Welding knowledge rule modeling and reasoning method with judgment parameter and judgment logic separated
By extracting the judgment data from the welding knowledge rules to form a parameter table, and writing complex logic into a function, reasoning based on the table lookup method, the problems of inconvenience in data update and insufficient processing of complex conditions in the welding knowledge rules modeling and inference are solved, and the problem of inconvenience of data update and insufficient processing of complex conditions in the welding knowledge rules is improved. Application effect and flexibility.
Patent Information
- Application Number
- CN202411423481.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-12
- Publication Date
- 2025-02-18
AI Technical Summary
The existing welding knowledge rule modeling and inference methods have problems such as inconvenient data update, insufficient ability to handle complex conditions, improper parameter correlation processing, and limited flexibility in the application.
By extracting the judgment data in welding knowledge rules, forming a parameter table, establishing a multi-dimensional parameter table or using multiple related parameter tables to express complex dependencies, and writing complex judgment logic into functions or subroutines based on the lookup table The method of realizing the reasoning of welding knowledge rules.
Effectively respond to problems such as untimely data updates, insufficient ability to handle complex conditions, improper parameter correlation processing, and limited flexibility, improve the application effect of welding knowledge rules, reduce the difficulty and workload of writing, and improve readability and flexibility.
Smart Images
Figure CN119476433A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of artificial intelligence technology for welding processes, and in particular to a welding knowledge rule modeling and reasoning method with judgment parameters and judgment logic separated, as well as a system, equipment and medium thereof. Background Art
[0002] Welding is one of the important processes for connecting metal materials. In order to ensure the quality and safety of welding, it is usually necessary to operate according to specific standards and specifications. These standards and specifications often exist in the form of natural language, and contain a series of knowledge rules on how to select the correct welding method, parameter settings, and evaluate welding results based on given parameters (such as material type, thickness, welding speed, etc.).
[0003] In modern manufacturing, such knowledge rules are converted into a form that can be recognized and executed by computers, usually directly through programming. However, the judgment logic of this method is closely integrated with the judgment data, resulting in problems such as lengthy and difficult to maintain code, poor scalability and reusability.
[0004] In the related art, the above-mentioned problems existing in the knowledge rule modeling and reasoning methods have been solved to a certain extent by separating the judgment parameters from the judgment logic. However, in the application of welding knowledge rules, due to the complexity, real-time and dynamic requirements of welding parameters, although separating the parameters from the logic by separating the judgment parameters from the judgment logic helps to simplify the coding, for the welding process, there are problems such as inconvenient data updating, insufficient ability to handle complex conditions, improper handling of parameter correlation and limited flexibility. Summary of the invention
[0005] The present invention provides a welding knowledge rule modeling and reasoning method and its system, equipment and medium that separate judgment parameters from judgment logic, which solves the problems of inconvenient data updating, insufficient ability to handle complex conditions, improper parameter correlation processing and limited flexibility in the application of welding knowledge rules in the knowledge rule modeling and reasoning methods in related technologies.
[0006] In order to achieve the above objectives, this application adopts the following technical solutions:
[0007] In a first aspect, a welding knowledge rule modeling method is provided in which judgment parameters and judgment logic are separated, comprising:
[0008] According to the content of the welding knowledge rules, multiple interrelated parameter tables of different dimensions are created and stored in a database; wherein each of the parameter tables includes a table name, multiple variables and values corresponding to each variable;
[0009] Determine the judgment condition of the judgment logic according to the content of the welding knowledge rule, express the judgment condition as a conditional expression based on the variables in the parameter table, and obtain a conditional expression group; wherein, for the variables having nonlinear relationships between multiple variables, construct a separate function expression;
[0010] A table lookup method corresponding to the welding knowledge rule is constructed according to the table name, the conditional expression group and the constructed function, wherein the return result of the table lookup method includes: a result row set and the number of result rows; and each variable of each row in the result row set is represented;
[0011] A welding knowledge rule model is constructed based on the parameter table, conditional expressions, constructed functions and table lookup method.
