A product design change test method, apparatus, and medium

Abstract

The application discloses a product design change test method, device and medium, the method comprises the following steps: obtaining the design change request of an initial product, determining structured change information according to the design change request, determining change type, change level and change task according to change content information, finding a reference product similar to the initial product and reference test information of the reference product from a preset change database according to the change content information, the change type and the change level, executing the change task on the initial product to obtain a target product, testing the target product according to the reference test information to obtain actual measurement product information, and determining a design change test result of the target product according to the initial product information, the actual measurement product information and the expected product information. The application can obtain the reference test information of the reference product as a reference, does not need to rely on manual experience to formulate a test scheme, improves the test efficiency, and can evaluate and feed back whether the design change achieves an expected target.

Description

Technical Field

[0001] This application belongs to the field of product manufacturing, and specifically relates to a product design change testing method, apparatus and medium. Background Technology

[0002] With the rapid development of the automotive industry, product iteration is accelerating, market demands are becoming increasingly diversified, and relevant standards are constantly being updated, resulting in more frequent product design changes.

[0003] However, existing technologies still face technical bottlenecks in design change management. Design change-related information is diverse in form and structure, making it impossible to analyze and utilize it systematically. When testing the changed product, there are no historical test cases or standard procedures for reference. Test plan development relies on manual experience, resulting in low testing efficiency and poor consistency. It is also impossible to conduct closed-loop evaluation and feedback on whether the change has achieved the expected goals. Summary of the Invention

[0004] The purpose of this application is to provide a product design change testing method, apparatus, and medium, which is achieved as follows: In a first aspect, embodiments of this application provide a product design change testing method, the method comprising: Obtain the initial product design change request, and determine the structured change information based on the design change request; the structured change information includes change content information, initial product information, and expected product information; The change type, change level, and change task are determined based on the changed content information; Based on the change content information, the change type, and the change level, search the preset change database for reference products similar to the initial product and reference test information of the reference products; The target product is obtained by performing the change task on the initial product; The target product is tested based on the reference test information to obtain the actual product information; The design change test results of the target product are determined based on the initial product information, the measured product information, and the expected product information.

[0005] Optionally, the changed content information includes at least one of the following: changed text information, associated object information, risk analysis information, cost change information, and timeliness information; The steps for determining the change type, change level, and change task based on the changed content information include: Extract at least one keyword from the changed text information, and determine the feature weights corresponding to at least one keyword; Generate a feature vector for the changed text information based on the keywords and the feature weights corresponding to the keywords; The feature vector is input into a trained design change classification model for classification to obtain candidate change types and the confidence level of the candidate change types. If the confidence level is greater than or equal to a preset confidence level threshold, the candidate change type will be used as the change type. The change impact parameters are determined based on the associated object information, the risk analysis information, the cost change information, and the timeliness information; The change level is determined based on the change impact parameters; The change task is generated based on the changed text information, associated object information, risk analysis information, cost change information, and timeliness information.

[0006] Optionally, the step of determining the change impact parameters based on the associated object information, the risk analysis information, the cost change information, and the timeliness information includes: Determine the scope of influence parameters based on the associated object information; The risk parameters for change are determined based on the risk analysis information. Determine the cost change parameters based on the cost change information; The change timeliness parameters are determined based on the aforementioned timeliness information; The change impact parameters are determined based on the impact scope parameter, the change risk parameter, the cost change parameter, the change timeliness parameter, and the preset weight parameter.

[0007] Optionally, the method further includes: The approval path and approval time for the change task are determined based on the change level. In response to the completion of the change task according to the approval path and the approval time, the change task is executed on the initial product to obtain the target product.

[0008] Optionally, the step of performing the change task on the initial product to obtain the target product includes: The change task is broken down into several change sub-tasks; Several change sub-tasks are executed on the initial product, and during the execution, several execution progress data corresponding to the several change sub-tasks are collected based on a preset monitoring frequency. The execution progress data are compared with the preset progress benchmarks corresponding to the modified sub-tasks to obtain several progress deviation data. If any of the aforementioned progress deviation data exceeds the preset warning threshold, then a warning message for the changed subtask is generated and displayed. If all of the aforementioned execution progress data reach a completion status, the change task is determined to be completed, and the target product is obtained.

[0009] Optionally, the step of testing the target product based on the reference test information to obtain the actual product information includes: A reference test task is generated based on the reference test information, and candidate test tasks similar to the reference test task are obtained. Perform the reference test task and / or the candidate test task on the target product to obtain the actual product information.

[0010] Optionally, the initial product information includes initial performance data, initial cost data, and initial quality data; the expected product information includes expected performance data, expected cost data, and expected quality data; and the measured product information includes measured performance data, measured cost data, and measured quality data. The steps for determining the design change test results of the target product based on the initial product information, the measured product information, and the expected product information include: The performance change effect is determined based on the initial performance data, the measured performance data, and the expected performance data. The effect of cost changes is determined based on the initial cost data, the measured cost data, and the expected cost data. The effect of the quality change is determined based on the initial quality data, the measured quality data, and the expected quality data. The design change test results are determined based on the effects of the performance changes, the cost changes, and the quality changes.

[0011] Optionally, the method further includes: The initial product is associated with and stored in the change database along with the change content information, the initial product information, the expected product information, the change type, the change level, the change task, the reference test information, the target product, and the feature vector; wherein, the change type and the feature vector are used as incremental training samples to incrementally train the design change classification model.

[0012] Secondly, embodiments of this application provide a product design change testing device, the device comprising: The change request acquisition module is used to acquire design change requests for the initial product and determine structured change information based on the design change requests; the structured change information includes change content information, initial product information, and expected product information; The change information determination module is used to determine the change type, change level, and change task based on the change content information. The reference product search module is used to search for reference products similar to the initial product and reference test information of the reference products from a preset change database based on the change content information, the change type, and the change level. The design change execution module is used to execute the change task on the initial product to obtain the target product; The target product testing module is used to test the target product based on the reference testing information to obtain the actual product information. The test result acquisition module is used to determine the design change test results of the target product based on the initial product information, the actual product information, and the expected product information.

[0013] Thirdly, embodiments of this application provide a readable storage medium on which a program or instructions are stored, and when the program or instructions are executed by a processor, they implement the method described above.

[0014] The embodiments of this application have the following advantages: In this embodiment, a design change request for the initial product is obtained. Based on the design change request, structured change information is determined. This structured change information includes change content information, initial product information, and expected product information. The change type, change level, and change task are determined based on the change content information. Reference products similar to the initial product and their reference test information are searched from a pre-set change database based on the change content information, change type, and change level. The change task is executed on the initial product to obtain the target product. The target product is tested based on the reference test information to obtain actual product information. The design change test results of the target product are determined based on the initial product information, actual product information, and expected product information. This application can obtain structured change information, making the form and structure of design change-related information uniform, enabling systematic analysis and utilization. When testing the changed product, reference test information of the reference product can be obtained as a reference, eliminating the need to rely on manual experience to formulate test plans, improving testing efficiency, and enhancing the consistency of testing similar products. This application obtains the design change test results of the target product, enabling evaluation and feedback on whether the design change has achieved its expected goals. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below.

