Service-oriented manufacturing product service configuration optimization method and system

Abstract

The present invention provides a method and system for optimizing the configuration of service-oriented manufacturing products and services, and relates to the field of service configuration optimization. The present invention constructs a confidence rule base through a set of premise attributes; initializes a product service configuration scheme set and a confidence rule base parameter set, and determines the reference level of each premise attribute; calculates the matching degree between the new product premise attributes and the reference level of each premise attribute in the customer premise attribute set; calculates the activation weight of each rule in the rule base for the new product and customer information set based on the confidence rule base parameter set and the matching degree; fuses the rules in the confidence rule base according to the activation weight, calculates the confidence level of each product service configuration decision, and obtains the optimal product service configuration decision scheme. The present invention qualitatively describes product information and customer information in the actual environment by establishing a confidence rule base, thereby achieving a qualitative description of product information and customer information in the actual environment and obtaining a product service configuration decision scheme that is close to reality.

Description

Technical Field

[0001] The present invention relates to the technical field of service configuration optimization, and in particular to a method and system for optimizing the service configuration of a service-oriented manufacturing product. Background Art

[0002] Product-service configuration is a crucial issue for service-oriented manufacturing enterprises as they transform and upgrade, effectively improve their supply systems, and adapt to evolving consumption patterns. Compared to the traditional independent provision of products and services, optimizing product-service configuration poses significant challenges due to the significant disparity between product and customer information. The relationship between product-service configuration solutions and customer needs is difficult to quantitatively analyze using precise mathematical models. As traditional manufacturing becomes increasingly service-oriented, addressing the diverse and ambiguous nature of personalized products and customer needs, developing new models to analyze and optimize product-service configuration has become increasingly important.

[0003] Existing research generally establishes configuration models based on performance, cost, and delivery time within module and objective constraints, then solves these models using an improved non-dominated sorting genetic algorithm to obtain optimized results. Alternatively, a modular product configuration optimization method based on an improved weighted sum algorithm has been developed. Each of these approaches has its own advantages and disadvantages. However, in real-world environments, product and customer information is difficult to accurately and quantitatively describe due to its heterogeneity and ambiguity. These approaches fail to account for this issue, resulting in models that are not well-suited to real-world situations and a discrepancy between the service configuration optimization results and actual conditions. Summary of the Invention

[0004] (1) Technical problems solved

[0005] In response to the shortcomings of the existing technology, the present invention provides a service configuration optimization method and system for service-oriented manufacturing products, which solves the technical problem that the model proposed by the existing method is not applicable to the actual situation, resulting in a deviation between the service configuration optimization results and the actual situation.

[0006] (2) Technical solution

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0008] In a first aspect, the present invention provides a method for optimizing service configuration of a service-oriented manufacturing product, comprising:

[0009] S1. Acquire a set of prerequisite attributes based on historical product information and historical user information;

[0010] S2. Building a confidence rule base based on the premise attribute set;

[0011] S3. Initialize the product service configuration solution set and the confidence rule base parameter set, and determine the reference level of each premise attribute;

[0012] S4. Calculate the matching degree between the new product premise attribute and the reference level of each premise attribute in the customer premise attribute set;

[0013] S5. Based on the confidence rule base parameter set and the matching degree, calculating the activation weight of each rule in the rule base for the new product premise attribute and customer premise attribute set;

[0014] S6. According to the activation weight, the rules in the confidence rule base are integrated, the confidence of each product service configuration decision is calculated, the confidence of each configuration decision is compared, and the product service configuration decision solution with the largest confidence is taken as the optimization result.

