Intelligent information system integrated service platform based on big data

Abstract

The invention discloses an intelligent information system integration service platform based on big data, and relates to the technical field of information integration services, the intelligent information system integration service platform comprises an intelligent data collection module, an information integration module and an intelligent push module, the comprehensive type data comprises user type data and commodity type data, the information integration module is used for integrating the comprehensive type data, determining relevance in the comprehensive type data through data analysis and setting a commodity trend function through the commodity type data collected in a historical time period, and the intelligent pushing module is used for pushing the commodity trend function to the user type data. And the intelligent pushing module is used for setting a multi-objective constraint optimization function of information integration intelligent pushing, solving the multi-objective constraint optimization function based on constraint conditions by taking a commodity trend function for maximizing different commodity categories as an objective function, integrating an optimization result and user portrait data, formulating an intelligent pushing strategy and realizing accurate commodity pushing.

Description

Technical Field

[0001] The present invention belongs to the technical field of information integration services, and in particular relates to an intelligent information system integration service platform based on big data. Background Art

[0002] Information integration refers to the use of unified standards, specifications and coding for the information of each subsystem and user in the system to achieve information sharing across the entire system, thereby enabling interaction and orderly work between related user software. It is an important direction for the development of information systems, which helps to improve the overall efficiency of the system and achieve optimal allocation and efficient use of resources.

[0003] In the field of product information push, due to differences in data formats and standards between different systems and technical platforms, data is difficult to share between different systems, forming information islands. This not only limits the efficiency of data utilization, but also increases the difficulty of data integration. In addition, data is often fragmented, that is, data is scattered in different systems and databases, lacking unified management and integration. This fragmented state is not conducive to in-depth analysis and mining of data, thus affecting the accuracy and effectiveness of product information push.

[0004] Therefore, it is urgent to provide an intelligent information system integration service technology based on big data. By adopting a unified data format and standard, data sharing and intercommunication between different systems can be realized. This breaks the information island, enables data to flow freely between different systems, improves the efficiency of data utilization, realizes comprehensive data integration and unified management, and provides strong support for product information push. With the continuous development of technology, the application of intelligent data collection modules will become more and more extensive, bringing more innovations and opportunities to the field of product information push. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent information system integration service platform based on big data, which is used to solve the technical problem that it is difficult to achieve comprehensive integration and unified management of data in the prior art.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions: An intelligent information system integration service platform based on big data, including: an intelligent data collection module, an information integration module, and an intelligent push module; The intelligent data collection module is used to collect comprehensive data within a preset time period, and the comprehensive data includes user data and commodity data. User type data includes the user's age range, gender, and shopping information; Product type data includes sales unit price, sales quantity, sales time, negative review rate and sales channel distribution of different categories of products; The information integration module is used to integrate comprehensive data and determine the correlation in the comprehensive data through data analysis. The commodity trend function is set through the commodity type data collected in the historical time period. The user profile data is determined by extracting the user type data who purchased a specific commodity category through a specific sales channel within a specific time period. The intelligent push module is used to set the multi-objective constraint optimization function of information integration intelligent push, with maximizing the commodity trend function of different commodity categories as the objective function, solving the multi-objective constraint optimization function based on the constraint conditions, and formulating the intelligent push strategy by integrating the optimization results with the user portrait data.

[0007] Furthermore, the comprehensive type data within the preset time period is collected, and the specific method is as follows: Determine the duration T as a cycle, divide each cycle into m time periods, and the duration of each time period is t. Within the n cycle durations, collect real-time or historical comprehensive type data from various big data information sources. The comprehensive type data includes user type data and product type data.

[0008] Furthermore, the commodity type data includes: By determining the average sales price of all commodity categories within n periods, different commodity categories are numbered from low to high according to the average sales price, and the commodity type number set is determined as , where i is the product category numbered i, I is the total number of product categories, and the sales channels are numbered and marked in random order to determine the sales channel number set as , in the xth time period, record the product type data of the i-th product type number in the j-th sales channel as , It is a data set that includes average sales price, total sales quantity, sales negative review rate, and sales time.

