provided in an embodiment of the present application; Figure 2 It is a schematic diagram of obtaining an evaluation model provided in an embodiment of the present application; Figure 3 It is a schematic diagram of generating a linear function display space and a quadratic function display space provided in an embodiment of the present application; Figure 4 is a schematic diagram of a linear function provided in an embodiment of the present application; Figure 5 It is a structural schematic diagram of a half-high container trading system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0024] It should be noted that, if there is no conflict, the various features in the embodiments of the present invention can be combined with each other, and all are within the protection scope of the present invention. In addition, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flow chart, in some cases, the steps shown or described can be performed in a different order from the module division in the device schematic diagram or the order in the flow chart.

[0025] The terms "first", "second", "third", "fourth", etc. (if any) in the description and claims of the present invention and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in sequences other than those illustrated or described herein.

[0026] It should be understood that in the present invention, "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products or apparatuses.

[0027] Unless otherwise defined, all technical and scientific terms used in this specification have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0028] See also Figure 1 , Figure 1 This is a flow chart of a transaction method for a semi-high container provided in an embodiment of the present application, including steps S1 to S4, which are as follows: S1. Respond to a resale transaction instruction, receive basic characteristics of a box uploaded by a first transaction terminal, retrieve a basic model of a box and a basic value of a box according to the basic characteristics of the box, and send them to the first transaction terminal.

[0029] Among them, the resale transaction instruction refers to the instruction issued by the seller for conducting a second-hand transaction of the container for sale; the first transaction end refers to the terminal device used by the seller, which may be a computer, a smart phone, a tablet computer, etc. The basic characteristics of the container are the basic characteristics or attributes of the half-high container for sale, including but not limited to model, size, material and purchase year, etc.; the basic model of the container refers to the digital model used to describe the corresponding basic characteristics of the half-high container for sale; the basic value of the container refers to the price paid by the seller when initially purchasing the half-high container for sale.

[0030] It is understandable that once the model and purchase year of the semi-high container for sale are determined based on the basic characteristics of the container uploaded by the seller, the size, material and other relevant data of the semi-high container can also be determined based on the model and purchase year.

[0031] In some embodiments, step S1 (responding to the resale transaction instruction, receiving the basic characteristics of the box uploaded by the first transaction terminal, retrieving the basic model of the box and the basic value of the box according to the basic characteristics of the box and sending them to the first transaction terminal) specifically includes steps S11-S13: S11. In response to the resale transaction instruction, a property entry interface is called, and property editing data of the half-high container to be sold is acquired based on the property entry interface.

[0032] Among them, the attribute entry interface represents a user interface for the seller to input the basic characteristics or attributes of the semi-high container; the semi-high container for sale represents the semi-high container that the seller intends to conduct a second-hand transaction; the attribute editing data represents the attribute data of the semi-high container for sale input by the seller on the attribute entry interface, which may be the model and purchase year of the semi-high container for sale.

[0033] S12, identifying the attribute editing data, acquiring basic characteristics of the box, and extracting resale attribute data according to the basic characteristics of the box, wherein the resale attribute data includes a basic model of the box and a basic value of the box.

[0034] The resale attribute data represents basic transaction data of second-hand transactions of the semi-high containers for sale.

[0035] Specifically, the attribute editing data can be identified by using technologies such as text recognition and image processing to obtain the attribute editing data, and then keywords are extracted from the basic features of the box to complete the extraction of the basic features of the box. Technologies such as text recognition, keyword extraction and image processing are well known to those skilled in the art and will not be described in detail. S13: Send the box basic model and the box basic value to the first transaction end.

[0036] It should be noted that a communication connection is established between the server and the first transaction end, and the two can transmit data, send messages and receive responses to each other. The server can receive the basic characteristics of the box sent by the first transaction end, process the basic characteristics of the box, obtain the basic model of the box and the basic value of the box, and send it to the first transaction end.

[0037] S2. Based on the transparent layer, the planning traces of the box basic model by the first transaction end are received, the planning area is determined according to the planning traces, and an evaluation model is obtained based on the actual defect image associated with the planning area and sent to the detection end.

[0038] Among them, see Figure 2 , Figure 2It is a schematic diagram of obtaining an evaluation model provided by an embodiment of the present application, wherein the transparent layer represents a virtual layer or visual effect; the planning trace represents the drawing path when the user marks on the transparent layer; the planning area is a closed area surrounded by the planning trace, that is, a closed area surrounded by the drawing path; the actual defect image represents an actual appearance image containing appearance defects of a half-high container for sale; the primary evaluation model represents a basic model of the box body incorporating appearance defect data; the detection end represents a terminal device used by a third-party staff member, which may be a computer, a smart phone, a tablet computer, etc.

[0039] In some embodiments, step S2 (receiving the planning traces of the first transaction end for the box basic model based on the transparent layer, determining the planning area according to the planning traces, and obtaining an evaluation model based on the planning area and associating the actual defect image to send to the detection end) specifically includes steps S21-S24: S21. Receive click information on the box basic model from the first transaction end, where the click information includes outer side click information and / or inner side click information, and determine the click surface of the box basic model according to the click information.

[0040] Among them, the click information indicates the position and operation of the seller clicking on the surface of the box basic model through the first transaction terminal; the outer surface click information indicates the position and operation of the seller clicking on the outer surface of the box basic model; the inner surface click information indicates the position and operation of the seller clicking on the inner surface of the box basic model; the click surface indicates the specific surface clicked by the seller when performing the click operation on the box basic model.

[0041] The received click information can be analyzed through a data analysis model to determine which side of the box base model the seller clicked. The data analysis model is well known to those skilled in the art and will not be described in detail.

[0042] For example, the basic model of a half-high container for sale has 12 faces, which are numbered with Arabic numerals 1 to 12. The received click information is parsed to obtain the click position and operation of the seller. It is determined that the click is on face numbered 7 in the basic model of the container. Then, face numbered 7 is the clicked face.

[0043] S22: Retrieve a transparent layer corresponding to the click surface and overlay it on the click surface, obtain the user's planned action based on the transparent layer, and identify the planned action to obtain a planning trace.

[0044] The planning action represents the operation data drawn by the user on the transparent layer, and the user represents the seller.

[0045] Specifically, a corresponding transparent layer is retrieved according to the determined click surface and superimposed on the click surface. The seller can draw on the transparent layer, and the user's drawing path is obtained in real time when the seller draws. The drawing path is the planning trace.

[0046] S23. Determine a planning area corresponding to the click surface according to the planning trace, where the planning area includes an internal planning area and / or an external planning area.

[0047] The internal planning area is a closed area surrounded by planning traces on the inner surface; the external planning area is a closed area surrounded by planning traces on the outer surface.

[0048] S24: Based on the actual defect image corresponding to the internal planning area and / or the external planning area, an evaluation model is obtained and sent to the detection end.

[0049] It should be noted that a communication connection is established between the server and the detection end, and the two can transmit data, send messages and receive responses to each other. The server can receive the refrigeration detection requirements sent by the detection end, obtain an evaluation model and send it to the detection end.

[0050] In some embodiments, step S24 (obtaining an evaluation model based on the actual defect image corresponding to the internal planning area and / or the external planning area and sending it to the detection end) specifically includes steps S241-S247: S241. In response to the first transaction terminal selecting information of the internal planning areas one by one, an actual defect image is received and associated with the internal planning areas.

