Design parameter value generation method, device and computer readable medium

Abstract

A design parameter value generation method, device and computer-readable medium, the design parameter value generation method comprising: determining a target design parameter with a design parameter value generation requirement (101); obtaining at least two first training data including first design parameter values ​​corresponding to the target design parameter (102); generating a first parameter identifier for identifying the first design parameter value for each first design parameter value (103); training a parameter value generation model using each first design parameter value and the corresponding first parameter identifier (104); generating a second parameter identifier for identifying the target design parameter in the data to be processed according to semantic information of the data to be processed and semantic information of the first training data (105); inputting the second parameter identifier into the parameter value generation model to obtain a second design parameter value corresponding to the target design parameter in the data to be processed (106). The method can improve the accuracy of the recommended design parameter value.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to a method, device and computer-readable medium for generating design parameter values. Background Art

[0002] The design process of process flow and production line usually involves a large number of design parameters. Engineers need to determine the design parameter value corresponding to each design parameter. For example, in the process of manufacturing process design, engineers need to determine the time required for a certain machine to complete a certain manufacturing step. For each design parameter in the design process, engineers need to spend a long time to determine the design parameter value corresponding to the design parameter. In order to improve the efficiency of determining the design parameter value, the design parameter value can be recommended to the engineer based on the historical parameter design data.

[0003] Currently, when recommending design parameter values ​​to engineers based on historical parameter design data, for a design parameter whose design parameter value is to be recommended, a historical design parameter similar to the design parameter is determined from the reference historical parameter design data, and then the design parameter value of the design parameter is recommended based on the determined similar historical design parameter.

[0004] With regard to the current method of recommending design parameter values, for a design parameter whose design parameter value is to be recommended, since there may be multiple historical design parameters similar to the design parameter in the historical parameter design data, and the design parameter values ​​recommended with reference to different historical design parameters may be different, the existing design parameter value recommendation method only selects one of the similar historical design parameters to recommend the design parameter value, which results in poor accuracy of the recommended design parameter value. Summary of the invention

[0005] In view of this, the design parameter value generation method, device and computer-readable medium provided by the present invention can improve the accuracy of the recommended design parameter values.

[0006] In a first aspect, an embodiment of the present invention provides a method for generating a design parameter value, comprising:

[0007] determining a target design parameter with a design parameter value generation requirement;

[0008] Acquire at least two first training data, wherein the first training data includes a first design parameter value corresponding to the target design parameter;

[0009] For each of the first design parameter values, a first parameter identifier for identifying the first design parameter value is generated, wherein if an absolute value of a difference between two first parameter identifiers is less than a first preset threshold, then an absolute value of a difference between the two first design parameter values ​​identified by the two first parameter identifiers is less than a second preset threshold;

[0010] Using each of the first design parameter values ​​and the corresponding first parameter identifiers to train a parameter value generation model, wherein the parameter value generation model is used to generate corresponding design parameter values ​​according to the input parameter identifiers;

[0011] Generate a second parameter identifier for identifying the target design parameter in the data to be processed according to the semantic information of the data to be processed and the semantic information of each of the first training data, wherein the semantic information is used to describe the attributes of the data, and if the similarity between the semantic information of one of the first training data and the semantic information of the data to be processed is greater than a third preset threshold, then the absolute value of the difference between the first parameter identifier and the second parameter identifier for identifying the first design parameter value in the first training data is less than a fourth preset threshold;

[0012] The second parameter identifier is input into the parameter value generation model to obtain a second design parameter value corresponding to the target design parameter in the data to be processed.

[0013] In a first possible implementation manner, in combination with the first aspect, the acquiring at least two first training data includes:

[0014] For each second training data input, determining whether the second training data includes the target design parameter;

[0015] If the second training data includes the target design parameter, determining whether the second training data includes the first design parameter value corresponding to the target design parameter;

[0016] If the second training data includes the first design parameter value corresponding to the target design parameter, determining the second training data as one of the first training data;

[0017] If the second training data does not include the target design parameter, the second training data is discarded.

[0018] In a second possible implementation manner, in combination with the above-mentioned first possible implementation manner, after determining whether the second training data includes the first design parameter value corresponding to the target design parameter, the method further includes:

[0019] If the second training data does not include the first design parameter value corresponding to the target design parameter, determining whether there is third training data in each of the first training data, wherein the semantic information of the third training data is similar to the semantic information of the second training data;

[0020] If the third training data exists in each of the first training data, generating the first design parameter value corresponding to the target design parameter in the second training data according to the first design parameter value corresponding to the target design parameter in the third training data, and determining the second training data as one of the first training data;

[0021] If the third training data does not exist in each of the first training data, the second training data is discarded.

[0022] In a third possible implementation manner, in combination with the foregoing second possible implementation manner, generating, according to the first design parameter value corresponding to the target design parameter in the third training data, the first design parameter value corresponding to the target design parameter in the second training data includes:

[0023] The first design parameter value corresponding to the target design parameter in the third training data is used as the first design parameter value corresponding to the target design parameter in the second training data.

[0024] In a fourth possible implementation manner, in combination with the first aspect and any one of the first possible implementation manner, the second possible implementation manner, and the third possible implementation manner of the first aspect, the generating, for each of the first design parameter values, a first parameter identifier for identifying the first design parameter value includes:

[0025] Acquire a third parameter identifier included in the first training data, wherein the third parameter identifier is a field in the semantic information;

[0026] For each of the first training data, the third parameter identifier in the first training data is mapped to the first parameter identifier used to identify the first design parameter value in the first training data, wherein if the similarity of the semantic information of two of the first training data is greater than the third preset threshold, and the absolute value of the difference between the two first design parameter values ​​included in the two first training data is less than the second preset threshold, then the absolute value of the difference between the two first parameter identifiers mapped from the two first training data is less than the first preset threshold.

[0027] In a second aspect, an embodiment of the present invention further provides a design parameter value generating device, comprising:

[0028] a parameter determination module for determining a target design parameter having a design parameter value generation requirement;

[0029] a data acquisition module, configured to acquire at least two first training data, wherein the first training data includes a first design parameter value corresponding to the target design parameter determined by the parameter determination module;

[0030] a first identification mapping module, configured to generate, for each of the first design parameter values ​​included in the training data acquired by the data acquisition module, a first parameter identification for identifying the first design parameter value, wherein if the absolute value of the difference between two first parameter identifications is less than a first preset threshold, the absolute value of the difference between the two first design parameter values ​​identified by the two first parameter identifications is less than a second preset threshold;

[0031] a model training module, configured to generate a model by using the first design parameter values ​​included in each of the first training data acquired by the data acquisition module and the corresponding first parameter identifier training parameter values ​​determined by the first identifier mapping module, wherein the parameter value generation model is configured to generate corresponding design parameter values ​​according to an input parameter identifier;

[0032] a second identification mapping module, configured to generate a second parameter identification for identifying the target design parameter in the data to be processed according to the semantic information of the data to be processed and the semantic information of the first training data acquired by the data acquisition module, wherein the semantic information is used to describe the attributes of the data, and if the similarity between the semantic information of the first training data and the semantic information of the data to be processed is greater than a third preset threshold, then the absolute value of the difference between the first parameter identification for identifying the first design parameter value in the first training data and the second parameter identification is less than a fourth preset threshold;

[0033] A parameter value generation module is used to input the second parameter identifier generated by the second identifier mapping module into the parameter value generation model trained by the model training module to obtain a second design parameter value corresponding to the target design parameter in the data to be processed.

[0034] In a first possible implementation manner, in combination with the above second aspect, the data acquisition module includes:

[0035] a first judging unit, configured to judge, for each second training data input, whether the second training data includes the target design parameter;

[0036] a second judging unit, configured to judge whether the second training data includes the first design parameter value corresponding to the target design parameter when the first judging unit determines that the second training data includes the target design parameter;

[0037] a first execution unit, configured to determine a second training data as a first training data when the second judgment unit determines that the second training data includes the first design parameter value corresponding to the target design parameter;

[0038] A second execution unit is used to discard the second training data when the first judgment unit determines that the second training data does not include the target design parameter.