[0015] Preferably, the constructing of a confidence rule base based on the premise attribute set includes:

[0016]

[0017]

[0018] Then{(D1,β 1,k ),(D2,β 2,k ),…,(D N ,β N,k )}

[0019] Where: R k is the kth rule of the confidence rule optimization inference model;

[0020] z 1,1 ,z 1,2 ,…,z 1,S and z 2,1 ,z 2,2 ,…,z 2,T They represent the values ​​of the product premise attribute and the customer premise attribute in the kth rule of the confidence library respectively;

[0021] D={D1,D2,D3…,D N} represents the set of product service configuration decision solutions, and N represents the total number of all possible configuration solutions;

[0022] β j,k Indicates the decision plan D in the kth rule relative to the jth j Confidence level, and

[0023] Preferably, calculating the matching degree between the new product prerequisite attribute and the reference level of each prerequisite attribute in the customer prerequisite attribute set includes:

[0024] S401, obtaining a new set of product and customer information;

[0025] S402: Compare the new product prerequisite attributes with the reference level of each prerequisite attribute in the customer prerequisite attribute set to calculate the individual matching degree;

[0026] S403: Go through the entire database to obtain the matching degree distribution of the new product premise attribute and customer premise attribute set and each premise attribute.

[0027] Preferably, comparing the new product prerequisite attribute with the reference level of each prerequisite attribute in the customer prerequisite attribute set to calculate the individual matching degree includes:

[0028] For product prerequisite attributes:

[0029]

[0030]

[0031]

[0032] For customer premise attributes:

[0033]

[0034]

[0035]

[0036] in:

[0037] represents the individual matching degree of the premise attributes of the p-th reference level product;

[0038] represents the individual matching degree of the premise attributes of the qth reference level customer;

[0039] z' 1,s Indicates the prerequisite attribute reference value of the new product information;

[0040] z' 2,t Indicates the prerequisite attribute reference value of the new customer information;

[0041] Represents the premise attribute X s The value corresponding to the pth reference level;

[0042] Represents the premise attribute Y t The value corresponding to the qth reference level.

[0043] Preferably, the calculation of the activation weight of each rule in the rule base for the new product premise attribute and customer premise attribute set based on the confidence rule base parameter set and the matching degree includes:

[0044] calculate δ i is the weight of the i-th premise attribute;

[0045] Calculate the activation weight of each rule for the new product premise attribute and customer premise attribute set z:

[0046]

[0047] Among them, ω k ∈[0,1],k=1,2,…,L;θ k Indicates the rule weight of the kth rule.

[0048] Preferably, the rules in the confidence rule base are integrated according to the activation weights to calculate the confidence level of each product service configuration decision, including:

[0049] The L rules in the rule base are integrated and the product service configuration solution D is obtained through the evidence reasoning algorithm. j Confidence

[0050]

[0051] in:

[0052]

[0053] Obtain product service configuration decisions and their confidence distributions;

[0054]

[0055] Where: S(x) represents the set of confidence levels for each product service configuration decision.

[0056] In a second aspect, the present invention provides a service-oriented manufacturing product service configuration optimization system, comprising:

[0057] A prerequisite attribute set acquisition module is used to acquire a prerequisite attribute set based on historical product information and historical user information;

[0058] A confidence rule base construction module is used to construct a confidence rule base based on a set of premise attributes;

[0059] The reference level determination module is used to initialize the product service configuration solution set and the confidence rule base parameter set, and determine the reference level of each premise attribute;

[0060] A matching degree acquisition module calculates the matching degree between the new product premise attribute and the reference level of each premise attribute in the customer premise attribute set;

[0061] An activation weight calculation module is used to calculate the activation weight of each rule in the rule base for the new product premise attribute and customer premise attribute set based on the confidence rule base parameter set and matching degree;

[0062] The optimal product service configuration decision solution acquisition module is used to fuse the rules in the confidence rule base according to the activation weight, calculate the confidence of each product service configuration decision, compare the confidence of each configuration decision, and take the product service configuration decision solution with the largest confidence as the optimization result.

[0063] Preferably, the constructing of a confidence rule base based on the premise attribute set includes:

[0064]

[0065]

[0066] Then{(D1,β 1,k ),(D2,β 2,k ),…,(D N ,β N,k )}

[0067] Where: R k is the kth rule of the confidence rule optimization inference model;

[0068] z 1,1 ,z 1,2 ,…,z 1,S and z 2,1 ,z 2,2 ,…,z 2,T They represent the values ​​of the product premise attribute and the customer premise attribute in the kth rule of the confidence library respectively;

[0069] D={D1,D2,D3…,D N} represents the set of product service configuration decision solutions, and N represents the total number of all possible configuration solutions;

