Product recommendation method and system based on big data
Through big data analysis of user preferences and consumption habits, adjusting the issuance time and denomination of vouchers, solving the problem of excessive vouchers in traditional systems, improving user experience and voucher utilization, and ensuring that users can use it to the maximum extent when needed Vouchers to improve consumption satisfaction.
Patent Information
- Application Number
- CN202410935324.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-12
- Publication Date
- 2024-11-12
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Traditional product recommendation systems push excessive vouchers when users have low consumption demands, which can easily cause user disgust and consumption pressure, and reduce user experience.
Through big data analysis of user preference information, voucher usage behavior and consumption habits, adjust the time and denomination of vouchers, ensure that vouchers can be used to maximize the use of users when they are ready to purchase, and improve user experience and satisfaction.
It improves the accuracy and utilization of vouchers, enhances the user experience, ensures that users can get the maximum discount when needed, and improves consumption satisfaction.
Smart Images

Figure CN118941354A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of product voucher issuance, and in particular to a product recommendation method and system based on big data. Background Art
[0002] With the continuous development of my country's economy, many companies provide online product sales services to consumers through product sales platforms. In order to stimulate consumer consumption, the sales platforms push products through product recommendation systems and regularly issue coupons on the sales platforms to increase the total consumption of the sales platforms.
[0003] In the prior art, the product recommendation system mainly obtains the user's preferred product information from the customer's purchase or browsing history, recommends relevant products that can meet the needs, and stimulates consumption and discovers potential customers by issuing vouchers, so that they can be transformed from browsers to consumers; at the same time, it improves the user's loyalty to the e-commerce system and increases the probability of re-consumption. However, the traditional marketing service system has the problem of excessively pushing vouchers when the user's consumption demand is low, which is easy to cause users' disgust and resistance, and will cause users to have greater consumption pressure and reduce their consumption experience. Therefore, it is very necessary to design a product recommendation method and system based on big data with a high degree of humanization and strong detection ability of recommendation user groups. Summary of the invention
[0004] The purpose of the present invention is to provide a product recommendation method and system based on big data to solve the problems raised in the above background technology.
[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a product recommendation method based on big data, comprising the following steps:
[0006] Step S1: Connecting a product recommendation system to the product sales platform, extracting information about the issuance of vouchers, sales products, and target users' preference values for products on the sales platform through a database;
[0007] Step S2: The system extracts information about the vouchers issued by the product sales platform, detects the user's preference for the product, and analyzes the user's behavior in receiving the vouchers to determine whether the user is ready to consume the vouchers;
[0008] Step S3: The system analyzes the consumption habits of users who use coupons for discount products on the sales platform, counts the time nodes when coupons are issued for such products, obtains the amount of coupons that can be used by users for single and multiple consumption at different time points, and detects the real-time consumption pressure information of users for coupons;
[0009] Step S4: The system calculates the consumer's satisfaction with the use of the voucher by detecting the consumption pressure information, issues the vouchers stored in the product sales platform to the consumer at the corresponding time point, and adjusts the validity period of the voucher denomination.
[0010] According to the above technical solution, step S2 includes:
[0011] Step S21: When the product sales platform detects that the user enters the sales platform for browsing, the stored voucher information is extracted, and the voucher validity period is obtained as t0, where t0 is in hours. If the user collects the voucher on the page at this time, the page hyperlink detection unit recognizes that the voucher collection hyperlink on the mobile terminal sales platform page operated by the user has been used, and then transmits the information that the voucher has been collected to the storage terminal;
[0012] Step S22: The product recommendation system extracts the user's preference value Q for the product of this type through the user data preference storage unit, wherein the value of the preference value is determined according to the number of times the user visits the browsing interface of the product of this type, wherein the user's preference value Q for the product of this type is K times the number of times the user visits the browsing interface of the product of this type, wherein K is the average number of coupons received by the user on the browsing interface;
[0013] Step S23: Possibility of the user consuming the voucher Where Q0 is the total number of refreshed vouchers in the current browsing interface. If the vouchers refreshed in the browsing interface have the same amount every P hours, the number of vouchers with the same amount in the vouchers is recorded as 1, where P is one tenth of the current product voucher validity period t0;
[0014] Step S24: If it is detected that the possibility of the user consuming the voucher exceeds ε%, it is determined that the user is ready to consume the voucher, where ε is a consumption possibility limit ratio value set by the system.