[0039] In a second possible implementation manner, in combination with the above-mentioned first possible implementation manner, the data acquisition module further includes:

[0040] a third judging unit, configured to judge whether there is third training data in each of the first training data when the second judging unit determines that the second training data does not include the first design parameter value corresponding to the target design parameter, wherein the semantic information of the third training data is similar to the semantic information of the second training data;

[0041] a third execution unit, configured to generate, when the third judgment unit determines that the third training data exists in each of the first training data, the first design parameter value corresponding to the target design parameter in the second training data according to the first design parameter value corresponding to the target design parameter in the third training data, and determine the second training data as one of the first training data;

[0042] A fourth execution unit is used to discard the second training data when the third judgment unit determines that the third training data does not exist in each of the first training data.

[0043] In a third possible implementation, in combination with the above second possible implementation,

[0044] The third execution unit is used to use the first design parameter value corresponding to the target design parameter in the third training data as the first design parameter value corresponding to the target design parameter value in the second training data.

[0045] In a fourth possible implementation manner, in combination with the foregoing second aspect and any one of the first possible implementation manner, the second possible implementation manner, and the third possible implementation manner of the second aspect, the first identity mapping module includes:

[0046] an identification acquisition unit, configured to acquire a third parameter identification included in the first training data, wherein the third parameter identification is a field in the semantic information;

[0047] an identifier mapping unit, used for mapping, for each of the first training data, the third parameter identifier acquired by the identifier acquisition unit in the first training data to the first parameter identifier for identifying the first design parameter value in the first training data, wherein if the similarity of the semantic information of two first training data is greater than the third preset threshold, and the absolute value of the difference between the two first design parameter values ​​included in the two first training data is less than the second preset threshold, then the absolute value of the difference between the two first parameter identifiers mapped for the two first training data is less than the first preset threshold.

[0048] In a third aspect, an embodiment of the present invention further provides another design parameter value generating device, comprising: at least one memory and at least one processor;

[0049] The at least one memory is used to store a machine-readable program;

[0050] The at least one processor is used to call the machine-readable program to execute the method provided by the first aspect or any possible implementation of the first aspect.

[0051] In a fourth aspect, an embodiment of the present invention further provides a computer-readable medium having computer instructions stored thereon. When the computer instructions are executed by a processor, the processor executes the method provided by the first aspect or any possible implementation of the first aspect.

[0052] It can be seen from the above technical solution that after determining a target design parameter with a design parameter value generation requirement, a plurality of first training data including first design parameter values ​​corresponding to the target design parameter values ​​are obtained, and then for each first design parameter value in the first training data, a first parameter identifier for identifying the first design parameter value is generated, and it is ensured that when the absolute value of the difference between the two first parameter identifiers is less than the first preset threshold, the absolute value of the difference between the two first design parameter values ​​identified by the two first parameter identifiers is less than the second preset threshold, and then the parameter value generation model is trained using each first design parameter value and the corresponding first parameter identifier. When it is necessary to recommend a design parameter value for the target design parameter in the data to be processed, a second parameter identifier for identifying the target design parameter in the data to be processed is generated according to the semantic information of the data to be processed and the semantic information of each first training data, and it is ensured that when the similarity between the semantic information of a first training data and the semantic information of the data to be processed is greater than the second preset threshold, the absolute value of the difference between the first parameter identifier for identifying the first design parameter value in the first training data and the second parameter identifier is less than the fourth preset threshold, and then the generated second parameter identifier is input into the parameter value generation model to obtain the second design parameter value corresponding to the target design parameter in the data to be processed. It can be seen that the parameter value generation model is trained based on multiple first design parameter values, and the parameter value generation model is used to generate second design parameter values ​​recommended to engineers. Since the generated second design parameter values ​​comprehensively consider various first design parameter values, errors in a single first design parameter value will not lead to large errors in the generated second design parameter values, thereby improving the accuracy of the recommended design parameter values. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Other features, characteristics, advantages and benefits of the present invention will become more apparent from the following detailed description taken in conjunction with the accompanying drawings.

[0054] Figure 1 is a flow chart of a method for generating design parameter values ​​provided by an embodiment of the present invention;

[0055] Figure 2A It is a schematic diagram of a semantic mapping design parameter identifier provided by an embodiment of the present invention;

[0056] Figure 2B is a flowchart of a first training data acquisition method provided by an embodiment of the present invention;

[0057] Figure 3 is a flowchart of another first training data acquisition method provided by an embodiment of the present invention;

[0058] Figure 4is a flow chart of a method for generating a first parameter identifier provided by an embodiment of the present invention;

[0059] Figure 5 is a flow chart of another method for generating design parameter values ​​provided by an embodiment of the present invention;

[0060] Figure 6 is a schematic diagram of a design parameter value generating device provided by an embodiment of the present invention;

[0061] Figure 7 is a schematic diagram of another design parameter value generating device provided by an embodiment of the present invention;

[0062] Figure 8 is a schematic diagram of another design parameter value generating device provided by an embodiment of the present invention;

[0063] Fig. 9 is a schematic diagram of another design parameter value generating device provided by an embodiment of the present invention;

[0064] Fig.10 It is a schematic diagram of a design parameter value generating device including a memory and a processor provided by an embodiment of the present invention.

[0065] List of reference numerals:

[0066] 101: Determine target design parameters with design parameter value generation requirements

[0067] 102: Obtain at least two first training data

[0068] 103: Generate a first parameter identifier for identifying the first design parameter value

[0069] 104: Generate a model using each first design parameter value and the corresponding first parameter identifier training parameter value

[0070] 105: Generate a second parameter identifier for identifying a target design parameter in the data to be processed

[0071] 106: Input the second parameter identifier into the parameter value generation model to obtain the second design parameter value

[0072] 201: Determine whether the input second training data includes the target design parameter

[0073] 202: Determine whether the second training data includes a first design parameter value corresponding to the target design parameter

[0074] 203: Determine the second training data as a first training data

[0075] 204: Discard the second training data

[0076] 205: Determine whether there is third training data in each first training data

[0077] 206: Generate a first design parameter value for the second training data, and determine the second training data as the first training data

[0078] 401: Obtain the third parameter identifier included in the first training data

[0079] 402: Map the third parameter identifier in the first training data to the first parameter identifier

[0080] 501: Determine target design parameters with design parameter value generation requirements

[0081] 502: Obtaining second training data including target design parameters

[0082] 503: Generate a first design parameter value for the second training data to obtain the first training data

[0083] 504: Map the third parameter identifier in the first training data to the first parameter identifier

[0084] 505: Generate a model according to each first design parameter value and the corresponding first parameter identifier training parameter value

[0085] 506: Generate a second parameter identifier for identifying a target design parameter in the data to be processed

[0086] 507: Input the second parameter identifier into the parameter value generation model to obtain the second design parameter value

[0087] 601: parameter determination module 602: data acquisition module 603: first identification mapping module

[0088] 604: Model training module 605: Second identification mapping module 606: Parameter value generation module

[0089] 6021: first judgment unit 6022: second judgment unit 6023: first execution unit

[0090] 6024: second execution unit 6025: third judgment unit 6026: third execution unit

[0091] 6027: fourth execution unit 6031: identification acquisition unit 6032: identification mapping unit

[0092] 1001: Memory 1002: Processor DETAILED DESCRIPTION

[0093] As mentioned above, when recommending design parameter values ​​to engineers based on historical parameter design data, for a design parameter whose design parameter value is to be recommended, a design parameter value is recommended with reference to a historical design parameter in the historical parameter design data that is similar to the design parameter. However, there may be multiple historical design parameters similar to the design parameter in the historical parameter design data, and different historical design parameters may be different. Therefore, the design parameter value recommended with reference to only one of the historical design parameters may not be accurate.

