Parameter management method and system for accurate component replacement recommendation

Abstract

The invention provides a parameter management method and system for accurate component replacement recommendation, and relates to the technical field of parameter management, and the method comprises the steps: constructing a multi-scene parameter constraint model which comprises an application scene layer, a parameter constraint layer and an evaluation index layer; obtaining a parameter constraint condition set according to the target application scene information, and constructing an adaptive parameter feature mapping matrix; and converting candidate alternative component parameter information into a feature vector through the matrix, calculating a matching degree score with the parameter feature vector, a comprehensive performance matching degree, a cost control degree and a supply periodicity to generate an alternative scheme list, and optimizing a weight coefficient by utilizing execution feedback. According to the invention, the accuracy of component replacement recommendation is improved, and intelligent replacement scheme generation under multiple scenes is realized.

Description

Technical Field

[0001] The present invention relates to parameter management technology, and in particular to a parameter management method and system for accurate component replacement recommendation. Background Art

[0002] With the rapid development of electronic information technology, the types and quantity of electronic components have increased dramatically. At the same time, the speed of electronic product updates has accelerated, and market competition has become increasingly fierce. In the design, production and maintenance of electronic products, component replacement is often required. For example, due to the discontinuation of the original component, price increases, long supply cycles, etc., it is necessary to find suitable replacement components.

[0003] However, traditional component replacement methods mainly rely on engineers' experience and manual search, which is inefficient and prone to errors. Especially in complex systems, the parameters between components are interrelated, and simple parameter matching often cannot guarantee that the system performance after replacement is not affected. In addition, traditional replacement methods are difficult to comprehensively consider multiple factors such as performance, cost, and supply cycle, resulting in a low degree of optimization of replacement solutions.

[0004] Lack of consideration for application scenarios. Different application scenarios have different parameter requirements for components. For example, industrial control scenarios have higher requirements for reliability and stability, while consumer electronics scenarios focus more on cost and power consumption. Traditional substitution methods often ignore the differences in application scenarios, resulting in insufficient applicability of alternative solutions. Low parameter matching accuracy. Traditional substitution methods usually only consider a few key parameters and ignore the influence of other parameters, resulting in low parameter matching accuracy and inability to guarantee system performance after replacement. Difficulty in achieving multi-objective optimization. Component replacement requires comprehensive consideration of multiple objectives such as performance, cost, and delivery cycle. Traditional substitution methods are difficult to achieve multi-objective optimization. Summary of the invention

[0005] The embodiments of the present invention provide a parameter management method and system for accurate component replacement recommendation, which can solve the problems in the prior art.

[0006] According to a first aspect of the embodiments of the present invention,

[0007] Provides parameter management methods for accurate component replacement recommendations, including:

[0008] Construct a multi-scenario parameter constraint model, the multi-scenario parameter constraint model includes an application scenario layer, a parameter constraint layer and an evaluation index layer; wherein the application scenario layer includes application feature data of industrial control scenarios, communication equipment scenarios, consumer electronics scenarios, and medical equipment scenarios; the parameter constraint layer sets a set of parameter constraint conditions for each application scenario, and the evaluation index layer sets quantitative scoring standards for performance matching, cost control, and supply cycle;

[0009] Receive component replacement requirements, extract target application scenario information from the component replacement requirements, and obtain a corresponding parameter constraint condition set from the multi-scenario parameter constraint model according to the target application scenario information; construct an adaptive parameter feature mapping matrix, the adaptive parameter feature mapping matrix converts the parameter constraint condition set into a quantifiable parameter feature vector, and dynamically adjusts the weight coefficient of each feature item in the parameter feature vector according to the target application scenario information;

[0010] Generate alternative solutions based on the adaptive parameter feature mapping matrix, including establishing a component parameter feature library, converting parameter information of candidate alternative components into feature vector form, and calculating a matching score between the feature vector of the candidate alternative component and the parameter feature vector; the matching score comprehensively considers the performance matching, cost control, and supply cycle in the evaluation index layer, selects a preset number of candidate alternative components with the highest matching scores to form an alternative solution list, and uses the execution feedback data of the alternative solution list to optimize the weight coefficients in the adaptive parameter feature mapping matrix.

[0011] Construct a multi-scenario parameter constraint model, the multi-scenario parameter constraint model includes an application scenario layer, a parameter constraint layer and an evaluation index layer; wherein the application scenario layer includes application feature data of industrial control scenarios, communication equipment scenarios, consumer electronics scenarios and medical equipment scenarios, including:

[0012] Constructing a multi-scenario parameter constraint model framework, wherein the multi-scenario parameter constraint model framework includes a hierarchical structure, and the hierarchical structure is, from top to bottom, an application scenario layer, a parameter constraint layer, and an evaluation index layer;

[0013] Constructing the application scenario layer, the application scenario layer includes industrial control scenarios, communication equipment scenarios, consumer electronics scenarios, and medical equipment scenarios, collecting application feature data of the industrial control scenarios, the communication equipment scenarios, the consumer electronics scenarios, and the medical equipment scenarios, and storing the application feature data in the application scenario layer in the form of a multi-dimensional parameter matrix;

[0014] The parameter constraint layer is constructed based on the application feature data, and the parameter constraint layer constructs a corresponding parameter constraint rule set for each scenario of the application scenario layer, and the parameter constraint rule set includes a threshold constraint rule, an association constraint rule, and a mutually exclusive constraint rule, and the parameter constraint rule set is used to limit the value range and combination mode of the application feature data;

[0015] The evaluation index layer is constructed based on the parameter constraint rule set, and the evaluation index layer establishes a parameter evaluation matrix, wherein the parameter evaluation matrix includes a technical index evaluation sub-matrix, a performance index evaluation sub-matrix, and a cost index evaluation sub-matrix, and the parameter evaluation matrix performs quantitative scoring on the application feature data;

[0016] The scoring result of the parameter evaluation matrix is ​​fed back to the parameter constraint layer for dynamically adjusting the parameter constraint rule set. The adjustment result of the parameter constraint rule set is passed to the application scenario layer for updating the collection strategy of the application feature data, thereby forming a closed-loop optimization mechanism for multi-scenario parameter constraints.

[0017] The parameter constraint layer sets a set of parameter constraint conditions for each application scenario, and the evaluation index layer sets quantitative scoring criteria for performance matching, cost control, and delivery cycle, including:

[0018] Construct a parameter constraint layer, wherein the parameter constraint layer sets a set of parameter constraints for industrial control scenarios, communication equipment scenarios, consumer electronics scenarios, and medical equipment scenarios. The set of parameter constraints for the industrial control scenario includes control accuracy requirements, real-time response requirements, and anti-interference capability requirements; the set of parameter constraints for the communication equipment scenario includes signal integrity requirements, electromagnetic compatibility requirements, and power consumption control requirements; the set of parameter constraints for the consumer electronics scenario includes package size requirements, cost control requirements, and environmental adaptability requirements; and the set of parameter constraints for the medical equipment scenario includes safety requirements, reliability requirements, and biocompatibility requirements;

[0019] Specific parameter thresholds are set for the parameter constraint condition set. The parameter thresholds required for control accuracy include the analog signal sampling bit number not less than 16 bits and the sampling frequency not less than 1 MHz. The parameter thresholds required for real-time response include the signal processing delay time less than 1 microsecond and the bus communication delay less than 100 nanoseconds. The parameter thresholds required for anti-interference capability include the common mode rejection ratio greater than 80 decibels and the power supply rejection ratio greater than 60 decibels. The parameter thresholds required for signal integrity include the data transmission rate not less than 10 gigabits per second and the signal jitter value less than 50 picoseconds. The parameter thresholds required for electromagnetic compatibility include the radiation emission limit less than 40 decibels microvolts per meter. The parameter thresholds required for power consumption control include the power density per unit area less than 0.1 watt per square millimeter.

[0020] Construct an evaluation index layer, which sets quantitative scoring standards for performance matching, cost control, and delivery cycle. The performance matching adopts a five-level quantitative scoring method, where the parameter gets 100 points if it reaches the upper limit of the constraint condition and 60 points if it reaches the lower limit, and the intermediate value is calculated by linear interpolation; the cost control adopts a relative scoring method, where 80 points are scored based on the industry average level, and 10 points are added for every 10% reduction in cost, and 10 points are subtracted for every 10% increase in cost; the delivery cycle constructs a scoring function based on delivery stability and timeliness, and the scoring function is the total score of 100 points minus the number of delayed days multiplied by 10 points minus the standard deviation of delivery fluctuations multiplied by 5 points;

[0021] The weight coefficients of the performance matching degree, the cost control degree, and the delivery cycle degree in different application scenarios are determined by using the hierarchical analysis method. The weight coefficients of the industrial control scenario are 0.5, 0.3, and 0.2, the weight coefficients of the communication equipment scenario are 0.4, 0.4, and 0.2, the weight coefficients of the consumer electronics scenario are 0.3, 0.5, and 0.2, and the weight coefficients of the medical equipment scenario are 0.6, 0.2, and 0.2;

[0022] A fuzzy comprehensive evaluation matrix is ​​constructed based on the weight coefficients and the quantitative scoring criteria, and the fuzzy comprehensive evaluation matrix outputs a comprehensive score; actual application data is collected, and the deviation value between the comprehensive score and the actual application effect is calculated. When the deviation value exceeds a preset threshold, the weight coefficients and the quantitative scoring criteria are updated to achieve dynamic optimization of the scoring system.

[0023] Receiving a component replacement requirement, extracting target application scenario information in the component replacement requirement, and acquiring a corresponding parameter constraint condition set from the multi-scenario parameter constraint model according to the target application scenario information includes:

[0024] Receive a component replacement requirement in a standardized format, wherein the component replacement requirement includes a basic information field, an application scenario field, and a replacement requirement field. The basic information field includes a requirement number, submission time, and urgency. The application scenario field includes usage environment information, working condition information, and function positioning information. The replacement requirement field includes key parameter information of the original component and replacement condition information.