[0012] In a first possible implementation manner of the first aspect, creating multiple interrelated parameter tables of different dimensions according to the content of the welding knowledge rules and storing them in a database specifically includes:
[0013] Determine the relationships between variables;
[0014] According to the relationship between variables, multiple interrelated parameter tables of different dimensions are established;
[0015] Using a database to store parameter tables ensures that when one parameter changes, all related parameters can be updated accordingly.
[0016] In a second aspect, a welding knowledge rule reasoning method is provided in which judgment parameters and judgment logic are separated, including:
[0017] A welding knowledge rule modeling method in which the judgment parameter and the judgment logic are separated as described in the first aspect is adopted to obtain a welding knowledge rule model;
[0018] Call the search method corresponding to the target knowledge rule model to obtain the result row set and the number of result rows;
[0019] The value of each variable in each row of the result row set is obtained and the reasoning logic based on the welding knowledge rule model is executed.
[0020] In a first possible implementation manner of the second aspect, calling the search method corresponding to the target knowledge rule model to obtain a result row set and the number of result rows specifically includes:
[0021] Matching the parameter table according to the table name in the search method to obtain a matching parameter table;
[0022] Starting from the first row of the matching parameter table, according to the conditional expression group and the corresponding values of each variable in the current row
[0023] Perform conditional judgment. If the condition is met, save the entire current row in the result row set and start judging the next row; or, if the condition is not met, directly start judging the next row until all rows in the matching parameter table are judged;
[0024] Returns the set of result rows and the number of result rows.
[0025] In a third aspect, a welding knowledge rule modeling system is provided in which judgment parameters and judgment logic are separated, including:
[0026] A parameter table construction module is used to create multiple interrelated parameter tables of different dimensions according to the content of welding knowledge rules and store them in a database; wherein each parameter table includes a table name, multiple variables and values corresponding to each variable;
[0027] A conditional expression module, used to determine the judgment condition of the judgment logic according to the content of the welding knowledge rule, and to express the judgment condition as a conditional expression based on the variables in the parameter table to obtain a conditional expression group; wherein, for the variables having nonlinear relationships between multiple variables, a separate function expression is constructed;
[0028] A table lookup method construction module is used to construct a table lookup method corresponding to the welding knowledge rule according to the table name, the conditional expression group and the constructed function, and the return result of the table lookup method includes: a result row set and the number of result rows; and each variable of each row in the result row set is represented;
[0029] A model building module is used to build a welding knowledge rule model based on the parameter table, conditional expression, constructed function and table lookup method.
[0030] In a first possible implementation manner of the third aspect, the parameter table construction module is specifically used to:
[0031] Determine the relationships between variables;
[0032] According to the relationship between variables, multiple interrelated parameter tables of different dimensions are established;
[0033] Using a database to store parameter tables ensures that when one parameter changes, all related parameters can be updated accordingly.
[0034] In a fourth aspect, a welding knowledge rule reasoning system is provided in which judgment parameters and judgment logic are separated, comprising:
[0035] A welding knowledge rule model module, used to obtain a welding knowledge rule model by adopting the welding knowledge rule modeling method in which the judgment parameter and the judgment logic are separated as described in the first aspect;
[0036] A push search module is used to call the search method corresponding to the target knowledge rule model to obtain the result row set and the number of result rows;
[0037] The reasoning module is used to obtain the value of each variable in each row of the result row set and execute the reasoning logic based on the welding knowledge rule model.
[0038] In a first possible implementation manner of the fourth aspect, the reasoning module is specifically used to:
[0039] Matching the parameter table according to the table name in the search method to obtain a matching parameter table;
[0040] Starting from the first row of the matching parameter table, according to the conditional expression group and the corresponding values of each variable in the current row
[0041] Perform conditional judgment. If the condition is met, save the entire current row in the result row set and start judging the next row; or, if the condition is not met, directly start judging the next row until all rows in the matching parameter table are judged;
[0042] Returns the set of result rows and the number of result rows.