[0016] Figure 1This is a flowchart illustrating the steps of a product design change testing method provided in one embodiment of this application; Figure 2 This is a schematic diagram of the structure of a product design change management system provided in one embodiment of this application; Figure 3 This is a flowchart illustrating the steps for determining a change category according to an embodiment of this application; Figure 4 This is a flowchart illustrating the steps of design change approval according to an embodiment of this application; Figure 5 This is a flowchart illustrating the steps of a product design change management method according to an embodiment of this application; Figure 6 This is a schematic diagram of the structure of a product design change testing device provided in one embodiment of this application. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the various embodiments of this application will be described in detail below with reference to the accompanying drawings. However, those skilled in the art will understand that many technical details have been presented in the various embodiments of this application to enable readers to better understand this application. However, the technical solutions claimed in this application can be implemented even without these technical details and various changes and updates based on the following embodiments. The division of the various embodiments below is for the convenience of description and should not constitute any limitation on the specific implementation of this application. The various embodiments can be combined with and referenced by each other without contradiction.

[0018] Currently, automotive companies face numerous technical bottlenecks in product design change management: vague change classification standards rely solely on manual experience to determine change types, leading to inconsistent handling of similar changes; a lack of quantitative basis for tiered assessments results in subjective and arbitrary risk assessments and impact scope analyses, easily leading to simplified approval processes for high-risk changes or excessive approval for low-risk changes; a mismatch between approval processes and change levels, lacking dynamic adjustment mechanisms, resulting in low approval efficiency; untimely tracking of change execution processes makes it difficult to accurately grasp the progress of each stage; and a lack of systematic verification and feedback on change effects, with historical change data failing to form effective knowledge base and unable to provide decision support for subsequent changes.

[0019] Therefore, this application provides a product design change testing method, apparatus, and medium that can acquire structured change information, making the form and structure of design change-related information uniform, enabling systematic analysis and utilization. When testing the modified product, reference test information of the reference product can be obtained as a reference, eliminating the need to rely on manual experience to formulate test plans, thus improving testing efficiency and consistency in testing similar products. This application obtains the design change test results of the target product, enabling evaluation and feedback on whether the design change has achieved the expected goals.

[0020] Reference Figure 1 The diagram shows a flowchart of a product design change testing method provided in an embodiment of this application.

[0021] In this embodiment, the product design change testing method can be applied to a product design change management system. A product design change management system refers to a tool or platform used to manage product design changes, helping enterprises record, track, analyze, and optimize the design change process to ensure the accuracy, consistency, and effectiveness of the changes.

[0022] The method may specifically include the following steps: Step 101: Obtain the initial product design change request and determine the structured change information based on the design change request; the structured change information includes change content information, initial product information and expected product information.

[0023] In this embodiment of the application, a design change request for the initial product can be obtained, and structured change information can be determined based on the design change request. Specifically, the initial product refers to a product requiring design changes, and the product specifically refers to an entity or system with specific functions, structures, performance, and technical specifications formed through design, manufacturing, or engineering activities.

[0024] A design change request is a formal application document or electronic instruction submitted by relevant personnel, requesting specific modifications to the product design. Structured change information is a standardized collection of information that conforms to a preset format and contains complete elements, formed after the design change request has been parsed and reorganized.

[0025] In this embodiment, the structured change information may include change content information, initial product information, and expected product information. The change content information may be a description of the specific design change plan, including details such as the object of modification, the method of modification, and changes in technical parameters. The initial product information may refer to the complete state and data of the product to be modified in terms of function, structure, performance, materials, and technical parameters before the implementation of the design change, providing a benchmark for comparing the implementation and effects of the change. The expected product information may be the target state such as the performance indicators, functional characteristics, or specifications that the product is expected to achieve after the design change.

[0026] In practice, design change requests can be represented as standardized change application forms. These forms include fields for change name, applying department, applicant, reason for change, product model involved, component number involved, description of change content, and expected target. They support the input of text, images, and attachments. The form fields use a dynamic loading mechanism, which can automatically adjust the required and optional fields according to different product types.

[0027] Then, it can interact with enterprise PLM (Product Lifecycle Management) systems, ERP (Enterprise Resource Planning) systems, and MES (Manufacturing Execution System) systems to automatically obtain the BOM (Bill of Materials) structure of the components involved in the change, i.e., the initial product, historical change records, current production status, and inventory information data. The interface adopts a RESTful API (Representational State Transfer Application Programming Interface) architecture, and the data transmission adopts JSON (JavaScript Object Notation) format. It supports both real-time synchronization and scheduled batch synchronization modes, and the interface call frequency can be set to 1 time / minute. Then, the collected structured change information can be checked for completeness and validity. Completeness check can be performed to check whether required fields are empty, and validity check can be performed to verify whether the part number and product model format are correct using regular expressions. For invalid information, a pop-up window can be used to prompt the applicant of the design change request to make corrections. After the verification is passed, a unique change request number can be generated for the design change request, in the format of "PDCM_ECR + year + month + day + 4-digit serial number".

[0028] Step 102: Determine the change type, change level, and change task based on the change content information.

[0029] In this embodiment of the application, the change type, change level, and change task can be determined based on the change content information.

[0030] The change type can refer to the category categorized based on the technical characteristics, scope of impact, or implementation objectives of the design change, such as material change, structural change, and software change, to guide differentiated processing procedures and evaluation standards. In specific implementation, change types can include material changes, functional changes, performance changes, structural changes, color changes, dimensional changes, control program software changes, interface definition changes, chip replacement changes, and electronic component changes, etc.

[0031] The change level can refer to the priority indicator assessed based on the impact, risk level, and implementation complexity of the design change, such as major change, important change, and general change, which is used to match the corresponding approval process and resource allocation.

[0032] Among them, the change task can refer to the specific executable work unit decomposed to realize a specific design change, including the task content, responsible person, time node and deliverables, which constitute the basic components of the change implementation plan.

[0033] Step 103: Based on the change content information, change type and change level, search the preset change database for reference products similar to the initial product and reference test information for the reference products.

[0034] In this embodiment of the application, reference products similar to the initial product and reference test information of the reference products can be found from a preset change database based on the change content information, change type and change level.

[0035] The change database can store relevant product information and complete change process data related to historical design changes. The change database supports retrieval and analysis by change type, change level, and product model.

[0036] Reference products can refer to historical product models or versions that exist in the change database and are similar to the current product to be changed in terms of structure, function, or technical features.

[0037] Reference test information can refer to test-related information such as test plans and test conditions recorded during the testing activities performed on the reference product during historical changes.

[0038] In practical implementation, the change information can include product model and change text information. Based on the product model, change type, and change level, design change cases of historical products similar to the current initial product can be found in the change database. Then, the feature vector of the change text information corresponding to the current initial product can be determined based on the change text information. The feature vector of the change text information corresponding to the reference product's design change cases can be obtained, and the cosine similarity between the two can be calculated. Historical products with a cosine similarity greater than or equal to 0.8 are used as reference products, and the test plan and test conditions used when testing the reference product are used as reference test information.

[0039] Cosine similarity can be calculated using the following formula:

[0040] in, Cosine similarity is represented by θ, where θ represents the vector similarity. and Angle in n-dimensional space. The feature vector representing the change text information corresponding to the initial product. The feature vector of the corresponding change text information for historical products, where n represents the total number of feature dimensions of the vector, and i represents the dimension index of the vector. Representing vectors Component values ​​in the i-th dimension Representing vectors The component value in the i-th dimension.

[0041] In one optional embodiment of this application, reference products similar to the initial product and reference test information of the reference products can also be searched from a preset change database based on any one of the change content information, change type, and change level.

[0042] Step 104: Perform a change task on the initial product to obtain the target product.

[0043] In this embodiment, a change task can be performed on an initial product to obtain a target product. The target product may refer to the final product state formed after all design change tasks have been completed, and its functions, structure, or performance have been updated according to the change requirements.