[0070] β j,k Indicates the decision plan D in the kth rule relative to the jth j Confidence level, and

[0071] Preferably, calculating the matching degree between the new product prerequisite attribute and the reference level of each prerequisite attribute in the customer prerequisite attribute set includes:

[0072] S401, obtaining a new set of product and customer information;

[0073] S402: Compare the new product prerequisite attributes with the reference level of each prerequisite attribute in the customer prerequisite attribute set to calculate the individual matching degree;

[0074] S403: Go through the entire database to obtain the matching degree distribution of the new product premise attribute and customer premise attribute set and each premise attribute.

[0075] Preferably, comparing the new product prerequisite attribute with the reference level of each prerequisite attribute in the customer prerequisite attribute set to calculate the individual matching degree includes:

[0076] For product prerequisite attributes:

[0077]

[0078]

[0079]

[0080] For customer premise attributes:

[0081]

[0082]

[0083]

[0084] in:

[0085] represents the individual matching degree of the premise attributes of the p-th reference level product;

[0086] represents the individual matching degree of the premise attributes of the qth reference level customer;

[0087] z' 1,s Indicates the prerequisite attribute reference value of the new product information;

[0088] z' 2,t Indicates the prerequisite attribute reference value of the new customer information;

[0089] Represents the premise attribute X s The value corresponding to the pth reference level;

[0090] Represents the premise attribute Y t The value corresponding to the qth reference level.

[0091] (3) Beneficial effects

[0092] The present invention provides a method and system for optimizing service configuration for service-oriented manufacturing products. Compared with the existing technology, it has the following advantages:

[0093] The present invention obtains a set of premise attributes based on historical product information and historical user information; constructs a confidence rule base based on the premise attribute set; initializes a set of product and service configuration solutions and a set of confidence rule base parameters, and determines a reference level for each premise attribute; calculates the matching degree between the new product premise attributes and the reference level of each premise attribute in the customer premise attribute set; calculates the activation weight of each rule in the rule base for the new product premise attributes and the customer premise attribute set based on the confidence rule base parameter set and the matching degree; fuses the rules in the confidence rule base according to the activation weight, calculates the confidence level of each product and service configuration decision, compares the confidence levels of each configuration decision, and uses the corresponding product and service configuration decision solution as the optimization result. The present invention qualitatively describes product information and customer information in the actual environment by establishing a confidence rule base, thereby achieving a qualitative description of product information and customer information in the actual environment and obtaining a product and service configuration decision solution that is close to reality. BRIEF DESCRIPTION OF THE DRAWINGS

[0094] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0095] Figure 1 This is a flowchart of a service configuration optimization method for a service-oriented manufacturing product according to an embodiment of the present invention. DETAILED DESCRIPTION

[0096] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention are clearly and completely described. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0097] The embodiments of the present application provide a method and system for optimizing the service configuration of service-oriented manufacturing products, thereby solving the problem that the models proposed by existing methods are not applicable to the actual situation, resulting in a deviation between the service configuration optimization results and the actual situation. It achieves qualitative description of product information and customer information in the actual environment, and obtains a product service configuration decision plan that is close to reality.

[0098] The technical solution in the embodiments of the present application is to solve the above technical problems, and the overall idea is as follows:

[0099] Existing methods for optimizing product and service configurations in service-oriented manufacturing generally include the following: 1. A configuration model is established with performance, cost, and delivery time as targets within module and objective constraints, and an improved non-dominated sorting genetic algorithm is used to solve the optimization results. 2. A hierarchical analysis method is used to calculate weights in modular product configuration design based on an improved weighted sum algorithm. 3. Considering the correlation between product manufacturing and service provision, the product and service system solution configuration process under supply and demand interaction is characterized, and a bilevel programming model is constructed to maximize customer satisfaction and minimize enterprise operating costs, which is then solved using a genetic algorithm. None of these methods consider the heterogeneity and ambiguity of a company's product and customer information, making it difficult to accurately and quantitatively describe them. When faced with specific practical problems, the product and service configuration decision solutions derived from these methods often deviate from reality.