[0043] In a fifth aspect, an electronic device is provided, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of the method described in the first aspect or the second aspect are implemented.
[0044] In a sixth aspect, a readable storage medium is provided, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the method described in the first aspect or the second aspect are implemented.
[0045] The welding knowledge rule modeling and reasoning method of the present application, which separates the judgment parameters from the judgment logic, forms a parameter table by extracting all the judgment data in the knowledge rule, and expresses its complex dependency by establishing a multi-dimensional parameter table or using multiple related parameter tables; for complex judgment logic, certain specific complex conditions are separately written into functions or subroutines; the reasoning of welding knowledge rules is realized based on the table lookup method, so as to effectively deal with the problems of untimely data update, insufficient ability to handle complex conditions, improper parameter correlation and limited flexibility, thereby improving the application effect of welding knowledge rules, and specifically bringing the following advantages:
[0046] 1) When modeling knowledge rules, there is no need to repeatedly write judgment logic, which reduces the difficulty and workload of writing and improves readability;
[0047] 2) Knowledge rule judgment data is centrally managed in the form of tables. When the data in the knowledge rule content needs to be expanded and maintained, only the data table needs to be expanded or maintained. Users do not need to master programming languages and skills, which reduces the risk of errors in judgment logic due to expansion and modification of data.
[0048] 3) Since the judgment logic of the knowledge rule is separated from the judgment data, the judgment logic can be hidden during system implementation to prevent user modifications and misoperations from causing logical errors and program crashes, and the parameter table can be issued to users for modification to meet the needs of knowledge rule expansion and maintenance, thereby improving the flexibility of knowledge rule modeling.
[0049] 4) The parameter table can be used as a public resource for different knowledge rules. When a rule is updated or modified, it can be reused in other knowledge rules. You only need to change the table lookup conditions and corresponding functions according to actual needs. When the knowledge rules involve a large amount of judgment data, the workload can be greatly reduced.
[0050] 5) When creating the parameter table corresponding to the welding knowledge rules according to the content of the welding knowledge rules, the correlation between the parameters is taken into consideration to ensure that the parameter table can accurately reflect the complex situations in the real world and has good maintainability and scalability.
[0051] 6) The table lookup method focuses on simple condition matching, and leaves complex processing to specialized functions, which can make the entire system structure more reasonable. It can effectively manage complex conditions in welding knowledge rules and ensure the efficient operation of the entire system. BRIEF DESCRIPTION OF THE DRAWINGS
[0052] Figure 1 A schematic flow chart of a welding knowledge rule modeling method with separation of judgment parameters and judgment logic provided in an embodiment of the present application;
[0053] Figure 2 A schematic flow chart of a welding knowledge rule reasoning method with separation of judgment parameters and judgment logic provided in an embodiment of the present application;
[0054] Figure 3 A structural block diagram of a welding knowledge rule modeling system with separated judgment parameters and judgment logic provided in an embodiment of the present application;
[0055] Figure 4 A structural block diagram of a welding knowledge rule reasoning system with separated judgment parameters and judgment logic provided in an embodiment of the present application;
[0056] Figure 5 A structural block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0057] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined purpose, the technical solutions in the embodiments of the present application are clearly described. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of the present application.
[0058] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way are interchangeable where appropriate, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.
[0059] The description of the method flow in the specification of the present application and the steps of the flowchart in the drawings of the present specification do not have to be strictly executed according to the step numbers, and the method steps can be executed in a different order. Moreover, some steps can be omitted, multiple steps can be combined into one step, and / or one step can be decomposed into multiple steps.
[0060] In combination with the accompanying drawings and preferred embodiments, the welding knowledge rule modeling, reasoning method and system, equipment and medium for separating judgment parameters and judgment logic provided in the embodiments of the present application are described in detail as follows.
[0061] First, the application scenarios of the welding knowledge rule modeling and reasoning method in which the judgment parameters and judgment logic are separated in the embodiment of the present application are described in detail.
