A quality technical information recommendation method for a spatial product design analysis process

Abstract

The application relates to a quality technical information recommendation method for a space product design analysis process. The method comprises the following steps: acquiring a plurality of quality technical information tables which determine the quality of a space product, wherein the quality technical information tables comprise physical parameters related to the design and manufacturing of the space product; performing data compression and dimension reduction on the quality technical information tables to obtain quality technical feature vectors; obtaining a first priority based on the quality technical feature vectors and a space product quality prediction model; and obtaining recommended quality technical information tables based on the first priority. According to the scheme, data compression and dimension reduction processing is adopted, the quality technical information tables are input into the space product quality prediction model, and the most suitable quality technical information tables are obtained. The method greatly improves the accuracy and work efficiency of parameter screening, reduces the demand for experiments and trial and error, helps to realize high-quality design and manufacturing of the space product, and further ensures the high quality and reliability of the space product.

Description

Technical Field

[0001] This invention relates to a method for recommending quality technical information for the design and analysis process of space products. Background Technology

[0002] In existing space product design and manufacturing technologies, the design and manufacturing process involves a large number of diverse physical parameters, which together determine the quality of the product.

[0003] However, existing technologies lack effective methods for screening these parameters to find suitable parameters that ensure the quality of space products. Conventional screening methods often rely on extensive experimentation and trial and error, which not only consumes enormous time and resources but also makes it difficult to ensure that the obtained parameters are optimal or most suitable. Furthermore, manually processing numerous physical parameters and corresponding data, especially when the data volume is huge, undoubtedly increases the workload and complexity, making it even more difficult and challenging to find the parameters that are critical to product quality.

[0004] Accordingly, there is a need in this field for a new quality information recommendation scheme to address the above problems. Summary of the Invention

[0005] In order to overcome the above-mentioned defects, the present invention is proposed to provide a solution or at least a partial solution to the problem of difficulty in finding optimal quality information in the design and manufacturing technology of space products in the prior art.

[0006] In a first aspect, the present invention provides a method for recommending quality technical information for the design and analysis process of space products. The method includes: acquiring multiple quality technical information tables that determine the quality of space products, wherein the quality technical information tables include physical parameters involved in the design and manufacturing of space products; performing data compression and dimensionality reduction on the quality technical information tables to obtain quality technical feature vectors; obtaining a first priority based on the quality technical feature vectors and a space product quality prediction model; and obtaining recommended quality technical information tables based on the first priority.

[0007] As an alternative or supplement to the above solutions, in a method according to an embodiment of the present invention, "compressing and reducing the dimensionality of the quality technical information table to obtain a quality technical feature vector" includes: normalizing the data in the quality technical information table using a multivariate function to obtain a normalized quality parameter set; and performing additive dimensionality reduction analysis on the normalized quality parameter set to obtain a quality technical feature vector.

[0008] As an alternative or supplement to the above solutions, in a method according to an embodiment of the present invention, the mathematical representation of the multivariate function is as follows:

[0009]

[0010] Where S(x) is a multivariate function, x is the physical parameter in the quality technical information table, and c is the gain coefficient; the additive dimensionality reduction analysis is calculated using the following formula:

[0011] or

[0012]

[0013] Where A I S(x) and A II S(x) is the quality technology feature vector.

[0014] As an alternative or supplement to the above solutions, in a method according to an embodiment of the present invention, "obtaining a first priority based on the quality technology feature vector and the spatial product quality prediction model" includes: inputting the quality technology feature vector into the modeled spatial product quality prediction model to obtain corresponding path parameters; and obtaining a first priority based on the path parameters.

[0015] As an alternative or supplement to the above solutions, in a method according to an embodiment of the present invention, the first priority is calculated using the following formula:

[0016]

[0017] Where, λ i Let be the path coefficient of the i-th explicit variable. Let be the mean of the physical parameters in the quality technical information table of the i-th quality technical feature vector, and n be the number of physical parameters in the corresponding quality technical information table of the calculated quality technical feature vector.