[0009] Furthermore, the commodity trend function is set by using the commodity type data collected in the historical time period. The specific method is as follows: Using the formula represents the commodity trend function, where It represents the product trend function of the i-th product type number sold in the j-th sales channel in the x-th time period, It represents the average sales price of the i-th product type number when it is sold in the j-th sales channel during the x-th time period. It represents the average sales cost of the i-th product type number when it is sold in the j-th sales channel in the x-th time period. It represents the total sales quantity of the i-th product type number when it is sold in the j-th sales channel during the x-th time period. It represents the negative sales review rate of the i-th product type number when it is sold in the j-th sales channel in the x-th time period. It means that the sales time of the i-th product type number sold in the j-th sales channel in the x-th time period is recorded as the sales time. The weight coefficient representing the average sales price, represents the weight coefficient of the total sales quantity, Represents the weight coefficient of the negative sales review rate, It represents the weight coefficient of sales time, and e represents the base of the logarithm of natural numbers.

[0010] Furthermore, the negative sales review rate refers to the ratio of the number of negative reviews given by customers through a sales channel to the total number of reviews for a certain product category after it is sold through a certain channel within a period of time; Sales time refers to the average length of time required to sell a product of a certain product category through a certain sales channel within a certain time period.

[0011] Furthermore, the user profile data is determined by extracting the user type data who purchased a specific category of goods through a specific sales channel within a specific time period. The specific method is as follows: User portrait data refers to the main age group data of commodity consumption users. The age groups are divided by g. The difference between the maximum age and the minimum age in each age group is g. A is the initial age and A is the ending age. m age groups are divided between a and A by g. The number of users in each age group is determined and a threshold B is set. When the ratio of characteristic user data in a certain age group to characteristic user data in the total age group is greater than or equal to B, the age group is judged to be the main age group of commodity consumption users. Otherwise, the age group is not the main age group of commodity consumption users.

[0012] Furthermore, a multi-objective constraint optimization function for information integration and intelligent push is set to maximize the commodity trend function of different commodity categories as the objective function. The specific method is as follows: Using the formula represents the multi-objective constrained optimization function for different commodity categories, where i represents the number of the i-th commodity type, j represents the j-th sales channel, x represents the x-th time period, J represents a total of J sales channels, m represents a total of m time periods, Fr(i) represents the best commodity trend indicator for the i-th commodity type, It represents the product trend function of the i-th product type number sold in the j-th sales channel in the x-th time period, The exponential part is the base of the natural logarithm of the impulse function, t is the length of a time period, and c is a constant.

[0013] Furthermore, based on the constraints, the multi-objective constraint optimization function is solved, and the optimization results and user portrait data are integrated to formulate an intelligent push strategy. The specific method is as follows: The constraint condition of sales time limit is expressed as follows: the product with product type number i is restricted from being sold in a certain sales channel after a certain time period; The constraint condition of sales channel restriction is expressed as follows: the product with product type number i is restricted from being sold in a certain sales channel within a certain time period; The optimization algorithm is used to solve the multi-objective constrained optimization function to obtain the best product trend index for each product type in each time period and sales channel. The optimization results are combined with user portrait data to formulate an intelligent push strategy to determine which sales channels should be used to push which product categories with the largest product trend index to which age groups in different time periods. Product push is implemented according to the intelligent push strategy, and sales data after the push is collected to evaluate the push effect. Based on the evaluation results, necessary adjustments and optimizations are made to the push strategy to ultimately achieve accurate product push.

