CN117540894B

CN117540894B - Method, apparatus and storage medium for generating inspection plan

Info

Publication number: CN117540894B
Application number: CN202311527693.5A
Authority: CN
Inventors: 简锦
Original assignee: Xiwei Technology Guangzhou Co ltd
Current assignee: Xiwei Technology Guangzhou Co ltd
Priority date: 2023-11-15
Filing date: 2023-11-15
Publication date: 2024-06-07
Anticipated expiration: 2043-11-15
Also published as: CN117540894A

Abstract

The application discloses a method, equipment and a storage medium for generating an inspection plan, and belongs to the technical field of data processing. The method comprises the following steps: acquiring technical requirements in engineering drawings of a target product, wherein the technical requirements represent technical texts related to the product and sub-products in the product in the process of producing the product; determining a general test rule matched with the technical requirement from a general test rule library, wherein a plurality of general test rules are stored in the general test rule library, and each general test rule is used for indicating at least one test item and a test standard corresponding to each test item; and generating a test plan of the target product according to the universal test rule matched with the technical requirement. According to the scheme, the universal inspection rules matched with the technical requirements are determined in the preset universal inspection rule library, so that an inspection plan is generated, the inspection plans are not needed to be created for the products and the sub-products in the products manually, and the generation efficiency and the accuracy of the inspection plan are improved.

Description

Method, apparatus and storage medium for generating inspection plan

Technical Field

The present application relates to the field of data processing technologies, and in particular, to a method, an apparatus, and a storage medium for generating an inspection plan.

Background

In the quality management control process of manufacturing industry, engineering drawings are often needed in the design process of the product, for example, based on CAD engineering drawings, a designer can mark the sizes, technical requirements, tolerance requirements and the like of all parts in the product in the engineering drawings, and then a test plan of the product is formulated according to the marking information.

Because of the close relationship between the technical requirements and the inspection plans in the engineering drawing, in order to ensure the quality and the safety of the product, the technical requirements of the product must be defined in the engineering drawing, and the corresponding inspection plans must be formulated to verify whether the product meets the requirements. Currently, inspection plans are created manually for individual products (including parts in the product). The number of parts in the engineering drawing is large, and the technical requirements on each part are also very high, so that the manual creation of the scheme of the inspection plan is low in efficiency.

Disclosure of Invention

The application provides a method, equipment and storage medium for generating a test plan, which improve the generation efficiency of the test plan. The technical scheme is as follows:

In a first aspect, there is provided a method of generating a verification plan, the method comprising: obtaining technical requirements in engineering drawings of a target product; determining a universal test rule matched with the technical requirement from a universal test rule library, wherein a plurality of universal test rules are stored in the universal test rule library, and each universal test rule is used for indicating at least one test item and a test standard corresponding to each test item; and generating a test plan of the target product according to a general test rule matched with the technical requirement.

In a second aspect, there is provided an apparatus for generating a verification plan, the apparatus comprising: the acquisition module is used for acquiring the technical requirements in the engineering drawing of the target product; the matching module is used for determining a universal test rule matched with the technical requirement from a universal test rule library, wherein a plurality of universal test rules are stored in the universal test rule library, and each universal test rule is used for indicating at least one test item and a test standard corresponding to each test item; and the generation module is used for generating a test plan of the target product according to the universal test rule matched with the technical requirement.

In a third aspect, there is provided a computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the computer program implementing the method of the first aspect described above when executed by the processor.

In a fourth aspect, a computer readable storage medium is provided, the computer readable storage medium storing a computer program, which when executed by a processor, implements the method of the first aspect.

In a fifth aspect, there is provided a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method of the first aspect described above.

The embodiment of the application provides a method, equipment and a storage medium for generating a verification plan, which are used for acquiring technical requirements in engineering drawings of a target product according to the scheme provided by the application, wherein the technical requirements represent technical texts related to the product and sub-products in the product in the process of producing the product; determining a general test rule matched with the technical requirement from a general test rule library, wherein a plurality of general test rules are stored in the general test rule library, and each general test rule is used for indicating at least one test item and a test standard corresponding to each test item; the general inspection rule library stores a large number of preset general inspection rules, can be reused, and improves efficiency. And generating a test plan of the target product according to the universal test rule matched with the technical requirement. According to the scheme, the universal inspection rules matched with the technical requirements are determined in the preset universal inspection rule library, so that an inspection plan is generated, the inspection plans are not needed to be created for the products and the sub-products in the products manually, and the generation efficiency of the inspection plan is improved. And compared with the problem that the manual creation of the inspection plan is easy to make mistakes due to the fact that the experience of the creator is relied on, the method for generating the inspection plan provided by the scheme further improves the accuracy of the inspection plan.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flow chart of a method of generating a verification plan provided by an embodiment of the present application;

FIG. 2 is an exemplary schematic diagram of one technical requirement provided by an embodiment of the present application;

FIG. 3 is an exemplary diagram of a generic verification rule provided by an embodiment of the present application;

FIG. 4 is a flow chart of another method of generating a verification plan provided by an embodiment of the present application;

FIG. 5 is a flow chart of yet another method of generating a verification plan provided by an embodiment of the present application;

FIG. 6 is an exemplary schematic diagram of a correspondence between technical requirements and inspection plans provided by an embodiment of the present application;

FIG. 7 is a flow chart of yet another method of generating a verification plan provided by an embodiment of the present application;

FIG. 8 is a flow chart of yet another method of generating a verification plan provided by an embodiment of the present application;

FIG. 9A is a schematic illustration of an engineering drawing provided by an embodiment of the present application;

FIG. 9B is a schematic diagram of a text recognition result of an engineering drawing according to an embodiment of the present application;

FIG. 9C is an exemplary diagram of a validation rule provided by an embodiment of the present application;

FIG. 10 is a schematic structural view of an apparatus for generating an inspection plan according to an embodiment of the present application;

fig. 11 is a schematic structural diagram of a computer device according to an embodiment of the present application.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the embodiments of the present application will be described in further detail with reference to the accompanying drawings.

It should be understood that references to "a plurality" in this disclosure refer to two or more. In the description of the present application, "/" means or, unless otherwise indicated, for example, A/B may represent A or B; "and/or" herein is merely an association relationship describing an association object, and means that three relationships may exist, for example, a and/or B may mean: a exists alone, A and B exist together, and B exists alone. In addition, in order to facilitate the clear description of the technical solution of the present application, the words "first", "second", etc. are used to distinguish the same item or similar items having substantially the same function and function. It will be appreciated by those of skill in the art that the words "first," "second," and the like do not limit the amount and order of execution, and that the words "first," "second," and the like do not necessarily differ.

Before explaining the embodiments of the present application in detail, application scenarios and related techniques of the embodiments of the present application are described.

Inspection plans (which may also be referred to as inspection plan files) are important for quality management. The method is an important link of quality management, can help enterprises to reduce quality risks, improve product quality and strengthen market competitiveness of the enterprises. The importance of the inspection plan to quality management is embodied in several aspects: 1. ensuring that the product meets the quality requirement: the inspection plan can help enterprises to effectively control the quality of products, ensure that the products can meet the requirements and standards of clients, and avoid economic loss and reputation damage caused by the quality problem of the products. 2. The production efficiency is improved: invalid inspection and repeated inspection can be avoided through scientific inspection plan making, quality hidden trouble in production is eliminated, and production efficiency is improved. 3. Improving the quality standardization level: inspection planning requires scientific definition of product quality requirements according to relevant standards and regulations, thereby promoting enterprise quality management standardization. 4. Better obeys market demand: the quality requirements of products are evaluated according to market demands in the establishment of the inspection plan, and the detection method and the quality standard are continuously improved, so that the demands of customers and the market demands are met.

The establishment of a test plan (Standard Inspection Plan) by the traditional quality department generally has the following technical problems: 1. relying on manual experience: traditional methods of planning rely primarily on experience and skill of inspectors, lack of standardized and scientific methods, and may vary from inspector to inspector. 2. Low efficiency: the traditional formulation method needs to consume a great deal of time and labor cost, and is not beneficial to production and efficiency improvement. 3. The quality is poor: because of the lack of a standardized method in planning, the quality inspection planning precision and accuracy are lower, and erroneous judgment is easy to cause. 4. Non-real-time updating: once the production environment changes or special conditions occur, the plan is difficult to adjust in time, and the actual production requirement cannot be adapted in time. 5. Inconvenient quantitative analysis: the inspection plan of the traditional quality department is difficult to quantitatively analyze, data analysis and optimization improvement are difficult to perform, and quantitative evaluation on the quality improvement effect is difficult to perform.

Currently, enterprises can make inspection plans through manual writing, semi-automatic methods and algorithm-based methods. However, for manual writing, which requires expertise and experience, is cumbersome and error-prone, and cannot generate a large number of inspection plans in a short time, and the quality of the inspection plans is affected by human factors. For the semi-automatic method, inspection plan generation software is required, parameters are required to be manually selected and adjusted, and the accuracy and standardization of a generated result are difficult to ensure. For the algorithm-based method, a large amount of data training and algorithm optimization are needed, the current performance is poor, the generation efficiency is low, and the complex industrial production environment requirements are difficult to meet. Therefore, the current inspection plan generation method has the technical problems of low inspection plan generation efficiency, low accuracy, low automation degree and the like.

The technical problems affect the efficiency and the precision of the traditional quality department inspection plan making, and limit the improvement space of quality management. Accordingly, there is a need to provide a method of generating a quality inspection plan that improves the accuracy, efficiency, and level of standardization of the quality inspection plan. Based on the above, the application provides a full-automatic rule-based inspection plan generation method, which has the characteristics of high efficiency, accuracy, standardization, automation and the like, and can meet the requirements in different production environments.

The method for generating the inspection plan provided by the embodiment of the application can be applied to computer equipment capable of generating the inspection plan, such as a smart phone, a tablet personal computer, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a server and the like. The embodiments of the present application are not limited in any way by the particular type of computer device.

An embodiment of the present application provides a method for generating a verification plan, as shown in fig. 1, and fig. 1 is a flowchart of a method for generating a verification plan provided by an embodiment of the present application, where the method for generating a verification plan includes:

S101, obtaining technical requirements in engineering drawings of target products.