[0015] According to the above technical solution, step S3 includes:
[0016] Step S31: The page timer starts timing after the voucher is issued, and the timing unit stops timing for the first time when the system recognizes that the voucher is received, and the time t2 that has passed since the user received the voucher is obtained;
[0017] Step S32: extract the user's consumption behavior information, and determine the time point when the user consumes by obtaining the click position of the user when using the voucher through the hyperlink detection unit on the user's mobile terminal. When the user places a consumption order, the timer stops for the second time, and the consumption interval time is obtained as t1. If t1>T1, and the consumption pressure of the user when he does not consume the target voucher is detected, the consumption pressure of the user currently consuming the voucher is At the same time, the system obtains the maximum amount of user vouchers based on the collected user data, where T1 is the consumption interval limit time;
[0018] Step S33: The timer continues to count. If the user does not consume the target voucher, the user's consumption pressure of the voucher will increase in real time as time t increases. where t max +t2≤T-T1, T is the time interval for batch issuance of vouchers within the platform, where λ is the conversion level. When it is detected that the user's real-time consumption pressure of vouchers exceeds the maximum demand value FD, the system transmits the information that the consumption pressure has reached the maximum value to the push control terminal of the product sales platform. The push control terminal controls that the same type of vouchers will no longer be issued to the user before the voucher expires. The value of FD is proportional to the average time value between receiving the voucher and using the voucher from the historical records of the user's use of all vouchers retrieved by the system.
[0019] According to the above technical solution, in step S32, the detection method for the system to obtain the maximum superposition amount of the user's consumption voucher includes:
[0020] Step S321: The product recommendation system extracts and stores the information of the vouchers issued by the marketing platform, and randomly selects two vouchers from the vouchers. If the interval between the issuance of the two selected vouchers is less than T and the information of the issued vouchers is within the validity period, it is searched whether they can be used in a superimposed manner. If so, the voucher amount between the voucher with a later issuance time and the next batch issuance time of the vouchers is superimposed, and step S322 is executed; otherwise, the two vouchers are marked as non-superimposable, and two vouchers are selected again from the optional vouchers for retrieval, wherein at least one of the two vouchers selected again is different from the vouchers selected in the previous selection scheme, and the step is stopped until a voucher that can be used in a superimposed manner is retrieved or all vouchers are exhausted and no vouchers that can be used in a superimposed manner are detected;
[0021] Step S322: Based on the stacked vouchers, the system selects another voucher whose issuance interval with the selected voucher is less than T and is still within the validity period to continue stacking, and determines whether the voucher can continue to stack the amount within the selected time period. If it can be stacked, repeat the current operation instruction of step S312 until there are no other vouchers that can be stacked within the current selected time period, and stop stacking, and set the total amount of stacked vouchers currently set to the maximum stacking amount X max , predict the amount of vouchers that users can consume Where n is the number of vouchers corresponding to the maximum stacking amount; otherwise, select the other two vouchers from the available vouchers.
[0022] According to the above technical solution, in step S4, the consumer's satisfaction with the use of the voucher Among them, γ is the unit conversion parameter. If the usage satisfaction does not reach the platform satisfaction limit, the voucher will be issued at the time closest to the consumer's expected consumption time, so that the voucher can be used when the user consumes; if the issuance time belongs to the same batch, the validity period of the voucher that is not included in the screening range will be extended, and the total amount of vouchers that consumers can use during the consumption era will be dynamically controlled to reach 80%.
