Product information system based on big data association analysis

Abstract

The invention discloses a product information method based on big data association analysis. The method comprises the following steps: inputting a product into a product information system; the product information system obtains evaluation information of the products input into the system, and the obtaining method comprises network search and e-commerce platform data arrangement; classifying all input products according to the obtained product information and classification standards of the user; products in the same category are analyzed, product quality indexes are analyzed, and parameter data examples and user evaluation are associated; establishing a six-dimensional diagram of a user expected index, editing the six-dimensional diagram of the expected index by the user according to a product analysis result and provided product parameter analysis information, matching the six-dimensional diagram of the product with the six-dimensional diagram of the user expected index to obtain matching degree values V, sorting the matching degree values V from high to low, finally, the product information system recommends the products to the user according to the sorted corresponding products, and the method has the advantages of being high in individuation degree and capable of promoting diversified development of the market.

Description

Technical Field

[0001] The present invention relates to the technical field of big data analysis, and in particular to a product information system based on big data association analysis. Background Art

[0002] In the current market environment, the uneven quality of products has caused widespread doubts among consumers, prompting them to adopt a conservative follow-up purchase strategy to reduce the risk of purchasing unsatisfactory products. However, this behavior often forces consumers to compromise or even sacrifice personal preferences when they are not completely satisfied. In order to avoid further compromise, the existing product information system based on big data association analysis provides users with customized product recommendations by analyzing user behavior, preferences and demand data, while promoting the market to develop in a more diversified and innovative direction, achieving improved user satisfaction and continuous optimization of the market ecology. However, many consumers tend to follow the crowd, that is, to make choices based on the simplified logic of sales volume and word-of-mouth generated by big data analysis. However, this trend not only fails to accurately match the personalized needs of users, but also increases the risk of "mistaken traps" in purchase decisions. Therefore, the current problem that needs to be solved is how to meet the personalized needs of users while reducing the probability of "pitfalls" where products are seriously inconsistent with user expectations. Therefore, it is necessary to design a product information system based on big data association analysis that has a high degree of personalization and can promote the diversified development of the market. Summary of the invention

[0003] The purpose of the present invention is to provide a product information system based on big data association analysis to solve the problems raised in the above background technology.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions: a product information method based on big data association analysis, comprising the following steps:

[0005] Step S1: Enter the product into the product information system. The product information system enters the various parameter data of the product through data transmission, manual registration, and batch entry, and the product information system obtains the data;

[0006] Step S2: The product information system obtains evaluation information of the products entered into the system, and the acquisition method includes network search and e-commerce platform data collation;

[0007] Step S3: Classify all entered products according to the acquired product information and the user's classification criteria;

[0008] Step S4: Analyze the products in the same category currently selected by the user and deeply evaluate the product indicators;

[0009] Step S5: Analyze the product quality indicators and associate parameter data examples with user evaluations;

[0010] Step S6: Establish a six-dimensional graph of user expected indicators. The user edits the six-dimensional graph of expected indicators based on the product analysis results and the provided product parameter analysis information. Then, a six-dimensional graph of the product is established for the product according to the six sets of parameter information corresponding to the user's six-dimensional graph. The six-dimensional graph of the product is matched with the six-dimensional graph of the user's expected indicators, and the matching values ​​V are obtained respectively. The matching values ​​V are sorted from high to low. Finally, the product information system will recommend products to the user based on the products corresponding to the sorting.

[0011] According to the above technical solution, the classification method in step S3 is specifically:

[0012] Step S31: During the process of entering products into the product information system, the product information system intelligently identifies the product name based on the entered information, and automatically assigns product category keywords based on the product name. At the same time, during the process of entering products, product dealers can also enter product features and product models as keywords. Users use the keyword classification module to preliminarily classify all products in the product information system;

[0013] Step S32: Then, according to the user's budget price, the budget price range for the product is input, and each product also corresponds to a selling price, and the products that meet the user's budget price are further classified and screened;

[0014] Step S33: After limiting the product category and the price range of the product, the user can propose product function requirements, and then the product information system will filter out products of this type that have the functions required by the user within the user's budget price range.

