Recommendation method and device

Abstract

The invention relates to a recommendation method and device. The method comprises the steps of obtaining user data of a target user and price data of an object to be sold; the to-be-sold object comprises a product or service; based on the user data and the price data of the to-be-sold object, respectively obtaining a purchase intention and a purchase ability of the target user for the to-be-sold object; and determining a target to-be-sold object from the to-be-sold objects based on the purchase intention and the purchase capability, and recommending the target to-be-sold object to the target user. As the target recommendation object has the purchasing willingness and the purchasing capability for the target user, the target user is enabled to be more likely to purchase the target recommendation object by recommending to the target user, and the recommendation efficiency can be improved to a great extent.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and more particularly to recommended methods and apparatus. Background Technology

[0002] With the continuous development of technology, mobile phones and other terminal products have become widely used. Users can easily shop online through their mobile phones.

[0003] In related technologies, online sales platforms typically recommend products to users based on their historical behavior records. However, these recommended products are often not what the users need, resulting in low recommendation efficiency. Summary of the Invention

[0004] This disclosure provides a recommended method and apparatus.

[0005] According to a first aspect of this disclosure, a recommendation method is provided, the method comprising:

[0006] Acquire user data of the target users and price data of the items to be sold; the items to be sold include products or services.

[0007] Based on the user data and the price data of the items for sale, the target user's willingness and ability to purchase the items for sale are obtained respectively.

[0008] Based on the purchase intention and the purchase ability, target products are identified from the products available for sale, and the target products are recommended to the target users.

[0009] According to a second aspect of this disclosure, a recommended apparatus is provided, the apparatus comprising:

[0010] The price data acquisition module is used to acquire user data of target users and price data of objects to be sold; the objects to be sold include products or services.

[0011] The willingness and ability acquisition module is used to acquire the target user's willingness and ability to purchase the object for sale based on the user data and the price data of the object for sale, respectively.

[0012] The recommendation module is used to determine target items for sale from the list of items for sale based on the purchase intention and the purchase ability, and recommend the target items for sale to the target user.

[0013] According to a third aspect of this disclosure, an electronic device is provided. The electronic device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the program to implement the method described above.

[0014] According to a fourth aspect of this disclosure, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the methods described above.

[0015] According to a fifth aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the methods described above.

[0016] The recommendation method and apparatus provided in this disclosure acquire user data of a target user and price data of an object for sale; the object for sale includes products or services; based on the user data and the price data of the object for sale, the target user's willingness and ability to purchase the object for sale are obtained respectively; based on the willingness and ability to purchase, a target object for sale is determined from the objects for sale, and recommended to the target user. Since the target recommended object has the willingness and ability to purchase for the target user, recommending it to the target user makes the target user more likely to purchase the target recommended object, thereby greatly improving recommendation efficiency. Attached Figure Description

[0017] Further details, features, and advantages of this disclosure are disclosed in the following description of exemplary embodiments in conjunction with the accompanying drawings, in which:

[0018] Figure 1 A flowchart of a recommended method provided for an exemplary embodiment of this disclosure;

[0019] Figure 2 A schematic diagram of a motion curve function provided for an exemplary embodiment of this disclosure;

[0020] Figure 3 A schematic block diagram of the functional modules of a recommended apparatus provided for an exemplary embodiment of this disclosure;

[0021] Figure 4 A structural block diagram of an electronic device provided as an exemplary embodiment of this disclosure;

[0022] Figure 5 A block diagram of a computer system provided for an exemplary embodiment of this disclosure. Detailed Implementation

[0023] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0024] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0025] The term "comprising" and its variations as used herein are open-ended, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below. It should be noted that the concepts of "first", "second", etc., used in this disclosure are only used to distinguish different devices, modules, or units, and are not intended to limit the order of functions performed by these devices, modules, or units or their interdependencies.

[0026] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0027] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0028] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0029] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message.

