A data resource evaluation management method and system for industrial manufacturing enterprises

Abstract

The present invention discloses a data resource evaluation management method and system for an industrial manufacturing enterprise, and relates to the technical field of enterprise data resource evaluation management, including an input module, a product preliminary screening module, and a product secondary screening module. The present invention constructs a product demand model and a product supply model, and performs a first round and a second round of screening when configuring products. In the first round of screening, relevant dimensions of the products are scored, and the products are matched according to the product demand degree of the enterprise in the above dimensions. In the second round of screening, other dimensions are selected for scoring, and the product demand degree of the enterprise in the above dimensions is scored to select the second round of products for enterprise decision makers to choose. Enterprise decision makers do not need to configure products completely based on their own subjective judgment, so that the process of configuring products is more scientific and objective, which is conducive to improving work efficiency and the quality of product procurement.

Description

Technical Field

[0001] The present invention belongs to the technical field of enterprise data resource evaluation management, and in particular, relates to a method and system for industrial manufacturing enterprise data resource evaluation management. Background Art

[0002] Enterprise data resources refer to the various data assets owned and accumulated by the enterprise, including unique business data, customer data, market data, supply chain data, employee data, etc. These data can come from internal systems, external partners, social media and other channels, and are an important basis for enterprise operations and decision-making. Enterprise data resources are of great significance to the development and competitiveness of enterprises. Through the collection, storage, management and analysis of data, enterprises can use data resources to conduct business analysis, trend forecasting, marketing, customer relationship management, etc., to provide strong support for enterprise decision-making. Enterprise data resources can play a role in the following aspects: strategic decision-making, operation optimization, customer relationship management, innovation and research and development, risk management: through the integration and analysis of data, enterprises can timely identify risks and problems, and take corresponding measures for risk management and prevention to protect corporate interests and reputation. In order to make full use of enterprise data resources, enterprises need to establish a sound data management system, including data collection, integration, storage, analysis and protection.

[0003] In the prior art, there are related technical solutions for managing enterprise data resources, such as:

[0004] A Chinese patent with publication number CN110458528A discloses a full-business configuration management platform based on CMDB operation and maintenance management, which specifically discloses: including a server, a login window connected to the server to realize user login, a storage module that establishes a data connection with the server to store platform resource data, and a communication module that establishes communication with the server to realize data interaction between various units of the platform; configuration management: automatic discovery of units and configuration management libraries to centralize the configuration information management of all resources, build operation and maintenance management metadata, and provide resource data for monitoring and operation and maintenance processes; automatically calculate the optimal path, recommend the most reasonable configuration, and guide configuration managers to perform resource configuration; unified collection operation layer, unified resource library, and APP based on platform services and component specifications that can be continuously enriched and expanded.

[0005] A Chinese patent with the authorization number CN116596462B discloses a blockchain-based enterprise management paradigm R&D project management system; specifically disclosed: it includes a demand matching module, which is configured to generate project resources for R&D project matching based on a database; a category management module, which is configured to manage the project resources generated by the demand matching module and generate R&D items; a process management module, which is configured to perform data management, progress management, and coordination management on the R&D items in the time dimension; and an evaluation feedback module, which is configured to evaluate the completed R&D items in the process management module.

[0006] The Chinese patent with the authorization number CN112732823B discloses a method for implementing a monitoring system for the entire process of material supply in an enterprise; specifically, the method includes the following steps: the custom kanban submodule obtains and displays the project material progress, material detail progress, and supply index data associated with the current logged-in user from the database when triggered; the material supply entire process analysis submodule obtains and displays the processing time of different supply units, different projects, and different material categories from the database when triggered. The entire process of material supply analysis, including custom kanban, multi-dimensional material category processing efficiency analysis, and abnormal tracing, is realized, which helps to fully and deeply understand the material supply level, thereby helping enterprises to formulate correct management strategies and improve management efficiency.

[0007] When an enterprise has a need to purchase products, existing enterprise decision makers generally decide on the type of products to be purchased based on their subjective judgment. However, due to different requirements for products due to various production needs in the enterprise, and the supervisors or decision makers' understanding of product information, product technical information and other aspects of information is mostly one-sided, there is a problem of blindness in the purchase of products, which will lead to a mismatch between the products needed by the enterprise and the products purchased by the enterprise, which will affect work efficiency and the quality of product purchases, and also cause losses to the enterprise. Summary of the invention

[0008] In view of the problems in the related technologies, the present invention proposes an enterprise resource management method and system based on cloud computing to overcome the above technical problems existing in the existing related technologies.

[0009] In order to solve the above technical problems, the present invention is achieved through the following technical solutions:

[0010] The present invention is a data resource evaluation and management method for industrial manufacturing enterprises. The specific steps for configuring enterprise products are as follows:

[0011] S1. Input product information;

[0012] S2. Perform a first round of screening on product configuration according to the product information combined with the first product demand information;

[0013] The specific steps include:

[0014] S21. Build product demand model and product supply model;

[0015] S22, calculating the first product demand information by using the product demand model to obtain first data; calculating the information in the product information that matches the first product demand information by using the product supply model to obtain second data;

[0016] The first product demand information is calculated by the product demand model to obtain first data; the first product demand information includes product demand information in the information field, product demand information in the product quality field, product demand information in the production and supply field, product demand information in the technical information field, product demand information in the cost information field, product demand information in the market information field, and product demand information in the customer information field;

