Operation product recommendation method and related products

Abstract

The invention discloses an operation product recommendation method and related products. The method comprises the steps of obtaining target user information, product information of multiple operation products corresponding to an operation project and an operation index of the operation project; determining an operation trend of the operation project based on a prediction model and the operation index of the operation project; determining a recommendation strategy based on the operation trend of the operation project; and screening the plurality of operation products by using a rule model based on the recommendation strategy, the product information of the plurality of operation products and the target user information, and determining a recommended operation product. The operation trend of the operation project is analyzed by using the prediction model, and the capability of the model to dynamically adapt to the market environment is predicted. The multiple operation products are screened through the rule model, the most suitable product can be automatically matched to the target user according to the recommendation strategy, invalid marketing behaviors are reduced, and the accuracy of recommending the operation products is improved.

Description

Technical Field

[0001] This application relates to the field of data filtering technology, and in particular to a recommendation method for operational products and related products. Background Technology

[0002] With the continued advancement of inclusive finance policies, increasing residents' property income and accelerating the construction of a multi-tiered investment market have become important development directions, highlighting the strategic value of over-the-counter (OTC) bond business. Against this backdrop, OTC bond recommendation systems, as an important tool in financial services, have gradually entered a mature application stage in recent years, relying on the rapid development of cutting-edge technologies such as artificial intelligence, big data, and machine learning.

[0003] Currently, over-the-counter bond recommendations primarily rely on a comprehensive analysis of multi-dimensional data, including market trends, bond ratings, macroeconomic indicators, and investor risk preferences, to provide personalized and customized bond investment advice to institutional and individual investors. However, existing recommendation methods still largely depend on manual judgment, which not only suffers from low efficiency but may also introduce uncertainty due to subjective factors, affecting the accuracy and consistency of the recommendation results. Summary of the Invention

[0004] Based on the above problems, this application provides a method for recommending operational products and related products, with the aim of improving the accuracy of recommending operational products.

[0005] The embodiments of this application disclose the following technical solutions:

[0006] The first aspect of this application provides a method for recommending operational products, including:

[0007] Acquire target user information, product information of multiple operational products corresponding to the operational project, and operational metrics of the operational project;

[0008] The operational trend of the operational project is determined based on the predictive model and the operational indicators of the operational project.

[0009] The recommendation strategy is determined based on the operational trends of the aforementioned projects;

[0010] The recommended operational products are determined by using a rule model to filter the multiple operational products based on the recommendation strategy, product information of the multiple operational products, and target user information.

[0011] A second aspect of this application provides a device for recommending operating products, comprising:

[0012] The acquisition module is used to acquire target user information, product information of multiple operational products corresponding to the operational project, and operational metrics of the operational project.

[0013] The prediction module is used to determine the operational trend of the operational project based on the prediction model and the operational indicators of the operational project;

[0014] The recommendation strategy determination module is used to determine the recommendation strategy based on the operational trends of the operational projects.

[0015] The recommended operational product determination module is used to filter the multiple operational products based on the recommendation strategy, the product information of the multiple operational products, and the target user information using a rule model, and determine the recommended operational products.

[0016] A third aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the recommended method for the operating product provided in the first aspect.

[0017] The fourth aspect of this application provides a computer program product, including a computer program that, when executed by a processor, implements a recommended method for operating the product provided in the first aspect.

[0018] Compared with the prior art, this application has the following beneficial effects:

[0019] This application includes obtaining target user information, product information of multiple operational products corresponding to the operational project, and operational indicators of the operational project; determining the operational trend of the operational project based on a prediction model and the operational indicators of the operational project; determining a recommendation strategy based on the operational trend of the operational project; and using a rule model to filter the multiple operational products based on the recommendation strategy, the product information of the multiple operational products, and the target user information to determine recommended operational products.

[0020] This application utilizes predictive models to analyze operational trends of projects, enabling the system to dynamically adapt to the market environment. Traditional recommendation systems often rely on static historical data, while this application dynamically adjusts its recommendation strategy based on real-time or periodically updated operational metrics (such as sales growth trends, user activity, and market competition). This capability is particularly important for coping with a rapidly changing market environment, helping companies seize opportunities and mitigate risks. By filtering multiple operational products through rule-based models, the system can automatically match the most suitable products to target users according to the recommendation strategy. This not only reduces the time cost of manual screening and decision-making but also avoids biases caused by human factors. Furthermore, accurate recommendations can effectively improve conversion rates and enhance the accuracy of recommended operational products. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 A flowchart illustrating a method for recommending operational products provided in this application embodiment;

[0023] Figure 2 A flowchart illustrating an operational product screening method provided in this application embodiment;

[0024] Figure 3 This is a structural diagram of a product recommendation device provided in an embodiment of this application. Detailed Implementation

[0025] As described earlier, current over-the-counter bond recommendations are primarily based on a comprehensive analysis of multi-dimensional information, including market trends, bond credit ratings, macroeconomic data, and investors' risk tolerance, aiming to provide personalized and differentiated investment advice to institutional and individual clients. However, the current recommendation process still heavily relies on manual intervention, which is not only inefficient but also susceptible to subjective judgment, potentially leading to shortcomings in the accuracy and stability of the recommendation results.

[0026] In view of the above problems, this application provides a method for recommending operational products and related products. The method includes: obtaining target user information, product information of multiple operational products corresponding to the operational project, and operational indicators of the operational project; determining the operational trend of the operational project based on a prediction model and the operational indicators of the operational project; determining a recommendation strategy based on the operational trend of the operational project; and using a rule model to filter the multiple operational products based on the recommendation strategy, the product information of the multiple operational products, and the target user information to determine recommended operational products.

[0027] This application introduces a predictive model to analyze the operational trends of projects. Compared to traditional recommendation systems that primarily rely on static historical data, it innovatively employs real-time or periodically updated operational metrics (such as sales growth, user activity, and market competition) to dynamically optimize and adjust recommendation strategies. This feature is particularly crucial in responding to rapidly changing market environments, helping companies to promptly capture market opportunities and mitigate potential risks. Building upon this foundation, this application further constructs a rule-based model to intelligently filter multiple operational products and automatically match the product that best meets the needs of target users based on the current recommendation strategy. This mechanism not only significantly reduces the decision-making costs and subjective biases associated with manual intervention but also effectively improves recommendation efficiency and accuracy. Simultaneously, personalized recommendation results help enhance user experience, increase conversion rates, and thus drive overall business growth.

[0028] In order to help those skilled in the art better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 those skilled in the art without creative work are within the scope of protection of this application.

[0029] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data shall comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0030] Figure 1 A flowchart illustrating a method for recommending operational products provided in this application embodiment is shown below. Figure 1 As shown, the recommended methods for operating products include:

[0031] S101: Obtain target user information, product information of multiple operational products corresponding to the operational project, and operational metrics of the operational project.

[0032] This application does not limit the acquisition method. For example, it can collect target user information from multiple data sources such as bank CRM systems, customer transaction records, and APP behavior logs, including user age, occupation, risk preference level, historical investment preferences, and account balance. At the same time, it can periodically collect bond information from the bank's internal data platform and product information of all bond-related wealth management products (such as treasury bonds, corporate bonds, and policy bank bonds) involved in the operation projects of other banks, including product yield, term, risk level, and liquidity. In addition, it can also access the real-time operation indicators of the project, such as the current number of participants, product sales trends, and market interest rate fluctuations.

[0033] S102: Determine the operational trend of the operational project based on the prediction model and the operational indicators of the operational project.

[0034] This application does not limit the specific prediction methods. For example, it can call a pre-trained prediction model (such as LSTM, XGBoost, Prophet, etc.), input operational indicator data of the current project (such as the sales growth curve of the past 30 days, changes in user traffic, market interest rate trends, etc.), and predict the development trend of the project in the future. For example, it can predict whether a certain type of bond will experience a buying peak in the next month, or whether the market acceptance of a certain financial product will decline.

[0035] S103: Determine the recommended strategy based on the operational trends of the aforementioned projects.

[0036] This application does not limit the specific method for determining the recommendation strategy. For example, it can predict the upward and downward trends of the yields to maturity of 1-year and 5-year bonds based on a forecasting model. An upward trend indicates a price decline, and a downward trend indicates a price increase. An active recommendation strategy (i.e., the first strategy in this application) is adopted when prices are rising, and a passive recommendation strategy (i.e., the second strategy in this application) is adopted when prices are falling.

[0037] S104: Using a rule model, the multiple operational products are filtered based on the recommendation strategy, the product information of the multiple operational products, and the target user information to determine the recommended operational products.

[0038] This application does not limit the method for determining the recommended operating products. For example, based on the active or passive strategy adopted, the customer type input by the user (individual customer or corporate customer), the holding purpose (holding to maturity, mid-term transaction), the minimum holding period of bonds, the applicable income tax rate for corporate customers, etc., the corresponding rule matching is retrieved from the rule base (for example, for a risk-averse investor, the rule model will prioritize screening low-risk, stable-return products; while for customers with larger capital, the risk restrictions can be relaxed, and high-yield potential products can be considered as the main focus). Through the corresponding rule reasoning, 2 to 5 operating products (such as bonds) that best match the current recommendation strategy and user preferences are obtained as recommended operating products.

