A requirement analysis and procurement method and system for new product project management

Abstract

The present invention belongs to the technical field of requirements analysis. The present invention discloses a requirements analysis and procurement method and system for new product project management. The method includes: collecting M groups of project requirements data; performing clustering analysis on the project requirements data to obtain n requirement clusters; constructing a requirements structure relationship model for each requirement cluster, and obtaining an effective quality set based on the requirements structure relationship model; optimizing the requirements structure relationship model to obtain an optimized requirements distribution pattern; according to the optimized requirements distribution pattern, performing optimized selection of suppliers to obtain an optimal supplier combination; taking the optimal supplier combination as a procurement plan, evaluating procurement risks according to the effective quality set, and formulating risk response measures, accurately identifying high-risk requirements and suppliers, formulating differentiated risk response strategies, preventing and reducing procurement risks from the source, and ensuring the smooth progress of the project.

Description

Technical Field

[0001] The present invention relates to the technical field of demand analysis, and more specifically, to a demand analysis and procurement method and system for new product project management. Background Art

[0002] As market competition intensifies, companies are increasingly in need of launching new products and services; the successful implementation of new product projects is crucial for companies to maintain their competitiveness and expand into new markets. However, new product projects usually involve complex demand analysis and procurement processes, which require weighing multiple factors, such as demand priority, technical complexity, supplier capabilities, cost control, etc., which brings many challenges to the efficient advancement of projects.

[0003] In the implementation of new product projects, traditional demand analysis and procurement methods have many shortcomings, which have brought many obstacles to the smooth progress of the project; first, the existing methods are difficult to fully grasp the inherent correlation between demands, and often consider each demand as an independent individual, ignoring the mutual influence and constraint relationship between demands. This isolated analysis method cannot accurately assess the actual importance and complexity of each demand, resulting in unreasonable resource allocation and inefficient project execution; secondly, in the supplier selection link, the existing methods usually only consider a single factor, such as cost or quality, and lack a comprehensive evaluation of multi-dimensional indicators. This simplistic approach makes it difficult to fully grasp the actual capabilities of suppliers, which may lead to improper selection, affect the quality of new product delivery, and increase procurement risks; thirdly, the traditional methods lack scientificity in demand distribution and resource allocation, and are prone to concentrated or over-dispersed demand, resulting in waste of resources or excessive pressure on the supply chain, which seriously affects the efficient advancement of the project; in addition, the existing methods have obvious shortcomings in procurement risk management and control, lack of differentiated identification and response to different demands and supplier risks, and cannot timely discover and resolve potential risks, which may lead to project delays or quality problems, causing significant losses to the company.

[0004] In view of this, the present invention proposes a demand analysis and procurement method and system for new product project management to solve the above problems. Summary of the invention

[0005] In order to overcome the above defects of the prior art and to achieve the above purpose, the present invention provides the following technical solution: a demand analysis and procurement method for new product project management, comprising: step 1, collecting M groups of project demand data;

[0006] Step 2: Perform cluster analysis on the project demand data to obtain n demand clusters;

[0007] Step 3: construct a demand structure relationship model for each demand cluster, and obtain a valid quality set based on the demand structure relationship model;

[0008] Step 4: Optimize the requirement structure relationship model to obtain the optimized requirement distribution pattern;

[0009] Step 5: Based on the optimized requirement distribution pattern, conduct optimized selection of suppliers to obtain the optimal supplier combination;

[0010] Step 6: Take the optimal supplier combination as the procurement plan, evaluate the procurement risks according to the effective quality set, and formulate risk response measures.

[0011] Furthermore, the project requirement data includes project basic information, requirement information, and cost information;

[0012] The project basic information includes project name, project type, project budget, and project cycle;

[0013] The requirement information includes requirement source, requirement priority, and requirement category; the cost information is the estimated procurement cost and implementation cost for each requirement.

[0014] Furthermore, the methods for performing clustering analysis include:

[0015] Perform standardization or normalization processing on the project requirement data, define clustering features, where the clustering features include requirement priority, requirement category, procurement cost, and implementation cost; represent the clustering features as a multi-dimensional vector;

[0016] Define that the project requirement data is composed of the mixture of K probability distributions, and then obtain the corresponding mixture model of the project requirement data; K is an integer greater than 1; each probability distribution corresponds to a potential clustering;

[0017] Then the probability density function of the mixture model ; where, is the covariate vector, is the mixing weight of the th probability distribution, satisfying that the sum of the mixing weights of all probability distributions is 1; is the density function of the th probability distribution; is the parameter of the density function of the th probability distribution, is the original project requirement data;

[0018] Randomly initialize the parameters of the density function of each probability distribution, and for each data point y, calculate its initial posterior probability in each probability distribution, where, represents the hidden clustering label;

[0019] ; where, is a data point the likelihood under the k-th probability distribution; according to the calculated posterior probability, re-estimate the comprehensive parameters of each probability distribution, where the comprehensive parameters include the mixing weights and the parameters of the density function; the re-estimation formula is:

[0020] ; where is the index of the data point; is the total number of data points; is the mixing weight of the k-th probability distribution after re-estimation;

[0021] ; is the parameter of the density function of the k-th probability distribution after re-estimation; repeat until the preset maximum number of iterations is reached;

[0022] Set the number of clusters n. For different numbers of clusters n, take the number of clusters as the number of probability distributions, and respectively obtain the corresponding mixture models through iterative updates; for each mixture model, calculate its log-likelihood value and the number of parameters p; based on the log-likelihood value and the number of parameters p, calculate the goodness-of-fit metric ; where is the adjustment factor; select the number of clusters that minimizes the value of as n;

[0023] Take the n at this time as the number of probability distributions, calculate the posterior probability that each data point belongs to each probability distribution, and assign each data point to the probability distribution with the largest posterior probability. The probability distribution at this time is the demand cluster.

