Product mining method and system based on big data analysis

Abstract

The invention provides a product mining method based on big data analysis, and the method comprises the steps: collecting basic information of users, and forming a to-be-analyzed user distribution relationship network; collecting feedback data, and selecting a target user; customer data is deeply mined, customer behaviors are analyzed, and new product probabilities are summarized; potential demands of customers are mined, and product innovation is carried out; performing competitive product analysis on the new product; the steps are specifically carried out on any product. The invention also provides a system for realizing the method. The system comprises a big data acquisition module, a feedback data arrangement module, a data parameter distribution module, an organization innovation workshop module, a demand product comparison module and a demand mining direction confirmation module. In the operation process of user demand mining and product mining, the user attribute data of the corresponding users are analyzed, so that the analysis basis is more sufficient, and more influence factors are eliminated, and therefore, the mined information and innovative products can accurately meet the demands of the users.

Description

Technical Field

[0001] The present invention relates to the technical field of big data mining, and particularly relates to a product mining method and system based on big data analysis. Background Art

[0002] User demand analysis and product mining that meets user demands are crucial for the data life cycle in today's big data era. Precise and effective user demand analysis can provide a lot of valuable information for manufacturers to use to improve market competitiveness and product quality, thus enriching daily production and life in the digital economy era. The current user demand mining technologies are emerging in an endless stream. Due to the influence of the diversity and complexity of big data, when mining products that meet user demands, it will be affected by many exclusive factors, and thus the mined information cannot accurately meet user demands. Summary of the Invention

[0003] The purpose of the present invention is to provide a product mining method and system based on big data analysis for the problems existing in the prior art.

[0004] To achieve the above purpose, the technical solution adopted by the present invention is:

[0005] A product mining method based on big data analysis, comprising the following steps:

[0006] Collect basic information of users, determine whether there is a relevant relationship between the users to be analyzed and the distribution positions of the users according to the basic information, and form a corresponding user distribution relationship network to be analyzed. In the user distribution relationship network to be analyzed, the distribution relationship between the users to be analyzed is related to the relevant relationship of the users;

[0007] Obtain feedback data by recording the basic information of users and using methods such as telephone return visits, email replies, and collecting social media comments;

[0008] Deeply mine existing customer data according to the obtained feedback data, analyze the behaviors, purchase records, and reasons for their loss of customers based on the current data, summarize the needs and trends of users, and summarize the probability of new products;

[0009] According to the probability of new products, mine potential customer needs, and innovate new products that meet user needs. The new products can be developed and optimized through open discussions and brainstorming;

[0010] Conduct competitive product analysis on the new products and other existing products. The competitive product analysis includes product front-end analysis and product back-end analysis;

[0011] Through demand mining, confirm the needs of the current target users and specify them for any one product.

[0012] Further, the basic information is applied to the big data collection module. Coordinate information is provided in the big data collection module. The groups of the coordinate information include the original user group and the typical user group. The distribution of the mining parameters of the original user group is used to reflect the distribution coordinate data of the differential users in the typical user group in the distribution relationship network of the users to be analyzed.

[0013] Further, the telephone return visit, the email return message, and the method of collecting social media comments belong to the feedback data sorting module. An identity division unit is provided in the feedback data sorting module. The identity division unit divides the personnel attributes into target users, potential users, and other relevant personnel.

[0014] Further, the feedback data is applied to the data parameter distribution module. The data parameter distribution module divides the feedback data into benchmark user data and adjusted user data, obtains the distribution of the mining parameters of the benchmark users and the distribution of the mining parameters of the adjusted users, and analyzes the associated mining error indicators corresponding to the mining networks of various types of users.

[0015] Further, the methods of open discussion and brainstorming belong to the organizational innovation workshop module. Among them, the interior of the organizational innovation workshop module is divided into regions, and information on different aspects of competing products is obtained according to the divided regions.

[0016] Further, the methods of product front-end analysis and product back-end analysis belong to the demand product comparison module. An independent storage unit and a pair-wise division unit are provided in the demand product comparison module. Product positioning, product structure, product experience, product function, and profit model storage blocks are set in the independent storage unit. Instruction documents, technical documents, and open-source system blocks are set in the pair-wise division unit.