[0015] According to the above technical solution, step S4 further includes the following steps:

[0016] Step S41: After the user has completed product classification, all parameter indicators of the classified products are obtained;

[0017] Step S42: when there are common parameter types in the classified products, the same parameter types are marked with the same standard, and the parameter types marked with the same standard are compared;

[0018] Step S43: While comparing, use the formula Calculate the parameter standard index value P of the same standard mark, where p i is the common parameter value of each product under the current common parameter type, i = 1, 2, ... n; n is the number of products with the common parameter type under the current category;

[0019] Step S44: When p iWhen <P, the parameter type currently analyzed by the product is classified as a disadvantageous parameter indicator; i =P, the parameter type currently analyzed by the product is classified as a balanced parameter indicator; when p i When it is greater than P, the parameter type currently analyzed by the product is classified as an advantage parameter indicator;

[0020] Step S45: When there are common parameter types in the classified products, the product-specific parameter types are separately sorted and counted.

[0021] According to the above technical solution, step S5 further includes: after the in-depth evaluation of product indicators is completed, the user selects two groups of product parameters under the same parameter type, the indicator difference analysis module uses electrical signals to retrieve product evaluation data, and uses the difference between the two groups of product parameters and the product parameter type as keywords to retrieve evaluations associated with the selected parameter type and parameters in the evaluation database, and uses them as analysis.

[0022] According to the above technical solution, the sum of the six-dimensional parameter type index values ​​of the six-dimensional graph of user expected indicators established in step S6 shall not be higher than the preset value T, where T is a fixed value obtained by weighting according to the budget price after the user screens out similar products.

[0023] A product information system based on big data association analysis includes a product information acquisition module, a product information classification module, a product evaluation and analysis module and a related product recommendation module, characterized in that: the product information acquisition module is used to acquire various specific information of the product, the product information acquisition module is electrically connected to the product information classification module, the product information classification module is used to classify the product according to the information acquired by the product information acquisition module, the product evaluation and analysis module is used to deeply evaluate the product and analyze the product according to the product information and classification labels, the product information acquisition module and the product information classification module are both electrically connected to the product evaluation and analysis module, the related product recommendation module is electrically connected to the product evaluation and analysis module, and the related product recommendation module is used to recommend products to users in a personalized manner according to user needs.

[0024] According to the above technical solution, the product information acquisition module includes a product parameter acquisition module and a product evaluation acquisition module. The product parameter acquisition module is used to obtain the specific model and various parameter data of the product, and the product evaluation acquisition module is used to obtain the historical reputation of the product and specific user evaluation information.

[0025] According to the above technical solution, the product information classification module includes a functional classification module, a price classification module and a keyword classification module. The functional classification module is used to classify products according to set functional divisions, the price classification module is used to classify products according to set price ranges, and the keyword classification module is used to assign product keyword tags according to product information and classify according to keywords set by users.

[0026] According to the above technical solution, the product evaluation and analysis module includes a horizontal indicator evaluation module, a good and bad indicator classification module and an indicator difference analysis. The horizontal indicator evaluation module is used to perform a horizontal comparative evaluation on the same parameter indicators of products under the same category after the user completes the product classification. The good and bad indicator classification module is used to divide the advantages and disadvantages standards of various product indicators according to the current product classification. The indicator difference analysis module is used to analyze the good and bad indicators of the parameters.

[0027] According to the above scheme, the associated product recommendation module includes a user expected indicator establishment module and a product matching module. The user expected indicator establishment module is used to establish a user's expected indicator map based on the user's product needs and price expectations, and the product matching module is used to match and recommend user needs with products that meet user expectations.

[0028] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention, by further distinguishing parameter categories of similar products for in-depth evaluation and analysis, and intuitively providing prompts for the advantages and disadvantages of parameter indicators of different product categories and separate statistical compilation of diversified product parameter types, can effectively help users quickly and objectively understand the products, and help users match their needs with product parameter types to obtain the most suitable products, thereby achieving a high degree of personalization and promoting the diversified development of the market. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0030] Figure 1 It is a schematic diagram of the system module composition of the present invention. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0032] See also Figure 1 The present invention provides a technical solution: a product information system based on big data association analysis, including a product information acquisition module, a product information classification module, a product evaluation and analysis module and a related product recommendation module, the product information acquisition module is used to acquire various specific information of the product, the product information acquisition module is electrically connected to the product information classification module, the product information classification module is used to classify the product according to the information acquired by the product information acquisition module, the product evaluation and analysis module is used to deeply evaluate the product and analyze the product according to the product information and classification labels, the product information acquisition module and the product information classification module are both electrically connected to the product evaluation and analysis module, the related product recommendation module is electrically connected to the product evaluation and analysis module, and the related product recommendation module is used to recommend products to users in a personalized manner according to user needs.

