Product recommendation method and apparatus, computer-readable storage medium, and processor

Abstract

The application discloses a product recommendation method and device, a computer readable storage medium and a processor. The method comprises the following steps: obtaining a set of products to be recommended for a target object; determining attribute information of each product to be recommended in the set of products to be recommended according to a user preference attribute table, wherein the user preference attribute table is used for recording attribute information of historical products selected by the target object; determining a recommendation score according to the attribute information of each product to be recommended, wherein the recommendation score is used for quantifying the selection tendency of the target object to product attributes; and recommending the products to be recommended to the target object according to the recommendation score. The application solves the technical problem that product recommendation cannot be accurately performed.

Description

Product recommendation methods, devices, computer-readable storage media, and processors Technical Field

[0001] This invention relates to the field of computers, and more specifically, to a product recommendation method, apparatus, computer-readable storage medium, and processor. Background Technology

[0002] Traditional recommendation systems simply select certain products to display to users. The interaction with users is essentially "preparing a recommendation list, and the user browsing the list in the order of recommendations." Because this process of interaction with users is not fully incorporated, the recommended content may not be of interest to the user.

[0003] There is currently no effective solution to the problem of inaccurate product recommendations mentioned above. Summary of the Invention

[0004] This invention provides a product recommendation method, apparatus, computer-readable storage medium, and processor to at least solve the technical problem of inaccurate product recommendations.

[0005] According to one aspect of the present invention, a product recommendation method is provided, comprising: obtaining a set of products to be recommended for a target object; determining attribute information of each product to be recommended in the set of products to be recommended based on a user preference attribute table, wherein the user preference attribute table is used to record attribute information of historical products selected by the target object; determining a recommendation score based on the attribute information of each product to be recommended, wherein the recommendation score is used to quantify the target object's preference for product attributes; and recommending the products to be recommended to the target object based on the recommendation score.

[0006] Optionally, obtaining the set of products to be recommended for the target object includes: obtaining product browsing records and product purchase records of all preset objects in a preset shopping platform, wherein the product browsing records are used to represent all browsed products of the preset objects in the preset shopping platform, and the product purchase records are used to identify all purchased products of the preset objects in the preset shopping platform; determining a first selection weight of the browsed products and a second selection weight of the purchased products; determining a selection score of the browsed products based on the first selection weight, and determining a selection score of the purchased products based on the second selection weight, wherein the selection score is used to quantify the target object's preference for products; and determining the set of products to be recommended for the target object based on the selection scores of the browsed products and the selection scores of the purchased products.

[0007] Optionally, before determining the attribute information of each product to be recommended in the set of products to be recommended based on the user preference attribute table, the method further includes: selecting a pair of products to be compared in the set of products to be recommended, wherein the pair of products to be compared consists of the two products with the greatest similarity difference in the set of products to be recommended; obtaining the target product selected by the target object from the pair of products to be compared; and determining the user preference attribute table based on the attribute information of the target product.

[0008] Optionally, the attribute information includes: attribute items, and determining the user preference attribute table based on the attribute information of the target product includes: obtaining the target attribute items of the target product; and updating the selection count corresponding to the target attribute items in the user preference attribute table.

[0009] Optionally, after updating the selection count of the target attribute item in the user preference attribute table, the method further includes: sorting the attribute items in the user preference attribute table in descending order of the selection count; distributing the descendingly sorted attribute items to a first attribute set and a second attribute set in a serpentine manner; selecting a first product to be recommended that satisfies the first attribute set and a second product to be recommended that satisfies the second attribute set from the set of products to be recommended; and using the first product to be recommended and the second product to be recommended as the product pair to be compared.

[0010] Optionally, after sorting the attribute items in the user preference attribute table in descending order of the number of selections, the method further includes: detecting empty attribute items in the user preference attribute table in descending order of the number of selections, wherein the empty attribute items are attribute items that do not exist in the products to be recommended in the set of products to be recommended.

[0011] Optionally, after selecting the first product to be recommended and the first product to be compared as the product pair to be compared, the method further includes: recording the number of times the product pair to be compared is selected; and determining a recommendation score for each product to be recommended if the number of selections exceeds a preset selection threshold.