[0025] A scenario feature dictionary is constructed based on the content of the application scenario domain, wherein the scenario feature dictionary includes an industrial control scenario feature word set, a communication equipment scenario feature word set, a consumer electronics scenario feature word set, and a medical equipment scenario feature word set. The industrial control scenario feature word set includes programmable logic controller, closed-loop control, and real-time performance; the communication equipment scenario feature word set includes base station, router, and transmission rate; the consumer electronics scenario feature word set includes mobile terminal, portable device, and user interface; and the medical equipment scenario feature word set includes diagnostic instrument, vital sign monitoring, and medical safety.

[0026] The word vector of the scene feature word set is trained by using the Word2Vec model using the scene feature dictionary, and the cosine similarity between the scene description text in the application scenario domain and each scene feature word set is calculated based on the word vector, and when the maximum similarity value exceeds 0.8, the scene attribution of the scene description text is determined, and when the difference between multiple similarity values ​​is less than 0.1, the scene of the scene description text is marked as a mixed application type;

[0027] Based on the scene attribution of the scene description text, a general constraint condition set is obtained from a multi-scene parameter constraint model, when the scene is attributed to an industrial control scene, the general constraint condition set includes control accuracy constraints, real-time response constraints, and anti-interference capability constraints; when the scene is attributed to a communication device scene, the general constraint condition set includes signal integrity constraints, electromagnetic compatibility constraints, and power consumption control constraints; when the scene is attributed to a consumer electronics scene, the general constraint condition set includes package size constraints, cost control constraints, and environmental adaptability constraints; when the scene is attributed to a medical device scene, the general constraint condition set includes safety constraints, reliability constraints, and biocompatibility constraints;

[0028] Supplement the environmental adaptability of the general constraint condition set according to the use environment information in the application scenario domain; when the temperature environment in the use environment information is between negative forty degrees Celsius and eighty-five degrees Celsius, add a constraint condition that the temperature drift coefficient is less than one fifty millionth per degree Celsius to the general constraint condition set; when the humidity environment in the use environment information exceeds eighty-five percent relative humidity, add a constraint condition that the moisture-proof grade is not less than MSL level three to the general constraint condition set; according to the vibration frequency range in the use environment information, add an anti-vibration performance constraint condition to the general constraint condition set; according to the interference source characteristics in the use environment information, add an electromagnetic compatibility index constraint condition to the general constraint condition set;

[0029] Constructing an alternative solution knowledge base and recording the correspondence between scenario features and parameter constraints in historical alternative solutions, using the scenario description text to search for similar scenarios in the alternative solution knowledge base, obtaining the retrieved historically verified valid parameter constraints as supplementary constraints, and appending the supplementary constraints to the general constraint set;

[0030] Recording the effect data of the alternative solutions corresponding to the general constraint condition set in actual application, adjusting and relaxing the restrictions of the general constraint condition set based on the effect data when the number of selectable alternative solutions is less than a preset lower limit, and adjusting and tightening the requirements of the general constraint condition set based on the effect data when actual application problems occur in the alternative solutions;

[0031] The adjusted general constraint condition set is graded according to mandatory constraints and recommended constraints. The mandatory constraints are used to ensure the basic availability of alternative solutions, and the recommended constraints are used to optimize the matching degree of the screening alternative solutions. The graded general constraint condition set is output in a structured format as parameter constraint condition data.

[0032] Constructing an adaptive parameter feature mapping matrix, wherein the adaptive parameter feature mapping matrix converts the parameter constraint condition set into a quantifiable parameter feature vector, and dynamically adjusts the weight coefficient of each feature item in the parameter feature vector according to the target application scenario information, including:

[0033] Receive a set of parameter constraints, where the set of parameter constraints includes physical characteristic constraints, electrical characteristic constraints, reliability characteristic constraints, and economic characteristic constraints. The physical characteristic constraints include package size constraints, weight constraints, and heat dissipation coefficient constraints. The electrical characteristic constraints include operating voltage constraints, input and output impedance constraints, and frequency response constraints. The reliability characteristic constraints include service life constraints, failure rate constraints, and environmental adaptability constraints. The economic characteristic constraints include unit price constraints, supply stability constraints, and minimum order quantity constraints.

[0034] Constructing an adaptive parameter feature mapping matrix, wherein the number of rows of the adaptive parameter feature mapping matrix is ​​the number of parameter constraints, the number of columns is the number of standardized feature dimensions, and each element of the adaptive parameter feature mapping matrix represents a mapping value of a corresponding parameter constraint on a corresponding feature dimension;

[0035] The continuous parameters in the parameter constraint condition set are converted into values ​​in the range of zero to one by normalization processing, a five-level quantization standard is established for discrete parameters and quantized values ​​of 0.2, 0.4, 0.6, 0.8 and 1.0 are assigned, and for Boolean parameters, satisfying the requirements is recorded as one and not satisfying the requirements is recorded as zero, and the converted values ​​are filled into the adaptive parameter feature mapping matrix;

[0036] Calculating the Pearson correlation coefficient between the parameters in the adaptive parameter feature mapping matrix, marking the parameter pair as a strongly correlated group when the absolute value of the correlation coefficient is greater than 0.7, and establishing a linkage weight adjustment mechanism for the strongly correlated parameter group;

[0037] Receive target application scenario information, construct a scenario feature vector based on the target application scenario information, the scenario feature vector includes a function importance index, an environmental severity index, and a cost sensitivity index, and use a support vector machine to divide the target application scenario information into a high reliability requirement category, a high performance requirement category, and a low cost requirement category;

[0038] According to the scene feature vector and the scene demand category, the weight coefficients in the adaptive parameter feature mapping matrix are dynamically adjusted using a weight adjustment objective function. The weight adjustment objective function includes a functional matching evaluation sub-function, an environmental adaptability evaluation sub-function, and an economic rationality evaluation sub-function. A particle swarm optimization algorithm is used to solve the optimal weight combination.

[0039] Generating an alternative solution based on the adaptive parameter feature mapping matrix includes establishing a component parameter feature library, converting parameter information of candidate alternative components into a feature vector form, and calculating a matching score between the feature vector of the candidate alternative component and the parameter feature vector, including:

[0040] Construct a component parameter feature library, wherein the component parameter feature library includes a resistor component library, a capacitor component library, an inductor component library, a diode component library, and a transistor component library. Each component library includes a rated parameter field, a performance parameter field, a reliability parameter field, and an economic parameter field. The rated parameter field includes nominal value information and rated power information. The performance parameter field includes temperature coefficient information and frequency characteristic information. The reliability parameter field includes failure rate information and service life information. The economic parameter field includes unit price information and delivery period information.

[0041] Receiving an adaptive parameter feature mapping matrix and target component parameter constraints, wherein the adaptive parameter feature mapping matrix includes a physical characteristic mapping layer, an electrical characteristic mapping layer, a reliability characteristic mapping layer, and an economic characteristic mapping layer, and generating a target parameter feature vector based on the target component parameter constraints;

[0042] Retrieving the component parameter feature library to obtain candidate replacement component information, the candidate replacement component information including parameter value information and parameter type information, and inputting the candidate replacement component information into the adaptive parameter feature mapping matrix;

[0043] The continuous parameters in the candidate replacement component information are converted by a logarithmic normalization method, a mapping dictionary is established for discrete parameters to map discrete values ​​to discrete points in the range of zero to one, and zero-one encoding is used for Boolean parameters to generate a candidate replacement component feature vector;

[0044] Calculating the weighted cosine similarity between the candidate replacement component feature vector and the target parameter feature vector, wherein the weight coefficient of the weighted cosine similarity is provided by the adaptive parameter feature mapping matrix, and using local sensitive hashing technology to accelerate similarity calculation;

[0045] The supply chain stability score is calculated based on the supplier rating information and historical supply record information, and the cost economy score is calculated based on the procurement cost information, inventory cost information, and replacement cost information. The final matching score is calculated by combining the weighted cosine similarity score, supply chain stability score, and cost economy score.

[0046] According to a second aspect of the embodiments of the present invention,

[0047] Provides a parameter management system for accurate component replacement recommendations, including:

[0048] The first unit is used to construct a multi-scenario parameter constraint model, which includes an application scenario layer, a parameter constraint layer and an evaluation index layer; wherein the application scenario layer includes application feature data of industrial control scenarios, communication equipment scenarios, consumer electronics scenarios and medical equipment scenarios; the parameter constraint layer sets a set of parameter constraint conditions for each application scenario, and the evaluation index layer sets quantitative scoring standards for performance matching, cost control and delivery cycle;

[0049] The second unit is used to receive component replacement requirements, extract target application scenario information in the component replacement requirements, and obtain a corresponding parameter constraint condition set from the multi-scenario parameter constraint model according to the target application scenario information; construct an adaptive parameter feature mapping matrix, the adaptive parameter feature mapping matrix converts the parameter constraint condition set into a quantifiable parameter feature vector, and dynamically adjusts the weight coefficient of each feature item in the parameter feature vector according to the target application scenario information;

[0050] The third unit is used to generate alternative solutions based on the adaptive parameter feature mapping matrix, including establishing a component parameter feature library, converting the parameter information of candidate alternative components into feature vector form, and calculating the matching score between the feature vector of the candidate alternative component and the parameter feature vector; the matching score comprehensively considers the performance matching, cost control, and supply cycle in the evaluation index layer, selects a preset number of candidate alternative components with the highest matching scores to form an alternative solution list, and uses the execution feedback data of the alternative solution list to optimize the weight coefficients in the adaptive parameter feature mapping matrix.

[0051] According to a third aspect of the embodiments of the present invention,

[0052] An electronic device is provided, comprising:

[0053] processor;

[0054] a memory for storing processor-executable instructions;

[0055] The processor is configured to call the instructions stored in the memory to execute the aforementioned method.