[0024] Furthermore, the acquisition method of the covariate vector includes:

[0025] Select the project type, project budget, and project cycle as covariate features; map the selected covariate features to a multi-dimensional feature space; at this time, the project requirement data is used as data points in the multi-dimensional feature space; calculate the distance between any two data points in the multi-dimensional feature space and construct a distance matrix D; set a seed point set S, randomly select a data point as the first seed point s1, add s1 to the seed point set S, and iteratively select seed points. For the current seed point set S, calculate the nearest distance between each data point that is not a seed point and the seed points in S, and select the data point with the largest nearest distance as the new seed point. Add the new seed point s_new to the seed point set S. Set a distance threshold and repeat. When the nearest distance from all data points that are not seed points to the seed points in S is less than this distance threshold, stop the iterative selection; starting from each seed point in the seed point set S, extend several scan lines in the multi-dimensional feature space and define the direction of the scan lines.

[0026] Along each scan line, mark the encountered data points as the neighborhood points of the corresponding seed point. For each seed point, regard all the data points within the neighborhood formed by its neighborhood points as a cluster, calculate the statistics of the covariate features of the data points in each cluster, and form these statistics into a covariate vector.

[0027] Further, the method for defining the direction of the scan line includes:

[0028] For each data point , calculate its density value and density gradient vector in the multi-dimensional feature space; where is a preset step size; for each seed point s, obtain its density value and density gradient vector;

[0029] Initially, define the direction of the scan line as the direction of the density gradient vector of the seed point s; denoted as the initial direction; extend the scan line from the seed point s along the initial direction, take a step size on the scan line, and calculate the density gradient vector of the new data point at this step size; adjust the direction of the scan line to the direction of, and repeat to continuously adjust the direction of the scan line to extend in the direction of the fastest increasing density; set the maximum length L_max of the scan line. When the length of the scan line exceeds L_max or it encounters a region where the density gradient vector is 0, terminate this scan line; restart the next scan line from the seed point, and the direction is determined according to the current density gradient vector.

[0030] Further, the method for constructing the requirement structure relationship model includes:

[0031] Take the data points within the requirement cluster as requirements; for each requirement cluster, construct a two-dimensional lattice structure, which consists of several regular lattices.

[0032] For each requirement in the requirement cluster, use a mapping function to map the requirement to a lattice point on the lattice of the two-dimensional lattice structure; obtain a lattice field; define the interaction range of the interaction and calculate the interaction between requirements; the calculation formula for the interaction is:

[0033] ; where is the requirement and the requirement the interaction between them; is the priority of the requirement , is the priority of the requirement , is the cost of the requirement , is the cost of the requirement ; and are weight coefficients;

[0034] Define the energy field of the lattice field ;

[0035] ; where is the field operator at the lattice point ; is the mass parameter; is the coupling constant; is the differential operator, representing the difference between adjacent lattice points; for each lattice point , calculate the local effective mass ;

[0036] ; where, is the traversal index of the lattice point, traversing the lattice points that interact with the lattice point ;

[0037] At this time, the two-dimensional lattice structure integrating the local effective mass and the energy field is the constructed requirement structure relationship model;

[0038] The acquisition method of the effective mass set includes:

[0039] Initialize the local effective mass of all lattice points, use the mean field approximation or other numerical methods to solve the energy field to obtain the field operator, and repeatedly calculate the local effective mass of each lattice point based on the field operator until the preset number of iterations is reached; fix the local effective mass of each lattice point at this time to form the effective mass set.

[0040] Further, the method for obtaining the optimized demand distribution pattern includes:

[0041] Obtain the initial demand distribution pattern from the demand structure relationship model, that is, the initial mapping position of each demand on the grid; set the initial temperature T0, the temperature decrease rate a1, and the termination temperature Tend; define the objective function as the weighted sum of the energy field and the demand distribution uniformity;

[0042] The formula for demand distribution uniformity is:

[0043] ; where is the demand density at the grid point , is the demand distribution uniformity, is the average value of the demand densities of all grid points; is the number of rows of the two-dimensional grid structure, is the number of columns of the two-dimensional grid structure; the demand density is the weighted sum of the quantity and priority of the demand at the corresponding grid point;

[0044] Calculate the value of the objective function corresponding to the initial demand distribution pattern ; set the current temperature , and set an iteration number for each temperature; at the current temperature, perform iterations:

[0045] For the demand structure relationship model, define its neighborhood structure as an 8-neighborhood; preset a fixed radius, and for each grid point, calculate the demand density within the fixed radius around it; set the maximum neighborhood radius Rmax, the minimum neighborhood radius Rmin, and the density threshold; for grid points with a demand density less than or equal to the density threshold, set their neighborhood radius to Rmin; for grid points with a demand density greater than the density threshold, set their neighborhood radius to Rmax; for each demand, construct a corresponding adaptive neighborhood according to the neighborhood radius of the grid point where it is located;

[0046] Randomly select a demand, and randomly select a new position according to the adaptive neighborhood of the grid point where the demand is currently located; obtain a new distribution pattern; calculate the value of the objective function of the new distribution pattern , calculate the energy difference ;

[0047] If is less than or equal to 0, then accept the new distribution pattern and update ; if is greater than 0, then accept the new distribution pattern with a probability of ;

[0048] Repeat until the number of iterations at this temperature is reached; reduce the temperature and repeat the iteration. The temperature reduction is the temperature drop rate a1 multiplied by the current temperature as the temperature for the next iteration; until the current temperature is less than Tend; at this time, output the finally obtained new distribution pattern, which is the optimized demand distribution pattern.

