Data-driven Product Configuration Life Cycle Stage Prediction Method and System

Abstract

The present invention provides a data-driven method, system, storage medium and electronic device for predicting the life cycle stage of product configuration, which relates to the technical field of data mining. In the present invention, according to the social comment data and the specification documents, a relationship matrix between user requirements and product configuration parameters is obtained, and the importance of product configuration parameters is obtained in combination with the importance of user requirements; a reverse dissatisfaction cumulative model is constructed to obtain the novelty of product configuration parameters; using the importance of the product configuration parameters as the abscissa and the novelty of the product configuration parameters as the ordinate, a life cycle evaluation framework of the product configuration parameters is constructed. It can predict in advance the development law of the life cycle stage of product configuration. Only by obtaining the social comment data of users and the specification documents of product parameters, it is not affected by other fluctuating factors, the results are more stable and reliable, and have good interpretability, which has important guiding value for the business decisions of enterprises.

Description

Technical Field

[0001] The present invention relates to the technical field of data mining, and particularly relates to a data-driven method, system, storage medium and electronic device for predicting the life cycle stage of product configuration. Background Art

[0002] Due to the iterative update of product technology and the rapid change of user needs, product configuration has its specific life cycle law. The traditional life cycle analysis framework mainly divides the life cycle into four stages: germination period, growth period, maturity period, and decline period according to the change trend of market scale. Product configurations in different stages require different marketing strategies to improve the company's competitiveness.

[0003] Currently, there are mainly three methods for predicting the product configuration life cycle: sales volume growth rate method, curve judgment method, and experience judgment method. However, these methods all have a drawback that the observation period of the market scale is too long and cannot reflect the changes in the product configuration life cycle in a timely manner. Sometimes, it is also interfered by short-term market demand fluctuations, resulting in inaccurate predictions and affecting the company's strategic implementation. Summary of the Invention

[0004] (I) Technical Problems to be Solved

[0005] In view of the deficiencies of the prior art, the present invention provides a data-driven method, system, storage medium and electronic device for predicting the life cycle stage of product configuration, and solves the technical problem that the changes in the product configuration life cycle cannot be reflected in a timely manner.

[0006] (II) Technical Solutions

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

[0008] A data-driven method for predicting the life cycle stage of product configuration, comprising:

[0009] Obtaining social comment data of users for products and a description document of product configuration parameters;

[0010] According to the social comment data and the description document, obtaining a relationship matrix between user needs and product configuration parameters, and combining the importance of user needs to obtain the importance of product configuration parameters;

[0011] Constructing a reverse dissatisfaction cumulative model to obtain the novelty of product configuration parameters;

[0012] Taking the importance of the product configuration parameters as the abscissa and the novelty of the product configuration parameters as the ordinate, constructing a life cycle evaluation framework for product configuration parameters; the life cycle evaluation framework is used to predict the life cycle stage of product configuration parameters.

[0013] Preferably, obtaining the relationship matrix between user requirements and product configuration parameters according to the social comment data and the instruction document, and obtaining the importance of product configuration parameters in combination with the importance of user requirements, including:

[0014] S21. Constructing the positive association and negative association between product configuration parameters and user requirements according to the social comment data and the instruction document;

[0015] S22. Constructing a QFD model according to the positive association and negative association between product configuration parameters and user requirements to obtain the relationship matrix between user requirements and product configuration parameters;

[0016] S23. Obtaining the importance of the product configuration parameters according to the relationship matrix in combination with the importance of user requirements; wherein, the importance of user requirements is obtained by calculating the requirement frequency of social comment data.

[0017] Preferably, the positive association and negative association in S21 are respectively expressed as:

[0018]

[0019] Wherein, is the user requirement obtained from the user comment data z , and respectively represent the positive evaluation and negative evaluation regarding the user requirement z , is the product configuration parameter x ;

[0020] 、 respectively represent the positive and negative associations between the product configuration parameter x and the user requirement z ; and respectively represent the joint probabilities of the product configuration parameter x obtaining positive and negative evaluations with the user requirement z ; represents the probability that the product adopts the product configuration parameter x , and respectively represent the probabilities of the user requirement z obtaining positive and negative evaluations.