[0039] The above describes the main technical solution of this application. Further implementations of the main technical solution are now introduced. Details are as follows:

[0040] Since the product information of multiple operational products corresponding to an operational project is relatively large, in order to ensure the efficiency of subsequent steps, this application also provides a method for extracting key information from the product information of multiple operational products corresponding to an operational project:

[0041] Key information is extracted from the product information of the multiple operational products to obtain key information of the multiple operational products.

[0042] This application also provides a specific example of extracting key information from product information of multiple operational products corresponding to an operational project:

[0043] Use the following rules to extract the remaining days of product information for operating products:

[0044] Remaining days = (Year * 365 + Days) of the remaining term.

[0045] The coupon rate for operating products is extracted using the following rules:

[0046] In bond information data, if the coupon rate is not equal to 0, the coupon rate remains unchanged; if the coupon rate is 0, the coupon rate = (100 - issue price) * term * 100 / 365.

[0047] Interest payment period 1 for extracting product information of operating products using the following rules:

[0048] On each bond trading day, the "interest payment period 1" is assigned a value according to the bond's interest payment frequency code INTS_FRQ, where: INTS_FRQ=1, then interest payment period 1=0.25; INTS_FRQ=2, then interest payment period 1=0.5; INTS_FRQ=3, then interest payment period 1=0; INTS_FRQ=4, then interest payment period 1=1; INTS_FRQ=5, then interest payment period 1=1 / 12.

[0049] Note: The values ​​of INTS_FRQ mean: 1 for quarterly, 2 for semi-annual, 3 for annual, 4 for due date, and 5 for monthly.

[0050] Interest payment period 2 for extracting product information of operating products using the following rules:

[0051] ① The interest payment period 1 = 0.25. If the number of days beyond the whole year in the remaining term is greater than 273, then the interest payment period 2 = 0; if 182 < the number of days beyond the whole year in the remaining term ≤ 273, then the interest payment period 2 = 0.25; if 91 < the number of days beyond the whole year in the remaining term ≤ 182, then the interest payment period 2 = 0.5; if 0 < the number of days beyond the whole year in the remaining term ≤ 91, then the interest payment period 2 = 0.75; if the number of days beyond the whole year in the remaining term = 0, then the interest payment period 2 = 1.

[0052] ② The interest payment period 1 = 0.5. If the number of extra days outside the whole year in the remaining term is > 182, then the interest payment period 2 = 0; if 0 < the number of extra days outside the whole year in the remaining term ≤ 182, then the interest payment period 2 = 0.5; if the number of extra days outside the whole year in the remaining term is 0, then the interest payment period 2 = 1.

[0053] ③ If interest payment period 1 = 0, and the number of extra days outside the whole year in the remaining term is greater than 0, then interest payment period 2 = 0. If the number of extra days outside the whole year in the remaining term is 0, then interest payment period 2 = 1.

[0054] ④ If interest payment period 1 = 1, then interest payment period 2 = 0.

[0055] ⑤ Interest payment period 1 = 1 / 12, interest payment period 2 will not be assigned a value for the time being.

[0056] Extract the interest payment frequency value from the product information of the operating products using the following rules:

[0057] ①If interest payment cycle 1 = 0.25, then the number of interest payments = (whole years in the remaining term + 1) - interest payment cycle 2.

[0058] ② Interest payment cycle 1 = 0.5, number of interest payments = (full years in the remaining term + 1) - interest payment cycle 2.

[0059] ③Interest payment cycle 1 = 0, number of interest payments = (whole year in the remaining term + 1) - interest payment cycle 2.

[0060] ④ Interest payment cycle 1 = 1, number of interest payments = 1.

[0061] ⑤ Interest payment cycle 1 = 1 / 12, the number of interest payments is not assigned for the time being.

[0062] The following rules are used to extract accrued interest on product information for operating products:

[0063] If the bond's abbreviation does not contain the words "discount," then:

[0064] Accrued interest = coupon rate * (remaining days - 1) / 365. The calculated value is rounded to 6 decimal places, and the output value is rounded to 2 decimal places.

[0065] If the bond's abbreviation contains the word "discount," then:

[0066] Accrued interest = (100 - issue price) * (remaining days - 1) / term. The calculated value is rounded to 6 decimal places, and the output value is rounded to 2 decimal places.

[0067] The following rules are used to extract the actual customer return on investment for operating products:

[0068] If the bond's abbreviation does not contain the words "discount," then:

[0069] Actual customer yield = (100 + coupon rate * number of interest payments - full purchase price) * 365 * 100% / (full purchase price * remaining days), with the calculated value rounded to 4 decimal places.

[0070] If the bond's abbreviation contains the word "discount," then:

[0071] Actual customer return = (100 - purchase price) * 365 * 100% / (purchase price * remaining days), with the calculated value rounded to 4 decimal places.

[0072] The applicable income tax rate for corporate clients who extract product information for operational products using the following rules:

[0073] Corporate clients are eligible for income tax rates of 0%, 15%, 20%, or 25%, or enter any value; the default is 25%.

[0074] Tax-free yield for corporate clients who extract product information for operating products using the following rules:

[0075] If the bond's abbreviation does not contain the words "discount," then:

[0076] The tax-free yield for corporate clients = [(100 + coupon rate * number of interest calculations - purchase price - accrued interest) * (1 - applicable corporate income tax rate) + accrued interest] * 365 * 100% / (purchase price * remaining days), with the calculated value rounded to 4 decimal places.

[0077] If the bond's abbreviation contains the words "discount," then:

[0078] Corporate customer's tax-free yield = [(100 - purchase price - accrued interest) * (1 - applicable corporate customer income tax rate) + accrued interest] * 365 * 100% / (purchase price * remaining days), the calculated value is rounded to 4 decimal places.

[0079] Comparable deposit yields for corporate clients are extracted using the following rules to obtain product information for operational products:

[0080] Comparable deposit yield for corporate clients = tax-free yield for corporate clients / (1 - applicable income tax rate for corporate clients), with the calculated value rounded to four decimal places.

[0081] Extract the price difference of product information for operating products using the following rules:

[0082] Price difference = Investor's selling price - Investor's buying price (which is a negative value).

[0083] The median estimated number of days for the price difference of the product information of the operating products is extracted using the following rules:

[0084] The median number of days for the parity spread is calculated as: Parity Spread * 365 / (Coupon Rate * 100), with the calculated value rounded to zero decimal places.

[0085] Group the products being operated using the following rules:

[0086] ① Treasury Bonds: The bond type is "book-entry treasury bonds".

[0087] ② Policy Bank Bonds: The bond types are "China Development Bank Bonds" + "Agricultural Development Bank Bonds" + "Export-Import Bank Bonds".

[0088] ③ Local government debt group: The bond type is "local government debt".

[0089] ④ Other bond groups: Bonds other than those mentioned above.

[0090] Within each group of bonds, those with the same price difference are grouped together, with no limit on the total number of groups.

[0091] This application also provides specific embodiments for extracting key information from target user information:

[0092] Extract the target user information, including the customer's holding purpose (e.g., holding to maturity, mid-term transaction), customer type (e.g., individual customer, corporate customer), applicable income tax rate for corporate customers (e.g., 25%, 20%), and minimum holding period (e.g., 60 days, 180 days).

[0093] Minimum holding days: Any value greater than 0 that the client can enter based on their own liquidity management needs, in days.

[0094] Corporate clients' applicable income tax rate: Corporate clients need to select 25%, 20%, 15%, or 0% based on the calculation of the corporate client's tax-free return and comparable deposit return, or directly enter a number less than 25%, with 25% as the default.

[0095] Regarding S104, which uses a rule model to filter the multiple operational products based on the recommendation strategy, the product information of the multiple operational products, and the target user information to determine the recommended operational products, this application provides a specific embodiment:

[0096] Figure 2 A flowchart of an operational product screening method provided in this application embodiment is shown below. Figure 2 As shown, S201: Determine the type of the target user based on the target user information.

[0097] S202: If the target user is an individual, then the individual rule layer in the rule model is used to filter the multiple operational products based on the recommendation strategy, the product information of the multiple operational products, and the target user information to determine the recommended operational products.

[0098] S203: If the target user is an enterprise, then the enterprise rule layer in the rule model is used to filter the multiple operational products based on the recommendation strategy, the product information of the multiple operational products, and the target user information to determine the recommended operational products.

[0099] This implementation dynamically matches products based on user holding goals, minimum holding days, and market trends, improving recommendation accuracy. It incorporates upward / downward strategies to adjust recommendation logic in real time, adapting to market changes. Strict matching of remaining term and holding period reduces the risk of early redemption and fund mismatch. Recommended products better meet actual user needs, improving satisfaction and conversion rates. The multi-condition combination judgment mechanism supports flexible expansion, facilitating the introduction of more user profile dimensions or product types in the future.

[0100] This application also provides a specific extension to S202, which utilizes the personal rule layer in the rule model to filter the multiple operational products based on the recommendation strategy, the product information of the multiple operational products, and the target user information to determine the recommended operational products:

[0101] If the target user information meets any one of the first screening conditions, then multiple operational products are screened according to the first screening rule to determine the recommended operational product; the first screening conditions include a first sub-condition, a second sub-condition, a third sub-condition, and a fourth sub-condition; the first sub-condition includes that the target holding in the target user information is a first holding target (e.g., held to maturity); the second sub-condition includes that the target holding in the target user information is a second holding target (e.g., mid-term transaction), the minimum holding days in the target user information are less than or equal to a first preset threshold (e.g., 60 days), and the recommended strategy is a first strategy (e.g., an upward strategy); the third sub-condition includes that the target holding in the target user information is a second holding target (e.g., mid-term transaction), the minimum holding days in the target user information are less than or equal to a second preset threshold (e.g., 90 days), and the recommended strategy is a second strategy (e.g., a downward strategy).