[0030] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device. It is understood that the above notification and user authorization process is merely illustrative and does not constitute a limitation on the implementation of this disclosure; other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0031] To improve the efficiency of product or service recommendations and ensure that recommended products or services better meet users' needs and actual purchasing power, embodiments of this disclosure identify user motivations to obtain their willingness to purchase a certain product or service, predict the psychological price point they are willing to pay for that product or service, and determine the products or services the user wants and can afford to buy. By recommending these desired and affordable products or services to users, the probability of them purchasing the recommended products or services can be increased, thereby improving recommendation efficiency.

[0032] Therefore, in order to improve recommendation efficiency, this disclosure first provides a recommendation method, such as... Figure 1 As shown, the method may include the following steps:

[0033] In step S110, user data of the target user and price data of the object to be sold are obtained.

[0034] The items for sale include products or services.

[0035] In the embodiments, for example, when it is detected that a target user is browsing on an online shopping platform, the user data of the target user can be obtained. The user data may include at least one of historical shopping behavior, user profile and real-time behavior data. The real-time behavior data may include the user's browsing or clicking behavior.

[0036] The embodiment can also obtain price data of the object to be sold, which can be a product or service, specifically the product or service that the user is browsing, or currently popular products or services, etc., but the embodiment is not limited to this.

[0037] In step S120, based on user data and price data of the items to be sold, the target user's willingness and ability to purchase the items to be sold are obtained respectively.

[0038] In this embodiment, by analyzing the target user's user data and the price data of the object to be sold, the target user's willingness and ability to purchase the object to be sold are determined.

[0039] When a user's desire to buy is high, their corresponding psychological price point is high; conversely, when their desire to buy is low, their corresponding psychological price point is relatively low. When a user's desire and ability to buy are met, timely recommendations can encourage them to make a purchase, thus facilitating the transaction.

[0040] In this embodiment, a model can be constructed using user data and price data as input to obtain the target user's willingness and ability to purchase the product. For example, real-time acquisition of user behavior data, historical profiles, and market competitor price data is possible. Data required when recommending smart home products and similar products includes user browsing data on home smart security products on mobile apps, such as prices, performance, and likes / dislikes. It can also include publicly available data on consumer spending preferences for home security products from the National Bureau of Statistics or industry association websites, including detailed dimensions and attributes such as region, income level, and family structure. Unstructured knowledge base data can also be fully acquired while adhering to data privacy requirements. This data is used to construct a model that can identify user motivation, purchasing power, and provide timely personalized recommendations.

[0041] In step S130, based on purchasing intention and purchasing ability, target items for sale are identified from the list of items for sale, and the target items for sale are recommended to the target users.

[0042] In this embodiment, by analyzing the target user's purchase intention and purchasing power, target items that the target user wants and can afford to buy are identified from the list of available items for sale, and then recommended to the target user. Since the recommended items are aligned with the target user's purchase intention and purchasing power, recommending them to the target user increases the likelihood of them purchasing the recommended items, thereby significantly improving recommendation efficiency.

[0043] Based on the above embodiments, in another embodiment provided in this disclosure, the method may further include the following steps:

[0044] In step S140, based on user data and price data, a first set of objects for sale with purchasing intentions is determined from the objects for sale.

[0045] In this embodiment, the first step in a user's purchasing behavior is determining whether the user intends to buy. Identifying and predicting the user's intended purchase involves two parts: first, identifying and predicting the product or service the user intends to buy; and second, the probability value of the user's intention to purchase the intended product or service. The final output includes the user identifier, the product or service the user intends to buy, the probability value of the user's intention to purchase the intended product or service, and a single-dimensional dynamic threshold.

[0046] In this embodiment, identifying and predicting the products or services a user intends to purchase may specifically include the following processes:

[0047] 1) Corpus collection.

[0048] In this embodiment, data input can be processed based on the constructed data described above. For example, a related multimodal base model can be used to analyze video, audio, or text corpora generated by users on shopping platforms. Behavioral data such as user logins, business transactions, product processing, or complaints from the business service system can be aggregated to form a corpus that can identify and predict the products or services that users intend to purchase.

[0049] 2) Corpus knowledge processing.

[0050] The implementation can further utilize the vertical model's AI (Artificial Intelligence) video analysis, NLP (Natural Language Processing), speech-to-text and other technical capabilities to process the corpus into an understandable and storable user knowledge base.