[0033] The product information acquisition module includes a product parameter acquisition module and a product evaluation acquisition module. The product parameter acquisition module is used to obtain the specific model and various parameter data of the product, and the product evaluation acquisition module is used to obtain the historical reputation of the product and specific user evaluation information.

[0034] The product information classification module includes a functional classification module, a price classification module and a keyword classification module. The functional classification module is used to classify products according to set functional divisions, the price classification module is used to classify products according to set price ranges, and the keyword classification module is used to assign product keyword tags based on product information and classify products according to keywords set by users.

[0035] The product evaluation and analysis module includes a horizontal indicator evaluation module, a good and bad indicator classification module and an indicator difference analysis. The horizontal indicator evaluation module is used to conduct a horizontal comparative evaluation of the same parameter indicators of products under the same category after the user has completed the product classification. The good and bad indicator classification module is used to divide the advantages and disadvantages of various product indicators according to the current product classification. The indicator difference analysis module is used to analyze the good and bad indicators of the parameters.

[0036] The associated product recommendation module includes a user expectation index establishment module and a product matching module. The user expectation index establishment module is used to establish a user expectation index map based on the user's product needs and price expectations. The product matching module is used to match and recommend user needs with products that meet user expectations.

[0037] The method for operating the product information system comprises the following steps:

[0038] Step S1: Enter the product into the product information system. The product information system enters the various parameter data of the product through data transmission, manual registration, and batch entry, and the data is obtained by the product information system; then the detailed information of the product can be browsed through the product information system;

[0039] Step S2: The product information system obtains evaluation information of the products entered into the system. The acquisition method includes network search and e-commerce platform data collation, thereby obtaining consumers' evaluation information on the products from multiple aspects, and collating the evaluation information so that users can quickly understand the objective evaluation of the products;

[0040] Step S3: Classify all entered products according to the acquired product information and the user's classification criteria;

[0041] Step S4: Analyze the products in the same category currently selected by the user and deeply evaluate the product indicators;

[0042] Step S5: Analyze the product quality indicators and associate parameter data examples with user evaluations;

[0043] Step S6: Establish a six-dimensional graph of user expected indicators. The user edits the six-dimensional graph of expected indicators based on the product analysis results and the provided product parameter analysis information. Then, a six-dimensional graph of the product is established for the product according to the six groups of parameter information corresponding to the six-dimensional graph of the user, and the six-dimensional graph of the product is matched with the six-dimensional graph of user expected indicators to obtain matching values ​​V respectively, and the matching values ​​V are sorted from high to low. Finally, the product information system will recommend products to the user based on the products corresponding to the sorting. Finally, it is achieved that all indicators of the products selected by the user meet the user's expectations, and the objectively existing disadvantage parameter indicators of the products selected by the user are also within the user's psychological acceptance range, and the product price also meets the user's expectations, achieving a high degree of personalization and promoting the diversified development of the market.

[0044] The classification method in step S3 is specifically:

[0045] Step S31: During the process of entering products into the product information system, the product information system intelligently identifies the product name based on the entered information, and automatically assigns product category keywords based on the product name. At the same time, during the process of entering products, product dealers can also enter product features and product models as keywords. Users use the keyword classification module to preliminarily classify all products in the product information system;

[0046] Step S32: Then, according to the user's budget price, the budget price range for the product is input, and each product also corresponds to a selling price, and the products that meet the user's budget price are further classified and screened;

[0047] Step S33: After limiting the product category and the price range of the product, the user can propose product function requirements, and then screen out products of this type that have the functions required by the user within the user's budget price range through the product information system; through the product classification function, the user's target products can be quickly classified and screened out to reduce the number of unqualified products, avoid too many products interfering with user selection and judgment, and even cause users to have psychological resistance to selecting good products. At the same time, through the product classification function, it can pave the way for the effectiveness of subsequent product analysis and evaluation, reduce invalid indicator comparisons of products of different types and prices, and make accurate analysis for user selection.