[0017] The first data is a collection of data including first product demand information;

[0018] Calculate the information in the product information that matches the first product demand information through a product supply model to obtain second data;

[0019] The product information includes name, model, specification, production date, shelf life, material, high temperature resistance, acid and alkali resistance, safety, production quantity per unit time, delivery cycle, inventory, production technology, manufacturing process, research and development progress, production cost, selling price, profit margin, market demand, nature of customers, number of customers and geographical location of customers;

[0020] The second data refers to a set of data required to be used from the product information in order to obtain the first product demand information;

[0021] S23, performing standardization processing on the first data and the second data to obtain standardized first data and standardized second data respectively;

[0022] S24, calculating similarity of the first data after the normalization process and the second data after the normalization process based on a neural network, and selecting products corresponding to the first data whose similarity meets the set threshold condition as candidate products, thereby completing the first round of screening;

[0023] S3, conducting a second round of screening on the candidate products to obtain second round candidate products;

[0024] The specific steps include:

[0025] S31, setting the second product demand information for the second round of screening;

[0026] S32, calculating the second product demand information through the product demand model to obtain third data, and calculating the second product demand information of the candidate products through the product supply model to obtain fourth data;

[0027] Calculating the second product demand information through the product demand model to obtain third data;

[0028] Calculating the second product demand information in the candidate products through the product supply model to obtain fourth data;

[0029] The high temperature resistance dimension, acid and alkali resistance dimension, safety dimension, production quantity dimension, supply cycle dimension, inventory dimension, production cost dimension, selling price dimension, profit margin dimension, customer nature dimension, customer quantity dimension and customer geographical location dimension are set as the second product demand information for the second round of screening;

[0030] The third data is a collection of data including the second product demand information;

[0031] The product supply model refers to a production cycle numerical model with product information, product supply quantity, and product supply cycle; the product supply model is used to represent the specific parameters, supply quantity, and supply cycle of the supplied products;

[0032] The fourth data refers to a set of data required to be used from the product supply model in order to obtain the second product demand information;

[0033] S33. Perform positive processing on the third data to obtain the third data after positive processing, and calculate the objective weight and information amount of each dimension in the product demand model, and then perform mean method processing on the third data after positive processing to obtain the third data after mean method processing, and then calculate the correlation factor between the third data after mean method processing and the fourth data, and perform grey correlation analysis on the third data after mean method processing and the fourth data through the correlation factor, calculate the grey weighted correlation between the third data after mean method processing and the fourth data, and then sort the grey weighted correlation to screen out the required products.

[0034] Preferably, before inputting product information, a step of verifying user identity and authority is also performed;

[0035] The specific steps of verifying user identity and authority are as follows:

[0036] S01. Enter the login page of the product and enter the user name and password;

[0037] S02. After the front end obtains the username and password, it generates a request, adds token information to the request header, and then sends the request to the backend;

[0038] S03. After receiving the request, the backend will first determine whether the request header contains a token. If not, an error message will be returned and the page will be redirected to the login page. If it does, the token will be parsed. After successful parsing, the username and password in the request will be compared with the parsed content of the token.

[0039] S04. After the username and password in the request are successfully compared with the content after the token is parsed, the database is queried, and the username and password in the request are compared with the data in the database. After the comparison is successful, the user is allowed to log in successfully.

[0040] Preferably, the product information includes name, model, specifications, production date, shelf life, material, high temperature resistance, acid and alkali resistance, safety, production quantity per unit time, delivery cycle, inventory, production technology, manufacturing process, R&D progress, production cost, selling price, profit margin, market demand size, nature of customers, number of customers and geographical location of customers.

[0041] Preferably, in S21, the building of the product demand model comprises the following steps:

[0042] The product demand model is represented by P k ={X k ,Y k ,Z k |k=1,2,...n1},

[0043] Among them, k is the enterprise product problem solving number, n1 is the total number of enterprise product solution needs, X k The total amount of product demand information in the information field required to solve the k-th product problem, Y k The total amount of product demand information in the technical information field required to solve the k-th product problem, Z k The total number of product demand information in the market information field required to solve the k-th product problem;

[0044] The first product demand information includes product demand information in the information field, product demand information in the product quality field, product demand information in the production and supply field, product demand information in the technical information field, product demand information in the cost information field, product demand information in the market information field and product demand information in the customer information field;

[0045] The product demand information in the information field includes name dimension, model dimension, specification dimension, production date dimension, shelf life dimension, and material dimension;

[0046] The product demand information in the technical information field includes production technology dimension, manufacturing process dimension and R&D progress dimension;

[0047] The product demand information in the market information field includes the dimension of market demand size.

[0048] Preferably, the S22 specifically includes the following steps:

[0049] Assume w i is the value of the i-th dimension in the product demand model, then the first data obtained by the product demand model is expressed as

[0050] Among them, n0 is the total number of dimensions selected in the product demand model in the first round of screening, w i The data value of is an integer between 1 and 5, and W is a set of data values ​​of each dimension selected by the product in the product demand model;

[0051] The product supply model is expressed as The T value calculated by the product supply model forms the second data;

[0052] Among them, t i Represents the value of the i-th dimension in the product supply model, indicating the total number of dimensions selected in the product supply model in the first round of screening. T is the set of data values ​​of each dimension selected by the product in the product supply model, and the data value of ti is an integer between 1 and 5;

[0053] The dimensions in the product supply model include name dimension, model dimension, specification dimension, production date dimension, shelf life dimension, material dimension, production technology dimension, manufacturing process dimension, R&D progress dimension and market demand size dimension.