[0044] Step 105: Test the target product based on the reference test information to obtain the actual product information.

[0045] In this embodiment of the application, the target product can be tested based on reference test information to obtain actual product information.

[0046] Actual product information refers to the collection of objective information such as real performance data, quality indicators, and functional verification results collected after actual testing of the target product that has undergone changes.

[0047] In practice, the target product can be tested based on the test plan, test conditions and other test-related information provided by the reference test information to obtain the actual test product information.

[0048] Step 106: Determine the design change test results of the target product based on the initial product information, the measured product information, and the expected product information.

[0049] In this embodiment, the design change test results of the target product can be determined based on initial product information, measured product information, and expected product information. The design change test results can refer to a comprehensive evaluation conclusion formed based on a comparative analysis of the initial product information, measured product information, and expected product information, regarding whether the design change has achieved its expected goals and whether the change effect is satisfactory.

[0050] In practice, design change test results can be determined based on either the variance rate or the target achievement rate. The variance rate reflects the absolute magnitude of the change's impact on the product's state and is used to assess the significance and intensity of the change's implementation. The target achievement rate measures the degree to which the change's effects align with the expected goals, directly evaluating whether the change accurately achieved the preset improvement objectives.

[0051] The difference rate can be calculated using the following formula:

[0052] The target achievement rate can be calculated using the following formula:

[0053] The initial product information, measured product information, and expected product information can all be replaced with corresponding data. Furthermore, when the expected target data is a reduction indicator, the absolute value can be taken.

[0054] This application can obtain structured change information, making the form and structure of design change-related information uniform, enabling systematic analysis and utilization. When testing the changed product, reference test information of the reference product can be obtained as a reference, eliminating the need to rely on manual experience to formulate test plans, thus improving testing efficiency and enhancing the consistency of testing similar products. This application obtains the design change test results of the target product, enabling the evaluation and feedback on whether the design change has achieved the expected goals.

[0055] In one optional embodiment of this application, the change content information includes at least one of the following: change text information, associated object information, risk analysis information, cost change information, and timeliness information; The steps to determine the change type, change level, and change task based on the change information include: S11, extract at least one keyword from the changed text information, and determine the feature weights corresponding to each keyword; S12, Generate a feature vector of the changed text information based on the keywords and the feature weights corresponding to the keywords; S13, input the feature vector into the trained design change classification model for classification, and obtain the candidate change type and the confidence level of the candidate change type; S14, if the confidence level is greater than or equal to the preset confidence level threshold, the candidate change type is used as the change type; S15, determine the change impact parameters based on related object information, risk analysis information, cost change information, and timeliness information; S16, Determine the change level based on the change impact parameters; S17, Generate a change task based on the change text information, related object information, risk analysis information, cost change information, and timeliness information.

[0056] In this embodiment of the application, at least one keyword can be extracted from the changed text information, and the feature weights corresponding to the at least one keyword can be determined.

[0057] Keywords refer to representative and distinctive core words or terms identified from the change text information using natural language processing technology, used to characterize the technical attributes or business scope of the current design change. In practice, the change text information can be preprocessed, including word segmentation, stop word removal, and word vector conversion, before extracting change feature keywords.

[0058] Feature weights refer to the quantitative values ​​assigned to each keyword, which reflect the importance or distinguishing ability of the keyword in representing changed content. They can be calculated using statistical methods such as TF-IDF.

[0059] In practical implementation, the feature weights can be calculated using the following formula:

[0060] in, This represents the feature weight of keyword j in modified text information i, where i represents the modified text information and j represents the keyword. This represents the word frequency of keyword j in modified text information i, which is the ratio of the number of times keyword j appears in modified text information i to the total number of words in modified text information i.

[0061] Indicates inverse document frequency. ,in, This indicates the total number of changed documents. For containing feature words The number of documents.

[0062] Then, feature vectors of the modified text information can be generated based on the keywords and their corresponding feature weights. A feature vector can refer to a numerical representation of a set of keywords and their corresponding feature weights. Feature vectors are used to convert unstructured text information into a mathematical structure that can be processed by machine learning models.

[0063] Feature vectors can be input into a trained design change classification model for classification, yielding candidate change types and their confidence levels. The design change classification model refers to a machine learning model trained on historical change data, capable of automatically identifying and outputting change categories and their confidence levels based on the input feature vectors; examples include Support Vector Machines (SVMs) or neural network models.

[0064] The design change classification model uses feature vectors from historical change cases as training samples. Key model parameters, such as the penalty coefficient C, kernel function type, and the specific value of its parameter γ, can be optimized using cross-validation. For example, the penalty coefficient C can be set to 1.0, and the kernel function can be a radial basis function (RBF). The value can be set to 0.1.

[0065] If the confidence level is greater than or equal to a preset confidence threshold, the candidate change type is adopted as the change type. Here, candidate change type refers to the change category predicted by the change classification model based on the input feature vector. The confidence threshold is a pre-set minimum confidence standard used to determine whether the classification result is acceptable.

[0066] In practical implementation, the feature vector of the change text information corresponding to the initial product can be input into the trained design change classification model, which outputs candidate change types and confidence levels. Taking a confidence threshold of 0.85 as an example, when the confidence level is ≥0.85, the candidate change type is directly used as the change type. When the confidence level is <0.85, the change application can be pushed to the expert review queue, where experts manually confirm the change type. At the same time, the expert confirmation results are added to the training set as incremental training samples, and the design change classification model is retrained periodically.

[0067] In this embodiment, change impact parameters can be determined based on associated object information, risk analysis information, cost change information, and timeliness information, and the change level can be determined based on the change impact parameters.

[0068] Among them, the related object information can refer to product components, system modules, technical documents or external dependent objects that are directly or indirectly related to this design change.

[0069] Risk analysis information can refer to the identification, assessment, and classification results of technical risks, quality risks, safety risks, and project risks that may be caused by design changes.

[0070] Cost change information can refer to the estimated or actual cost changes resulting from the implementation of design changes, including material costs, labor costs, equipment costs, and indirect costs.

[0071] Timeliness information can refer to the requirements and constraints of design changes in the time dimension, including the time when the requirement is put forward, the expected completion time, and the degree of urgency.

[0072] Change impact parameters can refer to composite indicators that are formed by quantitative calculations based on multi-dimensional information such as related objects, risks, costs, and timeliness, and are used to objectively characterize the overall impact of design changes.

[0073] In practice, the level of change can be determined by comparing the change-affecting parameter with a preset threshold. Let S represent the change-affecting parameter. The number indicates that the change level is a major change. The number indicates that the change level is important. The score indicates that the change level is a general change.

[0074] In this embodiment of the application, a change task can be generated based on the change text information, associated object information, risk analysis information, cost change information, and timeliness information.

[0075] In practical implementation, change text information can be parsed to extract core operational instructions, and combined with related object information to clarify the components and responsible departments involved in the change. Subsequently, based on risk analysis information, verification or review tasks are inserted for high-risk processes. Budgets are allocated and cost control nodes are set with reference to cost change information. At the same time, task start and end times and critical paths are planned based on timeliness information. Finally, the above elements are automatically integrated to decompose the change objective into a series of specific sub-tasks with clearly defined responsible persons, deliverables, timelines, and dependencies, forming a structured, executable, and traceable change task plan.