[0023] According to the above technical solution, the product recommendation system includes a data collection module, a voucher usage analysis module and a product discount recommendation module. The data collection module is used to obtain the validity period information of the product vouchers in the product recommendation system; the voucher usage analysis module is used to determine whether different user groups can use the product vouchers within the validity period, analyze the best time to push vouchers to users, and detect the user's satisfaction with the use of voucher discount products; the product discount recommendation module is used to adjust the issuance time of the single issuance voucher with the closest expected time when it is detected that the user's satisfaction does not reach the platform satisfaction limit.
[0024] According to the above technical solution, the data collection module includes a voucher information collection module, a marketing data collection module and a user preference data storage unit. The voucher information collection module is used to obtain specific information about vouchers issued by the marketing platform; the marketing data collection module is used to obtain specific information about products sold within the marketing platform; and the user preference data storage unit is used to extract and store the preference value information of target users within the marketing platform for platform products.
[0025] According to the above technical solution, the voucher usage analysis module includes a page hyperlink detection unit, a voucher issuance analysis module and a user consumption behavior prediction module. The page hyperlink detection unit is used to detect the voucher collection hyperlink set in the voucher issuance page; the voucher issuance analysis module is used to analyze the user's demand for using vouchers when the marketing platform issues vouchers; the user consumption behavior prediction module is used to predict the user's own consumption habits for voucher discount products.
[0026] According to the above technical solution, the user consumption behavior prediction module includes a consumption pressure analysis submodule and a discount detection submodule. The consumption pressure analysis submodule is used to detect the consumption pressure information of the user after receiving the voucher; the discount detection submodule is used to detect the discount strength obtained by the user using the voucher in each time period.
[0027] According to the above technical solution, the voucher issuance analysis module includes a usage period detection submodule and a consumption possibility screening submodule. The usage period detection submodule is used to detect the corresponding time of the usage period specified for the vouchers when the vouchers are issued in the marketing platform, and detect the time nodes of the user's demand for the vouchers when different vouchers are pushed to the user's mobile terminal; the consumption possibility screening submodule is used to screen the user group who consumes the vouchers.
[0028] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention obtains the number of times the historical user browses the current voucher collection page by extracting the user's preference information, and performs ratio analysis by detecting the number of vouchers collected on the page and comparing the total number of page vouchers refreshed within the monitoring period, thereby obtaining the possibility that the current user consumes the vouchers, thereby improving the accuracy of detecting the use of vouchers by users, and making the screening range of the voucher-using user group more accurate; by slightly adjusting the issuance time of the vouchers and the valid period of the specific vouchers, the user group that can effectively use the vouchers is greatly increased, and the overall user experience is significantly improved; at the same time, by the interval time and the response to the issuance time and valid period of the vouchers, it is ensured that the user can obtain the maximum voucher discount when preparing to purchase, while improving the utilization rate of the issued vouchers, and can also greatly improve the user's consumption satisfaction. 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 flow chart of a method for operating a product recommendation system provided by the present invention;
[0031] Figure 2 It is a schematic diagram of the module composition of a product recommendation system provided by the present invention. DETAILED DESCRIPTION
[0032] 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.
[0033] See also Figure 1 The present invention provides a technical solution: a product recommendation method based on big data, comprising the following steps:
[0034] Step S1: Connecting a product recommendation system to the product sales platform, extracting information about the issuance of vouchers, sales products, and target users' preference values for products on the sales platform through a database;
[0035] Step S2: The system extracts information about the vouchers issued by the product sales platform, detects the user's preference for the product, and analyzes the user's behavior in receiving the vouchers to determine whether the user is ready to consume the vouchers;
[0036] Step S3: The system analyzes the consumption habits of users who use coupons for discount products on the sales platform, counts the time nodes when coupons are issued for such products, obtains the amount of coupons that can be used by users for single and multiple consumption at different time points, and detects the real-time consumption pressure information of users for coupons;
[0037] Step S4: The system calculates the consumer's satisfaction with the use of the voucher by detecting the consumption pressure information, issues the vouchers stored in the product sales platform to the consumer at the corresponding time point, and adjusts the validity period of the voucher denomination.