[0102] If the target user information meets the second screening condition, the remaining period is defined as being greater than the minimum holding days in the target user information and less than the third preset threshold (e.g., 365 days). Multiple operating products are screened according to the remaining period, and the multiple operating products after screening are screened again according to the second screening rule to determine the recommended operating product. The second screening condition includes the target holding in the target user information being the second holding target, the minimum holding days in the target user information being greater than the first preset threshold and less than or equal to the fourth preset threshold (e.g., 180 days), and the recommendation strategy being the first strategy.

[0103] If the target user information meets the third screening condition, the remaining period is defined as being greater than the third preset threshold and less than the fifth preset threshold (e.g., 730 days). Multiple operational products are screened according to the remaining period, and the multiple operational products after screening are screened again according to the second screening rule to determine the recommended operational product. The third screening condition includes the target holding in the target user information being the second holding target, the minimum holding days in the target user information being greater than the fourth preset threshold and less than or equal to the third preset threshold, and the recommendation strategy being the first strategy.

[0104] If the target user information meets the fourth screening condition, the remaining period is defined as being greater than the minimum holding days in the target user information and less than the third preset threshold. Multiple operating products are screened according to the remaining period, and the multiple operating products after screening are screened again according to the second screening rule to determine the recommended operating product. The fourth screening condition includes the target holding in the target user information being the second holding target, the minimum holding days in the target user information being greater than the fourth preset threshold and less than or equal to the third preset threshold, and the recommendation strategy being the second strategy.

[0105] If the target user information meets the fifth screening condition, the remaining period is defined as being greater than the fifth preset threshold and less than the sixth preset threshold (e.g., 1825 days). Multiple operational products are screened according to the remaining period, and the multiple operational products after screening are screened again according to the second screening rule to determine the recommended operational products. The fifth screening condition includes the target holding target in the target user information being the second holding target, the minimum holding days in the target user information being greater than the third preset threshold, and the recommendation strategy being the first strategy.

[0106] If the target user information meets the sixth screening condition, the remaining period is defined as being greater than the fifth preset threshold and less than the seventh preset threshold (e.g., 1095 days). Multiple operational products are screened according to the remaining period, and the multiple operational products after screening are screened again according to the second screening rule to determine the recommended operational product. The sixth screening condition includes the target holding in the target user information being the second holding target, the minimum holding days in the target user information being greater than the third preset threshold, and the recommendation strategy being the second strategy.

[0107] If the target user information meets the seventh screening condition, the remaining period is defined as being greater than the minimum holding days in the target user information and less than the third preset threshold. Multiple operating products are screened according to the remaining period, and the multiple operating products after screening are screened again according to the second screening rule to determine the recommended operating product. The seventh screening condition includes the target holding in the target user information being the second holding target, the minimum holding days in the target user information being greater than the second preset threshold and less than or equal to the fourth preset threshold, and the recommendation strategy being the second strategy.

[0108] This application does not limit the first, second, and third screening rules, but rather provides one optional embodiment:

[0109] The first filtering rule includes defining the remaining period as less than the minimum holding days in the target user information, filtering multiple operating products according to the remaining period, sorting the multiple operating products after filtering, and determining the first and second ranked operating products as recommended operating products.

[0110] The second screening rule includes sorting the multiple screened operational products according to operational indicators to obtain a ranking result; determining the absolute value of the price difference for each operational product; if the absolute values ​​of the price differences for multiple operational products are inconsistent, the operational product with the smallest absolute value of the price difference and the first-ranked operational product in the ranking result are selected as recommended operational products; if the absolute values ​​of the price differences for multiple operational products are consistent, the first-ranked and second-ranked operational products in the ranking result are selected as recommended operational products.

[0111] The third screening rule includes screening based on the ranking of the screened operational products, and determining the first one as the recommended operational product.

[0112] This application provides a specific application embodiment for S202, which utilizes the personal rule layer in the rule model to filter multiple operational products based on the recommendation strategy, product information of the multiple operational products, and target user information to determine recommended operational products:

[0113] A. Bond screening logic for individual clients:

[0114] If the holding purpose of A1 is "hold to maturity", then the priority of the recommended bond screening criteria is as follows:

[0115] ① "Remaining Maturity" < "Minimum Holding Days for Bonds".

[0116] ② Select the bond with the highest "yield to maturity at investor purchase price" from each group. The bond highlights are: 1.

[0117] ③ Select one bond from each group based on the second highest "yield to maturity at investor purchase price". The bond's highlights are: 2.

[0118] Two bonds per group, for a total of eight recommended bonds. If other bond groups are empty, then empty bonds will be recommended (the same applies below).

[0119] If the purpose of holding A2 is "mid-term trading", then the priority of the recommended bond screening criteria is as follows:

[0120] Customer A21 enters "Minimum holding period for bonds" ≤ 365 days.

[0121] Based on the 1-year bond market trend (A211), if the market is experiencing a rise in bond prices:

[0122] Customer A2111 inputs "Minimum holding period for bonds" ≤ 60 days. The recommended bond filtering criteria are prioritized as follows for each group:

[0123] ① "Remaining Maturity" < "Minimum Holding Days for Bonds".

[0124] ② Select the bond with the highest "yield to maturity at investor purchase price" from each group. The bond highlights are: 1.

[0125] ③ Select one bond from each group based on the second highest "yield to maturity at investor purchase price". The bond's highlights are: 2.

[0126] Two sticks per group, for a total of eight sticks recommended.

[0127] Customer A21121 inputs 60 days < "Minimum Holding Period for Bonds" ≤ 180 days. The recommended bond filtering criteria are prioritized as follows:

[0128] ① The customer's input "Minimum holding days for bonds" < "Remaining term" < 365 days.

[0129] ② The top ten "Investor purchase price yield to maturity" ranked from highest to lowest.

[0130] ③ Select the bond with the highest "yield to maturity at investor's purchase price". Bond highlights are: 3 and 6.

[0131] ④ Among the bonds with the smallest absolute price difference, select the one with the highest "yield to maturity at the investor's purchase price". The bond highlights are: 5 and 6. If the absolute price differences are all the same, select the second one from the highest to the lowest "yield to maturity at the investor's purchase price". The bond highlights are: 4 and 6.

[0132] Two sticks per group, for a total of eight sticks recommended.

[0133] Customer A21122 entered 180 days < "Minimum Holding Period for Bonds" ≤ 365 days. The recommended bond selection criteria for each group are prioritized as follows:

[0134] ①365 days < "Remaining period" < 730 days.

[0135] ② The top ten "Investor purchase price yield to maturity" ranked from highest to lowest.

[0136] ③ Select the bond with the highest "yield to maturity at investor purchase price". The bond highlights are: 3 and 6.

[0137] ④ Among the bonds with the smallest absolute price difference, select the one with the highest "yield to maturity at the investor's purchase price". The bond highlights are: 5 and 6. If the absolute price differences are all the same, select the second one from the highest to the lowest "yield to maturity at the investor's purchase price". The bond highlights are: 4 and 6.

[0138] Two sticks per group, for a total of eight sticks recommended.

[0139] Customer A212 inputs "Minimum Holding Period for Bonds" ≤ 365 days, referencing 1-year market conditions. If bond prices are falling:

[0140] Customer A2121 inputs "Minimum holding period for bonds" ≤ 90 days. The recommended bond filtering criteria are prioritized as follows for each group:

[0141] ① "Remaining Maturity" < "Minimum Holding Days for Bonds".

[0142] ② Select the bond with the highest "yield to maturity at investor purchase price" from each group. The bond highlights are: 1.

[0143] ③ Select one bond from each group based on the second highest "yield to maturity at investor purchase price". The bond's highlights are: 2.

[0144] Two sticks per group, for a total of eight sticks recommended.

[0145] Customer A21221 inputs 90 days < "Minimum Holding Period for Bonds" ≤ 180 days. The recommended bond filtering criteria are prioritized as follows:

[0146] ① "Minimum holding period for bonds" < "Remaining maturity" < 365 days.

[0147] ② Among the bonds with the smallest absolute value of the price difference, select the bond with the highest "yield to maturity at the investor's purchase price". The bond highlights are: 5 and 6.

[0148] One item per group, for a total of four items recommended.

[0149] Customer A21222 inputs 180 days < "Minimum Holding Period for Bonds" ≤ 365 days. The recommended bond selection criteria for each group are prioritized as follows:

[0150] ① The customer's input "Minimum holding days for bonds" < "Remaining term" < 365 days.

[0151] ② Select the bond with the highest "yield to maturity at investor purchase price". The bond highlights are: 3 and 6.

[0152] ③ Among the bonds with the smallest absolute price difference, select the one with the highest "yield to maturity at the investor's purchase price". The bond highlights are: 5 and 6. If the absolute price differences are all the same, select the second one from highest to lowest "yield to maturity at the investor's purchase price". The bond highlights are: 4 and 6.