[0100] Based on the above problems, an embodiment of the present invention proposes a service-oriented manufacturing product service configuration optimization method based on a confidence rule base. This method constructs a confidence rule base to qualitatively describe product information and customer information in the actual environment, and solves the product service configuration optimization problem based on the characteristics of the differences and ambiguity of product and customer information in real situations. The solution of the embodiment of the present invention is closer to the actual process and has good generalization and practical significance.

[0101] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0102] The embodiment of the present invention provides a method for optimizing service configuration of service-oriented manufacturing products. Figure 1 Shown, including:

[0103] S1. Acquire a set of prerequisite attributes based on historical product information and historical user information;

[0104] S2. Build a confidence rule base based on the premise attribute set;

[0105] S3. Initialize the product service configuration solution set and the confidence rule base parameter set, and determine the reference level of each premise attribute;

[0106] S4. Calculate the matching degree between the new product premise attribute and the reference level of each premise attribute in the customer premise attribute set;

[0107] S5. Based on the confidence rule base parameter set and matching degree, calculate the activation weight of each rule in the rule base for the new product premise attribute and customer premise attribute set;

[0108] S6. According to the activation weight, the rules in the confidence rule base are integrated, the confidence of each product service configuration decision is calculated, the confidence of each configuration decision is compared, and the product service configuration decision solution with the largest confidence is taken as the optimization result.

[0109] The embodiment of the present invention establishes a trust rule base to qualitatively describe product information and customer information in the actual environment, thereby achieving a qualitative description of product information and customer information in the actual environment and obtaining a product service configuration decision plan that is close to reality.

[0110] The following describes each step in detail:

[0111] In step S1, a set of prerequisite attributes is obtained based on historical product information and historical user information. The specific implementation process is as follows:

[0112] Collect historical product information and historical user information. The premise attributes representing product information include product price, product lifespan, etc., and the premise attributes representing customer information include customer asset size, customer historical transaction frequency, etc. The premise attribute sets representing products and customers are {X1, X2, X3, ... X S} and {Y1,Y2,Y3,…Y T}, the sth product attribute and the tth customer attribute are represented by X s and Y t Where S represents the number of product information prerequisite attributes, T represents the number of customer information prerequisite attributes; s = 1, 2, ..., S; t = 1, 2, ..., T.

[0113] In step S2, a confidence rule base is constructed based on the premise attribute set. The specific implementation process is as follows:

[0114]

[0115]

[0116] Then{(D1,β 1,k ),(D2,β 2,k ),…,(D N ,β N,k )}

[0117] Where: R k is the kth rule of the confidence rule optimization inference model; z 1,1 ,z 1,2 ,…,z 1,s and z 2,1 ,z 2,2 ,…,z 2,T They represent the values ​​of product premise attributes and customer premise attributes in the kth rule of the confidence library D={D1,D2,D3…,DN} represents the set of product service configuration decision solutions; N represents the total number of all possible configuration solutions; β j,k (j=1,2,…,N) represents the decision solution D in the kth rule relative to the jth decision solution j Confidence level, and

[0118] In step S3, the product service configuration solution set and the confidence rule base parameter set are initialized, and the reference level of each premise attribute is determined. The specific implementation process is as follows:

[0119] Initialize the product service configuration solution set {D1,…, D N} and the confidence rule base parameter set {θ1,…,θ L ,δ1,…,δ S+T ,β 1,k ,…,β N,k}, and determine the reference level of each premise attribute. For example Indicates the reference level of the s-th product premise attribute, n s Indicates the number of reference levels on the premise attribute of the sth product, using Represents the premise attribute X s The value corresponding to the pth reference level. represents the reference level of the premise attribute of the t-th customer, n t Indicates the number of reference levels on the premise attribute of the t-th customer, using Represents the premise attribute Y t The value corresponding to the qth reference level; θ k (k=1,2,…,L) is defined as the rule weight of the kth rule, L is the total number of rules in the confidence rule base; δ i (i=1, 2, ..., S+T) represents the attribute weight in the kth rule. In the embodiment of the present invention, historical data refers to the enterprise's past customer transaction history data, such as what product configuration decision plan the enterprise adopted when a certain type of customer purchased a certain type of product.