[0094] In an embodiment of the present invention, for a target design parameter with a design parameter value generation requirement, multiple first training data are obtained, and each first training data includes a first design parameter value corresponding to the target design parameter. Then, a first parameter identifier is generated for identifying each first design parameter value, and it is ensured that when the absolute value of the difference between two first parameter identifiers is less than a first preset threshold, the absolute value of the difference between the two first design parameter values ​​identified by the two first parameter identifiers is less than a second preset threshold. Then, each first design parameter value and the corresponding first parameter identifier are used to train a parameter value generation model. When it is necessary to recommend a design parameter value for a target design parameter in the data to be processed, a second parameter identifier for identifying the target design parameter in the data to be processed is generated based on the semantic information of the data to be processed and the semantic information of each first training data, and it is ensured that when the similarity between the semantic information of a first training data and the semantic information of the data to be processed is greater than a second preset threshold, the absolute value of the difference between the first parameter identifier for identifying the first design parameter value in the first training data and the second parameter identifier is less than a fourth preset threshold, and then the second parameter identifier is input into the parameter value generation model to obtain a second design parameter value corresponding to the target design parameter in the data to be processed, and the second design parameter value is used as the design parameter value recommended to the engineer. It can be seen that the parameter value generation model is trained based on each first design parameter value and the corresponding first parameter identifier. When it is necessary to recommend a design parameter value for a target design parameter in the data to be processed, a second parameter identifier is generated according to the semantic information of the data to be processed and the semantic information of the first training data. The second parameter identifier is input into the parameter value generation model to obtain the recommended second design parameter value. Since the parameter value generation model is trained based on each first design parameter value, the generated second design parameter value comprehensively refers to each first design parameter value, thereby avoiding the randomness that exists when recommending design parameter values ​​with reference to only one historical design parameter, and thus can improve the accuracy of the recommended design parameter value.

[0095] In the embodiment of the present invention, the first preset threshold, the second preset threshold, the third preset threshold and the fourth preset threshold are all preset values, and the specific value size can be determined according to the type of the target design parameter and the value range of the target design parameter. For example, when the target design parameter is the processing time required for the wire cutting equipment to process a certain workpiece, the first preset threshold can be set to 5, the second preset threshold to 3, the third preset threshold to 90%, and the fourth preset threshold to 5.

[0096] In the embodiment of the present invention, for any two first parameter identifiers, if the absolute value of the difference between the two first parameter identifiers is less than the first preset threshold, then the absolute value of the difference between the two first design parameter values ​​identified by the two first parameter identifiers is less than the second preset threshold, and at this time, the absolute value of the difference between the two first parameter identifiers is positively correlated with the absolute value of the difference between the corresponding two first design parameter values, that is, the smaller the absolute value of the difference between any two first parameter identifiers, the smaller the absolute value of the difference between the two first design parameter values ​​identified by the two first parameter identifiers. By generating a first parameter identifier for identifying the first design parameter value, similar first design parameter values ​​have similar first parameter identifiers, and then the parameter value generation model can be trained using each first design parameter value and the corresponding first parameter identifier, so that the trained parameter value generation model can generate the design parameter value according to the input parameter identifier.

[0097] In an embodiment of the present invention, for any first training data, if the similarity between the semantic information of the first training data and the semantic information of the data to be processed is greater than a third preset threshold, the absolute value of the difference between the first parameter identifier used to identify the first design parameter value in the first training data and the second parameter identifier is less than a fourth preset threshold, that is, the higher the similarity between the semantic information between the first training data and the data to be processed, the smaller the difference between the first parameter identifier used to identify the first design parameter value in the first training data and the second parameter identifier used to identify the target design parameter in the data to be processed. Since semantic information is used to describe the attributes of data, if the semantic information of a first training data has a high degree of similarity with the semantic information of the data to be processed, the numerical value of the target design parameter in the data to be processed should be close to the first design parameter value in the first training data. Therefore, when determining the second parameter identifier for identifying the target design parameter in the data to be processed, it is necessary to make the numerical value of the second parameter identifier close to the first parameter identifier for identifying the first design parameter value in the first training data. In this way, after the second parameter identifier is input into the parameter value generation model, the parameter value generation model can output the second design parameter value close to the first design parameter value in the first training data, thereby further ensuring the accuracy of the recommended design parameter values.

[0098] It should be noted that the first parameter identifier and the second parameter identifier can be pure numerical values ​​or a combination of numerical values ​​and letters or symbols. When the first parameter identifier and the second parameter identifier are pure numerical values, the difference between the two first parameter identifiers and the difference between the first parameter identifier and the second parameter identifier can be directly calculated. For example, the first parameter identifier is 100, the second parameter identifier is 101, and the absolute value of the difference between the first parameter identifier and the second parameter identifier is equal to 1. When the first parameter identifier and the second parameter identifier are a combination of numerical values ​​and letters or symbols, the letters and symbols in the first parameter identifier and the second parameter identifier can be ignored, and only the numerical parts of the first parameter representation and the second parameter identifier are calculated. For example, the first parameter identifier is S100, the second parameter identifier is S102, and the absolute value of the difference between the first parameter identifier and the second parameter identifier is equal to 2.

[0099] The design parameter value generating method and device provided by the embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0100] like Figure 1 As shown, an embodiment of the present invention provides a method for generating a design parameter value, which may include the following steps:

[0101] Step 101: determining a target design parameter with a design parameter value generation requirement;

[0102] Step 102: Acquire at least two first training data, wherein the first training data includes a first design parameter value corresponding to the target design parameter;

[0103] Step 103: for each first design parameter value, generating a first parameter identifier for identifying the first design parameter value, wherein if the absolute value of the difference between two first parameter identifiers is less than a first preset threshold, the absolute value of the difference between the two first design parameter values ​​identified by the two first parameter identifiers is less than a second preset threshold;

[0104] Step 104: training a parameter value generation model using each first design parameter value and the corresponding first parameter identifier, wherein the parameter value generation model is used to generate the corresponding design parameter value according to the input parameter identifier;

[0105] Step 105: generating a second parameter identifier for identifying a target design parameter in the data to be processed according to the semantic information of the data to be processed and the semantic information of the first training data, wherein the semantic information is used to describe the attributes of the data, and if the similarity between the semantic information of the first training data and the semantic information of the data to be processed is greater than a third preset threshold, then the absolute value of the difference between the first parameter identifier for identifying the first design parameter value in the first training data and the second parameter identifier is less than a fourth preset threshold;

[0106] Step 106: Input the second parameter identifier into the parameter value generation model to obtain a second design parameter value corresponding to the target design parameter in the data to be processed.

[0107] The design parameter value generation method provided by the embodiment of the present invention, after determining a target design parameter with a design parameter value generation requirement, obtains a plurality of first training data including a first design parameter value corresponding to the target design parameter value, and then generates a first parameter identifier for identifying the first design parameter value for each first training data, and ensures that when the absolute value of the difference between the two first parameter identifiers is less than the first preset threshold, the absolute value of the difference between the two first design parameter values ​​identified by the two first parameter identifiers is less than the second preset threshold, and then uses each first design parameter value and the corresponding first parameter identifier to train the parameter value generation model. When it is necessary to recommend a design parameter value for the target design parameter in the data to be processed, a second parameter identifier for identifying the target design parameter in the data to be processed is generated according to the semantic information of the data to be processed and the semantic information of each first training data, and ensures that when the similarity between the semantic information of a first training data and the semantic information of the data to be processed is greater than the second preset threshold, the absolute value of the difference between the first parameter identifier for identifying the first design parameter value in the first training data and the second parameter identifier is less than the fourth preset threshold, and then the generated second parameter identifier is input into the parameter value generation model to obtain the second design parameter value corresponding to the target design parameter in the data to be processed. It can be seen that the parameter value generation model is trained based on multiple first design parameter values, and the parameter value generation model is used to generate second design parameter values ​​recommended to engineers. Since the generated second design parameter values ​​comprehensively consider various first design parameter values, errors in a single first design parameter value will not lead to large errors in the generated second design parameter values, thereby improving the accuracy of the recommended design parameter values.