[0056] A fourth aspect of the embodiments of the present invention is:

[0057] A computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the aforementioned method is implemented.

[0058] The beneficial effects of this application are as follows:

[0059] 1. Improve the accuracy of component replacement recommendations: By building a multi-scenario parameter constraint model and an adaptive parameter feature mapping matrix, it is possible to more accurately match the needs of the target application scenario, improve the applicability of alternative solutions, and avoid performance or compatibility issues caused by parameter mismatch.

[0060] 2. Optimize the comprehensive performance of alternative solutions: This method comprehensively considers multiple evaluation indicators such as performance matching, cost control and supply cycle, and realizes the comprehensive evaluation and optimization of alternative solutions, helping users to reduce costs and shorten procurement cycles while meeting performance requirements.

[0061] 3. Continuously improve the effectiveness of alternative recommendations: Utilize the execution feedback data of the alternative list to dynamically optimize the weight coefficients in the adaptive parameter feature mapping matrix, so that the system can continuously learn and improve, improve the effectiveness and accuracy of alternative recommendations, and better meet actual application needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1A flow chart of a parameter management method recommended for precise component replacement according to an embodiment of the present invention;

[0063] Figure 2 A schematic diagram of the structure of a parameter management system for precise component replacement recommendation according to an embodiment of the present invention. DETAILED DESCRIPTION

[0064] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0065] The technical solution of the present invention is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0066] Figure 1 FIG. 1 is a flow chart of a parameter management method for precise component replacement recommendation according to an embodiment of the present invention. Figure 1 As shown, the method includes:

[0067] S11. Construct a multi-scenario parameter constraint model, the multi-scenario parameter constraint model includes an application scenario layer, a parameter constraint layer and an evaluation index layer; wherein the application scenario layer includes application feature data of industrial control scenarios, communication equipment scenarios, consumer electronics scenarios, and medical equipment scenarios; the parameter constraint layer sets a set of parameter constraint conditions for each application scenario, and the evaluation index layer sets quantitative scoring standards for performance matching, cost control, and delivery cycle;

[0068] S12. Receive component replacement requirements, extract target application scenario information from the component replacement requirements, and obtain a corresponding parameter constraint condition set from the multi-scenario parameter constraint model according to the target application scenario information; construct an adaptive parameter feature mapping matrix, the adaptive parameter feature mapping matrix converts the parameter constraint condition set into a quantifiable parameter feature vector, and dynamically adjusts the weight coefficient of each feature item in the parameter feature vector according to the target application scenario information;

[0069] S13. Generate alternative solutions based on the adaptive parameter feature mapping matrix, including establishing a component parameter feature library, converting the parameter information of candidate alternative components into feature vector form, and calculating the matching score between the feature vector of the candidate alternative component and the parameter feature vector; the matching score comprehensively considers the performance matching, cost control, and delivery cycle in the evaluation index layer, selects a preset number of candidate alternative components with the highest matching scores to form an alternative solution list, and uses the execution feedback data of the alternative solution list to optimize the weight coefficients in the adaptive parameter feature mapping matrix.

[0070] In an optional implementation, a multi-scenario parameter constraint model is constructed, wherein the multi-scenario parameter constraint model includes an application scenario layer, a parameter constraint layer, and an evaluation index layer; wherein the application scenario layer includes application feature data of industrial control scenarios, communication equipment scenarios, consumer electronics scenarios, and medical equipment scenarios, including:

[0071] Constructing a multi-scenario parameter constraint model framework, wherein the multi-scenario parameter constraint model framework includes a hierarchical structure, and the hierarchical structure is, from top to bottom, an application scenario layer, a parameter constraint layer, and an evaluation index layer;

[0072] Constructing the application scenario layer, the application scenario layer includes industrial control scenarios, communication equipment scenarios, consumer electronics scenarios, and medical equipment scenarios, collecting application feature data of the industrial control scenarios, the communication equipment scenarios, the consumer electronics scenarios, and the medical equipment scenarios, and storing the application feature data in the application scenario layer in the form of a multi-dimensional parameter matrix;

[0073] The parameter constraint layer is constructed based on the application feature data, and the parameter constraint layer constructs a corresponding parameter constraint rule set for each scenario of the application scenario layer, and the parameter constraint rule set includes a threshold constraint rule, an association constraint rule, and a mutually exclusive constraint rule, and the parameter constraint rule set is used to limit the value range and combination mode of the application feature data;

[0074] The evaluation index layer is constructed based on the parameter constraint rule set, and the evaluation index layer establishes a parameter evaluation matrix, wherein the parameter evaluation matrix includes a technical index evaluation sub-matrix, a performance index evaluation sub-matrix, and a cost index evaluation sub-matrix, and the parameter evaluation matrix performs quantitative scoring on the application feature data;

[0075] The scoring result of the parameter evaluation matrix is ​​fed back to the parameter constraint layer for dynamically adjusting the parameter constraint rule set. The adjustment result of the parameter constraint rule set is passed to the application scenario layer for updating the collection strategy of the application feature data, thereby forming a closed-loop optimization mechanism for multi-scenario parameter constraints.

[0076] The multi-scenario parameter constraint model construction method is used to optimize parameter configuration across different application scenarios and improve product design efficiency and performance. The core of this method is to build a hierarchical model, which includes an application scenario layer, a parameter constraint layer, and an evaluation index layer, and realize closed-loop optimization of parameter configuration through dynamic interaction among the three.

[0077] First, build the application scenario layer. This layer covers various application scenarios, such as industrial control, communication equipment, consumer electronics, and medical equipment. For each scenario, its application feature data needs to be collected. These data reflect the specific needs and limitations of the scenario, such as the requirements for real-time and reliability in industrial control scenarios, the requirements for bandwidth and latency in communication equipment scenarios, the requirements for power consumption and user experience in consumer electronics scenarios, and the requirements for safety and accuracy in medical equipment scenarios. These application feature data are stored in the form of a multi-dimensional parameter matrix. For example, for a consumer electronic product, its application feature data may include parameters such as screen size, processor speed, battery capacity, and camera pixels. The values ​​of these parameters constitute a multi-dimensional matrix. Assume a specific example, a smartphone has a screen size of 6.5 inches, a processor speed of 2.4GHz, a battery capacity of 4500mAh, and a camera pixel of 48 million. These data constitute part of the application feature data of the smartphone in the consumer electronics scenario.

[0078] Next, a parameter constraint layer is constructed based on the application feature data. The parameter constraint layer constructs a corresponding parameter constraint rule set for each scenario in the application scenario layer. The rule set contains three types of constraint rules: threshold constraint rules, association constraint rules, and mutually exclusive constraint rules. Threshold constraint rules limit the value range of a single parameter, for example, the battery capacity must be between 3000mAh and 5000mAh. Association constraint rules define the interdependence between parameters, for example, the higher the processor speed, the larger the battery capacity is usually required to support it. Mutually exclusive constraint rules stipulate that certain parameters cannot take specific values ​​at the same time, for example, in low power mode, the screen brightness cannot exceed 50% of the maximum brightness. Continuing with the above smartphone as an example, assume that there is an association constraint rule: if the processor speed is higher than 2.2GHz, then the battery capacity must be greater than 4000mAh. Since the processor speed of this smartphone is 2.4GHz, its battery capacity of 4500mAh meets the association constraint rule.

[0079] Then, the evaluation index layer is constructed based on the parameter constraint rule set. The evaluation index layer establishes a parameter evaluation matrix, which includes a technical indicator evaluation sub-matrix, a performance indicator evaluation sub-matrix, and a cost indicator evaluation sub-matrix. The technical indicator evaluation sub-matrix focuses on the technical characteristics of the product, such as transmission rate, power consumption, etc. The performance indicator evaluation sub-matrix focuses on the performance of the product, such as response time, stability, etc. The cost indicator evaluation sub-matrix focuses on the manufacturing cost of the product, such as material cost, processing cost, etc. The parameter evaluation matrix quantitatively scores the application feature data. For example, a battery capacity of 4500mAh can get 9 points (out of 10 points), and a processor speed of 2.4GHz can get 8 points.

[0080] Finally, the scoring results of the parameter evaluation matrix are fed back to the parameter constraint layer for dynamic adjustment of the parameter constraint rule set. For example, if the score of a parameter is conscientiously lower than expected, the threshold constraint of the parameter can be relaxed or its associated constraints can be adjusted. The adjustment results of the parameter constraint rule set are passed to the application scenario layer to update the collection strategy of application feature data. For example, if the importance of a parameter decreases in actual application, the collection frequency or accuracy of the parameter can be reduced. This feedback mechanism forms a closed-loop optimization mechanism for multi-scenario parameter constraints, which can continuously improve the parameter configuration scheme.

[0081] The solution of this application can:

[0082] Improve product design efficiency: By pre-defining parameter constraint rules and evaluation indicators, invalid design solutions can be effectively avoided, the number of design iterations can be reduced, and the product development cycle can be shortened. Optimize product performance: Through multi-scenario parameter constraints and evaluations, the best parameter configuration solution can be found to maximize product performance while meeting the needs of different scenarios. Reduce product costs: Through parameter constraints and cost indicator evaluations, product costs can be effectively controlled, over-design can be avoided, and more cost-effective solutions can be selected.