The engineering drawing of the target product is a technical document used for accurately expressing the shape, the size, related technical requirements, tolerance requirements and the like of the target product. Wherein the technical requirements include at least one of surface roughness, material requirements, process requirements, assembly requirements, identification requirements and safety requirements, that is, the technical requirements in the engineering drawing may be one or more. Technical requirements can be expressed in engineering drawings as specifications on dimensions, shapes, surface roughness, materials, surface treatments and the like, and the specifications are required to meet the requirements of various stages of design, manufacture, field installation and the like.

The target product is a finished product or sub-products in the finished product, and the finished product is formed by assembling a plurality of sub-products. The engineering drawing of the target product can be the engineering drawing of the finished product, and also can be the engineering drawing of a certain sub-product in the finished product. For example, the finished product is a dyeing lamp, the dyeing lamp comprises a machine head and a base, and the engineering drawing can be the engineering drawing of the dyeing lamp or the engineering drawing of the machine head or the base.

Technical requirements in engineering drawings can be manually marked and converted into text forms. The technical requirements in the engineering drawing can be detected through a pre-trained target detection model to obtain the position information of the target frame including the technical requirements, and then the position information of the target frame is input into a target recognition model to be recognized, so that the technical requirements in the engineering drawing are output.

As shown in fig. 2, fig. 2 is an exemplary schematic diagram of a technical requirement provided by an embodiment of the present application, and fig. 2 shows a technical requirement in an engineering drawing of a component, which includes: 1. surface bluing treatment; 2. the edges and corners are blunted.

S102, determining a general inspection rule matched with the technical requirement from a general inspection rule library, wherein a plurality of general inspection rules are stored in the general inspection rule library, and each general inspection rule is used for indicating at least one inspection item and an inspection standard corresponding to each inspection item.

In the embodiment of the application, a plurality of general inspection rules are stored in the general inspection rule base, and the general inspection rules can be applicable to all products with the technical requirements and have universality. Each generic test rule may include at least one test characteristic, each test characteristic including a test item and test criteria for the test item, and may include other characteristics of test method, test type, etc. That is, each generic inspection rule includes at least one inspection item that corresponds to an inspection standard, e.g., the inspection item is a bolt surface finish, and the inspection standard is whether the bolt surface finish is greater than a preset finish threshold. The generic verification rules may also include verification methods, batch requirements, and the like.

Illustratively, each generic inspection rule includes one or more inspection items, each inspection item having a corresponding inspection standard. In addition, each inspection item may also have a corresponding inspection method, batch requirements, etc., which are not limited by the embodiment of the present application.

FIG. 3 is a schematic illustration of a generic verification rule provided by an embodiment of the present application, as shown in FIG. 3; the general inspection rules shown in fig. 3 are general inspection rules for plastics, and include security, appearance, packaging requirements, and property names (i.e., inspection items) such as data cores, each of which corresponds to a property number, and are shown in fig. 3 as VIS00001-VIS00004, the inspection standards of each inspection item are all satisfying the general inspection standards of plastics, and the inspection types of each inspection item are all visual.

When rule matching is performed, keywords or semantic representations in technical requirements can be extracted, and a universal checking rule matched with the keywords or semantic representations is searched in a universal checking rule base and used as the universal checking rule matched with the technical requirements. For example, the keyword or the semantic representation may be represented in the form of a vector, and among a plurality of general test rules, vector similarity between the keyword or the semantic and each general test rule is calculated to obtain a plurality of vector similarities, and the general test rule corresponding to the maximum similarity value among the plurality of vector similarities is used as the general test rule matched with the technical requirement. Of course, other methods may be used to perform rule matching in the present solution, which is not limited to the embodiment of the present application.

In some embodiments, a plurality of test rule files corresponding to the plurality of general test rules one-to-one are stored in the general test rule base, each test rule file for defining a corresponding general test rule, each general test rule file including at least one rule described in a rule language, each rule including a trigger condition and an execution action.

The generic verification rules need to be described in a structured language (i.e., rule language) in order to be recognizable by the computer device when rule matching is performed. Among them, rule Language (Rule Language) includes, but is not limited to: drools, CLIPS, JESS, etc. Or may be implemented in some programming language (e.g., java, python, C ++, etc.). The verification rules are realized by selecting a proper rule language, and the general verification rules are stored by adopting a structured language (namely, the rule language), so that the verification rules can be recognized by computer equipment when the rules are matched later, and the matching efficiency is improved. And by defining the structured data standard, the data is converted into a computer readable data format, namely, the data is described by adopting a rule language, so that the program processing is convenient, and the consistency of the data can be maintained.

Each inspection rule file is used to define a corresponding generic inspection rule, i.e., a rule form. The trigger condition is used for indicating whether the inspection standard of one or more inspection items is met, and the execution action is used for indicating actions executed under different judging results of the trigger condition.

One general Rule corresponds to a Rule file, and one general Rule file includes at least one Rule, each Rule is composed of a premise and a conclusion, the former is used for judging whether a Condition is satisfied, the latter is used for executing a specific task or generating a specific result, and one Rule (Rule) contains a triggering Condition (Condition) and an executing Action (Action). Wherein the trigger condition is a combination of check data and business logic defining a rule trigger condition, which may include one or more conditions; an action refers to an operation performed after a rule is triggered, and may be a function, writing a log, sending a mail, triggering other rules, etc.

Rules define trigger conditions and execution actions, which are the basic units of a rule matching engine for executing the generation method of the inspection plan, encapsulating logic to solve specific problems. The rule contains one or more conditions (as trigger conditions), and an action that is performed when all conditions are satisfied. A rule describing the state of a business logic or a data, which may be written in the form of a plague language, requires defining trigger conditions and performing actions.

Illustratively, the rule indicates that "when the order amount is greater than 100, discount 10% is applied" is explained as an example.

Rule order amount greater than 100'

when

$order：Order(amount>100)

then

$order.apply Discount(0.1)；

end

The conditions to be defined in the above rules may generally be expressed in the form of object attributes, such as order: order (amount100), where Order is the Order object and amountis the Order amount attribute. The action to be defined in the rule may be a function, writing a log, sending a mail, triggering other rules, etc. The following is a simple example of the actions: $order, applied discover (0.1), here $order represents an order object satisfying the condition, apply discover is one method of order object, 0.1 is a Discount value.

The verification rule file is the most basic component of a rule base (including general verification rules or special verification rules), and is typically used to store all rule definitions and written in a rule language. One or more rules may be included in the verification rule file, each rule consisting of preconditions and conclusions, and may include various types of input and output data. The verification rules may be stored in the form of a decision table, which is a spreadsheet-like structure for storing content information for the rules. Typically, the rows of the decision table represent preconditions for the rules, the columns represent conclusions and conditions for the rules, and the cells are written with actions or results specified by the corresponding rules. The rule is stored by using the decision table, so that the rule can be written more conveniently, quickly and intuitively. The data structure of the decision table is a common rule definition in the rule matching engine (the generation method used to execute the inspection plan). By defining elements such as rows, columns, cells, grouping standards, judging modes and the like, rules in a rule base can be effectively managed, and more efficient rule judgment and operation can be realized.

The data structure for constructing the decision table is as follows: (1) The decision table includes rows and columns, the rows representing preconditions in the rule, the columns representing conclusions and conditions of the rule. (2) The cells in the decision table represent the content and actions of the rule, typically used to write the corresponding rule operation. (3) Typically the rule matching engine supports grouping rows and columns in a decision table. The grouping criteria in the decision table are used to tell the rule matching engine how to group the rows and columns in the decision table to achieve a more efficient rule determination. (4) decision table also requires a decision mode of specifying rules. Rule matching engines typically support two modes, e.g., sum (AND) AND OR (OR). (5) Each rule base needs to specify one or more rule targets for specifying the application scope and execution result of the rule.

The general inspection rule library of the scheme stores a large number of preset general inspection rules, can be reused, and improves efficiency. And the universal test rules matched with the technical requirements are determined from the universal test rule library, so that the test rules do not need to be manually formulated for each product and sub-products in the products, and the data processing efficiency is improved.

S103, generating a test plan of the target product according to the general test rule matched with the technical requirement.

In the embodiment of the application, the inspection plan is generated according to the inspection items indicated by the matched general inspection rules and the inspection standards corresponding to the inspection items. The inspection plan is the integration of the inspection project related to the target product and the corresponding inspection standard, and can be expressed in written forms such as text, tree diagram, table and the like, and is used for guiding inspection work.

Since the technical requirements may be one or more, the general checking rules may be one or more from the viewpoint of the number of technical requirements. Since the target product is a finished product or a sub-product in the finished product, when the target product is a finished product, the target product may include not only the technical requirements of the finished product but also the technical requirements of the sub-product in the finished product, and thus, from the viewpoint of the number of products, the general inspection rule may be one or more. Since one general inspection rule corresponds to at least one rule, the general inspection rule indicates at least one inspection item, the inspection items and the inspection criteria correspond one-to-one, and thus the number of inspection items may be one or more. Based on the above description, in the case where the number of the common inspection rules is plural and the number of the inspection items is plural, the inspection plan is generated based on the respective inspection items indicated by the respective common inspection rules and the inspection standards corresponding to the respective inspection items.

In the example, the inspection plan is formulated according to the technical requirements in the engineering drawing and is mainly used for verifying whether the product meets the requirements. The verification plan may include the characteristics that should be verified, sampling plan, verification method, reception criteria, etc. The inspection plan is designed by combining the manufacturing process, the production process, the working procedure and the like are monitored and controlled in the manufacturing process, and the finished product is subjected to sampling inspection, full inspection and the like to verify whether the product meets the technical requirements or not so as to ensure the quality of the product. Inspection plans are a series of inspection standards and methods established for products of different characteristics and purposes, including visual inspection, dimensional inspection, durability inspection, etc., to ensure that the quality of the product is controllable. The inspection plan can help to formulate reasonable process parameters and equipment options to ensure that the product meets inspection standards. The inspection plan can standardize operation requirements, reduce operation errors and improve product consistency and quality stability. The inspection plan can also help monitor quality abnormality problems in the production process, adjust the process scheme in time and ensure the product quality.

The method for generating the inspection plan provided by the embodiment of the application is applied to computer equipment, the computer equipment can integrate a rule matching engine, and the computer equipment can realize the method for generating the inspection plan provided by the embodiment of the application through the rule matching engine. Wherein the rule matching engine is used for performing rule matching by utilizing a general checking rule base. For example, after obtaining the technical requirements, the general inspection rules stored in the general inspection rule base are used for matching the corresponding general inspection rules for the technical requirements, and then the matched general inspection rules are used for generating an inspection plan. The general test rule base may be stored in a computer device or a cloud device, which is not limited in the embodiment of the present application.