[0108] In the embodiment of the present invention, when step 105 generates the second parameter identifier according to the semantic information of the data to be processed and the semantic information of each first training data, the similarity between the data to be processed and the first training data is determined according to the semantic information. If the similarity between a first training data and the data to be processed is higher, the first parameter identifier of the first design parameter value in the first training data is closer to the second parameter identifier. The semantic information is used to describe the attributes of the data. The semantic information may include multiple fields. For example, in the process of designing a first training data of a product processing, the semantic information of the first training data is the machine type, the machine name, and the stage involved in the product processing.

[0109] In an embodiment of the present invention, since the trained parameter value generation model is used to generate corresponding design parameter values ​​according to the input parameter identifier, in order to enable the parameter value generation model to generate design parameter values ​​for target design parameters in the data to be processed, it is first necessary to generate a second parameter identifier for identifying the target design parameters in the data to be processed. Specifically, when generating the second parameter identifier, a first training data that is closest to the data to be processed in the semantic space can be found from each first training data according to the semantic information of the data to be processed and the semantic information of each first training data, that is, a first training data that is most similar to the data to be processed can be found from each first training data, and then the second parameter identifier is determined according to the first parameter identifier of the first design parameter value in the found first training data, so that the determined second parameter identifier is the same as or similar to the first parameter identifier of the first design parameter value in the found first training data. Since the parameter value generation model is obtained by training the first design parameter value and the corresponding first parameter identifier, after determining the second parameter identifier based on the first parameter identifier of the first design parameter value in the first training data similar to the data to be processed, and inputting the determined second parameter identifier into the parameter value generation model, the parameter value generation model can input the second design parameter value, and the first design parameter value in the first training data similar to the data to be processed is close to the second design parameter value.

[0110] It should be noted that the target design parameter is a field, and the first design parameter value and the second design parameter value are specific parameter values ​​of the target design parameter. For example, if the target design parameter is the time required for a machine to complete a workpiece processing step, the first design parameter value may be 20 seconds, and the second design parameter value may be 56 seconds.

[0111] Optionally, in Figure 1 On the basis of the design parameter value generation method shown, when the first parameter identifier for identifying the first design parameter value is generated in step 103, the purpose is to make the value of the generated first parameter identifier correlated with the value of the first design parameter value, so that the parameter value generation model can be trained according to each first design parameter value and the corresponding first parameter identifier, so that the trained parameter value generation model can generate the corresponding design parameter value according to the input parameter identifier. However, in the first training data obtained under normal circumstances, there is no correlation between the value of the parameter identifier for identifying the first design parameter value and the value of the first design parameter value, so it is necessary to generate a first parameter identifier that is correlated with the value of the first design parameter value for the first design parameter value in the first training data.

[0112] like Figure 2AAs shown, the five first design parameters are respectively the first design parameter 1, the first design parameter 2, the first design parameter 3, the first design parameter 4 and the first design parameter 5, wherein the original identification of the first design parameter 1 is A, the original identification of the first design parameter 2 is B, the original identification of the first design parameter 3 is C, the original identification of the first design parameter 4 is D, and the original identification of the first design parameter 5 is E.

[0113] The values ​​of the first design parameter 1 and the first design parameter 3 are similar, and the values ​​of the first design parameter 2 and the first design parameter 5 are similar, but there is no correlation between the original identifier A and the original identifier C, and there is no correlation between the original identifier B and the original identifier E. Therefore, it is impossible to generate a model based on the 5 first design parameters and the corresponding original identifier training parameter values.

[0114] By performing semantic mapping, the original identifier A is mapped to S11, the original identifier B is mapped to S31, the original identifier C is mapped to S12, the original identifier D is mapped to S21, and the original identifier E is mapped to S32.

[0115] After semantic mapping, the identifier of the first design parameter 1 is S11, the identifier of the first design parameter 2 is S31, the identifier of the first design parameter 3 is S12, the identifier of the first design parameter 4 is S21, and the identifier of the first design parameter 5 is S32. It can be seen that the values ​​of the first design parameter 1 and the first design parameter 3 are similar, and the corresponding identifier S11 of the first design parameter 1 and the identifier S12 of the first design parameter 3 are also similar. The values ​​of the first design parameter 2 and the first design parameter 5 are similar, and the corresponding identifier S31 of the first design parameter 2 and the identifier S32 of the first design parameter 5 are also similar, so that the identifier of the first design parameter is correlated with the value of the first design parameter, so that the parameter value generation model can be trained using the first design parameter and the identifier (first parameter identifier) ​​mapped out by semantics.

[0116] Optionally, in Figure 1 Based on the design parameter value generation method shown in FIG. 1 , when obtaining the first training data in step 102, the training data including the first design parameter value can be directly determined as the first training data. Figure 2B As shown, the method for obtaining the first training data may include the following steps:

[0117] Step 201: for each second training data input, determine whether the second training data includes the target design parameter, if it is Y, execute step 202, if not N, execute step 204;

[0118] Step 202: determining whether the second training data includes a first design parameter value corresponding to the target design parameter;

[0119] Step 203: when the second training data includes the first design parameter value corresponding to the target design parameter, the second training data is determined as the first training data, and the current process ends;

[0120] Step 204: discard the second training data.

[0121] In the embodiment of the present invention, since it is necessary to use the first design parameter value in the first training data to train the parameter value generation model, and the first design parameter value is the specific value of the target design parameter, the first training data first needs to include the target design parameter. After determining that a second training data includes the target design parameter, it is also necessary to determine whether the second training data includes the first design parameter value corresponding to the target design parameter, that is, to determine whether the second training data includes the specific value of the target design parameter. If the second training data includes the first design parameter value corresponding to the target design parameter, it means that the target design parameter in the second training data has prior knowledge, and the first design parameter value corresponding to the target design parameter in the second training data can be used to train the parameter value generation model, and then the second training data is determined as a first training data. If it is determined that a second training data does not include the target design parameter, the second training data is useless for training the parameter value generation model, and the second training data is discarded.

[0122] In an embodiment of the present invention, second training data with prior knowledge for the target design parameters is determined as the first training data, and then after the parameter value generation model is trained using the first design parameter value in the first training data, it can be ensured that the trained parameter value generation model can generate the second design parameter value more accurately, thereby further improving the accuracy of the recommended design parameter value.

[0123] Optionally, in Figure 2B Based on the first training data acquisition method shown, in addition to directly determining the training data including the first design parameter value as the first training data, the first training data can also be generated based on the training data including the target design parameter value but not including the first design parameter value. Figure 3 As shown, the method for obtaining the first training data may include the following steps:

[0124] Step 201: for each second training data input, determine whether the second training data includes the target design parameter, if it is Y, execute step 202, if not N, execute step 204;

[0125] Step 202: Determine whether the second training data includes a first design parameter value corresponding to the target design parameter. If it is Y, execute step 203; if not, execute step 205.

[0126] Step 203: determining the second training data as one training data, and ending the current process;

[0127] Step 205: judging whether there is third training data in each first training data according to the semantic information of the second training data and the semantic information of each first training data that has been determined, wherein the semantic information of the third training data is similar to that of the second training data; if so, executing step 206; if not, executing step 204;

[0128] Step 206: generating a first design parameter value corresponding to the target design parameter in the second training data according to the first design parameter value corresponding to the target design parameter in the third training data, determining the second training data as a first training data, and ending the current process;

[0129] Step 204: discard the second training data.