[0076] In practical implementation, intelligent classification and grading based on knowledge graphs can be used to obtain change types and change levels. For example, this can be achieved by constructing a knowledge graph covering the automotive product design domain. This knowledge graph uses nodes to represent entities such as automotive parts, design parameters, process requirements, and regulatory standards, and edges to represent the relationships between entities. For example, a part node can be connected to performance parameter nodes such as power and torque, and simultaneously associated with process nodes such as production processes and assembly procedures, as well as standard nodes such as emission regulations. When a design change occurs, the technical field and scope of impact of the change can be automatically identified by traversing the nodes and edges connected to the changed content in the knowledge graph. Simultaneously, predefined semantic rules and impact propagation models in the graph can be invoked, such as determining the compliance level based on whether the change affects regulatory nodes, or assessing the implementation risk based on the complexity of associated process nodes. Finally, by comprehensively considering the scope of association, rule matching results, and impact propagation depth, the change's category label and level assessment are automatically output, achieving intelligent classification and grading based on semantic association and logical reasoning.

[0077] This application achieves intelligent management of design changes through automation technology, significantly improving the efficiency and accuracy of change processing. First, natural language processing technology extracts keywords from change text information and calculates feature weights to generate feature vectors. Combined with machine learning models, this enables automatic classification of change types, reducing manual intervention and improving classification accuracy. Second, by comprehensively considering related objects, risks, costs, and timeliness information, the impact parameters of changes are quantified, and change levels are dynamically determined, ensuring the scientific and rational nature of change decisions. Finally, structured change tasks are automatically generated, enhancing the controllability and transparency of change execution. This effectively reduces the time and labor costs of change management while improving the success rate and quality of change implementation.

[0078] In one optional embodiment of this application, the step of determining the change impact parameters based on associated object information, risk analysis information, cost change information, and timeliness information includes: S21, Determine the scope of influence parameters based on the associated object information; S22, Determine the change risk parameters based on risk analysis information; S23, Determine cost change parameters based on cost change information; S24, Determine the change timeliness parameters based on the timeliness information; S25. Determine the impact parameters of the change based on the impact scope parameters, change risk parameters, cost change parameters, change timeliness parameters, and preset weight parameters.

[0079] In this embodiment, the scope of influence parameter can be determined based on the associated object information, the change risk parameter can be determined based on the risk analysis information, the cost change parameter can be determined based on the cost change information, and the change timeliness parameter can be determined based on the timeliness information.

[0080] The scope of impact parameter can refer to a metric used to quantify the number of product components, the breadth of system modules, and the coverage of production batches involved in a design change.

[0081] Change risk parameters can refer to the numerical representation of potential negative consequences such as technical failures, quality defects, and safety compliance issues that may be caused by design changes, based on risk analysis information and after quantifying the levels of these consequences.

[0082] Cost change parameters can refer to the quantitative assessment of changes in direct and indirect costs resulting from the implementation of design changes, including the combined impact of material, labor, equipment, and management costs.

[0083] The change timeliness parameter can be used to quantify the urgency of design changes in the time dimension. It is usually calculated based on the relationship between the time of requirement submission, deadline, and project critical path.

[0084] In practice, information on related objects, risk analysis, cost change, and timeliness can be quantitatively scored, with each indicator scoring between 1 and 5 points.

[0085] The impact scope parameter A can be determined based on the number of components involved in the change, the BOM level, and the production batch. When the number of components involved in the change is greater than 50, or the BOM level is greater than or equal to level 3, or the change affects production batches for more than 6 months, the impact scope parameter can be 5 points; when the number of components involved is 20-50, or the BOM level is level 2, or the change affects production batches for 3-6 months, the impact scope parameter can be 3 points; when the number of components involved is less than 20, or the BOM level is level 1, or the change affects production batches for less than 3 months, the impact scope parameter can be 1 point. The change risk parameter B can be based on the results of FMEA (Failure Mode and Effects Analysis) analysis, taking into account the quality risks, safety risks, and compliance risks that the change may cause. When a fatal risk occurs, the change risk parameter can be 5 points; when a serious risk occurs, the change risk parameter can be 4 points; when a general risk occurs, the change risk parameter can be 2 points; and when there is no obvious risk, the change risk parameter can be 1 point. The cost change parameter C can be calculated based on the direct cost increase and return on investment caused by the change. When the cost increase is greater than RMB 1 million or the return on investment is less than 5%, the cost change parameter can be 5 points; when the cost increase is between RMB 500,000 and RMB 1 million or the return on investment is between 5% and 10%, the cost change parameter can be 3 points; when the cost increase is less than RMB 500,000 or the return on investment is greater than 10%, the cost change parameter can be 1 point. The change timeliness parameter D can be adjusted based on the urgency of the change requirement. If the change needs to be completed within 1 week, the change timeliness parameter can be 5 points; if it needs to be completed within 1-4 weeks, the change timeliness parameter can be 3 points; and if it needs to be completed in more than 4 weeks, the change timeliness parameter can be 1 point.

[0086] Then, the impact parameters of the change can be determined based on the impact scope parameter, change risk parameter, cost change parameter, change timeliness parameter, and preset weight parameters. The preset weight parameters refer to a set of proportional coefficients pre-set in the evaluation model to characterize the relative importance of each impact parameter in the overall evaluation. Preset weight parameters may include impact scope weight, change risk weight, cost factor weight, and change timeliness weight.

[0087] In practical implementation, the Analytic Hierarchy Process (AHP) can be used to determine the weights of each indicator, and the weight values ​​can be calculated by constructing a judgment matrix, such as setting the weights for the scope of influence. Change risk weights Cost factor weight Change the timeliness weight And the reasonableness of the weight allocation is ensured through a consistency check, with the consistency ratio being [missing information]. .

[0088] The change impact parameters can be calculated using the following formula:

[0089] Where S represents the change impact parameter, A represents the impact scope parameter, B represents the change risk parameter, C represents the cost change parameter, and D represents the change timeliness parameter. Indicates the weight of the scope of influence. This indicates a change in risk weights. Indicates the weight of cost factors. This indicates the weight of the change in timeliness.

[0090] This application achieves a scientific assessment of change impact by quantifying multi-dimensional information such as scope of impact, risk, cost, and timeliness, and combining it with preset weight parameters to calculate change impact parameters. The resulting change impact parameters provide a reliable basis for determining the subsequent change level, thereby improving the efficiency of change management and the scientific nature of decision-making.

[0091] In one optional embodiment of this application, the method further includes the following steps: S31, Determine the approval path and approval time for the change task based on the change level; S32, in response to the completion of the change task according to the approval path and approval time, execute the change task on the initial product to obtain the target product.

[0092] In this embodiment, the approval path and duration of a change task can be determined based on the change level. Upon completion of the change task approval according to the path and duration, the change task is executed on the initial product to obtain the target product. The approval path refers to the sequence of review nodes that a design change must pass through in the approval process, consisting of different roles or departments arranged sequentially. The approval path ensures that the change receives necessary technical, quality, and business reviews before implementation. The approval duration refers to the maximum allowed or expected time for the design change to remain at each node in the approval path. This duration can be differentiated based on the change level and urgency to control approval process efficiency and prevent delays.

[0093] In practical implementation, an approval process template library can be built based on the BPMN 2.0 (Business Process Model and Annotation 2nd Edition) standard.

[0094] The approval process for major changes includes review by the applying department manager, review by the technical department, review by the quality department, review by the finance department, review by the purchasing department, review by the production department, approval by the chief engineer, and approval by the general manager.

[0095] The approval process for significant changes includes review by the requesting department manager, review by the technical department, review by the quality department, review by relevant business departments, and approval by the chief engineer.