[0054] Preferably, S23 specifically includes the following steps:

[0055] The method adopted for the standardization process is the Z-score method. Let the W data set and the T data set after the standardization process be W' and T', W' represents the first data after the standardization process, and T' represents the second data after the standardization process;

[0056] but

[0057]

[0058] Where: w i is the value of the i-th dimension in the W data set, t i is the value of the i-th dimension in the T data set, μ W is the mean of each dimension of the W dataset, μ Tis the mean of each dimension of the T data set, σ W is the standard deviation of each dimension of the W data set, σ T is the standard deviation of each dimension of the T data set, w i ' and t i 'respectively w i and t i The value obtained after standardization.

[0059] Preferably, S24 specifically includes the following steps:

[0060] The similarity calculation between W' and T' includes the following steps:

[0061] S241, normalize W' and T' to obtain W" and T, represents the first data after normalization, represents the second data after normalization; wherein w i ”,t i ”∈[0,1],0≤|w” i -t" i |≤1 and i∈{1,2,...,n0};

[0062] S242, randomly extract 10% of the data from the W" data set N is a natural number set, W" x As a training sample set;

[0063] S243, using cotangent similarity to calculate the training sample set W" x The average similarity between each data in T" and all data in T", set

[0064] in:

[0065]

[0066] Representation data With data set T' x The average similarity between x As the expected output, x i ∈{x1,x2,...,x s}, j1∈{1,2,...,n0};

[0067] S244, input the training set W" to the initialized BP neural network x and the expected output Y x , train the network model until the network model converges to an error accuracy less than 0.001, and obtain a trained network model;

[0068] S245, input the complete data set W" into the trained network model for simulation to obtain the average similarity between all data in the W" data set and T", set as in for The average similarity with the data set T”, j1∈{1,2,...,n0}, n0 is the total number of dimensions selected in the product demand model in the first round of screening;

[0069] S246. Calculate the mean of the average similarity between all data in the W” data set and the data set T” to obtain the similarity simi(W”,T”) between the W” data set and the data set T”. The calculation formula is:

[0070]

[0071] S247. Set a round threshold ρ1, and based on the calculated simi(W”, T”), select products corresponding to simi(W”, T”) that are less than the threshold ρ1 as candidate products.

[0072] The high temperature resistance dimension, acid and alkali resistance dimension, safety dimension, production quantity dimension, supply cycle dimension, inventory dimension, production cost dimension, selling price dimension, profit margin dimension, customer nature dimension, customer quantity dimension and customer geographical location dimension are set as the second product demand information for the second round of screening;

[0073] The S32 specifically includes the following steps:

[0074] W1 represents the third data obtained by calculating the second product demand information by the product demand model, and n3 represents the total number of the second product demand information screened in the second round; T1 represents fourth data obtained by calculating the second product demand information among the candidate products by the product supply model;

[0075] The S33 specifically includes the following steps:

[0076] S331, using a positive method to process the third data to obtain the third data after positive processing

[0077]

[0078] Where: w 1j is the value of the jth dimension in the third data W1, j∈{1,2,...,n3}, w min is the minimum value of the jth dimension in the third data W1 among the candidate products, is the maximum value of the jth dimension in the product demand model among the candidate products, w' 1j w 1j The value after positive processing;

[0079] S332. Calculate the objective weight M of the jth dimension in the product demand model j And the amount of information N j ,

[0080]

[0081]

[0082] Where: r ij is the correlation between the i-th dimension and the j-th dimension in the product demand model, S j is the standard deviation of the j-th dimension value in the product demand model;

[0083] S333, using the mean method to process the third data W'1 after the forward processing, to obtain the third data processed by the mean method

[0084]

[0085] Where: k is the enterprise product problem solving number, k = 1, 2, ..., n1, n1 is the total number of enterprise product solution requirements, w' i (k) is to find the data value of the i-th dimension in W'1 for solving the product problem of the enterprise numbered k, To solve the problem of enterprise product number k, the average value of the data value of the i-th dimension in the product demand model, w i (k) is w' i (k) Data value obtained after dimensionless processing;

[0086] S334, calculating the correlation factor between the third data and the fourth data after the mean value method processing

[0087]

[0088] Where: k = 1, 2, ..., n1, n1 is the total number of enterprise product demand, t(k) is the reference value sequence composed of the data value of the i-th dimension in the fourth data T1 as the reference value for solving the enterprise product problem numbered k, i∈{1, 2, ..., n3}, w i (k) to find the data value of the i-th dimension in the third data W1 for solving the enterprise product problem numbered k;

[0089] S335, calculating the grey weighted correlation between the third data and the fourth data processed by the mean value method through the correlation factor,

[0090]

[0091] Where: n1 is the total number of product demand for the enterprise, M j is the objective weight of the jth dimension in the product demand model, To find the correlation factor of the enterprise product problem numbered k;

[0092] S336. Sort the grey weighted association degrees to screen out the second-round candidate products for selection by decision makers.

[0093] Preferably, the screening process of the second round of candidate products in S336 is as follows:

[0094] The number of alternatives ρ3 is set, and after calculating the correlation factor, the second-round threshold ρ2 is set. The second-round candidate products are sorted according to the calculated gray weighted correlation values, and the first ρ3 second-round candidate products corresponding to the gray weighted correlation greater than the threshold ρ2 are selected for decision makers to choose.