[0014] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are: 1. The present invention can quantify the sales effect of different commodity categories when they are sold through different sales channels in different time periods by collecting the commodity trend function set by comprehensive type data, and help enterprises identify which sales channels and time periods are most beneficial to the sales of specific commodity categories. By extracting the user type data who purchases a specific commodity category through a specific sales channel in a specific time period, important user portrait data is constructed, which helps enterprises to more accurately understand the characteristics of the target user group, such as the main age group, etc.; 2. The present invention sets a multi-objective constraint optimization function to maximize the commodity trend function of different commodity categories, while considering constraints such as sales time restrictions and sales channel restrictions, and formulates an intelligent push strategy, which helps to improve the accuracy and effectiveness of the push, and can push the most suitable commodities to the target user groups according to the characteristics of different commodity categories, time periods and sales channels. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1A flowchart of an intelligent information system integration service platform based on big data is shown; Figure 2 A method step diagram of intelligent information system integration service based on big data is shown. DETAILED DESCRIPTION

[0017] 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.

[0018] like Figure 1 , Figure 2 The intelligent information system integration service platform based on big data shown in the figure specifically includes: an intelligent data collection module, an information integration module, and an intelligent push module; An intelligent data collection module is used to collect comprehensive type data, determine a period T as a cycle length, divide each cycle length into m time periods, and the length of each time period is t. Within the n cycle length, obtain real-time or historical comprehensive type data from various big data information sources, such as social media platform information sources, transaction platform information sources, commodity sales channel platform information sources, and personal behavior log information. The comprehensive type data includes user type data and commodity type data, wherein the user type data includes the user's age range, gender, and shopping information, and the commodity type data includes the sales unit price, sales quantity, sales time, negative review rate, and sales channel distribution of different categories of commodities; Determine the average sales price of all commodity categories within n periods, and number different commodity categories from low to high according to their average sales prices, thereby determining a set of commodity type numbers divided by price, and record this set of commodity type numbers as , where i is the product category numbered i, I is the total number of product categories, and the sales channels of different product types are further numbered and marked in random order to determine the sales channel number set, which is recorded as , in the xth time period, record the product type data of the i-th product type number in the j-th sales channel as ,in It is a data set containing the average sales price, total sales quantity, negative sales review rate, and sales time of the i-th product type number when it is sold in the j-th sales channel in the x-th time period. The negative sales review rate refers to the ratio of the number of negative reviews feedback from customers through a sales channel to the total number of reviews after a certain product category is sold through a certain channel in a period of time. The sales time refers to the average length of time required to sell a product when a certain product category is sold through a certain sales channel in a certain time period.

[0019] The information integration module is used to integrate comprehensive data and determine the correlation in the comprehensive data through data analysis. The commodity trend function is set through the commodity type data collected in the historical time period to filter the sales channels that are beneficial to different commodity categories. The specific expression of the commodity trend function is as follows: ; in, It represents the product trend function of the i-th product type number sold in the j-th sales channel in the x-th time period, It represents the average sales price of the i-th product type number when it is sold in the j-th sales channel during the x-th time period. It represents the average sales cost of the i-th product type number when it is sold in the j-th sales channel in the x-th time period. It represents the total sales quantity of the i-th product type number when it is sold in the j-th sales channel during the x-th time period. It represents the negative sales review rate of the i-th product type number when it is sold in the j-th sales channel in the x-th time period. It means that the sales time of the i-th product type number sold in the j-th sales channel in the x-th time period is recorded as the sales time. The weight coefficient representing the average sales price, represents the weight coefficient of the total sales quantity, Represents the weight coefficient of the negative sales review rate, It represents the weight coefficient of sales time, and e represents the base of the logarithm of natural numbers.

[0020] By setting the commodity trend function, a large number of commodity type data are integrated to quantify the sales effects of different commodity categories when they are sold through different sales channels in different time periods. The larger the value of the commodity trend function, the better the sales effect of the specific commodity category when it is sold through a specific sales channel in a specific time period. Conversely, the smaller the value of the commodity trend function, the worse the sales effect of the specific commodity category when it is sold through a specific sales channel in a specific time period.