[0153] Two sticks per group, for a total of eight sticks recommended.

[0154] Customer A22 enters "Minimum holding period for bonds" > 365 days.

[0155] Based on the 5-year bond market trend (A221), if the bond price trend is upward, the recommended bond selection criteria priority for each group is as follows:

[0156] ①730 days < "Remaining term" < 1825 days.

[0157] ② The top ten "Investor purchase price yield to maturity" ranked from highest to lowest.

[0158] ③ Select the bond with the highest "yield to maturity at investor purchase price". The bond highlights are: 3 and 6.

[0159] ④ Among the bonds with the smallest absolute price difference, select the one with the highest "yield to maturity at the investor's purchase price". The bond highlights are: 5 and 6. If the absolute price differences are all the same, select the second one from the highest to the lowest "yield to maturity at the investor's purchase price". The bond highlights are: 4 and 6.

[0160] Two sticks per group, for a total of eight sticks recommended.

[0161] Customer A222 inputs "Minimum Holding Period for Bonds" > 365 days. Referring to the 5-year market trend, if bond prices are falling, the recommended bond selection criteria priority for each group is as follows:

[0162] ①730 days < "Remaining term" < 1095 days.

[0163] ② The top ten "Investor purchase price yield to maturity" ranked from highest to lowest.

[0164] ③ Select the bond with the highest "yield to maturity at investor purchase price". The bond highlights are: 3 and 6.

[0165] ④ Among the bonds with the smallest absolute price difference, select the one with the highest "yield to maturity at the investor's purchase price". The bond highlights are: 5 and 6. If the absolute price differences are all the same, select the second one from the highest to the lowest "yield to maturity at the investor's purchase price". The bond highlights are: 4 and 6.

[0166] Two sticks per group, for a total of eight sticks recommended.

[0167] This application provides a specific extension to the method in S203, which uses the enterprise rule layer of the rule model to filter multiple operational products based on the recommendation strategy, product information of the multiple operational products, and target user information to determine recommended operational products:

[0168] If the target user information meets any one of the eighth screening conditions, then multiple operational products are screened according to the fourth screening rule to determine the recommended operational product; the eighth screening condition includes the fifth sub-condition, the sixth sub-condition, and the seventh sub-condition; the fifth sub-condition includes the target being held as the first holding target in the target user information; the sixth sub-condition includes the target being held as the second holding target in the target user information, the minimum holding days in the target user information being less than or equal to the third preset threshold, and the recommendation strategy being the first strategy; the seventh sub-condition includes the target being held as the second holding target in the target user information, the minimum holding days in the target user information being less than or equal to the fourth preset threshold, and the recommendation strategy being the second strategy.

[0169] If the target user information meets the ninth screening condition, then multiple operational products are screened according to the fifth screening rule to determine three recommended operational products; the ninth screening condition includes the target holding in the target user information being the second holding target, the minimum holding days in the target user information being greater than the second preset threshold and less than or equal to the fourth preset threshold, and the recommendation strategy being the first strategy.

[0170] If the target user information meets the tenth screening condition, then multiple operational products are screened according to the sixth screening rule to determine three recommended operational products; the tenth screening condition includes the target holding target in the target user information being the second holding target, the minimum holding days in the target user information being greater than the fourth preset threshold and less than or equal to the third preset threshold, and the recommendation strategy being the first strategy.

[0171] If the target user information meets the eleventh screening condition, then multiple operational products are screened according to the seventh screening rule to determine three recommended operational products; the eleventh screening condition includes the target holding target in the target user information being the second holding target, the minimum holding days in the target user information being greater than the fourth preset threshold and less than or equal to the third preset threshold, and the recommendation strategy being the second strategy.

[0172] If the target user information meets the twelfth screening condition, then the multiple operational products after the second screening are screened according to the eighth screening rule to determine the recommended operational products; the twelfth screening condition includes the target holding target in the target user information being the second holding target, the minimum holding days in the target user information being greater than the third preset threshold, and the recommendation strategy being the first strategy.

[0173] If the target user information meets the thirteenth screening condition, then the multiple operational products after the second screening are screened according to the ninth screening rule to determine the recommended operational product; the thirteenth screening condition includes the target holding target in the target user information being the second holding target, the minimum holding days in the target user information being greater than the third preset threshold, and the recommendation strategy being the second strategy.

[0174] This application does not limit the fourth, fifth, sixth, seventh, eighth, and ninth screening rules, but provides one possible embodiment:

[0175] The fourth screening rule includes defining the remaining period as less than or equal to the minimum number of days held in the target user information, screening multiple operational products according to the remaining period and preset screening requirements, sorting the multiple operational products after screening according to operational indicators, and determining the first and second ranked operational products as recommended operational products.

[0176] The fifth screening rule includes a first sub-screening rule and a second sub-screening rule. The first sub-screening rule includes defining the remaining term as greater than the minimum holding days in the target user information and less than a third preset threshold, screening multiple operating products according to the remaining term and preset screening requirements, and sorting the screened operating products according to operating indicators to obtain a ranking result; determining the absolute value of the price difference for each operating product, and if the absolute values ​​of the price differences for multiple operating products are inconsistent, then the operating product with the smallest absolute value of the price difference and the first-ranked operating product in the ranking result are selected as recommended operating products; if the absolute values ​​of the price differences for multiple operating products are consistent, then the first-ranked and second-ranked operating products in the ranking result are selected as recommended operating products. The second sub-screening rule includes defining the remaining term as less than or equal to the minimum holding days in the target user information, screening multiple operating products according to the remaining term and preset screening requirements, and sorting the screened operating products according to operating indicators, and selecting the first-ranked operating product in the ranking result as the recommended operating product.

[0177] The sixth screening rule includes a third sub-screening rule and a fourth sub-screening rule. The third sub-screening rule includes defining the remaining term as greater than a third preset threshold and less than a fifth preset threshold, screening multiple operational products according to the remaining term and preset screening requirements, and sorting the screened operational products according to operational indicators to obtain a ranking result; determining the absolute value of the price difference for each operational product, and if the absolute values ​​of the price differences for multiple operational products are inconsistent, then the operational product with the smallest absolute value of the price difference and the first-ranked operational product in the ranking result are selected as recommended operational products; if the absolute values ​​of the price differences for multiple operational products are consistent, then the first-ranked and second-ranked operational products in the ranking result are selected as recommended operational products. The fourth sub-screening rule includes defining the remaining term as less than or equal to the minimum holding days in the target user information, screening multiple operational products according to the remaining term and preset screening requirements, and sorting the screened operational products according to operational indicators, and selecting the first-ranked operational product in the ranking result as the recommended operational product.

[0178] The seventh screening rule includes the fifth sub-screening rule and the second sub-screening rule; the fifth sub-screening rule includes defining the remaining period as greater than the minimum holding days in the target user information and less than the third preset threshold, screening multiple operational products according to the remaining period and preset screening requirements, sorting the multiple operational products after screening according to operational indicators, and determining the first and second ranked operational products as recommended operational products.

[0179] The eighth screening rule includes defining the remaining term as greater than the fifth preset threshold and less than the sixth preset threshold, screening multiple operating products according to the remaining term and preset screening requirements, and sorting the screened multiple operating products according to operating indicators to obtain a ranking result; determining the absolute value of the price difference for each operating product, if the absolute values ​​of the price differences of multiple operating products are inconsistent, then the first-ranked operating product in the ranking result is taken as the recommended operating product, and if the absolute values ​​of the price differences of multiple operating products are consistent, then the first-ranked operating product and the second-ranked operating product in the ranking result are determined as recommended operating products.

[0180] The ninth screening rule includes defining the remaining term as greater than the fifth preset threshold and less than the seventh preset threshold, screening multiple operating products according to the remaining term and preset screening requirements, and sorting the screened multiple operating products according to operating indicators to obtain a ranking result; determining the absolute value of the price difference for each operating product, if the absolute values ​​of the price differences of multiple operating products are inconsistent, then the first-ranked operating product in the ranking result is taken as the recommended operating product, and if the absolute values ​​of the price differences of multiple operating products are consistent, then the first-ranked operating product and the second-ranked operating product in the ranking result are determined as recommended operating products.

[0181] This application provides a specific application embodiment for S203, which utilizes the enterprise rule layer in the rule model to filter multiple operational products based on the recommendation strategy, product information of the multiple operational products, and target user information to determine recommended operational products:

[0182] B Corporate Client Bond Screening Logic:

[0183] If the holding purpose of B1 is "hold to maturity", then the priority of the recommended bond screening criteria is as follows:

[0184] ① "Remaining maturity" ≦ "Minimum holding days of the bond".

[0185] ② Select one bond from each of the Treasury bond group and the local government bond group based on the highest "tax-free yield for corporate clients". The bond highlight feedback is: 7. Select one bond from the policy bank bond group based on the highest "actual yield for clients". The bond highlight feedback is: 8.

[0186] ③ Select one bond each from the Treasury bond group and the local government bond group based on the second-highest "tax-free yield for corporate clients". The bond highlight feedback is: 9. Select one bond from the policy bank bond group based on the second-highest "actual yield for clients". The bond highlight feedback is: 10.

[0187] Two bonds are recommended per group, for a total of six. The third bond in each group is displayed blank on the output page.