[0083] In an optional implementation, the parameter constraint layer sets a set of parameter constraint conditions for each application scenario, and the evaluation index layer sets quantitative scoring criteria for performance matching, cost control, and delivery cycle, including:

[0084] Construct a parameter constraint layer, wherein the parameter constraint layer sets a set of parameter constraints for industrial control scenarios, communication equipment scenarios, consumer electronics scenarios, and medical equipment scenarios. The set of parameter constraints for the industrial control scenario includes control accuracy requirements, real-time response requirements, and anti-interference capability requirements; the set of parameter constraints for the communication equipment scenario includes signal integrity requirements, electromagnetic compatibility requirements, and power consumption control requirements; the set of parameter constraints for the consumer electronics scenario includes package size requirements, cost control requirements, and environmental adaptability requirements; and the set of parameter constraints for the medical equipment scenario includes safety requirements, reliability requirements, and biocompatibility requirements;

[0085] Specific parameter thresholds are set for the parameter constraint condition set. The parameter thresholds required for control accuracy include the analog signal sampling bit number not less than 16 bits and the sampling frequency not less than 1 MHz. The parameter thresholds required for real-time response include the signal processing delay time less than 1 microsecond and the bus communication delay less than 100 nanoseconds. The parameter thresholds required for anti-interference capability include the common mode rejection ratio greater than 80 decibels and the power supply rejection ratio greater than 60 decibels. The parameter thresholds required for signal integrity include the data transmission rate not less than 10 gigabits per second and the signal jitter value less than 50 picoseconds. The parameter thresholds required for electromagnetic compatibility include the radiation emission limit less than 40 decibels microvolts per meter. The parameter thresholds required for power consumption control include the power density per unit area less than 0.1 watt per square millimeter.

[0086] Construct an evaluation index layer, which sets quantitative scoring standards for performance matching, cost control, and delivery cycle. The performance matching adopts a five-level quantitative scoring method, where the parameter gets 100 points if it reaches the upper limit of the constraint condition and 60 points if it reaches the lower limit, and the intermediate value is calculated by linear interpolation; the cost control adopts a relative scoring method, where 80 points are scored based on the industry average level, and 10 points are added for every 10% reduction in cost, and 10 points are subtracted for every 10% increase in cost; the delivery cycle constructs a scoring function based on delivery stability and timeliness, and the scoring function is the total score of 100 points minus the number of delayed days multiplied by 10 points minus the standard deviation of delivery fluctuations multiplied by 5 points;

[0087] The weight coefficients of the performance matching degree, the cost control degree, and the delivery cycle degree in different application scenarios are determined by using the hierarchical analysis method. The weight coefficients of the industrial control scenario are 0.5, 0.3, and 0.2, the weight coefficients of the communication equipment scenario are 0.4, 0.4, and 0.2, the weight coefficients of the consumer electronics scenario are 0.3, 0.5, and 0.2, and the weight coefficients of the medical equipment scenario are 0.6, 0.2, and 0.2;

[0088] A fuzzy comprehensive evaluation matrix is ​​constructed based on the weight coefficients and the quantitative scoring criteria, and the fuzzy comprehensive evaluation matrix outputs a comprehensive score; actual application data is collected, and the deviation value between the comprehensive score and the actual application effect is calculated. When the deviation value exceeds a preset threshold, the weight coefficients and the quantitative scoring criteria are updated to achieve dynamic optimization of the scoring system.

[0089] Construction of parameter constraint layer and evaluation index layer

[0090] First, construct the parameter constraint layer and set the corresponding parameter constraint condition set for different application scenarios.

[0091] Industrial control scenarios: focus on control accuracy, real-time response and anti-interference ability. For example, control accuracy requires that the analog signal sampling bit number is not less than 16 bits and the sampling frequency is not less than 1MHz; real-time response requires that the signal processing delay time is less than 1 microsecond and the bus communication delay is less than 100 nanoseconds; anti-interference ability requires that the common mode rejection ratio is greater than 80 decibels and the power supply rejection ratio is greater than 60 decibels.

[0092] Communication equipment scenario: Focus on signal integrity, electromagnetic compatibility, and power consumption control. For example, signal integrity requires a data transmission rate of no less than 10 Gbps and a signal jitter value of less than 50 picoseconds; electromagnetic compatibility requires a radiation emission limit of less than 40 dBμV / m; power consumption control requires a power density per unit area of ​​less than 0.1 W / mm 2 .

[0093] Consumer electronics scenarios: focus on package size, cost control, and environmental adaptability. For example, the package size requires a maximum length of no more than 50mm, a maximum width of no more than 30mm, and a maximum height of no more than 10mm; cost control requires the total cost of components to be less than $10; and environmental adaptability requires an operating temperature range of -20°C to +60°C.

[0094] Medical equipment scenario: focus on safety, reliability and biocompatibility. For example, safety requires leakage current to be less than 10μA; reliability requires MTBF to be greater than 10,000 hours; and biocompatibility requires compliance with ISO10993 standards.

[0095] Then, build the evaluation indicator layer and set quantitative scoring standards for performance matching, cost control and delivery cycle.

[0096] Performance matching: A five-level quantitative scoring method is used. If the parameter reaches the upper limit of the constraint condition, 100 points are awarded, and if it reaches the lower limit, 60 points are awarded. The intermediate values ​​are calculated using linear interpolation. For example, if the upper limit of a parameter constraint condition is 100, the lower limit is 50, and the actual value is 75, then the performance matching score is 80 points.

[0097] Cost control degree: Relative scoring method is adopted. 80 points are scored based on the industry average level. 10 points are added for every 10% reduction in cost, and 10 points are subtracted for every 10% increase in cost. For example, if the industry average cost is 100 yuan and the actual cost is 90 yuan, the cost control degree score is 90 points.

[0098] Delivery cycle: A scoring function is constructed based on delivery stability and timeliness. The scoring function is the total score of 100 points minus the number of days of delay multiplied by 10 points minus the standard deviation of delivery fluctuation multiplied by 5 points.

[0099] Determination of weight coefficients and construction of fuzzy comprehensive evaluation matrix

[0100] Next, the analytic hierarchy process is used to determine the weight coefficients of performance matching, cost control and delivery cycle in different application scenarios.

[0101] Industrial control scenario: The performance matching weight is 0.5, the cost control weight is 0.3, and the delivery cycle weight is 0.2.

[0102] Communication equipment scenario: The performance matching weight is 0.4, the cost control weight is 0.4, and the delivery cycle weight is 0.2.

[0103] Consumer electronics scenario: The performance matching weight is 0.3, the cost control weight is 0.5, and the supply cycle weight is 0.2.

[0104] Medical equipment scenario: The performance matching weight is 0.6, the cost control weight is 0.2, and the delivery cycle weight is 0.2.

[0105] A fuzzy comprehensive evaluation matrix is ​​constructed based on weight coefficients and quantitative scoring criteria. The fuzzy comprehensive evaluation matrix outputs a comprehensive score.

[0106] Dynamic optimization of the scoring system

[0107] Finally, collect actual application data and calculate the deviation between the comprehensive score and the actual application effect. When the deviation exceeds the preset threshold, update the weight coefficient and quantitative scoring standard to achieve dynamic optimization of the scoring system. For example, if the preset threshold is 10 points, the comprehensive score of a product is 80 points, the actual application effect score is 60 points, and the deviation is 20 points, which exceeds the preset threshold, then the weight coefficient and quantitative scoring standard need to be updated.

[0108] The solution of this application can

[0109] Improve evaluation accuracy: Through multi-dimensional parameter constraints and quantitative scoring, combined with weight coefficients of different application scenarios, a more comprehensive and accurate evaluation of products is achieved, and the accuracy and reliability of evaluation results are improved. Optimize resource allocation: According to the focus of different application scenarios, dynamically adjust the weight coefficient and scoring criteria, which can effectively guide the rational allocation of resources and improve resource utilization efficiency. Promote continuous improvement: Through deviation value analysis and dynamic optimization mechanism, the scoring system can be continuously improved to make it closer to actual application and promote the continuous improvement of product performance and quality.

[0110] In an optional implementation, receiving a component replacement requirement, extracting target application scenario information in the component replacement requirement, and acquiring a corresponding parameter constraint condition set from the multi-scenario parameter constraint model according to the target application scenario information includes:

[0111] Receive a component replacement requirement in a standardized format, wherein the component replacement requirement includes a basic information field, an application scenario field, and a replacement requirement field. The basic information field includes a requirement number, submission time, and urgency. The application scenario field includes usage environment information, working condition information, and function positioning information. The replacement requirement field includes key parameter information of the original component and replacement condition information.

[0112] A scenario feature dictionary is constructed based on the content of the application scenario domain, wherein the scenario feature dictionary includes an industrial control scenario feature word set, a communication equipment scenario feature word set, a consumer electronics scenario feature word set, and a medical equipment scenario feature word set. The industrial control scenario feature word set includes programmable logic controller, closed-loop control, and real-time performance; the communication equipment scenario feature word set includes base station, router, and transmission rate; the consumer electronics scenario feature word set includes mobile terminal, portable device, and user interface; and the medical equipment scenario feature word set includes diagnostic instrument, vital sign monitoring, and medical safety.