[0038] The embodiments of the present invention obtain the number of times that historical users browse the current voucher collection page by extracting the user's preference information, and perform ratio analysis by detecting the number of vouchers collected on the page and comparing the total number of page vouchers refreshed within the monitoring period to obtain the possibility that the current user will consume the vouchers, thereby improving the accuracy of detecting the use of vouchers by users and making the screening range of the voucher-using user group more accurate; by slightly adjusting the voucher issuance time and the specific voucher validity period, the user group that can effectively use the vouchers is greatly increased, so that the overall user experience is significantly improved; at the same time, by the interval time and the response to the voucher issuance time and validity period, it is ensured that the user can obtain the maximum voucher discount when preparing to purchase, while improving the utilization rate of the issued vouchers, and greatly improving the user's consumption satisfaction.
[0039] In a preferred embodiment, step S2 comprises:
[0040] Step S21: When the product sales platform detects that the user enters the sales platform for browsing, the stored voucher information is extracted, and the voucher validity period is obtained as t0, where t0 is in hours. If the user collects the voucher on the page at this time, the page hyperlink detection unit recognizes that the voucher collection hyperlink on the mobile terminal sales platform page operated by the user has been used, and then transmits the information that the voucher has been collected to the storage terminal;
[0041] Step S22: The product recommendation system extracts the user's preference value Q for the product of this type through the user data preference storage unit, wherein the value of the preference value is determined according to the number of times the user visits the browsing interface of the product of this type, wherein the user's preference value Q for the product of this type is K times the number of times the user visits the browsing interface of the product of this type, wherein K is the average number of coupons received by the user on the browsing interface;
[0042] Step S23: Possibility of the user consuming the voucher Where Q0 is the total number of refreshed vouchers in the current browsing interface. If the vouchers refreshed in the browsing interface have the same amount every P hours, the number of vouchers with the same amount in the vouchers is recorded as 1, where P is one tenth of the current product voucher validity period t0;
[0043] Step S24: If it is detected that the possibility of the user consuming the voucher exceeds ε%, it is determined that the user is ready to consume the voucher, where ε is a consumption possibility limit ratio value set by the system.
[0044] The user group targeted by the technical solution is the user who is ready to consume the vouchers, so the user group who is ready to consume the vouchers in the target detection group is screened through step S2.
[0045] In the prior art, the time a user stays on the browsing interface can be used as a measure of the user's network interface. However, since the issuance time of the voucher is relatively fixed, some users can directly enter the receiving interface to receive it. Compared with other users who stay on the browsing interface for a long time but do not receive the voucher, they are more likely to consume the voucher. The method cannot be adapted to the screening of the voucher user group. Compared with the prior art, this technical solution extracts the user's preference information, obtains the number of times the historical user browses the current voucher collection page, detects the number of vouchers received on the page through the page hyperlink detection unit, and compares the total number of page vouchers refreshed during the monitoring period for ratio analysis, and obtains the possibility of the current user consuming the voucher, thereby improving the accuracy of the detection of user use of vouchers and making the screening range of the voucher user group more accurate.