[0018] As an alternative or supplement to the above solutions, in a method according to an embodiment of the present invention, "inputting the quality technical feature vector into a pre-modeled spatial product quality prediction model to obtain corresponding path parameters" includes: determining whether the quality technical feature vector satisfies a multivariate normal distribution; if the quality technical feature vector satisfies a multivariate normal distribution, the spatial product quality prediction model uses the maximum likelihood method to obtain the path parameters; for input quality technical feature vectors that do not satisfy a multivariate normal distribution, the spatial product quality prediction model uses an asymptotic distribution free estimation fitting index or a bootstrap method to obtain the path parameters.

[0019] As an alternative or supplement to the above solutions, in a method according to an embodiment of the present invention, the space product quality prediction model includes latent variables, wherein the number of quality technical feature vectors is the same as the number of latent variables.

[0020] As an alternative or supplement to the above solutions, in a method according to an embodiment of the present invention, the space product quality prediction model is a structural equation model.

[0021] In a second aspect, a control device is provided, comprising a processor and a storage device, the storage device being adapted to store a plurality of computer programs, the computer programs being adapted to be loaded and run by the processor to perform the quality technical information recommendation method for the space product design analysis process described in any of the above-described technical solutions.

[0022] In a third aspect, a computer-readable storage medium is provided, wherein a plurality of computer programs are stored therein, the computer programs being adapted to be loaded and run by a processor to perform the quality technical information recommendation method for the space product design analysis process described in any of the above-described technical solutions.

[0023] The present invention comprises one or more of the following technical solutions:

[0024] Beneficial effects:

[0025] The technical solution of this invention achieves efficient screening of diverse physical parameters during the design and manufacturing process of space products, effectively solving the problem of determining product quality under complex parameter environments. This solution employs data compression and dimensionality reduction processing to synthesize the quality technical information table into a quality technical feature vector. Then, through a space product quality prediction model, the first priority is accurately obtained, and the most suitable quality technical information table is recommended accordingly. This method greatly improves the accuracy and efficiency of parameter screening, reduces the need for experiments and trial-and-error, and helps to achieve high-quality design and manufacturing of space products, further ensuring the high quality and reliability of space products. Attached Figure Description

[0026] The disclosure of this invention will become more readily understood with reference to the accompanying drawings. It will be readily understood by those skilled in the art that these drawings are for illustrative purposes only and are not intended to limit the scope of protection of this invention. Furthermore, similar numbers in the drawings are used to denote similar components, wherein:

[0027] Figure 1 This is a flowchart of the main steps of a quality technical information recommendation method for a space-oriented product design and analysis process according to an embodiment of the present invention;

[0028] Figure 2 This is a flowchart of the sub-steps of a quality technical information recommendation method for a space-oriented product design and analysis process according to an embodiment of the present invention. Detailed Implementation

[0029] Some embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0030] In the description of this invention, "module" and "processor" can include hardware, software, or a combination of both. A module can include hardware circuitry, various suitable sensors, communication ports, memory, and may also include software components, such as computer programs, or a combination of software and hardware. A processor can be a central processing unit, microprocessor, image processor, digital signal processor, or any other suitable processor. The processor has data and / or signal processing capabilities. The processor can be implemented in software, in hardware, or a combination of both. Non-transitory computer-readable storage media includes any suitable medium capable of storing computer programs, such as magnetic disks, hard disks, optical disks, flash memory, read-only memory, random access memory, etc. The term "A and / or B" means all possible combinations of A and B, such as only A, only B, or A and B. The terms "at least one A or B" or "at least one of A and B" have a similar meaning to "A and / or B" and can include only A, only B, or A and B. The singular terms "a" or "this" can also include plural forms.