[0049] Further, the method for obtaining the optimal supplier combination includes:

[0050] Collect relevant information of potential suppliers, including supplier name, supplier type, supplier ability, supplier rating, and supplier cost;

[0051] According to the demand and budget, determine the constraint conditions for supplier selection; formalize the constraint conditions as hard constraints; based on the relevant information of potential suppliers, construct a model for evaluating supplier quality; the output of this model is the quality score of the supplier;

[0052] Regard each demand in the optimized demand distribution pattern as a molecule; assign an initial quality value to each molecule, determined based on the priority and complexity indicators of the demand; construct an optimization function; the optimization function is the weighted sum of the quality score of the supplier and the quality value of the molecule;

[0053] Combine the suppliers, assign a supplier to each molecule to obtain a supplier combination, and calculate the value of the optimization function under the current supplier combination; use an optimization algorithm to perform optimization iterations on the supplier combination, and stop the optimization iteration when the value of the optimization function converges, and output the supplier combination at this time, which is the optimal supplier combination.

[0054] A demand analysis and procurement system for new product project management, which is used to implement the demand analysis and procurement method for new product project management described above, includes: a data collection module for collecting M groups of project demand data;

[0055] A preliminary analysis module for performing cluster analysis on the project demand data to obtain n demand clusters;

[0056] A model construction module for constructing a demand structure relationship model for each demand cluster and obtaining an effective quality set based on the demand structure relationship model;

[0057] An optimization module for optimizing the demand structure relationship model to obtain an optimized demand distribution pattern;

[0058] A supplier matching module for performing optimized supplier selection according to the optimized demand distribution pattern to obtain an optimal supplier combination;

[0059] A risk prediction module, which is used to take the optimal supplier combination as a procurement plan, evaluate procurement risks according to the effective quality set, and formulate risk response measures; each module is connected by wired and / or wireless means to achieve data transmission between modules.

[0060] The technical effects and advantages of a demand analysis and procurement method and system for a new product project management according to the present invention:

[0061] The present invention can deeply explore the internal connections and influences between requirements, breaking through the limitations of traditional methods that only consider single requirements. By establishing a requirement structure relationship model, the actual importance and complexity of each requirement can be accurately evaluated, laying a foundation for subsequent resource allocation and risk control; secondly, it realizes the balanced distribution of requirements in different regions, avoids the inefficiencies of resource concentration or excessive dispersion, and improves the overall resource utilization efficiency; furthermore, by combining the supplier quality model with an optimization algorithm, multiple key factors can be comprehensively considered to select the optimal supplier combination, ensure the high-quality delivery of new product projects, and reduce the total procurement cost; in addition, an effective quality set and a supplier risk assessment mechanism are introduced, which can accurately identify high-risk requirements and suppliers, formulate differentiated risk response strategies, prevent and reduce procurement risks from the source, and ensure the smooth progress of the project. Description of the Drawings

[0062] Figure 1 It is a schematic diagram of a demand analysis and procurement method for a new product project management according to the present invention;

[0063] Figure 2 It is a schematic diagram of a demand analysis and procurement system for a new product project management according to the present invention. Detailed Embodiments

[0064] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0065] Embodiment 1

[0066] Please refer to Figure 1 As shown, a demand analysis and procurement method for a new product project management in this embodiment includes:

[0067] Step 1: Collect M groups of project requirement data;

[0068] Step 2: Perform cluster analysis on the project requirement data to obtain n requirement clusters; both M and n are integers greater than 1;

[0069] Step 3: Construct a requirement structure relationship model for each requirement cluster, and obtain an effective quality set based on the requirement structure relationship model;

[0070] Step 4: Optimize the requirement structure relationship model to obtain an optimized requirement distribution pattern;

[0071] Step 5: According to the optimized requirement distribution pattern, conduct an optimized selection of suppliers to obtain an optimal supplier portfolio;

[0072] Step 6: Take the optimal supplier portfolio as the procurement plan, evaluate the procurement risks based on the effective quality set, and formulate risk response measures.

[0073] The project requirement data includes project basic information, requirement information, and cost information; the project basic information includes project name, project type, project budget, and project cycle; the requirement information includes requirement source, requirement priority, and requirement category; the cost information is the estimated procurement cost and implementation cost for each requirement;

[0074] The project name is in string form and is used to uniquely identify the project. The project type, requirement source, requirement priority, and requirement category are represented by digital codes. For the requirement source, for example, 1 represents from customers, 2 represents from internal, 3 represents regulatory requirements, etc.; for the requirement category, for example, 1 represents functional requirements, 2 represents non-functional requirements, 3 represents constraints, etc.