[0120] In step S4, the matching degree between the new product prerequisite attribute and the reference level of each prerequisite attribute in the customer prerequisite attribute set is calculated. The specific implementation process is as follows:

[0121] S401. Obtain a new product and customer information set Z.

[0122] Z={z′ 1,1 ,z′ 1,2 …z′ 1,S ,z′ 2,1 ,z′ 2,2 …z′2,T}.

[0123] S402: Compare the reference level of each premise attribute and calculate the individual matching degree.

[0124] For attribute collections

[0125]

[0126]

[0127]

[0128] For attribute collections

[0129]

[0130]

[0131]

[0132] S403. At this time, the matching degree distribution of the new product premise attributes and customer premise attribute set Z and each premise attribute is obtained throughout the entire database:

[0133]

[0134] For convenience, the following Unified use It means that when m=1, n=s, r=p; when m=2, n=t, r=q.

[0135] In step S5, based on the confidence rule base parameter set and matching degree, the activation weight of each rule in the rule base for the new product premise attribute and customer premise attribute set is calculated. The specific implementation process is as follows:

[0136] calculate δ i is the weight of the i-th premise attribute;

[0137] Calculate the activation weight of each rule for the new product premise attribute and customer premise attribute set z

[0138]

[0139] Among them, ω k ∈[0,1],k=1,2,…,L.

[0140] In step S6, the rules in the confidence rule base are integrated according to the activation weights, the confidence of each product service configuration decision is calculated, and the product service configuration decision solution with the highest confidence is used as the optimization result. The specific implementation process is as follows:

[0141] The L rules in the rule base are integrated and the product service configuration solution D is obtained through the evidence reasoning algorithm. j Confidence

[0142]

[0143] in:

[0144]

[0145] Get the product service configuration decision and its confidence distribution, that is, get the confidence corresponding to each configuration decision:

[0146]

[0147] Compare the confidence of each configuration decision size, The corresponding product service configuration decision plan result is taken as the optimization result.

[0148] An embodiment of the present invention further provides a service-oriented manufacturing product service configuration optimization system, comprising:

[0149] A prerequisite attribute set acquisition module is used to acquire a prerequisite attribute set based on historical product information and historical user information;

[0150] A confidence rule base construction module is used to construct a confidence rule base based on a set of premise attributes;

[0151] The reference level determination module is used to initialize the product service configuration solution set and the confidence rule base parameter set, and determine the reference level of each premise attribute;

[0152] A matching degree acquisition module calculates the matching degree between the new product premise attribute and the reference level of each premise attribute in the customer premise attribute set;

[0153] An activation weight calculation module is used to calculate the activation weight of each rule in the rule base for the new product premise attribute and customer premise attribute set based on the confidence rule base parameter set and matching degree;

[0154] The optimal product service configuration decision solution acquisition module is used to fuse the rules in the confidence rule base according to the activation weight, calculate the confidence of each product service configuration decision, compare the confidence of each configuration decision, and take the product service configuration decision solution with the largest confidence as the optimization result.

[0155] It is understood that the service-oriented manufacturing product service configuration optimization system provided by the embodiment of the present invention corresponds to the above-mentioned service-oriented manufacturing product service configuration optimization method. The explanations, examples, beneficial effects, etc. of its relevant contents can refer to the corresponding contents in the service-oriented manufacturing product service configuration optimization method, and will not be repeated here.

[0156] In summary, compared with the existing technology, the present invention has the following beneficial effects:

[0157] 1. The embodiment of the present invention establishes a trust rule base to qualitatively describe product information and customer information in the actual environment, thereby achieving a qualitative description of product information and customer information in the actual environment and obtaining a product service configuration decision plan that is close to reality.

[0158] 2. This embodiment of the present invention addresses the product and service configuration optimization problem for service-oriented manufacturing enterprises. Based on a confidence rule base and evidential reasoning, it first determines a set of premise attributes representing product and customer information. It then initializes the parameters in the rule base and the product and service configuration decision set based on historical data to complete the construction of a rule-based reasoning model. Using an evidential reasoning algorithm, it calculates the confidence distribution of the final product and service configuration decision plan by calculating individual matching degrees, activation weights, and confidence after information fusion. This model approach can effectively describe actual conditions, optimize product and service configuration issues faced by service-oriented manufacturing industries, and guide enterprise production and operations.