[0046] In a preferred embodiment, step S3 includes:
[0047] Step S31: The page timer starts timing after the voucher is issued, and the timing unit stops timing for the first time when the system recognizes that the voucher is received, and the time t2 that has passed since the user received the voucher is obtained;
[0048] Step S32: extract the user's consumption behavior information, and determine the time point when the user consumes by obtaining the click position of the user when using the voucher through the hyperlink detection unit on the user's mobile terminal. When the user places a consumption order, the timer stops for the second time, and the consumption interval time is obtained as t1. If t1>T1, and the consumption pressure of the user when he does not consume the target voucher is detected, the consumption pressure of the user currently consuming the voucher is At the same time, the system obtains the maximum amount of user vouchers based on the collected user data, where T1 is the consumption interval limit time;
[0049] Step S33: The timer continues to count. If the user does not consume the target voucher, the user's consumption pressure of the voucher will increase in real time as time t increases. where t max +t2≤T-T1, T is the time interval for batch issuance of vouchers within the platform, where λ is the conversion level. When it is detected that the user's real-time consumption pressure of vouchers exceeds the maximum demand value FD, the system transmits the information that the consumption pressure has reached the maximum value to the push control terminal of the product sales platform. The push control terminal controls that the same type of vouchers will no longer be issued to the user before the voucher expires. The value of FD is proportional to the average time value between receiving the voucher and using the voucher from the historical records of the user's use of all vouchers retrieved by the system.
[0050] If the user does not use the coupon, the pressure to consume the coupon will gradually increase over time until it expires. The greater the consumption pressure on consumers when they receive the coupons, the more they must go to the target location to consume the coupons within a short period of time. The lower the consumer's satisfaction with the use of the coupons, the more necessary it is to adjust the unified issuance time of the coupons or the validity period of specific coupons as much as possible after determining the coupons that users need to use.
[0051] Consumers also have different consumption habits for different products. For example, when using restaurant meal coupons, consumers collect restaurant vouchers in advance, and consume the vouchers in sequence within the voucher validity period based on their own consumption needs and the voucher validity period information. However, when using coffee vouchers, consumers collect relevant vouchers before consumption and consume coffee. At the same time, the difference in consumption habits is also related to the frequency of issuing vouchers for the consumer product to a certain extent.
[0052] The possibility of users collecting a large number of vouchers at the current time point is determined through the user's consumption habits, and the discount on vouchers currently available to the user is determined.
[0053] Since it is not the case that the higher the consumption desire of the target monitored person, the more frequently the vouchers need to be pushed to the target monitored person. In actual situations, pushing vouchers to the target monitored person too much is likely to cause the target monitored person to feel disgusted, which in turn reduces the frequency of using the vouchers). Through this technical solution, by analyzing the actual needs of the target monitored person and the acceptability of the issuance of vouchers, the amount and validity period of the vouchers are further modified to meet the actual needs of the target monitored person. In this way, it is possible to determine whether the target monitored person will have resistance to the issuance of vouchers when the vouchers are issued again. This quantitative screening of the target monitored person group provides a strong basis for more humane product recommendations.
[0054] In step S32 of this embodiment, the detection method for the system to obtain the maximum superposition amount of the user's consumption voucher includes:
[0055] Step S321: The product recommendation system extracts and stores the information of the vouchers issued by the marketing platform, and randomly selects two vouchers from the vouchers. If the interval between the issuance of the two selected vouchers is less than T and the information of the issued vouchers is within the validity period, it is searched whether they can be used in a superimposed manner. If so, the voucher amount between the voucher with a later issuance time and the next batch issuance time of the vouchers is superimposed, and step S322 is executed; otherwise, the two vouchers are marked as non-superimposable, and two vouchers are selected again from the optional vouchers for retrieval, wherein at least one of the two vouchers selected again is different from the vouchers selected in the previous selection scheme, and the step is stopped until a voucher that can be used in a superimposed manner is retrieved or all vouchers are exhausted and no vouchers that can be used in a superimposed manner are detected;
[0056] Step S322: Based on the stacked vouchers, the system selects another voucher whose issuance interval with the selected voucher is less than T and is still within the validity period to continue stacking, and determines whether the voucher can continue to stack the amount within the selected time period. If it can be stacked, repeat the current operation instruction of step S312 until there are no other vouchers that can be stacked within the current selected time period, and stop stacking, and set the total amount of stacked vouchers currently set to the maximum stacking amount X max , predict the amount of vouchers that users can consume Where n is the number of vouchers corresponding to the maximum stacking amount; otherwise, select the other two vouchers from the available vouchers.