[0075] The ways of conducting cluster analysis include:

[0076] Standardize or normalize the project requirement data to make different features on the same magnitude, define the clustering features, and the clustering features include requirement priority, requirement category, procurement cost, and implementation cost; represent the clustering features as a multi-dimensional vector.

[0077] Define that the project requirement data is composed of the mixture of K probability distributions, and then obtain the corresponding mixture model of the project requirement data; K is an integer greater than 1; each probability distribution corresponds to a potential cluster;

[0078] Then the probability density function of the mixture model ; where, is the covariate vector, is the mixing weight of the th probability distribution, and the sum of the mixing weights of all probability distributions is 1; is the density function of the th probability distribution, such as Gaussian distribution, Student's t-distribution, etc.; is the parameter of the density function of the th probability distribution, is the original project requirement data.

[0079] Select the project type, project budget, and project cycle as covariate features; map the selected covariate features to a multi-dimensional feature space; at this time, the project requirement data is used as data points in the multi-dimensional feature space; calculate the distance between any two data points in the multi-dimensional feature space and construct a distance matrix D; the distance is calculated as the Euclidean distance or cosine similarity between the vector compositions of the covariate features.

[0080] Set the seed point set S, randomly select a data point as the first seed point s1, add s1 to the seed point set S, and iteratively select seed points. For the current seed point set S, calculate the nearest distance between each data point that is not a seed point and the seed points in S, and select the data point with the largest nearest distance as the new seed point. Add the new seed point s_new to the seed point set S, set a distance threshold, and repeat until the nearest distance from all data points that are not seed points to the seed points in S is less than the distance threshold, then stop the iterative selection.

[0081] From each seed point in the seed point set S, extend several scan lines in the multi-dimensional feature space; and define the direction of the scan lines; for each data point , calculate its density value in the multi-dimensional feature space and the density gradient vector ; where, is a preset step size;

[0082] For each seed point s, obtain its density value and density gradient vector; initially, define the direction of the scan line as the direction of the density gradient vector of the seed point s; denoted as the initial direction; this can ensure that the scan line extends in the direction of increasing density; extend the scan line from the seed point s along the initial direction, take a step size on the scan line, and calculate the new data point at this step size and its density gradient vector ; adjust the direction of the scan line to the direction of, and repeat to continuously adjust the direction of the scan line to extend in the direction of the fastest increasing density; set the maximum length L_max of the scan line, and when the length of the scan line exceeds L_max or encounters a region where the density gradient vector is 0, terminate this scan line; restart the next scan line from the seed point, and the direction is determined according to the current density gradient vector.

[0083] Along each scan line, mark the data points encountered as the neighborhood points of the corresponding seed points. The same data point may be covered by the scan lines of multiple seed points. In this case, conflicts need to be resolved (such as the seed point with the closest distance wins).

[0084] For each seed point, all the data points within the neighborhood formed by its neighboring points are regarded as a cluster, and the statistics (such as mean, variance, etc.) of the covariate features of the data points within each cluster are calculated. These statistics are used to form a covariate vector and input it as the covariate information of the corresponding cluster into the mixture model.

[0085] Randomly initialize the parameters of the density function of each probability distribution. For each data point y, calculate its initial posterior probability under each probability distribution , where represents the hidden clustering label; actually, it reflects the potential clustering belonging of the data point and is a latent random variable that needs to be inferred and estimated based on the observed data.

[0086] ; where is the data point 's likelihood under the k-th probability distribution, indicating the probability of coming from the -th probability distribution; according to the calculated posterior probability, re-estimate the comprehensive parameters of each probability distribution. The comprehensive parameters include the mixing weight and the parameters of the density function.

[0087] The formula for re-estimation is:

[0088] ; where is the index of the data point; is the total number of data points (the number of groups of project requirement data); is the mixing weight of the k-th probability distribution after re-estimation.

[0089] ; is the parameter of the density function of the k-th probability distribution after re-estimation; repeat until the preset maximum number of iterations is reached.

[0090] Set the number of clusters n. For different numbers of clusters n, take the number of clusters as the number of probability distributions and obtain the corresponding mixture models obtained by iterative update respectively; for each mixture model, calculate its log-likelihood value and the number of parameters p; calculate the goodness-of-fit index based on the log-likelihood value ; where is the adjustment factor, usually taking a natural number within 2 to 5; select the number of clusters that minimizes the value of as n; take the n at this time as the number of probability distributions, calculate the posterior probability of each data point belonging to each probability distribution, and assign each data point to the probability distribution with the maximum posterior probability. The probability distribution at this time is the demand cluster.

[0091] The ways to construct the requirement structure relationship model include:

[0092] Taking the data points within the requirement cluster as requirements; for each requirement cluster, constructing a two-dimensional lattice structure, which contains several regular lattices; for each requirement in the requirement cluster, using a mapping function (such as linear mapping or non-linear mapping) to map the requirement to a lattice point on the lattice of the two-dimensional lattice structure; obtaining a lattice field.

[0093] Defining the interaction range (such as nearest neighbor or next-nearest neighbor) of the interactions, and calculating the interactions between requirements; the calculation formula for the interactions is:

[0094] ; where is the interaction between requirement and requirement ; is the priority of requirement (requirement priority), is the priority of requirement (requirement priority), is the cost of requirement (procurement cost and implementation cost), is the cost of requirement (procurement cost and implementation cost); and are weight coefficients.