[0021] Preferably, the relationship matrix in S22 is expressed as:

[0022]

[0023] Among them, represents the relationship matrix between user requirements z and product configuration parameters x .

[0024] Preferably, the importance of the product configuration parameters in S23 is expressed as:

[0025]

[0026] Among them, represents the importance of the product configuration parameter x ; represents the importance of the user requirement z .

[0027] Preferably, the steps of constructing the reverse dissatisfaction cumulative model and obtaining the novelty of product configuration parameters include:

[0028] S31. Construct the dissatisfaction degree of the j product configuration parameters x , and the formula is as follows:

[0029]

[0030] Among them, represents the positive emotion frequency of the j product configuration parameter x ; represents the negative emotion frequency of the j product configuration parameter x ;

[0031] S32. Construct the reverse dissatisfaction cumulative model, and the formula is as follows:

[0032]

[0033] Among them, represents the cumulative reverse dissatisfaction of the product configuration parameter x , which is used to evaluate the novelty of the product configuration parameter and is positively correlated with the novelty of the product configuration parameter; N represents the total number of products in the segmented market.

[0034] Preferably, after constructing the life cycle assessment framework of the product configuration parameters, according to the life cycle assessment framework, the TOPSIS method is used to evaluate and rank the product configuration parameters in the same life cycle stage, specifically including:

[0035] Select the highest product configuration parameter evaluation and the lowest product configuration parameter evaluation ; Among them , respectively represent the highest and lowest product configuration parameters i the importance; and respectively represent the highest and lowest product configuration parameters i the cumulative reverse dissatisfaction, which is used to evaluate the novelty of product configuration parameters and is positively correlated with the novelty of product configuration parameters;

[0036] For the product configuration parameter x calculate its distance from the highest evaluation of the product configuration parameter and its distance from the lowest evaluation of the product configuration parameter The formula is as follows:

[0037]

[0038] According to the said and obtain the final performance evaluation of the product configuration parameter x The formula is as follows: The formula is as follows:

[0039]

[0040] Wherein, if the larger the value, the higher the evaluation ranking of the product configuration parameter x is.

[0041] A data-driven product configuration life cycle stage prediction system, comprising:

[0042] A data acquisition module, configured to acquire social comment data of users for products and description documents of product configuration parameters;

[0043] An importance acquisition module, configured to obtain a relationship matrix between user requirements and product configuration parameters according to the social comment data and description documents, and combine the importance of user requirements to obtain the importance of product configuration parameters;

[0044] A novelty acquisition module, configured to construct a cumulative reverse dissatisfaction model to obtain the novelty of product configuration parameters;

[0045] A stage prediction module, configured to use the importance of the product configuration parameter as the abscissa and the novelty of the product configuration parameter as the ordinate to construct a life cycle evaluation framework of the product configuration parameter; the life cycle evaluation framework is used to predict the life cycle stage of the product configuration parameter.

[0046] A storage medium stores a computer program for data-driven product configuration life cycle stage prediction, wherein the computer program enables a computer to execute the product configuration life cycle stage prediction method as described above.

[0047] An electronic device, comprising:

[0048] One or more processors; a memory; and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the programs include those for executing the product configuration life cycle stage prediction method as described above

[0049] (3) Beneficial effects

[0050] The present invention provides a data-driven product configuration life cycle stage prediction method, system, storage medium and electronic device. Compared with the prior art, the following beneficial effects are achieved:

[0051] The present invention includes obtaining social comment data of a user for a product and a description document of product configuration parameters; obtaining a relationship matrix between user requirements and product configuration parameters according to the social comment data and the description document, and obtaining the importance of product configuration parameters in combination with the importance of user requirements; constructing a reverse dissatisfaction cumulative model to obtain the novelty of product configuration parameters; using the importance of the product configuration parameters as the abscissa and the novelty of the product configuration parameters as the ordinate to construct a life cycle evaluation framework of the product configuration parameters; and using the life cycle evaluation framework to predict the life cycle stage of the product configuration parameters. It can predict in advance the development law of the life cycle stage of product configuration, only need to obtain the social comment data of the user and the description document of the product parameters, is not affected by other fluctuating factors, the result is more stable and reliable, and has good interpretability, which has important guiding value for the business decisions of enterprises. Description of the drawings

[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings without creative efforts based on these drawings.