[0095] Preferably, an industrial manufacturing enterprise data resource evaluation and management system comprises an input module, a product preliminary screening module, and a product secondary screening module;

[0096] The input module is used to input product information;

[0097] The product preliminary screening module is used to perform a first round of screening on product configurations according to the product information combined with the first product demand information;

[0098] The product secondary screening module is used to perform a second round of screening on candidate products.

[0099] The present invention has the following beneficial effects:

[0100] 1. In the present invention, by constructing a product demand model and a product supply model, the first and second rounds of screening are performed when configuring products. In the first round of screening, the product name dimension, model dimension, specification dimension, production date dimension, shelf life dimension, material dimension, production technology dimension, manufacturing process dimension, R&D progress dimension and market demand size dimension are scored, and the degree of product demand of the enterprise in the above dimensions is scored. Then, by standardizing the scoring data of the two aspects and calculating the similarity, the degree of matching between the product and the product required by the enterprise in the above dimensions is determined, thereby screening out the first round of products. In the second round of screening, the product's high temperature resistance dimension, acid and alkali resistance dimension, safety dimension, production quantity dimension, etc. are scored. The dimensions of supply cycle, inventory, production cost, selling price, profit margin, nature of customers, quantity of customers and geographical location of customers are scored, as well as the degree of demand for products in the above dimensions. The scored data are then processed using an objective weighting method in combination with a grey correlation analysis method. Finally, the data values ​​are calculated and sorted, thereby screening out the second round of products for enterprise decision makers to choose from. By adopting the above scheme, enterprise decision makers do not need to configure products entirely based on their own subjective judgment, making the process of configuring products more scientific and objective, so that the most suitable products can be purchased to meet the production needs of the enterprise, which is conducive to improving work efficiency and the quality of product purchases.

[0101] 2. In the present invention, according to the requirements of the product in various dimensions, the product information is divided into name, model, specification, production date, shelf life, material, high temperature resistance, acid and alkali resistance, safety, production quantity per unit time, supply cycle, inventory, production technology, manufacturing process, research and development progress, production cost, selling price, profit margin, market demand size, customer nature, number of customers and customer geographical location, so as to have an all-round positioning of the product information, thereby providing a more comprehensive and reliable basis for the purchase of the product.

[0102] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0103] In order to more clearly illustrate the technical solutions of the embodiments of the invention, the drawings required for describing the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the invention. For ordinary technicians in this field, they can also obtain drawings based on these drawings without paying creative work.

[0104] Figure 1 It is a structural schematic diagram of each module in an industrial manufacturing enterprise data resource evaluation and management system of the present invention;

[0105] Figure 2 The present invention is a flowchart of product screening in a method for data resource evaluation and management of industrial manufacturing enterprises. DETAILED DESCRIPTION

[0106] The following will be combined with the drawings in the embodiments of the invention to clearly and completely describe the technical solutions in the embodiments of the invention. Obviously, the described embodiments are only part of the embodiments of the invention, not all of the embodiments. Based on the embodiments in the invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the invention.

[0107] In the description of the present invention, it is necessary to understand that the terms "opening", "upper", "lower", "top", "middle", "inside" and the like indicating orientation or positional relationship are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the components or elements referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as limiting the invention.

[0108] The present invention is a data resource evaluation and management method for industrial manufacturing enterprises. The specific steps for configuring enterprise products are as follows:

[0109] S1. Input product information;

[0110] S2. Perform a first round of screening on product configuration according to the product information combined with the first product demand information;

[0111] The specific steps include:

[0112] S21. Build product demand model and product supply model;

[0113] S22, calculating the first product demand information by using the product demand model to obtain first data; calculating the information in the product information that matches the first product demand information by using the product supply model to obtain second data;

[0114] The first product demand information is calculated by the product demand model to obtain first data; the first product demand information includes product demand information in the information field, product demand information in the product quality field, product demand information in the production and supply field, product demand information in the technical information field, product demand information in the cost information field, product demand information in the market information field, and product demand information in the customer information field;

[0115] The first data is a collection of data including first product demand information;

[0116] Calculate the information in the product information that matches the first product demand information through a product supply model to obtain second data;

[0117] The product information includes name, model, specification, production date, shelf life, material, high temperature resistance, acid and alkali resistance, safety, production quantity per unit time, delivery cycle, inventory, production technology, manufacturing process, research and development progress, production cost, selling price, profit margin, market demand, nature of customers, number of customers and geographical location of customers;

[0118] The second data refers to a set of data required to be used from the product information in order to obtain the first product demand information;

[0119] S23, performing standardization processing on the first data and the second data to obtain standardized first data and standardized second data respectively;

[0120] S24, calculating similarity of the first data after the normalization process and the second data after the normalization process based on a neural network, and selecting products corresponding to the first data whose similarity meets the set threshold condition as candidate products, thereby completing the first round of screening;

[0121] S3, conducting a second round of screening on the candidate products to obtain second round candidate products;

[0122] The specific steps include:

[0123] S31, setting the second product demand information for the second round of screening;

[0124] S32, calculating the second product demand information through the product demand model to obtain third data, and calculating the second product demand information of the candidate products through the product supply model to obtain fourth data;