In one embodiment, the computer device is provided with a product management application, the product management application is integrated with a rule matching engine, and the computer device can realize the method for generating the verification plan provided by the embodiment of the application by running the product management application. The product management application can match the general inspection rules for the technical requirements of any product through the integrated rule matching engine in the running process, and generate an inspection plan of the product or the sub-product in the product based on the matched general inspection rules.

According to the scheme provided by the application, the technical requirements in the engineering drawing of the target product are acquired, wherein the technical requirements represent technical texts related to the product and sub-products in the product in the process of producing the product; determining a general test rule matched with the technical requirement from a general test rule library, wherein a plurality of general test rules are stored in the general test rule library, and each general test rule is used for indicating at least one test item and a test standard corresponding to each test item; the general inspection rule library stores a large number of preset general inspection rules, can be reused, and improves efficiency. And generating a test plan of the target product according to the universal test rule matched with the technical requirement. According to the scheme, the universal inspection rules matched with the technical requirements are determined in the preset universal inspection rule library, so that an inspection plan is generated, the inspection plans are not needed to be created for all products and sub-products in the products manually, and the generation efficiency of the inspection plans is improved. Compared with the phenomenon that the manual creation plan is easy to make mistakes, the method for generating the inspection plan further improves the accuracy of the generated result.

Before the method for generating the inspection plan provided by the embodiment of the application is executed, data (including technical requirements, rules, inspection items, inspection standards, trigger conditions, execution actions and other data) are required to be structured, and the data can be structured and stored in a knowledge warehouse mode in the embodiment. Next, a knowledge base will be described, which is typically a multi-level structure for storing all relevant data, models, business rules, etc. The data in the knowledge warehouse can be centrally managed and used, so that the coordination and sharing of cross-system, cross-department and cross-business scenes are realized, and the efficiency and the value of the whole knowledge base are improved.

The knowledge warehouse data structure for constructing a multi-level structure is as follows: (1) entity class: entity classes in the knowledge store are used to store and manage various business data and related knowledge content, typically including various attributes and features. For example, business objects such as clients, orders, products, etc. may be stored as entity classes, with their attributes and features, respectively. (2) metadata: metadata is a data set for describing entity classes and attributes, and is mainly used for describing information such as classification, relationship, constraint conditions and the like of data, so that a rule matching engine can conveniently process rules. For example, metadata may be defined to describe the relationship of the customer order to limit features such as the maximum value of the order amount. (3) cognitive model: the cognitive model is an important data structure in the rule matching engine that describes the business knowledge and various models in the rule base. The cognitive models typically contain information models, rule models, association models, etc. that describe various models in business processes, business features, business rules, and rule bases. The information model describes information and data in the business, and this model can form a generic language for the rule matching engine to understand and manipulate the data. The data model generally includes entity classes, metadata, attributes, and relationship structures that can be used to describe business entities, relationships between entities, and other data information. The rule model is the core of the rule base and contains the elements of rule such as conditions, actions and events, and the like, and is used for realizing various specific business logics. A rule model typically includes one or more rule bases (including the generic test rule base described above) that contain a set of related rule definitions, each rule definition including elements of conditions, actions, and events. A cognitive model may also include an association model, typically used to describe the relationships between business processes and business features. The association model contains one or more association managers that contain a set of association definitions and association types that describe the correlation between various business features. (4) other data structures: the knowledge store may also contain other common data structures, such as tree structures, graph structures, network structures, etc., for describing and processing various business processes or other related knowledge content.

The cognitive model in (3) above is described below in terms of three aspects, knowledge representation, reasoning mechanism and execution engine.

(1) The knowledge representation is the core of the rule matching engine, which defines the knowledge structure used by the rule matching engine. Rule matching engines typically use a form called Rule Language (Rule Language) to represent knowledge, which is a domain-specific Language used to represent and define rules. Common rule languages include Drools, jess, CLIPS, etc. In a rule matching engine for generating a verification plan, its knowledge representation mainly involves three aspects: product characteristics, inspection criteria, and inspection results. The product characteristics comprise information such as product name, model, material, size and the like; the inspection standard comprises information such as product inspection standard, inspection method and the like; the inspection result includes information of defect type, severity, and number of each product. This knowledge needs to be abstracted and normalized.

(2) The inference mechanism is the core execution portion of the rule matching engine that uses rules in the knowledge base to infer and make decisions. The inference mechanism of the rule matching engine is typically based on forward or backward reasoning. Forward reasoning is to derive a conclusion based on facts, while backward reasoning is to derive a conclusion from objects in reverse. Both of these reasoning mechanisms can be selected and used in combination according to the actual application scenario. After the rule matching engine matches the general test rule for the technical requirement, that is, after the method for generating the test plan provided by the scheme is executed, backward reasoning can be continuously used, the defect type and severity of the part are deduced according to the test standard and the test result, and whether rejection or rework is needed is judged. When the defect type and the severity of one part reach the specified values, the part is considered to be unqualified, and rejection operation is executed; when the defect type and the severity of one part do not exceed the specified values, the part is considered to meet the requirements, and pass operation is executed; otherwise, the part is considered to have certain defects, but the qualification standard can still be achieved through reworking.

(3) The execution engine is the core execution part of the rule matching engine, which is responsible for executing the reasoning results and outputting the final decision results. The execution engine may translate the implementation of the rules into machine-executable instructions to efficiently perform the inference operations. Typically, the execution engine returns the execution result to the application program, so that the application program can respond accordingly according to the result. The execution engine is mainly responsible for executing the conclusion drawn by backward reasoning, and making a subsequent production plan and adjusting the production plan of the parts according to the test result. According to the above rule, when all the parts are inspected, the execution engine can add the inspected parts to the production plan according to the inspection result, reject or rework the unqualified parts, and execute the production plan making operation.

The definition of the rule matching engine and the processing mode of the data processing are described above, so that the generation scheme of the inspection plan provided by the embodiment of the application is executed more efficiently, and the generation efficiency of the inspection plan is improved.

In some embodiments, the method of generating a verification plan further comprises: and (3) obtaining technical requirements in engineering drawings of the target product. That is, S101 in fig. 1 described above can also be realized in the following manner. Detecting engineering drawings through a target detection model to obtain position information of a plurality of target frames, wherein the target frames are used for indicating boundaries of various technical requirements in the engineering drawings, and the target detection model is used for carrying out target detection on images; and identifying the plurality of target frames through a target identification model according to the position information of the plurality of target frames to obtain a text identification result, wherein the text identification result comprises technical requirements in engineering drawings, and the target identification model is used for carrying out character identification on the images.

Wherein, the engineering drawing can be in an image format. The engineering drawing comprises interconnected parts and technical requirements about the parts. Inputting an engineering drawing into a target detection model, searching the outline (or boundary) of an area where a technical requirement is located through the target detection model, adding a rectangular frame to the outline (or boundary), namely marking key information to be identified by the rectangular frame, taking the rectangular frame as a target frame, marking a plurality of target frames, and outputting position information of the plurality of target frames, wherein the position information of the target frame can be coordinate information.

Each target frame is used for indicating the boundary of the area where the technical requirement is located in the engineering drawing, namely, the technical requirement of any part is included in each target frame. Technical requirements in engineering drawings can be expressed by text, and the text can comprise letters, numbers and other characters.

The target detection model in the example is obtained by training a large number of engineering drawing sample sets, and has a function of target detection on images. The target detection model may be a machine learning model, such as convolutional neural network (Convolutional Neural Networks, CNN), recurrent neural network (Recurrent Neural Network, RNN), semi-supervised learning (Semi-Supervised Learning, SSL), or the like. The object detection model may also be an object detection algorithm (object detection) including, but not limited to: an algorithm based on region detection, such as an R-CNN (Regions with CNN features) series target detection algorithm, an algorithm based on region extraction, such as a YOLO series target detection algorithm, and a detection algorithm based on key points, such as an Anchor-Free series target detection model.

In the embodiment of the application, after the position information of a plurality of target frames is obtained, for each target frame, the specific position of the target frame can be found in the engineering drawing according to the position information of the target frame, namely, the image area corresponding to the target frame is found, so that character recognition is carried out on the target frame, and the text recognition result corresponding to the target frame is obtained. The target box in this example indicates the boundary of the area where the technical requirement is located, and the text recognition result may be text about any one or any combination of surface roughness, material requirement, process requirement, assembly requirement, identification requirement, and security requirement. The above recognition process is performed on each of the plurality of target boxes to obtain a text recognition result (i.e., a technical requirement in text form) of the engineering drawing.

The target recognition model in this example is obtained by training a large number of target frame sample sets (including technical requirement samples, tolerance requirement samples and product information samples in engineering drawings, wherein the samples can be in an image format), and has the function of character recognition on images. The object recognition model is a machine learning model, for example, a classification model, a prediction model, and a feature extraction model based on deep learning. The object recognition model may employ any of the following family type models: R-CNN family, which includes but is not limited to R-CNN, FAST-RCNN, FASTER-RCNN; end-to-end YOLO family including, but not limited to YOLO, YOLOV1, YOLOV, YOLOV3, TINY YOLO), SSD (Single Shot Multi Box Detector) family, and the like.

According to the method, the device and the system, the target recognition model is used for carrying out character recognition on the content in the target frames according to the position information of the target frames output by the target detection model and combining engineering drawings, text recognition results (i.e. technical requirements) of the target frames are output, manual labeling of text content on each target frame is not needed, and data processing efficiency is improved. Compared with the phenomena of error marking, missing marking and the like which are easy to occur in manual marking, the drawing information identification accuracy is improved in the example.

According to the embodiment of the application, the object in the engineering drawing is detected through the target detection model, technical requirements and the like of parts in the engineering drawing are marked by the rectangular frame (serving as the target frame), the position information of the target frame is output, and drawing information of the engineering drawing is not required to be manually identified and extracted, so that the target detection efficiency is improved. And identifying the plurality of target frames through a target identification model according to the position information of the plurality of target frames to obtain a text identification result, wherein the text identification result comprises technical requirements in engineering drawings, and the target identification model is used for carrying out character identification on the images. According to the method, the target recognition model is used for recognizing the content in the target frame according to the position information of the target frame output by the target detection model and combining with engineering drawings, the technical requirements of text forms are output, and the drawing information of the engineering drawings is not required to be recognized and extracted manually, so that the data processing efficiency is improved. Compared with the phenomena of error marking, missing marking and the like which are easy to occur in manual marking, the engineering drawing identification method provided by the scheme also improves the accuracy of drawing information identification.

