CN114210597A - Conductive adhesive recommendation method and system for semiconductor device and readable storage medium - Google Patents
Conductive adhesive recommendation method and system for semiconductor device and readable storage medium Download PDFInfo
- Publication number
- CN114210597A CN114210597A CN202210159813.XA CN202210159813A CN114210597A CN 114210597 A CN114210597 A CN 114210597A CN 202210159813 A CN202210159813 A CN 202210159813A CN 114210597 A CN114210597 A CN 114210597A
- Authority
- CN
- China
- Prior art keywords
- conductive adhesive
- semiconductor device
- information
- matching degree
- conductive
- 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.)
- Granted
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
Landscapes
- Adhesives Or Adhesive Processes (AREA)
Abstract
According to the conductive adhesive recommending method and system for the semiconductor device and the readable storage medium, the information of the semiconductor device is obtained, the conductive adhesive suitable for the semiconductor device is obtained through the online adapter, the conductive adhesive and the information of the semiconductor device are compared and analyzed, the matching degree of the conductive adhesive and the semiconductor device is obtained, and the conductive adhesive with the highest matching degree is selected. The conductive adhesive which does not reach the carbon emission standard in the production process is screened out by analyzing the production information of the conductive adhesive suitable for the semiconductor device, so that the carbon emission requirement of a semiconductor product is ensured.
Description
Technical Field
The invention relates to the technical field of semiconductors and data mining, in particular to a conductive adhesive recommending method and system for a semiconductor device and a readable storage medium.
Background
The conductive adhesive is an adhesive with certain conductivity after being cured or dried, and can connect a plurality of conductive materials together to form an electric path between the connected materials. The variety of the conductive adhesive is various, and under the condition of no screening, the optimal conductive adhesive can not be selected easily due to insufficient information, and at the present stage, the selection of the conductive adhesive of the semiconductor device mainly depends on the personal experience and the personal technology of technicians, and the range of the selected conductive adhesive has limitation.
There are thus deficiencies in the art and improvements are needed.
Disclosure of Invention
In view of the above problems, it is an object of the present invention to provide a conductive paste recommendation method, system and readable storage medium for a semiconductor device, which can select the optimum conductive paste for the semiconductor device more efficiently.
The invention provides a conductive adhesive recommendation method of a semiconductor device, which comprises the following steps:
acquiring information of a semiconductor device;
obtaining conductive adhesive information suitable for the semiconductor device according to the information of the semiconductor device;
comparing and analyzing the information of the conductive adhesive and the semiconductor device to obtain the matching degree information of the conductive adhesive and the semiconductor device;
and sending the conductive adhesive with the highest matching degree to the terminal for displaying.
In this scheme, still include:
acquiring working environment information of a semiconductor device;
and judging whether the conductive adhesive can normally operate in the working environment of the semiconductor device, and if not, setting the matching degree of the conductive adhesive to be zero.
In this scheme, still include:
acquiring price information of the conductive adhesive;
and judging whether the price of the conductive adhesive exceeds a preset threshold value, if so, decreasing the matching degree of the conductive adhesive according to the fact that the price exceeds the preset threshold value, and sending the obtained matching degree to a server for storage.
In this scheme, still include:
acquiring the use method information of the conductive adhesive;
forming a difficulty degree value according to the using method of the conductive adhesive;
and judging whether the difficulty degree value exceeds a preset threshold value, and if so, setting the matching degree of the conductive adhesive to be zero.
In this scheme, still include:
acquiring production information of the conductive adhesive;
according to the production information of the conductive adhesive, obtaining carbon emission information of the conductive adhesive in the production process;
and judging whether the carbon emission of the conductive adhesive in production exceeds a preset threshold value, and if so, setting the matching degree of the conductive adhesive to be zero.
In this scheme, still include:
acquiring historical conductive adhesive of a semiconductor device and product yield information of the semiconductor device and the historical conductive adhesive;
obtaining a neural network model of the semiconductor device according to the historical conductive adhesive of the semiconductor device and the product yield information of the semiconductor device and the historical conductive adhesive;
and judging whether the yield of the conductive adhesive in the neural network model is lower than a preset threshold value or not, and if so, setting the matching degree of the conductive adhesive to be zero.
The second aspect of the present invention provides a conductive paste recommendation system for a semiconductor device, including a memory and a processor, where the memory includes a conductive paste recommendation method program for the semiconductor device, and when executed by the processor, the conductive paste recommendation method program for the semiconductor device implements the following steps:
acquiring information of a semiconductor device;
obtaining conductive adhesive information suitable for the semiconductor device according to the information of the semiconductor device;
comparing and analyzing the information of the conductive adhesive and the semiconductor device to obtain the matching degree information of the conductive adhesive and the semiconductor device;
and sending the conductive adhesive with the highest matching degree to the terminal for displaying.
In this scheme, still include:
acquiring working environment information of a semiconductor device;
and judging whether the conductive adhesive can normally operate in the working environment of the semiconductor device, and if not, setting the matching degree of the conductive adhesive to be zero.
In this scheme, still include:
acquiring price information of the conductive adhesive;
and judging whether the price of the conductive adhesive exceeds a preset threshold value, if so, decreasing the matching degree of the conductive adhesive according to the fact that the price exceeds the preset threshold value, and sending the obtained matching degree to a server for storage.