[0012] According to another aspect of the present invention, a product recommendation apparatus is also provided, comprising: an acquisition module, configured to acquire a set of products to be recommended for a target object; a first determination module, configured to determine attribute information of each product to be recommended in the set of products to be recommended based on a user preference attribute table, wherein the user preference attribute table is used to record attribute information of historical products selected by the target object; a second determination module, configured to determine a recommendation score based on the attribute information of each product to be recommended, wherein the recommendation score is used to quantify the target object's preference for product attributes; and a recommendation module, configured to recommend the products to be recommended to the target object based on the recommendation score.

[0013] According to another aspect of the present invention, a computer-readable storage medium is also provided for storing a program, wherein the program controls the device where the computer-readable storage medium is located to execute the above-described product recommendation method when the program is running.

[0014] According to another aspect of the present invention, a processor is also provided, characterized in that the processor is used to run a program, wherein the program executes the above-described product recommendation method when it runs.

[0015] In this embodiment of the invention, a set of products to be recommended to the target object is obtained; the attribute information of each product to be recommended in the set of products to be recommended is determined according to a user preference attribute table, wherein the user preference attribute table is used to record the attribute information of historical products selected by the target object; a recommendation score is determined according to the attribute information of each product to be recommended, wherein the recommendation score is used to quantify the target object's preference for product attributes; and products to be recommended are recommended to the target object according to the recommendation score, thereby achieving the purpose of recommending products to the target object based on the target object's preference for product attributes, thus achieving the technical effect of accurately recommending products to the target object, and thus solving the technical problem of inaccurate product recommendation. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0017] Figure 1 is a flowchart of a product recommendation method according to an embodiment of the present invention;

[0018] Figure 2 is a schematic diagram of a product recommendation device according to an embodiment of the present invention;

[0019] Figure 3 is a structural block diagram of a computer terminal according to an embodiment of the present invention. Detailed Implementation

[0020] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0021] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0022] According to an embodiment of the present invention, a product recommendation method embodiment is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0023] Figure 1 is a flowchart of a product recommendation method according to an embodiment of the present invention. As shown in Figure 1, the method includes the following steps:

[0024] Step S102: Obtain the set of products to be recommended for the target object;

[0025] Step S104: Determine the attribute information of each product to be recommended in the set of products to be recommended based on the user preference attribute table, wherein the user preference attribute table is used to record the attribute information of historical products selected by the target object;

[0026] Step S106: Determine the recommendation score based on the attribute information of each product to be recommended, wherein the recommendation score is used to quantify the target object's preference for product attributes;

[0027] Step S108: Recommend the product to be recommended to the target audience based on the recommendation score.

[0028] In this embodiment of the invention, a set of products to be recommended to the target object is obtained; the attribute information of each product to be recommended in the set of products to be recommended is determined according to a user preference attribute table, wherein the user preference attribute table is used to record the attribute information of historical products selected by the target object; a recommendation score is determined according to the attribute information of each product to be recommended, wherein the recommendation score is used to quantify the target object's preference for product attributes; and products to be recommended are recommended to the target object according to the recommendation score, thereby achieving the purpose of recommending products to the target object based on the target object's preference for product attributes, thus achieving the technical effect of accurately recommending products to the target object, and thus solving the technical problem of inaccurate product recommendation.

[0029] In step S102 above, the target audience can be users who need product recommendations.

[0030] In step S102 above, the set of products to be recommended can be determined based on the target object's historical shopping information, wherein the historical shopping information includes at least: product browsing history and product purchase history.

[0031] In step S104 above, the user preference attribute table is determined based on the attribute information of the target object's historical product selections. For example, the user preference attribute table can record the product's attribute items and the number of times each attribute item was selected.

[0032] Optionally, the attribute information may include: attribute items and the number of times each attribute item was selected.

[0033] In step S106 above, the recommendation score of the product to be recommended can be determined based on the attribute items of the product to be recommended and the number of times each attribute item is selected.