[0096] The typical approval process for changes includes review by the requesting department manager, assessment by the technical department, and approval by the department head.

[0097] The approval process supports custom editing of workflow templates, allowing users to add, delete, or adjust the order of approval nodes.

[0098] Then, based on the product type, department, and assessed change level involved, the system automatically matches the corresponding approver. The priority order for matching is: change level is the highest, followed by product type, and finally, the department involved. When the target approver has a time conflict or abnormal permissions, the system automatically assigns the approval task to their pre-designated authorized agent. Agent information is dynamically obtained through a real-time data interface with the enterprise OA system, ensuring the accuracy and timeliness of the assignment information.

[0099] State machines can also be used to manage the approval process status, which includes "pending submission", "pending review", "under review", "approved", "rejected" and "withdrawn". Once a node is approved, the process automatically moves to the next node and notifies the approver through multiple channels such as email, SMS and WeChat.

[0100] This application also includes an approval timeout reminder mechanism. The approval time limit for each stage of major changes is 48 hours, for important changes it is 24 hours, and for general changes it is 8 hours. If the approval is not completed within the time limit, it will be automatically escalated to its superior approver.

[0101] This application automates and streamlines the approval process for change tasks by setting approval paths and durations based on change levels. This further enhances the transparency and efficiency of the approval process and effectively reduces approval delays and human error.

[0102] In one optional embodiment of this application, the step of performing a modification task on the initial product to obtain the target product includes: S41, split the change task into several change sub-tasks; S42, execute several change sub-tasks on the initial product respectively, and collect several execution progress data corresponding to several change sub-tasks based on the preset monitoring frequency during the execution process; S43, compare several execution progress data with the preset progress benchmarks corresponding to each of the changed subtasks to obtain several progress deviation data; S44, If any progress deviation data exceeds the preset warning threshold, generate and display the warning information for the changed subtask. S45, if several execution progress data have reached the completion status, determine that the change task has been completed and obtain the target product.

[0103] In this embodiment, a change task can be broken down into several sub-tasks. These sub-tasks may include design changes, drawing releases, procurement changes, production process adjustments, inventory management, and inspection standard updates. Each sub-task has a corresponding responsible person, start and end dates, and deliverables. In practical implementation, a Work Breakdown Structure (WBS) can be used to decompose the change task into a hierarchical structure of smaller work units based on manageability and deliverability principles. Each unit has a clear scope, responsibility, and deliverables. The sub-task hierarchy does not exceed three levels, and a Gantt chart can be used to display the task plan.

[0104] Several modification sub-tasks are executed on the initial product. During execution, based on a preset monitoring frequency, several execution progress data points corresponding to these modification sub-tasks are collected. The monitoring frequency refers to the periodic setting at which the system automatically collects task progress data at preset time intervals, such as once per hour, every two hours, or once per day. This is used to track the regularity of the execution process and can be customized according to actual needs. Execution progress data can refer to quantitative information reflecting the task completion status collected at the monitoring frequency during the execution of the modification sub-tasks, such as completion percentage, elapsed man-hours, deliverable submission status, or key milestone achievement indicators.

[0105] In practice, the execution progress data of each change subtask can be collected in real time. Specifically, the execution progress data of the design change subtask is obtained through document status changes in the PLM system, the execution progress data of the procurement change subtask is obtained through order status updates in the ERP system, and the execution progress data of the production process adjustment subtask is obtained through process document version updates in the MES system. The progress data collection frequency can be set to once every 2 hours, and the completion status of each subtask can also be visualized through progress bars and percentages.

[0106] Several execution progress data points are compared with the preset progress benchmarks corresponding to the changed subtasks to obtain several progress deviation data points. If any progress deviation data point exceeds a preset warning threshold, a warning message for the changed subtask is generated and displayed. The progress deviation data refers to the quantified value of the deviation calculated by comparing the actual execution progress of the changed subtask with its preset planned progress, and can be expressed as a percentage of time lag or workload difference. The warning threshold is a pre-set critical value used to determine whether the progress deviation has reached a point where an alarm should be triggered; it can be set according to actual conditions.

[0107] In practice, when the execution progress data of a subtask lags behind the planned progress by more than 20% or an abnormal situation occurs, an early warning mechanism can be triggered. The early warning levels are divided into yellow, orange and red warnings. The early warning information can be pushed through system pop-ups and the responsible person's mobile APP (application), and an exception handling work order will be automatically generated and assigned to the relevant person in charge.

[0108] When all execution progress data reaches the completion status, that is, when all change subtasks have been completed, it can be determined that the change task has been completed and the target product has been obtained.

[0109] This application achieves refined management of the change task execution process by breaking down change tasks into several sub-tasks and collecting execution progress data in real time based on a preset monitoring frequency. By comparing progress deviations with early warning thresholds, timely warning information is generated to ensure early detection and handling of problems. This also improves the transparency and controllability of change execution, ultimately ensuring the efficient completion of change tasks and the achievement of the target product.

[0110] In one optional embodiment of this application, the step of testing the target product based on reference test information to obtain actual product information includes: S51, Generate a reference test task based on the reference test information, and obtain candidate test tasks similar to the reference test task; S52, perform reference test tasks and / or candidate test tasks on the target product to obtain actual product information.

[0111] In the embodiments of this application, a reference test task can be generated based on reference test information, and a candidate test task similar to the reference test task can be obtained. The reference test task and / or the candidate test task can be executed on the target product to obtain the actual test product information.

[0112] Among them, reference test tasks can refer to specific test work instructions for target products, which are transformed from reference test information of reference products, including test items, methods, conditions and acceptance criteria.

[0113] Candidate test tasks can refer to alternative test tasks that are highly similar to the current reference test task in terms of test purpose, object, or method, retrieved from the test case library through similarity matching and other technologies.

[0114] In the specific implementation, firstly, corresponding reference test tasks are generated based on the test items and standards recorded in the reference test information. Then, based on the content of these tasks, candidate test tasks with similar purposes or methods can be matched from the change database as supplementary tasks. Next, the aforementioned reference and candidate test tasks are executed on the target product for which changes have been completed, and all performance and quality data generated during the testing process are fully recorded. Finally, the data is summarized to form actual product information including measured indicators, functional status, and verification results.

[0115] This application generates reference test tasks by referencing test information and obtains candidate test tasks using similarity matching technology, achieving intelligent generation and optimization of test tasks for the target product. This not only improves the efficiency of test task generation but also enriches the diversity of test schemes by introducing candidate test tasks, ensuring comprehensive test coverage. Simultaneously, executing reference test tasks and / or candidate test tasks on the target product effectively verifies its performance and quality, ensuring it meets design requirements and expected standards. This enhances the scientific nature of the testing process and the reliability of the test results, providing strong support for product quality assurance.

[0116] In one optional embodiment of this application, the initial product information includes initial performance data, initial cost data, and initial quality data; the expected product information includes expected performance data, expected cost data, and expected quality data; and the measured product information includes measured performance data, measured cost data, and measured quality data.

[0117] In practice, after the change is implemented, measured performance data, measured cost data, and measured quality data can be collected. Measured performance data is obtained through bench tests and road tests. Measured cost data is extracted from the cost accounting module of the ERP system. Measured quality data is collected from the quality traceability module of the MES system and the customer feedback module of the CRM system. The data collection period can be set to 3 months after the change is completed, or it can be set according to the actual situation.

[0118] Initial performance data can refer to the measured values ​​of the product's technical indicators in terms of functionality, efficiency, and reliability before the implementation of the change.