[0031] See appendix Figure 1 , Figure 1 This is a schematic flowchart illustrating the main steps of a quality technical information recommendation method for a space-oriented product design and analysis process according to an embodiment of the present invention. Figure 1 As shown, the method for recommending quality technical information for the space product design and analysis process in this embodiment of the invention mainly includes the following steps S10-S40.

[0032] Step S10: Obtain multiple quality technical information tables that determine the quality of the space product.

[0033] In this embodiment, the quality technical information sheet includes the physical parameters involved in the design and manufacture of the space product.

[0034] In one embodiment, a series of quality technical information tables are obtained, which contain key physical parameters that determine the quality of space products. In this embodiment, the quality technical information tables are derived from various published papers and other relevant literature, and they contain various physical parameters involved in the design and manufacturing process of space products.

[0035] To better understand this embodiment, the following explanation is provided. For the design and manufacture of a particular space product, there are typically numerous publicly available papers or other documents. Most of these papers or documents detail the product's superiority based on their own parameters. However, considering that the experimental conclusions in these papers or documents may be influenced by the credibility of the literature and other factors, their accuracy and consistency may vary. Therefore, independent and rigorous verification of the conclusions obtained from these documents is crucial.

[0036] Relying entirely on experimental methods for verification not only consumes a lot of resources and money, but also takes a long time and extends the cycle, making it particularly unsuitable for situations that require extensive verification.

[0037] Therefore, a more efficient method is adopted in this technology. First, representative quality technical information tables are extracted from various documents. These tables record in detail the physical parameters involved in the design and manufacturing process.

[0038] Through comprehensive and in-depth data analysis, this step aims to accurately identify and extract quality technology information, providing reliable foundational data for subsequent data compression, dimensionality reduction, and quality prediction.

[0039] In this embodiment, a quality technical information table is provided. Multiple quality technical information tables are obtained for subsequent data analysis and processing. Unitless values ​​such as material type can be specified with units, for example, the unit for material type is "*", thus distinguishing it from other physical parameters. The parameter value for material type represents different materials.

[0040]

[0041]

[0042] Step S20: Compress and reduce the dimensionality of the quality and technical information table to obtain the quality and technical feature vector.

[0043] In this embodiment, data compression is performed using multivariate functions, and data dimensionality reduction is performed using additive methods.

[0044] In one implementation, the quality technical information table undergoes a series of data processing steps, the main goal of which is to compress and reduce the dimensionality of the original data. Processing large-dimensional data leads to enormous computational costs, making it difficult to build accurate models and perform data regression. Therefore, this step is crucial for subsequent regression analysis.

[0045] In this implementation, the main combined variables obtained after dimensionality reduction are integrated into a single feature vector. This "vector" is actually a set of numerical values, which represent the transformed and processed original data. This feature vector may contain a wide variety of numerical values, each representing certain aspects of the original data.

[0046] This results in a more concise and easier-to-process quality technical feature vector, which is then used for subsequent regression analysis.

[0047] In this embodiment, the quality technology feature vector is obtained through steps S201-S202, such as... Figure 2 As shown, the details are as follows:

[0048] Step S201: Use multivariate functions to normalize the data in the quality technical information table to obtain a standardized set of quality parameters.

[0049] In this embodiment, the multivariate function is an S-function.

[0050] In one implementation, an S-function is used to normalize the data in the quality technical information table, ultimately obtaining a normalized set of quality parameters. In this embodiment, the data in the quality technical information table is transformed to a specific range, [0,1], using a specific mathematical expression. This transformation helps eliminate dimensional and numerical range differences between data points, making the data more suitable for subsequent analysis.

[0051] The normalization process begins with each data point in the quality technical information sheet. These data points may have different numerical ranges and units, and normalization is the process of converting these values ​​to the same standard, making the data analyzable.

[0052] For example, if the original numerical range of a certain quality parameter is [10, 100], then through multivariate function normalization, this range can be transformed to [0, 1]. This not only makes the data more standardized, but also facilitates subsequent data processing and analysis, allowing for the avoidance of biases caused by differences in numerical ranges when dealing with multiple parameters.