[0125] Calculating the second product demand information through the product demand model to obtain third data;

[0126] Calculating the second product demand information in the candidate products through the product supply model to obtain fourth data;

[0127] The high temperature resistance dimension, acid and alkali resistance dimension, safety dimension, production quantity dimension, supply cycle dimension, inventory dimension, production cost dimension, selling price dimension, profit margin dimension, customer nature dimension, customer quantity dimension and customer geographical location dimension are set as the second product demand information for the second round of screening;

[0128] The third data is a collection of data including the second product demand information;

[0129] The product supply model refers to a production cycle numerical model with product information, product supply quantity, and product supply cycle; the product supply model is used to represent the specific parameters, supply quantity, and supply cycle of the supplied products;

[0130] The fourth data refers to a set of data required to be used from the product supply model in order to obtain the second product demand information;

[0131] S33. Perform positive processing on the third data to obtain the third data after positive processing, and calculate the objective weight and information amount of each dimension in the product demand model, and then perform mean method processing on the third data after positive processing to obtain the third data after mean method processing, and then calculate the correlation factor between the third data after mean method processing and the fourth data, and perform grey correlation analysis on the third data after mean method processing and the fourth data through the correlation factor, calculate the grey weighted correlation between the third data after mean method processing and the fourth data, and then sort the grey weighted correlation to screen out the required products.

[0132] Furthermore, before entering product information, a step of verifying user identity and authority is performed;

[0133] The specific steps of verifying user identity and authority are as follows:

[0134] S01. Enter the login page of the product and enter the user name and password;

[0135] S02. After the front end obtains the username and password, it generates a request, adds token information to the request header, and then sends the request to the backend;

[0136] S03. After receiving the request, the backend will first determine whether the request header contains a token. If not, an error message will be returned and the page will be redirected to the login page. If it does, the token will be parsed. After successful parsing, the username and password in the request will be compared with the parsed content of the token.

[0137] S04. After the username and password in the request are successfully compared with the content after the token is parsed, the database is queried, and the username and password in the request are compared with the data in the database. After the comparison is successful, the user is allowed to log in successfully.

[0138] The implementation method of the above scheme is specifically that token is defined as an encrypted string composed of characters.

[0139] Furthermore, the product information includes name, model, specifications, production date, shelf life, material, high temperature resistance, acid and alkali resistance, safety, production quantity per unit time, delivery cycle, inventory, production technology, manufacturing process, R&D progress, production cost, selling price, profit margin, market demand size, customer nature, number of customers and the geographical location of customers.

[0140] Furthermore, in S21, the building of the product demand model includes the following steps:

[0141] The product demand model is represented by P k ={X k ,Y k ,Z k |k=1,2,...n1},

[0142] Among them, k is the enterprise product problem solving number, n1 is the total number of enterprise product solution needs, X k The total amount of product demand information in the information field required to solve the k-th product problem, Y k The total amount of product demand information in the technical information field required to solve the k-th product problem, Z k The total number of product demand information in the market information field required to solve the k-th product problem;

[0143] The first product demand information includes product demand information in the information field, product demand information in the product quality field, product demand information in the production and supply field, product demand information in the technical information field, product demand information in the cost information field, product demand information in the market information field and product demand information in the customer information field;

[0144] The product demand information in the information field includes name dimension, model dimension, specification dimension, production date dimension, shelf life dimension, and material dimension;

[0145] The product demand information in the technical information field includes production technology dimension, manufacturing process dimension and R&D progress dimension;

[0146] The product demand information in the market information field includes the market demand size dimension;

[0147] The S22 specifically includes the following steps:

[0148] Assume w i is the value of the i-th dimension in the product demand model, then the first data obtained by the product demand model is expressed as

[0149] Among them, n0 is the total number of dimensions selected in the product demand model in the first round of screening, w iThe data value of is an integer between 1 and 5, and W is a set of data values ​​of each dimension selected by the product in the product demand model;

[0150] The product supply model is expressed as

[0151] The T value calculated by the product supply model forms the second data;

[0152] Among them, ti represents the value of the i-th dimension in the product supply model, represents the total number of dimensions selected in the product supply model in the first round of screening, T is the set of data values ​​of each dimension selected by the product in the product supply model, and t i The data value of is an integer between 1 and 5;

[0153] The dimensions in the product supply model include name dimension, model dimension, specification dimension, production date dimension, shelf life dimension, material dimension, production technology dimension, manufacturing process dimension, R&D progress dimension, and market demand size dimension;

[0154] S23 specifically includes the following steps:

[0155] The method adopted for the standardization process is the Z-score method. Let the W data set and the T data set after the standardization process be W' and T', W' represents the first data after the standardization process, and T' represents the second data after the standardization process;

[0156] but

[0157]

[0158] Where: w i is the value of the i-th dimension in the W data set, t i is the value of the i-th dimension in the T data set, μ W is the mean of each dimension of the W dataset, μ T is the mean of each dimension of the T data set, σ W is the standard deviation of each dimension of the W data set, σ T is the standard deviation of each dimension of the T data set, w i ' and t i 'respectively w i and t i The numerical value obtained after the standardization process, S24 specifically includes the following steps:

[0159] The similarity calculation between W' and T' includes the following steps:

[0160] S241, normalize W' and T' to obtain W" and T, represents the first data after normalization, represents the second data after normalization; wherein w i ”,t i ”∈[0,1],0≤|w” i -t" i |≤1 and i∈{1,2,...,n0};