[0057] In a preferred embodiment, step S4, the consumer's satisfaction with the voucher Among them, γ is the unit conversion parameter. If the usage satisfaction does not reach the platform satisfaction limit, the voucher will be issued at the time closest to the consumer's expected consumption time, so that the voucher can be used when the user consumes; if the issuance time belongs to the same batch, the validity period of the voucher that is not included in the screening range will be extended, and the total amount of vouchers that consumers can use during the consumption era will be dynamically controlled to reach 80%.
[0058] The problem that this technical solution needs to solve is: under the premise of maintaining a certain number and amount of vouchers issued by the marketing platform, how to target different consumers' usage habit information on vouchers and change the time nodes for issuing different vouchers so that consumers can make the most of vouchers when consuming, thereby improving consumers' consumption satisfaction, and providing vouchers to consumers when it is detected that consumers have the intention to consume. However, such vouchers can only improve consumers' purchase satisfaction, but cannot stimulate consumers' purchasing needs and increase consumers' consumption desire from "0" to "1". Therefore, the amount of vouchers issued based on consumer monitoring is relatively small; but by observing the vouchers that consumers notice when browsing the marketing platform, consumers' consumption desire can be aroused.
[0059] The improvement made by this technical solution compared with the prior art is: by slightly adjusting the issuance time of the voucher and the useful period of a specific voucher, the user group that can effectively use the voucher is greatly increased, so that the overall user experience is significantly improved.
[0060] How to predict the interval between when consumers browse the marketing platform mall and when they are ready to buy products, and ensure that users can get the maximum voucher discount when they are ready to buy by responding to the interval time and the time and validity period of the voucher issuance, while improving the utilization rate of the vouchers issued, and greatly improving the consumption satisfaction of users.
[0061] The product recommendation system includes a data collection module, a voucher usage analysis module and a product discount recommendation module. The data collection module is used to obtain the validity period information of the product vouchers in the product recommendation system; the voucher usage analysis module is used to determine whether different user groups can use the product vouchers within the validity period, analyze the best time to push vouchers to users, and detect user satisfaction with the use of voucher discount products; the product discount recommendation module is used to adjust the issuance time of the single issuance voucher with the closest expected time when it is detected that the user satisfaction does not reach the platform satisfaction limit.
[0062] The data collection module includes a voucher information collection module, a marketing data collection module and a user preference data storage unit. The voucher information collection module is used to obtain specific information about vouchers issued by the marketing platform; the marketing data collection module is used to obtain specific information about products sold on the marketing platform; and the user preference data storage unit is used to extract and store the preference value information of target users on the marketing platform for platform products.
[0063] The voucher usage analysis module includes a page hyperlink detection unit, a voucher issuance analysis module and a user consumption behavior prediction module. The page hyperlink detection unit is used to detect the voucher collection hyperlink set in the voucher issuance page; the voucher issuance analysis module is used to analyze the user's demand for using vouchers when issuing vouchers on the marketing platform; the user consumption behavior prediction module is used to predict the user's own consumption habits for voucher discount products.
[0064] The user consumption behavior prediction module includes a consumption pressure analysis submodule and a discount detection submodule. The consumption pressure analysis submodule is used to detect the consumption pressure information of users after they receive the vouchers; the discount detection submodule is used to detect the discount strength obtained by users using vouchers in different time periods.
[0065] The voucher issuance analysis module includes a usage period detection submodule and a consumption possibility screening submodule. The usage period detection submodule is used to detect the corresponding time of the usage period of the vouchers when the vouchers are issued in the marketing platform, and to detect the time nodes of the user's demand for the vouchers when different vouchers are pushed to the user's mobile terminal; the consumption possibility screening submodule is used to screen the user groups who consume the vouchers.
[0066] 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.