In this scheme, still include:
acquiring the use method information of the conductive adhesive;
forming a difficulty degree value according to the using method of the conductive adhesive;
and judging whether the difficulty degree value exceeds a preset threshold value, and if so, setting the matching degree of the conductive adhesive to be zero.
In this scheme, still include:
acquiring production information of the conductive adhesive;
according to the production information of the conductive adhesive, obtaining carbon emission information of the conductive adhesive in the production process;
and judging whether the carbon emission of the conductive adhesive in production exceeds a preset threshold value, and if so, setting the matching degree of the conductive adhesive to be zero.
In this scheme, still include:
acquiring historical conductive adhesive of a semiconductor device and product yield information of the semiconductor device and the historical conductive adhesive;
obtaining a neural network model of the semiconductor device according to the historical conductive adhesive of the semiconductor device and the product yield information of the semiconductor device and the historical conductive adhesive;
and judging whether the yield of the conductive adhesive in the neural network model is lower than a preset threshold value or not, and if so, setting the matching degree of the conductive adhesive to be zero.
A third aspect of the present invention provides a computer-readable storage medium, which includes a program of a conductive paste recommendation method for a semiconductor device, and when the program of the conductive paste recommendation method for a semiconductor device is executed by a processor, the steps of the conductive paste recommendation method for a semiconductor device according to any one of the above are implemented.
According to the conductive adhesive recommending method and system for the semiconductor device and the readable storage medium, the information of the semiconductor device is obtained, the conductive adhesive suitable for the semiconductor device is obtained through the online adapter, the conductive adhesive and the information of the semiconductor device are compared and analyzed, the matching degree of the conductive adhesive and the semiconductor device is obtained, and the conductive adhesive with the highest matching degree is selected. The conductive adhesive which does not reach the carbon emission standard in the production process is screened out by analyzing the production information of the conductive adhesive suitable for the semiconductor device, so that the carbon emission requirement of a semiconductor product is ensured.
Drawings
Fig. 1 shows a flow chart of a conductive paste recommendation method of a semiconductor device of the present invention;
fig. 2 is a block diagram of a conductive paste recommendation system for a semiconductor device according to the present invention.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.
Fig. 1 shows a flow chart of a conductive paste recommendation method of a semiconductor device according to the present invention.
As shown in fig. 1, the present invention discloses a conductive adhesive recommendation method for a semiconductor device, comprising:
s102, acquiring information of the semiconductor device;
s104, obtaining conductive adhesive information suitable for the semiconductor device according to the information of the semiconductor device;
s106, comparing and analyzing the information of the conductive adhesive and the information of the semiconductor device to obtain matching degree information of the conductive adhesive and the semiconductor device;
and S108, transmitting the conductive adhesive with the highest matching degree to a terminal for displaying.
According to the embodiment of the invention, the information of the semiconductor device comprises basic information such as material composition, functional application and the like of the semiconductor device, the main keyword information in the information of the semiconductor device is extracted, then the keyword information is automatically matched with the conductive adhesive suitable for the semiconductor device through an online adapter, when only one conductive adhesive suitable for the semiconductor device is available, the server directly sends the conductive adhesive to a terminal for display, when the types of the conductive adhesives suitable for the semiconductor device are more than or equal to two, the conductive adhesive and the main keyword information in the information of the semiconductor device are compared and analyzed to obtain the matching degree information of the conductive adhesive and the semiconductor device, the conductive adhesive with the highest matching degree is selected and sent to the terminal for display, and if the matching degrees of various conductive adhesives are the same and are the highest, the secondary keyword information in the information of the semiconductor device is extracted, and carrying out second comparison analysis on the conductive adhesive with the same and highest matching degree and the secondary keyword information in the semiconductor device information to obtain second matching degree information, judging the second matching degree, if the matching degrees of the multiple conductive adhesives are the same and the highest, continuously extracting the secondary keyword information in the semiconductor device information until one conductive adhesive is screened out, and sending the conductive adhesive to a terminal for display.
According to the embodiment of the invention, the method further comprises the following steps:
acquiring working environment information of a semiconductor device;
and judging whether the conductive adhesive can normally operate in the working environment of the semiconductor device, and if not, setting the matching degree of the conductive adhesive to be zero.
It should be noted that, the working environment of the semiconductor device is obtained, the temperature, the humidity and the vibration are extracted, and whether the conductive adhesive of the semiconductor device can continuously and normally operate in the working environment is judged according to the temperature, the humidity and the vibration. For example, the conductive adhesive a can only normally operate at a temperature below 60 degrees celsius, the semiconductor device may reach 70 degrees celsius after operation, and the conductive adhesive a directly deforms or cannot normally operate at a temperature of 70 degrees celsius, so that the matching degree between the conductive adhesive a and the semiconductor device is set to zero.
According to the embodiment of the invention, the method further comprises the following steps:
acquiring price information of the conductive adhesive;
and judging whether the price of the conductive adhesive exceeds a preset threshold value, if so, decreasing the matching degree of the conductive adhesive according to the fact that the price exceeds the preset threshold value, and sending the obtained matching degree to a server for storage.