[0119] Initial cost data can refer to the statistical records of the expenses incurred in the product's materials, production, management, and other aspects before the change is implemented.

[0120] Initial quality data can refer to the product's quality status records in terms of pass rate, defect rate, and customer complaints before the change is implemented.

[0121] Expected performance data can refer to the target technical indicators such as functionality, efficiency, and reliability that the product is expected to achieve after the changes are completed.

[0122] Expected cost data can refer to the target cost range for materials, production, management, and other aspects that are allowed or planned to be invested after the change is completed.

[0123] Expected quality data can refer to the target quality levels that the product is expected to achieve after the change, such as pass rate, defect rate, and customer satisfaction.

[0124] Actual performance data can refer to the results of technical indicators such as function, efficiency, and reliability obtained from actual testing of the modified product.

[0125] Actual cost data can refer to the statistical results of expenses actually incurred in the material, production, and management aspects during the implementation of the change.

[0126] Actual quality data can refer to the pass rate, defect rate, and customer feedback of the modified product in actual production.

[0127] The steps for determining the design change test results of the target product based on initial product information, measured product information, and expected product information include: S61, determine the effect of performance changes based on initial performance data, measured performance data and expected performance data; S62, determine the effect of cost changes based on initial cost data, measured cost data and expected cost data; S63, determine the effect of quality changes based on initial quality data, measured quality data and expected quality data; S64. Determine the design change test results based on the effects of performance changes, cost changes, and quality changes.

[0128] In this embodiment, the performance change effect can be determined based on initial performance data, measured performance data, and expected performance data. The performance change effect can refer to the achievement rate of the performance improvement target.

[0129] In practical implementation, the effect of performance changes can be calculated using the following formula:

[0130] A performance improvement target achievement rate of ≥90% is considered excellent, 70%-90% is considered good, and <70% is considered unsatisfactory.

[0131] In this embodiment, the effect of cost changes can be determined based on initial cost data, measured cost data, and expected cost data. The effect of cost changes can refer to the achievement rate of cost optimization goals.

[0132] In practice, the effect of cost changes can be calculated using the following formula:

[0133] A cost optimization target achievement rate of ≥90% is considered excellent, a cost optimization target achievement rate of 70%-90% is considered good, and a cost optimization target achievement rate of <70% is considered unsatisfactory.

[0134] In this embodiment, the effect of quality change can be determined based on initial quality data, measured quality data, and expected quality data. The effect of quality change can refer to the achievement rate of quality improvement dimension targets.

[0135] In practical implementation, the effect of quality changes can be calculated using the following formula:

[0136] A quality improvement target achievement rate of ≥90% is considered excellent, a quality improvement target achievement rate of 70%-90% is considered good, and a quality improvement target achievement rate of <70% is considered unsatisfactory.

[0137] In this embodiment, design change test results can be generated comprehensively based on the effects of performance changes, cost changes, and quality changes.

[0138] This application quantifies the effects of performance, cost, and quality changes by comparing initial, measured, and expected performance, cost, and quality data, and generates design change test results based on target achievement rates. Formulaic calculations ensure the objectivity and accuracy of the evaluation process, while a tiered standard visually presents the effects of the changes, facilitating rapid assessment of their effectiveness. The comprehensive evaluation results across performance, cost, and quality dimensions fully reflect the overall impact of design changes, providing a scientific basis for subsequent decision-making and enhancing the systematic nature and reliability of design change testing.

[0139] In one optional embodiment of this application, the method further includes the following steps: S71, the initial product and change content information, initial product information, expected product information, change type, change level, change task, reference test information, target product and feature vector are associated and stored in the change database; among them, the change type and feature vector are used as incremental training samples to incrementally train the design change classification model.

[0140] In this embodiment, the initial product and change content information, initial product information, expected product information, change type, change level, change task, reference test information, target product and feature vector can be associated and stored in the change database.

[0141] In practical implementation, a structured change database can be built. This database can store basic information about historical changes, classification results, hierarchical evaluation data, approval process records, execution process data, and effect evaluation reports. A relational database can be used to store structured data, while a file server can be used to store unstructured data such as attachments. The change database uses MySQL (an open-source relational database management system) and supports retrieval by change type, change level, product model, etc.

[0142] In this embodiment, the change type and feature vector can be used as incremental training samples to incrementally train the design change classification model.

[0143] In practical implementation, the design change classification model can be optimized periodically. Based on newly accumulated change data, the model can be retrained, and kernel function parameters and penalty coefficients can be adjusted. Furthermore, the least squares method can be used to optimize the weights for impact scope, change risk, cost factors, and change timeliness, ensuring that the deviation rate between the assessment results and the actual change impact is less than 5%. Performance metrics before and after optimization are recorded to continuously improve accuracy.

[0144] This application constructs a structured change database, linking and storing initial products with change-related information to support efficient retrieval and data management. Simultaneously, by utilizing change types and feature vectors as incremental training samples, the design change classification model is periodically optimized, improving its accuracy and adaptability, and providing reliable data support for the classification and evaluation of design changes.

[0145] This application utilizes TF-IDF feature extraction and SVM classification algorithms to automatically classify change types, reducing subjective human judgment and achieving high classification accuracy. The model is continuously optimized through learning. A multi-dimensional quantitative evaluation index system is established, employing a weighted summation algorithm to calculate a comprehensive score to determine the change level. The evaluation process is transparent and traceable, ensuring objective and fair classification results. Based on the change level, the approval process is automatically matched, enabling intelligent allocation and flow control of approval nodes, improving approval efficiency and reducing management costs. Through task decomposition, progress monitoring, and anomaly warnings, the change execution status is monitored in real time, allowing for timely detection and handling of problems, ensuring smooth change implementation. The change effects are verified from multiple dimensions, including performance, cost, and quality, ensuring the achievement of change goals and providing a basis for subsequent improvements. A change case knowledge base is constructed, providing references for new changes through similarity matching, and the model is optimized based on historical data to continuously improve change management capabilities.

[0146] Reference Figure 2 The diagram shows a structural schematic of a product design change management system provided in an embodiment of this application.

[0147] The product design change management system includes a change application and information collection module, a change classification module, a change grading and evaluation module, a change approval process management module, a change execution and tracking module, a change effect verification module, and a knowledge base and optimization module.

[0148] The Change Request and Information Collection module is used to receive design change requests submitted by change applicants, collect structured change information related to the changes, and provide a data foundation for subsequent classification and grading.

[0149] The change classification module automatically categorizes change types based on change feature information by designing a change classification model.

[0150] The change classification assessment module performs quantitative assessments based on parameters such as the scope of impact of the change, the risk of the change, the cost of the change, and the timeliness of the change, calculates the impact parameters of the change, and then determines the change level.

[0151] The change approval process management module dynamically matches the corresponding approval process based on the change level, enabling automatic allocation and flow control of approval nodes.

[0152] The change execution and tracking module is used to monitor the progress of changes in the design, procurement, and production stages, and to record key milestone information.

[0153] The change effect verification module verifies whether the change effect has achieved the expected goals by comparing product performance data, cost data, and quality data before and after the change.

[0154] The knowledge base and optimization module store historical change cases and handling experience. It provides reference for new changes through case similarity matching, and continuously optimizes the design change classification model and the weights of impact scope parameters, change risk parameters, cost change parameters, and change timeliness parameters based on historical data.

[0155] Reference Figure 3 The diagram illustrates a flowchart of steps for determining a change category according to an embodiment of this application.

