CN118133763B - Method, device and system for predicting PCB design components and storage medium - Google Patents
Method, device and system for predicting PCB design components and storage medium Download PDFInfo
- Publication number
- CN118133763B CN118133763B CN202410559713.5A CN202410559713A CN118133763B CN 118133763 B CN118133763 B CN 118133763B CN 202410559713 A CN202410559713 A CN 202410559713A CN 118133763 B CN118133763 B CN 118133763B
- Authority
- CN
- China
- Prior art keywords
- pcb design
- design scheme
- component
- target
- components
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000013461 design Methods 0.000 title claims abstract description 222
- 238000000034 method Methods 0.000 title claims abstract description 32
- 239000013598 vector Substances 0.000 claims abstract description 39
- 239000011159 matrix material Substances 0.000 claims description 61
- 238000004590 computer program Methods 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 12
- 238000000354 decomposition reaction Methods 0.000 claims description 11
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000012938 design process Methods 0.000 abstract description 6
- 238000004891 communication Methods 0.000 description 11
- MINPZZUPSSVGJN-UHFFFAOYSA-N 1,1,1,4,4,4-hexachlorobutane Chemical compound ClC(Cl)(Cl)CCC(Cl)(Cl)Cl MINPZZUPSSVGJN-UHFFFAOYSA-N 0.000 description 9
- 101150049492 DVR gene Proteins 0.000 description 9
- 101100084627 Neurospora crassa (strain ATCC 24698 / 74-OR23-1A / CBS 708.71 / DSM 1257 / FGSC 987) pcb-4 gene Proteins 0.000 description 9
- 238000010586 diagram Methods 0.000 description 6
- 230000003321 amplification Effects 0.000 description 5
- 238000003199 nucleic acid amplification method Methods 0.000 description 5
- ZHBBDTRJIVXKEX-UHFFFAOYSA-N 1-chloro-2-(3-chlorophenyl)benzene Chemical compound ClC1=CC=CC(C=2C(=CC=CC=2)Cl)=C1 ZHBBDTRJIVXKEX-UHFFFAOYSA-N 0.000 description 4
- 239000003990 capacitor Substances 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 150000003071 polychlorinated biphenyls Chemical class 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000001914 filtration Methods 0.000 description 3
- AGCPZMJBXSCWQY-UHFFFAOYSA-N 1,1,2,3,4-pentachlorobutane Chemical compound ClCC(Cl)C(Cl)C(Cl)Cl AGCPZMJBXSCWQY-UHFFFAOYSA-N 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000005669 field effect Effects 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000008719 thickening Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000004148 unit process Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Stored Programmes (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a prediction method, a device, a system and a storage medium of a PCB design component, wherein the method comprises the following steps: acquiring at least one initial usage description similar to the target usage description, and taking a PCB design scheme corresponding to the at least one initial usage description as a reference object; acquiring component information in a reference object PCB design scheme, and acquiring hidden feature vectors of each component, the whole reference object PCB design scheme and a target PCB design scheme in the reference object PCB design scheme; and then obtaining each component in the target PCB design scheme, and forming the target PCB design scheme by each component. According to the application, the association relation between the whole PCB circuit and each component is obtained through the PCB design scheme of the historical data, so that a prediction thought is provided for the target demand PCB design scheme in view of the association relation, the accuracy of component selection is improved, and the efficiency of component selection in the PCB design process is greatly improved.
Description
Technical Field
The application relates to the technical field of electronic systems and integrated circuit designs, in particular to a method, a device, a system and a storage medium for predicting a PCB design component.
Background
In the prior art, a professional is required to select components in a PCB design scheme according to professional knowledge and limited experience, so that the PCB design difficulty is high, the design is limited, and the design efficiency is low. Meanwhile, the design thought of the PCB is limited by limited experience, so that the design effect is poor.
Therefore, a new design approach for component selection in PCB design is needed.
Disclosure of Invention
In view of this, embodiments of the present disclosure provide a method, apparatus, system and storage medium for predicting PCB design components.
The embodiment of the specification provides the following technical scheme:
the embodiment of the specification provides a prediction method of a PCB design component, which comprises the following steps:
Acquiring at least one initial usage description similar to the target usage description, and taking a PCB design scheme corresponding to the at least one initial usage description as a reference object;
Acquiring component information in a reference object PCB design scheme, and acquiring hidden feature vectors of each component, the whole reference object PCB design scheme and a target PCB design scheme in the reference object PCB design scheme;
And obtaining each component in the target PCB design scheme and the target PCB design scheme formed by the components according to the hidden feature vector.