[0053] Figure 1 It is an overall framework diagram of a data-driven product configuration life cycle stage prediction method provided by an embodiment of the present invention;

[0054] Figure 2 It is a flow schematic diagram of a data-driven product configuration life cycle stage prediction method provided by an embodiment of the present invention;

[0055] Figure 3 It is a schematic diagram of a life cycle evaluation framework of product configuration parameters provided by an embodiment of the present invention;

[0056] Figure 4 A schematic diagram for importance-novelty analysis of product configuration parameters provided by an embodiment of the present invention. Detailed implementation manners

[0057] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described. Apparently, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0058] By providing a data-driven product configuration life cycle stage prediction method, system, storage medium and electronic device, embodiments of the present application solve the technical problem that the changes in the product configuration life cycle cannot be reflected in a timely manner.

[0059] The overall idea of the technical solutions in the embodiments of the present application to solve the above technical problems is as follows:

[0060] The data-driven product configuration life cycle stage prediction method provided by the embodiments of the present invention can be applied to various sub-sectors, such as the automotive industry, e-commerce, etc. This method mainly includes three parts, as Figure 1 shown, which are respectively: (1) Importance evaluation of product configuration parameters; (2) Novelty evaluation of product configuration parameters; (3) Prediction of product configuration life cycle stages.

[0061] Specifically: First, a mapping relationship between user requirements and configuration parameters is established using the Quality Function Deployment (QFD) model, and the importance of user requirements is transformed into the importance of configuration parameters. Second, an Inverse Dissatisfaction Accumulation (IDA) model is proposed to evaluate the novelty of configuration parameters, and product configuration parameters are divided into the germination stage, growth stage, maturity stage and decline stage according to importance-novelty analysis, which is convenient for enterprises to conduct product configuration analysis.

[0062] To better understand the above technical solutions, the above technical solutions will be described in detail below in conjunction with the accompanying drawings of the specification and specific implementation manners.

[0063] Embodiment:

[0064] As Figure 2 shown, an embodiment of the present invention provides a data-driven product configuration life cycle stage prediction method, including:

[0065] S1. Obtain the social comment data of users for the product and the instruction document of the product configuration parameters.

[0066] S2. According to the social comment data and the instruction document, obtain the relationship matrix between user requirements and product configuration parameters, and combine the importance of user requirements to obtain the importance of product configuration parameters.

[0067] S3. Construct a reverse dissatisfaction cumulative model to obtain the novelty of product configuration parameters.

[0068] S4. Take the importance of the product configuration parameters as the abscissa and the novelty of the product configuration parameters as the ordinate to construct a life cycle assessment framework for the product configuration parameters; the life cycle assessment framework is used to predict the life cycle stage of the product configuration parameters.

[0069] The embodiments of the present invention can predict in advance the development law of the life cycle stage of product configuration. Only by obtaining the social comment data of users and the instruction document of product parameters, without being affected by other fluctuating factors, the results are more stable and reliable, and have good interpretability, which has important guiding value for the business decisions of enterprises.

[0070] Next, each step of the above technical solution will be introduced in detail:

[0071] In step S1, obtain the social comment data of users for the product and the instruction document of the product configuration parameters.

[0072] In step S2, according to the social comment data and the instruction document, obtain the relationship matrix between user requirements and product configuration parameters, and combine the importance of user requirements to obtain the importance of product configuration parameters.