It should be noted that the price of the conductive adhesive directly affects the cost of the semiconductor device, but when the matching degree of the performance of the conductive adhesive and the semiconductor device is high, the influence of partial price can be eliminated. Therefore, when the price of the conductive adhesive exceeds a preset threshold value, the matching degree of the conductive adhesive is decreased progressively according to the condition that the price exceeds the preset threshold value. For example, the price of the conductive adhesive a is 1000 yuan/kg, the preset threshold value of the price of the conductive adhesive is 800 yuan/kg, when the price of the conductive adhesive exceeds the preset threshold value, the matching value of 1 point is correspondingly reduced every time the price exceeds 100 yuan/kg, the initial matching value of the conductive adhesive a is 90, the initial matching value of the conductive adhesive B is 85, the price is 780 yuan/kg, and the final matching value of the conductive adhesive a is 90- (1000-.
According to the embodiment of the invention, the method further comprises the following steps:
acquiring the use method information of the conductive adhesive;
forming a difficulty degree value according to the using method of the conductive adhesive;
and judging whether the difficulty degree value exceeds a preset threshold value, and if so, setting the matching degree of the conductive adhesive to be zero.
The difficulty level of the method of using the conductive paste is determined by extracting keyword information from the information on the method of using the conductive paste, and the less the number of keywords, the simpler the method of using the conductive paste, and the smaller the difficulty level value obtained. When the difficulty degree exceeds a preset threshold value, the method for using the conductive adhesive cannot realize the mass production of the semiconductor device under the existing condition, or the method for using the conductive adhesive can realize the mass production of the semiconductor device under the existing condition but the cost is too high.
According to the embodiment of the invention, the method further comprises the following steps:
acquiring production information of the conductive adhesive;
according to the production information of the conductive adhesive, obtaining carbon emission information of the conductive adhesive in the production process;
and judging whether the carbon emission of the conductive adhesive in production exceeds a preset threshold value, and if so, setting the matching degree of the conductive adhesive to be zero.
The carbon emission information of the conductive adhesive in the production process is obtained by obtaining the production information of the conductive adhesive, and the carbon emission information includes direct carbon emission information and indirect carbon emission information. The direct carbon emission of the conductive adhesive in the production process is the carbon dioxide value generated by a factory when the conductive adhesive is produced, and the indirect carbon emission is the consumption of energy, raw materials, water and the like when the conductive adhesive is produced. By combining the direct carbon emission and the indirect carbon emission of the conductive adhesive with a preset carbon emission threshold (carbon emission standard specified by the state), whether the carbon emission of the conductive adhesive exceeds the standard or not is judged, and if yes, the matching degree of the semiconductor is set to be zero.
According to the embodiment of the invention, the method further comprises the following steps:
acquiring historical conductive adhesive of a semiconductor device and product yield information of the semiconductor device and the historical conductive adhesive;
obtaining a neural network model of the semiconductor device according to the historical conductive adhesive of the semiconductor device and the product yield information of the semiconductor device and the historical conductive adhesive;
and judging whether the yield of the conductive adhesive in the neural network model is lower than a preset threshold value or not, and if so, setting the matching degree of the conductive adhesive to be zero.
It should be noted that, starting from the research and development of the conductive adhesive, the development process of the conductive adhesive, the bonding process of the conductive adhesive and the semiconductor device, and the yield information of the conductive adhesive and the semiconductor device are recorded, through learning and analysis of data, the system automatically optimizes the yield value of the conductive adhesive in the neural network model, and when the yield value of the conductive adhesive in the simulation is lower than the preset yield threshold value, the matching degree of the conductive adhesive is set to zero. The step of judging whether the yield of the conductive adhesive in the neural network model is lower than the preset threshold value may be that conductive adhesive information and semiconductor information are input into the neural network model to obtain a yield value, and then judging whether the yield value is lower than the preset threshold value. For example, the yield of the conductive adhesive C in the neural network model is 90%, and the preset yield threshold of the conductive adhesive and the semiconductor device is 98%, then the yield of the conductive adhesive C and the semiconductor device does not reach the standard, and the matching degree of the conductive adhesive C is set to zero.
According to the embodiment of the invention, the method further comprises the following steps:
obtaining the composition information of the conductive adhesive material suitable for the semiconductor device according to the neural network model information of the conductive adhesive and the basic information of the semiconductor device;
and judging whether the conductive adhesive material of the semiconductor device is a ready-made product or not, and if so, sending product information consisting of the conductive adhesive material to a terminal for display.
It should be noted that, by analyzing the basic information of the semiconductor device, the neural network model of the conductive adhesive automatically optimizes the composition information of the conductive adhesive material suitable for the semiconductor device, and determines whether the composition of the conductive adhesive material of the semiconductor device is a ready-made product, if so, the product information composed of the conductive adhesive material is recommended to a terminal for display, and if not, the cost required by the conductive adhesive material for manufacturing the product is calculated, and the composition of the conductive adhesive material and the cost information of the manufactured product are sent to the terminal for display.
According to the embodiment of the invention, the method further comprises the following steps:
analyzing historical conductive adhesive of the semiconductor device and product yield information of the semiconductor device and the historical conductive adhesive to obtain optimal component proportion information and production process information of the conductive adhesive;
and sending the optimal component proportion information and the production process information of the conductive adhesive to a preset terminal for generating guidance.
When the conductive adhesive recommendation process is performed, the method can analyze the data information of the conductive adhesive and the semiconductor according to the historical data information of the conductive adhesive and the semiconductor, and analyze the optimal component proportion information and the generation process information of the conductive adhesive. Specifically, historical conductive adhesive of the semiconductor device and product yield information of the semiconductor device and the historical conductive adhesive can be input into a preset neural network model for training to obtain a conductive adhesive production neural network model, and then current semiconductor information is input into the trained production neural network model to obtain optimal component proportion information and production process information of the conductive adhesive. And sending the optimal component proportion information and the production process information of the conductive adhesive to a preset terminal to help the preset terminal to guide the production of the conductive adhesive. The matching and the guidance of the conductive adhesive are carried out in an artificial intelligent mode, so that the production efficiency of semiconductors and the conductive adhesive can be improved, and the using effect of products is improved.