[0161] S242, randomly extract 10% of the data from the W" data set N is a natural number set, W" x As a training sample set;

[0162] S243, using cotangent similarity to calculate the training sample set W" x The average similarity between each data in T" and all data in T", set

[0163] in:

[0164]

[0165] Representation data With data set T' x The average similarity between x As the expected output, x i ∈{x1,x2,...,x s}, j1∈{1,2,...,n0};

[0166] S244, input the training set W" to the initialized BP neural network x and the expected output Y x , train the network model until the network model converges to an error accuracy less than 0.001, and obtain a trained network model;

[0167] S245, input the complete data set W" into the trained network model for simulation to obtain the average similarity between all data in the W" data set and T", set as in for The average similarity with the data set T”, j1∈{1,2,...,n0}, n0 is the total number of dimensions selected in the product demand model in the first round of screening;

[0168] S246. Calculate the mean of the average similarity between all data in the W” data set and the data set T” to obtain the similarity simi(W”,T”) between the W” data set and the data set T”. The calculation formula is:

[0169]

[0170] S247. Set a round threshold ρ1, and based on the calculated simi(W”, T”), select products corresponding to simi(W”, T”) that are less than the threshold ρ1 as candidate products.

[0171] The implementation method of the above scheme is specifically as follows: in the first round of screening, the product name dimension, model dimension, specification dimension, production date dimension, shelf life dimension, material dimension, production technology dimension, manufacturing process dimension, R&D progress dimension and market demand size dimension are scored, and the demand degree of the demand side's product in the above dimensions is scored. Then, by standardizing the scoring data of both aspects and calculating the similarity, the matching degree between the provider's product and the demand side's product in the above dimensions is determined, thereby screening out the first round of products.

[0172] Furthermore, the high temperature resistance dimension, the acid and alkali resistance dimension, the safety dimension, the production quantity dimension, the supply cycle dimension, the inventory dimension, the production cost dimension, the selling price dimension, the profit margin dimension, the customer nature dimension, the customer quantity dimension and the customer geographical location dimension are set as the second product demand information for the second round of screening;

[0173] The S32 specifically includes the following steps:

[0174] W1 represents the third data obtained by calculating the second product demand information by the product demand model, and n3 represents the total number of the second product demand information screened in the second round; T1 represents fourth data obtained by calculating the second product demand information among the candidate products by the product supply model;

[0175] The S33 specifically includes the following steps:

[0176] S331, using a positive method to process the third data to obtain the third data after positive processing

[0177]

[0178] Where: w 1j is the value of the jth dimension in the third data W1, j∈{1,2,...,n3}, w min is the minimum value of the jth dimension in the third data W1 among the candidate products, is the maximum value of the jth dimension in the product demand model among the candidate products, w' 1j w 1j The value after positive processing;

[0179] S332. Calculate the objective weight M of the jth dimension in the product demand model j And the amount of information N j ,

[0180]

[0181]

[0182] Where: r ij is the correlation between the i-th dimension and the j-th dimension in the product demand model, S j is the standard deviation of the j-th dimension value in the product demand model;

[0183] S333, using the mean method to process the third data W'1 after the forward processing, to obtain the third data processed by the mean method

[0184]

[0185] Where: k is the enterprise product problem solving number, k = 1, 2, ..., n1, n1 is the total number of enterprise product solution requirements, w' i (k) is to find the data value of the i-th dimension in W'1 for solving the product problem of the enterprise numbered k, To solve the problem of enterprise product number k, the average value of the data value of the i-th dimension in the product demand model, w i (k) is w' i (k) Data value obtained after dimensionless processing;

[0186] S334, calculating the correlation factor between the third data and the fourth data after the mean value method processing

[0187]

[0188] Where: k = 1, 2, ..., n1, n1 is the total number of enterprise product demand, t(k) is the reference value sequence composed of the data value of the i-th dimension in the fourth data T1 as the reference value for solving the enterprise product problem numbered k, i∈{1, 2, ..., n3}, w i (k) to find the data value of the i-th dimension in the third data W1 for solving the enterprise product problem numbered k;

[0189] S335, calculating the grey weighted correlation between the third data and the fourth data processed by the mean value method through the correlation factor,

[0190]

[0191] Where: n1 is the total number of product demand for the enterprise, M j is the objective weight of the jth dimension in the product demand model, To find the correlation factor of the enterprise product problem numbered k;

[0192] S336, sorting the grey weighted association degrees to screen out the second round candidate products for selection by decision makers. The screening process of the second round candidate products in S336 is as follows:

[0193] The number of alternatives ρ3 is set, and after calculating the correlation factor, the second-round threshold ρ2 is set. The second-round candidate products are sorted according to the calculated gray weighted correlation values, and the first ρ3 second-round candidate products corresponding to the gray weighted correlation greater than the threshold ρ2 are selected for decision makers to choose.

[0194] The implementation method of the above scheme is specifically as follows: the value of the adjustment factor θ is between 0 and 1, and θ=0.5 is generally taken. In the second round of screening, the high temperature resistance dimension, acid and alkali resistance dimension, safety dimension, production quantity dimension, supply cycle dimension, inventory dimension, production cost dimension, selling price dimension, profit margin dimension, customer nature dimension, customer quantity dimension and customer geographical location dimension of the provider's product are scored, and the demand degree of the demand side's product in the above dimensions is scored. Then, the scoring data is processed using an objective weighting method and a gray correlation analysis method. Finally, the data values ​​are calculated and sorted, so as to screen out the second round of products for enterprise decision makers to choose. By adopting the above scheme, enterprise decision makers do not need to configure products entirely based on their own subjective judgment, making the process of configuring products more scientific and objective, so that the most suitable products can be configured for purchase, which is conducive to improving work efficiency and the completion quality of product purchases.