[0073] The embodiments of the present invention propose an accurate and efficient data-driven importance evaluation method for product configuration parameters, which can provide a reference for the improvement priority level of product configuration parameters and serve as an index basis for enterprises to design product configuration schemes. Specifically, in this step, the mapping relationship between product configuration and user requirements is obtained by constructing the positive and negative associations between product configuration parameters and user requirements, and the importance of product configuration is determined by the importance of user requirements , and the relationship matrix between user requirements and product configuration jointly determine the importance of product configuration .

[0074] Among them, the importance evaluation of product configuration mainly includes the following three steps:

[0075] S21. According to the social comment data and the instruction document, construct the positive and negative associations between product configuration parameters and user requirements.

[0076] Each product has specific configuration parameter information. By combining the product configuration evaluation with social comment text data, the mapping relationship between product configuration and user needs can be obtained. The sentiment of comment attributes is divided into positive and negative, indicating whether the user needs are met or not. The probability and joint probability of product configuration and user needs evaluation are used to evaluate the association between product configuration parameters and user needs.

[0077] The positive association and negative association between the product configuration parameters and user needs are respectively expressed as:

[0078]

[0079] Wherein, is the user need obtained from user comment data z , and respectively represent the positive evaluation and negative evaluation of the user need z , is the product configuration parameter x ;

[0080] 、 respectively represent the positive and negative associations between the product configuration parameter x and the user need z ; and respectively represent the joint probabilities of the product configuration parameter x and the user need z obtaining positive and negative evaluations; represents the probability that the product adopts the product configuration parameter x , and respectively represent the probabilities that the user need z obtains positive and negative evaluations.

[0081] Exemplarily, in the embodiment of the present invention, it is set that when the value of the positive association or negative association between the configuration parameter and the user need is not greater than 1, it indicates that there is no significant relationship, and the value is set to 0.

[0082] S22. According to the positive association and negative association between the product configuration parameters and user needs, construct a QFD model to obtain the relationship matrix between user needs and product configuration parameters, which is expressed as:

[0083]

[0084] Wherein, represents the relationship matrix between the user need z and the product configuration parameter x .

[0085] S23. Obtain the importance of the product configuration parameters according to the relationship matrix and in combination with the importance of user requirements, where the importance of user requirements is obtained by calculating the requirement frequency of social comment data.

[0086] The embodiment of the present invention proposes a novel method for evaluating the novelty of product configuration parameters driven by accurate and efficient data, and constructs a reverse dissatisfaction cumulative model to achieve quantitative measurement of product configuration novelty. Specifically, the relationship between product configuration and user requirements is a many-to-many relationship, that is, each user requirement usually corresponds to multiple values of product configuration, and each product configuration parameter often corresponds to multiple user requirements. By constructing a QFD matrix and designing a measurement formula to evaluate the mapping relationship between product configuration and requirements

[0087] The importance of the product configuration parameters is expressed as:

[0088]

[0089] where represents the importance of the product configuration parameter x ; represents the importance of the user requirement z ;

[0090] In step S3, construct a reverse dissatisfaction cumulative model to obtain the novelty of product configuration parameters.

[0091] Novelty refers to the fact that in the process of product update and iteration, in order to better meet user requirements, enterprises continuously introduce new product configuration concepts. The embodiment of the present invention believes that the novelty of product configuration parameters depends on the number of dissatisfied customers and the number of products with this configuration, and measures the novelty of product configuration by proposing a reverse dissatisfaction cumulative model. Specifically, it includes:

[0092] S31. Construct the dissatisfaction degree of the configuration parameter j of the product x , and the formula is as follows:

[0093]

[0094] where represents the positive emotion frequency of the configuration parameter j of the product x ; represents the negative emotion frequency of the configuration parameter j of the product x ;

[0095] S32. Construct a reverse dissatisfaction cumulative model, and the formula is as follows:

[0096]

[0097] Among them, represents the cumulative reverse dissatisfaction of product configuration parameters, which is used to evaluate the novelty of product configuration parameters and is positively correlated with the novelty of product configuration parameters; x represents the total number of products in the segmented market. N It should be noted that when evaluating the novelty of product configuration parameters, an extreme situation needs to be avoided, that is, both of the following two conditions are met at the same time: ① The number of assembled products is extremely small, for example, the product assembly rate in the segmented market is lower than 1%; ② There are many negative evaluations and few positive evaluations of this configuration parameter of the assembled products. For example, the average dissatisfaction rate reaches more than 50%. When the above situation occurs, directly set this configuration to ultra-low novelty.