[0051] The one-by-one selection information indicates the selection order, position, size, shape and other attributes of the selected internal planning area.

[0052] Specifically, when the seller selects an internal planning area of ​​the box basic model through the first transaction terminal, the actual defects corresponding to the internal planning area are photographed through the first transaction terminal, the photographed image is cropped and enlarged, the actual defect image is obtained, and the actual defect image is located to the internal planning area through coordinates for association.

[0053] For example: the basic model of the box includes internal planning area A, internal planning area B and internal planning area C. The locations of internal planning area A and internal planning area B are both inner surface No. 3, and the location of internal planning area C is inner surface No. 4. First, it is recognized that the seller selects the internal planning area B of the basic model of the box through the first transaction terminal. At this time, the camera of the first transaction terminal is called to receive the seller's photographed picture of the actual defects corresponding to the internal planning area B on the inner surface No. 3 of the semi-high container to be sold; then it is recognized that the seller selects the internal planning area A, and the camera of the first transaction terminal is called to receive the seller's photographed picture of the actual defects corresponding to the internal planning area A on the inner surface No. 3 of the semi-high container to be sold; finally, it is recognized that the seller selects the internal planning area C, and the camera of the first transaction terminal is called to receive the seller's photographed picture of the actual defects corresponding to the internal planning area C on the inner surface No. 4 of the semi-high container to be sold.

[0054] S242. In response to any selected information of the external planning area by the first transaction terminal, obtain a click surface corresponding to the external planning area as a first click surface, and count all external planning areas of the first click surface as associated planning areas.

[0055] Among them, the any selected information indicates the area position, size, shape and other attributes corresponding to any external planning area of ​​the box basic model when the seller selects the external planning area through the first transaction terminal; the associated planning area indicates the external planning area that needs to be associated later.

[0056] Specifically, the click surface where the external planning area is located is determined according to the area position corresponding to the selected external planning area, the click surface is used as the first click surface, all external planning areas on the first click surface are identified, and these external planning areas are all used as associated planning areas.

[0057] For example, the basic model of the box includes external planning area D, external planning area E and external planning area F, and the locations of the above three external planning areas are all external surface No. 7. When it is identified that the seller selects any one of the external planning area D, external planning area E and external planning area F of the basic model of the box through the first transaction terminal, if the external planning area E is selected, the external surface No. 7 is the first click surface, and the camera of the first transaction terminal is called to receive the seller's photograph of the external surface No. 7 of the semi-high container for sale, and the external planning area D, the external planning area E and the external planning area F are all used as associated planning areas.

[0058] S243. Perform coordinate processing on the first click surface based on the center point of the first click surface to obtain multiple first coordinate sets corresponding to the associated planning area.

[0059] Among them, the center point represents the center position of the first click surface, which is the intersection position of two diagonal lines in the first click surface; the first coordinate set represents the coordinate value set of all points in the associated planning area.

[0060] Specifically, first obtain the intersection of the two diagonals in the first click surface, use the intersection as the center point of the first click surface, establish a coordinate system with the center point as the origin, convert the positions of all points in the first click surface into numerical representations, that is, each point in the first click surface has a unique coordinate value, obtain the coordinate value sets of all points in each associated planning area, and the coordinate value sets of all points corresponding to each associated planning area are used as the first coordinate set. The method of establishing a coordinate system is well known to those skilled in the art and will not be described in detail here.

[0061] Example: The outer surface No. 7 of the box basic model is the first click surface. The outer surface No. 7 includes the external planning area D, the external planning area E and the external planning area F. The intersection position of the two diagonals in the outer surface No. 7 is obtained, and the intersection position is used as the center point of the outer surface No. 7. A coordinate system is established with the center point as the origin, that is, the coordinate value of the center point is (0, 0). The positions of all points in the outer surface No. 7 are converted into numerical representations, and the coordinate value sets of all points in the external planning area D, the external planning area E and the external planning area F are obtained respectively. The coordinate value set of all points in the external planning area D is taken as a first coordinate set, the coordinate value set of all points in the external planning area E is taken as a first coordinate set, and the coordinate value set of all points in the external planning area F is taken as a first coordinate set. A total of 3 first coordinate sets are obtained.

[0062] S244, receiving the external side image corresponding to the click surface uploaded by the first transaction terminal, obtaining the box edge in the external side image, and intercepting the external side image according to the box edge to obtain the box side image.

[0063] Among them, the external side image, that is, the outer surface image, represents the image of the external side of the semi-high container for sale; the box edge represents the contour line of the external side of the semi-high container for sale; and the box side image represents the part of the external side image corresponding to the box side.

[0064] It should be noted that the external side image is the original image taken, which contains background information irrelevant to the side of the box. Therefore, the external side image needs to be processed to remove the irrelevant background information and only retain the partial image corresponding to the side of the box.

[0065] S245. Adjust the size of the box side image according to a preset size corresponding to the first click surface to obtain a standard image.

[0066] Among them, the preset size represents a preset reference size, including but not limited to information such as width and height; the standard image represents a transformed or adjusted side image of the box, whose size and proportion conform to the preset reference size.

[0067] Specifically, the original box side image is scaled, stretched, or transformed according to a preset reference size to achieve size adjustment so that it meets the preset reference size, which may include modifying the width, height, or aspect ratio of the image.

[0068] It should be noted that resizing the box side image can make the box side image have the same size and proportion as the first click surface of the box base model, thereby ensuring consistency and comparability between different images.

[0069] S246: coordinate the standard image based on the center point of the standard image, and determine a corresponding coordinate set in the standard image according to the first coordinate set to obtain a plurality of second coordinate sets.

[0070] Among them, the center point represents the intersection position of two diagonal lines in the standard image, and the intersection position is used as the center point of the standard image. A coordinate system is established with the center point as the origin, and the positions of all points in the standard image are converted into numerical representations, that is, each point in the standard image has a unique coordinate value, and the coordinate values ​​of each point in each first coordinate set are positioned to the standard image, and coordinate value sets corresponding to each first coordinate set are obtained respectively, and each corresponding coordinate value set is used as a second coordinate set. The method of establishing a coordinate system is well known to those skilled in the art and will not be repeated here.

[0071] For example, the outer surface No. 7 of the box basic model is the first click surface, and the outer planning area D, the outer planning area E, and the outer planning area F of the outer surface No. 7 correspond to a first coordinate set respectively. Position the coordinate values ​​of each point in the first coordinate set corresponding to the outer planning area D into the standard image, and obtain the second coordinate set corresponding to the outer planning area D; position the coordinate values ​​of each point in the first coordinate set corresponding to the outer planning area E into the standard image, and obtain the second coordinate set corresponding to the outer planning area E; position the coordinate values ​​of each point in the first coordinate set corresponding to the outer planning area F into the standard image, and obtain the second coordinate set corresponding to the outer planning area F.

[0072] S247. According to the second coordinate set, batch-cut corresponding areas in the standard image as actual defect images, associate the actual defect images with the corresponding external planning areas one by one, obtain an evaluation model and send it to the detection end.

[0073] Among them, batch capture means to extract multiple regions of interest from a standard image at one time and automatically. These regions of interest are corresponding regions, that is, actual defect images. Each corresponding region shows different appearance defects, such as protrusions, depressions, scratches, etc.