[0130] In an embodiment of the present invention, for second training data that includes a target design parameter but does not include a first design parameter corresponding to the target design parameter, third training data having semantic information similar to that of the second training data can be searched from each determined first training data, and then first design parameter values ​​corresponding to the target design parameter in the second training data are generated based on the first design parameter values ​​in the third training data, and then the second training data including the generated first design parameter values ​​is determined as a first training data to participate in the training of the parameter value generation model.

[0131] In an embodiment of the present invention, for the second training data including the target design parameter but not including the first design parameter value corresponding to the target design parameter, the first training data having similar semantic information to the second training data can be searched, and then the first design parameter value can be generated for the second training data according to the first design parameter value in the searched first training data, thereby increasing the number of first training data that can participate in the parameter value generation model training. By generating the first design parameter value for the second training data that does not include the first design parameter value, the number of first training data used for training the parameter value generation model can be increased, so that an accurate parameter value generation model can be generated for a smaller training set. In addition, by generating the first design parameter value for the second training data that does not include the first design parameter value, training data without prior knowledge can also participate in the model training process, thereby improving the applicability of the design parameter value generation method.

[0132] Optionally, in Figure 3On the basis of the first training data acquisition method shown, when generating the first design parameter value corresponding to the target design parameter in the second training data according to the first design parameter value corresponding to the target design parameter in the third training data in step 206, the first design parameter value corresponding to the target design parameter in the third training data can be directly used as the first design parameter value corresponding to the target design parameter in the second training data.

[0133] In the embodiment of the present invention, since the semantic information of the third training data is similar to the semantic information of the corresponding second training data, the value of the target design parameter in the second training data should be close to the value of the target design parameter in the third training data, so that the first design parameter value in the third training data can be directly determined as the first design parameter value corresponding to the target design parameter in the second training data, that is, the target design parameter in the second training data and the target design parameter in the third training data have the same first design parameter value. By making the target design parameter in the second training data and the target design parameter in the third training data have the same numerical value, the corresponding first design parameter value can be quickly generated for the target design parameter in the second training data, thereby improving the efficiency of obtaining the first training data.

[0134] It should be noted that, in addition to the above-mentioned embodiment directly determining the first design parameter value in the third training data as the first design parameter value corresponding to the target design parameter in the second training data, the value of the target design parameter in the second training data can also be determined according to the difference in semantic information between the second training data and the third training data and the first design parameter value in the third training data. For example, firstly calculate the matching coefficient between the semantic information in the second training data and the semantic information in the third training data, and then correct the first design parameter value in the third training data according to the calculated matching coefficient, and use the corrected first design parameter value in the third training data as the first design parameter value corresponding to the target design parameter in the second training data.

[0135] Optionally, in Figure 1 Based on the design parameter value generation method shown in FIG. 1 , when generating the first parameter identifier for identifying the first design parameter value in step 103, the third parameter identifier in the first training data can be mapped to the first parameter identifier. Figure 4 As shown, the method for generating the first parameter identifier may include the following steps:

[0136] Step 401: obtaining a third parameter identifier included in the first training data, wherein the third parameter identifier is a field in the semantic information;

[0137] Step 402: For each first training data, map the third parameter identifier in the first training data to a first parameter identifier for identifying the first design parameter value in the first training data, wherein if the similarity of the semantic information of two first training data is greater than a third preset threshold, and the absolute value of the difference between the two first design parameter values ​​included in the two first training data is less than a second preset threshold, then the absolute value of the difference between the two first parameter identifiers mapped from the two first training data is less than the first preset threshold.

[0138] In an embodiment of the present invention, the first training data originally includes a third parameter identifier for identifying the first design parameter value, but the third parameter identifier is usually not associated with the size of the first design parameter value identified by it, so it is impossible to train the parameter value generation model based on the third parameter identifier and the first design parameter value identified by it. To this end, it is necessary to map the third parameter identifier to the first parameter identifier based on the semantic information of the first training data, so that the size of the first parameter identifier and the first device parameter value identified by it are associated, and only then can the parameter value generation model be trained based on the first parameter identifier and the first design parameter value identified by it, so that the corresponding design parameter value can be obtained after the parameter identifier is input into the parameter value generation model.

[0139] In an embodiment of the present invention, when mapping the third parameter identifier to the first parameter identifier, the value of the third parameter identifier will not affect the size of the first parameter identifier, and the size of the first parameter identifier is determined by the semantic information of the corresponding first training data. Specifically, for any two first training data, the higher the similarity of the semantic information of the two first training data, and the smaller the difference between the two first design parameter values ​​in the two first training data, the smaller the difference between the two first parameter identifiers mapped for the two first training data. The third parameter identifier is mapped to the first parameter identifier based on the semantic information of the first training data and the size of the first design parameter value in the first training data, so that the size of the first parameter identifier and the first design parameter value it identifies are associated, so that the first parameter identifier and the first design parameter value can be clustered when the training parameter value generation model is generated, and the corresponding design parameter value can be generated according to the input parameter identifier.

[0140] In an embodiment of the present invention, a corresponding first parameter identifier is generated for a first design parameter value based on semantic mapping, so that the size of the first parameter identifier is associated with the size of the first design parameter value, so that the distance between two first parameter identifiers can reflect the similarity between the two first design parameter values ​​identified by the two first parameter identifiers, thereby recommending design parameter values ​​to engineers based on historical design parameter data.

[0141] The following takes the recommended design parameter values ​​in the product manufacturing process as an example to further describe the design parameter value generation method provided by the embodiment of the present invention in detail. Figure 5 As shown, the method may include the following steps:

[0142] Step 501: Determine a target design parameter with a design parameter value generation requirement.

[0143] In the embodiment of the present invention, according to the design requirements of the engineers, the design parameters whose design parameter values ​​need to be recommended to the engineers are determined as the target design parameters.

[0144] For example, during the design process, engineers need to obtain the processing time required for a corresponding machine to complete a corresponding process, so the processing time is determined as the target design parameter.

[0145] Step 502: Acquire second training data including target design parameters.

[0146] In the embodiment of the present invention, second training data including target design parameters is acquired from historical parameter design data.

[0147] For example, second training data including target design parameters is obtained from historical parameter design data, and the obtained second training data is shown in Table 1 below.

[0148] Table 1

[0149] product step Process Machine Name Machine Model Processing time P01 10 Process 20 S502 A 20 P01 10 Process 20 S109 A P01 20 Process 30 T232 B 5 P01 30 Process 50 S377 D 29 P01 30 Process 50 S372 D P01 30 Process 50 S375 D P01 30 Process 50 S376 D P01 40 Process 60 S391 E 9 P01 50 Process 70 S733 F 56 P01 50 Process 70 S730 F P01 50 Process 70 S731 F P01 50 Process 70 S732 F P01 50 Process 70 S734 F

[0150] In the above Table 1, a total of 13 second training data are obtained, wherein each line is a second training data, and each second training data includes six fields, namely, product, step, process, machine name, machine model and processing time. The values ​​of these six fields are the semantic information of the corresponding second training data, wherein the processing time field included in the semantic information is the target design parameter.

[0151] Step 503: Generate a first design parameter value for the second training data to obtain first training data.

[0152] In an embodiment of the present invention, after obtaining the second training data including the target design parameter, for each second training data, if the second training data includes the first design parameter value corresponding to the target design parameter, the second training data is directly used as a first training data; if the second training data does not include the first design parameter value corresponding to the target design parameter, then according to the semantic information of the second training data, the first design parameter value in the first training data similar to the second training data is used as the first design parameter value corresponding to the target design parameter in the second training data.

[0153] For example, among the 13 second training data shown in Table 1, the five second training data corresponding to the machine names S502, T232, S377, S391 and S733 include specific values ​​of the processing time, and the five second training data are directly used as the five first training data. The second training data corresponding to the machine name S109 has the same product, step, process and machine model as the second training data corresponding to the machine name S502, so the processing time of the second training data is configured to 20, and then the second training data is used as a first training data. Similarly, the processing time of the three second training data corresponding to the machine names S372, S375 and S376 is configured to 29, and then the three second training data are used as three first training data; the processing time of the four second training data corresponding to the machine names S730, S731, S732 and S734 is configured to 56, and then the four second training data are used as four first training data. The obtained first training data are shown in Table 2 below.