[0051] 3) Identify and predict the products or services that users intend to purchase.

[0052] In the embodiments, the interaction behavior between users and the platform can be obtained, for example, by using multi-turn dialogue and intelligent question-answering model capabilities to identify user intent online and transform user intent into the product or service desired by the user.

[0053] For example, you can select knowledge data files from the user's knowledge base covering the past six months to create a user intent-driven product or service set model, such as a neural network model, and configure training parameters such as chunk size, chunk length, semantic chunking, chunking rules, training model type, and filtering rules. The model outputs the set of products or services the user intends to purchase, i.e., the first set of items for sale.

[0054] In step S150, the willingness probability of each item in the first set of items to be sold is obtained, and the purchase willingness of the target user for the item to be sold is determined based on the willingness probability.

[0055] In the embodiments, after identifying the products or services that users want to buy, the users' willingness to buy different products or services is different, and the users' willingness to buy products or services with different prices is also different.

[0056] The example determines the probability of a user's willingness to buy a product by considering multiple dimensions such as emotion, behavior, and rating, and uses this probability as the probability of wanting to buy the product at the base price.

[0057] (1) Input data:

[0058] User historical behavior data on the target product and similar products (such as login, browsing, favorites or complaints), sentiment analysis results of multimodal corpus on the target product and similar products (text, voice or video), and user historical ratings of the target product and similar products (such as 1 to 5 points).

[0059] Calculation of the probability of potential buyers and similar products (W) m The functional relationship is as follows:

[0060] W m =α×S sentiment +β×S behavior +γ×S historical (1)

[0061] S sentiment The sentiment score (0-1) based on NLP is calculated using the following formula:

[0062]

[0063] S behavior Behavioral weight score (0-1), calculation formula:

[0064]

[0065] The behaviors include: click-through rate, dwell time, number of favorites, number of add-to-carts, number of shares, etc., and the weights are determined by AHP (Analytic Hierarchy Process).

[0066] S historical : Normalized historical purchase rating (0-1), calculated using the following formula:

[0067]

[0068] Where α, β, and γ are dynamic adjustment coefficients, which can be obtained by training a random forest model, and α + β + γ = 1.

[0069] For users, their willingness to purchase a product is influenced by both their emotional connection to the current product and the impact of previously recommended products. If the previously recommended product is one that the user has a high purchase intention for, then the purchase intention for the recommended product will be enhanced. Furthermore, the shorter the time interval between the previously recommended product and the product to be recommended, the greater the corresponding enhancement of purchase intention.

[0070] Based on the above, the probability W of wanting to buy m The calculated function relationship is updated as follows:

[0071]

[0072] Where Δt is the time interval between the user's first purchase behavior within a set time period and the end time, and the end time can be the time of the last purchase behavior within the set time period. Wi' is the probability of the user's willingness to buy product l when the user has a purchase behavior within Δt time period, ρ is the number of products that the user has a purchase behavior within Δt time period, ρ is an adjustment factor with a value between 0 and 1, used to set the degree of intention enhancement for different product types, Size is the number of transactions of product l, and P E The frequency of a user's consumption is the factor that determines the impact of preceding products on subsequent products.

[0073] (2) Dynamically determine the target products for sale and the dynamic threshold S(t) for wanting to buy similar products.

[0074]

[0075] Where t is the current time point, T is the product life cycle (unit: days), τ is the best recommended time point for fitting historical data (0≤τ≤1, relative to the life cycle ratio), and γ is the decay coefficient, which controls the sensitivity of the threshold over time. It can represent the absolute distance between the current time and the best recommended time point, and can be obtained by fitting historical data.

[0076] In the embodiment, the above-mentioned willingness probability can be compared with the dynamic to determine whether the user has the willingness to purchase the item for sale, that is, whether they want to buy it.

[0077] Based on the above embodiments, in another embodiment provided in this disclosure, the method may further include the following steps:

[0078] In step S160, the basic consumption capacity index of the target user is obtained based on user data.

[0079] In step S170, the purchasing power of the target user for the target product is determined based on the basic consumption capacity index.