[0074] According to the second coordinate set, it can be determined which areas of the standard image are related to the external planning area, and these corresponding areas are cropped and enlarged, and associated with the external planning area. The user can view the corresponding actual defect image by clicking on the external planning area.

[0075] In an embodiment of the present application, the corresponding click surface can be obtained according to the external planning area information selected by the first transaction terminal, and the click surface can be used as the first click surface. All external planning areas of the first click surface are counted as associated planning areas. The external side images corresponding to the associated planning areas are processed through coordinate processing and size adjustment to obtain a standard image. Coordinate processing is performed based on the center point of the standard image to determine the corresponding coordinate set. The corresponding areas in the standard image are batch-intercepted according to the second coordinate set as actual defect images. The actual defect images obtained by batch processing are associated one-to-one with the external planning areas, thereby obtaining an evaluation model. The embodiment of the present invention improves the update speed of the external appearance data in the box basic model by batch-intercepting the corresponding areas in the standard image as actual defect images, and associating the actual defect images obtained by batch processing with the external planning areas one-to-one, thereby quickly obtaining an evaluation model.

[0076] Step S3: According to the refrigeration detection requirements of the detection end, the primary evaluation model is divided based on the cabinet endpoints to obtain a multi-level function display space, and a multi-level function is obtained to customize and update the multi-level function display space to obtain a secondary evaluation model.

[0077] Among them, the refrigeration detection demand represents a request triggered by a third-party staff through the detection terminal to conduct a refrigeration performance test on the half-high container for sale; the box endpoint represents all vertices of the half-high container for sale, and the number can be specifically 8; the multi-level function display space represents a visualization area for describing the refrigeration performance with a function; the multi-level function represents a trend of the test temperature over time; the secondary evaluation model represents a basic box model that incorporates appearance defect data and refrigeration performance test data.

[0078] In some embodiments, step S3 (according to the refrigeration detection requirements of the detection end, dividing the primary evaluation model based on the cabinet endpoints to obtain a multi-level function display space, obtaining a multi-level function to customize and update the multi-level function display space, and obtaining a secondary evaluation model) specifically includes steps S31-S33: S31. According to the refrigeration monitoring requirements of the detection end, the sensor layout information uploaded by the detection end is obtained, and based on the sensor layout information, the cabinet corner point at the corresponding position is determined as the display endpoint, and a first-level function display space is constructed at the position of the first evaluation model corresponding to the display endpoint.

[0079] The sensor layout information indicates the specific location information of all temperature sensors on the half-high container for sale; the box corner points indicate the eight vertices of the half-high container for sale; the display endpoints indicate specific location points used to construct a multi-level function display space; the first-level function display space refers to the visualization area generated by the function that describes the fluctuation of vertex temperature over time. Specifically, see Figure 3 , Figure 3 Schematic diagram of generating a linear function display space and a quadratic function display space provided by an embodiment of the present application. In order to implement a refrigeration performance test on a half-high container for sale, a temperature sensor may be set at each of the eight vertices of the half-high container for sale in advance, for a total of eight temperature sensors, which may be patch-type temperature sensors. The installation of the temperature sensors may be completed by a third-party staff member. When the third-party staff member performs a refrigeration performance test on the half-high container for sale, the patch-type temperature sensors are attached to the eight vertices of the half-high container for sale in advance, and removed in time after the test is completed.

[0080] S32, determining the middle position of the primary evaluation model in the length direction, and using the middle position as a reference to perform spatial expansion to both sides to generate a secondary function display space, wherein the multi-level function display space includes a primary function display space and a secondary function display space.

[0081] The middle position in the length direction represents the model center point of an evaluation model; and the secondary function display space refers to a visualization area generated by a function that describes the fluctuation of the endpoint average temperature with the test time.

[0082] S33, obtaining the primary function corresponding to the display endpoint to update the primary function display space, obtaining the corresponding secondary function according to the summary information of multiple primary functions, updating the secondary function display space based on the secondary function, and obtaining a secondary evaluation model.

[0083] Among them, the first-level function represents the function of endpoint temperature fluctuation with test time; the second-level function represents the function of endpoint average temperature fluctuation with test time, and the secondary evaluation model represents an evaluation model after the first-level function display space and the second-level function display space are updated.

[0084] In some embodiments, step S33 (obtaining the primary function corresponding to the display endpoint to update the primary function display space, obtaining the corresponding secondary function according to the summary information of multiple primary functions, and updating the secondary function display space based on the secondary function to obtain the secondary evaluation model) specifically includes steps S331-S332: S331, receiving temperature fluctuation data acquired by each sensor, generating a primary function corresponding to each display endpoint based on the temperature fluctuation data, and updating the corresponding primary function display space according to the primary function.

[0085] The temperature fluctuation data represent the change data of the endpoint temperature acquired by each temperature sensor over the test time.

[0086] Specifically, the endpoint temperature obtained by the receiving temperature sensor at each test time is obtained, and the corresponding relationship between the test time and the endpoint temperature is obtained. Taking the display endpoint as the origin, according to the corresponding relationship between the test time and the endpoint temperature, a linear function is established with the test time as the horizontal axis value and the endpoint temperature as the vertical axis value, so as to update the first-level function display space corresponding to each display endpoint.

[0087] S332. Taking the moment of each of the first-level functions as a reference, perform temperature mean processing on the multiple first-level functions to obtain summary information corresponding to each moment, generate a corresponding second-level function according to the summary information, update the second-level function display space based on the second-level function, and obtain a secondary evaluation model.

[0088] The summary information represents the temperatures acquired by multiple temperature sensors.

[0089] Specifically, the average value of multiple endpoint temperatures obtained at the same test time is obtained, and the obtained temperature is the average endpoint temperature corresponding to the test time. The average endpoint temperature corresponding to each test time is obtained, and the corresponding relationship between the test time and the average endpoint temperature is obtained. The secondary function is established with the middle position as the origin, the test time point as the horizontal axis value, and the average endpoint temperature as the vertical axis value. The secondary function display space corresponding to the middle position is updated.

[0090] In the embodiment of the present application, the present invention obtains the sensor layout information uploaded by the detection end according to the refrigeration monitoring requirements of the detection end, determines the corner point of the box at the corresponding position as the display endpoint based on the sensor layout information, constructs a first-level function display space at the position of the first evaluation model corresponding to the display endpoint, determines the middle position in the length direction of the first evaluation model, and uses the middle position as a reference to expand the space to both sides to generate a second-level function display space, the multi-level function display space includes a first-level function display space and a second-level function display space, obtains the first-level function corresponding to the display endpoint to update the first-level function display space, obtains the corresponding second-level function according to the summary information of multiple first-level functions, updates the second-level function display space based on the second-level function, and obtains a second-level evaluation model. The present invention displays the functions corresponding to each display endpoint by generating a first-level function display space, and displays the second-level function obtained from the summary information of the first-level function by generating a second-level function display space, thereby updating the refrigeration effect in the first evaluation model, so that the user can clearly see the refrigeration effect of the half-high container for sale when viewing the model.

[0091] The transaction method of the semi-high container further includes: The spatial model parameters of the primary function display space and the secondary function display space are obtained, and the spatial center points of the primary function display space and the secondary function display space are determined.