[0048] Step S4 further comprises the following steps:

[0049] Step S41: After the user has completed product classification, all parameter indicators of the classified products are obtained;

[0050] Step S42: when there are common parameter types in the classified products, the same parameter types are marked with the same standard, and the parameter types marked with the same standard are compared;

[0051] Step S43: While comparing, use the formula Calculate the parameter standard index value P of the same standard mark, where p i is the common parameter value of each product under the current common parameter type, i = 1, 2, ... n; n is the number of products with the common parameter type under the current category;

[0052] Step S44: When p i When <P, the parameter type currently analyzed by the product is classified as a disadvantageous parameter indicator; i =P, the parameter type currently analyzed by the product is classified as a balanced parameter indicator; when p i When it is greater than P, the parameter type currently analyzed by the product is classified as an advantage parameter indicator;

[0053] Step S45: When there are common parameter types in the classified products, the product-specific parameter types are separately sorted and counted; because even products of the same type are composed of different types of parameter data, different parameter types are difficult to measure with the same standard, and it is impossible to give a unified comprehensive evaluation score. Even if an objective evaluation score is given, it will often cause users to only choose products with high comprehensive evaluation scores and ignore the diversity of products. Then, by further distinguishing the parameter categories of similar products for in-depth evaluation and analysis, and intuitively providing prompts for the advantages and disadvantages of parameter indicators of different categories of products and separately sorting out the diverse product parameter types, it can effectively help users quickly and objectively understand the products, and help users match their needs with product parameter types to obtain the most suitable products.

[0054] Step S5 further includes: after the in-depth evaluation of product indicators is completed, the user selects two groups of product parameters under the same parameter type, the indicator difference analysis module uses electrical signals to retrieve product evaluation data, and uses the difference between the two groups of product parameters and the product parameter type as keywords to retrieve the evaluation associated with the selected parameter type and parameters in the evaluation database, and uses it as analysis; then, when the user has differences in some product parameters, the indicator difference analysis module can be used to quickly understand the importance of the parameter difference, so that the user can judge the product more clearly.

[0055] The sum of the six-dimensional parameter type index values ​​of the six-dimensional graph of user expected indicators established in step S6 shall not be higher than a preset value T, where T is a fixed value obtained by weighting according to the budget price after the user screens out similar products; thereby effectively ensuring that the product selected by the user meets the expectations of product parameters under the current budget, and avoiding blindly high expectations for products that are out of price, and failing to select satisfactory products that are out of touch with reality.

[0056] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0057] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A product information method based on big data association analysis, characterized in that: The operating method of the product information system comprises the following steps: Step S1: Enter the product into the product information system. The product information system enters the various parameter data of the product through data transmission, manual registration, and batch entry, and the product information system obtains the data; Step S2: The product information system obtains evaluation information of the products entered into the system, and the acquisition method includes network search and e-commerce platform data collation; Step S3: Classify all entered products according to the acquired product information and the user's classification criteria; Step S4: then analyze the products in the same category currently selected by the user and deeply evaluate the product indicators; Step S5: Analyze the product quality indicators and associate parameter data examples with user evaluations; Step S6: Establish a six-dimensional graph of user expected indicators. The user edits the six-dimensional graph of expected indicators based on the product analysis results and the provided product parameter analysis information. Then, a six-dimensional graph of the product is established for the product according to the six sets of parameter information corresponding to the user's six-dimensional graph. The six-dimensional graph of the product is matched with the six-dimensional graph of the user's expected indicators, and the matching values ​​V are obtained respectively. The matching values ​​V are sorted from high to low. Finally, the product information system will recommend products to the user based on the products corresponding to the sorting.