The embodiment of the specification also provides a predicting device for a PCB design component, the predicting device for a PCB design component includes:
an acquisition module, configured to acquire at least one initial usage description similar to a target usage description, and take a PCB design scheme corresponding to the at least one initial usage description as a reference object;
The analysis module is used for acquiring the component information in the PCB design scheme as the reference object and acquiring hidden feature vectors of each component, the whole reference object PCB design scheme and the target PCB design scheme in the reference object PCB design scheme;
And the output module is used for obtaining each component in the target PCB design scheme and the target PCB design scheme formed by the components according to the hidden characteristic vector.
The embodiment of the specification also provides a prediction system of the PCB design components, which comprises a memory, a processor and a computer program, wherein the computer program is stored in the memory, and the processor runs the computer program to execute the prediction method of the PCB design components.
The embodiments of the present specification also provide a readable storage medium having stored therein a computer program for implementing the method of predicting PCB design components as described above when executed by a processor.
Compared with the prior art, the beneficial effects that above-mentioned at least one technical scheme that this description embodiment adopted can reach include at least:
According to the application, the association relation between the whole circuit of the PCB design scheme and each component is obtained through the PCB design scheme of the historical data, so that a prediction thought is provided for the target demand PCB design scheme in view of the association relation, richer data support is provided for the PCB design, the accuracy of component selection is improved, and meanwhile, the prediction thought is provided for the target demand PCB design scheme by obtaining the design relation between the whole PCB design thought and the components thereof, and the efficiency of component selection in the PCB design process is greatly improved. Meanwhile, the application is suitable for different types of PCB design tasks, has wide applicability, does not need professional design, and saves labor cost.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for predicting PCB design components provided by the application;
fig. 2 is a schematic diagram of a classical scenario of PCB design component prediction provided by the present application;
FIG. 3 is a schematic diagram of the present application for predicting a target PCB design using historical PCB designs similar to the target PCB design concept;
fig. 4 is a schematic diagram of an apparatus for predicting PCB design components provided by the present application;
Fig. 5 is a schematic diagram of a system for predicting PCB design components provided by the present application.
Detailed Description
Embodiments of the present application will be described in detail below with reference to the accompanying drawings.
Other advantages and effects of the present application will become apparent to those skilled in the art from the following disclosure, which describes the embodiments of the present application with reference to specific examples. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. The application may be practiced or carried out in other embodiments that depart from the specific details, and the details of the present description may be modified or varied from the spirit and scope of the present application. It should be noted that the following embodiments and features in the embodiments may be combined with each other without conflict. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It is noted that various aspects of the embodiments are described below within the scope of the following claims. It should be apparent that the aspects described herein may be embodied in a wide variety of forms and that any specific structure and/or function described herein is merely illustrative. Based on the present disclosure, one skilled in the art will appreciate that one aspect described herein may be implemented independently of any other aspect, and that two or more of these aspects may be combined in various ways. For example, apparatus may be implemented and/or methods practiced using any number and aspects set forth herein. In addition, such apparatus may be implemented and/or such methods practiced using other structure and/or functionality in addition to one or more of the aspects set forth herein.
It should also be noted that the illustrations provided in the following embodiments merely illustrate the basic concept of the present application by way of illustration, and only the components related to the present application are shown in the drawings and are not drawn according to the number, shape and size of the components in actual implementation, and the form, number and proportion of the components in actual implementation may be arbitrarily changed, and the layout of the components may be more complicated.
In addition, in the following description, specific details are provided in order to provide a thorough understanding of the examples. However, it will be understood by those skilled in the art that the present invention may be practiced without these specific details.
In the prior art, a professional is required to select components in a PCB design scheme according to professional knowledge and limited experience, so that the PCB design difficulty is high, the design is limited, and the design efficiency is low. Meanwhile, the design thought of the PCB is limited by limited experience, so that the design effect is poor.
Based on the above, the application provides a prediction scheme of PCB design components: as shown in fig. 3, by researching the association relationship between the whole circuit of the PCB design scheme and each component thereof in the historical PCB-ase:Sub>A design process, further, ase:Sub>A prediction thought is provided for the target requirement PCB-B design in view of the association relationship, and prediction recommendation is performed for the components in the target requirement PCB-B design scheme, so that richer datase:Sub>A support is provided for the PCB design, the accuracy of component selection is improved, and meanwhile, the prediction thought is provided for the target requirement PCB design scheme by acquiring the design relationship between the whole PCB design thought and the components contained therein, and the efficiency of component selection in the PCB design process is greatly improved.