[0156] The classification module includes a feature extraction unit, a classification model training unit, and an automatic classification unit.

[0157] The feature extraction unit is used to preprocess the changed text information, including word segmentation, stop word removal, word vector conversion, extraction of changed feature keywords, and calculation of keyword weights of feature keywords using the TF-IDF algorithm.

[0158] The classification model training unit is used to construct a classification model using the Support Vector Machine (SVM) algorithm. Change types are categorized into ten major types: material change, functional change, performance change, structural change, color change, size change, control program software change, interface definition change, chip replacement change, and electronic component change. The change classification model uses feature vectors from historical change cases as training samples. Key model parameters, such as the penalty coefficient C, kernel function type, and the specific value of its parameter γ, can be optimized using cross-validation. For example, the penalty coefficient C can be set to 1.0, and the kernel function can be a radial basis function (RBF). The value can be set to 0.1.

[0159] The automatic classification unit is used to input the feature vector corresponding to the initial product, which is also the feature vector of the new change application, into the trained design change classification model, and output the change type and confidence level. When the confidence level is ≥0.85, the change type is directly determined; when the confidence level is <0.85, the change application is pushed to the expert review queue, and the expert manually confirms the change type. At the same time, the expert confirmation result is added to the training set as a new sample, and the design change classification model is retrained periodically.

[0160] Reference Figure 4 The diagram illustrates a flowchart of the steps for design change approval according to an embodiment of this application.

[0161] The change approval process management module includes a process configuration unit, a node allocation unit, and a flow control unit.

[0162] The process configuration unit is used to build an approval process template library based on the BPMN 2.0 standard.

[0163] The approval process for major changes includes review by the applying department manager, review by the technical department, review by the quality department, review by the finance department, review by the purchasing department, review by the production department, approval by the chief engineer, and approval by the general manager.

[0164] The approval process for significant changes includes review by the requesting department manager, review by the technical department, review by the quality department, review by relevant business departments, and approval by the chief engineer.

[0165] The typical approval process for changes includes review by the requesting department manager, assessment by the technical department, and approval by the department head.

[0166] The approval process supports custom editing of workflow templates, allowing users to add, delete, or adjust the order of approval nodes.

[0167] The node allocation unit automatically matches the appropriate approver based on the product type, department, and assessed change level involved in the change. The priority order for matching is: change level highest, followed by product type, and finally, department involved. When the target approver has a time conflict or abnormal permissions, the approval task is automatically assigned to their pre-designated authorized agent. Agent information is dynamically obtained through a real-time data interface with the enterprise OA system, ensuring the accuracy and timeliness of the allocation information.

[0168] The workflow control unit uses a state machine to manage the approval process status. Approval process statuses include "Pending Submission," "Pending Review," "Under Review," "Approved," "Rejected," and "Withdrawn." Once an approval at a certain stage is approved, the process automatically moves to the next stage and notifies the approver via multiple channels, including email, SMS, and WeChat. An approval timeout reminder mechanism is also in place: 48 hours for major changes, 24 hours for important changes, and 8 hours for general changes. If approval is not granted within the time limit, it is automatically escalated to the next higher-level approver.

[0169] Reference Figure 5 The diagram illustrates a flowchart of a product design change management method according to an embodiment of this application.

[0170] Step 1: Change Request and Information Collection: The applicant submits a change request through the system and fills out a standardized form. The system automatically retrieves relevant data from the company's various information systems. The information verification unit verifies the collected information and generates a change request number upon successful verification. Step 2: Automatic Change Classification: The feature extraction unit extracts features from the changed content and generates feature vectors. The automatic classification unit inputs the feature vectors into the trained SVM classification model to determine the change type. Low-confidence results are reviewed and confirmed by experts. Step 3: Change Classification Assessment: The indicator quantification unit quantifies and scores the scope of impact, risk level, cost factors, and time urgency; the weight determination unit determines the weight of each indicator using the AHP method; and the comprehensive score calculation unit calculates the comprehensive score according to the weighted summation formula to determine the change level. Step 4: Approval process matching and execution: The change approval process management module matches the corresponding approval process according to the change level, the node allocation unit automatically assigns approvers, the flow control unit manages the status and flow of the approval process, notifies approvers through multiple channels, and monitors the approval progress; Step 5: Change Execution and Tracking: The task decomposition unit breaks down the change execution into sub-tasks, the progress monitoring unit collects progress data in real time and displays it visually, and the anomaly warning unit issues warnings for delays or abnormal situations and generates processing work orders. Step 6: Verification of Change Effect: The data acquisition unit collects relevant data after the change, the comparative analysis unit calculates the difference rate and the target achievement rate, and the effect evaluation unit evaluates the effect of the change from multiple dimensions and generates an evaluation report; Step 7: Knowledge Accumulation and Model Optimization: The knowledge base stores the cases of this change, the similarity matching unit provides reference cases for new changes, and the model optimization unit regularly optimizes the classification and grading models based on historical data.

[0171] Reference Figure 6 The diagram shows a structural schematic of a product design change testing device according to an embodiment of this application. The device includes: The change request acquisition module 601 is used to acquire the design change request of the initial product and determine the structured change information based on the design change request; the structured change information includes change content information, initial product information and expected product information; The change information determination module 602 is used to determine the change type, change level, and change task based on the change content information. The reference product search module 603 is used to search for reference products similar to the initial product and reference test information of the reference products from a preset change database based on the change content information, the change type and the change level. Design change execution module 604 is used to execute the change task on the initial product to obtain the target product; The target product testing module 605 is used to test the target product according to the reference testing information to obtain the actual product information. The test result acquisition module 606 is used to determine the design change test result of the target product based on the initial product information, the actual product information and the expected product information.

[0172] The changed information includes at least one of the following: changed text information, related object information, risk analysis information, cost change information, and timeliness information; The change information determination module 602 includes: The first information determination submodule is used to extract at least one keyword from the changed text information and determine the feature weights corresponding to at least one keyword. The second information determination submodule is used to generate a feature vector of the changed text information based on the keyword and the feature weight corresponding to the keyword. The third information determination submodule is used to input the feature vector into the trained design change classification model for classification, and to obtain the candidate change type and the confidence level of the candidate change type. The fourth information determination submodule is used to determine the candidate change type as the change type when the confidence level is greater than or equal to a preset confidence level threshold. The fifth information determination submodule is used to determine the change impact parameters based on the associated object information, the risk analysis information, the cost change information, and the timeliness information; The sixth information determination submodule is used to determine the change level based on the change impact parameters; The seventh information determination submodule is used to generate the change task based on the change text information, associated object information, risk analysis information, cost change information, and timeliness information.

[0173] In one optional embodiment of this application, the fifth information determination submodule includes: The first parameter determination unit is used to determine the influence range parameter based on the associated object information; The second parameter determination unit is used to determine the change risk parameters based on the risk analysis information. The third parameter determination unit is used to determine cost change parameters based on the cost change information. The fourth parameter determination unit is used to determine the change timeliness parameters based on the timeliness information; The fifth parameter determination unit is used to determine the change impact parameters based on the impact range parameter, the change risk parameter, the cost change parameter, the change timeliness parameter, and the preset weight parameter.

[0174] In one optional embodiment of this application, the apparatus further includes: The approval information acquisition module is used to determine the approval path and approval time of the change task based on the change level. The change triggering module is used to execute the change task on the initial product to obtain the target product in response to the completion of the change task approval according to the approval path and the approval time.