[0062] There are many types of parameters involved in the welding process, including but not limited to welding temperature, welding speed, welding current, voltage, welding material type, weld size, welding position, etc. The relationship between these parameters is often complex and changeable, and the welding process usually requires a high degree of real-time and dynamic performance, because the welding environment may change at any time (such as temperature fluctuations, material property changes, etc.). Many variables involved in the welding process, such as material type, thickness, welding speed, etc., are interdependent with some welding parameters, making the relationship between these variables very complex, and it is difficult to separate the judgment parameters from the judgment logic by simple means.
[0063] Based on this, an embodiment of the present application provides a welding knowledge rule modeling method that separates judgment parameters from judgment logic. A parameter table is formed by extracting all the judgment data in the knowledge rules, and complex dependencies are expressed by establishing a multi-dimensional parameter table or using multiple related parameter tables. For complex judgment logic, certain specific complex conditions are separately written into functions or subroutines. The reasoning of welding knowledge rules is realized based on a table lookup method, so as to effectively deal with problems such as untimely data updates, insufficient ability to handle complex conditions, improper parameter correlation and limited flexibility, thereby improving the application effect of welding knowledge rules.
[0064] See also Figure 1 , the embodiment of the present application provides a welding knowledge rule modeling method in which judgment parameters and judgment logic are separated, such as Figure 1 As shown, the modeling method of the embodiment of the present application includes:
[0065] Step S1, creating multiple interrelated parameter tables of different dimensions according to the content of the welding knowledge rules and storing them in a database; wherein each parameter table includes a table name, multiple variables and values corresponding to each variable.
[0066] In order to separate the judgment data from the judgment logic, firstly, a parameter table corresponding to the target knowledge rule is created according to the content of the target knowledge rule, which specifically includes the following steps:
[0067] Step S101, determining the relationship between variables.
[0068] In order to effectively deal with the correlation between parameters when creating the parameter table corresponding to the welding knowledge rules and ensure that the parameter table can accurately reflect the complex situations in the real world, before creating the parameter table, it is necessary to first deeply analyze all the variables in the welding knowledge rules and the dependencies between them. For example, the choice of welding current may depend on multiple factors such as material type, electrode diameter, welding position, etc.
[0069] Step S102: establishing a plurality of interrelated parameter tables of different dimensions according to the relationships between the variables.
[0070] These complex dependencies can be expressed by creating multi-dimensional parameter tables or using multiple related parameter tables. For example, a separate table can be set up for each material type, which contains the parameter values for different welding conditions applicable to that material. Similarly, a separate table can be created for welding current selection rules, welding speed, temperature, etc.
[0071] Create multiple tables to handle complex dependencies, such as a table for welding current selection and another table that records one or more recommended welding parameters based on material properties.
[0072] Step S103, using a database to store the parameter table to ensure that when a parameter changes, all related parameters can be updated accordingly.
[0073] Use a relational database (such as MySQL, PostgreSQL, etc.) or a non-relational database (such as MongoDB) to store parameter tables. Set foreign key constraints, triggers, or write custom functions / stored procedures to ensure that when a parameter changes, all related parameters are updated accordingly to maintain data consistency. Database query languages (such as SQL) can provide powerful query capabilities, making table lookups based on complex conditions easier and more efficient.
[0074] Step S2, determining the judgment conditions of the judgment logic according to the content of the welding knowledge rule, expressing the judgment conditions as conditional expressions based on the variables in the parameter table, and obtaining a conditional expression group; wherein, for variables having nonlinear relationships between multiple variables, constructing a separate function representation.
[0075] The judgment conditions of the judgment logic, that is, all the key factors that affect the final judgment result, convert the relationship between these factors into a set of conditional expressions. When dealing with some complex judgment logic in welding knowledge rules, there are some situations involving nonlinear relationships and dynamic changes between multiple variables, which may not be achieved through simple table lookup operations. In response to this, this application writes a dedicated function for each complex condition.