The following describes the technical scheme provided by each embodiment of the present application with reference to the accompanying drawings.
As shown in FIG. 1, the application provides a method for predicting a PCB design component, which comprises steps S101-S103. Wherein step S101, at least one initial usage description similar to the target usage description is obtained, and a PCB design scheme corresponding to the at least one initial usage description is taken as a reference object. Step S102, obtaining component information in the PCB design scheme serving as the reference object, and obtaining hidden feature vectors of each component in the PCB design scheme serving as the reference object, the whole PCB design scheme serving as the reference object and the target PCB design scheme. And step S103, obtaining each component in the target PCB design scheme and the target PCB design scheme formed by the components according to the hidden feature vector.
In order to solve the problems of the prior art that the PCB design process requires professional personnel to select components and parts, the design is limited, and the PCB design efficiency is low. The design of the application is based on the prediction thought of the target PCB design components. For example, a prior art data set of PCB designs is first constructed, which stores historical PCB designs. In some embodiments, the dataset also stores a description of the use in a mapping relationship with the PCB design. As shown in table 1 below, the PCB design and its use are described.
TABLE 1
When the objective usage description "indoor air quality monitoring multiple sensors" is required to be designed for a corresponding PCB, for example, an initial usage description similar to the objective usage description is selected from the above-mentioned exemplary initial usage descriptions, on the one hand, a referenceable information source is enriched compared with the prior art, and on the other hand, by acquiring at least one initial usage description similar to the objective usage description, the accuracy and efficiency of PCB design component prediction are aimed to be improved.
At least one initial usage description similar to the target usage description is acquired in step S101, and a PCB design scheme corresponding to the at least one initial usage description is taken as a reference object.
For example, PCBs 2 and 4 similar to the description of the intended use are acquired. In some embodiments, the PCB design scheme corresponding to the initial usage description with the highest similarity is taken as a reference object. Or the initial usage description with the similarity exceeding the preset threshold value is taken as a reference object, for example, the PCB2 and the PCB4 are taken as reference objects.
In step S102, component information in the reference object PCB design is obtained, and a hidden feature vector of each component in the reference object PCB design, the overall reference object PCB design, and the target PCB design is obtained.
In combination with the above embodiment, the information of each component in the corresponding PCB design scheme will be obtained as the reference object initial usage description, for example, components such as a communication module, a capacitor, a diode, etc. are corresponding to the PCB2 circuit, and components such as a microcontroller, a communication module, a display screen, a diode, etc. are corresponding to the PCB4 circuit.
The components of the PCB6 are obtained in combination with the use of components similar to the PCB design described for the intended use and components known for the intended PCB design. The present embodiment constructs the training data set with some known component information present in the PCB6, as in table 2.
TABLE 2
Taking the contents in the table 2 as co-occurrence matrixes, and obtaining the co-occurrence matrixes by multiplying the PCB design scheme matrix and the component matrix under the framework of a matrix decomposition algorithm.
If the co-occurrence matrix corresponding to 3×8 dimensions in table 2 is decomposed into a form of multiplying a PCB design scheme matrix in 3×k dimensions by a component matrix in k×8 dimensions, where k is a hidden feature vector dimension, that is, the number of hidden features, and a k value is automatically obtained in matrix decomposition, the size of k determines the strength of the expression capability of the hidden feature vector, and the larger k is, the stronger the expression information is, that is, the more specific the PCB design scheme and the classification of the components are divided. In this embodiment, k is 2, i.e. a hidden feature vector with 2 dimensions is obtained.
Namely, the hidden feature vector is used as a description feature converted between the PCB design scheme and the components, and the similarity relevance is described by mapping the PCB design scheme and the component data into a high-dimensional space and a new semantic space respectively, and of course, the higher the dimension is, the closer the similarity relevance is described.
In step S103, each component in the target PCB design and the target PCB design composed of each component are obtained according to the hidden feature vector.
And in combination with table 2, the target use description is taken as a new row number in the matrix, the co-occurrence matrix is 3 multiplied by 8, the hidden feature vector is obtained by decomposing the co-occurrence matrix, the components in the target PCB6 circuit are finally obtained, and the obtained components form the target PCB design scheme.