[0175] In one optional embodiment of this application, the design change execution module 604 includes: The first execution submodule is used to split the change task into several change subtasks; The second execution submodule is used to execute several of the change sub-tasks on the initial product respectively, and during the execution process, collect several execution progress data corresponding to several change sub-tasks based on a preset monitoring frequency; The third execution submodule is used to compare the execution progress data with the preset progress benchmarks corresponding to each of the modified subtasks to obtain several progress deviation data. The fourth execution submodule is used to generate and display the warning information of the changed subtask if any of the progress deviation data exceeds the preset warning threshold. The fifth execution submodule is used to determine that the change task has been completed and the target product is obtained when all of the aforementioned execution progress data have reached the completion status.

[0176] In one optional embodiment of this application, the target product testing module 605 includes: The first test submodule is used to generate a reference test task based on the reference test information and obtain candidate test tasks similar to the reference test task. The second testing submodule is used to perform the reference test task and / or the candidate test task on the target product to obtain the actual test product information.

[0177] In one optional embodiment of this application, the initial product information includes initial performance data, initial cost data, and initial quality data; the expected product information includes expected performance data, expected cost data, and expected quality data; and the measured product information includes measured performance data, measured cost data, and measured quality data. Test result acquisition module 606 includes: The first result acquisition submodule is used to determine the performance change effect based on the initial performance data, the measured performance data, and the expected performance data. The second result acquisition submodule is used to determine the cost change effect based on the initial cost data, the measured cost data and the expected cost data; The third result acquisition submodule is used to determine the effect of quality change based on the initial quality data, the measured quality data and the expected quality data. The fourth result acquisition submodule is used to determine the design change test results based on the performance change effect, the cost change effect, and the quality change effect.

[0178] In one optional embodiment of this application, the apparatus further includes: The database storage module is used to associate and store the initial product with the change content information, the initial product information, the expected product information, the change type, the change level, the change task, the reference test information, the target product, and the feature vector in the change database; wherein, the change type and the feature vector are used as incremental training samples to incrementally train the design change classification model.

[0179] As the apparatus embodiment is basically similar to the method embodiment, it is described in a relatively simple manner. For relevant details, please refer to the description of the method embodiment.

[0180] An embodiment of this application also provides an electronic device, which may include a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, it implements the method described above.

[0181] An embodiment of this application also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, it implements the method described above.

[0182] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0183] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0184] Those skilled in the art will understand that embodiments of this application can be provided as methods, apparatus, or computer program products. Therefore, embodiments of this application can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of this application can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0185] This application describes embodiments with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0186] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0187] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0188] Although preferred embodiments of the present application have been described, those skilled in the art, upon learning the basic inventive concept, can make other modifications and updates to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all modifications and updates falling within the scope of the embodiments of the present application.

[0189] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes the aforementioned element.

[0190] The above provides a detailed description of the product design change testing method, apparatus, equipment, and medium. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A product design change testing method, characterized in that, The method includes: Obtain the initial product design change request, and determine the structured change information based on the design change request; the structured change information includes change content information, initial product information, and expected product information; The change type, change level, and change task are determined based on the changed content information; Based on the change content information, the change type, and the change level, search the preset change database for reference products similar to the initial product and reference test information of the reference products; The target product is obtained by performing the change task on the initial product; The target product is tested based on the reference test information to obtain the actual product information; The design change test results of the target product are determined based on the initial product information, the measured product information, and the expected product information.

2. The method according to claim 1, characterized in that, The changed information includes at least one of the following: changed text information, related object information, risk analysis information, cost change information, and timeliness information; The steps for determining the change type, change level, and change task based on the changed content information include: Extract at least one keyword from the changed text information, and determine the feature weights corresponding to at least one keyword; Generate a feature vector for the changed text information based on the keywords and the feature weights corresponding to the keywords; The feature vector is input into a trained design change classification model for classification to obtain candidate change types and the confidence level of the candidate change types. If the confidence level is greater than or equal to a preset confidence level threshold, the candidate change type will be used as the change type. The change impact parameters are determined based on the associated object information, the risk analysis information, the cost change information, and the timeliness information; The change level is determined based on the change impact parameters; The change task is generated based on the changed text information, associated object information, risk analysis information, cost change information, and timeliness information.

3. The method according to claim 2, characterized in that, The steps for determining the change impact parameters based on the associated object information, the risk analysis information, the cost change information, and the timeliness information include: Determine the scope of influence parameters based on the associated object information; The risk parameters for change are determined based on the risk analysis information. Determine the cost change parameters based on the cost change information; The change timeliness parameters are determined based on the aforementioned timeliness information; The change impact parameters are determined based on the impact scope parameter, the change risk parameter, the cost change parameter, the change timeliness parameter, and the preset weight parameter.

4. The method according to claim 1, characterized in that, The method further includes: The approval path and approval time for the change task are determined based on the change level. In response to the completion of the change task according to the approval path and the approval time, the change task is executed on the initial product to obtain the target product.

5. The method according to claim 2, characterized in that, The steps of performing the change task on the initial product to obtain the target product include: The change task is broken down into several change sub-tasks; Several change sub-tasks are executed on the initial product, and during the execution, several execution progress data corresponding to the several change sub-tasks are collected based on a preset monitoring frequency. The execution progress data are compared with the preset progress benchmarks corresponding to the modified sub-tasks to obtain several progress deviation data. If any of the aforementioned progress deviation data exceeds the preset warning threshold, then a warning message for the changed subtask is generated and displayed. If all of the aforementioned execution progress data reach a completion status, the change task is determined to be completed, and the target product is obtained.

6. The method according to claim 1, characterized in that, The step of testing the target product based on the reference test information to obtain the actual product information includes: A reference test task is generated based on the reference test information, and candidate test tasks similar to the reference test task are obtained. Perform the reference test task and / or the candidate test task on the target product to obtain the actual product information.

7. The method according to claim 1, characterized in that, The initial product information includes initial performance data, initial cost data, and initial quality data; the expected product information includes expected performance data, expected cost data, and expected quality data; and the measured product information includes measured performance data, measured cost data, and measured quality data. The steps for determining the design change test results of the target product based on the initial product information, the measured product information, and the expected product information include: The performance change effect is determined based on the initial performance data, the measured performance data, and the expected performance data. The effect of cost changes is determined based on the initial cost data, the measured cost data, and the expected cost data. The effect of the quality change is determined based on the initial quality data, the measured quality data, and the expected quality data. The design change test results are determined based on the effects of the performance changes, the cost changes, and the quality changes.

8. The method according to claim 2, characterized in that, The method further includes: The initial product is associated with and stored in the change database along with the change content information, the initial product information, the expected product information, the change type, the change level, the change task, the reference test information, the target product, and the feature vector; wherein, the change type and the feature vector are used as incremental training samples to incrementally train the design change classification model.

9. A product design change testing device, characterized in that, The device includes: The change request acquisition module is used to acquire design change requests for the initial product and determine structured change information based on the design change requests; the structured change information includes change content information, initial product information, and expected product information; The change information determination module is used to determine the change type, change level, and change task based on the change content information. The reference product search module is used to search for reference products similar to the initial product and reference test information of the reference products from a preset change database based on the change content information, the change type, and the change level. The design change execution module is used to execute the change task on the initial product to obtain the target product; The target product testing module is used to test the target product based on the reference testing information to obtain the actual product information. The test result acquisition module is used to determine the design change test results of the target product based on the initial product information, the actual product information, and the expected product information.

10. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the method as described in any one of claims 1-8.

Images