[0195] Further, an industrial manufacturing enterprise data resource evaluation and management system includes an input module, a product preliminary screening module, and a product secondary screening module;

[0196] The input module is used to input product information;

[0197] The product preliminary screening module is used to perform a first round of screening on product configurations according to the product information combined with the first product demand information;

[0198] The product secondary screening module is used to perform a second round of screening on candidate products.

[0199] The implementation method of the above scheme is specifically to deploy the industrial manufacturing enterprise data resource evaluation and management system in the present invention into a cloud environment, and use cloud computing technology to calculate the configuration of the above products.

[0200] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0201] The preferred embodiments of the invention disclosed above are only used to help explain the invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the invention, so that those skilled in the art can understand and use the invention well.

Claims

1. A data resource evaluation and management method for an industrial manufacturing enterprise, characterized by: The specific steps for configuring enterprise products are as follows: S1. Input product information; S2. Perform a first round of screening on product configuration according to the product information combined with the first product demand information; The specific steps include: S21. Build product demand model and product supply model; The product demand model is represented by P k ={X k ,Y k ,Z k |k=1,2,...n1}, Among them, k is the enterprise product problem solving number, n1 is the total number of enterprise product solution needs, X k The total amount of product demand information in the information field required to solve the k-th product problem, Y k The total amount of product demand information in the technical information field required to solve the k-th product problem, Z k The total number of product demand information in the market information field required to solve the k-th product problem; S22. Calculate the first product demand information by using the product demand model to obtain first data; the first product demand information includes product demand information in the information field, product demand information in the product quality field, product demand information in the production and supply field, product demand information in the technical information field, product demand information in the cost information field, product demand information in the market information field, and product demand information in the customer information field; The first data is a collection of data including first product demand information; Calculate the information in the product information that matches the first product demand information through a product supply model to obtain second data; The product information includes name, model, specification, production date, shelf life, material, high temperature resistance, acid and alkali resistance, safety, production quantity per unit time, delivery cycle, inventory, production technology, manufacturing process, research and development progress, production cost, selling price, profit margin, market demand, nature of customers, number of customers and geographical location of customers; The second data refers to a set of data required to be used from the product information in order to obtain the first product demand information; S23, performing standardization processing on the first data and the second data to obtain standardized first data and standardized second data respectively; S24, calculating similarity of the first data after the normalization process and the second data after the normalization process based on a neural network, and selecting products corresponding to the first data whose similarity meets the set threshold condition as candidate products, thereby completing the first round of screening; S3, conducting a second round of screening on the candidate products to obtain second round candidate products; The specific steps include: S31, setting the second product demand information for the second round of screening; S32, calculating the second product demand information through the product demand model to obtain third data, specifically including the following steps: satisfying; W1 represents the third data obtained by calculating the second product demand information by the product demand model, and n3 represents the total number of the second product demand information screened in the second round; T1 represents fourth data obtained by calculating the second product demand information among the candidate products by the product supply model; Calculating the second product demand information in the candidate products through the product supply model to obtain fourth data; The high temperature resistance dimension, acid and alkali resistance dimension, safety dimension, production quantity dimension, supply cycle dimension, inventory dimension, production cost dimension, selling price dimension, profit margin dimension, customer nature dimension, customer quantity dimension and customer geographical location dimension are set as the second product demand information for the second round of screening; The third data is a collection of data including the second product demand information; The product supply model refers to a production cycle numerical model with product information, product supply quantity, and product supply cycle; the product supply model is used to represent the specific parameters, supply quantity, and supply cycle of the supplied products; The fourth data refers to a set of data required to be used from the product supply model in order to obtain the second product demand information; S33, preprocessing the third data to obtain the third data processed by the mean method; calculating the correlation factor between the third data processed by the mean method and the fourth data, and performing grey correlation analysis on the third data processed by the mean method and the fourth data through the correlation factor, calculating the grey weighted correlation between the third data processed by the mean method and the fourth data, and then sorting the grey weighted correlation to screen out the desired products, specifically comprising the following steps: S331, using a positive method to process the third data to obtain the third data after positive processing Where: w 1j is the value of the jth dimension in the third data W1, j∈{1,2,...,n3}, w min is the minimum value of the jth dimension in the third data W1 among the candidate products, is the maximum value of the jth dimension in the product demand model among the candidate products, w' 1j for e 1j The value after positive processing; S332. Calculate the objective weight M of the jth dimension in the product demand model j And the amount of information N j , Where: r ij is the correlation between the i-th dimension and the j-th dimension in the product demand model, S j is the standard deviation of the j-th dimension value in the product demand model; S333, using the mean method to process the third data W'1 after the forward processing, to obtain the third data processed by the mean method Where: k is the enterprise product problem solving number, k = 1, 2, ..., n1, n1 is the total number of enterprise product solution requirements, w' i (k) is to find the data value of the i-th dimension in W'1 for solving the product problem of the enterprise numbered k, To solve the problem of enterprise product number k, the average value of the data value of the i-th dimension in the product demand model, w i (k) is w' i (k) Data value obtained after dimensionless processing; S334, calculating the correlation factor between the third data and the fourth data after the mean value method processing Where: k = 1, 2, ..., n1, n1 is the total number of enterprise product demand, t(k) is the reference value sequence composed of the data value of the i-th dimension in the fourth data T1 as the reference value for solving the enterprise product problem numbered k, i∈{1, 2, ..., n3}, w i (k) to find the data value of the i-th dimension in the third data W1 for solving the enterprise product problem numbered k; S335, calculating the grey weighted correlation between the third data and the fourth data processed by the mean value method through the correlation factor, Where: n1 is the total number of product demand for the enterprise, M j is the objective weight of the jth dimension in the product demand model, To find the correlation factor of the enterprise product problem numbered k; S336. Sort the grey weighted association degrees to screen out the second-round candidate products for selection by decision makers.