In some embodiments, the universal inspection rule base stores therein universal inspection rules respectively corresponding to different specifications, including a first specification having a corresponding universal inspection rule in the universal inspection rule base and a second specification having no corresponding universal inspection rule in the universal inspection rule base. Based on the description of fig. 1 and the first general verification rule, as shown in fig. 4, fig. 4 is a flowchart of another method for generating a verification plan according to an embodiment of the present application, where the method for generating a verification plan includes:

S201, obtaining technical requirements in engineering drawings of target products.

In this example, S201 is identical to S101 in fig. 1, and the implementation process and the achieved technical effects can be seen in fig. 1, which is not described herein.

S202, under the condition that the general inspection rule library has the first technical requirement of the corresponding general inspection rule, determining the first general inspection rule corresponding to the first technical requirement from the general inspection rule library, wherein the first general inspection rule is a general inspection rule matched with the first technical requirement; the first general inspection rule is used for indicating whether the inspection target product meets at least one inspection item required to be performed by the first technical requirement and the inspection standard of each inspection item.

In the embodiment of the application, the technical requirements can be one or more, some technical requirements can be matched with the corresponding general inspection rule in the general inspection rule base, and some technical requirements can not be matched with the corresponding general inspection rule in the general inspection rule base. For convenience of description, a technical requirement that can be matched to a corresponding general inspection rule is referred to as a first technical requirement, and a technical requirement that cannot be matched to a corresponding general inspection rule is referred to as a second technical requirement. The present example employs a first specification and a second specification to indicate whether a specification can be matched to a verification rule, the first specification and the second specification representing a certain class of specifications and not a certain specification.

In this example, when matching the general test rules for the technical requirements, each technical requirement is matched, and if the general test rule base has the technical requirement (i.e., the first technical requirement) of the corresponding general test rule, the first general test rule corresponding to the first technical requirement is determined from the general test rule base. The first general inspection rule is matched with the first technical requirement, and then at least one inspection item and the inspection standard of each inspection item can be obtained based on the first general inspection rule, and each inspection item is inspected by referring to the inspection standard, so that whether the target product meets the first technical requirement is inspected. And the checking rule is not required to be written for technical requirements manually, so that the data processing efficiency is improved.

S203, receiving a creation operation for creating the check rule for the second technical requirement under the condition that the second technical requirement of the corresponding general check rule does not exist in the general check rule base.

S204, responding to the creation operation, and acquiring a second general check rule created by the creation operation.

In this example, when matching the general test rule with the technical requirements, each technical requirement is matched, and if the general test rule base does not have the technical requirement (i.e., the second technical requirement) of the corresponding general test rule, the general test rule needs to be created for the second technical requirement. Here, the user may create a verification rule for the second technical requirement on a display interface of the computer device, and the act of creating may be implemented by selecting or self-filling on the display interface, and the creating content includes: at least one test item associated with the test procedure of the second claim and the test criteria of the respective test item, a completed test rule is created as a second generic test rule. The second general inspection rule is an inspection rule created by a user and matched with the second technical requirement, and then at least one inspection item and the inspection standard of each inspection item can be known based on the second general inspection rule, and each corresponding inspection item is inspected by referring to the inspection standard, so as to inspect whether the target product meets the second technical requirement. And the checking rule is not required to be written for technical requirements manually, so that the data processing efficiency is improved.

S205, generating a test plan of the target product according to the first general test rule and/or the second general test rule.

And under the condition that one or more technical requirements belong to the first technical requirement, generating a test plan of the target product according to the test item indicated by the first general test rule and the test standard corresponding to the test item. And under the condition that one or more technical requirements belong to the second technical requirement, generating a test plan according to the test item indicated by the second general test rule and the test standard corresponding to the test item. And under the condition that the technical requirements comprise the first technical requirement and the second technical requirement, generating an inspection plan of the target product according to the inspection item indicated by the first general inspection rule and the inspection standard corresponding to the inspection item indicated by the second general inspection rule.

The method and the device consider not only the first general technical requirement, but also the second technical requirement which is not in the general inspection rule base, based on the first general inspection rule is directly matched in the general inspection rule base, and the second general inspection rule is created for the second technical requirement which is not matched with the general inspection rule, so that an inspection plan is generated, and the integrity of the inspection plan is improved.

The above-mentioned S202 and S203 to S204 are parallel schemes. In practical applications, S201, S202 may be performed, and then a verification plan for the target product is generated according to the first general verification rule. S201, S203, S204 may also be performed; then generating an inspection plan of the target product according to the second general inspection rule; S201-S204 may also be performed and S205 may then be performed, without limitation to the embodiments of the present application.

After S204 or S205, the following steps may also be performed in this scheme: the second universal verification rule is added to the universal verification rule base.

In the embodiment of the application, after the second general checking rule is created, the second technical requirement and the second general checking rule can be correspondingly added into the general checking rule base, so that the richness and the integrity of the general checking rule base are improved. In the process of generating the inspection plan of the next product, if the inspection plan has the same technical requirement as the second technical requirement in the scheme, the inspection plan is directly matched in the general inspection rule base, the user does not need to re-create, and the generation efficiency of the inspection plan is improved.

In some embodiments, the universal test rules repository also stores universal test plans corresponding to respective universal test rules. Based on fig. 4, as shown in fig. 5, fig. 5 is a flowchart of still another method for generating a verification plan according to an embodiment of the present application, where the method for generating a verification plan includes:

s301, obtaining technical requirements in engineering drawings of target products.

S302, under the condition that the general checking rule base has the first technical requirement of the corresponding general checking rule, determining the first general checking rule corresponding to the first technical requirement from the general checking rule base.

In this example, S301 to S302 are identical to S201 to S202 in fig. 4, and the implementation process and the achieved technical effects can be seen in fig. 4, which is not repeated here.

S303, determining a first general inspection plan corresponding to the first general inspection rule from the general inspection rule base.

In this example, the general inspection rule base stores general inspection rules corresponding to different technical requirements, and general inspection plans corresponding to the general inspection rules. Each generic test rule corresponds to one or more generic test plans, each generic test plan including at least one test item and a test standard corresponding to each test item.

For the first technical requirement, after the first universal inspection rule is matched in the universal inspection rule base, a first universal inspection plan (including one or more inspection plans) corresponding to the first universal inspection rule can be obtained from the universal inspection rule base.

S304, determining the inspection plan of the target product according to the general inspection plans corresponding to the general inspection rules matched with the technical requirements.

Wherein the technical requirements include a first technical requirement, and the universal inspection plan corresponding to each universal inspection rule matching the technical requirements includes the first universal inspection plan.

In the case that one or more technical requirements belong to the first technical requirement, for each technical requirement, merging the universal inspection plans corresponding to the universal inspection rules matched with the technical requirements (including merging one or more inspection plans of the technical requirements and merging the universal inspection plans corresponding to the technical requirements) to obtain the inspection plan of the target product. In case the plurality of technical requirements comprises a first technical requirement and a second technical requirement, the generic inspection plan corresponding to the generic inspection rule matching the technical requirements belonging to the first technical requirement and the inspection plan (which may be created by a user) of the technical requirements belonging to the second technical requirement are combined to obtain the inspection plan of the target product.

For example, as shown in fig. 6, fig. 6 is an exemplary schematic diagram of a correspondence between technical requirements and inspection plans provided by an embodiment of the present application, fig. 6 shows correspondence between three technical requirements and four general inspection plans, where the three technical requirements are technical requirement 1, technical requirement 2, and technical requirement 3, respectively, the inspection rule corresponding to the technical requirement 1 satisfies the a standard, the inspection rule corresponding to the technical requirement 2 satisfies the B standard, and the inspection rule corresponding to the technical requirement 3 satisfies the C standard. Wherein, the inspection plan corresponding to the technical requirement 1 comprises a general inspection plan two, the inspection plan corresponding to the technical requirement 2 comprises a general inspection plan one and a general inspection plan three, and the inspection plan corresponding to the technical requirement 3 comprises a general inspection plan one, a general inspection plan three and a general inspection plan four.

In the example, the verification rules and the verification plans are not required to be created for all technical requirements manually, and the generation efficiency of the verification plans is improved.

In some embodiments, the first specification is a specification of a first sub-product in the target product; based on fig. 1, as shown in fig. 7, fig. 7 is a flowchart of still another method for generating a verification plan according to an embodiment of the present application, where the method for generating a verification plan includes:

S401, obtaining technical requirements in engineering drawings of target products.

In this example, S401 is identical to S101 in fig. 1, and the implementation process and the achieved technical effects can be seen in fig. 1, which is not described herein.

S402, determining a first general inspection rule base corresponding to the product type of the first sub product from a general inspection rule base set, wherein the general inspection rule base set comprises general inspection rule bases respectively corresponding to different product types.

In the embodiment of the application, the first sub-product is any sub-product in the target product, the first sub-product has multiple types (or models or specifications), and the general inspection rule base set comprises first general inspection rule bases respectively corresponding to the multiple different types of sub-products. The product type to which the first sub-product belongs may represent a model or specification of the first sub-product.

Illustratively, the first sub-product is a bolt, and the product types to which the first sub-product belongs include, but are not limited to, M20, M24, M15, etc., where M20 represents a bolt diameter of 20 millimeters.