Other components such as communication modules and diodes are obtained, for example, from microcontrollers, sensors, etc. known in the PCB6 circuitry, ultimately constituting the target PCB6. In other embodiments, even if there are no known components in the target PCB6 circuit, other components in the target PCB6 circuit can be finally obtained through matrix similarity, matrix decomposition, and the like, and the target PCB6 circuit is finally formed.
In combination with the above embodiment, as shown in fig. 2, the component information of the reference object PCB design scheme, such as component 1 and component 2 … … component n, is obtained from the history database. Each component (e.g., component 1, component 3, component n, and component m) required for the target PCB6 is predicted from these reference components, and the target PCB6 is finally formed from these components.
According to the application, the association relation between the whole circuit of the PCB design scheme and each component is obtained through the PCB design scheme of the historical data, so that a prediction thought is provided for the target demand PCB design scheme in view of the association relation, richer data support is provided for the PCB design, the accuracy of component selection is improved, and meanwhile, the prediction thought is provided for the target demand PCB design scheme by obtaining the design relation between the whole PCB design thought and the components thereof, and the efficiency of component selection in the PCB design process is greatly improved. Meanwhile, the application is suitable for different types of PCB design tasks, has wide applicability, does not need professional design, and saves labor cost.
In some embodiments, the method for predicting a PCB design component further comprises: acquiring PCB design schemes of historical data and initial application descriptions corresponding to each PCB design scheme; obtaining respective corresponding feature vectors from the initial usage description and the target usage description through text conversion; the cosine similarity of the corresponding feature vectors between the initial usage descriptions is calculated, so that the similarity and the highest similarity of each initial usage and the target usage description are obtained; the PCB design scheme corresponding to the highest similarity initial use description is taken as a reference object.
In combination with the above embodiments, the PCB design scheme for obtaining the history data, such as the PCB1-PCB5, and the initial usage description corresponding to each circuit of the PCB1-PCB 5. And applying TF-IDF conversion to the initial usage description text of each PCB design scheme to obtain feature vectors. The results after TF-IDF treatment are shown in Table 3.
TABLE 3 Table 3
And further, the cosine similarity of the corresponding feature vectors between every two initial usage descriptions is calculated to obtain the similarity between each initial usage description and the target usage description, as shown in table 4.
TABLE 4 Table 4
And selecting the existing PCB design most similar to the target PCB design according to the obtained similarity. Based on the cosine similarity calculation, the PCB design most similar to PCB6 can be determined and the comparison results are shown in table 5.
TABLE 5
By ranking the similarities in table 5, a score ranging from 0.7 to 1.0 represents a high similarity, indicating that the PCB is very similar to the target PCB, and has many commonalities in component selection and application scenarios. 0.4-0.69 represents a moderate degree of similarity, indicating that the PCB has some similarity with the target PCB, but some differences exist. 0-0.39 represents low similarity, which means that the similarity between the PCB and the target PCB is not high, and the PCB and the target PCB may have larger difference in component selection and application scenes.
Finally, according to table 5, the highest similarity of PCB2 and PCB4 to PCB6 is obtained, so they will be chosen as reference objects for the subsequent ALS model training and component prediction steps.
In some embodiments, the method for predicting a PCB design component further comprises: obtaining a first initial usage description containing key features from historical data through semantic analysis according to the key word features in the target usage description; the first initial usage description corresponds to the PCB design scheme as a reference object.
Specifically, the functions of the initial usage descriptions corresponding to the PCB designs in the historical dataset are highlighted by performing label processing on the initial usage descriptions, such as marking the keyword features in each initial usage description, such as by thickening or the like. If the PCB1 corresponds to the initial usage description "outdoor environment monitoring temperature and humidity detection", the PCB2 corresponds to the initial usage description "air quality monitoring multiple gases", and the PCB4 corresponds to the initial usage description "data processing unit processes sensor data". The key word characteristics corresponding to the PCB1 are "outdoor", "temperature and humidity", the key word characteristics corresponding to the PCB2 are "air quality", and the key word characteristics corresponding to the PCB4 are "sensor".
The target PCB6 is generally described as "indoor air quality monitoring multiple sensors". The PCBs 2 and 4 containing the keyword features are obtained from the PCBs 1 to 5 by semantic analysis as first initial usage descriptions, and the PCBs 2 and 4 are taken as reference objects.
In some embodiments, the method for predicting a PCB design component further includes: analyzing components in the PCB design scheme as a reference object to obtain reference components, obtaining scoring co-occurrence matrixes of all the PCB design scheme of the reference object, the reference components and the target PCB design scheme, and carrying out matrix decomposition on the scoring co-occurrence matrixes to obtain hidden feature vectors corresponding to the reference components.