[0092] Among them, the spatial model parameters represent the interval values ​​corresponding to the x-axis, y-axis, and z-axis in the primary function display space and the secondary function display space; the spatial center point represents the center position of the space.

[0093] It should be noted that both the first-level function display space and the second-level function display space are three-dimensional spaces, including x-axis, y-axis and z-axis. For the first-level function display space and the second-level function display space, the interval values ​​in the x-axis, y-axis and z-axis directions are obtained respectively. Based on the interval values, the midpoint values ​​in the x-axis, y-axis and z-axis directions can be obtained respectively. The midpoint values ​​in the x-axis, y-axis and z-axis directions are combined to form the coordinates of the center point of the space, such as: the midpoint value of the x-axis is (minimum value of the interval value + maximum value of the interval value) / 2 in the x-axis direction.

[0094] A corresponding initial spatial display surface is established with the spatial center point as the center and the extreme values ​​of the spatial model parameters as the boundaries, and the initial spatial display surface includes a first spatial surface and a second spatial surface that are perpendicular to each other.

[0095] Among them, the extreme values ​​represent the maximum and minimum values ​​of the interval values ​​in the x-axis, y-axis and z-axis directions; the initial display surface of the space represents the central surface of each display space (primary function display space, secondary function display space); the first space surface represents the display surface in the horizontal direction; and the second space surface represents the display surface in the vertical direction.

[0096] It should be noted that the initial display surface is constructed with the center point of the space as the center, and the extreme values ​​of the space model parameters determine the horizontal and vertical ranges of the display surface. The initial display surface of the space established with the center point of the space as the center and the extreme values ​​of the space model parameters as the boundaries includes a first space surface and a second space surface that are perpendicular to each other. The first space surface and the second space surface can be called when the function needs to be displayed.

[0097] The first spatial surface or the second spatial surface is selected according to the user's interactive perspective, and the angle of the first spatial surface or the second spatial surface is adjusted, and the corresponding primary function or secondary function is added to the selected and adjusted first spatial surface or the second spatial surface.

[0098] The interactive perspective represents the angle and perspective taken by the user when viewing the evaluation model.

[0099] Although the function and the evaluation model are separate entities, the function can be loaded onto the corresponding spatial surface for display. When the user is viewing the evaluation model, he can see the function image associated with it, and can more intuitively understand the data changes in the evaluation model. The function display can be dynamically adjusted to ensure that it keeps pace with the changes in the evaluation model. The spatial surface displaying the function image is always consistent with the user's interaction angle, that is, the spatial surface displaying the function image is always facing the user.

[0100] Obtain each user's browsing data for the primary function display space and the secondary function display space to generate customized data. After determining that the user chooses to view a new box, generate a customized browsing video of the new box based on the customized data, so that the user can view the primary function display space and the secondary function display space based on the customized browsing video.

[0101] Among them, the browsing data refers to the data records generated when the user views the evaluation model; the customized data refers to the personalized needs and preference data of the user obtained based on the browsing data; the customized browsing video refers to the personalized video content generated based on the customized data, and these videos usually contain relevant information about the half-high containers for sale that the user is most interested in.

[0102] Different users' demands for semi-high containers vary depending on factors such as the industry they are in, the type of goods, and the mode of transportation. Therefore, the data generated when browsing the relevant information of semi-high containers for sale will also be different. Based on these different browsing data, personalized information such as user preferences, needs, and habits can be obtained, and customized data can be generated. Personalized video content is created based on these customized data to meet the personalized needs of different users.

[0103] Specifically, the first spatial surface or the second spatial surface is selected according to the user's interactive perspective, the angle of the first spatial surface or the second spatial surface is adjusted, and the corresponding primary function or secondary function is added to the selected and adjusted first spatial surface or the second spatial surface, which specifically includes the following steps: An initial interactive viewing angle of the user is determined, and one of a first spatial plane or a second spatial plane is determined based on the interactive viewing angle, wherein the interactive viewing angle in each direction has a preset first spatial plane or a preset second spatial plane.

[0104] The initial interaction perspective refers to the angle and perspective taken by the user when he or she first starts to view the evaluation model.

[0105] It should be noted that when viewing the evaluation model, the user may be looking straight ahead, looking down, or at other angles. The content viewed at different angles is different. According to the user's perspective and operation position, it can be determined which spatial surface of the first spatial surface or the second spatial surface is convenient for display and angle adjustment. The determined spatial surface is the selected spatial surface, that is, the spatial surface where the function will be displayed. Each interactive perspective in each direction has a preset first spatial surface or second spatial surface, which means that no matter what the user's interactive perspective is, there is a corresponding spatial surface that can be determined and selected.

[0106] The first-level function and the second-level function of each first-level function display space and the second-level function display space are displayed on the corresponding first space surface or the second space surface respectively.

[0107] That is, the corresponding functions in each primary function display space and secondary function display space are respectively displayed on the corresponding first space surface or second space surface.

[0108] If it is determined that the corresponding user has adjusted the angle, the primary function and the secondary function will no longer be displayed, and the first spatial surface or the second spatial surface will be adjusted with the angle based on the value of the angle adjustment, and the primary function and the secondary function will be displayed again after the angle adjustment.

[0109] Among them, the angle adjustment represents adjusting the display perspective of the spatial surface. The value of the angle adjustment is usually determined based on the user's interactive operations. When the user makes an angle adjustment, the corresponding operations are captured, such as dragging the mouse, sliding the touch screen, etc. These operations will generate a value representing the user's angle change in the horizontal and vertical directions. The angle change is the value of the angle adjustment; making a concomitant angle adjustment means that when the user changes the interaction angle, the system will automatically adjust the display method of the function graph to keep it consistent with the user's current interactive perspective.

[0110] Specifically, when a user views the evaluation model, the user's interaction actions are obtained, and whether the corresponding user needs to adjust the display angle is determined based on the interaction actions. If the display angle needs to be adjusted, the display of the first-level function and the second-level function is temporarily stopped, and the angle change amount is determined based on the interaction action. According to the angle change amount, the selected spatial surface is rotated around the center point of the space to change its display angle in the display space until the user is facing the spatial surface, and the corresponding first-level function or second-level function is added to the selected adjusted first spatial surface or second spatial surface.

[0111] After determining that the angle adjustment reaches a threshold, the first spatial surface or the second spatial surface is switched, and the corresponding primary function or secondary function is added to the selected adjusted first spatial surface or the second spatial surface.

[0112] The threshold value represents the critical point reached by the user in changing the display angle.

[0113] Specifically, if it is determined that the angle adjustment reaches a threshold, the system will switch to another spatial plane to display the corresponding function graph at a new angle.

[0114] In this embodiment, although the function and the evaluation model are in a separate state, the function can be loaded and displayed on the corresponding spatial plane, and the display angle of the function can be dynamically adjusted along with the operation of the evaluation model, so that users can more easily and intuitively view the changing trend of the function in the display space.

[0115] In some embodiments, the step of acquiring browsing data of each user on the primary function display space and the secondary function display space to generate customized data, and after determining that the user chooses to view a new cabinet, generating a customized browsing video of the new cabinet based on the customized data, so that the user can view the primary function display space and the secondary function display space based on the customized browsing video, includes: Obtain the first spatial surface or the second spatial surface corresponding to the primary function display space and the secondary function display space of each box with a historical number of views by each user, and obtain the dwelling time of each first spatial surface or the second spatial surface.