[0095] Defining the energy field of the lattice field ;

[0096] ; where is the field operator at lattice point , which can be understood as describing the intensity or presence degree of the requirement at this lattice point; is the mass parameter, understood as the inherent importance or basic cost of the requirement; is the coupling constant, describing the intensity of the interaction between requirements; is the differential operator, representing the difference between adjacent lattice points; it should be noted that and are written in this form because of following the Pauli exclusion principle, which means that two identical field operators cannot occupy the same quantum state; this is different from ordinary number multiplication.

[0097] For each lattice point , calculating the local effective mass ;

[0098] ; where, is the traversal index of the lattice points, traversing the lattice points that interact with the lattice points ; at this time, the two-dimensional lattice structure integrating the local effective mass and the energy field is the constructed demand structure relationship model.

[0099] Initialize the local effective mass of all lattice points, solve the energy field using the mean field approximation or other numerical methods to obtain the field operator, and repeatedly calculate the local effective mass of each lattice point based on the field operator until the preset number of iterations is reached; fix the local effective mass of each lattice point at this time to form an effective mass set;

[0100] Correspondingly, a local effective mass distribution map can be drawn to identify high / low effective mass regions, corresponding to high / low priority or complexity demand concentration areas; through the above steps, the effective mass of each lattice point considering the interaction between demands is calculated, and then the relationship between demands and the overall structure can be better understood.

[0101] The ways to obtain the optimized demand distribution pattern include:

[0102] Obtain the initial demand distribution pattern from the demand structure relationship model, that is, the initial mapping position of each demand on the lattice; set the initial temperature T0, the temperature decrease rate a1 (0 < a1 < 1), and the termination temperature Tend.

[0103] Define the objective function as the weighted sum of the energy field and the demand distribution uniformity, which is used to evaluate the quality of the demand distribution pattern; the formula for the demand distribution uniformity is:

[0104] ; where, is the demand density on the lattice point is the demand distribution uniformity, is the average value of the demand densities of all lattice points; is the number of rows of the two-dimensional lattice structure, is the number of columns of the two-dimensional lattice structure; the demand density is the weighted sum of the number and priority of the demands on the corresponding lattice point;

[0105] Calculate the value of the objective function corresponding to the initial demand distribution pattern ; set the current temperature , and set an iteration number for each temperature; at the current temperature, perform iterations:

[0106] For the demand structure relationship model, define its neighborhood structure as the set of adjacent positions where the demand can move on the grid; specifically, it is an 8-neighborhood (up, down, left, right, and the four diagonals); preset a fixed radius, and for each grid point, calculate the demand density within the fixed radius around it; set the maximum neighborhood radius Rmax, the minimum neighborhood radius Rmin, and the density threshold; for the grid points with a demand density less than or equal to the density threshold, set their neighborhood radius to Rmin; for the grid points with a demand density greater than the density threshold, set their neighborhood radius to Rmax; or use a non-linear method to map the demand density to the interval [Rmin, Rmax].

[0107] For each demand, construct a corresponding adaptive neighborhood according to the neighborhood radius of the grid point where it is located; the adaptive neighborhood includes the grid point and all grid point positions within its radius; randomly select a demand, and randomly select a new position according to the adaptive neighborhood of the grid point where the demand is currently located; obtain a new distribution pattern; calculate the value of the objective function of the new distribution pattern , calculate the energy difference ;

[0108] If is less than or equal to 0, then accept the new distribution pattern and update ; if is greater than 0, then accept the new distribution pattern with a probability .

[0109] Repeat until the number of iterations at this temperature is reached; reduce the temperature and repeat the iteration. The reduced temperature is the current temperature multiplied by the temperature drop rate a1 as the temperature for the next iteration; until the current temperature is less than Tend; at this time, output the finally obtained new distribution pattern, which is the optimized demand distribution pattern.

[0110] The methods for obtaining the optimal supplier combination include:

[0111] Collect relevant information of potential suppliers, including supplier name, supplier type, supplier ability, supplier rating, and supplier cost; preprocess the relevant information, such as filling in missing values, standardization, etc., to make the data computable.

[0112] According to the demand and budget, determine the constraints for supplier selection, such as cost ceiling, delivery cycle requirements, quality requirements, etc.; formalize the constraints as hard constraints.

[0113] Based on the relevant information of potential suppliers, build a model for evaluating supplier quality, and machine learning and other methods can be used; the output of this model is the quality score of the supplier, which is used for subsequent optimization; specifically, encode non-numerical data, such as converting the supplier type into a numerical label; extract features from the original data that are helpful for evaluating supplier quality, such as on-time delivery rate, quality qualification rate, customer satisfaction, etc., and build a feature matrix, where each row corresponds to a supplier and each column corresponds to a feature; label each supplier with a quality score or grade as the target value for supervised learning; the quality score can be obtained through manual evaluation or calculated based on historical performance; select a machine learning algorithm as the basic framework of the model, such as decision tree, random forest, support vector machine, etc.

[0114] Use the feature matrix to train the model, and adjust the model hyperparameters according to the performance of the model, such as the maximum depth of the decision tree, the number of trees in the random forest, etc.; use techniques such as cross-validation and grid search to optimize the model and improve its generalization ability on unseen data, persist the optimized model for subsequent use, and regularly collect new supplier data to update the model.