[0159] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0160] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A service-oriented manufacturing product service configuration optimization method, characterized in that: include: S1. Based on historical product information and historical user information, obtain the product premise attribute set and customer premise attribute set; where product premise attributes include product price and product lifespan, and customer premise attributes include customer asset size and customer historical transaction frequency, {X1, X2, X3, ... X S } represents the product premise attribute set, {Y1,Y2,Y3,…Y T } represents the customer premise attribute set, the sth product attribute and the tth customer attribute are represented by X s and Y t Represented by; where S represents the number of product information premise attributes, and T represents the number of customer information premise attributes; s = 1, 2, ..., S; t = 1, 2, ..., T; S2. Building a confidence rule base based on the product premise attribute set and the customer premise attribute set; each rule in the confidence rule base includes a value combination of the product attribute set and the customer attribute set and a confidence level of the corresponding product service configuration solution; S3. Initialize the product service configuration solution set and the confidence rule base parameter set, and determine the reference level of each premise attribute; S4. Calculate the matching degree between the new product premise attribute and the reference level of each premise attribute in the customer premise attribute set; S5. Based on the confidence rule base parameter set and the matching degree, calculating the activation weight of each rule in the rule base for the new product premise attribute and customer premise attribute set; S6. According to the activation weight, the rules in the confidence rule base are integrated, the confidence of each product service configuration decision is calculated, the confidence of each configuration decision is compared, and the product service configuration decision solution with the largest confidence is taken as the optimization result.

2. The service configuration optimization method for service-oriented manufacturing products according to claim 1, characterized in that: The constructing of a confidence rule base based on the product premise attribute set and the customer premise attribute set includes: Then{(D1,β 1,k ),(D2,β 2,k ),…,(D N ,b N,k )} Where: R k is the kth rule of the confidence rule optimization inference model; z 1,1 ,z 1,2 ,…,z 1,S and z 2,1 ,z 2,2 ,…,z 2,T They represent the values ​​of the product premise attribute and the customer premise attribute in the kth rule of the confidence library respectively; D={D1,D2,D3…,D N } represents the set of product service configuration decision solutions, and N represents the total number of all configuration solutions; β j,k Indicates the decision plan D in the kth rule relative to the jth j Confidence level, and 3. The service configuration optimization method for service-oriented manufacturing products according to any one of claims 1 to 2, characterized in that: Calculate the matching degree of the new product premise attribute with the reference level of each premise attribute in the customer premise attribute set, including: S401, obtaining a new set of product and customer information; S402: Compare the new product prerequisite attributes with the reference level of each prerequisite attribute in the customer prerequisite attribute set to calculate the individual matching degree; S403: Go through the entire database to obtain the matching degree distribution of the new product premise attribute and customer premise attribute set and each premise attribute.

4. The service configuration optimization method for service-oriented manufacturing products according to claim 3, characterized in that: Comparing the new product prerequisite attributes with the reference level of each prerequisite attribute in the customer prerequisite attribute set to calculate the individual matching degree includes: For product prerequisite attributes: For customer premise attributes: in: represents the individual matching degree of the premise attributes of the p-th reference level product; represents the individual matching degree of the premise attributes of the qth reference level customer; z′ 1,s Indicates the prerequisite attribute reference value of the new product information; z′ 2,t Indicates the prerequisite attribute reference value of the new customer information; Represents the premise attribute X s The value corresponding to the pth reference level; Represents the premise attribute Y t The value corresponding to the qth reference level.

5. The service configuration optimization method for service-oriented manufacturing products according to any one of claims 1 to 2, characterized in that: The calculation of the activation weight of each rule in the rule base for the new product premise attribute and customer premise attribute set based on the confidence rule base parameter set and the matching degree includes: calculate δ i is the weight of the i-th premise attribute; Calculate the activation weight of each rule for the new product premise attribute and customer premise attribute set z: Among them, ω k ∈[0,1],k=1,2,…,L;θ k Indicates the rule weight of the kth rule.

