Product review method and device, electronic equipment, storage medium and program product

Abstract

The embodiment of the invention provides a product review method and device, electronic equipment, a storage medium and a program product. The method comprises the following steps: receiving a demand instruction, and screening out a target product file from a plurality of to-be-matched product files based on demand information carried by the demand instruction; the plurality of to-be-matched product files are in one-to-one correspondence with the plurality of three-dimensional models; based on a preset review rule corresponding to the demand instruction, determining a first type of review result corresponding to the target product file; displaying a three-dimensional model corresponding to the target product file through at least one review terminal, and obtaining a second type of review result corresponding to the target product file from the review terminal; the review terminal is VR equipment; and determining a review result of the target product file in combination with the first type of review result and the second type of review result. The method is used for achieving the effects of improving the design communication efficiency, reducing potential risks and ensuring the rationality and feasibility of a design scheme.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of model review, in particular to a product review method and device, an electronic device, a storage medium and a program product. BACKGROUND

[0002] Traditional design scheme review mainly relies on two-dimensional drawings, three-dimensional models, effect pictures, animations and wooden models to verify the scheme. These methods can help the reviewer understand the design scheme to some extent, but they have the problems of insufficient intuitiveness and incomplete information expression, and it is difficult to fully reflect the structural details or complex relationships, which can easily lead to understanding deviation and review blind spots. In addition, the production and maintenance of these static or semi-dynamic models require a lot of manpower and financial resources, and the cost is high. When the design scheme changes, data may not be synchronized or hidden dangers may be left, which will increase the difficulty of subsequent adjustment.

[0003] Because a design project often involves complex structures, variable parameters and strict quality requirements, the traditional review method cannot efficiently and accurately capture potential problems in the design scheme, which can make the product manufactured based on the design scheme fail to meet the actual use requirements, and thus lead to repeated rework and correction of the design scheme, which will continuously increase the design cost, thereby increasing the pressure on project progress and economic burden. Therefore, it is urgent to use more intuitive, convenient and low-cost virtual simulation and dynamic review means to improve design communication efficiency, reduce potential risks and ensure the rationality and feasibility of the design scheme. SUMMARY

[0004] The embodiments of the present application provide a product review method and device, an electronic device, a storage medium and a program product to improve design communication efficiency, reduce potential risks and ensure the rationality and feasibility of the design scheme.

[0005] In a first aspect, the embodiments of the present application provide a product review method, comprising:

[0006] receiving a demand instruction, and based on demand information carried by the demand instruction, screening a target product file from a plurality of to-be-matched product files; the plurality of to-be-matched product files correspond one-to-one to a plurality of three-dimensional models;

[0007] determining a first type of review result corresponding to the target product file based on a preset review rule corresponding to the demand instruction;

[0008] displaying a three-dimensional model corresponding to the target product file through at least one review terminal, and obtaining a second type of review result corresponding to the target product file from the review terminal; the review terminal is a VR device;

[0009] Determine the review result of the target product file in combination with the first type of review result and the second type of review result.

[0010] In a possible implementation, the target product file includes a plurality of model features; and the preset review rule includes review standard information corresponding to the plurality of model features.

[0011] The first type of review result corresponding to the target product file is determined based on the preset review rule corresponding to the requirement instruction.

[0012] The review score corresponding to each model feature is determined based on the plurality of model features and the review standard information corresponding to each model feature.

[0013] The target score range corresponding to the review score is determined based on a plurality of pre-set score ranges; and the plurality of score ranges correspond to a plurality of prompt types one by one.

[0014] The prompt type of the target score range corresponding to each model feature is taken as the first type of review result.

[0015] In a possible implementation, the review score corresponding to each model feature is determined based on the plurality of model features and the review standard information corresponding to each model feature.

[0016] Each model feature and the corresponding review standard information are input into a pre-trained review model to obtain a local score of each model feature in a plurality of preset dimensions.

[0017] The local scores of the current model feature in the plurality of preset dimensions are accumulated for each model feature to obtain the review score.

[0018] In a possible implementation, after the first type of review result corresponding to the target product file is determined based on the preset review rule corresponding to the requirement instruction, the method further includes:

[0019] The prompt information is generated on the three-dimensional model corresponding to the target product file based on the first type of review result.

[0020] The three-dimensional model carrying the prompt information is displayed through a preset terminal, and the correction information is obtained from the preset terminal to adjust the first type of review result based on the correction information.

[0021] The review result of the target product file is determined in combination with the first type of review result and the second type of review result.