[0080] In this embodiment, feature variables can first be defined and constructed. Based on the data input from the first step of the overall model, feature variables are constructed, such as historical average order price, consumption fluctuations, and income level (e.g., inferred from access address or occupation information), which are related to the user's spending power.

[0081] In the embodiment, a consumer spending power index (CA) for the target products and similar products can be established, which can be referred to as the basic consumer spending power index.

[0082] Specifically, this may include the following processes:

[0083] (1) Select input features through feature engineering.

[0084] Acquire ARPU (average revenue per user) (e.g., average spending on target products and similar products) and spending volatility (μ). j ), activity participation frequency (N), consumption time preference (prefTpref), occupational level (K, discretized code of 1 to 5).

[0085] (2) Train the model using multiple model algorithms such as mmodel_list random forest, GBDT, XGB, and LGBM, and select the model based on the training time and accuracy.

[0086] Below is the logistic regression model.

[0087]

[0088] θ0~θ5: Logistic regression model parameters, which can be obtained by training with historical purchase data.

[0089] μ j Consumption volatility coefficient, calculation formula:

[0090]

[0091] in, This refers to the total spending amount of similar products for each item in a user's spending portfolio at various historical monitoring points in time. Let i represent the total consumption amount of similar products by users at each historical monitoring time point, where i represents the number of each historical monitoring time point, i = 1, 2, ..., n, and j represents the number of the j-th consumption item, j = 1, 2, ..., m. It should be noted that n-1 is used here instead of n as the denominator because it plays a role in unbiased estimation in the calculation of variance.

[0092] The above content determines the consumption capacity index from the perspective of general user spending power. However, for users, their consumption can usually be divided into long-term and short-term consumption capacity. For example, some users, based on their consumption data, have below-average spending power over a long period, but may have above-average spending power during certain holidays or promotional periods. Therefore, as an optimization, it is also necessary to consider the time span between adjacent consumption items in a user's consumption mix and the distribution of consumption peaks. For users with long-term consumption capacity, their consumption density remains balanced, and the changes in each consumption peak are stable. For users with short-term consumption capacity, their consumption density tends to be 0, and their consumption peaks fluctuate significantly.

[0093] Specifically as follows:

[0094] Long-term consumption capacity index (LC)

[0095]

[0096] E is the consumption density index, R is the monetary stability coefficient, and Q is the trend coefficient. The model parameters can be determined through model training, where:

[0097]

[0098] Q = The moving average rate of change of consumption amount over the most recent 3 periods.

[0099] Short-term consumption capacity index (SC).

[0100]

[0101] F represents peak-to-trough volatility, I represents burst message density, and D represents the response coefficient. These are the model parameters, which can be determined through model training. Where:

[0102]

[0103] Based on the calculated spending power index (CA), long-term spending power index (LC), and short-term spending power index (SC), we can fully explore users' precise consumption patterns. For users with a high spending power index and a long-term spending power index greater than a short-term spending power index, we provide regular recommendations. For users with a high spending power index and a short-term spending power index greater than a long-term spending power index, we provide targeted recommendations, i.e., recommendations during promotional periods.

[0104] In the embodiment, for dynamic capability threshold

[0105]

[0106] ARPU norm : Industry percentile of user ARPU (0-1) (Industry ARPU is constructed by modeling data obtained from the National Bureau of Statistics or large models).

[0107] Market_Trend: A market consumption trend index predicted through time series analysis.

[0108] ε1, ε2: weight coefficients, where ε1 + ε2 = 1.

[0109] In this embodiment, by obtaining the target user's basic spending power index and comparing it with a dynamic capability threshold, it can be determined whether the target user has the purchasing power to buy the object for sale.

[0110] Based on the above embodiments, in another embodiment provided in this disclosure, step S130 may further include the following steps:

[0111] In step S131, alternative potential buyers are identified from the pool of potential buyers based on purchasing intentions and purchasing power.

[0112] In this embodiment, candidate candidates for sale are identified from the list of available items. These are the items that the target user wants to buy and has the ability to purchase. To further improve recommendation efficiency, further filtering can be performed on these candidate candidates.

[0113] In step S132, an action curve function for the target user is constructed based on purchase intention and price data.