2. The product information method based on big data association analysis according to claim 1 is characterized by: The classification method in step S3 is specifically: Step S31: During the process of entering products into the product information system, the product information system intelligently identifies the product name based on the entered information, and automatically assigns product category keywords based on the product name. At the same time, during the process of entering products, product dealers can also enter product features and product models as keywords. Users use the keyword classification module to preliminarily classify all products in the product information system; Step S32: Then, according to the user's budget price, the budget price range for the product is input, and each product also corresponds to a selling price, and the products that meet the user's budget price are further classified and screened; Step S33: After limiting the product category and the price range of the product, the user can propose product function requirements, and then the product information system will filter out products of this type that have the functions required by the user within the user's budget price range.

3. The product information method based on big data association analysis according to claim 2 is characterized by: The step S4 further comprises the following steps: Step S41: After the user has completed product classification, all parameter indicators of the classified products are obtained; Step S42: when there are common parameter types in the classified products, the same parameter types are marked with the same standard, and the parameter types marked with the same standard are compared; Step S43: While comparing, use the formula Calculate the parameter standard index value P of the same standard mark, where p i is the common parameter value of each product under the current common parameter type, i = 1, 2, ... n; n is the number of products with the common parameter type under the current category; Step S44: When p i When <P, the parameter type currently analyzed by the product is classified as a disadvantageous parameter indicator; i =P, the parameter type currently analyzed by the product is classified as a balanced parameter indicator; when p i When it is greater than P, the parameter type currently analyzed by the product is classified as an advantage parameter indicator; Step S45: When there are common parameter types in the classified products, the product-specific parameter types are separately sorted and counted.

4. The product information method based on big data association analysis according to claim 3 is characterized by: The step S5 further includes: after the in-depth evaluation of product indicators is completed, the user selects two groups of product parameters under the same parameter type, the indicator difference analysis module uses electrical signals to retrieve product evaluation data, and uses the difference between the two groups of product parameters and the product parameter type as keywords to retrieve evaluations associated with the selected parameter type and parameters in the evaluation database, and uses them as analysis.

5. The product information method based on big data association analysis according to claim 4 is characterized by: The sum of the six-dimensional parameter type index values ​​of the six-dimensional graph of user expected indicators established in step S6 shall not be higher than a preset value T, where T is a fixed value obtained by weighting according to the budget price after the user screens out similar products.

6. A product information system based on big data association analysis, characterized by: It includes a product information acquisition module, a product information classification module, a product evaluation and analysis module and a related product recommendation module, and is characterized in that: the product information acquisition module is used to acquire various specific information of the product, the product information acquisition module is electrically connected to the product information classification module, the product information classification module is used to classify the product according to the information acquired by the product information acquisition module, the product evaluation and analysis module is used to conduct in-depth evaluation and analysis of the product according to the product information and classification labels, the product information acquisition module and the product information classification module are both electrically connected to the product evaluation and analysis module, the related product recommendation module is electrically connected to the product evaluation and analysis module, and the related product recommendation module is used to recommend products to users in a personalized manner according to user needs.

7. The product information system based on big data association analysis according to claim 6 is characterized by: The product information acquisition module includes a product parameter acquisition module and a product evaluation acquisition module. The product parameter acquisition module is used to obtain the specific model and various parameter data of the product, and the product evaluation acquisition module is used to obtain the historical reputation of the product and specific user evaluation information.

8. The product information system based on big data association analysis according to claim 7 is characterized by: The product information classification module includes a functional classification module, a price classification module and a keyword classification module. The functional classification module is used to classify products according to set functional divisions, the price classification module is used to classify products according to set price ranges, and the keyword classification module is used to assign product keyword tags according to product information and classify products according to keywords set by users.

9. The product information system based on big data association analysis according to claim 8, characterized in that: The product evaluation and analysis module includes a horizontal indicator evaluation module, a good and bad indicator classification module and an indicator difference analysis. The horizontal indicator evaluation module is used to perform a horizontal comparative evaluation on the same parameter indicators of products under the same category after the user has completed the product classification. The good and bad indicator classification module is used to classify the advantages and disadvantages of various product indicators according to the current product classification. The indicator difference analysis module is used to analyze the good and bad indicators of the parameters.

10. The product information system based on big data association analysis according to claim 6, characterized in that: The associated product recommendation module includes a user expected index establishment module and a product matching module. The user expected index establishment module is used to establish a user's expected index map based on the user's product needs and price expectations, and the product matching module is used to match and recommend user needs with products that meet the user's expectations.

Images