[0116] The viewed history quantity indicates the number of half-high containers for sale viewed by the user in the past period of time, which can be selected according to actual conditions; the dwell time indicates the length of time the user stays on each first spatial surface or second spatial surface when viewing the container.

[0117] Specifically, the browsing data records the number of boxes that each user has viewed historically, and the first spatial surface or the second spatial surface of the primary function display space and the secondary function display space corresponding to each box can be obtained, and the user's stay time on each first spatial surface or the second spatial surface can be obtained.

[0118] For example, a user has viewed 100 boxes in the past. The amount of data to be processed is large. The 10 boxes viewed recently can be obtained for analysis, and the number of historical views is 10. Obtain the first-level function display space corresponding to these 10 boxes and the first and second spatial surfaces corresponding to the second-level function display space, determine which spatial surfaces the user has browsed in these 10 boxes, and obtain the time the user has stayed in each browsed space.

[0119] The order of the first spatial surface or the second spatial surface corresponding to each box in the viewing history of each user is obtained, and a corresponding sequence angle node path is generated based on the order and angle of the first spatial surface or the second spatial surface.

[0120] Among them, the viewing history includes the boxes that the user has browsed before; the order represents the order in which the user views different spatial surfaces or adjusts angles, that is, the order of the views or adjusted angles that the user views in sequence during the browsing process; the sequential angle node path represents the path obtained by associating each spatial surface or angle passed by the user during the viewing process.

[0121] It should be noted that the browsing order of the user when viewing different spatial surfaces (such as the front view, side view, and top view) of each box is obtained based on the user's viewing history. For each spatial surface, the user may view it from different angles, such as switching from the front view to the side view or the top view, and may adjust the angle during the viewing process. The system generates a corresponding sequential angle node path based on the user's viewing order and angle adjustment record to reflect the user's browsing behavior.

[0122] The boxes are sorted based on the viewing time of each box of the historical number, and the dwelling weight of each dwelling time is generated based on the sorting. Each sequence has a preset dwelling weight, and the viewing time corresponding to the dwelling weight gradually increases from far to near.

[0123] The viewing time indicates the specific time point when the user views each box; the dwell weight indicates the weight value generated for each box for measuring the degree of attention; and corresponding dwell weights are pre-set for different viewing orders.

[0124] Specifically, the specific time points when the user views each box are sorted from far to near or from near to far. After sorting, the corresponding dwell weight can be determined according to the sorting order. The closer the specific time point of viewing the box is, the greater the dwell weight. For example, the dwell weight of the box viewed by the user today is greater than the dwell weight of the box viewed yesterday.

[0125] Based on the sequential angle node path, dwell time, and dwell weight, corresponding automatic data extraction is performed on the new box to generate a customized browsing video of the new box.

[0126] By parsing, filtering, converting and processing the data, the relevant parameters and information required for generating customized browsing videos are obtained, and customized browsing videos of new cabinets are generated based on this information.

[0127] In some embodiments, the automatic data extraction of the new cabinet based on the sequential angle node path and the dwell time to generate a customized browsing video of the new cabinet specifically includes the following steps: The number of sequential angle nodes in the sequential angle node path is obtained, and based on the comparison between the number and a preset number, a corresponding dwell time offset value is generated.

[0128] Among them, the preset number is a pre-set reference value for comparison and calculation with the number of sequential angle nodes; the dwell time offset value represents the adjustment amount of the dwell time of each sequential angle node determined according to the comparison result of the number of sequential angle nodes and the preset number.

[0129] It should be noted that the number of sequential angle nodes determines the number of angles displayed by the evaluation model when generating customized browsing videos. If the number of sequential angle nodes is large, it means that the evaluation model will display the box at more angles, so the dwell time at each angle will be reduced accordingly to ensure that the length of the entire customized video is moderate and not too long, so that users can quickly understand the situation at each angle within a limited time. On the contrary, if the number of sequential angle nodes is relatively small, it means that the evaluation model will more concentratedly display several important faces of each box, so that the dwell time of each face can be relatively long, allowing users to have more time to carefully observe the details of each face, so as to have a deeper understanding of the characteristics and status of the box.

[0130] The dwell time offset is processed based on the dwell time offset value to obtain the browsing sub-time of each sequential angle node in the sequential angle node path.

[0131] The browsing sub-time indicates the browsing time corresponding to each angle when browsing a certain surface. For example, the browsing time corresponding to viewing the front view of nearly 10 boxes, and the browsing time corresponding to viewing the front view of nearly 10 boxes with an offset of 30 degrees.

[0132] The browsing time of each sequential angle node is calculated by the following formula, , in, For the The first spatial surface or the second spatial surface is in the Browsing time from each angle, The box viewed for history is in The first spatial surface or the second spatial surface is in the The dwell time at each angle, The box viewed for history is in The first spatial surface or the second spatial surface is in the The stop weight of the angle, The upper limit value of the box viewed in history. The number of boxes viewed in history. is a constant value, is the number of sequential angle node paths, is the preset quantity, is the quantity weight value.

[0133] S4. Retrieve the comprehensive evaluation model to evaluate the secondary evaluation model to obtain an evaluation coefficient, adjust the basic value of the box according to the evaluation coefficient to obtain a recommended box value, and update the secondary evaluation model based on the recommended box value to obtain a comprehensive recommendation model.

[0134] Among them, the comprehensive evaluation model represents a model that comprehensively considers multiple factors, and the multiple factors may specifically be appearance defects and refrigeration performance; the evaluation coefficient represents a set of numerical values ​​in the evaluation process, which is used to indicate the importance of a certain attribute or feature; the recommended value of the cabinet is an estimated price obtained by adjusting the basic value of the cabinet according to the refrigeration performance and appearance defects; the comprehensive recommendation model is a combined model of the evaluation methods integrating appearance defects and refrigeration effects, which is used to comprehensively consider the appearance defects and refrigeration effects of the semi-high containers for sale, provide recommended data to users, and assist users in formulating transaction data.

[0135] In some embodiments, step S4 (calling the comprehensive evaluation model to evaluate the secondary evaluation model to obtain an evaluation coefficient, and adjusting the basic value of the box according to the evaluation coefficient to obtain the recommended value of the box) specifically includes steps S41-S44: S41. Retrieve the comprehensive evaluation model to obtain the fluctuation start data and fluctuation end data of the first-level function, determine the test fluctuation slope according to the fluctuation start data and fluctuation end data, and obtain the test fluctuation limit according to the fluctuation end data.

[0136] Among them, the fluctuation start data represents the position coordinates corresponding to the starting point of the curve in the primary function image; the fluctuation end data represents the position coordinates corresponding to the ending point of the curve in the primary function image; the test fluctuation slope represents the rate or trend of temperature change during the fluctuation period, which shows the refrigeration speed of the half-high container for sale; the vertical axis value in the position coordinates corresponding to the ending point of the curve in the primary function image is the test fluctuation limit, and the test fluctuation limit represents the lowest temperature that the half-high container for sale can reach when conducting a refrigeration performance test.