[0021] By extracting the user type data who purchased a specific commodity category through a specific sales channel within a specific time period, this type of user type data is recorded as characteristic user data, and the important user portrait data of the corresponding commodity category through the corresponding sales channel within the corresponding time period is established through the characteristic user data. The user portrait data refers to the main age group data of commodity consumption users. The age groups are divided into g, and the difference between the maximum age and the minimum age contained in each age group is g. A is the initial age and A is the end age. M age groups are divided between a and A through g, and the number of users in each age group is determined. A threshold B is set. When the ratio of characteristic user data in a certain age group to characteristic user data in the total age group is greater than or equal to B, the age group is judged to be the main age group of commodity consumption users. Otherwise, the age group is judged not to be the main age group of commodity consumption users. The intelligent push module is used to set the multi-objective constraint optimization function of information integration intelligent push, taking the maximization of the commodity trend function of different commodity categories as the objective function, taking the sales time limit and sales channel limit as the constraint conditions, and establishing the multi-objective constraint optimization function for different commodity categories. The specific expression of the multi-objective constraint optimization function is as follows: ; Where i represents the number of the i-th commodity type, j represents the j-th sales channel, x represents the x-th time period, J represents a total of J sales channels, m represents a total of m time periods, and Fr(i) represents the best commodity trend indicator for the i-th commodity type. It represents the product trend function of the i-th product type number sold in the j-th sales channel in the x-th time period, The exponential part represents the base of the natural number logarithm of the impulse function, t represents the length of a time period, and c represents a constant. In this embodiment, c=1; The constraint condition of sales time limit is expressed as follows: the product with product type number i is restricted from being sold in a certain sales channel after a certain time period; The constraint condition of sales channel restriction is expressed as follows: the product with product type number i is restricted from being sold in a certain sales channel within a certain time period; The optimization algorithm is used to solve the multi-objective constrained optimization function to obtain the best product trend indicators for each product type in each time period and sales channel. The optimization results are combined with user portrait data to formulate an intelligent push strategy to determine which product categories should be pushed to which age groups through which sales channels in different time periods. Product push is implemented according to the intelligent push strategy, and sales data after the push is collected to evaluate the push effect. Based on the evaluation results, necessary adjustments and optimizations are made to the push strategy to ultimately achieve accurate product push.

[0022] 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.

[0023] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. An intelligent information system integration service platform based on big data, characterized in that: include: An intelligent data collection module is used to collect comprehensive type data within a preset time period, and the comprehensive type data includes user type data and commodity type data; User type data includes the user's age range, gender, and shopping information; Product type data includes sales unit price, sales quantity, sales time, negative review rate and sales channel distribution of different categories of products; The information integration module is used to integrate comprehensive data and determine the correlation in the comprehensive data through data analysis. The commodity trend function is set through the commodity type data collected in the historical time period. The user profile data is determined by extracting the user type data who purchased a specific commodity category through a specific sales channel within a specific time period. The intelligent push module is used to set the multi-objective constraint optimization function of information integration intelligent push, with maximizing the commodity trend function of different commodity categories as the objective function, solving the multi-objective constraint optimization function based on the constraint conditions, and formulating the intelligent push strategy by integrating the optimization results with the user portrait data.

2. According to the big data-based intelligent information system integration service platform of claim 1, it is characterized in that: Collect comprehensive data within a preset time period. The specific method is: Determine the duration T as a cycle, divide each cycle into m time periods, and the duration of each time period is t. Within the n cycle durations, collect real-time or historical comprehensive type data from various big data information sources. The comprehensive type data includes user type data and product type data.

3. The intelligent information system integration service platform based on big data according to claim 1 is characterized in that: Product type data, including: By determining the average sales price of all commodity categories within n periods, different commodity categories are numbered from low to high according to the average sales price, and the commodity type number set is determined as , where i is the product category numbered i, I is the total number of product categories, and the sales channels are numbered and marked in random order to determine the sales channel number set as , in the xth time period, record the product type data of the i-th product type number in the j-th sales channel as , It is a data set that includes average sales price, total sales quantity, sales negative review rate, and sales time.