[0067] Finally, it should be noted that the above description 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 recommendation method based on big data, characterized by: The following steps are involved: Step S1: Connecting a product recommendation system to the product sales platform, extracting information about the issuance of vouchers, sales products, and target users' preference values for products on the sales platform through a database; Step S2: The system extracts information about the vouchers issued by the product sales platform, detects the user's preference for the product, and analyzes the user's behavior in receiving the vouchers to determine whether the user is ready to consume the vouchers; Step S3: The system analyzes the consumption habits of users who use coupons for discount products on the sales platform, counts the time nodes when coupons are issued for such products, obtains the amount of coupons that can be used by users for single and multiple consumption at different time points, and detects the real-time consumption pressure information of users for coupons; Step S4: The system calculates the consumer's satisfaction with the use of the voucher by detecting the consumption pressure information, issues the vouchers stored in the product sales platform to the consumer at the corresponding time point, and adjusts the validity period of the voucher denomination.
2. The product recommendation method based on big data according to claim 1, characterized in that: The step S2 comprises: Step S21: When the product sales platform detects that the user enters the sales platform for browsing, the stored voucher information is extracted, and the voucher validity period is obtained as t0, where t0 is in hours. If the user collects the voucher on the page at this time, the page hyperlink detection unit recognizes that the voucher collection hyperlink on the mobile terminal sales platform page operated by the user has been used, and then transmits the information that the voucher has been collected to the storage terminal; Step S22: The product recommendation system extracts the user's preference value Q for the product of this type through the user data preference storage unit, wherein the value of the preference value is determined according to the number of times the user visits the browsing interface of the product of this type, wherein the user's preference value Q for the product of this type is K times the number of times the user visits the browsing interface of the product of this type, wherein K is the average number of coupons received by the user on the browsing interface; Step S23: Possibility of the user consuming the voucher Where Q0 is the total number of refreshed vouchers in the current browsing interface. If the vouchers refreshed in the browsing interface have the same amount every P hours, the number of vouchers with the same amount in the vouchers is recorded as 1, where P is one tenth of the current product voucher validity period t0; Step S24: If it is detected that the possibility of the user consuming the voucher exceeds ε%, it is determined that the user is ready to consume the voucher, where ε is a consumption possibility limit ratio value set by the system.
3. The product recommendation method based on big data according to claim 2, characterized in that: The step S3 comprises: Step S31: The page timer starts timing after the voucher is issued, and the timing unit stops timing for the first time when the system recognizes that the voucher is received, and the time t2 that has passed since the user received the voucher is obtained; Step S32: extract the user's consumption behavior information, and determine the time point when the user consumes by obtaining the click position of the user when using the voucher through the hyperlink detection unit on the user's mobile terminal. When the user places a consumption order, the timer stops for the second time, and the consumption interval time is obtained as t1. If t1>T1, and the consumption pressure of the user when he does not consume the target voucher is detected, the consumption pressure of the user currently consuming the voucher is At the same time, the system obtains the maximum amount of the user's consumption voucher based on the collected user data, where T1 is the consumption interval limit time; Step S33: The timer continues to count. If the user does not consume the target voucher, the user consumes the voucher consumption pressure in real time as time t increases. where t max +t2≤T-T1, T is the time interval for batch issuance of vouchers within the platform, where λ is the conversion level. When it is detected that the user's real-time consumption pressure of vouchers exceeds the maximum demand value FD, the system transmits the information that the consumption pressure has reached the maximum value to the push control terminal of the product sales platform. The push control terminal controls that the same type of vouchers will no longer be issued to the user before the voucher expires. The value of FD is proportional to the average time value between receiving the voucher and using the voucher from the historical records of the user's use of all vouchers retrieved by the system.
4. The product recommendation method based on big data according to claim 3, characterized in that: In step S32, the system obtains the detection method of the maximum superposition amount of the user's consumption voucher, including: Step S321: The product recommendation system extracts and stores the information of the vouchers issued by the marketing platform, and randomly selects two vouchers from the vouchers. If the interval between the issuance of the two selected vouchers is less than T and the information of the issued vouchers is within the validity period, it is searched whether they can be used in a superimposed manner. If so, the voucher amount between the voucher with a later issuance time and the next batch issuance time of the vouchers is superimposed, and step S322 is executed; otherwise, the two vouchers are marked as non-superimposable, and two vouchers are selected again from the optional vouchers for retrieval, wherein at least one of the two vouchers selected again is different from the vouchers selected in the previous selection scheme, and the step is stopped until a voucher that can be used in a superimposed manner is retrieved or all vouchers are exhausted and no vouchers that can be used in a superimposed manner are detected; Step S322: Based on the stacked vouchers, the system selects another voucher whose issuance interval with the selected voucher is less than T and is still within the validity period to continue stacking, and determines whether the voucher can continue to stack the amount within the selected time period. If it can be stacked, repeat the current operation instruction of step S312 until there are no other vouchers that can be stacked within the current selected time period, and stop stacking, and set the total amount of stacked vouchers currently set to the maximum stacking amount X max , predict the amount of vouchers that users can consume Where n is the number of vouchers corresponding to the maximum stacking amount; otherwise, select the other two vouchers from the available vouchers.
5. The product recommendation method based on big data according to claim 4, characterized in that: In step S4, the consumer's satisfaction with the voucher Among them, γ is the unit conversion parameter. If the usage satisfaction does not reach the platform satisfaction limit, the voucher will be issued at the time closest to the consumer's expected consumption time, so that the voucher can be used when the user consumes; if the issuance time belongs to the same batch, the validity period of the voucher that is not included in the screening range will be extended, and the total amount of vouchers that consumers can use during the consumption era will be dynamically controlled to reach 80%.
6. The product recommendation system based on big data according to claim 5, characterized in that: The product recommendation system includes a data collection module, a voucher usage analysis module and a product discount recommendation module. The data collection module is used to obtain the validity period information of the product vouchers in the product recommendation system; the voucher usage analysis module is used to determine whether different user groups can use the product vouchers within the validity period, analyze the best time to push vouchers to users, and detect the user's satisfaction with the use of voucher discount products; the product discount recommendation module is used to adjust the issuance time of the single issuance voucher with the closest expected time when it is detected that the user's satisfaction does not reach the platform satisfaction limit.
7. The product recommendation system based on big data according to claim 6, characterized in that: The data collection module includes a voucher information collection module, a marketing data collection module and a user preference data storage unit. The voucher information collection module is used to obtain specific information about vouchers issued by the marketing platform; the marketing data collection module is used to obtain specific information about products sold on the marketing platform; and the user preference data storage unit is used to extract and store preference value information of target users on the marketing platform for platform products.
8. The product recommendation system based on big data according to claim 7, characterized in that: The voucher usage analysis module includes a page hyperlink detection unit, a voucher issuance analysis module and a user consumption behavior prediction module. The page hyperlink detection unit is used to detect the voucher collection hyperlink set in the voucher issuance page; the voucher issuance analysis module is used to analyze the user's demand for using vouchers when the marketing platform issues vouchers; the user consumption behavior prediction module is used to predict the user's own consumption habits for voucher discount products.
9. The product recommendation system based on big data according to claim 8, characterized in that: The user consumption behavior prediction module includes a consumption pressure analysis submodule and a discount detection submodule. The consumption pressure analysis submodule is used to detect the consumption pressure information of the user after receiving the cash voucher; the discount detection submodule is used to detect the discount strength obtained by the user using the cash voucher in each time period.
10. The product recommendation system based on big data according to claim 9, characterized in that: The voucher issuance analysis module includes a usage period detection submodule and a consumption possibility screening submodule. The usage period detection submodule is used to detect the time corresponding to the usage period specified for the vouchers when the vouchers are issued in the marketing platform, and detect the time nodes of the user's demand for the vouchers when different vouchers are pushed to the user's mobile terminal; the consumption possibility screening submodule is used to screen the user group who consumes the vouchers.