[0115] Regard each requirement in the optimized demand distribution pattern as a molecule; assign an initial quality value to each molecule, which is determined based on the priority and complexity metrics of the requirement; the complexity metric reflects the difficulty of requirement implementation and is determined after quantification through the technical complexity and resource requirements of the requirement.

[0116] Build an optimization function; the optimization function is the weighted sum of the quality score of the supplier and the quality value of the molecule, and the weights can be adjusted according to the actual situation.

[0117] Combine the suppliers, assign a supplier to each molecule, note that the suppliers can be repeated, obtain the supplier combination, and calculate the value of the optimization function under the current supplier combination; use an optimization algorithm (such as simulated annealing, genetic algorithm, etc.) to optimize and iterate the supplier combination, and stop the optimization iteration when the value of the optimization function converges, and output the supplier combination at this time, which is the optimal supplier combination.

[0118] Through the above steps, combined with the demand distribution pattern and supplier data, the optimal supplier combination that meets each demand cluster can be obtained.

[0119] Take the optimal supplier combination obtained through the optimization algorithm as the procurement plan for the project; for each demand cluster, list its corresponding supplier and the specific list of requirements to be purchased from this supplier; summarize the requirements that each supplier needs to provide to form a purchase order for each supplier; organize the purchase order, supplier information, delivery time, etc. into a formal procurement plan document.

[0120] The set of effective masses reflects the actual importance or complexity of each requirement after considering the interactions among requirements; for requirements with higher effective masses, there are greater risks in their implementation, and the delivery quality of suppliers will be more critical.

[0121] According to the value of the local effective mass, a risk score is assigned to each requirement, specifically through a non-linear mapping function; for each supplier, the sum of the risk scores of the requirements it is responsible for is aggregated as the risk value of the supplier; the risk value of the supplier is combined with its quality score (weighted sum) to obtain a comprehensive score; based on the comprehensive score, a comprehensive rating of the supplier is carried out to obtain the supplier rating. Specifically, by setting thresholds in segments and comparing with the comprehensive score, the corresponding supplier rating is obtained; suppliers with high risks and high quality need to be focused on; based on the supplier rating, risk response measures are formulated, such as increasing inspections and raising liquidated damages, etc., to reduce the procurement risk.

[0122] During the procurement execution process, continuously monitor the delivery quality and progress of suppliers; for suppliers with major risks, adjust the response measures in a timely manner according to the evaluation results; if a certain supplier fails to deliver on schedule or the quality is seriously unqualified, the supplier portfolio can be re-optimized based on the remaining requirements; the new supplier portfolio needs to be re-evaluated for risks and the procurement plan and risk response measures are adjusted accordingly.

[0123] This embodiment can deeply explore the internal connections and influences among requirements, breaking through the limitations of traditional methods that only consider single requirements. By establishing a requirement structure relationship model, the actual importance and complexity of each requirement can be accurately evaluated, laying a foundation for subsequent resource allocation and risk control; secondly, it realizes the balanced distribution of requirements in different regions, avoiding the inefficient situations of resource concentration or excessive dispersion, and improving the overall resource utilization efficiency; furthermore, by combining the supplier quality model with the optimization algorithm, multiple key factors can be comprehensively considered, the optimal supplier portfolio can be selected to ensure the high-quality delivery of new product projects and reduce the total procurement cost; in addition, the introduction of the set of effective masses and the supplier risk assessment mechanism can accurately identify high-risk requirements and suppliers, formulate differentiated risk response strategies, prevent and reduce procurement risks from the source, and ensure the smooth progress of the project.

[0124] Embodiment 2

[0125] Please refer to Figure 2 As shown, for the parts not described in detail in this embodiment, refer to the description content of Embodiment 1. A requirement analysis and procurement system for new product project management is provided, including:

[0126] A data acquisition module, used to acquire M groups of project requirement data;

[0127] A preliminary analysis module for performing clustering analysis on project requirement data to obtain n requirement clusters; both M and n are integers greater than 1;

[0128] A model construction module for constructing a requirement structure relationship model for each requirement cluster and obtaining an effective quality set based on the requirement structure relationship model;

[0129] An optimization module for optimizing the requirement structure relationship model to obtain an optimized requirement distribution pattern;

[0130] A supplier matching module for performing optimized selection of suppliers according to the optimized requirement distribution pattern to obtain an optimal supplier combination;

[0131] A risk prediction module for taking the optimal supplier combination as a procurement plan, evaluating procurement risks according to the effective quality set, and formulating risk response measures; each module is connected by wired and / or wireless means to realize data transmission between modules.

[0132] Embodiment 3

[0133] This embodiment publicly provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it realizes the operation mode of a requirement analysis and procurement method for a new product project management provided above.

[0134] Since the electronic device introduced in this embodiment is the electronic device adopted for implementing a requirement analysis and procurement method for a new product project management in the embodiments of the present application, based on the requirement analysis and procurement method for a new product project management introduced in the embodiments of the present application, those skilled in the art can understand the specific implementation manners and various variation forms of the electronic device in this embodiment. Therefore, the specific implementation of how this electronic device realizes the method in the embodiments of the present application will not be described in detail here. As long as those skilled in the art implement the electronic device adopted for a requirement analysis and procurement method for a new product project management in the embodiments of the present application, it falls within the scope of protection of the present application.

[0135] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters and threshold selection in the formulas are set by those skilled in the art according to the actual situation.