[0154] Table 2

[0155] product step Process Machine Name Machine Model Processing time P01 10 Process 20 S502 A 20 P01 10 Process 20 S109 A 20 P01 20 Process 30 T232 B 5 P01 30 Process 50 S377 D 29 P01 30 Process 50 S372 D 29 P01 30 Process 50 S375 D 29 P01 30 Process 50 S376 D 29 P01 40 Process 60 S391 E 9 P01 50 Process 70 S733 F 56 P01 50 Process 70 S730 F 56 P01 50 Process 70 S731 F 56 P01 50 Process 70 S732 F 56 P01 50 Process 70 S734 F 56

[0156] Step 504: Map the third parameter identifier in the first training data to the first parameter identifier.

[0157] In an embodiment of the present invention, for each first training data, the third parameter identifier originally used to identify the first design parameter value in the first training data is mapped to the first parameter identifier, and the mapped first parameter identifier is associated with the size of the corresponding first design parameter value. The smaller the difference between the two first parameter identifiers, the smaller the difference between the two first design parameter values ​​identified by the two first parameter identifiers.

[0158] For example, the machine name in the first training data is determined as the third parameter identifier, and the third parameter identifiers in each first training data are mapped to the first parameter identifier as shown in Table 3.

[0159] Table 3

[0160] The third parameter identifies the machine name. The first parameter identifies First design parameter value (processing time) S502 100 20

[0161] S109 101 20 T232 200 5 S377 300 29 S372 301 29 S375 302 29 S376 303 29 S391 400 9 S733 500 56 S730 501 56 S731 502 56 S732 503 56 S734 504 56

[0162] Step 505: Generate a model according to each first design parameter value and the corresponding first parameter identifier training parameter value.

[0163] In the embodiment of the present invention, each first parameter identifier and the first design parameter value identified by it are used as training data to train a parameter value generation model, thereby obtaining a parameter value generation model capable of generating corresponding design parameter values ​​according to the input parameter identifier.

[0164] For example, the last two columns of data in Table 3 are used as training data to train the parameter value generation model. After obtaining the parameter value generation model, each first parameter identification value is input into the parameter value generation model, and the recommended design parameter value output by the parameter value generation model can be obtained, as shown in Table 4. According to the data in Table 4, the recommended design parameter value output by the parameter value generation model according to the first parameter identification value is close to the first design parameter value identified by the first parameter identification, indicating that the parameter value generation model can generate relatively accurate design parameter values ​​according to the parameter identification.

[0165] Table 4

[0166]

[0167]

[0168] Step 506: Generate a second parameter identifier for identifying the target design parameter in the data to be processed.

[0169] In an embodiment of the present invention, when it is necessary to recommend design parameter values ​​for target design parameters in the data to be processed, a first training data similar to the data to be processed in the semantic space is searched from each of the first training data based on the semantic information of the data to be processed and each of the first training data, and then the second parameter identifier corresponding to the data to be processed is determined based on the first parameter identifier corresponding to the found first training data, so that the second parameter identifier is close to the first parameter identifier corresponding to the found first training data.

[0170] For example, in step 10 of manufacturing product P01, a new machine is added to complete step 10. The machine name of the newly added machine is S300, and the machine type of the newly added machine is type A. Since the corresponding product, step, process and machine model of the newly added machine are the same as those of the machine named S502, the second parameter identifier of the newly added machine can be mapped to 102, which is similar to the first parameter identifier corresponding to the machine named S502.

[0171] Step 507: Input the second parameter identifier into the parameter value generation model to obtain a second design parameter value.

[0172] In an embodiment of the present invention, after obtaining a second parameter identifier for identifying a target design parameter in the data to be processed, the obtained second parameter identifier is input into a parameter value generation model to obtain a second design parameter value output by the parameter value generation model, and the second design parameter value is the recommended design parameter value for the target design parameter in the data to be processed.

[0173] For example, after the second parameter identifier 102 is input into the parameter value generation model, the second design parameter value input into the parameter value generation model is 18.8147, that is, the time required for the machine with the recommended machine name S300 to complete the process 20 is 18.8147 seconds.

[0174] like Figure 6 As shown, an embodiment of the present invention provides a design parameter value generating device, comprising:

[0175] A parameter determination module 601, for determining target design parameters with design parameter value generation requirements;

[0176] A data acquisition module 602, used to acquire at least two first training data, wherein the first training data includes a first design parameter value corresponding to the target design parameter determined by the parameter determination module 601;

[0177] a first identification mapping module 603, for generating, for each first design parameter value included in the training data acquired by the data acquisition module 602, a first parameter identification for identifying the first design parameter value, wherein if the absolute value of the difference between two first parameter identifications is less than a first preset threshold, then the absolute value of the difference between the two first design parameter values ​​identified by the two first parameter identifications is less than a second preset threshold;

[0178] A model training module 604, used to generate a model by using the first design parameter values ​​included in each first training data acquired by the data acquisition module 602 and the corresponding first parameter identifier training parameter values ​​determined by the first identifier mapping module 603, wherein the parameter value generation model is used to generate the corresponding design parameter value according to the input parameter identifier;

[0179] a second identification mapping module 605, used to generate a second parameter identification for identifying a target design parameter in the data to be processed according to the semantic information of the data to be processed and the semantic information of the first training data acquired by the data acquisition module 602, wherein the semantic information is used to describe the attributes of the data, and if the similarity between the semantic information of the first training data and the semantic information of the data to be processed is greater than a third preset threshold, then the absolute value of the difference between the first parameter identification for identifying the first design parameter value in the first training data and the second parameter identification is less than a fourth preset threshold;

[0180] A parameter value generating module 606 is used to input the second parameter identifier generated by the second identifier mapping module 605 into the parameter value generating model trained by the model training module 604 to obtain a second design parameter value corresponding to the target design parameter in the data to be processed.

[0181] In an embodiment of the present invention, the parameter determination module 601 can be used to execute step 101 in the above method embodiment, the data acquisition module 602 can be used to execute step 102 in the above method embodiment, the first identification mapping module 603 can be used to execute step 103 in the above method embodiment, the model training module 604 can be used to execute step 104 in the above method embodiment, the second identification mapping module 605 can be used to execute step 105 in the above method embodiment, and the parameter value generation module 606 can be used to execute step 106 in the above method embodiment.

[0182] Optionally, in Figure 6 The design parameter values ​​are generated based on the device shown, as Figure 7 As shown, the data acquisition module 602 includes:

[0183] A first judging unit 6021, configured to judge, for each second training data input, whether the second training data includes the target design parameter;

[0184] A second judging unit 6022, configured to judge whether the second training data includes a first design parameter value corresponding to the target design parameter when the first judging unit 6021 determines that the second training data includes the target design parameter;

[0185] a first execution unit 6023, configured to determine a second training data as a first training data when the second judgment unit 6022 determines that the second training data includes a first design parameter value corresponding to the target design parameter;

[0186] A second execution unit 6024 is used to discard the second training data when the first judgment unit 6021 determines that the second training data does not include the target design parameter.

[0187] In an embodiment of the present invention, the first judgment unit 6021 can be used to execute step 201 in the above method embodiment, the second judgment unit 6022 can be used to execute step 202 in the above method embodiment, the first execution unit 6023 can be used to execute step 203 in the above method embodiment, and the second execution unit 6024 can be used to execute step 204 in the above method embodiment.