[0188] If the purpose of holding B2 is "mid-term trading", then the priority of the recommended bond screening criteria is as follows:

[0189] Customers in B21 should enter "Minimum holding period for bonds" ≤ 365 days.

[0190] Based on the 1-year bond market trend (B211), if the market is in a rising bond price trend:

[0191] Customer B2111 inputs "Minimum holding period for bonds" ≤ 90 days. The recommended bond filtering criteria are prioritized as follows for each group:

[0192] ① "Remaining maturity" ≦ "Minimum holding days of the bond".

[0193] ② Select one bond from each of the Treasury bond group and the local government bond group based on the highest "tax-free yield for corporate clients". The bond highlight feedback is: 7. Select one bond from the policy bank bond group based on the highest "actual yield for clients". The bond highlight feedback is: 8.

[0194] ③ Select one bond each from the Treasury bond group and the local government bond group based on the second-highest "tax-free yield for corporate clients". The bond highlight feedback is: 9. Select one bond from the policy bank bond group based on the second-highest "actual yield for clients". The bond highlight feedback is: 10.

[0195] Two bonds are recommended per group, for a total of six. The third bond in each group is displayed blank on the output page.

[0196] Customer B21121 inputs 90 days < "Minimum Holding Period for Bonds" ≤ 180 days. The recommended bond filtering criteria are prioritized as follows:

[0197] ① The customer's input "Minimum holding days for bonds" < "Remaining term" < 365 days.

[0198] ② Rank the top ten in the national debt group and local government debt group according to the "tax-free yield of corporate clients" from high to low; rank the top ten in the policy bank bond group according to the "actual yield of clients" from high to low.

[0199] ③ Select one bond from each of the Treasury bond group and the local government bond group based on the highest "tax-free yield for corporate clients". The bond highlights are: 11 and 6. Select one bond from the policy bank bond group based on the highest "actual yield for clients". The bond highlights are: 12 and 6.

[0200] ④ In the smallest absolute value range of price spreads, select one bond each from the Treasury bond group and the local government bond group based on the highest "tax-free yield for corporate clients," with bond highlights feedback as: 5 and 6; select one bond from the policy bank bond group based on the highest "actual yield for clients," with bond highlights feedback as: 5 and 6. If the absolute values ​​of price spreads are all the same, select the second bond from the Treasury bond group and the local government bond group based on the "tax-free yield for corporate clients" from highest to lowest, with bond highlights feedback as: 13 and 6; select the second bond from the policy bank bond group based on the "actual yield for clients" from highest to lowest, with bond highlights feedback as: 14 and 6.

[0201] ⑤ Re-screen bonds by "Remaining Maturity" ≤ "Minimum Holding Days". Select one bond each from the Treasury Bond Group and the Local Government Bond Group based on the highest "Tax-Free Yield for Corporate Clients". Bond Highlights Feedback: 7. Select one bond from the Policy Bank Bond Group based on the highest "Actual Yield for Clients". Bond Highlights Feedback: 8.

[0202] Three in each group, for a total of nine recommended.

[0203] Customer B21122 entered 180 days < "Minimum Holding Period for Bonds" ≤ 365 days. The recommended bond selection criteria are prioritized as follows:

[0204] ①365 days < "Remaining period" < 730 days.

[0205] ② Rank the top ten in the national debt group and local government debt group according to the "tax-free yield of corporate clients" from high to low; rank the top ten in the policy bank bond group according to the "actual yield of clients" from high to low.

[0206] ③ Select one bond from each of the Treasury bond group and the local government bond group based on the highest "tax-free yield for corporate clients". The bond highlights are: 11 and 6. Select one bond from the policy bank bond group based on the highest "actual yield for clients". The bond highlights are: 12 and 6.

[0207] ④ In the smallest absolute value range of price spreads, select one bond each from the Treasury bond group and the local government bond group based on the highest "tax-free yield for corporate clients," with bond highlights feedback as: 5 and 6; select one bond from the policy bank bond group based on the highest "actual yield for clients," with bond highlights feedback as: 5 and 6. If the absolute values ​​of price spreads are all the same, select the second bond from the Treasury bond group and the local government bond group based on the "tax-free yield for corporate clients" from highest to lowest, with bond highlights feedback as: 13 and 6; select the second bond from the policy bank bond group based on the "actual yield for clients" from highest to lowest, with bond highlights feedback as: 14 and 6.

[0208] ⑤ Re-screen bonds by "Remaining Maturity" ≤ "Minimum Holding Days". Select one bond each from the Treasury Bond Group and the Local Government Bond Group based on the highest "Tax-Free Yield for Corporate Clients". Bond Highlights Feedback: 7. Select one bond from the Policy Bank Bond Group based on the highest "Actual Yield for Clients". Bond Highlights Feedback: 8.

[0209] Three in each group, for a total of nine recommended.

[0210] Customer B212 inputs "Minimum Holding Period for Bonds" ≤ 365 days, referencing 1-year market conditions. If bond prices are falling:

[0211] Customer B2121 inputs "Minimum holding period for bonds" ≤ 180 days. The recommended bond filtering criteria are prioritized as follows for each group:

[0212] ① "Remaining maturity" ≦ "Minimum holding days of the bond".

[0213] ② Select one bond from each of the Treasury bond group and the local government bond group based on the highest "tax-free yield for corporate clients". The bond highlight feedback is: 7. Select one bond from the policy bank bond group based on the highest "actual yield for clients". The bond highlight feedback is: 8.

[0214] ③ Select one bond each from the Treasury bond group and the local government bond group based on the second-highest "tax-free yield for corporate clients". The bond highlight feedback is: 9. Select one bond from the policy bank bond group based on the second-highest "actual yield for clients". The bond highlight feedback is: 10.

[0215] Two bonds are recommended per group, for a total of six. The third bond in each group is displayed blank on the output page.

[0216] Customer B2122 inputs 180 days < "Minimum Holding Period for Bonds" ≤ 365 days. The recommended bond selection criteria are prioritized as follows:

[0217] ① The customer's input "Minimum holding days for bonds" < "Remaining term" < 365 days.

[0218] ② Within the smallest absolute value of the price spread, select two bonds each from the government bond group and the local government bond group, ranked from highest to lowest based on "tax-free yield for corporate clients." The bond highlight feedback is: 5. In the policy bank bond group, select two bonds each from highest to lowest based on "actual yield for clients." The bond highlight feedback is: 5.

[0219] ③ Re-screen bonds by "Remaining Maturity" ≤ "Minimum Holding Days". Select one bond each from the Treasury Bond Group and Local Government Bond Group based on the highest "Tax-Free Yield for Corporate Clients". Bond Highlights Feedback: 7. Select one bond from the Policy Bank Bond Group based on the highest "Actual Yield for Clients". Bond Highlights Feedback: 8.

[0220] Three in each group, for a total of nine recommended.

[0221] Customer B221 inputs "Minimum Holding Period for Bonds" > 365 days. Referencing the 5-year market trend, if the bond price is rising:

[0222] ①730 days < "Remaining term" < 1825 days.

[0223] ② Rank the top ten in the national debt group and local government debt group according to the "tax-free yield of corporate clients" from high to low; rank the top ten in the policy bank bond group according to the "actual yield of clients" from high to low.

[0224] ③ Select one bond from each of the Treasury bond group and the local government bond group based on the highest "tax-free yield for corporate clients". The bond highlights are: 11 and 6. Select one bond from the policy bank bond group based on the highest "actual yield for clients". The bond highlights are: 12 and 6.

[0225] ④ In the smallest absolute value range of price spreads, select one bond each from the Treasury bond group and the local government bond group based on the highest "tax-free yield for corporate clients," with bond highlights feedback as: 5 and 6; select one bond from the policy bank bond group based on the highest "actual yield for clients," with bond highlights feedback as: 5 and 6. If the absolute values ​​of price spreads are all the same, select the second bond from the Treasury bond group and the local government bond group based on the "tax-free yield for corporate clients" from highest to lowest, with bond highlights feedback as: 13 and 6; select the second bond from the policy bank bond group based on the "actual yield for clients" from highest to lowest, with bond highlights feedback as: 14 and 6.

[0226] ⑤ Re-screen bonds by "Remaining Maturity" ≤ "Minimum Holding Days". Select one bond each from the Treasury Bond Group and the Local Government Bond Group based on the highest "Tax-Free Yield for Corporate Clients". Bond Highlights Feedback: 7. Select one bond from the Policy Bank Bond Group based on the highest "Actual Yield for Clients". Bond Highlights Feedback: 8.

[0227] Three in each group, for a total of nine recommended.

[0228] Customer B222 inputs "Minimum Holding Period for Bonds" > 365 days. Referencing the 5-year market trend, if the bond price is declining:

[0229] ①730 days < "Remaining term" < 1095 days.

[0230] ② Rank the top ten in the national debt group and local government debt group according to the "tax-free yield of corporate clients" from high to low; rank the top ten in the policy bank bond group according to the "actual yield of clients" from high to low.

[0231] ③ Select one bond from each of the Treasury bond group and the local government bond group based on the highest "tax-free yield for corporate clients". The bond highlights are: 11 and 6. Select one bond from the policy bank bond group based on the highest "actual yield for clients". The bond highlights are: 12 and 6.