[0022] Determine the review result of the target product file in combination with the adjusted first type of review result and the second type of review result.

[0023] In a possible implementation, the plurality of model features correspond to the plurality of point positions of the three-dimensional model one by one.

[0024] The generating of the prompt information on the three-dimensional model corresponding to the target product file based on the first type of review result includes:

[0025] The prompt information is generated based on the prompt type corresponding to the target score range of each model feature, and the prompt information is marked on the point position corresponding to each model feature.

[0026] In a possible implementation, the determining of the review result of the target product file in combination with the first type of review result and the second type of review result includes:

[0027] In combination with the first type of review result and the second type of review result, the target prompt type for each model feature included in the target product file is obtained.

[0028] The model features that meet the preset type requirement of the target prompt type are screened out, and a ratio of a total number of the model features that meet the preset type requirement of the target prompt type to a total number of the model features included in the target product file is determined.

[0029] The review result is determined based on the model features that do not meet the preset type requirement of the target prompt type and the ratio.

[0030] In a second aspect, an embodiment of the present application provides a product review device, which includes:

[0031] The screening module is configured to receive a demand instruction, and based on demand information carried by the demand instruction, screen out a target product file from a plurality of to-be-matched product files; the plurality of to-be-matched product files correspond to a plurality of three-dimensional models one by one.

[0032] The determining module is configured to determine a first type of review result corresponding to the target product file based on a preset review rule corresponding to the demand instruction.

[0033] The obtaining module is configured to display the three-dimensional model carrying the prompt information through at least one review terminal, and obtain a second type of review result corresponding to the target product file from the review terminal.

[0034] The combination module is configured to determine a review result of the target product file in combination with the first type of review result and the second type of review result.

[0035] In a third aspect, an electronic device is provided, comprising: a memory, a processor;

[0036] The memory stores computer-executable instructions.

[0037] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the first aspect and / or various possible implementation manners of the first aspect.

[0038] In a fourth aspect, a computer-readable storage medium is provided, and the computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are executed by a processor, the computer-executable instructions are used to implement the first aspect and / or various possible implementation manners of the first aspect.

[0039] In a fifth aspect, a computer program product is provided, and the computer program product comprises a computer program. When the computer program is executed by a processor, the computer program implements the first aspect and / or various possible implementation manners of the first aspect.

[0040] The product review method, device, electronic device, storage medium, and program product provided in the embodiments of the present application combine automatic review with manual review to form a multi-angle and multi-dimensional evaluation system, thereby improving the accuracy and reliability of the review results. In the automatic review process, the actual requirements in the user requirement specification can be quickly matched with the specific description and data information of the three-dimensional model contained in the product file to be matched, thereby generating an objective first type of review result and reducing the degree of human participation. In the manual review process, the reviewer can achieve immersive interaction with the three-dimensional model through the VR device, which facilitates the reviewer to more directly identify hidden defects that are difficult to identify, and the reviewer can intuitively record the problems of the three-dimensional model and combine experience to judge the risks. By combining the manual review result and the automatic review result, the review speed of different three-dimensional models can be improved, the review accuracy can be improved, the three-dimensional model that finally passes the review can be more consistent with the user requirements, and the deviation between the three-dimensional model and the requirements can be reduced. BRIEF DESCRIPTION OF DRAWINGS

[0041] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and serve to explain the principles of the present application together with the specification.

[0042] Figure 1 A scene schematic diagram of the product review method provided in the present application;

[0043] Figure 2 A flowchart of the product review method provided in the present application;

[0044] Figure 3A structural schematic diagram of a product review device provided in the present application is shown in the following figure;

[0045] Figure 4 A structural schematic diagram of an electronic device provided in the present application is shown in the following figure.

[0046] The specific embodiments of the present application have been shown in the above figures, and will be described in more detail hereinafter. These figures and the written description are not intended to limit the scope of the present application in any way, but to illustrate the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0047] The exemplary embodiments will be described in detail herein with reference to the accompanying drawings. Unless otherwise indicated, the same numbers on different drawings represent the same or similar elements. The following detailed description does not limit the present application in any way. Instead, it is intended to provide an example of apparatus and methods in accordance with the present application as detailed in the appended claims.

[0048] The product review method provided in the embodiments of the present application can be applied in the application environment as shown in the following figure. Figure 1 In the application environment, the terminal 102, the server 104 and the review terminal 106 communicate with each other through the network.