[0114] The action curve function includes purchase intention and psychological price, with purchase intention and psychological price being positively correlated.

[0115] In step S133, the rate of change of the behavior curve is obtained based on the action curve function, and the target objects for sale that meet the target conditions are determined based on the rate of change of the behavior curve.

[0116] Specifically, in this embodiment, price changes affect purchasing intention, and the intensity of purchasing intention varies with price sensitivity. A dynamic purchasing intention model is constructed using an exponential decay model, and an action curve function is further constructed based on this dynamic purchasing intention model:

[0117]

[0118] Where r is the decay rate, which is obtained by fitting historical data. The probability of purchase intention at the base price (W is the probability of wanting to buy) m W0 is the base price, and w is the real-time price.

[0119] If the base price W0 = 1000 yuan, If the real-time price is W = 1200 yuan and r = 2, then substituting into the formula, we get W. 意愿 =0.54.

[0120]

[0121] The recommendation signal is either 0 or 1. When W... 意愿 >ω, When δ>0.5, the recommendation signal is recommendation 1; otherwise, it is 0.

[0122] ΔS / Δt: The rate of change of the behavior curve, which can be used to capture the user's real-time interest fluctuations.

[0123] In this embodiment, the rate of change of the behavior curve can be obtained based on the action curve function, and target saleable objects that meet the target conditions can be determined based on the rate of change of the behavior curve. For example, such as Figure 2 The above, Figure 2 This is a schematic diagram of the action curve function provided in this embodiment of the disclosure. When a user's desire to buy is high, their corresponding psychological price point is high; when a user's desire to buy is low, their corresponding psychological price point is relatively low. Recommendations can be implemented in a timely manner when the user's desire to buy and ability to buy are satisfied. Combined with... Figure 2 As shown, by obtaining the rate of change of the curve and comparing it with a threshold, the products or services that users want to buy and can buy can be obtained.

[0124] Based on the above embodiments, in another embodiment provided in this disclosure, a recommendation strategy for target users can be generated based on the basic consumption capacity index, long-term consumption capacity index and short-term consumption capacity index obtained above, and target push information can be pushed to target users based on the recommendation strategy.

[0125] In this embodiment, when the basic consumption capacity index is greater than the threshold and the long-term consumption capacity index is greater than the short-term consumption capacity index, target push information is pushed to the target user in the long term.

[0126] For example, when it is determined that CA is greater than a threshold If the long-term consumption capacity index (LC) is greater than the short-term consumption capacity index (SC), then the corresponding strategy type under the conventional recommendation model will be implemented as a long-term recommendation within the current recommendation period.

[0127] Alternatively, when the basic consumption capacity index is greater than the threshold and the long-term consumption capacity index is less than the short-term consumption capacity index, target information can be pushed to the target user in the short term.

[0128] For example, when it is determined that CA is greater than a threshold If the long-term consumption capacity index (LC) is less than the short-term consumption capacity index (SC), then the corresponding strategy type under the regular recommendation model will be implemented as a short-term recommendation within the current recommendation period. In other words, recommendations will only be made during the current activity period.

[0129] Or, if the basic consumption capacity index is less than At that time, a hybrid recommendation model is used to push targeted information to target users. This hybrid recommendation model includes a combination of long-term and short-term recommendations.

[0130] For example, when it is determined that CA is less than (Assuming the normal recommendation mode is met), then the hybrid recommendation mode is executed, that is, the strategy types included in the normal recommendation are combined for recommendation.

[0131] The recommendations in the embodiments may include routine recommendations and targeted recommendations.

[0132] In a standard recommendation model, recommendation strategies are categorized and identified. The corresponding strategy types can include: high motivation-high ability, high motivation-low ability, and low motivation-high ability. In this example, motivation corresponds to the aforementioned willingness, and ability refers to purchasing power.

[0133] For users with high motivation and high ability, purchase links can be directly pushed; for users with high motivation and low ability, installment payment options and coupons can be recommended; for users with low motivation and high ability, social network notifications can be triggered, such as "Your friend is also buying."