In combination with the above embodiment, the PCB2 and the PCB4 having the highest similarity with the PCB6 are taken as reference objects, and the components of the PCB2 and the PCB4 are obtained as reference components. For example, the sensor, the communication module, the capacitor and the diode in the PCB2 are used as reference components, and the controller, the communication module, the display screen and the diode in the PCB4 are used as reference components. And setting a scoring co-occurrence matrix for the PCB2, the PCB4, the target PCB6 and the reference components, and carrying out matrix decomposition on the scoring co-occurrence matrix to obtain hidden feature vectors corresponding to the reference components. In some embodiments, the historical database includes an initial usage description, a corresponding PCB design, and components in the PCB design, and in other embodiments, the historical database includes only the initial usage description, and the corresponding PCB design, where components in the PCB design are obtained by image analysis.
In combination with the above embodiment, the scoring co-occurrence matrix of the reference object PCB design scheme and the reference component is obtained asA latent feature vector of the PCB design and components is learned by training a latent semantic model (Latent factor model, LFM) using an alternating least Squares (ALTERNATING LEAST s) algorithm on the scoring co-occurrence matrix.
After model training is completed, hidden feature vectors as shown in Table 6 are obtained (only two feature dimensions are shown in this example).
TABLE 6
In some embodiments, each component in the target PCB design is obtained according to the hidden feature vector, including performing matrix decomposition corresponding to the reference component according to the reference object PCB design, the reference component, and the scoring co-occurrence matrix of the target PCB design, to obtain a first dimension matrix and a second dimension matrix; solving a relation in the scoring co-occurrence matrix according to the first dimension matrix and the second dimension matrix to obtain scores corresponding to all reference elements in the target PCB design scheme, and further determining each component required in the target PCB design scheme according to the scores; and setting a scoring relation between the reference components and the PCB design scheme in the scoring co-occurrence matrix.
Specifically, a scoring co-occurrence matrix A of a reference object PCB design scheme, a reference component and a target PCB design scheme is obtained to perform matrix decomposition corresponding to the reference component, wherein the scoring co-occurrence matrix A is thatAnd performing matrix decomposition to obtain a first dimension matrix, such as a PCB design scheme matrix, and a second dimension matrix, such as a component matrix. PCB design matrix such asComponent matrix such as. And solving the relation according to the matrix of the PCB design scheme matrix and the component matrix in the scoring co-occurrence matrix A, namely obtaining the scoring co-occurrence matrix A by multiplying the PCB design scheme matrix by the component matrix, thus obtaining the scores corresponding to each reference element in the target PCB design scheme, and finally determining each component required in the target PCB design scheme according to the scores. And setting a scoring relation between the reference components and the PCB design scheme in the scoring co-occurrence matrix. If the final target PCB design scheme is that the score of each component is 0.10 for the power management IC, 0.82 for the communication module, 0.65 for the display screen, 0.30 for the resistor, 0.60 for the capacitor and 0.79 for the diode, respectively.
In some embodiments, the method for predicting the PCB design components further includes obtaining a corresponding prediction conclusion in the plurality of target PCB design prediction schemes according to the prediction score level of each component.
In connection with the above embodiment, the predicted hidden feature vector is used to predict other components required for the target PCB6 and to provide a prediction score and probability requirement indication for each component as shown in table 7.
TABLE 7
The scoring range indicates that a predictive scoring level corresponds, e.g., 0.7-1.0 (high) represents a high probability of a desired component and 0.4-0.69 (possible) represents a possible desired component; 0-0.39 (low) represents a low probability of required components.
Thus, the prediction conclusion is obtained according to the prediction score level as follows:
1. High probability required components
Communication module (0.82) and diode (0.79): the predictive scores of these two components are very high, indicating that they are critical to the design of the target PCB 6. This means that the integration and application of these two components should be prioritized when designing the PCB 6.
2. Components that may be needed
Display screen (0.65) and capacitor (0.60): the scoring of these components is in the mid-range, indicating that they may be useful in the design of the PCB 6. They may not be as urgent as communication modules and diodes, but their application should still be considered, especially in situations where display or steady current is required.
3. Low probability required components
Power management IC (0.10) and resistor (0.30): these components have a lower score, indicating that they may not be necessary in the design of the PCB 6. This may be due to the fact that the specific function or design parameters of the PCB6 are not dependent on these components. Other alternatives are contemplated or omitted when selecting components.