[0137] Example: See Figure 4 , Figure 4 It is a schematic diagram of a first-level function provided in an embodiment of the present application. O is the origin of the coordinates, the horizontal coordinate x represents time, and the unit can be specifically minutes (min), and the vertical coordinate y represents the endpoint temperature, and the unit can be specifically degrees Celsius (℃). Point A is the starting point of the curve in the first-level function image, that is, the position coordinate of point A is the fluctuation start data, point B is the end point of the curve in the first-level function, that is, the position coordinate of point B is the fluctuation end data, and the slope corresponding to the straight line connecting point A and point B is the test fluctuation slope, and the vertical axis value -30℃ corresponding to point B is the test fluctuation limit.

[0138] S42. Obtain a first-level preset function corresponding to the first-level function, and determine a standard fluctuation slope according to the fluctuation start data and fluctuation end data of the first-level preset function.

[0139] Among them, the first-level preset function represents the ideal expected function of the temperature change over time corresponding to the semi-high container for sale, which can be specifically obtained based on the factory test data; the fluctuation start data corresponding to the first-level preset function is the starting point of the curve in the function image, and the fluctuation end data corresponding to the first-level function represents the end point of the curve in the function image; the standard fluctuation slope represents the standard refrigeration speed of temperature change over time.

[0140] S43. When the test fluctuation limit reaches a preset standard fluctuation limit, obtain the ratio information of the test fluctuation slope and the standard fluctuation slope, and obtain the effect evaluation coefficient according to the ratio information.

[0141] Among them, the standard fluctuation limit is the lowest temperature that can be reached in the refrigeration performance test of the half-high container for sale when it leaves the factory; the ratio information represents the relative relationship between the test fluctuation slope and the standard fluctuation slope, and shows the difference between the test fluctuation slope and the standard fluctuation slope; the effect evaluation coefficient reflects the degree of conformity between the actual temperature fluctuation and the expected fluctuation.

[0142] Specifically, the vertical axis value in the position coordinate corresponding to the end point of the curve in the first-level preset function graph is obtained as the preset standard fluctuation limit. When the test fluctuation limit does not reach the preset standard fluctuation limit, it means that the refrigeration performance of the semi-high container for sale is greatly reduced compared with that at the time of leaving the factory, and a higher effect evaluation coefficient will be given. When the test fluctuation limit reaches the preset standard fluctuation limit, it means that the minimum refrigeration temperature of the semi-high container for sale during the test can reach the minimum refrigeration temperature at the time of leaving the factory. At this time, the refrigeration speed needs to be compared, so the ratio information of the test fluctuation slope and the standard fluctuation slope is obtained, and the effect evaluation coefficient is obtained according to the ratio information.

[0143] S44. Calculate the basic value of the box based on the effect evaluation coefficient to obtain a first-level effect reduction associated with the first-level function, obtain a second-level effect reduction based on the sum of multiple first-level effect reductions, and associate the second-level effect reduction with the second-level function.

[0144] Among them, the first-level effect reduction represents the price reduction adjustment of the basic value of the semi-high container for sale according to the effect evaluation coefficient, and the second-level effect reduction represents the comprehensive price reduction adjustment obtained by integrating the price reduction adjustments corresponding to multiple first-level effect reductions.

[0145] For example: the basic value of the box is calculated based on the effect evaluation coefficient of each display endpoint, and the first-level effect reduction associated with the first-level function is 500 yuan. The first-level effect reduction corresponding to 2 of the 8 display endpoints is 200 yuan, and the first-level effect reduction corresponding to one display endpoint is 500 yuan, then the second-level effect reduction is 900 yuan. The second-level effect reduction is associated with the second-level function, so that the user can view the data corresponding to the second-level effect reduction when viewing the secondary evaluation model.

[0146] In some embodiments, step S4 (calling the comprehensive evaluation model to evaluate the secondary evaluation model to obtain an evaluation coefficient, and adjusting the basic value of the box according to the evaluation coefficient to obtain the recommended value of the box) specifically includes steps S45-S48: S45, calling up a comprehensive evaluation model to perform type analysis on the actual defect image to obtain the defect type of the actual defect image.

[0147] The comprehensive evaluation model is retrieved to perform type analysis on the actual defect image to obtain the defect type, which includes protrusions, depressions, scratches, etc.

[0148] S46, extracting the defect contour in the actual defect image, obtaining the defect area of ​​the defect contour, and obtaining a defect assessment coefficient according to the ratio of the defect area to the area normalization value.

[0149] Among them, the defect contour represents the boundary line of the defect area in the actual defect image; the defect area represents the total area of ​​the area surrounded by the defect contour, usually expressed in pixels or other appropriate units; the area normalization value represents the required data for normalizing the acquired defect area; the ratio of the defect area and the area normalization value is the value obtained after normalizing the defect area; the defect assessment coefficient represents an indicator used to assess the severity of appearance defects.

[0150] S47, calling up a preset correspondence table corresponding to the defect type, determining the defect reduction corresponding to the defect assessment coefficient according to the preset correspondence table, and associating the defect reduction with the planning area one by one, wherein the preset correspondence table includes a correspondence between coefficient intervals and defect reduction.

[0151] Among them, the preset correspondence table represents a pre-set comparison table that describes the correspondence between coefficient intervals and defect reductions; the defect reduction represents a price reduction adjustment determined according to the severity of the appearance defect.

[0152] The defect reduction is associated with the planning areas one by one, so that when the user views the comprehensive recommendation model, he can see how much the price of each planning area corresponds to.

[0153] For example: the location of the inner planning area C is inner surface No. 4, and the outer surface No. 7 includes the outer planning area D, the outer planning area E and the outer planning area F. When the user clicks on the inner surface No. 4, the inner planning area C is highlighted and the prompt "convex, price reduction of 200 yuan" is displayed. When the user clicks on the outer surface No. 7, the outer planning areas D, the outer planning areas E and the outer planning areas F are highlighted. When the outer planning area D is clicked, the prompt "convex, price reduction of 300 yuan" is displayed. When the outer planning area E is clicked, the prompt "concave, price reduction of 200 yuan" is displayed. When the outer planning area F is clicked, the prompt "scratches, price reduction of 100 yuan" is displayed.

[0154] S48. Obtain a total defect reduction according to the sum of the defect reductions, and reduce and adjust the basic value of the box based on the secondary effect reduction and the total defect reduction to obtain a recommended box value.

[0155] Among them, the total reduction in defects represents the sum of the reduction in defects corresponding to each planning area; the recommended value of the container represents the recommended price obtained after evaluating the appearance defects and refrigeration effect of the half-high container for sale.

[0156] In an embodiment of the present invention, the basic model and basic value of the semi-high container for sale can be determined based on the basic features of the container uploaded by the user, the appearance data of the basic model of the container can be updated to obtain a primary evaluation model, and the data corresponding to the refrigeration effect of the primary evaluation model can be updated to obtain a secondary evaluation model, and finally the secondary evaluation model can be evaluated to obtain an evaluation coefficient, and the basic value of the container can be adjusted based on the evaluation coefficient to obtain a recommended value of the container, and the secondary evaluation model can be updated based on the recommended value of the container to obtain a comprehensive recommendation model. The embodiment of the present invention performs automatic analysis based on the semi-high container data uploaded by the user, thereby generating recommended data, and assisting the user in formulating transaction data based on the recommended data.