[0136] The above are only the preferred embodiments of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions falling within the concept of the present invention belong to the protection scope of the present invention. It should be noted that for those of ordinary skill in the art, several improvements and refinements made without departing from the principle of the present invention should also be regarded as within the protection scope of the present invention.

Claims

1. A demand analysis and procurement method for new product project management, characterized in that: include: Step 1: Collect project demand data of group M; Step 2: Perform cluster analysis on the project demand data to obtain n demand clusters; Step 3: construct a demand structure relationship model for each demand cluster, and obtain a valid quality set based on the demand structure relationship model; The method of constructing the demand structure relationship model includes: The data points in the demand cluster are regarded as the demand; for each demand cluster, a two-dimensional grid structure is constructed, and the two-dimensional grid structure contains a number of regular grids; For each demand in the demand cluster, a mapping function is used to map the demand to a grid point on the grid of the two-dimensional grid structure; a grid field is obtained; the scope of interaction is defined, and the interaction between the demands is calculated; the calculation formula for the interaction is: U(i,j)=α×|r_i-r_j|+β×|c_i-c_j|; where U(i,j) is the interaction between demand i and demand j; r_i is the priority of demand i, r_j is the priority of demand j, c_i is the cost of demand i, c_j is the cost of demand j; α and β are weight coefficients; Define the energy field H of the lattice field; in is the field operator on the grid point I; m′ is the quality parameter; g is the coupling constant; is a differential operator, which represents the difference between adjacent grid points; for each grid point I, the local effective mass mf(I) is calculated; Among them, J is the traversal index of the grid point, traversing the grid points that interact with grid point I; At this time, the two-dimensional lattice structure integrating the local effective mass and energy field is used to construct the demand structure relationship model; The method for obtaining the effective quality set includes: Initialize the local effective mass of all grid points, use the mean field approximation or other numerical methods to solve the energy field, obtain the field operator, and repeatedly calculate the local effective mass of each grid point based on the field operator until the preset number of iterations is reached; fix the local effective mass of each grid point at this time to form an effective mass set; Step 4: Optimize the demand structure relationship model to obtain the optimal demand distribution pattern; Step 5: According to the optimal demand distribution pattern, optimize the supplier selection and obtain the optimal supplier combination; Step 6: Use the optimal supplier combination as the procurement plan, evaluate procurement risks based on the effective quality set, and develop risk response measures.

2. The demand analysis and procurement method for new product project management according to claim 1, characterized in that: The project demand data includes basic project information, demand information and cost information; Basic project information includes project name, project type, project budget and project period; Demand information includes demand source, demand priority and demand category; cost information includes the estimated procurement cost and implementation cost for each demand.

3. The demand analysis and procurement method for new product project management according to claim 2, characterized in that: The cluster analysis method includes: Standardize or normalize the project demand data, define clustering features, which include demand priority, demand category, procurement cost, and implementation cost; and represent the clustering features as a multidimensional vector; Define that the project demand data is a mixture of K probability distributions, and then obtain the mixture model corresponding to the project demand data; K is an integer greater than 1; each probability distribution corresponds to a potential cluster; Then the probability density function of the mixture model is Where z is the covariate vector, π_k is the mixing weight of the kth probability distribution, and the sum of the mixing weights of all probability distributions is 1; f_k(x|θ_k,z) is the density function of the kth probability distribution; θ_k is the parameter of the density function of the kth probability distribution, and x is the original project demand data; Randomly initialize the parameters of the density function of each probability distribution, and for each data point y, calculate its initial posterior probability P(Z=k|y) under each probability distribution, where Z represents the hidden cluster label; Among them, P(y|θ_k) is the likelihood of data point y under the kth probability distribution; according to the calculated posterior probability, the comprehensive parameters of each probability distribution are re-estimated, and the comprehensive parameters include the parameters of the mixing weight and the density function; the re-estimation formula is: Where m is the index of the data point; M is the total number of data points; π_k_new is the mixing weight of the kth probability distribution after re-estimation; θ_k_new=argmax∑ m P(Z=k|y)×log(P(y|θ_k)); θ_k_new is the parameter of the density function of the kth probability distribution after re-estimation; repeat until the preset maximum number of iterations is reached; Set the number of clusters n. For different numbers of clusters n, use the number of clusters as the number of probability distributions, and obtain the corresponding mixed models through iterative updates. For each mixed model, calculate its log-likelihood value LP and the number of parameters p. Calculate the fitting index HK=-2×LP+a×p×log(M) based on the log-likelihood value LP and the number of parameters p. Where a is the adjustment factor. Select the number of clusters that minimizes the value of HK as n. Take n at this time as the number of probability distributions, calculate the posterior probability of each data point belonging to each probability distribution, and assign each data point to the probability distribution with the largest posterior probability. The probability distribution at this time is the demand cluster.

4. The demand analysis and procurement method for new product project management according to claim 3, characterized in that: The method of obtaining the covariate vector includes: Select project type, project budget and project cycle as covariate features; map the selected covariate features to a multidimensional feature space; at this time, the project demand data is used as data points in the multidimensional feature space; calculate the distance between any two data points in the multidimensional feature space, and construct a distance matrix D; set a seed point set S, randomly select a data point as the first seed point s1, add s1 to the seed point set S, iteratively select seed points, for the current seed point set S, calculate the closest distance between each data point that is not a seed point and the seed point in S, select the data point with the largest closest distance as the new seed point, add the new seed point s_new to the seed point set S, set a distance threshold, and repeat until the closest distance of all data points that are not seed points to the seed points in S is less than the distance threshold, stop the iterative selection; starting from each seed point in the seed point set S, extend several scan lines in the multidimensional feature space, and define the direction of the scan line; Along each scan line, the data points encountered are marked as the neighborhood points of the corresponding seed point. For each seed point, all the data points in the neighborhood formed by its neighborhood points are regarded as a cluster. The statistics of the covariate features of the data points in each cluster are calculated, and these statistics are constructed into a covariate vector.