[0076] The obtained conditional expression can be one or more, so the conditional expression group contains one or more conditional expressions. When there are multiple conditional expressions, the multiple conditional expressions are taken as a whole.
[0077] Step S3, constructing a table lookup method corresponding to the welding knowledge rule according to the table name, the conditional expression group and the constructed function, the return result of the table lookup method includes: a result row set and the number of result rows; and representing each variable of each row in the result row set.
[0078] Specifically, after constructing the parameter table and determining the conditional expression, it is also necessary to construct a method that can obtain the value of the variable in the parameter table when the conditional expression is met, that is, a table lookup method. The table lookup method is specifically as follows:
[0079] Number of result rows = table lookup method (table name, conditional expression group, result row set); wherein, the result row set represents the set of rows obtained by table lookup, and the number of result rows represents the number of rows in the result row set. The input parameters of the table lookup method are the table name and the conditional expression group, the output parameter is the result row set, and the returned result is the number of result rows. Among them, when the number of result rows is equal to 0, it means that there are no results that meet the conditions in the parameter table, and the result row set is an empty set. The variables of each row in the result row set are represented in the following way: result row set [i]. variable name; wherein, i < number of result rows, i starts at 0. Using result row set [i]. variable name to represent the variables of each row in the result row set can avoid using specific data when expressing welding knowledge rules.
[0080] When encountering the above complex conditions, call the pre-configured dedicated function to obtain the result. This can keep the table lookup method simple and flexibly handle more complex logic.
[0081] Step S4, constructing a welding knowledge rule model based on the parameter table, conditional expression, constructed function and table lookup method.
[0082] The parameter table, conditional expression group, constructed function and table lookup method are integrated together to form a welding knowledge rule model.
[0083] The welding knowledge rule modeling method with judgment parameters and judgment logic separated provided in the embodiment of the present application forms a parameter table by extracting all judgment data in the knowledge rule, and expresses its complex dependency by establishing a multi-dimensional parameter table or using multiple related parameter tables; for complex judgment logic, certain specific complex conditions are separately written into functions or subroutines; the reasoning of welding knowledge rules is realized based on the table lookup method, so as to effectively deal with problems such as untimely data update, insufficient ability to handle complex conditions, improper parameter correlation and limited flexibility, thereby improving the application effect of welding knowledge rules, and specifically bringing the following advantages:
[0084] 1) When modeling knowledge rules, there is no need to repeatedly write judgment logic, which reduces the difficulty and workload of writing and improves readability;
[0085] 2) Knowledge rule judgment data is centrally managed in the form of tables. When the data in the knowledge rule content needs to be expanded and maintained, only the data table needs to be expanded or maintained. Users do not need to master programming languages and skills, which reduces the risk of errors in judgment logic due to expansion and modification of data.
[0086] 3) Since the judgment logic of the knowledge rule is separated from the judgment data, the judgment logic can be hidden during system implementation to prevent user modifications and misoperations from causing logical errors and program crashes, and the parameter table can be issued to users for modification to meet the needs of knowledge rule expansion and maintenance, thereby improving the flexibility of knowledge rule modeling.
[0087] 4) The parameter table can be used as a public resource for different knowledge rules. When a rule is updated or modified, it can be reused in other knowledge rules. You only need to change the table lookup conditions and corresponding functions according to actual needs. When the knowledge rules involve a large amount of judgment data, the workload can be greatly reduced.
[0088] 5) When creating the parameter table corresponding to the welding knowledge rules according to the content of the welding knowledge rules, the correlation between the parameters is taken into consideration to ensure that the parameter table can accurately reflect the complex situations in the real world and has good maintainability and scalability.
[0089] 6) The table lookup method focuses on simple condition matching, and leaves complex processing to specialized functions, which can make the entire system structure more reasonable. It can effectively manage complex conditions in welding knowledge rules and ensure the efficient operation of the entire system.