[0113] The word vector of the scene feature word set is trained by using the Word2Vec model using the scene feature dictionary, and the cosine similarity between the scene description text in the application scenario domain and each scene feature word set is calculated based on the word vector, and when the maximum similarity value exceeds 0.8, the scene attribution of the scene description text is determined, and when the difference between multiple similarity values ​​is less than 0.1, the scene of the scene description text is marked as a mixed application type;

[0114] Based on the scene attribution of the scene description text, a general constraint condition set is obtained from a multi-scene parameter constraint model, when the scene is attributed to an industrial control scene, the general constraint condition set includes control accuracy constraints, real-time response constraints, and anti-interference capability constraints; when the scene is attributed to a communication device scene, the general constraint condition set includes signal integrity constraints, electromagnetic compatibility constraints, and power consumption control constraints; when the scene is attributed to a consumer electronics scene, the general constraint condition set includes package size constraints, cost control constraints, and environmental adaptability constraints; when the scene is attributed to a medical device scene, the general constraint condition set includes safety constraints, reliability constraints, and biocompatibility constraints;

[0115] Supplement the environmental adaptability of the general constraint condition set according to the use environment information in the application scenario domain; when the temperature environment in the use environment information is between negative forty degrees Celsius and eighty-five degrees Celsius, add a constraint condition that the temperature drift coefficient is less than one fifty millionth per degree Celsius to the general constraint condition set; when the humidity environment in the use environment information exceeds eighty-five percent relative humidity, add a constraint condition that the moisture-proof grade is not less than MSL level three to the general constraint condition set; according to the vibration frequency range in the use environment information, add an anti-vibration performance constraint condition to the general constraint condition set; according to the interference source characteristics in the use environment information, add an electromagnetic compatibility index constraint condition to the general constraint condition set;

[0116] Constructing an alternative solution knowledge base and recording the correspondence between scenario features and parameter constraints in historical alternative solutions, using the scenario description text to search for similar scenarios in the alternative solution knowledge base, obtaining the retrieved historically verified valid parameter constraints as supplementary constraints, and appending the supplementary constraints to the general constraint set;

[0117] Recording the effect data of the alternative solutions corresponding to the general constraint condition set in actual application, adjusting and relaxing the restrictions of the general constraint condition set based on the effect data when the number of selectable alternative solutions is less than a preset lower limit, and adjusting and tightening the requirements of the general constraint condition set based on the effect data when actual application problems occur in the alternative solutions;

[0118] The adjusted general constraint condition set is graded according to mandatory constraints and recommended constraints. The mandatory constraints are used to ensure the basic availability of alternative solutions, and the recommended constraints are used to optimize the matching degree of the screening alternative solutions. The graded general constraint condition set is output in a structured format as parameter constraint condition data.

[0119] Receive a component replacement requirement in a standardized format, which contains three fields: basic information field (requirement number, submission time, urgency), application scenario field (usage environment information, working condition information, function positioning information) and replacement requirement field (original component key parameter information, replacement condition information). For example, a requirement can be: requirement number 20240828001, submission time August 28, 2024, high urgency, application scenario is the temperature controller in the industrial automation production line, the operating temperature range is -20℃ to 70℃, humidity is 80%, the function is to accurately control the temperature, the original component model is LM35, and the replacement is required to be more accurate and lower cost.

[0120] Next, we build a scenario feature dictionary. This dictionary contains feature word sets for four scenarios: industrial control, communication equipment, consumer electronics, and medical equipment. For example, the feature word set for industrial control scenarios includes programmable logic controller, closed-loop control, and real-time; the feature word set for communication equipment scenarios includes base station, router, transmission rate, etc.

[0121] The Word2Vec model is used to train the word vectors of the scene feature word set. The scene description text in the application scene domain, such as "temperature controller in industrial automation production line", is also converted into a word vector. The cosine similarity between the word vector of the scene description text and the word vector of each scene feature word set is calculated. Assuming that the similarity with the industrial control scene feature word set is 0.9, and the similarity with other scenes is less than 0.3, since 0.9 is greater than 0.8, it is determined that the scene description text belongs to the industrial control scene. If the similarity with the industrial control scene is 0.82 and the similarity with the consumer electronics scene is 0.73, since the difference is less than 0.1, it is marked as a mixed application type.

[0122] According to the scenario attribution, a set of general constraints is obtained from the multi-scenario parameter constraint model. For example, the set of general constraints for industrial control scenarios includes control accuracy constraints, real-time response constraints, and anti-interference capability constraints. The set of general constraints for communication equipment scenarios includes signal integrity constraints, electromagnetic compatibility constraints, power consumption control constraints, etc.

[0123] The general constraint set is supplemented with environmental adaptability based on the use environment information in the application scenario domain. For example, if the temperature environment in the use environment information is -40℃ to 85℃, then the constraint condition that the temperature drift coefficient is less than one in five million per degree Celsius is added to the general constraint set. If the humidity exceeds 85%, then the constraint condition that the moisture resistance level is not less than MSL level 3 is added. Similarly, the vibration resistance performance constraint condition is added based on the vibration frequency range, and the electromagnetic compatibility index constraint condition is added based on the interference source characteristics. In this case, since the operating temperature range is -20℃ to 70℃ and the humidity is 80%, there is no need to add temperature drift coefficient and moisture resistance level constraints, but corresponding constraints need to be added based on the specific vibration frequency and interference source characteristics.

[0124] Construct an alternative solution knowledge base to record the correspondence between scenario features and parameter constraints in historical alternative solutions. For example, in a historical alternative solution, the scenario feature is "pressure sensor in industrial automation production line", and the parameter constraints include "accuracy 0.1%" and "response time less than 1ms". Use the current scenario description text "temperature controller in industrial automation production line" to search for similar scenarios in the knowledge base. If a historical alternative solution for a similar scenario is retrieved, its parameter constraints are used as supplementary constraints and appended to the general constraint set.

[0125] Record the effect data of the alternative solutions corresponding to the general constraint set in actual applications. For example, record the actual accuracy, response time, power consumption and other data of the alternative solutions. If the number of available alternative solutions is less than the preset lower limit, such as less than 3, some restrictions in the general constraint set can be relaxed, such as relaxing the accuracy requirement from 0.1% to 0.2%. If the alternative solutions have problems in actual applications, such as insufficient reliability, it is necessary to tighten the requirements of the general constraint set, such as improving the reliability index.

[0126] Finally, the adjusted set of general constraints is classified into mandatory constraints and recommended constraints. For example, accuracy requirements, safety levels, etc. can be used as mandatory constraints, while cost, power consumption, etc. can be used as recommended constraints. The classified set of general constraints is output in a structured format as parameter constraint data, such as outputting data in JSON format, including mandatory constraints and recommended constraints.

[0127] The solution of this application can:

[0128] Improve substitution efficiency: By automatically extracting scenario information and matching parameter constraints, manual intervention can be reduced, thereby improving the efficiency of component substitution. For example, what was previously required to manually search for information and analyze parameters can now be done automatically, reducing the substitution time from several days to several hours. Improve the quality of alternative solutions: Through multi-scenario parameter constraint models, environmental adaptability supplements, knowledge base retrieval, etc., ensure that the generated constraints are more comprehensive and accurate, thereby improving the quality of alternative solutions. For example, some key parameters may have been ignored in the past, but now they can be considered more comprehensively, avoiding performance degradation or incompatibility problems after substitution. Achieve continuous optimization of alternative solutions: By recording the actual application effect data of alternative solutions and adjusting parameter constraints based on the effect data, continuous optimization of alternative solutions can be achieved. For example, if it is found based on actual application data that a parameter constraint is too strict, resulting in too few options, the constraint can be appropriately relaxed to expand the range of options.

[0129] In an optional implementation, an adaptive parameter feature mapping matrix is ​​constructed, wherein the adaptive parameter feature mapping matrix converts the parameter constraint condition set into a quantifiable parameter feature vector, and dynamically adjusts the weight coefficient of each feature item in the parameter feature vector according to the target application scenario information, including:

[0130] Receive a set of parameter constraints, where the set of parameter constraints includes physical characteristic constraints, electrical characteristic constraints, reliability characteristic constraints, and economic characteristic constraints. The physical characteristic constraints include package size constraints, weight constraints, and heat dissipation coefficient constraints. The electrical characteristic constraints include operating voltage constraints, input and output impedance constraints, and frequency response constraints. The reliability characteristic constraints include service life constraints, failure rate constraints, and environmental adaptability constraints. The economic characteristic constraints include unit price constraints, supply stability constraints, and minimum order quantity constraints.

[0131] Constructing an adaptive parameter feature mapping matrix, wherein the number of rows of the adaptive parameter feature mapping matrix is ​​the number of parameter constraints, the number of columns is the number of standardized feature dimensions, and each element of the adaptive parameter feature mapping matrix represents a mapping value of a corresponding parameter constraint on a corresponding feature dimension;

[0132] The continuous parameters in the parameter constraint condition set are converted into values ​​in the range of zero to one by normalization processing, a five-level quantization standard is established for discrete parameters and quantized values ​​of 0.2, 0.4, 0.6, 0.8 and 1.0 are assigned, and for Boolean parameters, satisfying the requirements is recorded as one and not satisfying the requirements is recorded as zero, and the converted values ​​are filled into the adaptive parameter feature mapping matrix;

[0133] Calculating the Pearson correlation coefficient between the parameters in the adaptive parameter feature mapping matrix, marking the parameter pair as a strongly correlated group when the absolute value of the correlation coefficient is greater than 0.7, and establishing a linkage weight adjustment mechanism for the strongly correlated parameter group;

[0134] Receive target application scenario information, construct a scenario feature vector based on the target application scenario information, the scenario feature vector includes a function importance index, an environmental severity index, and a cost sensitivity index, and use a support vector machine to divide the target application scenario information into a high reliability requirement category, a high performance requirement category, and a low cost requirement category;

[0135] According to the scene feature vector and the scene demand category, the weight coefficients in the adaptive parameter feature mapping matrix are dynamically adjusted using a weight adjustment objective function. The weight adjustment objective function includes a functional matching evaluation sub-function, an environmental adaptability evaluation sub-function, and an economic rationality evaluation sub-function. A particle swarm optimization algorithm is used to solve the optimal weight combination.

[0136] Receive a set of parameter constraints. This set covers various factors that need to be considered when selecting electronic components, which can be divided into four categories: physical characteristics, electrical characteristics, reliability characteristics, and economic characteristics. Physical characteristic constraints include the package size, weight, and heat dissipation coefficient of the components. Electrical characteristic constraints include operating voltage, input and output impedance, and frequency response. Reliability characteristic constraints cover service life, failure rate, and environmental adaptability. Economic characteristic constraints include unit price, supply stability, and minimum order quantity. For example, a specific application scenario may require that the operating voltage of the component is between 3.3V and 5V, the package size does not exceed 10mmx10mm, and the service life is at least 10,000 hours.