In some embodiments, components of the predetermined function are recommended to the target PCB design based on the hidden feature vector and components known in the target PCB design.
Specifically, the components with the preset functions refer to other types of components which realize specific functions except for active components and passive components.
Common other components include the following: (1) a power module: for providing supply voltage and current. (2) a sensor: for sensing environmental information such as temperature, humidity, illumination, etc. (3) an electric motor: for driving mechanical movements. (4) a display: for displaying images and text. (5) an acoustic module: for playing sound and music.
The active device refers to a device with active functions such as amplification and switching, and is mainly used for amplifying and switching a circuit. Common active devices include the following: (1) field effect transistor: for amplification, switching, etc. (2) a photocoupler: for isolating, transmitting signals, etc. (3) a transistor: for amplification, switching, etc. (4) an integrated circuit: multiple electronic components are integrated together to achieve more complex circuit functions.
The passive element is an element which does not have active functions such as amplification, switching and the like in a circuit, and is mainly used for filtering, distributing, protecting and the like of the circuit. Common passive components include the following: (1) resistance: for limiting current, dividing voltage, eliminating interference, etc. (2) capacitance: for storing charge, filtering, voltage stabilization, etc. (3) inductance: is used for storing magnetic field, dividing frequency, filtering, etc. (4) diode: for rectification, limiting, switching, etc. (5) triode: for amplification, switching, etc.
In connection with the above embodiment, components with specific functions are recommended to the target PCB6 based on the hidden feature vectors and components known in the design of the target PCB. Such as components for display functions such as a display screen are recommended to the target PCB6 based on hidden feature vectors and known microcontrollers, sensors, etc.
Fig. 4 an embodiment of the present disclosure provides an apparatus schematic diagram for predicting PCB design components, the apparatus comprising:
an obtaining module 21, configured to obtain at least one initial usage description similar to the target usage description, and take a PCB design scheme corresponding to the at least one initial usage description as a reference object;
The analysis module 22 is configured to obtain component information in the reference object PCB design, and obtain hidden feature vectors of each component in the reference object PCB design, the overall reference object PCB design, and the target PCB design;
And the output module 23 is used for obtaining each component in the target PCB design scheme and the target PCB design scheme formed by the components according to the hidden feature vector.
The apparatus of the embodiment shown in fig. 4 may be correspondingly used to perform the steps in the embodiment of the method shown in fig. 1, and the implementation principle and technical effects are similar, and are not repeated here.
In summary, the scheme for predicting the PCB design components in the embodiment of the specification has wider adaptability and universality, can synchronously realize various PCB design tasks, and increases the application range of the system; meanwhile, the design efficiency of the PCB is improved, the time for selecting components by a designer is greatly reduced, and the accuracy of component selection is improved by utilizing big data and machine learning; the provision of data driven decision support helps to avoid empirically and intuitively induced limitations, i.e., the inability of conventional methods to adequately consider all historical data, resulting in inaccurate predictions of component design.
Fig. 5 is a schematic diagram of a system structure for predicting PCB design components according to an embodiment of the present disclosure, as shown in fig. 5, the system 30 includes: a processor 31, a memory 32 and a computer program; wherein the method comprises the steps of
A memory 32 for storing said computer program, which memory may also be a flash memory (flash). Such as application programs, functional modules, etc. implementing the methods described above.
A processor 31 for executing the computer program stored in the memory to implement the steps executed by the apparatus in the above method. Reference may be made in particular to the description of the embodiments of the method described above.
Alternatively, the memory 32 may be separate or integrated with the processor 31.
When the memory 32 is a device separate from the processor 31, the apparatus may further include:
A bus 33 for connecting the memory 32 and the processor 31.
The present invention also provides a readable storage medium having stored therein a computer program for implementing the methods provided by the various embodiments described above when executed by a processor.
The readable storage medium may be a computer storage medium or a communication medium. Communication media includes any medium that facilitates transfer of a computer program from one place to another. Computer storage media can be any available media that can be accessed by a general purpose or special purpose computer. For example, a readable storage medium is coupled to the processor such that the processor can read information from, and write information to, the readable storage medium. In the alternative, the readable storage medium may be integral to the processor. The processor and the readable storage medium may reside in an Application SPECIFIC INTEGRATED Circuits (ASIC). In addition, the ASIC may reside in a user device. The processor and the readable storage medium may reside as discrete components in a communication device. The readable storage medium may be read-only memory (ROM), random-access memory (RAM), CD-ROMs, magnetic tape, floppy disk, optical data storage device, etc.