[0090] See also Figure 2 , the embodiment of the present application provides a welding knowledge rule reasoning method in which judgment parameters and judgment logic are separated, such as Figure 2 As shown, the reasoning method of the embodiment of the present application includes:
[0091] Step A1, obtaining a welding knowledge rule model by adopting the welding knowledge rule modeling method in which the judgment parameter and the judgment logic are separated as in the above embodiment;
[0092] Specifically, the modeling process of the welding knowledge rule model has been explained in the above embodiments and will not be repeated here.
[0093] Step A2, calling the search method corresponding to the target knowledge rule model to obtain the result row set and the number of result rows.
[0094] It is understandable that when the welding knowledge rule model is used for reasoning, the search method corresponding to the welding knowledge rule model needs to be called. The steps of calling the search method corresponding to the welding knowledge rule model to obtain the result row set and the number of result rows specifically include:
[0095] The parameter table is matched according to the table name in the search method to obtain a matching parameter table; it can be understood that if a matching parameter table is obtained by matching the parameter table according to the table name in the search method, the next step is continued to start the table search process; if there is no matching result, the table search process is terminated. Starting from the first row of the matching parameter table, conditional judgment is performed according to the conditional expression group and the corresponding values of each variable in the current row. If the condition is met, the entire current row is saved in the result row set and the next row judgment is started; or, if the condition is not met, the next row judgment is started directly until all rows in the matching parameter table are judged. Finally, when all rows in the matching parameter table are judged, the result row set and the number of result rows are returned.
[0096] Step A3, obtaining the value of each variable in each row of the result row set and executing the reasoning logic based on the welding knowledge rule model.
[0097] In the subsequent target knowledge rule reasoning, the value of each variable in each row of the result row set is obtained and the subsequent reasoning is completed.
[0098] The welding knowledge rule reasoning method with the judgment parameters and judgment logic separated above obtains the welding knowledge rule model for reasoning based on the welding knowledge rule modeling method with the judgment parameters and judgment logic separated above in the above embodiment, implements the steps of the above modeling method embodiment and each process of the embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.
[0099] See also Figure 3 Corresponding to the above-mentioned welding knowledge rule modeling method embodiment in which judgment parameters and judgment logic are separated, the present application embodiment provides a welding knowledge rule modeling system in which judgment parameters and judgment logic are separated, and the modeling system includes:
[0100] The parameter table construction module 1001 is used to create multiple interrelated parameter tables of different dimensions according to the content of the welding knowledge rules and store them in a database; wherein each of the parameter tables includes a table name, multiple variables and values corresponding to each variable;
[0101] The conditional expression module 1002 is used to determine the judgment condition of the judgment logic according to the content of the welding knowledge rule, and express the judgment condition as a conditional expression based on the variables in the parameter table to obtain a conditional expression group; wherein, for the variables having nonlinear relationships between multiple variables, a separate function expression is constructed;
[0102] The table lookup method construction module 1003 is used to construct a table lookup method corresponding to the welding knowledge rule according to the table name, the conditional expression group and the constructed function, and the return result of the table lookup method includes: a result row set and the number of result rows; and each variable of each row in the result row set is represented;
[0103] The model building module 1004 is used to build a welding knowledge rule model based on the parameter table, conditional expressions, constructed functions and table lookup methods.
[0104] Furthermore, the parameter table construction module 1001 is specifically used for:
[0105] Determine the relationships between variables;
[0106] According to the relationship between variables, multiple interrelated parameter tables of different dimensions are established;
[0107] Using a database to store parameter tables ensures that when one parameter changes, all related parameters can be updated accordingly.
[0108] The welding knowledge rule modeling system with the judgment parameters and judgment logic separated above implements the steps and various processes of the welding knowledge rule modeling method embodiment with the judgment parameters and judgment logic separated above, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.