[0017] Further, the method of data division belongs to the module for confirming the demand mining direction.

[0018] To better implement the above product mining method based on big data analysis, a system for the product mining method based on big data analysis is provided. The system includes a big data collection module, a feedback data sorting module, a data parameter distribution module, an organizational innovation workshop module, a demand product comparison module, and a module for confirming the demand mining direction.

[0019] Further, the big data collection module, the feedback data sorting module, the data parameter distribution module, the organizational innovation workshop module, the demand product comparison module, and the module for confirming the demand mining direction are sequentially connected for data transmission and stored in the computer program.

[0020] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0021] 1. Through market research on user groups, construct a network of distribution relationships of users to be analyzed that is needed; 2. Through the collection of feedback data, generate a group user data characterization vector of the distribution of group user mining parameters and the network of distribution relationships of users to be analyzed, and determine the corresponding relevant users; 3. Obtain the needs of users in different fields through the analysis of innovative products and competing products until the user needs mining and product mining are completed; 4. During the operation of user needs mining and product mining of the present invention, the user attribute data of the corresponding users is analyzed, making the analysis basis more sufficient and eliminating more influencing factors. Therefore, the mined information and innovative products can accurately meet the needs of users. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 is a flowchart of a product mining method based on big data analysis of the present invention;

[0023] Figure 2 is a system module block diagram of a product mining method based on big data analysis of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] Next, the technical solutions of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0025] Embodiment 1

[0026] Refer to the attached Figure 1 As shown, a product mining method and system based on big data analysis includes the following steps:

[0027] S1. Market research: Collect the basic information of users through online questionnaire surveys and offline random interviews. The basic information includes online information and offline information, and determine whether there is a relevant relationship between the users to be analyzed based on the basic information. After confirming the relevant relationship, determine the distribution positions between the users to form a corresponding network of distribution relationships of users to be analyzed. In the network of distribution relationships of users to be analyzed, the distribution relationship between the users to be analyzed is related to the relevant relationship of the users;

[0028] S2. Customer Feedback: By recording the basic information of users in step S1 and obtaining feedback data through methods such as telephone follow-up, email replies, and collecting social media comments. Among them, the forms of telephone follow-up include structured and unstructured. Structured means that the product manager prepares a series of questions in advance according to certain criteria and obtains content related to the target product through the user's answers to the questions. Unstructured means listing a rough idea and elaborating according to the specific situation of the follow-up. The recipients of email replies can be any one of industry experts, self-media influencers, and practitioners of similar products. The interviewees for social media comments are set as target users, who are people with high requirements for product experience, having the right to speak, and being good at expressing in the senior field;

[0029] S3. Data Analysis: Based on the feedback data obtained in step S2, deeply explore the existing customer data, and analyze the customer's behavior, purchase records, and reasons for churn according to the current data. After completing the corresponding data analysis, summarize the needs and trends of users. Secondly, the functions of data analysis include the statistical analysis of questionnaire data and the statistical analysis of operation data, and summarize the new product probability according to the corresponding data reports. The new product probability has the effects of exploring new needs and iterative needs of old products;

[0030] S4. Innovative Product: By relying on the new product probability in step S3, explore potential needs that customers have not expressed, and innovate new products that meet user needs. The new products can be developed and optimized through open discussions and brainstorming;

[0031] S5. Competitor Analysis: For the competitors mentioned in step S4, conduct competitor analysis on the new products and other existing products. Competitor analysis includes product front-end analysis and product back-end analysis. Product front-end analysis needs to analyze a product's product positioning, product structure, product experience, product functions, and profit model, and see the direction, target users, and model of competitors from the product positioning to further obtain corresponding new needs of users. Product back-end analysis is through demo presentations, specification documents, technical documents, open-source systems, front-end reverse engineering, and inquiries to programmers;

[0032] S6. Requirement Direction: Through the requirement mining in steps S1 to S5, confirm the requirements of the current target users, and according to the corresponding data division, confirm the requirement directions of users in different fields and specify them for any one product.