[0098] In step S4, taking the importance of the product configuration parameter as the abscissa and the novelty of the product configuration parameter as the ordinate, a life cycle evaluation framework of the product configuration parameter is constructed; the life cycle evaluation framework is used to predict the life cycle stage of the product configuration parameter.

[0099] As

[0100] shown, the life cycle stage of the product configuration parameter includes: germination period, growth period, maturity period and decline period. The life cycle evaluation framework can describe the characteristics of the product configuration life cycle. Figure 3 Among them, by setting thresholds for distinguishing the high and low importance and novelty, the life cycle stage of the product configuration parameter is divided into four quadrants, specifically as follows:

[0101] ① Germination period: low importance and high novelty, then the product configuration parameter is in the germination period. Only a few products can have such product configurations that meet the user's needs, and at the same time, the impact on consumers' purchase decisions is not high, and only the leading users in the market try to experience it.

[0102] ② Growth period: high importance and high novelty, then the product configuration parameter is in the growth period. There are more products that can meet the user's needs for such product configurations, and it has become an important consideration factor for the majority of consumers to purchase.

[0103] ③ Maturity period: high importance and low novelty, then the product configuration parameter is in the maturity period. Most products can meet the user's needs for such product configurations, and it is still an important consideration factor for consumers to choose products.

[0104] ④ Decline period: low importance and low novelty, then the product configuration parameter is in the decline period. Almost all products can meet the user's needs for such product configurations, and the number of products equipped with this configuration parameter is not large, and it is no longer an important consideration factor for consumers to purchase products.

[0105] ​

[0106] Further, in order to optimize the product configuration scheme and increase the probability of success after replacing the product configuration parameters, based on the above-mentioned life cycle assessment framework, the embodiments of the present invention can also evaluate and rank the product configuration parameters in the same life cycle stage based on the TOPSIS method. Specifically, it includes:

[0107] Select the highest product configuration parameter evaluation and the lowest product configuration parameter evaluation ; where 、 respectively represent the importance of the highest and lowest product configuration parameters i ; 、 respectively represent the cumulative reverse dissatisfaction of the highest and lowest product configuration parameters i , and the cumulative reverse dissatisfaction is used to evaluate the novelty of the product configuration parameters and is positively correlated with the novelty of the product configuration parameters;

[0108] For the product configuration parameter x , calculate its distance from the highest evaluation of the product configuration parameter , and its distance from the lowest evaluation of the product configuration parameter respectively. The formulas are as follows:

[0109]

[0110] According to the and , obtain the final performance evaluation x of the product configuration parameter . The formula is as follows:

[0111]

[0112] Among them, if has a larger value, the evaluation ranking of the product configuration parameter x is higher. [

[56] ]

[0113] To better help understand the superiority of the data-driven product configuration life cycle stage prediction method provided by the embodiments of the present invention, the following specific example is provided:

[0114] Automobile products involve numerous components, with rich structural and functional attributes, and the market environment is highly competitive. Therefore, compact automobile products are selected as the application case object of this patent. This patent selects 13 best-selling compact automobile products and collects the word-of-mouth data of these automobile products from the autohome.com.cn website. The publication time is from January 2018 to May 2020, and 19,856 social comment data are collected for application.

[0115] (1)Data preprocessing.

[0116] There are numerous product configurations for automobile products. To facilitate the analysis of product configuration design, 16 product configurations closely related to user needs are selected in this experiment, as shown in Table 1. Product configuration parameters can be divided into three types: boolean, multiple, and discrete.