5. The demand analysis and procurement method for new product project management according to claim 4, characterized in that: The method of defining the direction of the scan line includes: For each data point y, calculate its density value ρ(y) and density gradient vector in the multidimensional feature space Where δ is the preset step size; for each seed point s, obtain its density value and density gradient vector; Initially, the direction of the scan line is defined as the direction of the density gradient vector of the seed point s; recorded as the initial direction; a scan line is extended from the seed point s along the initial direction, a step length δ is taken on the scan line, and the density gradient vector of the new data point y′ under this step length is calculated Adjust the scan line direction to The scan line direction is adjusted repeatedly to extend in the direction where the density increases fastest. The maximum length of the scan line is set to L_max. When the length of the scan line exceeds L_max or encounters an area where the density gradient vector is 0, the scan line is terminated. The next scan line is restarted from the seed point, and the direction is determined by the current density gradient vector.

6. The demand analysis and procurement method for new product project management according to claim 5, characterized in that: The method for obtaining the optimal demand distribution pattern includes: Obtain the initial demand distribution pattern from the demand structure relationship model, that is, the initial mapping position of each demand on the grid; set the initial temperature T0, temperature drop rate a1, and end temperature Tend; define the objective function as the weighted sum of the energy field H and the uniformity of demand distribution; The formula for demand distribution uniformity is: Where d_I is the demand density at grid point I, U is the uniformity of demand distribution, d_avg is the average value of demand density at all grid points; M1 is the number of rows of the two-dimensional grid structure, and N1 is the number of columns of the two-dimensional grid structure; demand density is the weighted sum of the number and priority of the demand at the corresponding grid point; Calculate the value E0 of the objective function corresponding to the initial demand distribution pattern; set the current temperature T = T0, set an iteration number for each temperature; iterate at the current temperature: For the demand structure relationship model, its neighborhood structure is defined as 8 neighborhoods; a fixed radius is preset, and for each grid point, the demand density within the fixed radius around it is calculated; the maximum neighborhood radius Rmax, the minimum neighborhood radius Rmin and the density threshold are set; for grid points with demand density less than or equal to the density threshold, its neighborhood radius is set to Rmin; for grid points with demand density greater than the density threshold, its neighborhood radius is set to Rmax; for each demand, the corresponding adaptive neighborhood is constructed according to the neighborhood radius of the grid point where it is located; Randomly select a demand, and randomly select a new location according to the adaptive neighborhood of the grid point where the demand is currently located; obtain a new distribution pattern; calculate the value Enew of the objective function of the new distribution pattern, and calculate the energy difference ΔE=Enew-E0; If ΔE is less than or equal to 0, accept the new distribution pattern and update E0 = Enew; if ΔE is greater than 0, update the probability Accept new distribution patterns; Repeat until the number of iterations at that temperature is reached; lower the temperature and repeat the iteration, lowering the temperature to the temperature drop rate a1 multiplied by the current temperature as the temperature for the next iteration; until the current temperature is less than Tend; at this time, the new distribution pattern finally output is the optimized demand distribution pattern.

7. The method for demand analysis and procurement for new product project management according to claim 6, characterized in that: Methods for obtaining the optimal supplier combination include: Collect relevant information about potential suppliers, including supplier name, supplier type, supplier capabilities, supplier rating, and supplier cost; Determine the constraints for supplier selection based on demand and budget; formalize the constraints as hard constraints; build a model for evaluating supplier quality based on relevant information of potential suppliers; the output of the model is the supplier's quality score; Treat each demand in the optimal demand distribution pattern as a molecule; assign an initial quality value to each molecule, determined based on the priority and complexity index of the demand; construct an optimization function; the optimization function is the weighted sum of the supplier's quality score and the quality value of the molecule; Combine suppliers, assign a supplier to each molecule, obtain the supplier combination, and calculate the value of the optimization function under the current supplier combination; use the optimization algorithm to iterate the optimization of the supplier combination, stop the optimization iteration when the value of the optimization function converges, and output the supplier combination at this time, which is the optimal supplier combination.

8. A demand analysis and procurement system for new product project management, which is used to implement the demand analysis and procurement method for new product project management as claimed in any one of claims 1 to 7, characterized in that: include: Data collection module, used to collect M group project demand data; The preliminary analysis module is used to cluster the project demand data and obtain n demand clusters; A model building module is used to build a demand structure relationship model for each demand cluster and obtain a valid quality set based on the demand structure relationship model; Optimization module, used to optimize the demand structure relationship model and obtain the optimal demand distribution pattern; The supplier matching module is used to optimize the supplier selection according to the optimal demand distribution pattern to obtain the optimal supplier combination; The risk prediction module is used to use the optimal supplier combination as a procurement plan, evaluate procurement risks based on the effective quality set, and formulate risk response measures; each module is connected through wired and / or wireless means to achieve data transmission between modules.

Images