[0049] For example, the product review method is applied to the terminal 102. After receiving the demand instruction, the terminal 102 extracts a plurality of product files to be matched from the data storage system of the server 104 based on the demand information carried by the demand instruction, and selects a target product file from the plurality of product files to be matched. The plurality of product files to be matched correspond to a plurality of three-dimensional models one by one. Then, the terminal 102 determines a first type of review result corresponding to the target product file based on the preset review rule corresponding to the demand instruction. Further, the terminal 102 displays the three-dimensional model carrying the prompt information through at least one review terminal 106, and obtains a second type of review result corresponding to the target product file from the review terminal 106. Finally, the terminal 102 determines the review result of the target product file by combining the first type of review result and the second type of review result. The terminal 102 can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers and portable wearable devices. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, etc. The review terminal 106 can be, for example, a VR device. The server 104 can be implemented by an independent server or a server cluster composed of a plurality of servers. The terminal 102 and the server 104, and the review terminal 106 can be directly or indirectly connected through wired or wireless communication, for example, through network connection.

[0050] For example, the product review method is applied to the server 104, and the terminal 102 can send the demand instruction to the server 104 after receiving the demand instruction. The server 104 extracts a plurality of product files to be matched from the data storage system based on the demand instruction, and screens the target product file therefrom. The plurality of product files to be matched correspond one-to-one to a plurality of three-dimensional models. Then, the server 104 determines the first type of review result corresponding to the target product file based on the preset review rule corresponding to the demand instruction. Further, the server 104 displays the three-dimensional model carrying the prompt information through at least one review terminal 106, and obtains the second type of review result corresponding to the target product file from the review terminal 106. Finally, the server 104 determines the review result of the target product file in combination with the first type of review result and the second type of review result. It can be understood that the data storage system can be a separate storage device, or the data storage system is located on the server 104, or the data storage system is located on another terminal.

[0051] In one embodiment, a product review method is provided. The product review method is applied to a terminal for illustration in this embodiment. It can be understood that the product review method can also be applied to a server, and can also be applied to a system including a terminal and a server, and can be realized through the interaction of the terminal and the server. As shown in Figure 2 The product review method includes the following steps.

[0052] In step 202, a demand instruction is received, and a target product file is screened from a plurality of product files to be matched based on demand information carried by the demand instruction. The plurality of product files to be matched correspond one-to-one to a plurality of three-dimensional models.

[0053] The demand instruction refers to an instruction for screening a product file meeting a specific demand from a plurality of product files to be matched. The specific demand can be determined based on a user demand specification stored in a data storage system of a server.

[0054] The demand instruction can be issued by a staff through a human-computer interaction interface of a terminal. The human-computer interaction interface of the terminal can specifically display a platform interface, which is a platform interface pre-specified by a business provider and applied to review a plurality of three-dimensional models corresponding to a plurality of product files to be matched. The staff can issue the demand instruction to the terminal by uploading the user demand specification in the platform interface and clicking a virtual button on the platform interface, so as to trigger the plurality of product files to be matched.

[0055] The product file to be matched can include specific descriptions and data information of the three-dimensional model, which is used to accurately represent the actual features and parameters of the model. The product file to be matched may, for example, include design parameters, process parameters and position features of the corresponding three-dimensional model, wherein the design parameters may include equipment specifications, materials, sizes, etc.; the process parameters may include data related to the production process (such as temperature, pressure, flow, etc.); and the position features may include bit numbers, coordinate information and the like bound with the three-dimensional model, which are used to locate specific components in the three-dimensional model.

[0056] As an example, the three-dimensional model in this embodiment refers to a three-dimensional model of a product related to the pharmaceutical field, such as a bioreactor and the like.

[0057] It should be noted that the three-dimensional model is designed and made by a designer based on specific requirements of any user requirement specification. The plurality of product files to be matched and the three-dimensional models corresponding to the plurality of product files to be matched stored in the data storage system of the server are uploaded by different designers through a plurality of business terminals in communication connection with the server. As an example, when uploading the product file to be matched, the designer can mark a label of the corresponding user requirement specification on the product file to be matched, which can be a file name of the corresponding user requirement specification or a storage address of the user requirement specification in the data storage system, etc., to uniquely identify the user requirement specification corresponding to the current product file to be matched. Moreover, each three-dimensional model stored in the data storage system is uniquely associated with a product file to be matched.

[0058] After receiving the requirement instruction, the terminal can match the product file to be matched carrying the corresponding label as the target product file from the plurality of product files to be matched based on the requirement information carried by the requirement instruction, which can be understood as the user requirement specification corresponding to the requirement instruction.

[0059] Step 204, determining a first type of review result corresponding to the target product file based on a preset review rule corresponding to the requirement instruction.