According to the embodiment of the invention, the step of generating the neural network model specifically comprises the following steps:
acquiring historical state data; preprocessing the historical state data to obtain a training array; sending the training array to an initialized neural network model for training; acquiring the error rate of the trained neural network model; and if the error rate is less than a preset error rate threshold value, stopping training to obtain a preset neural network model. The production neural network model can be obtained by training through the method.
It should be noted that the historical state data is historical conductive adhesive of the semiconductor device and product yield information data of the semiconductor device and the historical conductive adhesive, and the more the obtained historical data, the more accurate the trained neural network model is. First, after obtaining the historical data, preprocessing is required, for example, normalization processing or format conversion processing is performed on the data to facilitate training of the neural network, and after preprocessing, a training data set is obtained. And then inputting the training data set into the initialized neural network model for training, wherein the training is machine automatic training, and the neural network model is finally obtained. And then inputting test data and judging the accuracy of the prediction result output by the neural network model. And comparing the prediction accuracy with a preset accuracy threshold, if the prediction accuracy exceeds the accuracy threshold, indicating that the neural network model can achieve a better prediction effect, and stopping training. Wherein the accuracy threshold may be 80-95%.
Fig. 2 is a block diagram of a conductive paste recommendation system for a semiconductor device according to the present invention.
As shown in fig. 2, a second aspect of the present invention provides a conductive paste recommendation system 2 for a semiconductor device, including a memory 21 and a processor 22, where the memory includes a conductive paste recommendation method program for the semiconductor device, and the conductive paste recommendation method program for the semiconductor device, when executed by the processor, implements the following steps:
acquiring information of a semiconductor device;
obtaining conductive adhesive information suitable for the semiconductor device according to the information of the semiconductor device;
comparing and analyzing the information of the conductive adhesive and the semiconductor device to obtain the matching degree information of the conductive adhesive and the semiconductor device;
and sending the conductive adhesive with the highest matching degree to the terminal for displaying.
According to the embodiment of the invention, the information of the semiconductor device comprises basic information such as material composition, functional application and the like of the semiconductor device, the main keyword information in the information of the semiconductor device is extracted, then the keyword information is automatically matched with the conductive adhesive suitable for the semiconductor device through an online adapter, when only one conductive adhesive suitable for the semiconductor device is available, the server directly sends the conductive adhesive to a terminal for display, when the types of the conductive adhesives suitable for the semiconductor device are more than or equal to two, the conductive adhesive and the main keyword information in the information of the semiconductor device are compared and analyzed to obtain the matching degree information of the conductive adhesive and the semiconductor device, the conductive adhesive with the highest matching degree is selected and sent to the terminal for display, and if the matching degrees of various conductive adhesives are the same and are the highest, the secondary keyword information in the information of the semiconductor device is extracted, and carrying out second comparison analysis on the conductive adhesive with the same and highest matching degree and the secondary keyword information in the semiconductor device information to obtain second matching degree information, judging the second matching degree, if the matching degrees of the multiple conductive adhesives are the same and the highest, continuously extracting the secondary keyword information in the semiconductor device information until one conductive adhesive is screened out, and sending the conductive adhesive to a terminal for display.
According to the embodiment of the invention, the method further comprises the following steps:
acquiring working environment information of a semiconductor device;
and judging whether the conductive adhesive can normally operate in the working environment of the semiconductor device, and if not, setting the matching degree of the conductive adhesive to be zero.
It should be noted that, the working environment of the semiconductor device is obtained, the temperature, the humidity and the vibration are extracted, and whether the conductive adhesive of the semiconductor device can continuously and normally operate in the working environment is judged according to the temperature, the humidity and the vibration. For example, the conductive adhesive a can only normally operate at a temperature below 60 degrees celsius, the semiconductor device may reach 70 degrees celsius after operation, and the conductive adhesive a directly deforms or cannot normally operate at a temperature of 70 degrees celsius, so that the matching degree between the conductive adhesive a and the semiconductor device is set to zero.
According to the embodiment of the invention, the method further comprises the following steps:
acquiring price information of the conductive adhesive;
and judging whether the price of the conductive adhesive exceeds a preset threshold value, if so, decreasing the matching degree of the conductive adhesive according to the fact that the price exceeds the preset threshold value, and sending the obtained matching degree to a server for storage.
It should be noted that the price of the conductive adhesive directly affects the cost of the semiconductor device, but when the matching degree of the performance of the conductive adhesive and the semiconductor device is high, the influence of partial price can be eliminated. Therefore, when the price of the conductive adhesive exceeds a preset threshold value, the matching degree of the conductive adhesive is decreased progressively according to the condition that the price exceeds the preset threshold value. For example, the price of the conductive adhesive a is 1000 yuan/kg, the preset threshold value of the price of the conductive adhesive is 800 yuan/kg, when the price of the conductive adhesive exceeds the preset threshold value, the matching value of 1 point is correspondingly reduced every time the price exceeds 100 yuan/kg, the initial matching value of the conductive adhesive a is 90, the initial matching value of the conductive adhesive B is 85, the price is 780 yuan/kg, and the final matching value of the conductive adhesive a is 90- (1000-.