In the following, description is made on rule application of multiple rule scenes including complex size classes, and a certain enterprise produces high-strength bolts with different specifications, and the specifications are divided into four types of M12, M16, M20 and M24. In this case, different general inspection rule bases may be established based on different bolt specifications, and then when the inspection plan is generated, a corresponding general inspection rule base may be selected for inspection according to a specific order specification (i.e., a first general inspection rule base corresponding to a product type to which the first sub-product belongs is determined from the general inspection rule base set). If a certain order contains bolts with two specifications of M12 and M20, the rule matching engine automatically selects a corresponding rule base for checking. The general test rule base for different types of bolts is as follows:

(1) General checking rule base for M12 bolts:

radius tolerance of rule M12 bolt "

when

bolt：Bolt(radius<5.5||radius>6.5)

then

Bolt. Error. Add ("radius tolerance cannot exceed 0.5 mm"); end (end)

Rule "M12 bolt Length tolerance"

when

bolt：Bolt(length<20||length>24)

then

Bolt. Error. Add ("length tolerance cannot exceed 2 mm"); end (end)

C. rules for M12 bolts.

(2) General test rule base for M16 bolts:

Radius tolerance of rule M16 bolt "

when

bolt：Bolt(radius<7.5||radius>8.5)

then

Bolt. Error. Add ("radius tolerance cannot exceed 0.5 mm"); end (end)

Rule "M16 bolt Length tolerance"

when

bolt：Bolt(length<30||length>36)

then

Bolt. Error. Add ("length tolerance cannot exceed 3 mm"); end (end)

C. Other rules regarding M16 bolts.

(3) General check rule base for M20 bolts:

Radius tolerance of rule M20 bolt "

when

bolt：Bolt(radius<9.5||radius>10.5)

then

Bolt. Error. Add ("radius tolerance cannot exceed 0.5 mm"); end (end)

Rule "M20 bolt Length tolerance"

when

bolt：Bolt(length<34||length>42)

then

Bolt. Error. Add ("length tolerance cannot exceed 4 mm"); end (end)

C. other rules regarding M20 bolts.

(4) General test rule base for M24 bolts:

radius tolerance of rule M24 bolt "

when

bolt:Bolt(radius<11.5||radius>12.5)

then

Bolt. Error. Add ("radius tolerance cannot exceed 0.5 mm");

end

Rule "M24 bolt Length tolerance"

when

bolt：Bolt(length<40||length>50)

then

Bolt. Error. Add ("length tolerance cannot exceed 5 mm");

end

c. Other rules regarding M24 bolts.

The four examples above illustrate bolts of different specifications having separate universal test rule bases that include several test rules, such as radius tolerances, length tolerances, surface finishes, etc., to ensure that each specification of bolt meets the corresponding requirements. In practical application, the rule matching engine can select a corresponding rule base according to the product type of the product, so that the automation and standardization of the whole production process are realized. It will be appreciated that if an enterprise needs to check different inspection requirements for bolts of multiple specifications, different rule bases may be established based on the attributes (e.g., radius, length, material, etc.) of the bolts, and then the corresponding rule bases may be selected for inspection based on the bolt specifications in the order before executing the rules.

S403, determining a general check rule matched with the technical requirement from the first general check rule base.

Wherein the specifications include a first specification.

S404, generating a test plan of the target product according to the general test rule matched with the technical requirement.

In this example, S404 is identical to S103 in fig. 1, and the implementation process and the achieved technical effects can be seen in fig. 1, which is not described herein.

In the embodiment of the application, after the technical requirements of the first sub-product in the target product are acquired, the first general inspection rule base corresponding to the product type to which the first sub-product belongs is selected from the general inspection rule base set, and then the general inspection rule matched with the technical requirements is determined from the first general inspection rule base, and the first general inspection rule base is matched with the product type to which the first sub-product belongs, so that the accuracy of the matched inspection rule is improved.

In some embodiments, based on the foregoing fig. 1, as shown in fig. 8, fig. 8 is a flowchart of still another method for generating a verification plan according to an embodiment of the present application, where the method for generating a verification plan includes:

s501, obtaining technical requirements and tolerance requirements in engineering drawings of target products.

In some embodiments, in addition to obtaining technical requirements in engineering drawings, other drawing information such as tolerance requirements, product information and the like in engineering drawings can also be obtained.

For example, the engineering drawing of the target product is detected through the target detection model, so that the position information of a plurality of target frames is obtained, and the target frames indicate the boundaries of the technical requirements or tolerance requirements in the engineering drawing. And then, identifying the plurality of target frames through a target identification model according to the position information of the plurality of target frames to obtain a text identification result, wherein the text identification result comprises technical requirements and tolerance requirements in engineering drawings.

The engineering drawing may include tolerance requirements for the parts, in addition to technical requirements for the parts and components connected to each other. The tolerance requirements include at least one of dimensional and geometric tolerances. Based on the above, the engineering drawing may be input into the target detection model, the outline (or boundary) of the region where the technical requirement or the tolerance requirement is located may be found by the target detection model, and a target frame may be added thereto to mark a plurality of target frames, and then the position information of the plurality of target frames may be coordinate information. Each target frame is used for indicating the boundary of the region where the technical requirement or the tolerance requirement is located in the engineering drawing, namely, the technical requirement or the tolerance requirement of any part is included in each target frame. The technical requirements in the engineering drawing can be represented by text or text and identification symbols, and the text can comprise letters, numbers and other characters. The identification symbol may be a symbol in the form of a graphic or icon or the like. The identification symbol may be a symbol for indicating flatness, or a symbol for indicating parallelism, etc., for example, in geometric tolerances included in the tolerance requirements.

After the position information of a plurality of target frames is obtained, for each target frame, an image area corresponding to the target frame can be found in the engineering drawing according to the position information of the target frame, so that character recognition is carried out on the image area, and a text recognition result corresponding to the target frame is obtained. If the target box indicates the boundary of the area where the technical requirement is located, the text recognition result can be any one or any combination of the text related to the surface roughness, the material requirement, the process requirement, the assembly requirement, the identification requirement and the safety requirement. If the target box indicates a boundary of a tolerance requirement, its text recognition result may be text about a dimensional tolerance or a geometric tolerance. The above recognition process is performed on each of the plurality of target boxes to obtain text recognition results (technical requirements of text forms, tolerance requirements and other drawing information) of the engineering drawing.

The detection target of the target detection model in the example is drawing information such as technical requirements and tolerance requirements in engineering drawings. The object in the engineering drawing is detected through the target detection model, technical requirements, tolerance requirements and the like of parts in the engineering drawing are marked by rectangular frames, position information of the target frame is output, character recognition is further carried out through the target recognition model according to the position information of the target frame, a text recognition result corresponding to the target frame is obtained, manual labeling of the target frame is not needed, and target detection efficiency is improved.

It should be noted that the engineering drawing may further include product information, where the product information includes at least a name of the target product, and in one example, the product information of the engineering drawing may also be obtained. Based on the above, the frame detected by the target detection model may indicate a technical requirement, a tolerance requirement or a boundary of product information in the engineering drawing, and the text recognition result recognized by the target recognition model includes the technical requirement, the tolerance requirement and the product information in the engineering drawing. For the detection process and the identification process of the product information, reference may be made to the above description of technical requirements and tolerance requirements, and will not be repeated here. The product information may include, among other things, the name of the target product, the production lot, the production station, etc. When the target product is a child product in the finished product, the product information may include the name of the child product, adjacent level (upper level and lower level) information of the child product, the name of the finished product to which the child product belongs, and the like. In addition, the product information may also include product information about the parts in the target product, such as a series of product information associated with the parts, such as a production lot, a production station, adjacent level information, a final product, etc. related to the parts.

S502, determining a general inspection rule matched with the technical requirement from a general inspection rule library, wherein a plurality of general inspection rules are stored in the general inspection rule library, and each general inspection rule is used for indicating at least one inspection item and an inspection standard corresponding to each inspection item.

In this example, S502 is identical to S102 in fig. 1, and the implementation process and the achieved technical effects can be seen in fig. 1, which is not described herein.

S503, generating a special inspection rule matched with the tolerance requirement, wherein the special inspection rule is used for indicating whether the inspection target product meets at least one inspection item required to be subjected to the tolerance requirement and the inspection standard of each inspection item.

In the embodiment of the application, the tolerance requirement is a requirement closely related to the target product or the sub-product of the target product, and may be only applicable to the target product or the sub-product in the target product without universality. After the tolerance requirement is acquired, a corresponding special inspection rule can be automatically created according to the text content of the tolerance requirement, and can also be created manually, so that the embodiment of the application is not limited. The inspection criteria of at least one inspection item and of the individual inspection items can then be ascertained on the basis of special inspection rules, and each respective inspection item is inspected with reference to the inspection criteria, so that it is checked whether the target product meets the tolerance requirements. And the checking rule is not required to be written for technical requirements manually, so that the data processing efficiency is improved.

For example, after the tolerance requirement in the engineering drawing is obtained, a corresponding special inspection rule is automatically generated according to the obtained tolerance requirement. For another example, a creation operation is received in which a user creates a verification rule for a tolerance requirement, and in response to the creation operation, a special verification rule created by the creation operation is obtained.

It should be noted that, S502 and S503 are parallel schemes, and the execution sequence of the present application is not limited, and the present application may be executed simultaneously or sequentially.

S504, generating a test plan of the target product according to the general test rule and the special test rule matched with the technical requirements.

And under the condition that the engineering drawing comprises technical requirements and tolerance requirements, generating an inspection plan of the target product according to the inspection items indicated by the general inspection rules matched with the technical requirements and the inspection standards corresponding to the inspection items indicated by the special inspection rules corresponding to the tolerance requirements.

The method and the device take technical requirements into account, tolerance requirements are also considered, based on the technical requirements, the inspection plan is generated according to the matched general inspection rules and special inspection rules related to the target product, and the integrity of the inspection plan is improved.

Further, product information in engineering drawings can be obtained, and accordingly, a test plan of a target product can be generated according to the product information, a general test rule matched with technical requirements and a special test rule corresponding to tolerance requirements.

It should be noted that the embodiments shown in fig. 1, fig. 4, fig. 5, fig. 7 and fig. 8 may be combined with each other to form more technical solutions. Exemplary, the first technical requirement and the second technical requirement in fig. 4 are combined with the first general inspection rule corresponding to the first technical requirement in fig. 5; the first technical requirement and the second technical requirement in fig. 4 are combined with the first general inspection rule base corresponding to the product type of the first sub-product in fig. 7; the first and second requirements in fig. 4 are combined with the tolerance requirements in fig. 8. Fig. 5 and fig. 7 are combined with each other, fig. 5 and fig. 8 are combined with each other, and fig. 7 and fig. 8 are combined with each other. And, the technical scheme that any three or more of the items in fig. 1, fig. 4, fig. 5, fig. 7 and fig. 8 are mutually combined. The above-mentioned technical solutions combined with each other are all within the protection scope of the embodiments of the present application, and specific implementation manner can be referred to the description of each embodiment, which is not repeated herein.

In the following, an exemplary application of the embodiment of the present application in a practical application scenario will be described.