[0060] Step 204 describes the process of automatically reviewing the target product file by the terminal according to the requirement information and the preset review rule stored in the data storage system, and generating the first type of review result.

[0061] The preset review rule is used to indicate a predefined review standard or criterion, which is used to evaluate whether the target product file meets the user requirements and design requirements indicated by the user requirement specification. The preset review rule can involve the range of parameters, the compliance of performance indicators, the rationality of design, the compliance of process parameters, etc.

[0062] It should be noted that the user requirement specification explicitly describes the detailed requirements and expectations of the customer, including the functions, performance, specifications, process parameters, etc. of the equipment. The preset review rules are evaluation standards and judgment criteria formulated according to the content of the user requirement specification, combined with engineering practice and design standards. These rules are used to guide the judgment of whether a design or product meets the customer's requirements and ensure the objectivity and consistency of the review.

[0063] The terminal automatically reviews the target product files screened out according to the pre-set review standards and confirms whether they meet the standards, thereby obtaining the first type of review result. The first type of review result is used to indicate the result of the automatic review.

[0064] Step 206, display the three-dimensional model corresponding to the target product file through at least one review terminal, and obtain the second type of review result corresponding to the target product file from the review terminal.

[0065] The review terminal refers to a device in communication connection with the terminal and the server. Multiple reviewers can view the three-dimensional model corresponding to the target product file through the review terminal and perform manual review. The results of the manual review are uploaded to the terminal through the review terminal as the second type of review result.

[0066] The review terminal can be a VR device. Multiple reviewers can view the three-dimensional model corresponding to the target product file through the VR device, directly observe the design details on the three-dimensional model, and compare with the common review method of displaying the three-dimensional model through a 2D screen. Through the VR device, the reviewer can more easily find potential problems in the three-dimensional model, and the reviewer can record the problems found in the manual review process through the functions of a brush, a camera, a voice, etc. The first type of review result is used to indicate the result of the manual review.

[0067] Step 208, combine the first type of review result and the second type of review result to determine the review result of the target product file.

[0068] As an example, a target product file can have multiple projects that need to be reviewed. For each project, the first type of review result and the second type of review result can be different. In this embodiment, the terminal can perform logical or processing on the first type of review result and the second type of review result. As long as one of the first type of review result or the second type of review result considers that a certain project is unqualified, the final review result of the project is considered to be unqualified, thereby obtaining the review result corresponding to the entire target product file.

[0069] The product review method combines automatic review and manual review to form a multi-angle and multi-dimensional evaluation system, thereby improving the accuracy and reliability of the review results. In the automatic review process, the actual requirements in the user requirement specification can be quickly matched with the specific description and data information of the three-dimensional model contained in the product file to be matched, thereby generating objective first-type review results and reducing the degree of manual participation. In the manual review process, the reviewer can have immersive interaction with the three-dimensional model through a VR device, which facilitates the reviewer to more directly identify hidden defects that are difficult to identify, and the reviewer can intuitively record the problems of the three-dimensional model and make risk judgments based on experience. By combining the manual review results and the automatic review results, the review speed of different three-dimensional models can be improved, the review accuracy can be improved, the three-dimensional model that finally passes the review can be more in line with the user requirements, and the deviation between the three-dimensional model and the requirements can be reduced.

[0070] In some optional embodiments, the target product file contains multiple model features; and the preset review rules include review standard information corresponding to the multiple model features.

[0071] Step 204 includes:

[0072] Based on the multiple model features and the review standard information corresponding to each model feature, a review score corresponding to each model feature is determined.

[0073] Based on the pre-set multiple score ranges, a target score range corresponding to the review score is determined; the multiple score ranges correspond to the multiple prompt types one by one.

[0074] The prompt type of the target score range corresponding to each model feature is taken as the first-type review result.

[0075] The model feature refers to a key attribute or dimension in the three-dimensional model that needs to be reviewed, for example, a geometric feature, a material feature, a process feature, a performance feature, etc. corresponding to the three-dimensional model.

[0076] The review standard information corresponding to the model feature refers to the standardized attribute or parameter corresponding to each key attribute or dimension that needs to be reviewed in the three-dimensional model.

[0077] Specifically, based on the multiple model features and the review standard information corresponding to each model feature, the step of determining the review score corresponding to each model feature includes:

[0078] Each model feature and the corresponding review standard information are input into a pre-trained review model to obtain a local score of each model feature in multiple preset dimensions;

[0079] For each model feature, the local scores of the current model feature in the multiple preset dimensions are accumulated to obtain the review score.