4. According to the big data-based intelligent information system integration service platform of claim 1, it is characterized in that: The commodity trend function is set based on the commodity type data collected during the historical period. The specific method is as follows: Using the formula represents the commodity trend function, where It represents the product trend function of the i-th product type number sold in the j-th sales channel in the x-th time period, It represents the average sales price of the i-th product type number when it is sold in the j-th sales channel during the x-th time period. It represents the average sales cost of the i-th product type number when it is sold in the j-th sales channel in the x-th time period. It represents the total sales quantity of the i-th product type number when it is sold in the j-th sales channel during the x-th time period. It represents the negative sales review rate of the i-th product type number when it is sold in the j-th sales channel in the x-th time period. It means that the sales time of the i-th product type number sold in the j-th sales channel in the x-th time period is recorded as the sales time. The weight coefficient representing the average sales price, represents the weight coefficient of the total sales quantity, Represents the weight coefficient of the negative sales review rate, It represents the weight coefficient of sales time, and e represents the base of the logarithm of natural numbers.

5. According to claim 4, the intelligent information system integration service platform based on big data is characterized in that: Negative sales review rate and sales time, including: The negative sales review rate refers to the ratio of the number of negative reviews given by customers through a sales channel to the total number of reviews for a certain product category after it is sold through a certain channel within a period of time; Sales time refers to the average length of time required to sell a product of a certain product category through a certain sales channel within a certain time period.

6. The intelligent information system integration service platform based on big data according to claim 1, characterized in that: By extracting the user type data who purchased a specific category of goods through a specific sales channel within a specific time period, the user portrait data is determined. The specific method is as follows: User portrait data refers to the main age group data of commodity consumption users. The age groups are divided by g. The difference between the maximum age and the minimum age in each age group is g. A is the initial age and A is the ending age. m age groups are divided between a and A by g. The number of users in each age group is determined and a threshold B is set. When the ratio of characteristic user data in a certain age group to characteristic user data in the total age group is greater than or equal to B, the age group is judged to be the main age group of commodity consumption users. Otherwise, the age group is not the main age group of commodity consumption users.

7. The intelligent information system integration service platform based on big data according to claim 1 is characterized in that: Set up a multi-objective constraint optimization function for information integration and intelligent push, with maximizing the commodity trend function of different commodity categories as the objective function. The specific method is as follows: Using the formula represents the multi-objective constrained optimization function for different commodity categories, where i represents the number of the i-th commodity type, j represents the j-th sales channel, x represents the x-th time period, J represents a total of J sales channels, m represents a total of m time periods, Fr(i) represents the best commodity trend indicator for the i-th commodity type, It represents the product trend function of the i-th product type number sold in the j-th sales channel in the x-th time period, The exponential part is the base of the natural logarithm of the impulse function, t is the length of a time period, and c is a constant.

8. The intelligent information system integration service platform based on big data according to claim 1, characterized in that: Solve the multi-objective constraint optimization function based on the constraint conditions, integrate the optimization results with the user portrait data, and formulate an intelligent push strategy. The specific method is as follows: The constraint condition of sales time limit is expressed as follows: the product with product type number i is restricted from being sold in a certain sales channel after a certain time period; The constraint condition of sales channel restriction is expressed as follows: the product with product type number i is restricted from being sold in a certain sales channel within a certain time period; The optimization algorithm is used to solve the multi-objective constrained optimization function to obtain the best product trend index for each product type in each time period and sales channel. The optimization results are combined with user portrait data to formulate an intelligent push strategy to determine which sales channels should be used to push which product categories with the largest product trend index to which age groups in different time periods. Product push is implemented according to the intelligent push strategy, and sales data after the push is collected to evaluate the push effect. Based on the evaluation results, necessary adjustments and optimizations are made to the push strategy to ultimately achieve accurate product push.

Images