According to the embodiment of the invention, the method further comprises the following steps:
acquiring the use method information of the conductive adhesive;
forming a difficulty degree value according to the using method of the conductive adhesive;
and judging whether the difficulty degree value exceeds a preset threshold value, and if so, setting the matching degree of the conductive adhesive to be zero.
The difficulty level of the method of using the conductive paste is determined by extracting keyword information from the information on the method of using the conductive paste, and the less the number of keywords, the simpler the method of using the conductive paste, and the smaller the difficulty level value obtained. When the difficulty degree exceeds a preset threshold value, the method for using the conductive adhesive cannot realize the mass production of the semiconductor device under the existing condition, or the method for using the conductive adhesive can realize the mass production of the semiconductor device under the existing condition but the cost is too high.
According to the embodiment of the invention, the method further comprises the following steps:
acquiring production information of the conductive adhesive;
according to the production information of the conductive adhesive, obtaining carbon emission information of the conductive adhesive in the production process;
and judging whether the carbon emission of the conductive adhesive in production exceeds a preset threshold value, and if so, setting the matching degree of the conductive adhesive to be zero.
The carbon emission information of the conductive adhesive in the production process is obtained by obtaining the production information of the conductive adhesive, and the carbon emission information includes direct carbon emission information and indirect carbon emission information. The direct carbon emission of the conductive adhesive in the production process is the carbon dioxide value generated by a factory when the conductive adhesive is produced, and the indirect carbon emission is the consumption of energy, raw materials, water and the like when the conductive adhesive is produced. By combining the direct carbon emission and the indirect carbon emission of the conductive adhesive with a preset carbon emission threshold (carbon emission standard specified by the state), whether the carbon emission of the conductive adhesive exceeds the standard or not is judged, and if yes, the matching degree of the semiconductor is set to be zero.
According to the embodiment of the invention, the method further comprises the following steps:
acquiring historical conductive adhesive of a semiconductor device and product yield information of the semiconductor device and the historical conductive adhesive;
obtaining a neural network model of the semiconductor device according to the historical conductive adhesive of the semiconductor device and the product yield information of the semiconductor device and the historical conductive adhesive;
and judging whether the yield of the conductive adhesive in the neural network model is lower than a preset threshold value or not, and if so, setting the matching degree of the conductive adhesive to be zero.
It should be noted that, starting from the research and development of the conductive adhesive, the development process of the conductive adhesive, the bonding process of the conductive adhesive and the semiconductor device, and the yield information of the conductive adhesive and the semiconductor device are recorded, through learning and analysis of data, the system automatically optimizes the yield value of the conductive adhesive in the neural network model, and when the yield value of the conductive adhesive in the simulation is lower than the preset yield threshold value, the matching degree of the conductive adhesive is set to zero. For example, the yield of the conductive adhesive C in the neural network model is 90%, and the preset yield threshold of the conductive adhesive and the semiconductor device is 98%, then the yield of the conductive adhesive C and the semiconductor device does not reach the standard, and the matching degree of the conductive adhesive C is set to zero.
According to the embodiment of the invention, the method further comprises the following steps:
obtaining the composition information of the conductive adhesive material suitable for the semiconductor device according to the neural network model information of the conductive adhesive and the basic information of the semiconductor device;
and judging whether the conductive adhesive material of the semiconductor device is a ready-made product or not, and if so, sending product information consisting of the conductive adhesive material to a terminal for display.
It should be noted that, by analyzing the basic information of the semiconductor device, the neural network model of the conductive adhesive automatically optimizes the composition information of the conductive adhesive material suitable for the semiconductor device, and determines whether the composition of the conductive adhesive material of the semiconductor device is a ready-made product, if so, the product information composed of the conductive adhesive material is recommended to a terminal for display, and if not, the cost required by the conductive adhesive material for manufacturing the product is calculated, and the composition of the conductive adhesive material and the cost information of the manufactured product are sent to the terminal for display.
According to the embodiment of the invention, the method further comprises the following steps:
analyzing historical conductive adhesive of the semiconductor device and product yield information of the semiconductor device and the historical conductive adhesive to obtain optimal component proportion information and production process information of the conductive adhesive;
and sending the optimal component proportion information and the production process information of the conductive adhesive to a preset terminal for generating guidance.
When the conductive adhesive recommendation process is performed, the method can analyze the data information of the conductive adhesive and the semiconductor according to the historical data information of the conductive adhesive and the semiconductor, and analyze the optimal component proportion information and the generation process information of the conductive adhesive. Specifically, historical conductive adhesive of the semiconductor device and product yield information of the semiconductor device and the historical conductive adhesive can be input into a preset neural network model for training to obtain a conductive adhesive production neural network model, and then current semiconductor information is input into the trained production neural network model to obtain optimal component proportion information and production process information of the conductive adhesive. And sending the optimal component proportion information and the production process information of the conductive adhesive to a preset terminal to help the preset terminal to guide the production of the conductive adhesive. The matching and the guidance of the conductive adhesive are carried out in an artificial intelligent mode, so that the production efficiency of semiconductors and the conductive adhesive can be improved, and the using effect of products is improved.
According to the embodiment of the invention, the step of generating the neural network model specifically comprises the following steps:
acquiring historical state data; preprocessing the historical state data to obtain a training array; sending the training array to an initialized neural network model for training; acquiring the error rate of the trained neural network model; and if the error rate is less than a preset error rate threshold value, stopping training to obtain a preset neural network model. The production neural network model can be obtained by training through the method.