[0080] The pre-trained review model can be a deep learning model or other machine learning model, which has learned the mapping relationship between the model features and the review dimensions. After inputting any model feature into the review model, the local score of the model feature in multiple preset dimensions can be obtained, and the local score is used to indicate the severity of the defect existing in the model feature in any preset dimension.

[0081] Further, the terminal can multiply the local scores of each model feature in all preset dimensions to obtain the final review score.

[0082] In an embodiment, the multiple preset dimensions can be used to indicate the severity S, possibility P and detectability D of the defects existing in each model feature, and the review score of each model feature can be calculated by the following formula:

[0083] RPN=S×P×D

[0084] Wherein, RPN represents the review score.

[0085] The multiple preset score ranges can be arranged in descending order of the score, for example, the smaller the score range, the lower the severity of the defect, that is, the smaller the score range, the lower the risk of the prompt type.

[0086] Finally, the terminal can take the set of prompt types corresponding to all model features as the first type of review result.

[0087] The product review method can quantize complex model features through numerical scores, reduce subjective factors, and improve the consistency and comparability of the review. Moreover, by setting multiple score ranges and corresponding prompt types, the design quality of the target product file can be fully reflected, and the first type of review result can more accurately and clearly reflect the actual situation of the three-dimensional model, thereby improving the standardization and accuracy of the review.

[0088] In some optional embodiments, after step 204, the method further includes:

[0089] Based on the first type of review result, generating prompt information on the three-dimensional model corresponding to the target product file;

[0090] Displaying the three-dimensional model carrying the prompt information through the preset terminal, and obtaining correction information from the preset terminal to adjust the first type of review result based on the correction information;

[0091] Step 208 includes:

[0092] The review result of the target product file is determined by combining the adjusted first type review result and the second type review result.

[0093] It should be noted that the model features can be geometric features, material features, process features, performance features, etc. corresponding to the three-dimensional model. The prompt type corresponding to each model feature included in the first type review result can be, for example, excellent, qualified, unqualified, etc. Correspondingly, the terminal can generate prompt information based on the model feature and the prompt type corresponding to the model feature.

[0094] For example, when the model feature is a geometric feature and the prompt type is unqualified, the terminal can generate the corresponding prompt information “size deviation is too large”; when the model feature is a material feature and the prompt type is unqualified, the terminal can generate the corresponding prompt information “material is not up to standard”, etc.

[0095] The preset terminal also refers to a device in communication connection with the terminal and the server. The staff who corrects the automatic review result can view the first type review result through the preset terminal and manually adjust the first type review result.

[0096] For example, a certain model feature is a geometric feature, and the corresponding prompt type is unqualified. The terminal generates the prompt information “size deviation is too large” on the three-dimensional model. The terminal displays the three-dimensional model carrying the prompt information to the staff who corrects the automatic review result through the preset terminal. After viewing the three-dimensional model carrying the prompt information, the staff considers that the model feature is qualified, and can correct the prompt type corresponding to the model feature from “unqualified” to “qualified”.

[0097] Specifically, the plurality of model features are one-to-one corresponding to a plurality of point positions of the three-dimensional model.

[0098] Based on the first type review result, the step of generating prompt information on the three-dimensional model corresponding to the target product file includes:

[0099] Based on the prompt type corresponding to the target score range of each model feature, the prompt information is generated and marked on the point position corresponding to each model feature.

[0100] As an example, the terminal can pre-create a unique identifier for each model feature and mark the corresponding physical point position in the three-dimensional model. Further, by constructing a model feature-point position association database, the three-dimensional space position corresponding to each model feature on the three-dimensional model is recorded.

[0101] The product review method can automatically generate prompt information of various model features corresponding to prompt types in the automatic review link, and intuitively and clearly display the prompt information through a preset terminal, so that a staff member who corrects the automatic review result can conveniently perform manual correction of the first type of review result. By adding the manual correction process in the automatic review link, the automatic review result of the three-dimensional model can be ensured to be more accurate.

[0102] In some optional embodiments, step 208 includes:

[0103] In combination with the first type of review result and the second type of review result, a target prompt type for each model feature included in the target product file is obtained.

[0104] Model features whose target prompt types meet preset type requirements are screened out, and a ratio of a total number of model features whose target prompt types meet preset type requirements to a total number of model features included in the target product file is determined.

[0105] Based on the model features whose target prompt types do not meet preset type requirements and the ratio, a review result is determined.