[0117] Table 1 Parameter classification of product configurations

[0118]

[0119] Boolean configuration parameters have only two values, 0 and 1. 1 indicates assembly, and 0 indicates non-assembly. For example, "automatic parking", "remote start", "active noise reduction", etc. Multiple product configuration parameters have multiple assembly options. For example, the intake form has "naturally aspirated" and "turbocharged", and the steering wheel material has three types: "plastic", "leatherette", and "genuine leather". The values of discrete product configuration parameters are usually discretely and orderly distributed. For example, the engine displacement usually has multiple values such as "1.4L", "1.5L", "1.6L", "1.8L", "2.0L", etc. For discrete product configuration parameters, they are divided into 2 - 4 categories according to needs and in the form of center matching. For example, the engine displacement can be set with two categories, "1.5L" and "2.0L", and other values are determined to belong to the category according to the distance from these two values. "1.6L" belongs to the "1.5L" category, and "1.8L" belongs to the "2.0L" category.

[0120] (2)Analysis of the importance of product configuration parameters.

[0121] There are 12 user needs closely related to product configurations, namely "fuel consumption", "trunk space", "front and rear row space", "engine", "power", "operation", "interior", "riding comfort", "acoustic comfort", "materials used", "seats", and "headlights".

[0122] According to the measurement formula of the correlation between user needs and configuration parameters a correlation is established between 12 user needs and 16 product configurations (39 configuration parameters). To simplify the presentation form, this patent sets the correlation as no relation ( ), weak relationship ( ), and strong relationship ( ). The strength of the association relationship is judged by setting a threshold. The specific situations are shown in Tables 2, 3, 4, and 5. According to the importance of user requirements and the association relationship with product configuration parameters, the importance of product configuration parameters is measured and normalized.

[0123] Table 2 Importance Evaluation of Product Configuration Parameters Based on QFD Model (Local 1)

[0124]

[0125] Table 3 Importance Evaluation of Product Configuration Parameters Based on QFD Model (Local 2)

[0126]

[0127] Table 4 Importance Evaluation of Product Configuration Parameters Based on QFD Model (Local 3)

[0128]

[0129] Table 5 Importance Evaluation of Product Configuration Parameters Based on QFD Model (Local 4)

[0130]

[0131] (3) Analysis of the novelty of product configuration parameters.

[0132] In the automotive segment market of this example experiment, there are 12 vehicle models and a total of 98 vehicle models, and each vehicle model is recorded as a product.

[0133] 1) According to the cumulative reverse dissatisfaction measurement formula, obtain the novelty level of each configuration parameter. The measurement formula meets the following two conditions: (1) The fewer the number of vehicle models equipped, the higher the novelty level; (2) The lower the dissatisfaction of the configuration parameter, the higher the novelty level.

[0134] 2) Normalize the measured value of the novelty level by reverse satisfaction , and the formula is as follows:

[0135]

[0136] Among them, represents the product configuration parameter after normalization xMeasurement results of novelty level. The measurement results of the novelty level of each product configuration parameter are shown in Table 6. It can be found that the novelty level of the high-end configuration is significantly higher than that of the low-end configuration and the null configuration. At the same time, the novelty level of the low-end configuration is significantly higher than that of the null configuration.

[0137] Table 6 Novelty evaluation of product configuration parameters based on the IDA model

[0138]

[0139] (4)Construction of the importance-novelty life cycle of product configuration parameters.

[0140] According to the importance and novelty evaluations, the product configuration parameters can be divided into four categories: the germination period, the growth period, the maturity period, and the decline period, as specifically shown in Figure 4 shown.

[0141] The vast majority of product configuration parameters belong to the growth period and the maturity period, and individual product configurations belong to the decline period and the germination period. For product configuration parameters in the germination period, such as "automatic parking" and "adaptive high and low beam headlights", the novelty is high, but the importance is insufficient, and the market share is small. For product configuration parameters in the growth period, such as "LED headlights", "leather seats", "360-degree panoramic image", etc., the novelty is high and the importance is also high, and the market share is in a growing state. For configuration parameters in the maturity period, such as "electric sunroof", "reversing image", etc., the novelty is not high, but the importance is still high, and the market share is in a saturated state. For product configuration parameters in the decline period, such as "fabric seats", "halogen headlights", the novelty is low and the importance is also low, and the market share is in a declining state.