[0188] Optionally, in Figure 7The design parameter values ​​are generated based on the device shown, as Figure 8 As shown, the data acquisition module 602 further includes:

[0189] a third judging unit 6025, configured to judge whether there is third training data in each of the first training data when the second judging unit 6022 determines that the second training data does not include the first design parameter value corresponding to the target design parameter, wherein the semantic information of the third training data is similar to the semantic information of the second training data;

[0190] a third execution unit 6026, configured to generate, when the third judgment unit 6025 determines that the third training data exists in each of the first training data, a first design parameter value corresponding to the target design parameter in the second training data according to the first design parameter value corresponding to the target design parameter in the third training data, and determine the second training data as a first training data;

[0191] A fourth execution unit 6027 is configured to discard the second training data when the third judgment unit 6025 determines that the third training data does not exist in each first training data.

[0192] In the embodiment of the present invention, the third judgment unit 6025 can be used to execute step 205 in the above method embodiment, the third execution unit 6026 can be used to execute step 206 in the above method embodiment, and the fourth execution unit 6027 can be used to execute step 204 in the above method embodiment.

[0193] Optionally, in Figure 8 On the basis of the design parameter value generating device shown, the third execution unit 6026 is used to use the first design parameter value corresponding to the target design parameter in the third training data as the first design parameter value corresponding to the target design parameter value in the second training data.

[0194] Optionally, in Figures 6 to 8 Based on the design parameter value generating device shown in any of the accompanying drawings, as Fig. 9 As shown, the first identification mapping module 603 includes:

[0195] An identification acquisition unit 6031, used to acquire a third parameter identification included in the first training data, wherein the third parameter identification is a field in the semantic information;

[0196] An identifier mapping unit 6032 is used to map, for each first training data, the third parameter identifier obtained by the identifier acquisition unit 6031 in the first training data to a first parameter identifier for identifying the first design parameter value in the first training data, wherein if the similarity of the semantic information of two first training data is greater than the third preset threshold, and the absolute value of the difference between the two first design parameter values ​​included in the two first training data is less than the second preset threshold, then the absolute value of the difference between the two first parameter identifiers mapped from the two first training data is less than the first preset threshold.

[0197] In the embodiment of the present invention, the identification acquisition unit 6031 may be used to execute step 401 in the above method embodiment, and the identification mapping unit 6032 may be used to execute step 402 in the above method embodiment.

[0198] like Fig.10 As shown, one embodiment of the present invention provides another design parameter value generating device, comprising:

[0199] At least one memory 1001, configured to store executable instructions;

[0200] At least one processor 1002 is coupled to the at least one memory 1001, and when executing the executable instructions, is configured to:

[0201] determining a target design parameter with a design parameter value generation requirement;

[0202] Acquire at least two first training data, wherein the first training data includes a first design parameter value corresponding to the target design parameter;

[0203] For each of the first design parameter values, a first parameter identifier for identifying the first design parameter value is generated, wherein if an absolute value of a difference between two first parameter identifiers is less than a first preset threshold, then an absolute value of a difference between the two first design parameter values ​​identified by the two first parameter identifiers is less than a second preset threshold;

[0204] Using each of the first design parameter values ​​and the corresponding first parameter identifiers to train a parameter value generation model, wherein the parameter value generation model is used to generate corresponding design parameter values ​​according to the input parameter identifiers;

[0205] Generate a second parameter identifier for identifying the target design parameter in the data to be processed according to the semantic information of the data to be processed and the semantic information of each of the first training data, wherein the semantic information is used to describe the attributes of the data, and if the similarity between the semantic information of one of the first training data and the semantic information of the data to be processed is greater than a third preset threshold, then the absolute value of the difference between the first parameter identifier and the second parameter identifier for identifying the first design parameter value in the first training data is less than a fourth preset threshold;

[0206] The second parameter identifier is input into the parameter value generation model to obtain a second design parameter value corresponding to the target design parameter in the data to be processed.

[0207] Optionally, in Fig.10 Based on the design parameter value generating device shown, the at least one processor 1002 is further configured to:

[0208] For each second training data input, determining whether the second training data includes the target design parameter;

[0209] If the second training data includes the target design parameter, determining whether the second training data includes the first design parameter value corresponding to the target design parameter;

[0210] If the second training data includes the first design parameter value corresponding to the target design parameter, determining the second training data as one of the first training data;

[0211] If the second training data does not include the target design parameter, the second training data is discarded.

[0212] Optionally, in Fig.10 Based on the design parameter value generating device shown, the at least one processor 1002 is further configured to:

[0213] If the second training data does not include the first design parameter value corresponding to the target design parameter, determining whether there is third training data in each of the first training data, wherein the semantic information of the third training data is similar to the semantic information of the second training data;

[0214] If the third training data exists in each of the first training data, generating the first design parameter value corresponding to the target design parameter in the second training data according to the first design parameter value corresponding to the target design parameter in the third training data, and determining the second training data as one of the first training data;

[0215] If the third training data does not exist in each of the first training data, the second training data is discarded.

[0216] Optionally, in Fig.10 Based on the design parameter value generating device shown, the at least one processor 1002 is further configured to:

[0217] The first design parameter value corresponding to the target design parameter in the third training data is used as the first design parameter value corresponding to the target design parameter in the second training data.

[0218] Optionally, in Fig.10 Based on the design parameter value generating device shown, the at least one processor 1002 is further configured to:

[0219] Acquire a third parameter identifier included in the first training data, wherein the third parameter identifier is a field in the semantic information;

[0220] For each of the first training data, the third parameter identifier in the first training data is mapped to the first parameter identifier used to identify the first design parameter value in the first training data, wherein if the similarity of the semantic information of two of the first training data is greater than the third preset threshold, and the absolute value of the difference between the two first design parameter values ​​included in the two first training data is less than the second preset threshold, then the absolute value of the difference between the two first parameter identifiers mapped from the two first training data is less than the first preset threshold.

[0221] The present invention also provides a computer-readable medium storing instructions for causing a computer to execute the design parameter value generation method as described herein. Specifically, a system or device equipped with a storage medium can be provided, on which a software program code for implementing the functions of any of the above-mentioned embodiments is stored, and a computer (or CPU or MPU) of the system or device reads and executes the program code stored in the storage medium.

[0222] In this case, the program code itself read from the storage medium can realize the function of any one of the above-mentioned embodiments, and thus the program code and the storage medium storing the program code constitute a part of the present invention.

[0223] The storage medium embodiments for providing the program code include a floppy disk, a hard disk, a magneto-optical disk, an optical disk (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), a magnetic tape, a non-volatile memory card, and a ROM. Alternatively, the program code can be downloaded from a server computer by a communication network.

[0224] In addition, it should be clear that the functions of any of the above embodiments can be implemented not only by executing the program code read by the computer, but also by enabling an operating system operating on the computer to complete part or all of the actual operations based on instructions from the program code.

[0225] In addition, it can be understood that the program code read from the storage medium is written to a memory provided in an expansion board inserted into the computer or written to a memory provided in an expansion unit connected to the computer, and then based on the instructions of the program code, a CPU installed on the expansion board or the expansion unit is enabled to perform part or all of the actual operations, thereby realizing the functions of any of the above-mentioned embodiments.

[0226] It should be noted that not all steps and modules in the above-mentioned processes and system structure diagrams are necessary, and some steps or modules can be ignored according to actual needs. The execution order of each step is not fixed and can be adjusted as needed. The system structure described in the above-mentioned embodiments can be a physical structure or a logical structure, that is, some modules may be implemented by the same physical entity, or some modules may be implemented by multiple physical entities, or some components in multiple independent devices may be implemented together.

[0227] In the above embodiments, the hardware unit can be realized by mechanical means or electrical means. For example, a hardware unit can include permanent dedicated circuits or logic (such as special processors, FPGA or ASIC) to complete the corresponding operation. The hardware unit can also include programmable logic or circuits (such as general-purpose processors or other programmable processors), which can be temporarily set by software to complete the corresponding operation. Concrete implementation (mechanical means or dedicated permanent circuits or temporarily set circuits) can be determined based on cost and time considerations.