[0134] Targeted recommendations include long-term recommendations, short-term recommendations, and hybrid long- and short-term recommendations. Targeted recommendations can serve as a supplementary model to regular recommendations. For example, a high-motivation, high-ability strategy can use long-term recommendations, short-term recommendations, and hybrid long- and short-term recommendations as supplementary recommendation models.

[0135] In the embodiments provided in this disclosure, the purchase intention model can be optimized using the AUC-ROC curve and the F1-Score model evaluation criteria. The model corresponding to the purchase ability can be optimized using model evaluation data such as the Gini coefficient and KS statistic. The model corresponding to the recommendation behavior can be optimized using the recommendation conversion rate and customer retention rate indicators.

[0136] During dynamic parameter optimization, the model can be trained based on the objective function to achieve parameter tuning.

[0137] The objective function can be: (Recommended Returns) i -λ Recommendation Cost i ), where λ is the cost-benefit balance coefficient, which can be dynamically adjusted through reinforcement learning, i is a variable, and n is the number of recommended objects.

[0138] This disclosure enables dynamic prediction and identification of purchase probabilities and achieves nonlinear and feedback-based optimization recommendation technology. For dynamic prediction of purchase probabilities, it constructs models related to purchase intention probability, purchase ability probability, and the relationship between price and intention, forming a dynamic purchase intention model and a method for dynamically adjusting parameters, thus achieving dynamic recommendations based on customer behavior patterns. For nonlinear processing, it uses an exponential decay model that better reflects reality, making the recommendation method more accurate.

[0139] In the case of dividing each functional module according to its corresponding functions, this disclosure provides a recommended device, which can be a server, a terminal, or a chip applied to a server. Figure 3A schematic block diagram of the functional modules of a recommended apparatus provided for an exemplary embodiment of this disclosure. For example... Figure 3 As shown, the recommended device includes:

[0140] Price data acquisition module 10 is used to acquire user data of target users and price data of objects to be sold; the objects to be sold include products or services.

[0141] The willingness and ability acquisition module 20 is used to acquire the target user's willingness and ability to purchase the object for sale based on the user data and the price data of the object for sale, respectively.

[0142] The recommendation module 30 is used to determine a target item from the list of items for sale based on the purchase intention and the purchase ability, and recommend the target item to the target user.

[0143] In yet another embodiment provided in this disclosure, the apparatus further includes:

[0144] Based on the user data and the price data, a first set of objects for sale with purchasing intentions is determined from the objects for sale;

[0145] The willingness probability of each item in the first set of items to be sold is obtained, and the purchase willingness of the target user for the items to be sold is determined based on the willingness probability.

[0146] In another embodiment provided in this disclosure, the apparatus further includes: a purchasing power determination module, specifically used for:

[0147] Based on the user data, obtain the target user's basic spending power index;

[0148] The target user's purchasing power for the items for sale is determined based on the basic consumption capacity index.

[0149] In another embodiment provided in this disclosure, the recommendation module is specifically used for:

[0150] Based on the purchase intention and the purchase ability, alternative sales targets are determined from the sales targets;

[0151] Based on the purchase intention and the price data, an action curve function for the target user is constructed; wherein, the action curve function includes purchase intention and psychological price, and the purchase intention is positively correlated with the psychological price;

[0152] The rate of change of the behavior curve is obtained based on the action curve function, and the target saleable object that meets the target conditions is determined based on the rate of change of the behavior curve.

[0153] In another embodiment provided in this disclosure, the push module is further configured to:

[0154] Obtain the target user's basic spending power index, long-term spending power index, and short-term spending power index;

[0155] Based on the basic consumption capacity index, the long-term consumption capacity index, and the short-term consumption capacity index, a recommendation strategy is generated for the target user, and target push information is pushed to the target user based on the recommendation strategy.

[0156] In another embodiment provided in this disclosure, the push module is further configured to:

[0157] When the basic consumption capacity index is greater than the threshold and the long-term consumption capacity index is greater than the short-term consumption capacity index, target push information is pushed to the target user in the long term.

[0158] Alternatively, when the basic consumption capacity index is greater than the threshold and the long-term consumption capacity index is less than the short-term consumption capacity index, target push information is pushed to the target user in the short term.