As shown in fig. 9A, fig. 9A is a schematic diagram of an engineering drawing provided by an embodiment of the present application, and target frame detection and recognition are performed on the engineering drawing to obtain a text recognition result, where the text recognition result includes technical requirements, tolerance requirements, and the like in the engineering drawing. Wherein, the technical requirements include: 1. surface bluing treatment; 2. edge angle chamfer; 3. unmarked tolerances of linear dimensions are according to GB/T1804-m; 4. the unlabeled form and position tolerance is according to GB/T1184-K; 5. precision grade: 8bD GB/T1365-1989. The text recognition result includes a tolerance requirement, where the tolerance requirement is shown in fig. 9B, fig. 9B is a schematic diagram of a text recognition result of an engineering drawing provided by an embodiment of the present application, fig. 9B is a result obtained after the tolerance requirement in the engineering drawing in fig. 9A is recognized, and the tolerance requirement in fig. 9B includes a serial number, a name (including linearity and diameter), a type (including linearity, diameter and geometric tolerance), a measurement quantity, a requirement, a target value, an upper tolerance, a lower tolerance, and a gauge type (including micrometer and laser range finder).

Note that the tolerance requirements are shown in table form in fig. 9B. It should be understood that the text recognition results (including technical requirements, tolerance requirements, and product information) in the embodiments of the present application may also be shown in other forms, such as text, graphics, etc., and fig. 9B is merely shown by way of example and is not limiting on the embodiments of the present application.

Based on fig. 9A and fig. 9B, by using the method for generating a verification plan provided by the embodiment of the present application, a verification plan is generated, as shown in fig. 9C, and fig. 9C is an exemplary schematic diagram of a verification rule provided by the embodiment of the present application. The inspection rules shown in fig. 9C include a general inspection rule including a general inspection rule regarding plastic class and a general inspection rule of copper foil, and a special inspection rule regarding tolerance requirements. The inspection items in the general inspection rules for plastics include security, appearance, packaging requirements, and data core, and the like, each of which corresponds to a feature number, shown in fig. 9C as VIS00001-VIS00004, the inspection criteria are all visual inspection types of the inspection items that satisfy the general inspection criteria for plastics. The test items in the general test rule of the copper foil include characteristic names of basis weight tests, each of which corresponds to a characteristic number, shown as RE001 in fig. 9C, the test standard is a general test standard that satisfies the copper foil, and the test type of the test item is a technical type. The test items in the special test rules concerning tolerance requirements include characteristic names of dimensions including a plurality of dimensions shown in fig. 9B, only partial dimensions (75.0, 47.0, 25.0, 21.5, 4.5) are illustrated in fig. 9C, each characteristic name corresponds to a characteristic number, and are shown in fig. 9C as M00001-M00005, the test criteria are the test criteria satisfying the respective dimensions, and the test types of the test items are all visual types.

It should be noted that, the general inspection rule for plastics includes 4 inspection items: the security, appearance, packaging requirements and data checks, each corresponding to a test standard, wherein the security and appearance may correspond to a first universal test plan and the packaging requirements and data checks may correspond to a second universal test plan. That is, a technical required inspection rule may correspond to a plurality of general inspection plans, and a general inspection plan may correspond to a plurality of inspection items and inspection criteria of each inspection item.

In some embodiments, the method of generating a verification plan further comprises: and (3) a general checking rule base creation process. The method comprises the following steps: acquiring technical requirements in engineering drawings of a plurality of products, and checking items and checking standards corresponding to the technical requirements; generating a general test rule corresponding to each technical requirement according to the test item and the test standard corresponding to each technical requirement; and creating a universal test rule base according to the universal test rule corresponding to each technical requirement.

When the universal inspection rule base is created, technical requirements in engineering drawings of a large number of products and inspection items and inspection standards corresponding to the technical requirements are collected and taken as samples, and for each technical requirement, mapping relations between the inspection items and the inspection standards corresponding to the technical requirements and the universal inspection rules are established and stored in a database to be used as the universal inspection rule base. And the general inspection rules matched with the technical requirements are provided for the computer equipment in the subsequent process of generating the inspection plan, so that the inspection rules do not need to be written for the technical requirements manually, and the data processing efficiency is improved.

The samples used in this example include not only general inspection rules regarding technical requirements, but also special inspection rules regarding tolerance requirements. When the universal test rule base is created, samples can be screened, the screened universal test rule is added to the universal test rule base, or both the universal test rule and the special test rule are added to the rule base, and then the special test rule is deleted, so that the creation process of the universal test rule base is completed.

Furthermore, the general rule checking library can also store different types of rule checking results, and the specific rule checking results are associated with specific error codes or warning information.

The embodiment of the application needs to create a general inspection rule base and a rule matching engine for executing the generation inspection technology, and establishes a matching relation between the general inspection rule base and engineering drawings (comprising technical requirements and tolerance requirements). The two creation processes complement each other. Next, description will be given of creation of a general inspection rule base, which is an example of a rule based on an inspection plan, in which the creation of inspection rules is performed in terms of whether or not geometric tolerances, appearance, and physical properties of the inspection machine parts meet specifications, and the like. The following is an exemplary illustration of a generic verification rule base.

Rule "bolt radius tolerance"

when

bolt：Bolt(radius<11.5||radius>12.5)

then

Bolt. Adderror ("radius tolerance cannot exceed 0.5 mm");

end

rule "bolt length tolerance"

when

bolt：Bolt(length<28||length>30)

then

Bolt. Adderror ("length tolerance cannot exceed 1 mm");

end

Rule "bolt surface finish"

when

bolt：Bolt(surfaceSmoothness<200)

then

Bolt. Adderror ("surface finish not satisfactory");

end

d.rule "bolt appearance"

when

Bolt: bolt (Apearance +.I = "smooth")

then

Bolt. Adderror ("appearance unsatisfactory");

end

e.rule "bolt tensile Strength"

when

bolt：Bolt(tensileStrength<500)

then

Bolt. Adderror ("tensile strength less than 500N");

end

Rule "bolt hardness"

when

bolt：Bolt(hardness<30)

then

Bolt. Adderror ("hardness below 30 HRC");

end

the rule base contains six rules: a. bolt radius tolerance rules: checking whether the radius tolerance of the bolt meets the specification, and if the radius tolerance exceeds 0.5mm, adding error information to an error list of the bolt. b. Bolt length tolerance rules: checking whether the length tolerance of the bolt meets the regulation, and if the length tolerance exceeds 1mm, adding error information into an error list of the bolt. c. Bolt surface finish rule: checking whether the surface finish of the bolt meets the requirement, and if the surface finish does not meet the requirement, adding error information into an error list of the bolt. d. The appearance of the bolts is regular: checking whether the appearance of the bolt meets the requirement or not, and if the appearance does not meet the requirement, adding error information into an error list of the bolt. e. Bolt tensile strength rule: checking whether the tensile strength of the bolt meets the requirement, and if the tensile strength is lower than 500N, adding error information into an error list of the bolt. f. Bolt hardness rule: checking whether the hardness of the bolt meets the requirement, and if the hardness is lower than 30HRC, adding error information into an error list of the bolt.

Further, the child products are different in product types, and the corresponding general inspection rule bases are different. When the general inspection rule base is established, the general inspection rule base can be divided according to the properties of the bolt, such as material type, wire diameter, head and the like. Then all of the generic rules, e.g., appearance and tensile strength rules, and rules specific to the specification bolt, e.g., radius tolerance rules, may be included in each generic test rule base. In the production process, the rule matching engine can select an associated rule base for inspection according to the bolt attributes, so that bolts of each specification are ensured to meet corresponding requirements. Correspondingly, when implementing the rule matching engine, a generic check rule base may be stored in the database and version control and updating performed using the rule base management tool. Also, order management tools are used to manage the order and related bolt attributes so that the rule matching engine can automatically select the appropriate rule base based on the order specifications. Therefore, the management and maintenance of the rule matching engine can be simplified, and the accurate control of the inspection requirements of bolts with different specifications can be ensured.

Further, the description is given in terms of creating a test rule base from the standpoint of establishing a matching relationship between the drawing and the test rule. Unstructured properties identified by Artificial Intelligence (AI) optical character recognition (Optical Character Recognition, OCR) techniques require automatic conversion to rules and archiving to a generic verification rule base. The following steps may be included.

(1) The data analyzed by the drawing comprises: ① Dimensional tolerance requirements: information indicating the dimensions of the parts and the tolerance ranges between the parts, surface tolerances, etc. ② Geometric requirements: geometric requirements between the parts are marked, including form and position tolerances, contour tolerances, and the like. ③ Surface roughness: the surface roughness requirements of the parts are marked, including roughness grade, surface treatment mode and the like. ④ The material requirements are as follows: the material type, material specification, hardness index, heat treatment mode, strength index, chemical composition, etc. of the parts are marked. ⑤ The process requirements are as follows: including processing requirements, inspection requirements, etc. ⑥ The assembly requirements are as follows: indicating the manner of assembly, precision requirements, assembly sequence, torque and tightening sequence of the fasteners, etc. ⑦ The identification requirements are as follows: coding mode, identification sign, position and size of marking the part identification. ⑧ Safety requirements: indicating the safety use requirement, safety warning sign, safety device, etc. ⑨ Other requirements are: modeling requirements, color requirements, quality testing standards, etc. The above ①-③ is a tolerance requirement, and ④-⑨ is a technical requirement.

(2) Performing rule recognition on the ①-⑨ content, and classifying the material requirement, the process requirement, the assembly requirement, the identification requirement, the safety requirement and other requirements into a general inspection rule; dimensional tolerance requirements, geometric requirements, and surface roughness requirements are generalized to special inspection rules that represent that such rules are reusable, and special inspection rules that represent that such rules are used only for this product (Part).

(3) An object named "Part" is created in the inspection plan database, which contains the following attributes:

declare Part

@propertyList:List

@material:String

@tolerance:String

@geometry:String

@surface:String

@process:String

@assembly:String

@identification:String

@safety:String

@others:String

end

Wherein the @ material, @ tool, @ geometry, @ surface, @ process, @ assembly, @ identification, @ security and @ other properties are data elements (corresponding ④、①、②、③、⑤、⑥、⑦、⑧ and ⑨) parsed from the drawing, respectively.

(4) A rule is created for each data element for archiving it to the rule base. For example, the following are rules that archive @ Material properties into a rule base:

rule "archival Material Requirements"

when

$part:Part(@material！＝null)

then

Insert (new Rule ("material requirement", $part @ material));

end

Wherein Rule objects represent rules in a Rule base, which contain two attributes: the requirements and values represent the names and values of the rules, respectively. This rule files the @ material property in the Part object as a rule named "Material Requirements" and adds it to the rule base.