[0137] Construct an adaptive parameter feature mapping matrix. This matrix is ​​the core of the entire method, which converts various constraints into quantifiable feature vectors. The number of rows in the matrix corresponds to the number of parameter constraints, and the number of columns corresponds to the number of standardized feature dimensions. Each element represents the mapping value of the corresponding parameter constraint on the corresponding feature dimension. For example, if we define five standardized feature dimensions: size, power consumption, performance, reliability, and cost, then each row of the matrix represents the score of a constraint on these five dimensions.

[0138] Numerically process the set of parameter constraints. In order to unify various types of constraints into a numerical range, data preprocessing is required. For continuous parameters such as operating voltage, normalization is used to convert them into numerical values ​​between 0 and 1. For discrete parameters such as package type, a five-level quantization standard is established and quantized values ​​of 0.2, 0.4, 0.6, 0.8, and 1.0 are assigned. For example, a small package is assigned a value of 0.2, a medium package is assigned a value of 0.6, and a large package is assigned a value of 1. For Boolean parameters such as whether they comply with the RoHS standard, meeting the requirements is recorded as 1, and not meeting the requirements is recorded as 0. The converted values ​​are filled into the adaptive parameter feature map matrix. Assuming that the quantized value of "weight constraint" in the "size" dimension is 0.8, in the "power consumption" dimension is 0.2, and in other dimensions is 0, these values ​​are filled in the corresponding positions of the matrix.

[0139] Handle strongly correlated parameter groups. Calculate the Pearson correlation coefficient between parameters in the adaptive parameter feature map matrix. If the absolute value of the correlation coefficient of two parameters is greater than 0.7, the two parameters are marked as a strongly correlated group. This means that there is a strong correlation between the two parameters, for example, size and weight are usually strongly correlated. Establish a linkage weight adjustment mechanism for strongly correlated parameter groups to avoid repeated calculations or contradictions. For example, if size and weight are strongly correlated, and size is important in a certain scenario, the weight of weight should also be increased accordingly.

[0140] Receive target application scenario information. The application scenario information determines which parameters are more important. The scenario feature vector contains a functional importance index, an environmental severity index, and a cost sensitivity index. For example, an aerospace application scenario will have high functional importance index and environmental severity index, while a consumer electronics product will have high cost sensitivity index. Use a support vector machine to classify the target application scenario information into a high reliability requirement category, a high performance requirement category, and a low cost requirement category. For example, based on the scenario feature vector, an aerospace application can be classified into a high reliability requirement category.

[0141] Dynamically adjust the weight coefficient. According to the scenario feature vector and scenario requirement category, the weight coefficient in the adaptive parameter feature mapping matrix is ​​dynamically adjusted using the weight adjustment objective function. The weight adjustment objective function contains a functional matching evaluation sub-function, an environmental adaptability evaluation sub-function, and an economic rationality evaluation sub-function. The particle swarm optimization algorithm is used to solve the optimal weight combination. For example, if the scenario belongs to the high reliability requirement category, the weight coefficient corresponding to the reliability characteristic will be higher. Assuming that the reliability score of a component is 0.9, the original weight is 0.3, and the adjusted weight is 0.6, the weighted score is 0.9*0.6=0.54.

[0142] The solution of this application can:

[0143] Improve the efficiency and accuracy of component selection: This method converts various constraints into quantifiable feature vectors and dynamically adjusts the weights according to the target application scenario. It can quickly screen out components that meet the requirements, avoid tedious manual comparison and screening processes, and improve the selection efficiency. At the same time, since the weights of various factors are taken into account, the selected components are more in line with actual needs, which improves the accuracy of selection. Enhance the adaptability of component selection: This method can dynamically adjust the parameter weights according to different application scenarios, making the selection process more flexible and able to adapt to various application needs. For example, for high-reliability applications, the weight of reliability indicators can be increased; for low-cost applications, the weight of economic indicators can be increased. Simplify the component selection process: This method converts the complex selection process into a series of standardized steps, simplifies the selection process, reduces the difficulty of selection, and even non-professionals can quickly get started. By automatically processing parameter constraints and scenario information, human intervention is reduced, and the objectivity and consistency of selection are improved.

[0144] In an optional implementation, generating an alternative solution based on the adaptive parameter feature mapping matrix includes establishing a component parameter feature library, converting parameter information of candidate alternative components into a feature vector form, and calculating a matching score between the feature vector of the candidate alternative component and the parameter feature vector, including:

[0145] Construct a component parameter feature library, wherein the component parameter feature library includes a resistor component library, a capacitor component library, an inductor component library, a diode component library, and a transistor component library. Each component library includes a rated parameter field, a performance parameter field, a reliability parameter field, and an economic parameter field. The rated parameter field includes nominal value information and rated power information. The performance parameter field includes temperature coefficient information and frequency characteristic information. The reliability parameter field includes failure rate information and service life information. The economic parameter field includes unit price information and delivery period information.

[0146] Receiving an adaptive parameter feature mapping matrix and target component parameter constraints, wherein the adaptive parameter feature mapping matrix includes a physical characteristic mapping layer, an electrical characteristic mapping layer, a reliability characteristic mapping layer, and an economic characteristic mapping layer, and generating a target parameter feature vector based on the target component parameter constraints;

[0147] Retrieving the component parameter feature library to obtain candidate replacement component information, the candidate replacement component information including parameter value information and parameter type information, and inputting the candidate replacement component information into the adaptive parameter feature mapping matrix;

[0148] The continuous parameters in the candidate replacement component information are converted by a logarithmic normalization method, a mapping dictionary is established for discrete parameters to map discrete values ​​to discrete points in the range of zero to one, and zero-one encoding is used for Boolean parameters to generate a candidate replacement component feature vector;

[0149] Calculating the weighted cosine similarity between the candidate replacement component feature vector and the target parameter feature vector, wherein the weight coefficient of the weighted cosine similarity is provided by the adaptive parameter feature mapping matrix, and using local sensitive hashing technology to accelerate similarity calculation;

[0150] The supply chain stability score is calculated based on the supplier rating information and historical supply record information, and the cost economy score is calculated based on the procurement cost information, inventory cost information, and replacement cost information. The final matching score is calculated by combining the weighted cosine similarity score, supply chain stability score, and cost economy score.

[0151] The invention discloses a method for generating electronic component replacement schemes, which can quickly and accurately screen out suitable replacement components from a component library according to target component parameters and constraint conditions provided by a user.

[0152] First, establish a comprehensive component parameter feature library. This library covers various types of electronic components, such as resistors, capacitors, inductors, diodes, and transistors. For each type of component, the library stores its key parameter information, which is divided into four fields: rated parameters, performance parameters, reliability parameters, and economic parameters. The rated parameter field contains information such as nominal value and rated power. The performance parameter field contains information such as temperature coefficient and frequency characteristics. The reliability parameter field contains information such as failure rate and service life. The economic parameter field contains information such as unit price and delivery time. For example, for a specific resistor, its rated parameter may be "100 ohms, 0.25 watts", the performance parameter may be "temperature coefficient of 100ppm / ℃", the reliability parameter may be "failure rate of 0.01% / 1000 hours", and the economic parameter may be "unit price 0.1 yuan, delivery time 1 week".

[0153] Next, the adaptive parameter feature mapping matrix and target component parameter constraints input by the user are received. The adaptive parameter feature mapping matrix contains a physical characteristic mapping layer, an electrical characteristic mapping layer, a reliability characteristic mapping layer, and an economic characteristic mapping layer. According to the target component parameter constraints, a target parameter feature vector is generated. For example, if the user needs a "100 ohm, 0.25 watt" resistor and is sensitive to temperature coefficient and price, then the target parameter feature vector will highlight the importance of these parameters.

[0154] Then, the candidate replacement component information similar to the target component is retrieved from the component parameter feature library. This information includes parameter value information and parameter type information. This information is input into the adaptive parameter feature mapping matrix. For example, a "91 ohm, 0.25 watt" resistor and a "110 ohm, 0.5 watt" resistor are retrieved as candidate replacement components.

[0155] In order to facilitate comparison, the information of candidate replacement components needs to be converted into feature vectors. For continuous parameters, such as resistance values, logarithmic normalization is used for conversion. For discrete parameters, such as package types, a mapping dictionary is established to map discrete values ​​to discrete points in the range of zero to one. For Boolean parameters, such as whether they comply with the RoHS standard, zero-one encoding is used. For example, "91 ohms" may be converted to 0.98 after logarithmic normalization, and "110 ohms" may be converted to 1.02.

[0156] Next, the weighted cosine similarity between the candidate replacement component feature vector and the target parameter feature vector is calculated. The weight coefficient is provided by the adaptive parameter feature mapping matrix. The local sensitive hashing technique is used to accelerate the similarity calculation. For example, assuming that the feature vector of the target resistor is [1, 0.5, 0.2], the feature vector of candidate resistor 1 is [0.98, 0.4, 0.1], and the feature vector of candidate resistor 2 is [1.02, 0.6, 0.3]. After weighted and cosine similarity calculation, the similarity of candidate resistor 1 is 0.95, and the similarity of candidate resistor 2 is 0.92.

[0157] In addition to similarity, supply chain stability and cost economy also need to be considered. The supply chain stability score is calculated based on the supplier rating information and historical supply record information. The cost economy score is calculated based on the procurement cost information, inventory cost information, and replacement cost information. For example, the supplier rating of candidate resistor 1 is high and the historical supply record is good, so the supply chain stability score is 0.9. The supplier rating of candidate resistor 2 is low and the historical supply record is average, so the supply chain stability score is 0.7.

[0158] Finally, the final matching score is calculated by combining the weighted cosine similarity score, supply chain stability score, and cost-effectiveness score. The candidate replacement component with the highest score is the final recommended alternative. For example, the final matching score of candidate resistor 1 is 0.95*0.5+0.9*0.3+0.8*0.2=0.9. The final matching score of candidate resistor 2 is 0.92*0.5+0.7*0.3+0.9*0.2=0.85. Therefore, candidate resistor 1 is a more suitable alternative.