[0142] The embodiment of the present invention provides a data-driven product configuration life cycle stage prediction system, including:

[0143] A data acquisition module for acquiring social comment data of users on products and the description documents of product configuration parameters;

[0144] An importance acquisition module for obtaining the relationship matrix between user requirements and product configuration parameters according to the social comment data and the description documents, and combining the importance of user requirements to obtain the importance of product configuration parameters;

[0145] A novelty acquisition module for constructing a reverse dissatisfaction cumulative model to obtain the novelty of product configuration parameters;

[0146] A stage prediction module for using the importance of the product configuration parameters as the abscissa and the novelty of the product configuration parameters as the ordinate to construct a life cycle evaluation framework of the product configuration parameters; the life cycle evaluation framework is used to predict the life cycle stage of the product configuration parameters.

[0147] An embodiment of the present invention provides a storage medium storing a computer program for predicting the product configuration life cycle stage driven by data, wherein the computer program enables a computer to execute the product configuration life cycle stage prediction method as described above.

[0148] An embodiment of the present invention provides an electronic device, including:

[0149] One or more processors; a memory; and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the programs include those for executing the product configuration life cycle stage prediction method as described above.

[0150] It can be understood that the data-driven product configuration life cycle stage prediction system, storage medium and electronic device provided by the embodiments of the present invention correspond to the data-driven product configuration life cycle stage prediction method provided by the embodiments of the present invention. For the explanations, examples, beneficial effects and other parts of the relevant content, reference can be made to the corresponding parts in the product configuration life cycle stage prediction method, which will not be elaborated herein.

[0151] In summary, compared with the prior art, the following beneficial effects are achieved:

[0152] 1. The embodiments of the present invention can predict in advance the development law of the product configuration life cycle stage. Only by obtaining the social comment data of users and the description documents of product parameters, it is not affected by other fluctuating factors, and the results are more stable and reliable, and have good interpretability, which has important guiding value for the business decisions of enterprises.

[0153] 2. The embodiments of the present invention propose an accurate and efficient data-driven method for evaluating the importance of product configuration parameters, which can provide a reference for the priority of improving product configuration parameters and serve as an index basis for enterprises to design product configuration schemes.

[0154] 3. The embodiments of the present invention propose an accurate and efficient data-driven method for evaluating the novelty of product configuration parameters, and construct a reverse dissatisfaction cumulative model to achieve quantitative measurement of product configuration novelty.

[0155] 4. The embodiments of the present invention apply the TOPSIS method to the constructed product configuration life cycle, which improves the probability of success after product configuration replacement.

[0156] It should be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the said element.

[0157] The above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A data-driven method for predicting the product configuration life cycle stage, characterized in that, including: Obtain social comment data of users for a product and a description document of product configuration parameters; According to the social comment data and the description document, obtain the relationship matrix between user requirements and product configuration parameters, and combine the importance of user requirements to obtain the importance of product configuration parameters; Construct a reverse dissatisfaction cumulative model to obtain the novelty of product configuration parameters; Use the importance of the product configuration parameters as the abscissa and the novelty of the product configuration parameters as the ordinate to construct a life cycle assessment framework for the product configuration parameters; the life cycle assessment framework is used to predict the life cycle stage of the product configuration parameters; The step of obtaining the relationship matrix between user requirements and product configuration parameters according to the social comment data and the description document, and combining the importance of user requirements to obtain the importance of product configuration parameters includes: S21. According to the social comment data and the description document, construct positive and negative associations between product configuration parameters and user requirements; S22. According to the positive and negative associations between the product configuration parameters and user requirements, construct a QFD model to obtain the relationship matrix between user requirements and product configuration parameters; S23. According to the relationship matrix, combine the importance of user requirements to obtain the importance of the product configuration parameters; wherein, the importance of user requirements is obtained by calculating the requirement frequency of the social comment data; The step of constructing a reverse dissatisfaction cumulative model to obtain the novelty of product configuration parameters includes: S31. Construct the product j The dissatisfaction level of the configuration parameters x is as follows: Among them, represents the j configuration parameters x of the positive sentiment frequency of the product, j and x represents the negative sentiment frequency of the configuration parameters of the product; S32. Construct a reverse dissatisfaction cumulative model, and the formula is as follows: Among them, represents the cumulative reverse dissatisfaction of product configuration parameters x , which is used to evaluate the novelty of product configuration parameters and is positively correlated with the novelty of product configuration parameters; N represents the total number of products in the segmented market.