[0228] The present invention is shown and described in detail above through the accompanying drawings and preferred embodiments. However, the present invention is not limited to these disclosed embodiments. Based on the above multiple embodiments, those skilled in the art can know that the code review methods in the above different embodiments can be combined to obtain more embodiments of the present invention, and these embodiments are also within the protection scope of the present invention.

Claims

1. A method for generating design parameter values ​​for manufacturing process design, characterized in that: include: determining a target design parameter with a design parameter value generation requirement; Acquire at least two first training data, wherein the first training data includes a first design parameter value corresponding to the target design parameter; For each of the first design parameter values, a first parameter identifier for identifying the first design parameter value is generated, wherein if an absolute value of a difference between two first parameter identifiers is less than a first preset threshold, then an absolute value of a difference between the two first design parameter values ​​identified by the two first parameter identifiers is less than a second preset threshold; Using each of the first design parameter values ​​and the corresponding first parameter identifiers to train a parameter value generation model, wherein the parameter value generation model is used to generate corresponding design parameter values ​​according to the input parameter identifiers; Generate a second parameter identifier for identifying the target design parameter in the data to be processed according to the semantic information of the data to be processed and the semantic information of each of the first training data, wherein the semantic information is used to describe the attributes of the data, and if the similarity between the semantic information of one of the first training data and the semantic information of the data to be processed is greater than a third preset threshold, then the absolute value of the difference between the first parameter identifier and the second parameter identifier for identifying the first design parameter value in the first training data is less than a fourth preset threshold; The second parameter identifier is input into the parameter value generation model to obtain a second design parameter value corresponding to the target design parameter in the data to be processed.

2. The method according to claim 1, characterized in that The obtaining of at least two first training data comprises: For each second training data input, determining whether the second training data includes the target design parameter; If the second training data includes the target design parameter, determining whether the second training data includes the first design parameter value corresponding to the target design parameter; If the second training data includes the first design parameter value corresponding to the target design parameter, determining the second training data as one of the first training data; If the second training data does not include the target design parameter, the second training data is discarded.

3. The method according to claim 2, characterized in that After determining whether the second training data includes the first design parameter value corresponding to the target design parameter, the method further includes: If the second training data does not include the first design parameter value corresponding to the target design parameter, determining whether there is third training data in each of the first training data, wherein the semantic information of the third training data is similar to the semantic information of the second training data; If the third training data exists in each of the first training data, generating the first design parameter value corresponding to the target design parameter in the second training data according to the first design parameter value corresponding to the target design parameter in the third training data, and determining the second training data as one of the first training data; If the third training data does not exist in each of the first training data, the second training data is discarded.

4. The method according to claim 3, characterized in that The step of generating the first design parameter value corresponding to the target design parameter in the second training data according to the first design parameter value corresponding to the target design parameter in the third training data comprises: The first design parameter value corresponding to the target design parameter in the third training data is used as the first design parameter value corresponding to the target design parameter in the second training data.

5. The method according to any one of claims 1 to 4, characterized in that: The step of generating, for each of the first design parameter values, a first parameter identifier for identifying the first design parameter value comprises: Acquire a third parameter identifier included in the first training data, wherein the third parameter identifier is a field in the semantic information; For each of the first training data, the third parameter identifier in the first training data is mapped to the first parameter identifier used to identify the first design parameter value in the first training data, wherein if the similarity of the semantic information of two of the first training data is greater than the third preset threshold, and the absolute value of the difference between the two first design parameter values ​​included in the two first training data is less than the second preset threshold, then the absolute value of the difference between the two first parameter identifiers mapped from the two first training data is less than the first preset threshold.

6. A design parameter value generating device for manufacturing process design, characterized in that: include: A parameter determination module (601) for determining a target design parameter with a design parameter value generation requirement; a data acquisition module (602), used for acquiring at least two first training data, wherein the first training data includes a first design parameter value corresponding to the target design parameter determined by the parameter determination module (601); a first identification mapping module (603), configured to generate, for each of the first design parameter values ​​included in the training data acquired by the data acquisition module (602), a first parameter identification for identifying the first design parameter value, wherein if the absolute value of the difference between two first parameter identifications is less than a first preset threshold, the absolute value of the difference between the two first design parameter values ​​identified by the two first parameter identifications is less than a second preset threshold; a model training module (604), configured to generate a model by using the first design parameter values ​​included in each of the first training data acquired by the data acquisition module (602) and the corresponding first parameter identifier training parameter values ​​determined by the first identifier mapping module (603), wherein the parameter value generation model is configured to generate corresponding design parameter values ​​according to an input parameter identifier; a second identification mapping module (605) for generating a second parameter identification for identifying the target design parameter in the data to be processed according to the semantic information of the data to be processed and the semantic information of the first training data acquired by the data acquisition module (602), wherein the semantic information is used to describe the attribute of the data, and if the similarity between the semantic information of the first training data and the semantic information of the data to be processed is greater than a third preset threshold, then the absolute value of the difference between the first parameter identification for identifying the first design parameter value in the first training data and the second parameter identification is less than a fourth preset threshold; A parameter value generation module (606) is used to input the second parameter identifier generated by the second identifier mapping module (605) into the parameter value generation model trained by the model training module (604) to obtain a second design parameter value corresponding to the target design parameter in the data to be processed.

7. The device according to claim 6, characterized in that The data acquisition module (602) includes: a first judging unit (6021), configured to judge, for each second training data input, whether the second training data includes the target design parameter; a second judging unit (6022), configured to judge whether the second training data includes the first design parameter value corresponding to the target design parameter when the first judging unit (6021) determines that the second training data includes the target design parameter; a first execution unit (6023), configured to determine the second training data as the first training data when the second judgment unit (6022) determines that the second training data includes the first design parameter value corresponding to the target design parameter; A second execution unit (6024) is used to discard the second training data when the first judgment unit (6021) determines that the second training data does not include the target design parameter.

8. The device according to claim 7, characterized in that The data acquisition module (602) further comprises: a third judgment unit (6025), configured to judge whether there is a third training data in each of the first training data when the second judgment unit (6022) determines that the second training data does not include the first design parameter value corresponding to the target design parameter, wherein the semantic information of the third training data is similar to the semantic information of the second training data; a third execution unit (6026), configured to generate, when the third judgment unit (6025) determines that the third training data exists in each of the first training data, the first design parameter value corresponding to the target design parameter in the second training data according to the first design parameter value corresponding to the target design parameter in the third training data, and determine the second training data as one of the first training data; A fourth execution unit (6027) is used to discard the second training data when the third judgment unit (6025) determines that the third training data does not exist in each of the first training data.

9. The device according to claim 8, characterized in that The third execution unit (6026) is used to use the first design parameter value corresponding to the target design parameter in the third training data as the first design parameter value corresponding to the target design parameter in the second training data.

10. The device according to any one of claims 6 to 9, characterized in that The first identification mapping module (603) comprises: an identification acquisition unit (6031), used to acquire a third parameter identification included in the first training data, wherein the third parameter identification is a field in the semantic information; An identifier mapping unit (6032) is used to map, for each of the first training data, the third parameter identifier obtained by the identifier obtaining unit (6031) in the first training data to the first parameter identifier used to identify the first design parameter value in the first training data, wherein if the similarity of the semantic information of two first training data is greater than the third preset threshold, and the absolute value of the difference between the two first design parameter values ​​included in the two first training data is less than the second preset threshold, then the absolute value of the difference between the two first parameter identifiers mapped from the two first training data is less than the first preset threshold.

11. A design parameter value generating device for manufacturing process design, characterized in that: include: At least one memory (1001) and at least one processor (1002); The at least one memory (1001) is used to store a machine-readable program; The at least one processor (1002) is configured to call the machine-readable program to execute the method according to any one of claims 1 to 5.

12. A computer readable medium, characterized in that The computer readable medium stores computer instructions, which, when executed by a processor, cause the processor to perform any one of the methods of claims 1 to 5.

Images