It should be noted that the historical state data is historical conductive adhesive of the semiconductor device and product yield information data of the semiconductor device and the historical conductive adhesive, and the more the obtained historical data, the more accurate the trained neural network model is. First, after obtaining the historical data, preprocessing is required, for example, normalization processing or format conversion processing is performed on the data to facilitate training of the neural network, and after preprocessing, a training data set is obtained. And then inputting the training data set into the initialized neural network model for training, wherein the training is machine automatic training, and the neural network model is finally obtained. And then inputting test data and judging the accuracy of the prediction result output by the neural network model. And comparing the prediction accuracy with a preset accuracy threshold, if the prediction accuracy exceeds the accuracy threshold, indicating that the neural network model can achieve a better prediction effect, and stopping training. Wherein the accuracy threshold may be 80-95%.
A third aspect of the present invention provides a computer-readable storage medium, which includes a program of a conductive paste recommendation method for a semiconductor device, and when the program of the conductive paste recommendation method for a semiconductor device is executed by a processor, the steps of the conductive paste recommendation method for a semiconductor device according to any one of the above are implemented.
According to the conductive adhesive recommending method and system for the semiconductor device and the readable storage medium, the information of the semiconductor device is obtained, the conductive adhesive suitable for the semiconductor device is obtained through the online adapter, the conductive adhesive and the information of the semiconductor device are compared and analyzed, the matching degree of the conductive adhesive and the semiconductor device is obtained, and the conductive adhesive with the highest matching degree is selected. The conductive adhesive which does not reach the carbon emission standard in the production process is screened out by analyzing the production information of the conductive adhesive suitable for the semiconductor device, so that the carbon emission requirement of a semiconductor product is ensured.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of the unit is only a logical functional division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units; can be located in one place or distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, all the functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Alternatively, the integrated unit of the present invention may be stored in a computer-readable storage medium if it is implemented in the form of a software functional module and sold or used as a separate product. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially implemented or a part contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, a ROM, a RAM, a magnetic or optical disk, or various other media that can store program code.
Claims (10)
1. A conductive adhesive recommendation method of a semiconductor device is characterized by comprising the following steps:
acquiring information of a semiconductor device;
obtaining conductive adhesive information suitable for the semiconductor device according to the information of the semiconductor device;
comparing and analyzing the information of the conductive adhesive and the semiconductor device to obtain the matching degree information of the conductive adhesive and the semiconductor device;
and sending the conductive adhesive with the highest matching degree to the terminal for displaying.
2. The method of claim 1, further comprising:
acquiring working environment information of a semiconductor device;
and judging whether the conductive adhesive can normally operate in the working environment of the semiconductor device, and if not, setting the matching degree of the conductive adhesive to be zero.
3. The method of claim 1, further comprising:
acquiring price information of the conductive adhesive;
and judging whether the price information of the conductive adhesive exceeds a preset threshold value, if so, decreasing the matching degree of the conductive adhesive according to the fact that the price information of the conductive adhesive exceeds the preset threshold value, and sending the obtained matching degree to a server for storage.
4. The method of claim 1, further comprising:
acquiring the use method information of the conductive adhesive;
forming a difficulty degree value according to the using method of the conductive adhesive;
and judging whether the difficulty degree value exceeds a preset threshold value, and if so, setting the matching degree of the conductive adhesive to be zero.
5. The method of claim 1, further comprising:
acquiring production information of the conductive adhesive;
according to the production information of the conductive adhesive, obtaining carbon emission information of the conductive adhesive in the production process;
and judging whether the carbon emission of the conductive adhesive in production exceeds a preset threshold value, and if so, setting the matching degree of the conductive adhesive to be zero.
6. The method of claim 1, further comprising:
acquiring historical conductive adhesive of a semiconductor device and product yield information of the semiconductor device and the historical conductive adhesive;
obtaining a neural network model of the semiconductor device according to the historical conductive adhesive of the semiconductor device and the product yield information of the semiconductor device and the historical conductive adhesive;
and judging whether the yield of the conductive adhesive in the neural network model is lower than a preset threshold value or not, and if so, setting the matching degree of the conductive adhesive to be zero.
7. A conductive paste recommendation system of a semiconductor device is characterized by comprising a memory and a processor, wherein the memory comprises a conductive paste recommendation method program of the semiconductor device, and the conductive paste recommendation method program of the semiconductor device realizes the following steps when being executed by the processor:
acquiring information of a semiconductor device;
obtaining conductive adhesive information suitable for the semiconductor device according to the information of the semiconductor device;
comparing and analyzing the information of the conductive adhesive and the semiconductor device to obtain the matching degree information of the conductive adhesive and the semiconductor device;
and sending the conductive adhesive with the highest matching degree to the terminal for displaying.
8. The system of claim 7, further comprising:
acquiring the use method information of the conductive adhesive;
forming a difficulty degree value according to the using method of the conductive adhesive;
and judging whether the difficulty degree value exceeds a preset threshold value, and if so, setting the matching degree of the conductive adhesive to be zero.