[0053] In this embodiment, the mathematical representation of a multivariate function is:

[0054]

[0055] Where S(x) is a multivariate function, x is the physical parameter in the quality technical information table, and c is the gain coefficient.

[0056] In this implementation, a gain coefficient *c* is introduced and multiplied by the physical parameter *x* from the quality technical information table to serve as the exponent of the natural coefficient *e*, thereby further altering the original normalization content. This subtle operation aims to adjust the weights of parameters during normalization, making the process more sensitive and thus better suited to practical needs. Specifically, the gain coefficient *c* can be the same or different for each physical parameter *x*. When the gain coefficients *c* differ, they not only affect the weight of each element in the eigenvector but also indirectly determine the importance of that eigenvector in the subsequent model. This ensures that the importance of each parameter is accurately reflected in the additive dimensionality reduction analysis. This coefficient allows the weighted summation of the original normalized quality parameters to retain the key information of the original data to the greatest extent possible, while also reducing the data dimensionality.

[0057] In this embodiment, the physical parameters in each quality technical information table are normalized to obtain a corresponding standardized quality parameter. The normalized set of all physical parameters in the quality technical information table is then used to obtain the standardized quality parameter set.

[0058] Step S202: Perform additive dimensionality reduction analysis on the normalized quality parameter set to obtain the quality technical feature vector.

[0059] In one implementation, the core objective of additive dimensionality reduction analysis is to reduce the dimensionality of the data while preserving its original characteristics, thus facilitating subsequent processing. This process involves feature extraction and integration, ensuring that each dimension contains multiple feature information from the original dataset. The additive model integrates the information from each feature through a weighted summation.

[0060] Through additive dimensionality reduction analysis, the resulting quality technical feature vector contains most of the information from the original normalized quality parameter set, but its dimensionality is significantly reduced, making it more suitable for subsequent quality prediction and analysis. This feature vector becomes a key input in subsequent steps, providing a foundation for spatial product quality prediction based on the SEM model.

[0061] In this implementation, additive dimensionality reduction analysis maintains the advantage of data monotonicity. This characteristic ensures that the dimensionality-reduced data still retains the key trends and patterns in the original data, which is crucial for subsequent regression analysis.

[0062] In this embodiment, the additive dimensionality reduction analysis is calculated using the following formula:

[0063] or

[0064]

[0065] Where AI S(x) and A II S(x) is the quality technology feature vector, where A is used when c is the uniform value. I The formula for S(x) uses A when c has different values. II The formula for S(x).

[0066] Preferably, to improve the internal correlation of the quality technical feature vector, in this embodiment, the composition of the quality technical feature vector is related to the number of latent variables. In this embodiment, each latent variable corresponds to several manifest variables, which are the physical parameters in the quality technical information table, and they directly affect the quality of the space product. Latent variables such as construction safety, construction comfort, and design and manufacturing quality cannot be measured, but they can be inferred to some extent from the manifest variables.

[0067] To achieve optimal dimensionality reduction, ideally, all manifest variables corresponding to each latent variable are weighted and superimposed to form a single quality technical feature vector. That is, the number of generated quality technical feature vectors is the same as the number of latent variables. For example, if in-depth analysis determines that the quality design of a spatial product involves four latent variables, then during additive dimensionality reduction analysis, we will obtain four quality technical feature vectors. These four vectors represent four different latent variables, and each quality technical feature vector is calculated by superimposing multiple manifest variables corresponding to that latent variable.

[0068] The importance of this step lies in its ability to achieve efficient data compression while preserving information. Reducing the dimensionality of the data simplifies the model, improves its efficiency, avoids overfitting caused by excessive dimensionality, and enhances the model's generalization ability. Simultaneously, through reasonable weight allocation and weighted summation, key information from the original data is preserved, providing reliable input for subsequent modeling.