[0157] See also Figure 5 , Figure 5 : is a structural schematic diagram of a half-high container trading system provided in an embodiment of the present application, the system comprising: The feature acquisition module is used to respond to the resale transaction instruction, receive the basic features of the box uploaded by the first transaction end, retrieve the basic model of the box and the basic value of the box according to the basic features of the box, and send them to the first transaction end.

[0158] The area association module is used to receive the planning traces of the first transaction end for the box basic model based on the transparent layer, determine the planning area according to the planning traces, and obtain an evaluation model based on the actual defect image associated with the planning area and send it to the detection end.

[0159] The customized update module is used to divide the primary evaluation model based on the cabinet endpoints to obtain a multi-level function display space according to the refrigeration detection requirements of the detection end, obtain the multi-level function to customize and update the multi-level function display space, and obtain a secondary evaluation model.

[0160] The model generation module is used to call the comprehensive evaluation model to evaluate the secondary evaluation model to obtain the evaluation coefficient, adjust the basic value of the box according to the evaluation coefficient to obtain the recommended value of the box, and update the secondary evaluation model based on the recommended value of the box to obtain the comprehensive recommendation model.

[0161] It should be noted that the above-mentioned half-high container trading system can execute the half-high container trading method provided in the embodiment of the present invention. For technical details and beneficial effects that are not fully described in the embodiment of the half-high container trading system, refer to the half-high container trading method provided in the embodiment of the present invention.

[0162] Through the description of the above embodiments, it can be clearly understood by those skilled in the art that each embodiment can be implemented by means of software plus a general hardware platform, or by hardware. It can be understood by those skilled in the art that all or part of the processes in the above embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0163] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A transaction method for a half-high container, characterized in that: include: In response to the resale transaction instruction, receiving the basic characteristics of the box uploaded by the first transaction terminal, retrieving the basic model of the box and the basic value of the box according to the basic characteristics of the box, and sending them to the first transaction terminal; Receiving the planning traces of the box basic model by the first transaction end based on the transparent layer, determining the planning area according to the planning traces, and obtaining an evaluation model based on associating the planning area with the actual defect image and sending it to the detection end; According to the refrigeration detection requirements of the detection end, the primary evaluation model is divided based on the cabinet endpoints to obtain a multi-level function display space, and a multi-level function is obtained to customize and update the multi-level function display space to obtain a secondary evaluation model; The comprehensive evaluation model is retrieved to evaluate the secondary evaluation model to obtain an evaluation coefficient, the basic value of the box is adjusted according to the evaluation coefficient to obtain a recommended box value, and the secondary evaluation model is updated based on the recommended box value to obtain a comprehensive recommendation model.

2. The transaction method of a semi-high container according to claim 1, characterized in that: The responding to the resale transaction instruction, receiving the basic characteristics of the box uploaded by the first transaction terminal, retrieving the basic model of the box and the basic value of the box according to the basic characteristics of the box and sending them to the first transaction terminal, includes: In response to the resale transaction instruction, calling the attribute entry interface, and acquiring attribute editing data of the half-high container for sale based on the attribute entry interface; Identify the attribute editing data, obtain basic characteristics of the box, and extract resale attribute data according to the basic characteristics of the box, wherein the resale attribute data includes a basic model of the box and a basic value of the box; The box basic model and the box basic value are sent to the first transaction end.

3. The transaction method of a semi-high container according to claim 2, characterized in that: The method of receiving the planning traces of the box basic model by the first transaction end based on the transparent layer, determining the planning area according to the planning traces, and obtaining an evaluation model based on associating the planning area with the actual defect image and sending it to the detection end includes: receiving click information of the first transaction terminal on the box body basic model, the click information including outer side surface click information and / or inner side surface click information, and determining the click surface of the box body basic model according to the click information; Retrieving a transparent layer corresponding to the click surface and superimposing it on the click surface, obtaining a user's planned action based on the transparent layer, and identifying the planned action to obtain a planning trace; Determine a planning area corresponding to the click surface according to the planning trace, wherein the planning area includes an internal planning area and / or an external planning area; Based on the actual defect image corresponding to the internal planning area and / or the external planning area, an evaluation model is obtained and sent to the detection end.

4. The transaction method of a semi-high container according to claim 3 is characterized in that: The step of obtaining an evaluation model based on the actual defect image corresponding to the internal planning area and / or the external planning area and sending the evaluation model to the detection end includes: In response to the first transaction terminal selecting information of the internal planning areas one by one, receiving the actual defect image and establishing association with the internal planning areas; In response to any selected information of the external planning area by the first transaction terminal, obtaining a click surface corresponding to the external planning area as a first click surface, and counting all external planning areas of the first click surface as associated planning areas; Performing coordinate processing on the first click surface based on the center point of the first click surface to obtain a plurality of first coordinate sets corresponding to the associated planning area; Receiving the external side image corresponding to the click surface uploaded by the first transaction terminal, obtaining the box edge in the external side image, and intercepting the external side image according to the box edge to obtain the box side image; Adjust the size of the box side image according to the preset size corresponding to the first click surface to obtain a standard image; Performing coordinate processing on the standard image based on the center point of the standard image, and determining a corresponding coordinate set in the standard image according to the first coordinate set to obtain a plurality of second coordinate sets; According to the second coordinate set, the corresponding areas in the standard image are batch-cut out as actual defect images, the actual defect images are associated one-to-one with the corresponding external planning areas, and an evaluation model is obtained and sent to the detection end.

5. The transaction method of a semi-high container according to claim 1, characterized in that: According to the refrigeration detection requirements of the detection end, the primary evaluation model is divided based on the cabinet endpoints to obtain a multi-level function display space, and a multi-level function is obtained to customize and update the multi-level function display space to obtain a secondary evaluation model, including: According to the refrigeration monitoring requirements of the detection end, the sensor layout information uploaded by the detection end is obtained, the cabinet corner point at the corresponding position is determined as the display endpoint based on the sensor layout information, and a first-level function display space is constructed at the position of the first evaluation model corresponding to the display endpoint; Determine the middle position of the primary evaluation model in the length direction, and use the middle position as a reference to perform spatial expansion on both sides to generate a secondary function display space, wherein the multi-level function display space includes a primary function display space and a secondary function display space; The first-level function corresponding to the display endpoint is obtained to update the first-level function display space, the corresponding second-level function is obtained according to the summary information of multiple first-level functions, the second-level function display space is updated based on the second-level function, and a secondary evaluation model is obtained.

6. The transaction method of a semi-high container according to claim 5, characterized in that: Acquire the primary function corresponding to the display endpoint to update the primary function display space, obtain the corresponding secondary function according to the summary information of multiple primary functions, update the secondary function display space based on the secondary function, and obtain the secondary evaluation model, including: receiving temperature fluctuation data acquired by each sensor, generating a primary function corresponding to each display endpoint based on the temperature fluctuation data, and updating the corresponding primary function display space according to the primary function; Taking the moment of each first-level function as a benchmark, multiple first-level functions are subjected to temperature mean processing to obtain summary information corresponding to each moment, and corresponding second-level functions are generated according to the summary information. Based on the second-level functions, the second-level function display space is updated to obtain a secondary evaluation model.