2. The method for evaluating and managing data resources of an industrial manufacturing enterprise according to claim 1, characterized in that: Step S1 specifically includes: S01. Enter the login page of the product and enter the user name and password; S02. After the front end obtains the username and password, it generates a request, adds token information to the request header, and then sends the request to the backend; S03. After receiving the request, the backend will first determine whether the request header contains a token. If not, an error message will be returned and the page will be redirected to the login page. If it does, the token will be parsed. After successful parsing, the username and password in the request will be compared with the parsed content of the token. S04. After the username and password in the request are successfully compared with the parsed content of the token, the database is queried, and the username and password in the request are compared with the data in the database. After the comparison is successful, the user is allowed to log in successfully. S05. Input product information.

3. The method for evaluating and managing data resources of an industrial manufacturing enterprise according to claim 1, characterized in that: The S22 specifically includes the following steps: Assume w i is the value of the i-th dimension in the product demand model, then the first data obtained by the product demand model is expressed as Among them, n0 is the total number of dimensions selected in the product demand model in the first round of screening, and W is the set of data values ​​of each dimension selected by the product in the product demand model; The product supply model is expressed as The T value calculated by the product supply model forms the second data; Among them, t i represents the value of the i-th dimension in the product supply model, represents the total number of dimensions selected in the product supply model in the first round of screening, and T is the set of data values ​​of each dimension selected by the product in the product supply model; S23 specifically includes the following steps: The method adopted for the standardization process is the Z-score method. Let the W data set and the T data set after the standardization process be W' and T', W' represents the first data after the standardization process, and T' represents the second data after the standardization process; but Where: w i is the value of the i-th dimension in the W data set, t i is the value of the i-th dimension in the T data set, μ W is the mean of each dimension of the W dataset, μ T is the mean of each dimension of the T data set, σ W is the standard deviation of each dimension of the W data set, σ T is the standard deviation of each dimension of the T data set, w i ' and t i 'respectively w i and t i The value obtained after standardization.

4. The method for evaluating and managing data resources of an industrial manufacturing enterprise according to claim 3 is characterized in that: S24 specifically includes the following steps: The similarity calculation between W' and T' includes the following steps: S241, perform normalization operation on W' and T' to obtain W" and T, represents the first data after normalization, represents the second data after normalization; wherein w i ”,t i ”∈[0,1],0≤|w″ i -t″ i |≤1 and i∈{1,2,...,n0}; S242, randomly extract 10% of the data from the W" data set x1,x2,...,x s ∈N, N is a natural number set, W″ x As a training sample set; S243, using cotangent similarity to calculate training sample set W″ x The average similarity between each data in T" and all data in T", set in: Representation data With the data set T″ x The average similarity between x As the expected output, x i ∈{x1,x2,...,x s }, j1∈{1,2,...,n0}; S244, input training set W″ to the initialized BP neural network x and the expected output Y x , train the network model until the network model converges to obtain a trained network model; S245, input the complete data set W" into the trained network model for simulation to obtain the average similarity between all data in the W" data set and T", set as in for The average similarity with the data set T”, j1∈{1,2,...,n0}, n0 is the total number of dimensions selected in the product demand model in the first round of screening; S246. Calculate the mean of the average similarity between all data in the W” data set and the data set T” to obtain the similarity simi(W”,T”) between the W” data set and the data set T”. The calculation formula is: S247. Set a round threshold ρ1, and based on the calculated simi(W”, T”), select products corresponding to simi(W”, T”) that are less than the threshold ρ1 as candidate products.

5. The method for evaluating and managing data resources of an industrial manufacturing enterprise according to claim 1, characterized in that: The screening process of the second round of candidate products described in S336 is as follows: The number of alternatives ρ3 is set, and after calculating the correlation factor, the second-round threshold ρ2 is set. The second-round candidate products are sorted according to the calculated gray weighted correlation values, and the first ρ3 second-round candidate products corresponding to the gray weighted correlation greater than the threshold ρ2 are selected for decision makers to choose.

6. An industrial manufacturing enterprise data resource evaluation management system, used to implement an industrial manufacturing enterprise data resource evaluation management method as claimed in any one of claims 1 to 5, characterized in that: It includes input module, product preliminary screening module and product secondary screening module; The input module is used to input product information; The product preliminary screening module is used to perform a first round of screening on product configurations according to the product information combined with the first product demand information; The product secondary screening module is used to perform a second round of screening on candidate products.

Images