[0159] Alternatively, when the basic consumption capacity index is less than a threshold, a hybrid recommendation mode is used to push target information to the target user; wherein, the hybrid recommendation mode includes a hybrid recommendation of long-term recommendation and short-term recommendation.

[0160] The recommendation device provided in this embodiment acquires user data of a target user and price data of items for sale; the items for sale include products or services; based on the user data and the price data of the items for sale, it acquires the target user's purchase intention and purchasing power for the items for sale; based on the purchase intention and purchasing power, it identifies target items for sale from the items for sale and recommends the target items for sale to the target user. Since the target recommended item has purchase intention and purchasing power for the target user, recommending it to the target user makes the target user more likely to purchase the target recommended item, thereby greatly improving recommendation efficiency.

[0161] This disclosure also provides an electronic device, including: at least one processor; a memory for storing processor-executable instructions; wherein the at least one processor is configured to execute the instructions to implement the methods disclosed in this disclosure.

[0162] Figure 4 This is a schematic diagram of the structure of an electronic device provided as an exemplary embodiment of this disclosure. For example... Figure 4As shown, the electronic device 1800 includes at least one processor 1801 and a memory 1802 coupled to the processor 1801. The processor 1801 can perform the corresponding steps in the methods disclosed in the embodiments of this disclosure.

[0163] The processor 1801 described above can also be called a central processing unit (CPU), which can be an integrated circuit chip with signal processing capabilities. Each step in the method disclosed in this embodiment can be implemented by the integrated logic circuitry in the processor 1801 or by software instructions. The processor 1801 can be a general-purpose processor, a digital signal processor (DSP), an ASIC (Application Specific Integrated Circuit), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this embodiment can be directly implemented by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software modules can be located in the memory 1802, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The processor 1801 reads information from the memory 1802 and, in conjunction with its hardware, completes the steps of the method described above.

[0164] Furthermore, various operations / processes according to this disclosure, implemented via software and / or firmware, can be transmitted from a storage medium or network to a computer system with a dedicated hardware architecture, such as... Figure 5 The computer system 1900 shown is equipped with the programs that constitute the software. When various programs are installed, the computer system is able to perform various functions, including those described above. Figure 5 A block diagram of a computer system provided for an exemplary embodiment of this disclosure.

[0165] Computer System 1900 is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices can also represent various forms of mobile devices, such as cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of this disclosure described and / or claimed herein.

[0166] like Figure 5 As shown, the computer system 1900 includes a computing unit 1901, which can perform various appropriate actions and processes based on a computer program stored in a read-only memory (ROM) 1902 or a computer program loaded from a storage unit 1908 into a random access memory (RAM) 1903. The RAM 1903 may also store various programs and data required for the operation of the computer system 1900. The computing unit 1901, ROM 1902, and RAM 1903 are interconnected via a bus 1904. An input / output (I / O) interface 1905 is also connected to the bus 1904.

[0167] Multiple components in computer system 1900 are connected to I / O interface 1905, including: input unit 1906, output unit 1907, storage unit 1908, and communication unit 1909. Input unit 1906 can be any type of device capable of inputting information into computer system 1900. Input unit 1906 can receive input digital or character information and generate key signal inputs related to user settings and / or function control of the electronic device. Output unit 1907 can be any type of device capable of presenting information and may include, but is not limited to, a monitor, speaker, video / audio output terminal, vibrator, and / or printer. Storage unit 1908 may include, but is not limited to, hard disks and optical disks. Communication unit 1909 allows computer system 1900 to exchange information / data with other devices via a network such as the Internet, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers, and / or chipsets, such as Bluetooth™ devices, WiFi devices, WiMax devices, cellular communication devices, and / or the like.

[0168] The computing unit 1901 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1901 performs the various methods and processes described above. For example, in some embodiments, the methods disclosed in this disclosure can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 1908. In some embodiments, part or all of the computer program can be loaded and / or installed on an electronic device via ROM 1902 and / or communication unit 1909. In some embodiments, the computing unit 1901 can be configured to perform the methods disclosed in this disclosure by any other suitable means (e.g., by means of firmware).