7. The transaction method of a semi-high container according to claim 6, characterized in that: Also includes: Acquire the space model parameters of the primary function display space and the secondary function display space, and determine the space center points of the primary function display space and the secondary function display space; Establishing a corresponding initial spatial display surface based on the spatial center point as the center and the extreme value of the spatial model parameter as the boundary, wherein the initial spatial display surface includes a first spatial surface and a second spatial surface that are perpendicular to each other; Selecting the first spatial surface or the second spatial surface according to the user's interactive perspective, adjusting the angle of the first spatial surface or the second spatial surface, and adding the corresponding primary function or secondary function to the selected and adjusted first spatial surface or the second spatial surface; Obtain each user's browsing data on the primary function display space and the secondary function display space to generate customized data. After determining that the user chooses to view a new box, generate a customized browsing video of the new box based on the customized data, so that the user can view the primary function display space and the secondary function display space based on the customized browsing video.

8. The transaction method of a semi-high container according to claim 7, characterized in that: The interacting with the user to select the first spatial surface or the second spatial surface according to the user's viewing angle, and adjusting the angle of the first spatial surface or the second spatial surface, and adding the corresponding primary function or secondary function to the selected and adjusted first spatial surface or the second spatial surface, includes: Determine an initial interactive viewing angle of the user, and determine one of a first spatial plane or a second spatial plane based on the interactive viewing angle, wherein the interactive viewing angle in each direction has a preset first spatial plane or a preset second spatial plane; Display the first-level function and the second-level function of each first-level function display space and the second-level function display space on the corresponding first space surface or the second space surface respectively; If it is determined that the corresponding user adjusts the angle, the primary function and the secondary function are no longer displayed, and the first spatial surface or the second spatial surface is adjusted with the angle based on the value of the angle adjustment, and the primary function and the secondary function are displayed again after the angle adjustment; After determining that the angle adjustment reaches a threshold, the first spatial surface or the second spatial surface is switched, and the corresponding primary function or secondary function is added to the selected adjusted first spatial surface or the second spatial surface.

9. The transaction method of a semi-high container according to claim 8, characterized in that: Obtaining each user's browsing data for the primary function display space and the secondary function display space to generate customized data, and after determining that the user chooses to view a new cabinet, generating a customized browsing video of the new cabinet based on the customized data, so that the user can view the primary function display space and the secondary function display space based on the customized browsing video, including: Obtain the first spatial surface or the second spatial surface corresponding to the primary function display space and the secondary function display space of each box of the historical number viewed by each user, and obtain the dwelling time of each first spatial surface or the second spatial surface; Obtaining the order of the first spatial plane or the second spatial plane corresponding to each box in the viewing history of each user, and generating a corresponding sequence angle node path based on the order and angle of the first spatial plane or the second spatial plane; Sorting the boxes based on the viewing time of each box of the historical number, generating a dwelling weight of each dwelling time based on the sorting, each sequence having a preset dwelling weight, and the viewing time corresponding to the dwelling weight gradually increases from far to near; Based on the sequential angle node path, dwell time, and dwell weight, corresponding automatic data extraction is performed on the new box to generate a customized browsing video of the new box.

10. The transaction method of a semi-high container according to claim 9, characterized in that: The step of automatically extracting corresponding data of the new box based on the sequential angle node path and the dwell time to generate a customized browsing video of the new box includes: Acquire the number of sequential angle nodes in the sequential angle node path, and generate a corresponding dwell time offset value based on the comparison between the number and a preset number; The dwell time offset is processed based on the dwell time offset value to obtain the browsing sub-time of each sequential angle node in the sequential angle node path; The browsing time of each sequential angle node is calculated by the following formula, , in, For the The first spatial surface or the second spatial surface is in the Browsing time from each angle, The box viewed for history is in The first spatial surface or the second spatial surface is in the The dwell time at each angle, The box viewed for history is in The first spatial surface or the second spatial surface is in the The stop weight of the angle, The upper limit value of the box viewed in history. The number of boxes viewed in history. is a constant value, is the number of sequential angle node paths, is the preset quantity, is the quantity weight value.

11. The transaction method of a semi-high container according to claim 1, characterized in that: The comprehensive evaluation model is retrieved to evaluate the secondary evaluation model to obtain an evaluation coefficient, and the basic value of the box is adjusted according to the evaluation coefficient to obtain the recommended value of the box, including: Retrieving the comprehensive evaluation model to obtain the fluctuation start data and the fluctuation end data of the first-level function, determining the test fluctuation slope according to the fluctuation start data and the fluctuation end data, and obtaining the test fluctuation limit according to the fluctuation end data; Obtaining a first-level preset function corresponding to the first-level function, and determining a standard fluctuation slope according to fluctuation start data and fluctuation end data of the first-level preset function; When the test fluctuation limit reaches a preset standard fluctuation limit, obtaining information on the ratio of the test fluctuation slope to the standard fluctuation slope, and obtaining an effect evaluation coefficient according to the ratio information; The basic value of the box is calculated based on the effect evaluation coefficient to obtain a first-level effect reduction associated with the first-level function, and a second-level effect reduction is obtained according to the sum of multiple first-level effect reductions, and the second-level effect reduction is associated with the second-level function.

12. The transaction method of a semi-high container according to claim 11, characterized in that: The comprehensive evaluation model is retrieved to evaluate the secondary evaluation model to obtain an evaluation coefficient, and the basic value of the box is adjusted according to the evaluation coefficient to obtain the recommended value of the box, including: The comprehensive evaluation model is retrieved to perform type analysis on the actual defect image to obtain the defect type of the actual defect image; Extracting a defect contour in the actual defect image, obtaining a defect area of ​​the defect contour, and obtaining a defect assessment coefficient according to a ratio of the defect area to an area normalized value; Retrieving a preset corresponding table corresponding to the defect type, determining the defect reduction corresponding to the defect assessment coefficient according to the preset corresponding table, and associating the defect reduction with the planning area one by one, wherein the preset corresponding table includes a correspondence between coefficient intervals and defect reductions; The total defect reduction is obtained according to the sum of the defect reductions, and the basic value of the box is reduced and adjusted based on the secondary effect reduction and the total defect reduction to obtain the recommended value of the box.

13. A trading system for half-high containers, characterized in that: include: A feature acquisition module, used to respond to the resale transaction instruction, receive the basic features of the box uploaded by the first transaction terminal, retrieve the basic model of the box and the basic value of the box according to the basic features of the box, and send them to the first transaction terminal; A region association module, used for receiving the planning traces of the first transaction end for the box basic model based on the transparent layer, determining the planning area according to the planning traces, and obtaining an evaluation model based on the planning area and associating the actual defect image to send to the detection end; A customization and updating module, for dividing the primary evaluation model based on the cabinet endpoints to obtain a multi-level function display space according to the refrigeration detection requirements of the detection end, obtaining a multi-level function to customize and update the multi-level function display space, and obtaining a secondary evaluation model; The model generation module is used to call the comprehensive evaluation model to evaluate the secondary evaluation model to obtain the evaluation coefficient, adjust the basic value of the box according to the evaluation coefficient to obtain the recommended value of the box, and update the secondary evaluation model based on the recommended value of the box to obtain the comprehensive recommendation model.

Images