[0106] In this embodiment, the terminal may, for example, compare, for each model feature, a prompt type of the model feature in the first type of review result and a prompt type of the model feature in the second type of review result, and retain a prompt type with a larger score range, i.e., a prompt type indicating a higher severity of defects, as the target prompt type.

[0107] The preset type requirements are used to screen out model features whose indicated defects have a general severity. For example, the prompt types corresponding to the model features may be excellent, qualified, and unqualified, and the prompt type meeting the preset type requirements may be qualified. The prompt type not meeting the preset type requirements refers to a prompt type indicating a higher severity of defects, for example, an unqualified prompt type.

[0108] Further, in the step of determining the review result based on the model features whose target prompt types do not meet preset type requirements and the ratio, the terminal may first calculate a qualified rate of the current target product file based on the ratio of the total number of model features whose target prompt types meet preset type requirements to the total number of model features included in the target product file, and then calculate the review result based on the qualified rate and the model features whose target prompt types do not meet preset type requirements.

[0109] Specifically, the terminal may calculate the qualified rate of the current target product file based on the ratio of the total number of model features whose target prompt types meet preset type requirements to the total number of model features included in the target product file, using the following formula:

[0110] Pass rate = 100 - 400 * X / N

[0111] Wherein, X represents the total number of model features whose target prompt type meets the preset type requirement, and N represents the total number of model features contained in the target product file. The formula can indicate that when the proportion of model features whose prompt type is qualified reaches 25%, the pass rate of the current target product file is reduced to 0.

[0112] Further, the terminal can calculate the review result based on the pass rate and the model features whose target prompt type does not meet the preset type requirement by using the following formula:

[0113] Review result = pass rate * T

[0114] Wherein, T is 0 when there is a model feature whose prompt type is unqualified, and T is 1 when there is no model feature whose prompt type is unqualified.

[0115] The above processing process is used to indicate that when the proportion of model features whose indicated defects are of general severity reaches 25% or there is a model feature whose indicated defects are of higher severity, the final review result of the current target product file is 0, that is, the current target product file fails the review. When the review result is not 0, it can be considered that the current target product file passes the review.

[0116] In an embodiment, the three-dimensional model corresponding to the target product file can contain four model features A, B, C, D, and E, wherein the target prompt type of model feature A is excellent, the target prompt type of model feature B is excellent, the target prompt type of model feature C is qualified, the target prompt type of model feature D is unqualified, and the target prompt type of model feature E is excellent, and the prompt type meeting the preset type requirement is qualified. The terminal can determine that the total number of model features whose target prompt type meets the preset type requirement in the current target product file is 1 (i.e., C), and the total number of model features whose target prompt type does not meet the preset type requirement is 1 (i.e., model feature D). Further, the terminal can calculate the ratio of the total number of model features whose target prompt type meets the preset type requirement to the total number of model features contained in the target product file as 1 / 5 = 0.2, and then calculate the pass rate of the current target product file based on the ratio 0.2 as 100 - 400 * 0.2 = 20. Since the total number of model features whose target prompt type does not meet the preset type requirement is 1, T is determined to be 0, and finally the terminal determines that the review result of the current target product file is 0, that is, the review fails.

[0117] The product review method can quantize the review result, thereby reducing the deviation of subjective judgment, clearly reflecting the defect severity or qualified condition, automatically calculating the qualified rate and the review result through a preset formula, reducing manual intervention, improving efficiency, fully considering the proportion and severity of the defects in the three-dimensional model, avoiding missing important problems, and improving the accuracy and reliability of the review result.

[0118] It should be understood that, although each step in the flowchart involved in the above embodiments is displayed in sequence according to the arrow, these steps are not necessarily executed in the order indicated by the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other orders. Moreover, at least part of the steps in the flowchart involved in the above embodiments can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily sequential, but can be alternately executed with at least part of other steps or steps or stages in other steps.

[0119] Based on the same inventive concept, the embodiments of the present application also provide a product review device for implementing the above-mentioned product review method. The implementation scheme for solving the problem provided by the product review device is similar to the implementation scheme described in the above product review method, so the specific limitations in one or more device embodiments provided below can refer to the limitations of the product review method described above, which will not be repeated here.

[0120] In one embodiment, as shown in Figure 3 a product review device 300 is provided, comprising:

[0121] The screening module 302 is configured to receive the demand instruction, and screen a target product file from a plurality of to-be-matched product files based on demand information carried by the demand instruction; the plurality of to-be-matched product files correspond one-to-one to a plurality of three-dimensional models;

[0122] The determination module 304 is configured to determine a first type of review result corresponding to the target product file based on a preset review rule corresponding to the demand instruction;

[0123] The acquisition module 306 is configured to display a three-dimensional model carrying prompt information through at least one review terminal, and acquire a second type of review result corresponding to the target product file from the review terminal;

[0124] The combination module 308 is configured to combine the first type of review result and the second type of review result to determine the review result of the target product file.