6. The service configuration optimization method for service-oriented manufacturing products according to claim 5, characterized in that: The rules in the confidence rule base are integrated according to the activation weights to calculate the confidence level of each product service configuration decision, including: The L rules in the rule base are integrated and the product service configuration solution D is obtained through the evidence reasoning algorithm. j Confidence in: Obtain product service configuration decisions and their confidence distributions; Where: S(x) represents the set of confidence levels for each product service configuration decision.

7. A service-oriented manufacturing product service configuration optimization system, characterized in that: include: The premise attribute set acquisition module is used to obtain the product premise attribute set and the customer premise attribute set based on historical product information and historical user information; wherein, the product premise attributes include product price and product lifespan, and the customer premise attributes include customer asset size and customer historical transaction frequency, {X1, X2, X3, ... X S } represents the product premise attribute set, {Y1,Y2,Y3,…Y T } represents the customer premise attribute set, the sth product attribute and the tth customer attribute are represented by X s and Y t Represented by; where S represents the number of product information premise attributes, and T represents the number of customer information premise attributes; s = 1, 2, ..., S; t = 1, 2, ..., T; A confidence rule base construction module is used to construct a confidence rule base based on the product premise attribute set and the customer premise attribute set; each rule in the confidence rule base includes a combination of values ​​of the product attribute set and the customer attribute set and the confidence level of the corresponding product service configuration solution; The reference level determination module is used to initialize the product service configuration solution set and the confidence rule base parameter set, and determine the reference level of each premise attribute; A matching degree acquisition module calculates the matching degree between the new product premise attribute and the reference level of each premise attribute in the customer premise attribute set; An activation weight calculation module is used to calculate the activation weight of each rule in the rule base for the new product premise attribute and customer premise attribute set based on the confidence rule base parameter set and matching degree; The optimal product service configuration decision solution acquisition module is used to fuse the rules in the confidence rule base according to the activation weight, calculate the confidence of each product service configuration decision, compare the confidence of each configuration decision, and take the product service configuration decision solution with the largest confidence as the optimization result.

8. The service-oriented manufacturing product service configuration optimization system according to claim 7, characterized in that: The construction of a confidence rule base based on the product premise attribute set and the customer premise attribute set includes: Then{(D1,β 1,k ),(D2,β 2,k ),…,(D N ,b N,k )} Where: R k is the kth rule of the confidence rule optimization inference model; z 1,1 ,z 1,2 ,…,z 1,S and z 2,1 ,z 2,2 ,…,z 2,T They represent the values ​​of the product premise attribute and the customer premise attribute in the kth rule of the confidence library respectively; D={D1,D2,D3…,D N } represents the set of product service configuration decision solutions, and N represents the total number of all configuration solutions; β j,k Indicates the decision plan D in the kth rule relative to the jth j Confidence level, and 9. The service-oriented manufacturing product service configuration optimization system according to any one of claims 7 to 8, characterized in that: Calculate the matching degree of the new product premise attribute with the reference level of each premise attribute in the customer premise attribute set, including: S401, obtaining a new set of product and customer information; S402: Compare the new product prerequisite attributes with the reference level of each prerequisite attribute in the customer prerequisite attribute set to calculate the individual matching degree; S403: Go through the entire database to obtain the matching degree distribution of the new product premise attribute and customer premise attribute set and each premise attribute.

10. The service-oriented manufacturing product service configuration optimization system according to claim 9, characterized in that: Comparing the new product prerequisite attributes with the reference level of each prerequisite attribute in the customer prerequisite attribute set to calculate the individual matching degree includes: For product prerequisite attributes: For customer premise attributes: in: represents the individual matching degree of the premise attributes of the p-th reference level product; represents the individual matching degree of the premise attributes of the qth reference level customer; z′ 1,s Indicates the prerequisite attribute reference value of the new product information; z′ 2,t Indicates the prerequisite attribute reference value of the new customer information; Represents the premise attribute X s The value corresponding to the pth reference level; Represents the premise attribute Y t The value corresponding to the qth reference level.

Images