[0069] Step S30: Based on the quality technology feature vector and the spatial product quality prediction model, obtain the first priority.

[0070] In this embodiment, the space product quality prediction model is the SEM model.

[0071] In one implementation, the first priority is obtained through steps S301 and S302.

[0072] Step S301: Input the quality technical feature vector into the modeled spatial product quality prediction model to obtain the corresponding path parameters.

[0073] In this embodiment, a path parameter will be generated corresponding to a quality technical information table.

[0074] In one implementation, the quality technical feature vector is a comprehensive set of parameters obtained after a series of precise calculations and weight allocations. These parameter sets contain the core information of each physical parameter in the original quality technical information table.

[0075] In this embodiment, the space product quality prediction model can describe the causal relationships between multiple latent variables. In the space product quality prediction model, the quality technology feature vector interacts with other variables through various paths defined in the model.

[0076] By inputting quality technical feature vectors into the space product quality prediction model, parameter values ​​for each path can be derived. These path parameters are essentially coefficients representing the relationships between variables; they quantify the mutual influence between latent variables and reflect the strength and direction of these interactions. In other words, they can clearly indicate the degree of influence of each quality technical feature vector on the quality of space products.

[0077] Step S302: Obtain the first priority based on the path parameters.

[0078] In this embodiment, a higher priority indicates that it better meets the requirements, and under the quality system, it is the optimal solution for quality.

[0079] In one implementation, the path parameters obtained in the previous step are used to derive a first priority through precise mathematical calculations. This value reflects the degree of consistency between the spatial product quality and the prediction model.

[0080] The first priority quantifies the degree of agreement between actual and expected parameters in a spatial product quality prediction model. This metric can be a percentage, typically ranging from 0% to 100%, where 0% represents a complete mismatch and 100% represents a perfect match. This priority value is used for subsequent evaluation and analysis, providing crucial information for final quality control and optimization.

[0081] In this embodiment, the first priority is obtained using the following formula:

[0082]

[0083] Where, λ i Let be the path coefficient of the i-th explicit variable. Let be the mean of the physical parameters in the quality technical information table of the i-th quality technical feature vector, and n be the number of physical parameters in the corresponding quality technical information table of the calculated quality technical feature vector.

[0084] This gives you the priority of one of the quality and technical information tables. Repeat the above steps to get the priority of the other quality and technical information tables.

[0085] Step S40: Obtain the recommended quality technology information table based on the first priority.

[0086] In this embodiment, the quality technical information table with the highest priority is recommended.

[0087] Here, we will explain the modeling process of the space product quality prediction model in this embodiment. The details are as follows:

[0088] First, it is necessary to identify all manifest and latent variables, and then classify the indicators to be measured into latent variables. These latent variables typically represent concepts that cannot be directly measured but can be indirectly measured through other variables, such as design and manufacturing quality and construction safety.

[0089] Reliability and validity testing is conducted to ensure the consistency and accuracy of the collected data. This step uses Cronbach's α coefficient to measure consistency. A value less than 0.6 indicates insufficient consistency; a value between 0.6 and 0.7 indicates considerable reliability; and a value greater than 0.7 indicates very good reliability. Validity testing uses the Kaiser-Meyer-Olkin Measure (KMO) and Bartlett's test of sphericity. The appropriateness of factor analysis can be assessed based on these values.

[0090] Based on the relationships between latent variables, an initial structural equation model can be constructed. This model depicts the path relationships between the latent and manifest variables, forming a complete network structure that lays the foundation for subsequent analysis.

[0091] Based on model identification, it is necessary to substitute observation data for parameter estimation, and evaluate the model according to the estimation results. After further correction and verification, the model becomes a well-formed spatial product quality prediction model.