[0125] In some optional embodiments, the target product file comprises a plurality of model features; and the preset review rule comprises review standard information corresponding to the plurality of model features.

[0126] The determining module 304 is further configured to:

[0127] determine a review score corresponding to each model feature based on the plurality of model features and the review standard information corresponding to each model feature;

[0128] determine a target score range corresponding to the review score based on a plurality of preset score ranges; the plurality of score ranges correspond to a plurality of prompt types one by one;

[0129] take the prompt type of the target score range corresponding to each model feature as the first type of review result.

[0130] In some optional embodiments, the determining module 304 is further configured to:

[0131] input each model feature and the corresponding review standard information into a pre-trained review model to obtain a local score of each model feature in a plurality of preset dimensions;

[0132] accumulate the local scores of the current model feature in the plurality of preset dimensions to obtain the review score for each model feature.

[0133] In some optional embodiments, the determining module 304 is further configured to:

[0134] generate prompt information on the three-dimensional model corresponding to the target product file based on the first type of review result;

[0135] display the three-dimensional model carrying the prompt information through a preset terminal, and obtain correction information from the preset terminal to adjust the first type of review result based on the correction information;

[0136] The combining module 308 is further configured to:

[0137] combine the adjusted first type of review result and the second type of review result to determine the review result of the target product file.

[0138] In some optional embodiments, the plurality of model features correspond to a plurality of point positions of the three-dimensional model one by one.

[0139] The determining module 304 is further configured to:

[0140] generate prompt information based on the prompt type of the target score range corresponding to each model feature, and mark the prompt information on the point position corresponding to each model feature.

[0141] In some optional embodiments, the combining module 308 is further configured to:

[0142] obtain a target prompt type for each model feature contained in the target product file in combination with the first type of review result and the second type of review result;

[0143] screen out the model features of the target prompt type meeting the preset type requirement, and determine a ratio of a total number of the model features of the target prompt type meeting the preset type requirement to a total number of the model features contained in the target product file;

[0144] determine the review result based on the model features of the target prompt type not meeting the preset type requirement and the ratio.

[0145] Each of the modules in the above apparatus can be realized by software, hardware, and a combination thereof in whole or in part. The above modules can be embedded in or independent of a processor in a computer device in a hardware form, or stored in a memory in a computer device in a software form, so as to be called and executed by a processor to perform the operations corresponding to the above modules.

[0146] Figure 4 The structural schematic diagram of the electronic device provided in the present application is shown in FIG. 4. As shown in FIG. 4, the electronic device 400 provided in the present embodiment comprises at least one processor 401 and a memory 402. Optionally, the device 400 further comprises a communication component 403. The processor 401, the memory 402, and the communication component 403 are connected through a bus 404. Figure 4

[0147] In the specific implementation process, the at least one processor 401 executes the computer execution instructions stored in the memory 402, so that the at least one processor 401 performs the above method.

[0148] The specific implementation process of the processor 401 can refer to the above method embodiments, which have similar implementation principles and technical effects, and will not be described here in detail.

[0149] In the above embodiments, it should be understood that the processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the disclosed method can be directly embodied as execution completed by a hardware processor, or executed by a combination of hardware and software modules in the processor.

[0150] ​The memory can include a random access memory (RAM) and can also include a non-volatile memory (NVM), such as at least one disk memory.

[0151] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, the bus in the drawings of the present application does not limit to only one bus or one type of bus.

[0152] The present application also provides a computer program product, comprising a computer program, which, when executed by a processor, implements the above method.

[0153] The present application also provides a computer readable storage medium, which stores computer execution instructions, and when a processor executes the computer execution instructions, the above method is implemented.

[0154] The above readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0155] An exemplary readable storage medium is coupled to the processor, so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be an integral part of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in the device.

[0156] The division of units is only a logical function division, and actual implementation can have another division manner, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0157] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, can be located in one place, or can be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0158] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit.

[0159] If the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the part of the present application that essentially contributes to the prior art or the part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various program code storage media.

[0160] Those skilled in the art can understand that all or part of the steps of the above-mentioned method embodiments can be completed by program instruction related hardware. The aforementioned program can be stored in a computer readable storage medium. The program executes the steps including the above-mentioned method embodiments when executed; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk, and various program code storage media.