9. The system of claim 7, further comprising:
acquiring production information of the conductive adhesive;
according to the production information of the conductive adhesive, obtaining carbon emission information of the conductive adhesive in the production process;
and judging whether the carbon emission of the conductive adhesive in production exceeds a preset threshold value, and if so, setting the matching degree of the conductive adhesive to be zero.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium includes a conductive paste recommendation method program for a semiconductor device, and when the conductive paste recommendation method program for a semiconductor device is executed by a processor, the steps of a conductive paste recommendation method for a semiconductor device according to any one of claims 1 to 6 are implemented.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210159813.XA CN114210597B (en) | 2022-02-22 | 2022-02-22 | Conductive adhesive recommendation method and system for semiconductor device and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210159813.XA CN114210597B (en) | 2022-02-22 | 2022-02-22 | Conductive adhesive recommendation method and system for semiconductor device and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114210597A true CN114210597A (en) | 2022-03-22 |
| CN114210597B CN114210597B (en) | 2022-04-26 |
Family
ID=80709150
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210159813.XA Active CN114210597B (en) | 2022-02-22 | 2022-02-22 | Conductive adhesive recommendation method and system for semiconductor device and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114210597B (en) |
Citations (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002340962A (en) * | 2001-05-11 | 2002-11-27 | Ibiden Co Ltd | Method and device for inspecting printed wiring board |
| US20090032444A1 (en) * | 2005-09-26 | 2009-02-05 | Sumitomo Electric Industries, Ltd. | Grain Classifying Device And Adhesive Containing Grains Classified By The Device |
| JP2011082211A (en) * | 2009-10-02 | 2011-04-21 | Dainippon Printing Co Ltd | Transparent conductive material and method of manufacturing the same |
| US20140327138A1 (en) * | 2013-05-01 | 2014-11-06 | Renesas Electronics Corporation | Semiconductor device |
| CN104820460A (en) * | 2015-04-03 | 2015-08-05 | 深圳市芯联电子科技有限公司 | Bandgap voltage reference source circuit |
| CN105143380A (en) * | 2013-03-28 | 2015-12-09 | 古河电气工业株式会社 | Adhesive tape and wafer-processing tape |
| CN108015013A (en) * | 2016-10-28 | 2018-05-11 | 荣旗工业科技（苏州）有限公司 | A kind of mobile phone conducting resinl detection device and its application |
| CN109495780A (en) * | 2018-10-16 | 2019-03-19 | 深圳壹账通智能科技有限公司 | A kind of Products Show method, terminal device and computer readable storage medium |
| CN109759355A (en) * | 2019-01-02 | 2019-05-17 | 张宪明 | Anisotropic conductive film conducting particles detection machine |
| CN109922968A (en) * | 2016-08-26 | 2019-06-21 | 荷兰应用自然科学研究组织Tno | For applying the method and system of pattern structure on the surface |
| CN111222960A (en) * | 2020-01-17 | 2020-06-02 | 青梧桐有限责任公司 | Room source recommendation method and system based on public traffic zone |
| CN111334237A (en) * | 2020-04-13 | 2020-06-26 | 艾硕新材料(上海)有限公司 | Polyurethane organic silicon conductive adhesive and preparation method and application thereof |
| US20200361210A1 (en) * | 2019-05-16 | 2020-11-19 | Seiko Epson Corporation | Information processing apparatus, printing apparatus, learning apparatus, and information processing method |
| CN112434811A (en) * | 2019-08-26 | 2021-03-02 | 华为技术有限公司 | Knowledge graph construction method and device, computing equipment and storage medium |
| CN112799514A (en) * | 2021-01-29 | 2021-05-14 | 中国工商银行股份有限公司 | Information recommendation method and device, electronic equipment and medium |
| CN113265210A (en) * | 2021-05-17 | 2021-08-17 | 北京中天鹏宇科技发展有限公司 | Adhesive with high electric and heat conductivity and preparation method thereof |
| CN113382541A (en) * | 2021-04-29 | 2021-09-10 | 邹文华 | Device for uniformly coating conductive adhesive on surface of PCB substrate after detection and additionally installing silicon wafer |
| CN113658662A (en) * | 2021-08-31 | 2021-11-16 | 平安医疗健康管理股份有限公司 | Medicine dispensing method, device, equipment and storage medium based on big medication data |
| CN113698877A (en) * | 2021-07-02 | 2021-11-26 | 杭州福斯特应用材料股份有限公司 | A pair of encapsulation glued membrane and use its photovoltaic module |
| CN113821717A (en) * | 2021-01-29 | 2021-12-21 | 北京沃东天骏信息技术有限公司 | Information processing method, information processing apparatus, storage medium, and electronic device |
| CN113845863A (en) * | 2021-10-15 | 2021-12-28 | 南方科技大学 | Conductive adhesive, preparation method thereof and conductive film |
| CN113934941A (en) * | 2021-10-12 | 2022-01-14 | 北京朗玛数联科技有限公司 | User recommendation system and method based on multi-dimensional information |
-
2022
- 2022-02-22 CN CN202210159813.XA patent/CN114210597B/en active Active
Patent Citations (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002340962A (en) * | 2001-05-11 | 2002-11-27 | Ibiden Co Ltd | Method and device for inspecting printed wiring board |
| US20090032444A1 (en) * | 2005-09-26 | 2009-02-05 | Sumitomo Electric Industries, Ltd. | Grain Classifying Device And Adhesive Containing Grains Classified By The Device |
| JP2011082211A (en) * | 2009-10-02 | 2011-04-21 | Dainippon Printing Co Ltd | Transparent conductive material and method of manufacturing the same |