(5) Adding general rules in a rule base, for example:

rule "check Material"

when

$part:Part(@material！＝null)

Rule (requirement= "Material requirement")

then

System.out.println ($part+ ") requires" + $rule.value;

end

This rule is used to check if the @ material property of the Part object satisfies a rule named "Material Requirements" in the rule base.

Sufficient rules are added or created in the rule base to cover all data requirements of the drawing parsing. For example, rules may be added to check requirements in terms of part material type, hardness, heat treatment, etc., or general rules may be created to check requirements in terms of dimensional tolerance ranges, accuracy requirements, form and position tolerances, etc. for different parts, taking care to remove specific product requirements (e.g., dimensional rules, tolerance rules, and roughness requirements) from the rule base, leaving only general, cross-product applicable tolerances, dimensions, and roughness rules. So that these general rules can be applied to different products and projects. Meanwhile, rule classification and labels are added in a rule base. For example, the classification may be performed in terms of a component class, a quality class, a functional class, or the like to which the rule applies. Thus, the rule base can be easier to manage, and the rule searching and archiving are more convenient. By means of these generic rules, automated rule checking can be achieved in various aspects of component design and production.

Further, additional objects may be created to store other rule base elements. For example, an object named "Requirement Type" may be created for storing the standard part Requirement Type for use in creating rules in the rule base. This object may contain two attributes: the requirements and descriptions represent the names and descriptions of the rule requirements, respectively.

Further, more operation logic can be added for rules in the rule base. For example, an object named "Rule Check Result" may be created for storing rule check results and associating those results with a particular error code or warning message. In this way, problems can be automatically identified at the time of inspection and responsive information provided when further investigation is required to speed up problem resolution.

Next, a description will be given of the establishment of a matching relationship between the general inspection rule base and engineering drawings (including technical requirements and tolerance requirements).

The rule matching engine established in this example is responsible for automatically identifying the inspection requirements of the product and structuring into product features that can be generalized by the inspection plan rule base. The method comprises the following steps: (1) determining a data range to be checked: such as the number of samples taken, the period of sample taken, the frequency of sample taken, etc. (2) determining rules and criteria to be checked: such as quality check criteria, check items, check methods, lot requirements, etc., these rules and criteria should be prioritized to facilitate automated processing. (3) determining a structured data criterion: by defining the structured data standard, the data is converted into a computer readable data format, which is convenient for program processing. This maintains data consistency and consistency. (4) design rule matching engine architecture: including inspection planning, rule engine implementation, computational analysis, and inspection report generation. (5) Rules of the rule matching engine are formulated, and the rule making of the check rule is realized through a programming language or rule engine software of an open source code. An appropriate rule language is selected to implement the verification rule. The built general checking rule base is used for storing all checking rules, and the definition of all checking rules including conditions, actions, input and output elements and the like is contained in the checking rule base. The verification rules are defined by writing a series of rules. A design rule program is required: the implementation of the rule matching engine program is based on a general checking rule base, and the program generates a required output result after matching with a predefined checking rule by inputting, sorting and checking data in the application program. After the rule program is designed, testing and verification are performed, and the validity of the program can be ensured through repeated testing and verification. In this process, the inspection rules in the program can be adjusted or new inspection rules can be added at any time to meet new inspection requirements. (6) According to the defined checking rule checking data, using the rule matching engine software of the programming language or the open source code to compare the read data with the defined checking rule and generate a checking result, wherein the checking result is passing or not passing. (7) Automatically generating a test report, the system automatically calculates the generated test results and generates an appropriate report. The inspection report may include inspection time, product information, product lot, inspection results, abnormal conditions, standard names of inspection, and operator information. (8) The rule matching engine based on the inspection plan provides feedback allowing the user to improve the inspection program by altering the inspection rules and criteria, providing a data base for better quality monitoring. (9) The finally generated inspection plan and inspection rules are stored in a general inspection rule base.

In connection with the general verification rule base and rule matching engine described above, the application of three different levels of rule matching engines is presented below by way of three examples.

Example one, rule application for dynamic change of sample yield.

Assuming that a home electronics product manufacturing enterprise needs to check products, a series of check plans need to be made. It is assumed that the manufacturing enterprise needs to make the following decisions before checking the plan:

1. If the order product quantity is greater than 100, a 100% check is required before the product is shipped.

2. If the products of the same production line have continuous quality problems, the inspection frequency needs to be increased.

3. The same test need not be performed every time for the same model of product.

4. The products are particularly inspected in some critical production links.

For the above requirements, the rule engine may be used to implement verification planning for the manufacturing enterprise. The method comprises the following specific steps:

1. Defining an entity object: two entity classes of orders and products are defined, including attributes such as order number, product model number, line number, product number, inspection status, inspection result, etc.

2. Formulating metadata: metadata defining orders and products, including information on relationships, constraints, ranges, and indicators.

3. And (3) making a cognitive model: and according to the actual requirements and the business flow, formulating an information model, a rule model, an association model and other cognitive models, and describing various business logics and rule conditions.

4. Writing rules: according to the inspection plan requirement, relevant rules are compiled, including rules of judging the quantity of ordered products, judging whether the products are inspected, judging continuous quality problems of the same production line and the like. For example:

If the number of ordered products is greater than 100, 100% inspection is required before the products are delivered; if the products of the same production line have continuous quality problems, the inspection frequency needs to be increased; for the products with the same model, links which are inspected before are included in the process of inspecting the subsequent production links; special inspections are required in some critical production steps, including welding, bonding, etc.

5. Testing and verifying: and testing and verifying the rule engine to ensure that the rule engine can accurately judge various conditions and provide support for the comprehensive inspection plan of a manufacturing enterprise.

Example two, rule application for non-complex size classes such as appearance/performance/physical class.

Assuming that an automobile manufacturing enterprise produces a car, various tests such as appearance inspection, performance test, chemical test, size test and the like need to be carried out according to the following rules in the production process:

1. Appearance inspection rule:

a. Defects such as pits, scratches, color differences and the like cannot be formed on the surface of the vehicle body;

b. the vehicle glass must not have obvious cracks or residual stains at important viewing angles;

c. the assembly direction of the marker lamp, the steering lamp, the fog lamp, the lens and the like on the bumper is correct, and the position is neat;

d. The hub is perfectly attached to the tire and the vehicle body, and the looseness is avoided.

2. Performance test rules:

a. the engine power is enough, and the starting and accelerating reactions are good;

b. the braking system has the advantages of high response speed, stable braking performance and short braking distance;

c. The tire is worn uniformly, and the grip is strong;

d. the suspension system should run steadily without shaking, and the vehicle body should not bounce when the pit goes over.

3. Chemical test rules:

a. the chemical composition of the coating, rubber and plastic should meet relevant regulations and standards;

b. The cooling system, the braking system and the engine lubricating oil should meet relevant regulations;

c. The fuel oil meets national and local standards.

4. Size test rule:

a. The vehicle door and the vehicle window can be completely opened and closed, and the door gaps are equal;

b. the internal instrument panel and the air conditioner control interface frame are required to be accurate and meet the requirements;

c. the seat in the car and the air conditioner flow direction gear position and the like accord with relevant regulations.

In response to the above needs, the product verification of the automobile manufacturing enterprise may be implemented using a rules engine. The method comprises the following specific steps:

1. defining an entity object: and defining the entity class of the automobile product and each test, wherein the entity class comprises attributes such as automobile types, test items, test results and the like.

2. Formulating metadata: metadata defining the automotive product and various tests including information such as relationships, constraints, ranges, and indicators.

3. And (3) making a cognitive model: and (3) formulating an information model, a rule model, an association model and other cognitive models according to actual requirements and service flows, and describing various service logics and rule conditions, such as appearance inspection rules, performance test rules, chemical test rules, size test rules and the like.

4. Writing rules: and writing relevant rules according to the test plan requirements, including judging appearance and performance test rules, chemical test rules, size test rules and the like. For example:

if the surface of the vehicle body has pits, scratches or color differences, the appearance is disqualified;

If the engine power is insufficient, the performance is unqualified;

If the fuel oil does not meet the national and local standards, the chemical test is not qualified;

If the door and window cannot be fully opened and closed, the dimensional test is failed.

5. Testing and verifying: and testing and verifying the rule engine to ensure that the rule engine can correctly judge each inspection rule and provide support for product inspection of manufacturing enterprises.

Example three, rule application including complex size classes for a multi-rule scenario, can be seen from the description above for high strength bolts with specifications divided into M12, M16, M20 and M24.

Based on the method for generating a verification plan provided in the foregoing embodiment, fig. 10 is a schematic structural diagram of an apparatus for generating a verification plan provided in an embodiment of the present application. The apparatus may be implemented as part or all of a computer device by software, hardware, or a combination of both. Referring to fig. 10, the apparatus 100 for generating a verification plan includes: the obtaining module 1001 is configured to obtain a technical requirement in an engineering drawing of a target product; a matching module 1002, configured to determine a general test rule matching the technical requirement from a general test rule library, where a plurality of general test rules are stored in the general test rule library, and each general test rule is used to indicate at least one test item and a test standard corresponding to each test item; a generating module 1003, configured to generate a verification plan of the target product according to the universal verification rule matched with the technical requirement.

Optionally, the general inspection rule library stores general inspection rules respectively corresponding to different technical requirements, and the technical requirements include a first technical requirement with a corresponding general inspection rule in the general inspection rule library;

The matching module 1002 is further configured to determine a first general test rule corresponding to the first technical requirement from the general test rule base, where the first general test rule is a general test rule matched with the first technical requirement; the first general inspection rule is used for indicating whether the inspection target product meets at least one inspection item required to be performed by the first technical requirement and the inspection standard of each inspection item.

Optionally, the technical requirements further include a second technical requirement that does not have a corresponding general verification rule in the general verification rule base, and the apparatus 100 for generating a verification plan further includes a receiving module 1004 and an adding module 1005;

a receiving module 1004, configured to receive a create operation for creating a verification rule for the second technical requirement;

the obtaining module 1001 is further configured to obtain, in response to the creating operation, a second general verification rule created by the creating operation;

an adding module 1005 further configured to add the second universal inspection rule to the universal inspection rule base;

The generating module 1003 is further configured to generate a verification plan of the target product according to the first universal verification rule and the second universal verification rule.