[0232] ④ In the smallest absolute value range of price spreads, select one bond each from the Treasury bond group and the local government bond group based on the highest "tax-free yield for corporate clients," with bond highlights feedback as: 5 and 6; select one bond from the policy bank bond group based on the highest "actual yield for clients," with bond highlights feedback as: 5 and 6. If the absolute values ​​of price spreads are all the same, select the second bond from the Treasury bond group and the local government bond group based on the "tax-free yield for corporate clients" from highest to lowest, with bond highlights feedback as: 13 and 6; select the second bond from the policy bank bond group based on the "actual yield for clients" from highest to lowest, with bond highlights feedback as: 14 and 6.

[0233] ⑤ Re-screen bonds by "Remaining Maturity" ≤ "Minimum Holding Days". Select one bond each from the Treasury Bond Group and the Local Government Bond Group based on the highest "Tax-Free Yield for Corporate Clients". Bond Highlights Feedback: 7. Select one bond from the Policy Bank Bond Group based on the highest "Actual Yield for Clients". Bond Highlights Feedback: 8.

[0234] Three in each group, for a total of nine recommended.

[0235] It is understood that in the specific implementation of this application, data such as target user information are involved. When the above embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0236] This application, by acquiring target user information, detailed information on multiple operational products, and operational metrics for operational projects, can comprehensively understand user needs, product characteristics, and current market trends. Combining predictive models with operational trend analysis allows for more accurate judgment of which products will be more competitive or aligned with market development trends in the future. This enables recommendation results to consider not only current user preferences but also future market changes, thereby improving the accuracy and foresight of recommendations. Utilizing predictive models to analyze operational trends gives the system the ability to dynamically adapt to the market environment. Traditional recommendation systems often rely on static historical data, while this application dynamically adjusts recommendation strategies through real-time or periodically updated operational metrics (such as sales growth trends, user activity, and market competition). This capability is particularly important for coping with a rapidly changing market environment, helping companies seize opportunities and mitigate risks.

[0237] By filtering multiple operational products through rule models, the most suitable products can be automatically matched to target users according to recommendation strategies. This not only reduces the time cost of manual screening and decision-making but also avoids biases caused by human factors. Furthermore, accurate recommendations can effectively improve conversion rates, reduce ineffective marketing activities, lower customer acquisition costs, and improve overall operational efficiency. This application, through in-depth analysis of target user information (such as user profiles, historical behavior, and preference characteristics), combined with product information and operational trends, can provide users with highly personalized product recommendations. This personalized service experience not only improves user satisfaction but also helps enhance user stickiness and promote the establishment of long-term customer relationships. By flexibly configuring rule models and predictive models, it can quickly adapt to different business scenarios and provide targeted solutions. It fully utilizes various types of structured data (such as user information and product attributes) and unstructured data (such as the changing trends of operational indicators), and through machine learning or statistical models for modeling and analysis, it significantly improves the data value mining capability. Compared to traditional human experience-based judgment, it has stronger data processing capabilities and a higher level of intelligence, enabling it to discover hidden patterns and rules from massive amounts of data, assisting enterprises in making more scientific decisions.

[0238] Figure 3 A structural diagram of a product recommendation device provided in this application embodiment is shown below. Figure 3 As shown, based on the method for recommending operational products provided in the preceding embodiments, this application also provides a corresponding device for recommending operational products, including:

[0239] The acquisition module is used to acquire target user information, product information of multiple operational products corresponding to the operational project, and operational metrics of the operational project.

[0240] The prediction module is used to determine the operational trend of the operational project based on the prediction model and the operational indicators of the operational project.

[0241] The recommendation strategy determination module is used to determine the recommendation strategy based on the operational trends of the operational projects.

[0242] The recommended operational product determination module is used to filter the multiple operational products based on the recommendation strategy, the product information of the multiple operational products, and the target user information using a rule model, and determine the recommended operational products.

[0243] As an optional embodiment, the device further includes:

[0244] The extraction module is used to extract key information from the product information of the multiple operating products to obtain key information of the multiple operating products.

[0245] As an optional implementation, the recommended operating product determination module specifically includes:

[0246] The type determination unit is used to determine the type of the target user based on the target user information.

[0247] The personal recommendation unit is used to filter the multiple operational products based on the recommendation strategy, the product information of the multiple operational products, and the target user information, using the personal rule layer in the rule model if the target user is an individual, and to determine the recommended operational products.

[0248] The enterprise recommendation unit is used to filter the multiple operational products based on the recommendation strategy, the product information of the multiple operational products, and the target user information, and determine the recommended operational products if the target user is an enterprise.

[0249] As an optional embodiment, the personal recommendation unit specifically includes:

[0250] The first judgment subunit is used to filter multiple operational products according to the first filtering rule and determine the recommended operational product if the target user information meets any one of the first filtering conditions. The first filtering conditions include a first sub-condition, a second sub-condition, a third sub-condition, and a fourth sub-condition. The first sub-condition includes that the target held in the target user information is a first holding target. The second sub-condition includes that the target held in the target user information is a second holding target, the minimum holding days in the target user information are less than or equal to a first preset threshold, and the recommendation strategy is a first strategy. The third sub-condition includes that the target held in the target user information is a second holding target, the minimum holding days in the target user information are less than or equal to a second preset threshold, and the recommendation strategy is a second strategy.

[0251] The second judgment subunit is used to define the remaining period as greater than the minimum holding days in the target user information and less than the third preset threshold if the target user information meets the second screening condition. It then filters multiple operating products according to the remaining period and performs a second screening on the multiple operating products after screening according to the second screening rule to determine the recommended operating product. The second screening condition includes the target holding in the target user information being the second holding target, the minimum holding days in the target user information being greater than the first preset threshold and less than or equal to the fourth preset threshold, and the recommendation strategy being the first strategy.

[0252] The third judgment subunit is used to define the remaining period as greater than the third preset threshold and less than the fifth preset threshold if the target user information meets the third screening condition. It then filters multiple operating products according to the remaining period and performs a second screening on the multiple operating products after screening according to the second screening rule to determine the recommended operating product. The third screening condition includes the target holding in the target user information being the second holding target, the minimum holding days in the target user information being greater than the fourth preset threshold and less than or equal to the third preset threshold, and the recommendation strategy being the first strategy.

[0253] The fourth judgment subunit is used to define the remaining period as greater than the minimum holding days in the target user information and less than the third preset threshold if the target user information meets the fourth screening condition. It then filters multiple operating products according to the remaining period and performs a second screening on the filtered multiple operating products according to the second screening rule to determine the recommended operating product. The fourth screening condition includes the target holding in the target user information being the second holding target, the minimum holding days in the target user information being greater than the fourth preset threshold and less than or equal to the third preset threshold, and the recommendation strategy being the second strategy.

[0254] The fifth judgment subunit is used to define the remaining period as greater than the fifth preset threshold and less than the sixth preset threshold if the target user information meets the fifth screening condition. It then filters multiple operating products according to the remaining period and performs a second screening on the multiple operating products after screening according to the second screening rule to determine the recommended operating product. The fifth screening condition includes the target holding target in the target user information being the second holding target, the minimum holding days in the target user information being greater than the third preset threshold, and the recommendation strategy being the first strategy.

[0255] The sixth judgment subunit is used to define the remaining period as greater than the fifth preset threshold and less than the seventh preset threshold if the target user information meets the sixth screening condition. It then filters multiple operational products according to the remaining period and performs a second screening on the multiple operational products after screening according to the second screening rule to determine the recommended operational product. The sixth screening condition includes the target holding target in the target user information being the second holding target, the minimum holding days in the target user information being greater than the third preset threshold, and the recommendation strategy being the second strategy.

[0256] The seventh judgment subunit is used to define the remaining period as greater than the minimum holding days in the target user information and less than the third preset threshold if the target user information meets the seventh screening condition. It then filters multiple operating products according to the remaining period and performs a second screening on the filtered multiple operating products according to the second screening rule to determine the recommended operating product. The seventh screening condition includes the target holding in the target user information being the second holding target, the minimum holding days in the target user information being greater than the second preset threshold and less than or equal to the fourth preset threshold, and the recommendation strategy being the second strategy.

[0257] As an optional embodiment, the enterprise recommendation unit specifically includes:

[0258] The eighth judgment subunit is used to filter multiple operational products according to the fourth filtering rule and determine the recommended operational product if the target user information meets any one of the eighth filtering conditions. The eighth filtering conditions include the fifth sub-condition, the sixth sub-condition, and the seventh sub-condition. The fifth sub-condition includes the target holding in the target user information being the first holding target. The sixth sub-condition includes the target holding in the target user information being the second holding target, the minimum holding days in the target user information being less than or equal to the third preset threshold, and the recommendation strategy being the first strategy. The seventh sub-condition includes the target holding in the target user information being the second holding target, the minimum holding days in the target user information being less than or equal to the fourth preset threshold, and the recommendation strategy being the second strategy.

[0259] The ninth judgment subunit is used to filter multiple operating products according to the fifth screening rule and determine three recommended operating products if the target user information meets the ninth screening condition. The ninth screening condition includes the target holding target in the target user information being the second holding target, the minimum holding days in the target user information being greater than the second preset threshold and less than or equal to the fourth preset threshold, and the recommendation strategy being the first strategy.

[0260] The tenth judgment subunit is used to filter multiple operating products according to the sixth screening rule if the target user information meets the tenth screening condition, and determine three recommended operating products; the tenth screening condition includes the target holding target in the target user information being the second holding target, the minimum holding days in the target user information being greater than the fourth preset threshold and less than or equal to the third preset threshold, and the recommendation strategy being the first strategy.