[0169] This disclosure also provides a computer-readable storage medium, wherein when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is able to perform the methods disclosed in this disclosure.

[0170] The computer-readable storage medium in this disclosure can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. The aforementioned computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specifically, the aforementioned computer-readable storage medium may include electrical connections based on one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0171] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0172] This disclosure also provides a computer program product, including a computer program, wherein the computer program, when executed by a processor, implements the methods disclosed in the embodiments of this disclosure.

[0173] In embodiments of this disclosure, computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include, but are not limited to, object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network (including a local area network (LAN) or a wide area network (WAN)), or it can be connected to an external computer.

[0174] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0175] The modules, components, or units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the modules, components, or units do not necessarily constitute a limitation on the module, component, or unit itself.

[0176] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary hardware logic components that can be used include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0177] The above description is merely an embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0178] While specific embodiments of this disclosure have been described in detail by way of example, those skilled in the art should understand that the examples are for illustrative purposes only and not intended to limit the scope of this disclosure. Those skilled in the art should understand that modifications can be made to the above embodiments without departing from the scope and spirit of this disclosure. The scope of this disclosure is defined by the appended claims.

Claims

1. A recommendation method, characterized in that, The method includes: Acquire user data of the target users and price data of the items to be sold; the items to be sold include products or services. Based on the user data and the price data of the items for sale, the target user's willingness and ability to purchase the items for sale are obtained respectively. Based on the purchase intention and the purchase ability, target products are identified from the products for sale, and the target products are recommended to the target users.

2. The method according to claim 1, characterized in that, The method further includes: Based on the user data and the price data, a first set of objects for sale with purchasing intentions is determined from the objects for sale; The willingness probability of each item in the first set of items to be sold is obtained, and the purchase willingness of the target user for the items to be sold is determined based on the willingness probability.

3. The method according to claim 2, characterized in that, The method further includes: Based on the user data, obtain the target user's basic spending power index; The target user's purchasing power for the items for sale is determined based on the basic consumption capacity index.

4. The method according to claim 1, characterized in that, The process of identifying target buyers from the pool of available buyers based on the purchase intention and the purchase ability includes: Based on the purchase intention and the purchase ability, alternative sales targets are determined from the sales targets; Based on the purchase intention and the price data, an action curve function for the target user is constructed; wherein, the action curve function includes purchase intention and psychological price, and the purchase intention is positively correlated with the psychological price; The rate of change of the behavior curve is obtained based on the action curve function, and the target saleable object that meets the target conditions is determined based on the rate of change of the behavior curve.

5. The method according to claim 1, characterized in that, The method further includes: Obtain the target user's basic spending power index, long-term spending power index, and short-term spending power index; Based on the basic consumption capacity index, the long-term consumption capacity index, and the short-term consumption capacity index, a recommendation strategy is generated for the target user, and target push information is pushed to the target user based on the recommendation strategy.

6. The method according to claim 5, characterized in that, The method further includes: When the basic consumption capacity index is greater than the threshold and the long-term consumption capacity index is greater than the short-term consumption capacity index, target push information is pushed to the target user in the long term. Alternatively, when the basic consumption capacity index is greater than the threshold and the long-term consumption capacity index is less than the short-term consumption capacity index, target push information is pushed to the target user in the short term. Alternatively, when the basic consumption capacity index is less than a threshold, a hybrid recommendation mode is used to push target information to the target user; wherein, the hybrid recommendation mode includes a hybrid recommendation of long-term recommendation and short-term recommendation.

7. A recommended device, characterized in that, The device includes: The price data acquisition module is used to acquire user data of target users and price data of objects to be sold; the objects to be sold include products or services. The willingness and ability acquisition module is used to acquire the target user's willingness and ability to purchase the object for sale based on the user data and the price data of the object for sale, respectively. The recommendation module is used to determine target items for sale from the list of items for sale based on the purchase intention and the purchase ability, and recommend the target items for sale to the target user.

8. An electronic device, characterized in that, include: At least one processor; Memory for storing the at least one processor-executable instruction; The at least one processor is configured to execute the instructions to implement the method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, When the instructions in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device is able to perform the method as described in any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method according to any one of claims 1-6.

Images