[0109] See also Figure 4 , corresponding to the above-mentioned welding knowledge rule reasoning method embodiment in which judgment parameters and judgment logic are separated, the embodiment of the present application provides a welding knowledge rule reasoning system in which judgment parameters and judgment logic are separated, and the reasoning system includes:
[0110] The welding knowledge rule model module 1005 is used to obtain a welding knowledge rule model by adopting the welding knowledge rule modeling method in which the judgment parameter and the judgment logic are separated as described above;
[0111] Search module 1006, used to call the search method corresponding to the target knowledge rule model to obtain the result row set and the number of result rows;
[0112] The reasoning module 1007 is used to obtain the value of each variable in each row of the result row set and execute the reasoning logic based on the welding knowledge rule model.
[0113] Furthermore, the reasoning module 1006 is specifically used for:
[0114] Matching the parameter table according to the table name in the search method to obtain a matching parameter table;
[0115] Starting from the first row of the matching parameter table, according to the conditional expression group and the corresponding values of each variable in the current row
[0116] Perform conditional judgment. If the condition is met, save the entire current row in the result row set and start judging the next row; or, if the condition is not met, directly start judging the next row until all rows in the matching parameter table are judged;
[0117] Returns the set of result rows and the number of result rows.
[0118] The welding knowledge rule modeling system in which the judgment parameters and judgment logic are separated implements the steps and various processes of the welding knowledge rule reasoning method embodiment in which the judgment parameters and judgment logic are separated, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.
[0119] See also Figure 5 , corresponding to the above-mentioned welding knowledge rule modeling and reasoning method embodiment in which the judgment parameters and the judgment logic are separated, the embodiment of the present application provides an electronic device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the steps and various processes of the above-mentioned welding knowledge rule modeling and reasoning method embodiment in which the judgment parameters and the judgment logic are separated are implemented, and the same technical effect can be achieved. To avoid repetition, they will not be repeated here.
[0120] The memory 1009 can be used to store software programs and various data. The memory 1009 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, an application program or instructions required for at least one function (such as a sound playback function, an image playback function, etc.), etc. In addition, the memory 1009 may include a volatile memory or a non-volatile memory, or the memory 1009 may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. Volatile memory can be random access memory (Random Access Memory, RAM), static random access memory (Static RAM, SRAM), dynamic random access memory (Dynamic RAM, DRAM), synchronous dynamic random access memory (Synchronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (Double Data Rate SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (Enhanced SDRAM, ESDRAM), synchronous linked dynamic random access memory
[0121] (Synchlink DRAM, SLDRAM) and direct RAM bus random access memory (Direct Rambus RAM, DRRAM). The memory 1009 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.
[0122] The processor 1010 may include one or more processing units; optionally, the processor 1010 integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to an operating system, a user interface, and application programs, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It is understandable that the modem processor may not be integrated into the processor 1010.
[0123] Corresponding to the above-mentioned welding knowledge rule modeling and reasoning method embodiment in which the judgment parameters and the judgment logic are separated, the embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by the processor, the steps and each process of the embodiment of the welding knowledge rule modeling and reasoning method embodiment in which the judgment parameters and the judgment logic are separated are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.
[0124] The processor is the processor in the electronic device in the above-mentioned embodiment of the present application. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.
[0125] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.
[0126] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods of each embodiment of the present application.
[0127] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.
Claims
1. A welding knowledge rule modeling method with separation of judgment parameters and judgment logic, characterized in that: include: According to the content of the welding knowledge rules, multiple interrelated parameter tables of different dimensions are created and stored in a database; wherein each of the parameter tables includes a table name, multiple variables and values corresponding to each variable; Determine the judgment condition of the judgment logic according to the content of the welding knowledge rule, express the judgment condition as a conditional expression based on the variables in the parameter table, and obtain a conditional expression group; wherein, for the variables having nonlinear relationships between multiple variables, construct a separate function expression; A table lookup method corresponding to the welding knowledge rule is constructed according to the table name, the conditional expression group and the constructed function, wherein the return result of the table lookup method includes: a result row set and the number of result rows; and each variable of each row in the result row set is represented; A welding knowledge rule model is constructed based on the parameter table, conditional expressions, constructed functions and table lookup method.