Optionally, the universal inspection rule base further stores universal inspection plans corresponding to the universal inspection rules;

the matching module 1002 is further configured to determine a first universal test plan corresponding to the first universal test rule from the universal test rule base;

The generating module 1003 is further configured to determine a test plan of the target product according to the universal test plans corresponding to the universal test rules matched with the technical requirements.

Optionally, the first technical requirement is a technical requirement of a first sub-product in the target product;

The matching module 1002 is further configured to determine a first universal inspection rule base corresponding to a product type to which the first sub-product belongs from a universal inspection rule base set, where the universal inspection rule base set includes universal inspection rule bases corresponding to different product types respectively; a generic test rule matching the technical requirement is determined from a first generic test rule library.

Optionally, the obtaining module 1001 is further configured to obtain a tolerance requirement in an engineering drawing of the target product;

The generating module 1003 is further configured to generate a special inspection rule matched with the tolerance requirement, where the special inspection rule is used to indicate whether the inspection target product meets at least one inspection item required to be performed by the tolerance requirement and an inspection standard of each inspection item; and generating an inspection plan of the target product according to the general inspection rule and the special inspection rule matched with the technical requirements.

Optionally, the obtaining module 1001 is further configured to detect an engineering drawing through a target detection model, so as to obtain position information of a plurality of target frames, where the target frames are used to indicate boundaries of each technical requirement in the engineering drawing, and the target detection model is used to perform target detection on an image; and identifying the plurality of target frames through a target identification model according to the position information of the plurality of target frames to obtain a text identification result, wherein the text identification result comprises technical requirements in engineering drawings, and the target identification model is used for carrying out character identification on the images.

Optionally, a plurality of test rule files corresponding to the plurality of general test rules one by one are stored in the general test rule base, each test rule file is used for defining a corresponding general test rule, each general test rule file comprises at least one rule described by a rule language, and each rule comprises a trigger condition and an execution action.

Optionally, the apparatus 100 for generating a verification plan further comprises a creation module 1006;

The obtaining module 1001 is further configured to obtain technical requirements in engineering drawings of a plurality of products, and test items and test standards corresponding to the technical requirements;

the generating module 1003 is further configured to generate a general test rule corresponding to each technical requirement according to the test item and the test standard corresponding to each technical requirement;

a creating module 1006, configured to create a general inspection rule base according to the general inspection rules corresponding to the respective technical requirements.

It should be noted that, when the device for generating the inspection plan provided in the above embodiment identifies the engineering drawing, only the division of the above functional modules is used for illustration, and in practical application, the above functional allocation may be performed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to perform all or part of the functions described above.

The functional units and modules in the above embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the embodiments of the present application.

The device for generating the inspection plan provided in the foregoing embodiment belongs to the same concept as the method embodiment for generating the inspection plan, and the specific working process and the technical effects brought by the units and the modules in the foregoing embodiment may be referred to in the method embodiment section, and are not repeated herein.

Based on the method for generating a verification plan provided in the foregoing embodiment, fig. 11 is a schematic structural diagram of a computer device provided in an embodiment of the present application, and as shown in fig. 11, the computer device 110 includes: the steps in the method of generating a verification plan in the above-described embodiment are implemented by the processor 1101, the memory 1102, and the computer program 1103 stored in the memory 1102 and executable on the processor 1101, when the processor 1101 executes the computer program 1103.

The computer device 110 may be a general purpose computer device or a special purpose computer device. In a specific implementation, the computer device 110 may be a desktop, a portable computer, a network server, a palmtop, a mobile phone, a tablet, a wireless terminal device, a communication device, or an embedded device, and embodiments of the present application are not limited to the type of computer device 110. It will be appreciated by those skilled in the art that fig. 11 is merely an example of computer device 110 and is not intended to limit computer device 110, and may include more or fewer components than shown, or may combine certain components, or may include different components, such as input-output devices, network access devices, etc.

The Processor 1101 may be a central processing unit (Central Processing Unit, CPU), and the Processor 1101 may also be other general purpose processors, digital signal processors (DIGITAL SIGNAL Processor, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), off-the-shelf Programmable gate array (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. The general purpose processor may be a microprocessor or may be any conventional processor.

The memory 1102 may in some embodiments be an internal storage unit of the computer device 110, such as a hard disk or memory of the computer device 110. Memory 1102 may also be an external storage device of computer device 110 in other embodiments, such as a plug-in hard disk, smart memory card (SMART MEDIA CARD, SMC), secure Digital (SD) card, flash memory card (FLASH CARD), etc. provided on computer device 110. Further, the memory 1102 may also include both internal storage units and external storage devices of the computer device 110. Memory 1102 is used to store operating systems, application programs, boot Loader (Boot Loader), data, and other programs, among others. Memory 1102 may also be used to temporarily store data that has been output or is to be output.

The embodiment of the application also provides a computer device, which comprises: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, which when executed by the processor performs the steps of any of the various method embodiments described above.

Embodiments of the present application also provide a computer readable storage medium storing a computer program which, when executed by a processor, performs the steps of the respective method embodiments described above.

Embodiments of the present application provide a computer program product which, when run on a computer, causes the computer to perform the steps of the various method embodiments described above.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present application may implement all or part of the flow of the above-described method embodiments, and may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and where the computer program, when executed by a processor, may implement the steps of the above-described method embodiments. Wherein the computer program comprises computer program code which may be in the form of source code, object code, executable files or in some intermediate form, etc. The computer readable medium may include at least: any entity or device capable of carrying computer program code to a photographing apparatus/terminal device, recording medium, computer Memory, ROM (Read-Only Memory), RAM (Random Access Memory ), CD-ROM (Compact Disc Read-Only Memory), magnetic tape, floppy disk, optical data storage device, and so forth. The computer readable storage medium mentioned in the present application may be a non-volatile storage medium, in other words, a non-transitory storage medium.

It should be understood that all or part of the steps to implement the above-described embodiments may be implemented by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. The computer instructions may be stored in the computer-readable storage medium described above.

In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.

Claims

1. A method of generating a verification plan, the method comprising:

obtaining technical requirements in engineering drawings of a target product; the technical requirements in the engineering drawing of the target product are obtained, and the method comprises the following steps: identifying technical requirements in engineering drawings of the target product to obtain technical requirements in a text form;

Determining a universal test rule matched with the technical requirement from a universal test rule library, wherein a plurality of universal test rules are stored in the universal test rule library, and each universal test rule is used for indicating at least one test item and a test standard corresponding to each test item; the general inspection rule includes a trigger condition for judging whether the inspection standard of the inspection item is satisfied and an execution action under different judgment results of the trigger condition;

Generating an inspection plan of the target product according to a general inspection rule matched with the technical requirement; the inspection plan is used to verify whether the manufacturing process and the corresponding finished product meet the specifications.

2. The method of claim 1, wherein the universal test rules library stores universal test rules corresponding to different technical requirements, respectively, the technical requirements including a first technical requirement having a corresponding universal test rule in the universal test rules library;

the determining the universal test rule matched with the technical requirement from the universal test rule base comprises the following steps:

Determining a first general test rule corresponding to the first technical requirement from the general test rule library, wherein the first general test rule is a general test rule matched with the first technical requirement;

the first general inspection rule is used for indicating whether the target product meets at least one inspection item required to be performed by the first technical requirement and the inspection standard of each inspection item.

3. The method of claim 2, wherein the specifications further comprise a second specification that does not have a corresponding generic verification rule in the generic verification rule base, the method further comprising:

receiving a creation operation for creating a verification rule for the second technical requirement;

Responding to the creation operation, and acquiring a second general check rule created by the creation operation;

adding the second universal inspection rule to the universal inspection rule base;

The step of generating the inspection plan of the target product according to the universal inspection rule matched with the technical requirement comprises the following steps:

and generating a test plan of the target product according to the first general test rule and the second general test rule.

4. The method of claim 2, wherein the universal test rules repository further stores universal test plans corresponding to respective universal test rules;

after determining the first general inspection rule corresponding to the first technical requirement from the general inspection rule base, the method further comprises:

Determining a first general inspection plan corresponding to the first general inspection rule from the general inspection rule library;

and determining the inspection plan of the target product according to the universal inspection plans corresponding to the universal inspection rules matched with the technical requirements.

5. The method of claim 2, wherein the first specification is a specification of a first sub-product in the target product;

Before determining the universal checking rule matched with the technical requirement from the universal checking rule base, the method further comprises the following steps:

Determining a first general inspection rule base corresponding to the product type of the first sub-product from a general inspection rule base set, wherein the general inspection rule base set comprises general inspection rule bases respectively corresponding to different product types;

A generic test rule matching the technical requirement is determined from the first generic test rule library.

6. The method of any of claims 1-5, wherein prior to generating the inspection plan for the target product according to the universal inspection rules matching the specifications, further comprising:

Acquiring tolerance requirements in engineering drawings of the target product;

Generating a special inspection rule matched with the tolerance requirement, wherein the special inspection rule is used for indicating whether the target product meets at least one inspection item required to be subjected to the tolerance requirement and the inspection standard of each inspection item;

And generating a test plan of the target product according to the general test rule matched with the technical requirement and the special test rule.

7. The method according to any one of claims 1 to 5, wherein the obtaining the technical requirements in the engineering drawing of the target product comprises:

Detecting the engineering drawing through a target detection model to obtain position information of a plurality of target frames, wherein the target frames are used for indicating boundaries of various technical requirements in the engineering drawing, and the target detection model is used for carrying out target detection on images;

And identifying the plurality of target frames through a target identification model according to the position information of the plurality of target frames to obtain a text identification result, wherein the text identification result comprises technical requirements in the engineering drawing, and the target identification model is used for carrying out character identification on the image.

8. The method of any of claims 1-5, wherein prior to determining a generic verification rule from a generic verification rule library that matches the technical requirement, further comprising:

Acquiring technical requirements in engineering drawings of a plurality of products, and checking items and checking standards corresponding to the technical requirements;

Generating a general test rule corresponding to each technical requirement according to the test item and the test standard corresponding to each technical requirement;

and creating the universal test rule base according to the universal test rules corresponding to the technical requirements.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, which computer program, when executed by the processor, implements the method according to any of claims 1-8.

10. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program which, when executed by a processor, implements the method according to any of claims 1-8.