[0033] Embodiment 2

[0034] Refer to the appendix Figure 2 As shown, in the embodiment of the present invention:

[0035] As a preferred technical solution, in step S1, the online questionnaire survey and the offline random interview belong to the big data collection module, and the basic information is applied to the big data collection module. The big data collection module is provided with coordinate information, and the groups of the coordinate information include the original user group and the typical user group. The mining parameter distribution of the original user group is used to reflect the distribution coordinate data of the differential users in the typical user group in the distribution relationship network of the users to be analyzed.

[0036] As a preferred technical solution, in step S2, methods such as telephone return visits, email replies, and collection of social media comments belong to the feedback data collation module. The feedback data collation module is provided with an identity division unit, and the identity division unit divides the personnel attributes into target users, potential users, and other relevant personnel.

[0037] As a preferred technical solution, in step S3, the feedback data is applied to the data parameter distribution module. The data parameter distribution module divides the feedback data into benchmark user data and adjusted user data, obtains the benchmark user mining parameter distribution and the adjusted user mining parameter distribution, and analyzes the associated mining error indicators corresponding to the mining networks of various users.

[0038] As a preferred technical solution, in step S4, the methods of open discussion and brainstorming belong to the organizational innovation workshop module. Among them, the interior of the organizational innovation workshop module is divided into regions, and information on different aspects of competing products is obtained according to the divided regions.

[0039] As a preferred technical solution, in step S5, the methods of product front-end analysis and product back-end analysis belong to the demand product comparison module. The demand product comparison module is provided with an independent storage unit and a corresponding division unit. The independent storage unit is provided with storage blocks for product positioning, product structure, product experience, product function, and profit model. The corresponding division unit is provided with instruction documents, technical documents, and open source system blocks.

[0040] As a preferred technical solution, in step S6, a confirmation requirement mining direction module is internally set in the data division.

[0041] In summary, the present invention can conduct market research on user groups, enabling the construction of a user distribution relationship network to be analyzed and obtaining the basic information of corresponding users. At the same time, it analyzes the data on the types of user subgroups corresponding to the user group distribution representation vectors, and then collects feedback data through channels such as telephone follow-up, email replies, and social media comments in customer feedback, so as to generate a distribution of group user mining parameters based on the data on the types of user subgroups and the group user data representation vectors of the user distribution relationship network to be analyzed. Combining with the insights deeply mined from existing customer data in data analysis, it facilitates the digitalization of the types and distribution coordinates of user groups, thereby determining the corresponding relevant users, and then through innovative product and competitor analysis, obtaining the requirements in different fields until the required mining direction is completed and any product is achieved. Based on the foregoing content, since in the process of user demand mining operation, it analyzes the user attribute data of corresponding users, making the analysis basis more sufficient and excluding more influencing factors. Therefore, the mined information can accurately meet the needs of users.

[0042] Embodiment III

[0043] To implement the product mining method based on big data analysis provided by this application, a system accessing the Internet is disclosed, including a big data collection module, a feedback data sorting module, a data parameter distribution module, an organizational innovation workshop module, a demand product comparison module, and a confirmation of demand mining direction module. All the above modules are separately set in physical hardware, and each module corresponds to a physical hardware.

[0044] As a preferred technical solution, the big data collection module, the feedback data sorting module, the data parameter distribution module, the organizational innovation workshop module, the demand product comparison module, and the confirmation of demand mining direction module are sequentially connected for data transmission, and the big data collected and analyzed is stored in the big data storage.

[0045] When this system executes the method, the big data collection module will collect the basic information of users obtained through online and offline means, and determine whether there is a relevant relationship between the users to be analyzed and the distribution positions of the users, forming a corresponding user distribution relationship network to be analyzed.

[0046] The big data collection module will transmit the processed basic information of users to the feedback data sorting module. The user can obtain feedback data through methods such as telephone follow-up, email replies, and collection of social media comments set in the feedback data sorting module. After that, the feedback data sorting module will divide the personnel attributes into target users, potential users, and other relevant personnel according to the obtained feedback data.

[0047] The feedback data collation module transmits the feedback data to the data parameter distribution module. The data parameter distribution module divides the feedback data into benchmark user data and adjusted user data, derives the benchmark user mining parameter distribution and the adjusted user mining parameter distribution, and analyzes the associated mining error indicators corresponding to various types of user mining networks. Based on the current data, the module analyzes the customer's behavior, purchase records and reasons for loss, summarizes user needs and trends, and summarizes the probability of new products.