[0261] The eleventh judgment subunit is used to filter multiple operational products according to the seventh screening rule if the target user information meets the eleventh screening condition, and determine three recommended operational products; the eleventh screening condition includes the target holding target in the target user information being the second holding target, the minimum holding days in the target user information being greater than the fourth preset threshold and less than or equal to the third preset threshold, and the recommendation strategy being the second strategy.

[0262] The twelfth judgment subunit is used to filter multiple operational products after the second screening according to the eighth screening rule if the target user information meets the twelfth screening condition, and determine the recommended operational product; the twelfth screening condition includes the target holding target in the target user information being the second holding target, the minimum holding days in the target user information being greater than the third preset threshold, and the recommendation strategy being the first strategy.

[0263] The thirteenth judgment subunit is used to filter multiple operational products after the second screening according to the ninth screening rule if the target user information meets the thirteenth screening condition, and to determine the recommended operational product; the thirteenth screening condition includes the target holding target in the target user information being the second holding target, the minimum holding days in the target user information being greater than the third preset threshold, and the recommendation strategy being the second strategy.

[0264] As an optional embodiment, the first filtering rule includes defining the remaining period as less than the minimum holding days in the target user information, filtering multiple operating products according to the remaining period, sorting the multiple operating products after filtering, and determining the first and second ranked operating products as recommended operating products.

[0265] The second screening rule includes sorting the multiple screened operational products according to operational indicators to obtain a ranking result; determining the absolute value of the price difference for each operational product; if the absolute values ​​of the price differences for multiple operational products are inconsistent, the operational product with the smallest absolute value of the price difference and the first-ranked operational product in the ranking result are selected as recommended operational products; if the absolute values ​​of the price differences for multiple operational products are consistent, the first-ranked and second-ranked operational products in the ranking result are selected as recommended operational products.

[0266] The third screening rule includes screening based on the ranking of the screened operational products, and determining the first one as the recommended operational product.

[0267] As an optional embodiment, the fourth screening rule includes defining the remaining period as less than or equal to the minimum number of days held in the target user information, screening multiple operational products according to the remaining period and preset screening requirements, sorting the multiple operational products after screening according to operational indicators, and determining the first and second ranked operational products as recommended operational products.

[0268] The fifth screening rule includes a first sub-screening rule and a second sub-screening rule. The first sub-screening rule includes defining the remaining term as greater than the minimum holding days in the target user information and less than a third preset threshold, screening multiple operating products according to the remaining term and preset screening requirements, and sorting the screened operating products according to operating indicators to obtain a ranking result; determining the absolute value of the price difference for each operating product, and if the absolute values ​​of the price differences for multiple operating products are inconsistent, then the operating product with the smallest absolute value of the price difference and the first-ranked operating product in the ranking result are selected as recommended operating products; if the absolute values ​​of the price differences for multiple operating products are consistent, then the first-ranked and second-ranked operating products in the ranking result are selected as recommended operating products. The second sub-screening rule includes defining the remaining term as less than or equal to the minimum holding days in the target user information, screening multiple operating products according to the remaining term and preset screening requirements, and sorting the screened operating products according to operating indicators, and selecting the first-ranked operating product in the ranking result as the recommended operating product.

[0269] The sixth screening rule includes a third sub-screening rule and a fourth sub-screening rule. The third sub-screening rule includes defining the remaining term as greater than a third preset threshold and less than a fifth preset threshold, screening multiple operational products according to the remaining term and preset screening requirements, and sorting the screened operational products according to operational indicators to obtain a ranking result; determining the absolute value of the price difference for each operational product, and if the absolute values ​​of the price differences for multiple operational products are inconsistent, then the operational product with the smallest absolute value of the price difference and the first-ranked operational product in the ranking result are selected as recommended operational products; if the absolute values ​​of the price differences for multiple operational products are consistent, then the first-ranked and second-ranked operational products in the ranking result are selected as recommended operational products. The fourth sub-screening rule includes defining the remaining term as less than or equal to the minimum holding days in the target user information, screening multiple operational products according to the remaining term and preset screening requirements, and sorting the screened operational products according to operational indicators, and selecting the first-ranked operational product in the ranking result as the recommended operational product.

[0270] The seventh screening rule includes the fifth sub-screening rule and the second sub-screening rule; the fifth sub-screening rule includes defining the remaining period as greater than the minimum holding days in the target user information and less than the third preset threshold, screening multiple operational products according to the remaining period and preset screening requirements, sorting the multiple operational products after screening according to operational indicators, and determining the first and second ranked operational products as recommended operational products.

[0271] The eighth screening rule includes defining the remaining term as greater than the fifth preset threshold and less than the sixth preset threshold, screening multiple operating products according to the remaining term and preset screening requirements, and sorting the screened multiple operating products according to operating indicators to obtain a ranking result; determining the absolute value of the price difference for each operating product, if the absolute values ​​of the price differences of multiple operating products are inconsistent, then the first-ranked operating product in the ranking result is taken as the recommended operating product, and if the absolute values ​​of the price differences of multiple operating products are consistent, then the first-ranked operating product and the second-ranked operating product in the ranking result are determined as recommended operating products.

[0272] The ninth screening rule includes defining the remaining term as greater than the fifth preset threshold and less than the seventh preset threshold, screening multiple operating products according to the remaining term and preset screening requirements, and sorting the screened multiple operating products according to operating indicators to obtain a ranking result; determining the absolute value of the price difference for each operating product, if the absolute values ​​of the price differences of multiple operating products are inconsistent, then the first-ranked operating product in the ranking result is taken as the recommended operating product, and if the absolute values ​​of the price differences of multiple operating products are consistent, then the first-ranked operating product and the second-ranked operating product in the ranking result are determined as recommended operating products.

[0273] This application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement a recommended method for operating a product.

[0274] This application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements a recommended method for operating a product.

[0275] This application provides a computer program product, including a computer program that, when executed by a processor, implements a recommended method for operating the product.

[0276] It should be noted that the various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, for the device and apparatus embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiments. The device and apparatus embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components indicated as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of the solution in this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0277] The above description is merely one specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for recommending operational products, characterized in that, The methods for recommending the operational products include: Acquire target user information, product information of multiple operational products corresponding to the operational project, and operational metrics of the operational project; The operational trend of the operational project is determined based on the predictive model and the operational indicators of the operational project. The recommendation strategy is determined based on the operational trends of the aforementioned projects; The recommended operational products are determined by using a rule model based on the recommendation strategy, product information of the multiple operational products, and target user information.

2. The method for recommending operational products according to claim 1, characterized in that, The method further includes: Key information is extracted from the product information of the multiple operational products to obtain key information of the multiple operational products.

3. The method for recommending operational products according to claim 1, characterized in that, The step of using a rule model to filter the multiple operational products based on the recommendation strategy, product information of the multiple operational products, and target user information to determine the recommended operational products specifically includes: The type of target user is determined based on the target user information; If the target user is an individual, then the individual rule layer in the rule model is used to filter the multiple operational products based on the recommendation strategy, the product information of the multiple operational products, and the target user information to determine the recommended operational products; If the target user is an enterprise, then the enterprise rule layer in the rule model is used to filter the multiple operational products based on the recommendation strategy, the product information of the multiple operational products, and the target user information to determine the recommended operational products.

4. The method for recommending operational products according to claim 3, characterized in that, The step of using the personal rule layer in the rule model to filter the multiple operational products based on the recommendation strategy, the product information of the multiple operational products, and the target user information to determine the recommended operational products specifically includes: If the target user information meets any one of the first screening conditions, then multiple operational products are screened according to the first screening rule to determine the recommended operational product; the first screening conditions include a first sub-condition, a second sub-condition, a third sub-condition, and a fourth sub-condition; the first sub-condition includes that the target held in the target user information is a first holding target; the second sub-condition includes that the target held in the target user information is a second holding target, the minimum holding days in the target user information are less than or equal to a first preset threshold, and the recommendation strategy is a first strategy; the third sub-condition includes that the target held in the target user information is a second holding target, the minimum holding days in the target user information are less than or equal to a second preset threshold, and the recommendation strategy is a second strategy; If the target user information meets the second screening condition, the remaining period is defined as being greater than the minimum holding days in the target user information and less than the third preset threshold. Multiple operating products are screened according to the remaining period, and the multiple operating products after screening are screened again according to the second screening rule to determine the recommended operating product. The second screening condition includes the target holding in the target user information being the second holding target, the minimum holding days in the target user information being greater than the first preset threshold and less than or equal to the fourth preset threshold, and the recommendation strategy being the first strategy. If the target user information meets the third screening condition, the remaining period is defined as being greater than the third preset threshold and less than the fifth preset threshold. Multiple operational products are screened according to the remaining period, and the multiple operational products after screening are screened again according to the second screening rule to determine the recommended operational product. The third screening condition includes the target holding in the target user information being the second holding target, the minimum holding days in the target user information being greater than the fourth preset threshold and less than or equal to the third preset threshold, and the recommendation strategy being the first strategy. If the target user information meets the fourth screening condition, the remaining period is defined as being greater than the minimum holding days in the target user information and less than the third preset threshold. Multiple operating products are screened according to the remaining period, and the multiple operating products after screening are screened again according to the second screening rule to determine the recommended operating product. The fourth screening condition includes the target holding in the target user information being the second holding target, the minimum holding days in the target user information being greater than the fourth preset threshold and less than or equal to the third preset threshold, and the recommendation strategy being the second strategy. If the target user information meets the fifth screening condition, the remaining period is defined as being greater than the fifth preset threshold and less than the sixth preset threshold. Multiple operational products are screened according to the remaining period, and the multiple operational products after screening are screened again according to the second screening rule to determine the recommended operational products. The fifth screening condition includes the target holding in the target user information being the second holding target, the minimum holding days in the target user information being greater than the third preset threshold, and the recommendation strategy being the first strategy. If the target user information meets the sixth screening condition, the remaining period is defined as being greater than the fifth preset threshold and less than the seventh preset threshold. Multiple operational products are screened according to the remaining period, and the multiple operational products after screening are screened again according to the second screening rule to determine the recommended operational products. The sixth screening condition includes the target holding in the target user information being the second holding target, the minimum holding days in the target user information being greater than the third preset threshold, and the recommendation strategy being the second strategy. If the target user information meets the seventh screening condition, the remaining period is defined as being greater than the minimum holding days in the target user information and less than the third preset threshold. Multiple operating products are screened according to the remaining period, and the multiple operating products after screening are screened again according to the second screening rule to determine the recommended operating product. The seventh screening condition includes the target holding in the target user information being the second holding target, the minimum holding days in the target user information being greater than the second preset threshold and less than or equal to the fourth preset threshold, and the recommendation strategy being the second strategy.