[0159] The solution of this application can:

[0160] Improve the efficiency and accuracy of component replacement: By building a comprehensive component parameter feature library and an adaptive parameter feature mapping matrix, it is possible to quickly and accurately screen out qualified alternatives from a large number of components, saving engineers time and energy. Reduce the risk of component replacement: By considering factors such as supply chain stability and cost-effectiveness, it is possible to reduce the risk of alternatives and avoid project delays or failures due to supply chain disruptions or excessive costs. Improve the reliability and economy of product design: By selecting more suitable alternative components, it is possible to improve the reliability and economy of product design and enhance the market competitiveness of products.

[0161] Figure 2 FIG. 1 is a schematic diagram of a parameter management system for accurate component replacement recommendation according to an embodiment of the present invention. Figure 2 As shown, the system comprises:

[0162] The first unit is used to construct a multi-scenario parameter constraint model, which includes an application scenario layer, a parameter constraint layer and an evaluation index layer; wherein the application scenario layer includes application feature data of industrial control scenarios, communication equipment scenarios, consumer electronics scenarios and medical equipment scenarios; the parameter constraint layer sets a set of parameter constraint conditions for each application scenario, and the evaluation index layer sets quantitative scoring standards for performance matching, cost control and delivery cycle;

[0163] The second unit is used to receive component replacement requirements, extract target application scenario information in the component replacement requirements, and obtain a corresponding parameter constraint condition set from the multi-scenario parameter constraint model according to the target application scenario information; construct an adaptive parameter feature mapping matrix, the adaptive parameter feature mapping matrix converts the parameter constraint condition set into a quantifiable parameter feature vector, and dynamically adjusts the weight coefficient of each feature item in the parameter feature vector according to the target application scenario information;

[0164] The third unit is used to generate alternative solutions based on the adaptive parameter feature mapping matrix, including establishing a component parameter feature library, converting the parameter information of candidate alternative components into feature vector form, and calculating the matching score between the feature vector of the candidate alternative component and the parameter feature vector; the matching score comprehensively considers the performance matching, cost control, and supply cycle in the evaluation index layer, selects a preset number of candidate alternative components with the highest matching scores to form an alternative solution list, and uses the execution feedback data of the alternative solution list to optimize the weight coefficients in the adaptive parameter feature mapping matrix.

[0165] According to a third aspect of the embodiments of the present invention,

[0166] An electronic device is provided, comprising:

[0167] processor;

[0168] a memory for storing processor-executable instructions;

[0169] The processor is configured to call the instructions stored in the memory to execute the aforementioned method.

[0170] A fourth aspect of the embodiments of the present invention is:

[0171] A computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the aforementioned method is implemented.

[0172] The present invention may be a method, an apparatus, a system and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for executing various aspects of the present invention.

[0173] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A parameter management method for accurate component replacement recommendation, characterized in that: include: Construct a multi-scenario parameter constraint model, the multi-scenario parameter constraint model includes an application scenario layer, a parameter constraint layer and an evaluation index layer; wherein the application scenario layer includes application feature data of industrial control scenarios, communication equipment scenarios, consumer electronics scenarios, and medical equipment scenarios; the parameter constraint layer sets a set of parameter constraint conditions for each application scenario, and the evaluation index layer sets quantitative scoring standards for performance matching, cost control, and supply cycle; Receiving a component replacement requirement, extracting target application scenario information from the component replacement requirement, and acquiring a corresponding parameter constraint condition set from the multi-scenario parameter constraint model according to the target application scenario information; Constructing an adaptive parameter feature mapping matrix, wherein the adaptive parameter feature mapping matrix converts the parameter constraint condition set into a quantifiable parameter feature vector, and dynamically adjusts the weight coefficient of each feature item in the parameter feature vector according to the target application scenario information; Generating an alternative solution based on the adaptive parameter feature mapping matrix includes establishing a component parameter feature library, converting parameter information of candidate alternative components into a feature vector form, and calculating a matching score between the feature vector of the candidate alternative component and the parameter feature vector; The matching score comprehensively considers the performance matching, cost control, and delivery cycle in the evaluation index layer, selects a preset number of candidate replacement components with the highest matching scores to form a list of alternative solutions, and uses the execution feedback data of the list of alternative solutions to optimize the weight coefficients in the adaptive parameter feature mapping matrix.

2. The method according to claim 1, characterized in that Construct a multi-scenario parameter constraint model, the multi-scenario parameter constraint model includes an application scenario layer, a parameter constraint layer and an evaluation index layer; wherein the application scenario layer includes application feature data of industrial control scenarios, communication equipment scenarios, consumer electronics scenarios and medical equipment scenarios, including: Constructing a multi-scenario parameter constraint model framework, wherein the multi-scenario parameter constraint model framework includes a hierarchical structure, and the hierarchical structure is, from top to bottom, an application scenario layer, a parameter constraint layer, and an evaluation index layer; Constructing the application scenario layer, the application scenario layer includes industrial control scenarios, communication equipment scenarios, consumer electronics scenarios, and medical equipment scenarios, collecting application feature data of the industrial control scenarios, the communication equipment scenarios, the consumer electronics scenarios, and the medical equipment scenarios, and storing the application feature data in the application scenario layer in the form of a multi-dimensional parameter matrix; The parameter constraint layer is constructed based on the application feature data, and the parameter constraint layer constructs a corresponding parameter constraint rule set for each scenario of the application scenario layer, and the parameter constraint rule set includes a threshold constraint rule, an association constraint rule, and a mutually exclusive constraint rule, and the parameter constraint rule set is used to limit the value range and combination mode of the application feature data; The evaluation index layer is constructed based on the parameter constraint rule set, and the evaluation index layer establishes a parameter evaluation matrix, wherein the parameter evaluation matrix includes a technical index evaluation sub-matrix, a performance index evaluation sub-matrix, and a cost index evaluation sub-matrix, and the parameter evaluation matrix performs quantitative scoring on the application feature data; The scoring result of the parameter evaluation matrix is ​​fed back to the parameter constraint layer for dynamically adjusting the parameter constraint rule set. The adjustment result of the parameter constraint rule set is passed to the application scenario layer for updating the collection strategy of the application feature data, thereby forming a closed-loop optimization mechanism for multi-scenario parameter constraints.

3. The method according to claim 1, characterized in that The parameter constraint layer sets a set of parameter constraint conditions for each application scenario, and the evaluation index layer sets quantitative scoring criteria for performance matching, cost control, and delivery cycle, including: Construct a parameter constraint layer, wherein the parameter constraint layer sets a set of parameter constraints for industrial control scenarios, communication equipment scenarios, consumer electronics scenarios, and medical equipment scenarios. The set of parameter constraints for the industrial control scenario includes control accuracy requirements, real-time response requirements, and anti-interference capability requirements; the set of parameter constraints for the communication equipment scenario includes signal integrity requirements, electromagnetic compatibility requirements, and power consumption control requirements; the set of parameter constraints for the consumer electronics scenario includes package size requirements, cost control requirements, and environmental adaptability requirements; and the set of parameter constraints for the medical equipment scenario includes safety requirements, reliability requirements, and biocompatibility requirements; Specific parameter thresholds are set for the parameter constraint condition set. The parameter thresholds required for control accuracy include the analog signal sampling bit number not less than 16 bits and the sampling frequency not less than 1 MHz. The parameter thresholds required for real-time response include the signal processing delay time less than 1 microsecond and the bus communication delay less than 100 nanoseconds. The parameter thresholds required for anti-interference capability include the common mode rejection ratio greater than 80 decibels and the power supply rejection ratio greater than 60 decibels. The parameter thresholds required for signal integrity include the data transmission rate not less than 10 gigabits per second and the signal jitter value less than 50 picoseconds. The parameter thresholds required for electromagnetic compatibility include the radiation emission limit less than 40 decibels microvolts per meter. The parameter thresholds required for power consumption control include the power density per unit area less than 0.1 watt per square millimeter. Construct an evaluation index layer, which sets quantitative scoring standards for performance matching, cost control, and delivery cycle. The performance matching adopts a five-level quantitative scoring method, where the parameter gets 100 points if it reaches the upper limit of the constraint condition and 60 points if it reaches the lower limit, and the intermediate value is calculated by linear interpolation; the cost control adopts a relative scoring method, where 80 points are scored based on the industry average level, and 10 points are added for every 10% reduction in cost, and 10 points are subtracted for every 10% increase in cost; the delivery cycle constructs a scoring function based on delivery stability and timeliness, and the scoring function is the total score of 100 points minus the number of delayed days multiplied by 10 points minus the standard deviation of delivery fluctuations multiplied by 5 points; The weight coefficients of the performance matching degree, the cost control degree, and the delivery cycle degree in different application scenarios are determined by using the hierarchical analysis method. The weight coefficients of the industrial control scenario are 0.5, 0.3, and 0.2, the weight coefficients of the communication equipment scenario are 0.4, 0.4, and 0.2, the weight coefficients of the consumer electronics scenario are 0.3, 0.5, and 0.2, and the weight coefficients of the medical equipment scenario are 0.6, 0.2, and 0.2; A fuzzy comprehensive evaluation matrix is ​​constructed based on the weight coefficients and the quantitative scoring criteria, and the fuzzy comprehensive evaluation matrix outputs a comprehensive score; actual application data is collected, and the deviation value between the comprehensive score and the actual application effect is calculated. When the deviation value exceeds a preset threshold, the weight coefficients and the quantitative scoring criteria are updated to achieve dynamic optimization of the scoring system.