The same and similar parts of the embodiments in this specification are all mutually referred to, and each embodiment focuses on the differences from the other embodiments. In particular, for the product embodiments described later, since they correspond to the methods, the description is relatively simple, and reference is made to the description of parts of the system embodiments.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any changes or substitutions easily contemplated by those skilled in the art within the scope of the present application should be included in the present application. Therefore, the protection scope of the application is subject to the protection scope of the claims.
Claims (9)
1. The method for predicting the PCB design components is characterized by comprising the following steps of:
Acquiring at least one initial usage description similar to the target usage description, and taking a PCB design scheme corresponding to the at least one initial usage description as a reference object;
Acquiring component information in a reference object PCB design scheme, and acquiring hidden feature vectors of each component, the whole reference object PCB design scheme and a target PCB design scheme in the reference object PCB design scheme;
Obtaining each component in the target PCB design scheme and the target PCB design scheme formed by the components according to the hidden feature vector;
wherein, according to the hidden feature vector, obtain each components and parts in the target PCB design scheme, include:
performing matrix decomposition corresponding to the reference component according to the scoring co-occurrence matrix of the reference object PCB design scheme, the reference component and the target PCB design scheme to obtain a first dimension matrix and a second dimension matrix;
solving a relation in the scoring co-occurrence matrix according to the first dimension matrix and the second dimension matrix, obtaining scores corresponding to all reference elements in the target PCB design scheme, and further determining each component required in the target PCB design scheme according to the scores; and setting a scoring relation between the reference components and the PCB design scheme in the scoring co-occurrence matrix.
2. The method for predicting a PCB design component of claim 1, further comprising:
Acquiring PCB design schemes of historical data and initial application descriptions corresponding to each PCB design scheme;
Obtaining respective corresponding feature vectors from the initial usage description and the target usage description through text conversion;
The cosine similarity of the corresponding feature vectors between every two initial use descriptions is calculated, so that the similarity and the highest similarity of each initial use description and the target use description are obtained;
the PCB design scheme corresponding to the highest similarity initial use description is taken as a reference object.
3. The method for predicting a PCB design component of claim 1, further comprising:
Obtaining a first initial usage description containing the keyword features from the historical data through semantic analysis according to the keyword features in the target usage description;
and taking the PCB design scheme corresponding to the first initial use description as a reference object.
4. The method for predicting a PCB design component of claim 1, further comprising:
analyzing components in the PCB design scheme as a reference object to obtain reference components;
And obtaining scoring co-occurrence matrixes of all the reference object PCB design schemes, the reference components and the target PCB design schemes, and carrying out matrix decomposition on the scoring co-occurrence matrixes to obtain hidden feature vectors corresponding to the reference components.
5. The method for predicting a PCB design component of claim 1, further comprising:
And obtaining corresponding prediction conclusion in the multiple target PCB design prediction schemes according to the prediction grading grade of each component.
6. The method of claim 4, wherein the components with the predetermined functions are recommended to the target PCB design according to the hidden feature vector and the known components in the target PCB design.
7. The device for predicting the PCB design components is characterized by comprising:
an acquisition module, configured to acquire at least one initial usage description similar to a target usage description, and take a PCB design scheme corresponding to the at least one initial usage description as a reference object;
The analysis module is used for acquiring the component information in the PCB design scheme as the reference object and acquiring hidden feature vectors of each component, the whole reference object PCB design scheme and the target PCB design scheme in the reference object PCB design scheme;
The output module is used for obtaining each component in the target PCB design scheme and the target PCB design scheme formed by the components according to the hidden feature vector;
wherein, according to the hidden feature vector, obtain each components and parts in the target PCB design scheme, include:
performing matrix decomposition corresponding to the reference component according to the scoring co-occurrence matrix of the reference object PCB design scheme, the reference component and the target PCB design scheme to obtain a first dimension matrix and a second dimension matrix;
solving a relation in the scoring co-occurrence matrix according to the first dimension matrix and the second dimension matrix, obtaining scores corresponding to all reference elements in the target PCB design scheme, and further determining each component required in the target PCB design scheme according to the scores; and setting a scoring relation between the reference components and the PCB design scheme in the scoring co-occurrence matrix.
8. A system for predicting a PCB design component, comprising a memory, a processor and a computer program, the computer program stored in the memory, the processor running the computer program to perform the method for predicting a PCB design component according to any one of claims 1-6.