5. The method for recommending operational products according to claim 3, characterized in that, The step of using the enterprise rule layer in the rule model to filter the multiple operational products based on the recommendation strategy, the product information of the multiple operational products, and the target user information to determine the recommended operational products specifically includes: If the target user information meets any one of the eighth screening conditions, then multiple operational products are screened according to the fourth screening rule to determine the recommended operational product; the eighth screening condition includes the fifth sub-condition, the sixth sub-condition, and the seventh sub-condition; the fifth sub-condition includes the target holding in the target user information being the first holding target; the sixth sub-condition includes the target holding in the target user information being the second holding target, the minimum holding days in the target user information being less than or equal to the third preset threshold, and the recommendation strategy being the first strategy; the seventh sub-condition includes the target holding in the target user information being the second holding target, the minimum holding days in the target user information being less than or equal to the fourth preset threshold, and the recommendation strategy being the second strategy; If the target user information meets the ninth screening condition, then multiple operational products are screened according to the fifth screening rule to determine three recommended operational products; the ninth screening condition includes the target holding target in the target user information being the second holding target, the minimum holding days in the target user information being greater than the second preset threshold and less than or equal to the fourth preset threshold, and the recommendation strategy being the first strategy; If the target user information meets the tenth screening condition, then multiple operational products are screened according to the sixth screening rule to determine three recommended operational products; the tenth screening condition includes the target holding target in the target user information being the second holding target, the minimum holding days in the target user information being greater than the fourth preset threshold and less than or equal to the third preset threshold, and the recommendation strategy being the first strategy; If the target user information meets the eleventh screening condition, then multiple operational products are screened according to the seventh screening rule to determine three recommended operational products; the eleventh screening condition includes the target holding target in the target user information being the second holding target, the minimum holding days in the target user information being greater than the fourth preset threshold and less than or equal to the third preset threshold, and the recommendation strategy being the second strategy; If the target user information meets the twelfth screening condition, then the multiple operational products after the second screening are screened according to the eighth screening rule to determine the recommended operational products; the twelfth screening condition includes the target holding target in the target user information being the second holding target, the minimum holding days in the target user information being greater than the third preset threshold, and the recommendation strategy being the first strategy; If the target user information meets the thirteenth screening condition, then the multiple operational products after the second screening are screened according to the ninth screening rule to determine the recommended operational product; the thirteenth screening condition includes the target holding target in the target user information being the second holding target, the minimum holding days in the target user information being greater than the third preset threshold, and the recommendation strategy being the second strategy.

6. The method for recommending operational products according to claim 4, characterized in that, The first filtering rule includes defining the remaining period as less than the minimum holding days in the target user information, filtering multiple operating products according to the remaining period, sorting the multiple operating products after filtering, and determining the first and second ranked operating products as recommended operating products. The second screening rule includes sorting the multiple screened operational products according to operational indicators to obtain a ranking result; determining the absolute value of the price difference for each operational product; if the absolute values ​​of the price differences for multiple operational products are inconsistent, the operational product with the smallest absolute value of the price difference and the first-ranked operational product in the ranking result are selected as recommended operational products; if the absolute values ​​of the price differences for multiple operational products are consistent, the first-ranked and second-ranked operational products in the ranking result are selected as recommended operational products. The third screening rule includes screening based on the ranking of the screened operational products, and determining the first one as the recommended operational product.

7. The method for recommending operational products according to claim 5, characterized in that, The fourth screening rule includes defining the remaining period as less than or equal to the minimum number of days held in the target user information, screening multiple operational products according to the remaining period and preset screening requirements, sorting the multiple operational products after screening according to operational indicators, and determining the first and second ranked operational products as recommended operational products. The fifth screening rule includes a first sub-screening rule and a second sub-screening rule. The first sub-screening rule includes defining the remaining term as greater than the minimum holding days in the target user information and less than a third preset threshold, screening multiple operating products according to the remaining term and preset screening requirements, and sorting the screened operating products according to operating indicators to obtain a ranking result; determining the absolute value of the price difference for each operating product, and if the absolute values ​​of the price differences for multiple operating products are inconsistent, then the operating product with the smallest absolute value of the price difference and the first-ranked operating product in the ranking result are selected as recommended operating products; if the absolute values ​​of the price differences for multiple operating products are consistent, then the first-ranked and second-ranked operating products in the ranking result are selected as recommended operating products. The second sub-screening rule includes defining the remaining term as less than or equal to the minimum holding days in the target user information, screening multiple operating products according to the remaining term and preset screening requirements, and sorting the screened operating products according to operating indicators, and selecting the first-ranked operating product in the ranking result as the recommended operating product. The sixth screening rule includes a third sub-screening rule and a fourth sub-screening rule. The third sub-screening rule includes defining the remaining term as greater than a third preset threshold and less than a fifth preset threshold, screening multiple operational products according to the remaining term and preset screening requirements, and sorting the screened operational products according to operational indicators to obtain a ranking result; determining the absolute value of the price difference for each operational product, and if the absolute values ​​of the price differences for multiple operational products are inconsistent, then the operational product with the smallest absolute value of the price difference and the first-ranked operational product in the ranking result are selected as recommended operational products; if the absolute values ​​of the price differences for multiple operational products are consistent, then the first-ranked and second-ranked operational products in the ranking result are selected as recommended operational products. The fourth sub-screening rule includes defining the remaining term as less than or equal to the minimum holding days in the target user information, screening multiple operational products according to the remaining term and preset screening requirements, and sorting the screened operational products according to operational indicators, and selecting the first-ranked operational product in the ranking result as the recommended operational product. The seventh screening rule includes the fifth sub-screening rule and the second sub-screening rule; the fifth sub-screening rule includes defining the remaining period as greater than the minimum holding days in the target user information and less than the third preset threshold, screening multiple operational products according to the remaining period and preset screening requirements, and sorting the multiple operational products after screening according to operational indicators, and determining the first and second ranked operational products as recommended operational products. The eighth screening rule includes defining the remaining term as greater than the fifth preset threshold and less than the sixth preset threshold, screening multiple operating products according to the remaining term and preset screening requirements, and sorting the screened multiple operating products according to operating indicators to obtain a ranking result; determining the absolute value of the price difference of each operating product, if the absolute values ​​of the price differences of multiple operating products are inconsistent, the first-ranked operating product in the ranking result is taken as the recommended operating product, if the absolute values ​​of the price differences of multiple operating products are consistent, the first-ranked operating product and the second-ranked operating product in the ranking result are determined as recommended operating products; The ninth screening rule includes defining the remaining term as greater than the fifth preset threshold and less than the seventh preset threshold, screening multiple operating products according to the remaining term and preset screening requirements, and sorting the screened multiple operating products according to operating indicators to obtain a ranking result; determining the absolute value of the price difference for each operating product, if the absolute values ​​of the price differences of multiple operating products are inconsistent, then the first-ranked operating product in the ranking result is taken as the recommended operating product, and if the absolute values ​​of the price differences of multiple operating products are consistent, then the first-ranked operating product and the second-ranked operating product in the ranking result are determined as recommended operating products.

8. A device for recommending operating products, characterized in that, The device for recommending the operating products includes: The acquisition module is used to acquire target user information, product information of multiple operational products corresponding to the operational project, and operational metrics of the operational project. The prediction module is used to determine the operational trend of the operational project based on the prediction model and the operational indicators of the operational project; The recommendation strategy determination module is used to determine the recommendation strategy based on the operational trends of the operational projects. The recommended operational product determination module is used to filter the multiple operational products based on the recommendation strategy, the product information of the multiple operational products, and the target user information using a rule model, and determine the recommended operational products.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the recommended method for operating the product as described in any one of claims 1-7.

10. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the recommended method for operating the product as described in any one of claims 1-7.

Images