2. The method for predicting the product configuration life cycle stage according to claim 1, wherein The positive and negative associations in S21 are respectively expressed as: Among them, is the user requirement obtained from the user comment data z , and respectively represent the positive evaluation and negative evaluation regarding the user requirement z ; is the product configuration parameter x ; 、 respectively represent the product configuration parameters x and the user requirements z of the positive and negative associations; and respectively represent the product configuration parameters x and the user requirements z to obtain the joint probability of positive and negative evaluations; represents the probability that the product adopts the product configuration parameter x , and respectively represent the probabilities that the user requirements z obtain positive and negative evaluations.

3. The product configuration life cycle stage prediction method according to claim 2, wherein The relationship matrix in S22 is expressed as: Among them, represents user requirements z and the product configuration parameters x is the relationship matrix therebetween.

4. The method for predicting the product configuration life cycle stage according to claim 3, wherein The importance of the product configuration parameters in S23 is expressed as: Among them, represents the importance of product configuration parameters x ; represents the importance of user requirements z .

5. The product configuration life cycle stage prediction method according to any one of claims 1 to 4, characterized in that, After constructing the life cycle assessment framework of the product configuration parameters, according to the life cycle assessment framework, use the TOPSIS method to evaluate and rank the product configuration parameters in the same life cycle stage, specifically including: Select the highest evaluation of product configuration parameters and the lowest evaluation of product configuration parameters ; where 、 respectively represent the importance of the highest and lowest product configuration parameters i ; 、 respectively represent the cumulative reverse dissatisfaction of the highest and lowest product configuration parameters i The cumulative reverse dissatisfaction is used to evaluate the novelty of product configuration parameters and is positively correlated with the novelty of product configuration parameters; For the product configuration parameters x , calculate their distances from the highest evaluation of the product configuration parameters , and their distances from the lowest evaluation of the product configuration parameters , the formulas are as follows: According to the said and , obtain the final performance evaluation of the product configuration parameters x , and the formula is as follows: ​ Among them, if the larger the value taken, the x higher the evaluation ranking of the product configuration parameters.

6. A data-driven product configuration life cycle stage prediction system, characterized in that, Used to execute the product configuration life cycle stage prediction method as described in claim 1, including: A data acquisition module, used to obtain social comment data of users for a product and a description document of product configuration parameters; An importance acquisition module, used to obtain the relationship matrix between user requirements and product configuration parameters according to the social comment data and the description document, and combine the importance of user requirements to obtain the importance of product configuration parameters; A novelty acquisition module, used to construct a reverse dissatisfaction cumulative model to obtain the novelty of product configuration parameters; A stage prediction module, used to use the importance of the product configuration parameters as the abscissa and the novelty of the product configuration parameters as the ordinate to construct a life cycle assessment framework for the product configuration parameters; the life cycle assessment framework is used to predict the life cycle stage of the product configuration parameters.

7. A storage medium, characterized in that, It stores a computer program for data-driven prediction of the product configuration life cycle stage, wherein the computer program causes the computer to execute the product configuration life cycle stage prediction method as described in any one of claims 1 to 5.

8. An electronic device, characterized in that, including: One or more processors; A memory; and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs including those for executing the product configuration life cycle stage prediction method according to any one of claims 1 to 5.

Images