| CN105143380A (en) * | 2013-03-28 | 2015-12-09 | 古河电气工业株式会社 | Adhesive tape and wafer-processing tape |
| US20140327138A1 (en) * | 2013-05-01 | 2014-11-06 | Renesas Electronics Corporation | Semiconductor device |
| CN104820460A (en) * | 2015-04-03 | 2015-08-05 | 深圳市芯联电子科技有限公司 | Bandgap voltage reference source circuit |
| CN109922968A (en) * | 2016-08-26 | 2019-06-21 | 荷兰应用自然科学研究组织Tno | For applying the method and system of pattern structure on the surface |
| CN108015013A (en) * | 2016-10-28 | 2018-05-11 | 荣旗工业科技（苏州）有限公司 | A kind of mobile phone conducting resinl detection device and its application |
| CN109495780A (en) * | 2018-10-16 | 2019-03-19 | 深圳壹账通智能科技有限公司 | A kind of Products Show method, terminal device and computer readable storage medium |
| CN109759355A (en) * | 2019-01-02 | 2019-05-17 | 张宪明 | Anisotropic conductive film conducting particles detection machine |
| US20200361210A1 (en) * | 2019-05-16 | 2020-11-19 | Seiko Epson Corporation | Information processing apparatus, printing apparatus, learning apparatus, and information processing method |
| CN112434811A (en) * | 2019-08-26 | 2021-03-02 | 华为技术有限公司 | Knowledge graph construction method and device, computing equipment and storage medium |
| CN111222960A (en) * | 2020-01-17 | 2020-06-02 | 青梧桐有限责任公司 | Room source recommendation method and system based on public traffic zone |
| CN111334237A (en) * | 2020-04-13 | 2020-06-26 | 艾硕新材料(上海)有限公司 | Polyurethane organic silicon conductive adhesive and preparation method and application thereof |
| CN112799514A (en) * | 2021-01-29 | 2021-05-14 | 中国工商银行股份有限公司 | Information recommendation method and device, electronic equipment and medium |
| CN113821717A (en) * | 2021-01-29 | 2021-12-21 | 北京沃东天骏信息技术有限公司 | Information processing method, information processing apparatus, storage medium, and electronic device |
| CN113382541A (en) * | 2021-04-29 | 2021-09-10 | 邹文华 | Device for uniformly coating conductive adhesive on surface of PCB substrate after detection and additionally installing silicon wafer |
| CN113265210A (en) * | 2021-05-17 | 2021-08-17 | 北京中天鹏宇科技发展有限公司 | Adhesive with high electric and heat conductivity and preparation method thereof |
| CN113698877A (en) * | 2021-07-02 | 2021-11-26 | 杭州福斯特应用材料股份有限公司 | A pair of encapsulation glued membrane and use its photovoltaic module |
| CN113658662A (en) * | 2021-08-31 | 2021-11-16 | 平安医疗健康管理股份有限公司 | Medicine dispensing method, device, equipment and storage medium based on big medication data |
| CN113934941A (en) * | 2021-10-12 | 2022-01-14 | 北京朗玛数联科技有限公司 | User recommendation system and method based on multi-dimensional information |
| CN113845863A (en) * | 2021-10-15 | 2021-12-28 | 南方科技大学 | Conductive adhesive, preparation method thereof and conductive film |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114210597B (en) | 2022-04-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114139839B (en) | Machine learning method based on working conditions and related device | |
| CN114210597B (en) | Conductive adhesive recommendation method and system for semiconductor device and readable storage medium | |
| CN110688098A (en) | Method and device for generating system framework code, electronic equipment and storage medium | |
| CN113590771A (en) | Data mining method, device, equipment and storage medium | |
| CN111026972A (en) | Subscription data pushing method, device, equipment and storage medium in Internet of things | |
| CN116703114A (en) | Classified storage method, system, device and medium for power dispatching data | |
| CN115147020B (en) | Decoration data processing method, device, equipment and storage medium | |
| Pau et al. | Electric current classification with tiny machine learning for home appliances | |
| CN112488410A (en) | Production equipment performance optimization method and device based on equipment comprehensive efficiency | |
| CN113327154A (en) | E-commerce user message pushing method and system based on big data | |
| CN113672497A (en) | Method, device and equipment for generating non-buried point event and storage medium | |
| CN112860671A (en) | Production factor data abnormity diagnosis method and device | |
| CN112579429A (en) | Problem positioning method and device | |
| CN114818502B (en) | Method and system for analyzing performance test data | |
| CN114268650B (en) | Configuration method and system for establishing communication connection | |
| CN109257206A (en) | A kind of method of data inputting and evaluation diagnostic message feedback | |
| CN116094778B (en) | Real-time monitoring system based on Internet | |
| CN116501915B (en) | Energy management end voice page retrieval method and system | |
| CN115933553B (en) | Power plant equipment state monitoring system and method | |
| CN116610960B (en) | Monitoring management system for artificial intelligence training parameters | |
| CN116558695B (en) | Terminal machine crimping force monitoring method, device and equipment based on voltage signals | |
| CN111861404A (en) | Data processing method and device based on intelligent machine and electronic equipment | |
| CN114282598A (en) | Multi-source heterogeneous power grid data fusion method, device, equipment and computer medium | |
| CN113535655A (en) | Log analysis method and device | |
| CN117376456A (en) | Gateway data template screening method |
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 | ||
| GR01 | Patent grant |