[0161] It should be understood that many of the materials and devices exemplified in this disclosure are articles of manufacture (i.e., articles of manufacture) according to this disclosure. The articles of manufacture can be manufactured as such or can be manufactured by combining the materials and devices exemplified in this disclosure. It is also to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting. It should be understood that, in some embodiments, equivalents to the specific electrode structures and / or methods described herein can be employed without departing from the scope of the application. Accordingly, the phraseology and terminology used herein is for the purpose of description and should not be regarded as limiting. The use of "including," "comprising," "having," "containing," "involving," "characterized by," "characterized into," and variations thereof herein, is meant to encompass the items listed thereafter, and equivalents thereof as well as additional items. Although the foregoing application has been described in some detail by way of illustration and example, it is not to be limited thereby, but rather, only by the scope of the appended claims.

Claims

1. A product review method characterized by, The method comprises the steps of: receiving a demand instruction and screening a target product file from a plurality of to-be-matched product files based on demand information carried by the demand instruction; a plurality of the to-be-matched product files correspond to a plurality of three-dimensional models one by one; determining a first type of review result corresponding to the target product file based on a preset review rule corresponding to the demand instruction; displaying a three-dimensional model corresponding to the target product file through at least one review terminal, and obtaining a second type of review result corresponding to the target product file from the review terminal; the review terminal is a VR device; determining a review result of the target product file in combination with the first type of review result and the second type of review result.

2. The method of claim 1, wherein, The target product file contains a plurality of model features; the preset review rule includes review standard information corresponding to a plurality of the model features; The method comprises the steps of: determining an evaluation score corresponding to each model feature based on a plurality of the model features and the review standard information corresponding to each model feature; determining a target score range corresponding to the evaluation score based on a plurality of pre-set score ranges; a plurality of the score ranges correspond to a plurality of prompt types one by one; taking the prompt type of the target score range of each model feature as the first type of review result.

3. The method of claim 2, wherein, The method comprises the steps of: inputting each model feature and the corresponding review standard information into a pre-trained review model to obtain a local score of each model feature in a plurality of preset dimensions; accumulating the local scores of the current model feature in a plurality of the preset dimensions to obtain the evaluation score for each model feature.

4. The method of claim 1, wherein, After determining the first type of review result corresponding to the target product file based on the preset review rule corresponding to the demand instruction, the method further comprises the steps of: generating prompt information on the three-dimensional model corresponding to the target product file based on the first type of review result; displaying the three-dimensional model carrying the prompt information through a preset terminal, and obtaining correction information from the preset terminal to adjust the first type of review result based on the correction information; The method comprises the steps of: determining the review result of the target product file in combination with the adjusted first type of review result and the second type of review result.

5. The method of claim 4, wherein, A plurality of the model features correspond to a plurality of point positions of the three-dimensional model one by one; The method comprises the steps of: generating prompt information based on the prompt type of the target score range of each model feature, and marking the prompt information on the point position corresponding to each model feature.

6. The method of claim 1, wherein, The method comprises the steps of: The target prompt type is obtained for each model feature contained in the target product file in combination with the first type of review result and the second type of review result; The model features of the target prompt type that meet the preset type requirement are screened out, and a ratio of a total number of the model features of the target prompt type that meet the preset type requirement to a total number of the model features contained in the target product file is determined; The review result is determined based on the model features of the target prompt type that do not meet the preset type requirement and the ratio.

7. A product review apparatus characterized by comprising: The method comprises the following steps: The screening module is configured to receive a demand instruction, and screen a target product file from a plurality of to-be-matched product files based on demand information carried by the demand instruction; The plurality of to-be-matched product files correspond to a plurality of three-dimensional models in a one-to-one manner; The determining module is configured to determine a first type of review result corresponding to the target product file based on a preset review rule corresponding to the demand instruction; The obtaining module is configured to display a three-dimensional model carrying the prompt information through at least one review terminal, and obtain a second type of review result corresponding to the target product file from the review terminal; The combining module is configured to combine the first type of review result and the second type of review result to determine a review result of the target product file.

8. An electronic device, comprising: The method comprises the following steps: A memory and a processor; The memory stores computer execution instructions; The processor executes the computer execution instructions stored in the memory, so that the processor executes the method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer execution instructions, and the computer execution instructions are executed by the processor to implement the method according to any one of claims 1-6.

10. A computer program product, characterised in that, The computer program is executed by the processor to implement the method according to any one of claims 1-6.

Images