2. The welding knowledge rule modeling method with separation of judgment parameters and judgment logic according to claim 1 is characterized in that: The method of creating multiple interrelated parameter tables of different dimensions according to the content of the welding knowledge rules and storing them in a database specifically includes: Determine the relationships between variables; According to the relationship between variables, multiple interrelated parameter tables of different dimensions are established; Using a database to store parameter tables ensures that when one parameter changes, all related parameters can be updated accordingly.
3. A welding knowledge rule reasoning method with separation of judgment parameters and judgment logic, characterized in that: include: A welding knowledge rule model is obtained by adopting a welding knowledge rule modeling method in which judgment parameters and judgment logic are separated as described in any one of claims 1 to 2; Call the search method corresponding to the target knowledge rule model to obtain the result row set and the number of result rows; The value of each variable in each row of the result row set is obtained and the reasoning logic based on the welding knowledge rule model is executed.
4. The welding knowledge rule reasoning method with separated judgment parameters and judgment logic according to claim 3 is characterized in that: The calling of the search method corresponding to the target knowledge rule model to obtain the result row set and the number of result rows specifically includes: Matching the parameter table according to the table name in the search method to obtain a matching parameter table; Starting from the first row of the matching parameter table, according to the conditional expression group and the corresponding values of each variable in the current row Perform conditional judgment. If the condition is met, save the entire current row in the result row set and start judging the next row; or, if the condition is not met, directly start judging the next row until all rows in the matching parameter table are judged; Returns the set of result rows and the number of result rows.
5. A welding knowledge rule modeling system with separated judgment parameters and judgment logic, characterized in that: include: A parameter table construction module is used to create multiple interrelated parameter tables of different dimensions according to the content of welding knowledge rules and store them in a database; wherein each parameter table includes a table name, multiple variables and values corresponding to each variable; A conditional expression module, used to determine the judgment condition of the judgment logic according to the content of the welding knowledge rule, and to express the judgment condition as a conditional expression based on the variables in the parameter table to obtain a conditional expression group; wherein, for the variables having nonlinear relationships between multiple variables, a separate function expression is constructed; A table lookup method construction module is used to construct a table lookup method corresponding to the welding knowledge rule according to the table name, the conditional expression group and the constructed function, and the return result of the table lookup method includes: a result row set and the number of result rows; and each variable of each row in the result row set is represented; A model building module is used to build a welding knowledge rule model based on the parameter table, conditional expression, constructed function and table lookup method.
6. The welding knowledge rule modeling system with separated judgment parameters and judgment logic according to claim 5 is characterized in that: The parameter table construction module is specifically used for: Determine the relationships between variables; According to the relationship between variables, multiple interrelated parameter tables of different dimensions are established; Using a database to store parameter tables ensures that when one parameter changes, all related parameters can be updated accordingly.
7. A welding knowledge rule reasoning system with separated judgment parameters and judgment logic, characterized in that: include: A welding knowledge rule model module, used to obtain a welding knowledge rule model by adopting a welding knowledge rule modeling method in which judgment parameters and judgment logic are separated as described in any one of claims 1 to 2; A search module is used to call the search method corresponding to the target knowledge rule model to obtain the result row set and the number of result rows; The reasoning module is used to obtain the value of each variable in each row of the result row set and execute the reasoning logic based on the welding knowledge rule model.
8. The welding knowledge rule reasoning system with separated judgment parameters and judgment logic according to claim 7 is characterized in that: The reasoning module is specifically used for: Matching the parameter table according to the table name in the search method to obtain a matching parameter table; Starting from the first row of the matching parameter table, according to the conditional expression group and the corresponding values of each variable in the current row Perform conditional judgment. If the condition is met, save the entire current row in the result row set and start judging the next row; Alternatively, if the condition is not met, the next row is directly judged until all rows in the matching parameter table are judged; Returns the set of result rows and the number of result rows.
9. An electronic device, characterized in that: The electronic device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the steps of the method according to any one of claims 1 to 4 when executed by the processor.
10. A readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.