9. A readable storage medium, wherein a computer program is stored in the readable storage medium, which computer program, when being executed by a processor, is adapted to implement the method of predicting a PCB design component according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410559713.5A CN118133763B (en) | 2024-05-08 | 2024-05-08 | Method, device and system for predicting PCB design components and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410559713.5A CN118133763B (en) | 2024-05-08 | 2024-05-08 | Method, device and system for predicting PCB design components and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118133763A CN118133763A (en) | 2024-06-04 |
| CN118133763B true CN118133763B (en) | 2024-07-12 |
Family
ID=91236146
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410559713.5A Active CN118133763B (en) | 2024-05-08 | 2024-05-08 | Method, device and system for predicting PCB design components and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118133763B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107038443A (en) * | 2017-04-28 | 2017-08-11 | 东莞市盟拓光电科技有限公司 | A kind of method and apparatus for positioning area-of-interest on circuit boards |
| CN112347084A (en) * | 2020-12-01 | 2021-02-09 | 广州辰创科技发展有限公司 | Intelligent PCB BOM generation method and system |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8839174B2 (en) * | 2012-01-31 | 2014-09-16 | Mentor Graphics Corporation | Placement and area adjustment for hierarchical groups in printed circuit board design |
| CN111626177B (en) * | 2020-05-22 | 2023-11-21 | 深圳技术大学 | PCB element identification method and device |
| CN113076450B (en) * | 2021-03-15 | 2024-03-22 | 北京明略软件系统有限公司 | Determination method and device for target recommendation list |
| CN114282485A (en) * | 2021-12-30 | 2022-04-05 | 湖南人文科技学院 | PCB design method for electronic circuit |
| CN115080587B (en) * | 2022-05-19 | 2024-04-16 | 华南理工大学 | Electronic component replacement method, device and medium based on knowledge graph |
| CN116992818B (en) * | 2023-09-20 | 2024-01-05 | 深圳市小铭工业互联网有限公司 | Circuit board layout design method and system |
-
2024
- 2024-05-08 CN CN202410559713.5A patent/CN118133763B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107038443A (en) * | 2017-04-28 | 2017-08-11 | 东莞市盟拓光电科技有限公司 | A kind of method and apparatus for positioning area-of-interest on circuit boards |
| CN112347084A (en) * | 2020-12-01 | 2021-02-09 | 广州辰创科技发展有限公司 | Intelligent PCB BOM generation method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118133763A (en) | 2024-06-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9582547B2 (en) | Generalized graph, rule, and spatial structure based recommendation engine | |
| CN110390052B (en) | Search recommendation method, training method, device and equipment of CTR (China train redundancy report) estimation model | |
| JP2017138985A (en) | Method and device for artificial intelligence-based mobile search | |
| WO2011126458A1 (en) | Automatic frequently asked question compilation from community-based question answering archive | |
| WO2009155375A2 (en) | System and method for aggregating and summarizing product/topic sentiment | |
| CN111291210A (en) | Image material library generation method, image material recommendation method and related device | |
| JP2019149140A (en) | Information search device and information search system | |
| CN105069103A (en) | Method and system for APP search engine to utilize client comment | |
| JP2015135668A (en) | Computing devices and methods of connecting people based on content and relational distance | |
| CN111651570A (en) | Text sentence processing method and device, electronic equipment and storage medium | |
| Cornelissen et al. | A structured approach to the strategies analysis phase of cognitive work analysis | |
| KR20120092756A (en) | Method and system for searching mobile application using human activity knowledge database | |
| US10740401B2 (en) | System for the automated semantic analysis processing of query strings | |
| CN106611058A (en) | Test question searching method and device | |
| CN111475645B (en) | Knowledge point labeling method, knowledge point labeling device and computer readable storage medium | |
| CN115080587B (en) | Electronic component replacement method, device and medium based on knowledge graph | |
| CN112330510A (en) | Volunteer recommendation method and device, server and computer-readable storage medium | |
| Hersh | Search still matters: information retrieval in the era of generative AI | |
| CN118133763B (en) | Method, device and system for predicting PCB design components and storage medium | |
| Li et al. | Infographics retrieval: A new methodology | |
| CN113780365A (en) | Sample generation method and device | |
| CN112417174A (en) | Data processing method and device | |
| CN110929526B (en) | Sample generation method and device and electronic equipment | |
| CN103038766B (en) | Logical operation system | |
| CN109213830B (en) | Document retrieval system for professional technical documents |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |