Right and interest product recommendation method, system, equipment and medium

Through the rule engine easyRule and the code modular rule unit, the problem of traditional hard-code difficult to meet the rapid iteration of equity products and business expansion is solved, and flexible equity products are recommended and maintenance costs are reduced.

CN119006091AInactive Publication Date: 2024-11-22SHANGHAI GARLIC SPROUT INFORMATION TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410964390.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-18
Publication Date
2024-11-22
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Traditional hard-coded methods are difficult to meet the requirements of rapid iteration of equity products and flexible business expansion, and the maintenance cost of recommendation rules is high, so non-technical personnel cannot quickly adjust their recommendation strategies.

Method used

The rule unit formed by the rules engine easyRule is adopted to match the rule feature values ​​based on the user's behavior information and system context information, generate operation expressions and calculate them, and determine the rule facts, thereby realizing the recommendation of equity products.

Benefits of technology

It reduces the maintenance cost of recommendation rules, enhances the flexibility and packaging capabilities of equity products, and provides complete equity life cycle management.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119006091A_ABST
    Figure CN119006091A_ABST
Patent Text Reader

Abstract

The invention discloses a right and interest product recommendation method, system and device and a medium. The method comprises the steps of obtaining related information of all to-be-recommended on-sale products in a current browsing page of a user; after a recommendation instruction is received, executing calculation on the rule units of which the rule characteristic values are matched and completed according to the system context information through a rule engine eyRule to obtain result data; determining an operation expression of each rule group based on the result data; performing calculation on the operation expression again by using a rule engine easyRule to generate a rule fact; and recommending the right and interest product corresponding to the fact that the rule is true as a target right and interest product. According to the invention, the rule units formed by modularization of reusable codes are used for selection when a product recommendation strategy is changed, and online recommendation logic change is realized before project release; the rule units and the operation expressions are calculated in sequence through a rule engine easyRule, right and interest product recommendation is carried out according to rule facts, and the requirements for rapid iteration and flexible business expansion of right and interest products are met.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of information management technology, and in particular to a method, system, device and medium for recommending equity products. Background Art

[0002] With the rapid development of the Internet, the concept of equity is widely used in the Internet industry, and a large number of equity providers and related equity products have emerged. Taking the mobile phone ticket booking software product, Zhixing Train Ticket APP (hereinafter referred to as Zhixing) as an example, it is accompanied by equity products such as ticket grabbing products, acceleration package products, video membership products, and high-speed rail catering products.

[0003] Different pages of the hotel business line, air ticket business line, and train business line need to bundle and recommend different equity products. Each business line needs to continuously adjust and enrich the types of equity products in response to market changes. The traditional hard-coded implementation method is difficult to meet the requirements of rapid iteration of equity products and flexible business expansion, and the maintenance cost of recommendation rules is high, and non-technical personnel cannot quickly adjust the recommendation strategy. Summary of the invention

[0004] The technical problem to be solved by the present invention is to overcome the defect that the traditional hard-coded implementation method in the prior art is difficult to meet the requirements of rapid iteration of equity products and flexible business expansion, and to provide a recommendation method, system, device and medium for equity products.

[0005] The present invention solves the above technical problems through the following technical solutions:

[0006] In a first aspect, the present invention provides a method for recommending equity products, the method comprising:

[0007] Obtaining all information related to the bundled products to be recommended under the user's current browsing page; the bundled product related information includes at least one of product rights list information, user's relevant behavior information and system context information pre-stored on the platform, the product rights list information includes a plurality of rights products, each of the rights products corresponds to a rule group in each bundled sale scenario, and the rule group includes a plurality of rule units with specific logic operation functions formed by code modularization;

[0008] The rule engine easyRule performs calculation on the rule unit that matches the rule feature value according to the system context information to obtain result data;

[0009] Determine an operation expression of each rule group based on the result data;

[0010] The rule engine easyRule is used to perform calculations on the operation expression again to generate a rule fact; the rule fact includes true or false, and when the rule fact is true, it means that the user meets the recommendation requirements of the current rule group, and when the rule fact is false, it means that the user does not meet the recommendation requirements of the current rule group;

[0011] The equity product corresponding to the true rule fact is recommended as the target equity product.

[0012] Preferably, before the step of using the rule engine easyRule to perform calculation on the rule unit that completes the rule feature value according to the system context information matching, the method further includes:

[0013] When a recommendation instruction is received, the rule feature value of the rule unit is verified according to the relevant behavior information and the system context information to filter out invalid rules of the rule group.

[0014] Preferably, the step of determining the operation expression of each rule group based on the result data comprises:

[0015] The result data corresponding to the rule unit are combined into the operation expression of the corresponding rule group through the decision factor mvel.

[0016] Preferably, the step of using the rule engine easyRule to recalculate the operation expression to generate a rule fact includes:

[0017] Obtaining the priority rule of the rule group;

[0018] According to the priority rule, the operation expression is delivered to the rule engine easyRule for calculation to generate the rule fact.

[0019] In a second aspect, the present invention provides a recommendation system for equity products, the recommendation system comprising:

[0020] an acquisition module, used to acquire all information related to the bundled products to be recommended under the page currently browsed by the user; the information related to the bundled products includes at least one of product rights list information, user related behavior information and system context information pre-stored on the platform; the product rights list information includes a plurality of rights products, each of which corresponds to a rule group in each bundled scenario, and the rule group includes a plurality of rule units with specific logic operation functions formed by code modularization;

[0021] A first calculation module, configured to perform calculations on the rule unit whose rule feature value is matched according to the system context information through the rule engine easyRule to obtain result data;

[0022] A determination module, used for determining an operation expression of each rule group based on the result data;

[0023] The second calculation module is used to use the rule engine easyRule to perform calculations on the operation expression again to generate a rule fact; the rule fact includes true or false, and when the rule fact is true, it means that the user meets the recommendation requirements of the current rule group, and when the rule fact is false, it means that the user does not meet the recommendation requirements of the current rule group;

[0024] The recommendation module is used to recommend the equity product corresponding to the true rule fact as a target equity product.

[0025] Preferably, the recommendation system further includes:

[0026] The verification module is used to verify the rule feature value of the rule unit according to the relevant behavior information and the system context information after receiving the recommendation instruction to filter out invalid rules of the rule group.

[0027] Preferably, the determining module is specifically used for:

[0028] The result data corresponding to the rule unit are combined into the operation expression of the corresponding rule group through the decision factor mvel.

[0029] Preferably, the second calculation module comprises:

[0030] An acquisition unit, used for acquiring the priority rule of the rule group;

[0031] The calculation unit is used to deliver the operation expression to the rule engine easyRule to perform calculation according to the priority rule to generate the rule fact.

[0032] In a third aspect, the present invention provides an electronic device comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the equity product recommendation method as described above when executed by the processor.

[0033] In a fourth aspect, the present invention provides a computer-readable storage medium, a computer program stored on the computer-readable storage medium, and the computer program, when executed by a processor, implements the equity product recommendation method as described above.

[0034] The positive and progressive effect of the present invention is that the present invention uses rule units formed by code modularization to reduce the maintenance cost of recommendation rules, and uses the rule engine easyRule to perform calculations on rule units and operation expressions in sequence, recommends equity products based on rule facts, enhances the flexibility of equity product packaging, and provides complete equity life cycle management. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 This is a flow chart of the method for recommending equity products according to Example 1 of the present invention.

[0036] Figure 2 This is a schematic diagram of the application of the method for recommending equity products according to Example 1 of the present invention.

[0037] Figure 3 This is a schematic diagram of the first module of the equity product recommendation system of Example 2 of the present invention.

[0038] Figure 4 This is a schematic diagram of the second module of the equity product recommendation system of Example 2 of the present invention.

[0039] Figure 5 This is a schematic diagram of the structure of an electronic device for implementing a method for recommending equity products according to Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0040] The present invention is further described below by way of examples, but the present invention is not limited to the scope of the examples.

[0041] Example 1

[0042] The recommendation method of the equity product in this embodiment is as follows: Figure 1 As shown, the recommended method includes:

[0043] S11. Obtaining all information related to the bundled products to be recommended under the page currently browsed by the user; the information related to the bundled products includes at least one of product rights list information, user related behavior information, and system context information pre-stored on the platform; the product rights list information includes a number of rights products, each of which corresponds to a rule group in each bundled scenario, and the rule group includes a number of rule units with specific logical operation functions formed by code modularization;

[0044] S12, using the rule engine easyRule to perform calculations on the rule units whose rule feature values ​​are matched according to the system context information to obtain result data;

[0045] S13, determining the operation expression of each rule group based on the result data;

[0046] S14, using the rule engine easyRule to perform calculations on the operation expression again to generate rule facts; rule facts include true or false, when the rule fact is true, it means that the user meets the recommendation requirements of the current rule group, and when the rule fact is false, it means that the user does not meet the recommendation requirements of the current rule group;

[0047] S15. The equity product corresponding to the true rule fact is recommended as the target equity product.

[0048] For the above step S11, when it is detected that the user is browsing information through the Internet APP platform, all the information to be recommended under the current browsing page (for example, the price position of the X page of smart travel) including the product rights list information, the user's relevant behavior information and the system context information pre-stored by the platform are obtained. The product rights list information may include the designated lower berth, night ticket issuance, worry-free refund and change, lounge, ticket grabbing coupon, compensation for failure to grab or golden finger and other rights products under the train ticket purchase or smart travel business offline. The user's relevant behavior information includes the user's historical browsing information and the user's historical order information, etc. The user's relevant behavior information includes the relevant information of the order under the current request link, such as the flight information.

[0049] For the above steps S12-S14, all rule units in each rule group match the corresponding feature values ​​in the information in the system context and deliver them to the rule engine easyRule for data initial run to obtain result data. The result data corresponding to each rule unit is true or false. The result data corresponding to the rule units in the rule group are combined into operation expressions through mvel. The rule engine easyRule performs calculations again on the operation expressions including true or false to obtain rule facts.

[0050] For the above step S15, obtain the rule facts corresponding to each rule group and the priority order of the rule groups, and recommend the equity product with the highest priority and true rule facts as the target equity product. Alternatively, two equity products with the highest priority and true rule facts can be recommended as target equity products.

[0051] For example, the current train shelf page bundles the benefits product A for enjoying travel, the benefits product B for safe travel, and the benefits product C for smooth travel. The recommendation rule for the benefits product A is that the ticket price is greater than 50 (a) and the user is a new customer (b), and a+b is used to represent the rule group O; the recommendation rule for the benefits product B is that the ticket price is less than 50 (c) and the user is a new customer (b), and c+b is used to represent the rule group P; the recommendation rule for the benefits product C is that the ticket price is greater than 50 (a) and the user is a new customer (b) and the order has been placed in the last three months (d), and a+b+d is used to represent the rule group Q. When the user browses to the train shelf page, the list of all effective product benefits on the train shelf is obtained, that is, the three rule groups O, P, and Q. From the user's relevant behavior information and the system context information pre-stored on the platform, it is obtained that the user is a new customer, the ticket price is 60, and there is an order record in the last three months.

[0052] Extract the rule units and perform the initial run to get the result data, that is, calculate the result data of the four rule units a, b, c and d, which are a: true, b: true, c: false, d: true respectively. Determine the operation expression corresponding to each rule group based on the result data. The operation expression corresponding to rule group O is a and b, the operation expression corresponding to rule group P is b and c, and the operation expression corresponding to rule group Q is a and b and d. Deliver the operation expression to the rule engine easyRule for secondary calculation. The operation expression can be executed in sequence according to the priority order of the rule group, and the rule fact generated is that rule group P is not satisfied, and rule group O and rule group Q are satisfied at the same time. However, since rule group Q has a higher priority, the operation expression corresponding to rule group Q is executed first. When rule group Q is executed to meet the recommendation requirements of the user's current rule group, the product rights and interests corresponding to rule group Q are recommended, that is, the Smooth Travel C rights and interests product is recommended.

[0053] In an optional embodiment, after receiving the step of the recommendation instruction, the recommendation method further includes:

[0054] S111 . After receiving the recommendation instruction, the rule feature values ​​of the rule unit are verified according to the relevant behavior information and the system context information to filter out invalid rules of the rule group.

[0055] Specifically, the train ticket page X now bundles the D package benefit product and the new X benefit package E benefit product. The recommendation rule for the D benefit product is that the ticket price is greater than 100 (a) and the user is an old customer (b) and the user account does not have the peace of mind refund and change benefit issued by the paid black diamond (c) and is not a risk control user (d). The recommendation rule for the E benefit product is a non-risk control user (d). The rule feature value of the rule unit a, the fare, needs to be passed from the requesting business party. However, when the fare rule feature value is verified, if it is detected that the business party does not pass it or the fare input is illegal (<0), all rule units involving the fare rule feature value and the rule group including the rule unit are eliminated. The operation expression (a+b+c+d) corresponding to the D benefit product contains the rule unit a, which will be eliminated and the calculation will not be performed, and the package E corresponding to the E benefit product will be recommended to the user.

[0056] In an optional implementation, step S14 specifically includes:

[0057] S141, obtaining a priority rule of a rule group;

[0058] S142. Deliver the operation expression to the rule engine easyRule to perform calculation according to the priority rule to generate rule facts.

[0059] For the above steps S141-S142, the operation expression corresponding to each rule group is delivered to the rule engine easyRule for calculation according to the order of priority rules of the rule group to obtain the rule facts corresponding to each rule group. When the rule fact is true, it means that the user meets the recommendation requirements of the corresponding rule group. When the rule fact is false, it means that the user does not meet the recommendation requirements of the corresponding rule group.

[0060] In an alternative embodiment, Figure 2 As shown, taking the train page X as an example, first obtain the list of all the equity package rule groups to be recommended on the train page X, and perform a filtering before extracting their rule units for the initial run; verify the rule feature value of each rule unit, which may be obtained by the requester or from the system context information. There are also rule feature values ​​that cannot be passed and need to be assembled in a series before being passed to the rule engine.

[0061] This embodiment provides a method for recommending equity products. The rule units formed by reusable code modularization are provided for selection when the product recommendation strategy is changed, so that the online recommendation logic change can be realized before the project is released. The rule engine easyRule is used to perform calculations on the rule units and operation expressions in sequence, and equity products are recommended according to the rule facts, so as to meet the requirements of rapid iteration of equity products and flexible business expansion.

[0062] Example 2

[0063] The recommendation method of the equity product in this embodiment is as follows: Figure 3 As shown, the recommendation system includes: an acquisition module 210 , a first calculation module 220 , a determination module 230 , a first calculation module 240 and a recommendation module 250 .

[0064] The acquisition module 210 is used to acquire all information related to the bundled products to be recommended under the page currently browsed by the user; the information related to the bundled products includes at least one of product rights list information, user related behavior information and system context information pre-stored on the platform, the product rights list information includes a number of rights products, each rights product corresponds to a rule group in each bundled scenario, and the rule group includes a number of rule units with specific logical operation functions formed by code modularization;

[0065] The first calculation module 220 is used to, after receiving the recommendation instruction, perform calculations on the rule units whose rule feature values ​​are matched according to the system context information through the rule engine easyRule to obtain result data;

[0066] A determination module 230, for determining an operation expression of each rule group based on the result data;

[0067] The second calculation module 240 is used to use the rule engine easyRule to perform calculations on the operation expression again to generate rule facts; the rule facts include true or false, when the rule fact is true, it means that the user meets the recommendation requirements of the current rule group, and when the rule fact is false, it means that the user does not meet the recommendation requirements of the current rule group;

[0068] The recommendation module 250 is used to recommend the equity product corresponding to the true rule fact as the target equity product.

[0069] When it is detected that the user browses information through the Internet APP platform, the acquisition module 210 obtains all the recommended product rights list information under the current browsing page (for example, the price position of the smart travel page X), the user's relevant behavior information and the system context information pre-stored by the platform. The product rights list information may include the designated lower berth, night ticket issuance, worry-free refund and change, lounge, ticket grabbing coupon, compensation for failure to grab or golden finger and other rights products under the train ticket purchase or smart travel business offline. The user's relevant behavior information includes the user's historical browsing information and the user's historical order information, etc. The user's relevant behavior information includes the relevant information of the order under the current request link, such as the flight information.

[0070] The first calculation module 220 matches all rule units under each rule group with the corresponding feature values ​​in the information in the system context and delivers them to the rule engine easyRule for data initial run to obtain result data. The result data corresponding to each rule unit is true or false. The determination module 230 combines the result data corresponding to the rule units in the rule group into an operation expression through mvel. The second calculation module 240 performs calculation again on the operation expression including true or false through the rule engine easyRule to obtain the rule fact.

[0071] The rule facts corresponding to each rule group and the priority order of the rule groups are obtained, and the recommendation module 250 recommends an equity product with the highest priority order and true rule facts as the target equity product, or recommends two equity products with the highest priority order and true rule facts as the target equity products.

[0072] For example, the current train shelf page bundles the benefits product A for enjoying travel, the benefits product B for safe travel, and the benefits product C for smooth travel. The recommendation rule for the benefits product A is that the ticket price is greater than 50 (a) and the user is a new customer (b), and a+b is used to represent the rule group O; the recommendation rule for the benefits product B is that the ticket price is less than 50 (c) and the user is a new customer (b), and c+b is used to represent the rule group P; the recommendation rule for the benefits product C is that the ticket price is greater than 50 (a) and the user is a new customer (b) and the order has been placed in the last three months (d), and a+b+d is used to represent the rule group Q. When the user browses to the train shelf page, the list of all effective product benefits on the train shelf is obtained, that is, the three rule groups O, P, and Q. From the user's relevant behavior information and the system context information pre-stored on the platform, it is obtained that the user is a new customer, the ticket price is 60, and there is an order record in the last three months.

[0073] Extract the rule units and perform the initial run to get the result data, that is, calculate the result data of the four rule units a, b, c and d, which are a: true, b: true, c: false, d: true respectively. Determine the operation expression corresponding to each rule group based on the result data. The operation expression corresponding to rule group O is a and b, the operation expression corresponding to rule group P is b and c, and the operation expression corresponding to rule group Q is a and b and d. Deliver the operation expression to the rule engine easyRule for secondary calculation. The operation expression can be executed in sequence according to the priority order of the rule group, and the rule fact generated is that rule group P is not satisfied, and rule group O and rule group Q are satisfied at the same time. However, since rule group Q has a higher priority, the operation expression corresponding to rule group Q is executed first. When rule group Q is executed to meet the recommendation requirements of the user's current rule group, the product rights and interests corresponding to rule group Q are recommended, that is, the Smooth Travel C rights and interests product is recommended.

[0074] In an alternative embodiment, Figure 4 As shown, the recommendation system also includes:

[0075] The verification module 211 is used to verify the rule feature values ​​of the rule unit according to the relevant behavior information and the system context information to filter out invalid rules of the rule group.

[0076] Specifically, the train ticket page X now bundles the D package benefit product and the new X benefit package E benefit product. The recommendation rule for the D benefit product is that the ticket price is greater than 100 (a) and the old customer user (b) and the user account does not have the peace of mind refund and change benefit issued by the paid black diamond (c) and is a non-risk control user (d). The recommendation rule for the E benefit product is a non-risk control user (d). The rule feature value of the rule unit a, the ticket price, needs to be passed from the requesting business party, but when the verification module 211 verifies the rule feature value of the ticket price, if it is detected that the business party does not pass it or the ticket price input is illegal (<0), all rule units involving the rule feature value of the ticket price and the rule group including the rule unit are eliminated. The operation expression (a+b+c+d) corresponding to the D benefit product contains the rule unit a, which will be eliminated and the calculation will not be performed, and the package E corresponding to the E benefit product will be recommended to the user.

[0077] In an alternative embodiment, Figure 4 As shown, the second calculation module 240 includes:

[0078] An acquisition unit 241 is used to acquire a priority rule of a rule group;

[0079] The calculation unit 242 is used to deliver the operation expression to the rule engine easyRule to perform calculation according to the priority rule to generate a rule fact.

[0080] The calculation unit 242 delivers the operation expression corresponding to each rule group to the rule engine easyRule for calculation according to the order of priority rules of the rule group, and obtains the rule facts corresponding to each rule group. When the rule fact is true, it means that the user meets the recommended requirements of the corresponding rule group. When the rule fact is false, it means that the user does not meet the recommended requirements of the corresponding rule group.

[0081] This embodiment provides a recommendation system for equity products. The rule units formed by reusable code modularization can be selected when the product recommendation strategy is changed, and the online recommendation logic change can be realized before the project is released. The rule engine easyRule performs calculations on the rule units and operation expressions in sequence, and recommends equity products according to the rule facts, meeting the requirements of rapid iteration of equity products and flexible business expansion.

[0082] Example 3

[0083] Figure 5 The schematic diagram of the structure of an electronic device provided in this embodiment includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the method for recommending equity products in Embodiment 1 is implemented when the processor executes the program. Figure 5 The electronic device 90 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0084] like Figure 5 As shown, the electronic device 90 may be in the form of a general-purpose computing device, for example, it may be a server device. The components of the electronic device 90 may include, but are not limited to: at least one processor 91, at least one memory 92, and a bus 93 connecting different system components (including the memory 92 and the processor 91).

[0085] The bus 93 includes a data bus, an address bus, and a control bus.

[0086] The memory 92 may include a volatile memory, such as a random access memory (RAM) 921 and / or a cache memory 922 , and may further include a read-only memory (ROM) 923 .

[0087] The memory 92 may also include a program / utility 925 having a set (at least one) of program modules 924, such program modules 924 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include an implementation of a network environment.

[0088] The processor 91 executes various functional applications and data processing by running the computer programs stored in the memory 92, such as the method for recommending equity products in Example 1 of the present invention.

[0089] The electronic device 90 may also communicate with one or more external devices 94 (e.g., keyboards, pointing devices, etc.). Such communication may be performed via an input / output (I / O) interface 95. Furthermore, the model generating device 90 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 96. Figure 5 As shown, the network adapter 96 communicates with other modules of the model-generated device 90 via the bus 93. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the model-generated device 90, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems, etc.

[0090] It should be noted that although several units / modules or sub-units / modules of the electronic device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to an embodiment of the present invention, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided into multiple units / modules to be embodied.

[0091] Example 4

[0092] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps in the method for recommending equity products in Embodiment 1 are implemented.

[0093] The readable storage medium may include but is not limited to: a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device or any suitable combination of the above.

[0094] In a possible implementation manner, the present invention may also be implemented in the form of a program product, which includes program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps in the method for recommending equity products of Example 1.

[0095] Among them, the program code for executing the present invention can be written in any combination of one or more programming languages, and the program code can be executed completely on the user device, partially on the user device, as an independent software package, partially on the user device and partially on a remote device, or completely on the remote device.

[0096] Although the specific embodiments of the present invention are described above, it should be understood by those skilled in the art that this is only for illustration and the protection scope of the present invention is defined by the appended claims. Those skilled in the art may make various changes or modifications to these embodiments without departing from the principles and essence of the present invention, but these changes and modifications all fall within the protection scope of the present invention.

Claims

1. A method for recommending equity products, characterized in that: The recommended methods include: Obtaining all information related to the bundled products to be recommended under the user's current browsing page; the bundled product related information includes at least one of product rights list information, user's relevant behavior information and system context information pre-stored on the platform, the product rights list information includes a plurality of rights products, each of the rights products corresponds to a rule group in each bundled sale scenario, and the rule group includes a plurality of rule units with specific logic operation functions formed by code modularization; The rule engine easyRule performs calculation on the rule unit that matches the rule feature value according to the system context information to obtain result data; Determine an operation expression of each rule group based on the result data; The rule engine easyRule is used to perform calculations on the operation expression again to generate a rule fact; the rule fact includes true or false, and when the rule fact is true, it means that the user meets the recommendation requirements of the current rule group, and when the rule fact is false, it means that the user does not meet the recommendation requirements of the current rule group; The equity product corresponding to the true rule fact is recommended as the target equity product.

2. The method for recommending equity products according to claim 1, characterized in that: Before the step of performing calculation on the rule unit matching the rule feature value according to the system context information by the rule engine easyRule, the method further includes: After receiving the recommendation instruction, the rule feature value of the rule unit is verified according to the relevant behavior information and the system context information to filter out invalid rules of the rule group.

3. The method for recommending equity products according to claim 1, characterized in that: The step of determining the operation expression of each rule group based on the result data comprises: The result data corresponding to the rule unit are combined into the operation expression of the corresponding rule group through the decision factor mvel.

4. The method for recommending equity products according to claim 1, characterized in that: The step of using the rule engine easyRule to recalculate the operation expression to generate a rule fact includes: Obtaining the priority rule of the rule group; According to the priority rule, the operation expression is delivered to the rule engine easyRule for calculation to generate the rule fact.

5. A recommendation system for equity products, characterized in that: The recommendation system comprises: an acquisition module, used to acquire all information related to the bundled products to be recommended under the page currently browsed by the user; the information related to the bundled products includes at least one of product rights list information, user related behavior information and system context information pre-stored on the platform; the product rights list information includes a plurality of rights products, each of which corresponds to a rule group in each bundled scenario, and the rule group includes a plurality of rule units with specific logic operation functions formed by code modularization; A first calculation module, configured to perform calculations on the rule unit whose rule feature value is matched according to the system context information through the rule engine easyRule to obtain result data; A determination module, used for determining an operation expression of each rule group based on the result data; The second calculation module is used to use the rule engine easyRule to perform calculations on the operation expression again to generate a rule fact; the rule fact includes true or false, and when the rule fact is true, it means that the user meets the recommendation requirements of the current rule group, and when the rule fact is false, it means that the user does not meet the recommendation requirements of the current rule group; The recommendation module is used to recommend the equity product corresponding to the true rule fact as a target equity product.

6. The equity product recommendation system according to claim 5, characterized in that: The recommendation system further includes: The verification module is used to verify the rule feature value of the rule unit according to the relevant behavior information and the system context information after receiving the recommendation instruction to filter out invalid rules of the rule group.

7. The equity product recommendation system according to claim 5, characterized in that: The determination module is specifically used for: The result data corresponding to the rule unit are combined into the operation expression of the corresponding rule group through the decision factor mvel.

8. The equity product recommendation system according to claim 5, characterized in that: The second calculation module includes: An acquisition unit, used for acquiring the priority rule of the rule group; The calculation unit is used to deliver the operation expression to the rule engine easyRule to perform calculation according to the priority rule to generate the rule fact.

9. An electronic device, characterized in that: The invention comprises a processor, a memory and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the method for recommending equity products as described in any one of claims 1 to 4 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for recommending equity products according to any one of claims 1 to 4 is implemented.