[0092] In this embodiment, the structural equation model (SEM) is as follows:

[0093]

[0094] Where η (an n×1 vector) represents the endogenous latent variable, B (an n×n vector) represents the coefficient matrix of the endogenous latent variable, Γ represents the coefficient matrix of the exogenous latent variable, ξ (an m×1 vector) represents the exogenous latent variable, ζ (an n×1 vector) represents the random disturbance term, Y (a q×1 vector) represents the observed index of η, and Λ y (q×n dimensional matrix) represents the factor loading matrix of Y on η, ε (q×1 dimensional vector) represents the measurement error of Y, X (p×1 dimensional vector) represents the observation index of ξ, Λx (p×n dimensional vector) represents the factor loading matrix of X on ξ, and δ (p×1 dimensional vector) represents the measurement error of X.

[0095] Before inputting the quality technology feature vector into the spatial product quality prediction model, it is determined whether the quality technology feature vector satisfies a multivariate normal distribution.

[0096] When the input quality feature vector follows a multivariate normal distribution, the maximum likelihood method is used for parameter estimation to obtain the path parameters. In this case, the parameter estimates given by the maximum likelihood method are unbiased, consistent, and asymptotically efficient. Unbiasedness means that the expected value of the estimate equals the true parameter value; consistency means that as the sample size approaches infinity, the parameter estimates converge to the true parameters; and asymptotic efficiency means that among all unbiased estimates, the maximum likelihood estimate has the smallest variance.

[0097] When the input quality technical feature vector does not conform to a multivariate normal distribution, the asymptotically distributed free estimation of the fit index or the bootstrap method can be used to obtain the path parameters. In one implementation, the asymptotically distributed free estimation of the fit index is used. This method is suitable for non-normal data and can obtain estimates of relevant parameters and standard errors. When the quality technical feature vector violates a normal distribution, the squared values ​​and standard errors of the quality technical feature vector need to be corrected accordingly to ensure more accurate and reliable results. Furthermore, the bootstrap method is a useful alternative, particularly suitable for parameter estimation of non-normal data. This resampling method can calculate the squared values, parameter estimates, and standard errors of the quality technical feature vector. A major advantage of the bootstrap method is that it does not rely on distributional assumptions when calculating parameter estimates, thus providing strong support for handling non-normal data.

[0098] It should be noted that although the steps in the above embodiments are described in a specific order, those skilled in the art will understand that in order to achieve the effects of the present invention, different steps do not necessarily have to be executed in such an order. They can be executed simultaneously (in parallel) or in other orders, and these variations are all within the scope of protection of the present invention.

[0099] Those skilled in the art will understand that all or part of the processes in the method of the above embodiment of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer programs, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable storage medium can include any entity or device capable of carrying the computer program, a medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory, a random access memory, an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc. It should be noted that the content included in the computer-readable storage medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable storage medium does not include electrical carrier signals and telecommunication signals.

[0100] Furthermore, the present invention also provides a control device. In one embodiment of the control device according to the present invention, the control device includes a processor and a storage device. The storage device can be configured to store a program for executing the quality technical information recommendation method for the space product design analysis process of the above-described method embodiments. The processor can be configured to execute the program in the storage device, which includes, but is not limited to, the program for executing the quality technical information recommendation method for the space product design analysis process of the above-described method embodiments. For ease of explanation, only the parts related to the embodiments of the present invention are shown; for specific technical details not disclosed, please refer to the method section of the embodiments of the present invention. This control device can be a control device device comprising various electronic devices.

[0101] Furthermore, the present invention also provides a computer-readable storage medium. In one embodiment of the computer-readable storage medium according to the present invention, the computer-readable storage medium can be configured to store a program for performing the quality technical information recommendation method for the space product design analysis process described in the above-described method embodiments. This program can be loaded and run by a processor to implement the quality technical information recommendation method for the space product design analysis process described above. For ease of explanation, only the parts related to the embodiments of the present invention are shown; for specific technical details not disclosed, please refer to the method section of the embodiments of the present invention. The computer-readable storage medium can be a storage device comprising various electronic devices. Optionally, in the embodiments of the present invention, the computer-readable storage medium is a non-transitory computer-readable storage medium.