[0048] The data parameter distribution module transmits data to the organizational innovation workshop module, which has two methods: open discussion and creative stimulation to collect information on different aspects of competitors.

[0049] The organization innovation workshop module transmits data to the product comparison module. The product comparison module is equipped with an independent storage unit and a positioning division unit. The independent storage unit is equipped with product positioning, product structure, product experience, product function and profit model storage blocks, and the positioning division unit is equipped with description documents, technical documents, and open source system blocks. The independent storage unit is the functional area for front-end product analysis, which compares competing products with existing products from different aspects; the undivided unit, that is, the product back-end analysis functional area, stores the description, technology and related systems or information of competing products.

[0050] After completing the user data mining, analysis, product discussion and creative formation, the entire set of data is stored in a big data storage device.

[0051] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. Product mining method based on big data analysis, It is characterized in that The following steps are involved: Collecting basic information of users, determining whether there is a correlation between the users to be analyzed and the distribution positions between the users according to the basic information, and forming a corresponding distribution relationship network of users to be analyzed, in which the distribution relationship between the users to be analyzed is related to the correlation between the users; By recording the user's basic information and obtaining feedback data through telephone calls, email responses and social media comments; Based on the feedback data obtained, we can deeply mine the existing customer data, analyze the customer's behavior, purchase history and reasons for loss based on the current data, summarize the user's needs and trends, and summarize the probability of new products; Based on the new product probability, potential customer needs are discovered and new products that meet user needs are innovated. The new products can be developed and optimized through open discussions and creative stimulation; Conduct competitive product analysis on the new product and other existing products, including product front-end analysis and product back-end analysis; Through demand mining, we can confirm the needs of current target users and specify them to any product.

2. The product mining method based on big data analysis according to claim 1, Features: The basic information is applied to a big data acquisition module, in which coordinate information is provided. The groups of the coordinate information include an original user group and a typical user group. The mining parameter distribution of the original user group is used to reflect the distribution coordinate data of the differential users in the typical user group in the user distribution relationship network to be analyzed.

3. The product mining method based on big data analysis according to claim 1, Features: The telephone return visit, the email reply and the method of collecting social media comments belong to a feedback data sorting module, and an identity division unit is provided in the feedback data sorting module, and the identity division unit divides personnel attributes into target users, potential users and other related personnel.

4. The product mining method based on big data analysis according to claim 1, Features: The feedback data is applied to a data parameter distribution module, which divides the feedback data into benchmark user data and adjusted user data, obtains the benchmark user mining parameter distribution and the adjusted user mining parameter distribution, and analyzes the associated mining error indicators corresponding to various types of user mining networks.

5. The product mining method based on big data analysis according to claim 1, Features: The open discussion and the creative stimulation method belong to the organizational innovation workshop module. The organizational innovation workshop module is divided into areas, and information on different aspects of competitors is obtained based on the divided areas.

6. The product mining method based on big data analysis according to claim 1, Features: The methods of front - end analysis and back - end analysis of the product belong to the demand product comparison module. An independent storage unit and a pairing division unit are provided in the demand product comparison module. In the independent storage unit, there are storage blocks for product positioning, product structure, product experience, product function, and profit model. In the pairing division unit, there are instruction document, technical document, and open - source system blocks.

7. The product mining method based on big data analysis according to claim 1, characterized in that: The method of data division belongs to the module for confirming the demand mining direction.

8. A system for the product mining method based on big data analysis according to any one of claims 1 - 7, characterized in that, The system includes a big data collection module, a feedback data sorting module, a data parameter distribution module, an organizational innovation workshop module, a demand product comparison module, and a module for confirming the demand mining direction.

9. The system for the product mining method based on big data analysis according to claim 8, characterized in that: The big data collection module, the feedback data sorting module, the data parameter distribution module, the organizational innovation workshop module, the demand product comparison module, and the module for confirming the demand mining direction are sequentially connected for data transmission and stored in the computer program.

Images