4. The method according to claim 1, characterized in that Receiving a component replacement requirement, extracting target application scenario information in the component replacement requirement, and acquiring a corresponding parameter constraint condition set from the multi-scenario parameter constraint model according to the target application scenario information includes: Receive a component replacement requirement in a standardized format, wherein the component replacement requirement includes a basic information field, an application scenario field, and a replacement requirement field. The basic information field includes a requirement number, submission time, and urgency. The application scenario field includes usage environment information, working condition information, and function positioning information. The replacement requirement field includes key parameter information of the original component and replacement condition information. A scenario feature dictionary is constructed based on the content of the application scenario domain, wherein the scenario feature dictionary includes an industrial control scenario feature word set, a communication equipment scenario feature word set, a consumer electronics scenario feature word set, and a medical equipment scenario feature word set. The industrial control scenario feature word set includes programmable logic controller, closed-loop control, and real-time performance; the communication equipment scenario feature word set includes base station, router, and transmission rate; the consumer electronics scenario feature word set includes mobile terminal, portable device, and user interface; and the medical equipment scenario feature word set includes diagnostic instrument, vital sign monitoring, and medical safety. The word vector of the scene feature word set is trained by using the Word2Vec model using the scene feature dictionary, and the cosine similarity between the scene description text in the application scenario domain and each scene feature word set is calculated based on the word vector, and when the maximum similarity value exceeds 0.8, the scene attribution of the scene description text is determined, and when the difference between multiple similarity values ​​is less than 0.1, the scene of the scene description text is marked as a mixed application type; Based on the scene attribution of the scene description text, a general constraint condition set is obtained from a multi-scene parameter constraint model, when the scene is attributed to an industrial control scene, the general constraint condition set includes control accuracy constraints, real-time response constraints, and anti-interference capability constraints; when the scene is attributed to a communication device scene, the general constraint condition set includes signal integrity constraints, electromagnetic compatibility constraints, and power consumption control constraints; when the scene is attributed to a consumer electronics scene, the general constraint condition set includes package size constraints, cost control constraints, and environmental adaptability constraints; when the scene is attributed to a medical device scene, the general constraint condition set includes safety constraints, reliability constraints, and biocompatibility constraints; Supplement the environmental adaptability of the general constraint condition set according to the use environment information in the application scenario domain; when the temperature environment in the use environment information is between negative forty degrees Celsius and eighty-five degrees Celsius, add a constraint condition that the temperature drift coefficient is less than one fifty millionth per degree Celsius to the general constraint condition set; when the humidity environment in the use environment information exceeds eighty-five percent relative humidity, add a constraint condition that the moisture-proof grade is not less than MSL level three to the general constraint condition set; according to the vibration frequency range in the use environment information, add an anti-vibration performance constraint condition to the general constraint condition set; according to the interference source characteristics in the use environment information, add an electromagnetic compatibility index constraint condition to the general constraint condition set; Constructing an alternative solution knowledge base and recording the correspondence between scenario features and parameter constraints in historical alternative solutions, using the scenario description text to search for similar scenarios in the alternative solution knowledge base, obtaining the retrieved historically verified valid parameter constraints as supplementary constraints, and appending the supplementary constraints to the general constraint set; Recording the effect data of the alternative solutions corresponding to the general constraint condition set in actual application, adjusting and relaxing the restrictions of the general constraint condition set based on the effect data when the number of selectable alternative solutions is less than a preset lower limit, and adjusting and tightening the requirements of the general constraint condition set based on the effect data when actual application problems occur in the alternative solutions; The adjusted general constraint condition set is graded according to mandatory constraints and recommended constraints. The mandatory constraints are used to ensure the basic availability of alternative solutions, and the recommended constraints are used to optimize the matching degree of the screening alternative solutions. The graded general constraint condition set is output in a structured format as parameter constraint condition data.

5. The method according to claim 1, characterized in that Constructing an adaptive parameter feature mapping matrix, wherein the adaptive parameter feature mapping matrix converts the parameter constraint condition set into a quantifiable parameter feature vector, and dynamically adjusts the weight coefficient of each feature item in the parameter feature vector according to the target application scenario information, including: Receive a set of parameter constraints, where the set of parameter constraints includes physical characteristic constraints, electrical characteristic constraints, reliability characteristic constraints, and economic characteristic constraints. The physical characteristic constraints include package size constraints, weight constraints, and heat dissipation coefficient constraints. The electrical characteristic constraints include operating voltage constraints, input and output impedance constraints, and frequency response constraints. The reliability characteristic constraints include service life constraints, failure rate constraints, and environmental adaptability constraints. The economic characteristic constraints include unit price constraints, supply stability constraints, and minimum order quantity constraints. Constructing an adaptive parameter feature mapping matrix, wherein the number of rows of the adaptive parameter feature mapping matrix is ​​the number of parameter constraints, the number of columns is the number of standardized feature dimensions, and each element of the adaptive parameter feature mapping matrix represents a mapping value of a corresponding parameter constraint on a corresponding feature dimension; The continuous parameters in the parameter constraint condition set are converted into values ​​in the range of zero to one by normalization processing, a five-level quantization standard is established for discrete parameters and quantized values ​​of 0.2, 0.4, 0.6, 0.8 and 1.0 are assigned, and for Boolean parameters, satisfying the requirements is recorded as one and not satisfying the requirements is recorded as zero, and the converted values ​​are filled into the adaptive parameter feature mapping matrix; Calculating the Pearson correlation coefficient between the parameters in the adaptive parameter feature mapping matrix, marking the parameter pair as a strongly correlated group when the absolute value of the correlation coefficient is greater than 0.7, and establishing a linkage weight adjustment mechanism for the strongly correlated parameter group; Receive target application scenario information, construct a scenario feature vector based on the target application scenario information, the scenario feature vector includes a function importance index, an environmental severity index, and a cost sensitivity index, and use a support vector machine to divide the target application scenario information into a high reliability requirement category, a high performance requirement category, and a low cost requirement category; According to the scene feature vector and the scene demand category, the weight coefficients in the adaptive parameter feature mapping matrix are dynamically adjusted using a weight adjustment objective function. The weight adjustment objective function includes a functional matching evaluation sub-function, an environmental adaptability evaluation sub-function, and an economic rationality evaluation sub-function. A particle swarm optimization algorithm is used to solve the optimal weight combination.

6. The method according to claim 1, characterized in that Generating an alternative solution based on the adaptive parameter feature mapping matrix includes establishing a component parameter feature library, converting parameter information of candidate alternative components into a feature vector form, and calculating a matching score between the feature vector of the candidate alternative component and the parameter feature vector, including: Construct a component parameter feature library, wherein the component parameter feature library includes a resistor component library, a capacitor component library, an inductor component library, a diode component library, and a transistor component library. Each component library includes a rated parameter field, a performance parameter field, a reliability parameter field, and an economic parameter field. The rated parameter field includes nominal value information and rated power information. The performance parameter field includes temperature coefficient information and frequency characteristic information. The reliability parameter field includes failure rate information and service life information. The economic parameter field includes unit price information and delivery period information. Receiving an adaptive parameter feature mapping matrix and target component parameter constraints, wherein the adaptive parameter feature mapping matrix includes a physical characteristic mapping layer, an electrical characteristic mapping layer, a reliability characteristic mapping layer, and an economic characteristic mapping layer, and generating a target parameter feature vector based on the target component parameter constraints; Retrieving the component parameter feature library to obtain candidate replacement component information, the candidate replacement component information including parameter value information and parameter type information, and inputting the candidate replacement component information into the adaptive parameter feature mapping matrix; The continuous parameters in the candidate replacement component information are converted by a logarithmic normalization method, a mapping dictionary is established for discrete parameters to map discrete values ​​to discrete points in the range of zero to one, and zero-one encoding is used for Boolean parameters to generate a candidate replacement component feature vector; Calculating the weighted cosine similarity between the candidate replacement component feature vector and the target parameter feature vector, wherein the weight coefficient of the weighted cosine similarity is provided by the adaptive parameter feature mapping matrix, and using local sensitive hashing technology to accelerate similarity calculation; The supply chain stability score is calculated based on the supplier rating information and historical supply record information, and the cost economy score is calculated based on the procurement cost information, inventory cost information, and replacement cost information. The final matching score is calculated by combining the weighted cosine similarity score, the supply chain stability score, and the cost economy score.

7. A parameter management system for accurate component replacement recommendation, used to implement the method according to any one of claims 1 to 6, characterized in that: include: The first unit is used to construct a multi-scenario parameter constraint model, which includes an application scenario layer, a parameter constraint layer and an evaluation index layer; wherein the application scenario layer includes application feature data of industrial control scenarios, communication equipment scenarios, consumer electronics scenarios and medical equipment scenarios; the parameter constraint layer sets a set of parameter constraint conditions for each application scenario, and the evaluation index layer sets quantitative scoring standards for performance matching, cost control and delivery cycle; The second unit is used to receive a component replacement requirement, extract target application scenario information in the component replacement requirement, and obtain a corresponding parameter constraint condition set from the multi-scenario parameter constraint model according to the target application scenario information; Constructing an adaptive parameter feature mapping matrix, wherein the adaptive parameter feature mapping matrix converts the parameter constraint condition set into a quantifiable parameter feature vector, and dynamically adjusts the weight coefficient of each feature item in the parameter feature vector according to the target application scenario information; A third unit is used to generate an alternative solution based on the adaptive parameter feature mapping matrix, including establishing a component parameter feature library, converting parameter information of candidate replacement components into a feature vector form, and calculating a matching score between the feature vector of the candidate replacement component and the parameter feature vector; The matching score comprehensively considers the performance matching, cost control, and delivery cycle in the evaluation index layer, selects a preset number of candidate replacement components with the highest matching scores to form a list of alternative solutions, and uses the execution feedback data of the list of alternative solutions to optimize the weight coefficients in the adaptive parameter feature mapping matrix.

8. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to call the instructions stored in the memory to execute the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images