[0102] Furthermore, it should be understood that since the various modules are only provided to illustrate the functional units of the device of the present invention, the physical devices corresponding to these modules may be the processor itself, or a part of the processor's software, hardware, or a combination of software and hardware. Therefore, the number of modules shown in the figures is merely illustrative.

[0103] Those skilled in the art will understand that the various modules in the device can be adaptively split or combined. Such splitting or combining of specific modules will not cause the technical solution to deviate from the principles of the present invention; therefore, the technical solutions after splitting or combining will fall within the protection scope of the present invention.

[0104] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A method for recommending quality technical information for the design and analysis process of space products, characterized in that, include: Obtain multiple quality technical information tables that determine the quality of space products, wherein the quality technical information tables include physical parameters involved in the design and manufacture of space products; The quality technology information table is compressed and dimensionality reduced to obtain a quality technology feature vector; Based on the aforementioned quality technology feature vector and spatial product quality prediction model, a first priority is obtained; A recommended quality technology information table is obtained based on the first priority; The step of obtaining the first priority based on the quality technology feature vector and the space product quality prediction model includes: inputting the quality technology feature vector into the modeled space product quality prediction model to obtain the corresponding path parameters; and obtaining the first priority based on the path parameters. The first priority is calculated using the following formula: Where, λ i Let be the path coefficient of the i-th explicit variable. Let be the mean of the physical parameters in the quality technical information table of the i-th quality technical feature vector, and n be the number of physical parameters in the corresponding quality technical information table of the calculated quality technical feature vector.

2. The method for recommending quality technical information for space product design and analysis processes according to claim 1, characterized in that, "Performing data compression and dimensionality reduction on the aforementioned quality and technical information table to obtain a quality and technical feature vector" includes: The data in the quality technical information table is normalized using multivariate functions to obtain a standardized set of quality parameters. Additive dimensionality reduction analysis is performed on the standardized quality parameter set to obtain the quality technical feature vector.

3. The method for recommending quality technical information for space product design and analysis processes according to claim 2, characterized in that, The mathematical representation of the multivariate function is: Where S(x) is a multivariate function, x is the physical parameter in the quality technical information table, and c is the gain coefficient; The additive dimensionality reduction analysis is calculated using the following formula: or Where A I S(x) and A II S(x) is the quality technology feature vector, and A is used when c is the uniformity value. I The formula for S(x) uses A when c has different values. II The formula for S(x).

4. The method for recommending quality technical information for space product design and analysis processes according to any one of claims 1, characterized in that, The spatial product quality prediction model is a structural equation model.

5. The method for recommending quality technical information for space product design and analysis processes according to claim 4, characterized in that, The space product quality prediction model includes latent variables, wherein the number of quality technical feature vectors is the same as the number of latent variables.

6. The method for recommending quality technical information for space product design and analysis processes according to claim 4, characterized in that, "Inputting the quality technical feature vector into the pre-modeled spatial product quality prediction model to obtain the corresponding path parameters" includes: Determine whether the quality technology feature vector satisfies a multivariate normal distribution; If the quality technical feature vector satisfies a multivariate normal distribution, the spatial product quality prediction model uses the maximum likelihood method to obtain the path parameters. When the input quality technical feature vector does not satisfy the multivariate normal distribution, the spatial product quality prediction model uses the asymptotic distribution free estimation fitting index or the bootstrap method to obtain the path parameters.

7. A control device comprising a processor and a storage device, said storage device being adapted to store a plurality of computer programs, characterized in that, The computer program is adapted to be loaded and run by the processor to perform the quality technical information recommendation method for the space-oriented product design analysis process as described in any one of claims 1 to 6.

8. A computer-readable storage medium storing a plurality of computer programs, characterized in that, The computer program is adapted to be loaded and run by a processor to perform the quality technical information recommendation method for the space-oriented product design analysis process as described in any one of claims 1 to 6.

Images