[0034] As an optional embodiment, obtaining the set of products to be recommended for the target object includes: obtaining product browsing records and product purchase records of all preset objects in a preset shopping platform, wherein the product browsing records are used to represent the browsed products of all preset objects in the preset shopping platform, and the product purchase records are used to identify the purchased products of all preset objects in the preset shopping platform; determining a first selection weight for browsed products and a second selection weight for purchased products; determining a selection score for browsed products based on the first selection weight, and determining a selection score for purchased products based on the second selection weight, wherein the selection score is used to quantify the target object's preference for products; and determining the set of products to be recommended for the target object based on the selection scores for browsed products and the selection scores for purchased products.

[0035] The above embodiments of the present invention can determine the products that most preset objects are interested in based on the product browsing and purchase records of all preset objects in a preset shopping platform. If multiple preset users purchase the same product, it indicates that most preset objects are interested in that product, and therefore the product is recommended to the target object, which will have a high probability of purchasing the product. Similarly, if multiple preset users browse the same product, it indicates that most preset objects are interested in that product, and therefore the product is recommended to the target object, which will have a high probability of purchasing the product. Furthermore, for the same product purchase and browsing behavior, the purchased product should be more of an interest than the browsed product. Therefore, when determining the products to be recommended to the target object based on the product browsing and purchase records, it is necessary to normalize the purchased products of the browsed products of the target object through selection weighting to determine the normalized selection score. The selection score quantifies the selection tendency of most preset objects towards the product, and then determines the set of products to be recommended to the target object based on the selection score. The target object then has a high probability of purchasing the products recommended in the set of products to be recommended, thus achieving the purpose of determining the set of products to be recommended to the target object based on the product browsing and purchase records of all preset objects in the preset shopping platform.

[0036] Optionally, the weight of the first choice is lower than the weight of the second choice.

[0037] Optionally, let c be the total number of products viewed by all preset objects in the preset shopping platform, b be the total number of products purchased, and each view be equivalent to b / c purchases. b / c is the first selection weight, and the second selection weight is 1.

[0038] As an optional embodiment, before determining the attribute information of each product in the set of products to be recommended based on the user preference attribute table, the method further includes: selecting a pair of products to be compared in the set of products to be recommended, wherein the pair of products to be compared consists of the two products with the greatest similarity difference in the set of products to be recommended; obtaining the target product selected by the target object from the pair of products to be compared; and determining the user preference attribute table based on the attribute information of the target product.

[0039] In the above embodiments of the present invention, before recommending products to the target object, two products with the greatest similarity difference can be selected from the set of products to be recommended as products to be compared for the target object to choose from. Then, a user preference attribute table is determined based on the attribute information of the target product selected by the target object, and the user preference attribute table represents the target object's preference for product attributes.

[0040] Optionally, the two products with the greatest similarity difference in the set of products to be recommended can be selected as the product pair to be compared. The greater the difference between the two products in the product pair to be compared, the more it can indicate the user's preference.

[0041] As an optional embodiment, the attribute information includes: attribute items. Determining the user preference attribute table based on the attribute information of the target product includes: obtaining the target attribute items of the target product; and updating the selection count corresponding to the target attribute items in the user preference attribute table.

[0042] In the above embodiments of the present invention, the attribute information of each product may include at least one attribute item. If the user preference attribute table records the attribute information of multiple products, then the user preference attribute table may record multiple attribute items and the number of times each attribute item is selected.

[0043] Optionally, the number of times an attribute item is selected can be determined based on the number of times a product is selected. For example, if product A includes attribute item A, product B includes attribute item A, and product C does not include attribute item A, and the target user selects product A, product B, and product C, then two of the three products include attribute item A. In this case, the user preference attribute table can record that attribute item A was selected twice.

[0044] As an optional embodiment, after updating the selection count of the target attribute item in the user preference attribute table, the method further includes: sorting the attribute items in the user preference attribute table in descending order of selection count; distributing the descendingly sorted attribute items to a first attribute set and a second attribute set in a serpentine manner; selecting a first recommended product that satisfies the first attribute set and a second recommended product that satisfies the second attribute set from the set of recommended products; and using the first recommended product and the second recommended product as a product pair to be compared.

[0045] In the above embodiments of the present invention, the serpentine allocation means that the attribute items arranged in descending order are divided into multiple attribute clusters. Each attribute cluster may include at least one attribute item. The attribute cluster in the first position is allocated to the first attribute set, the attribute cluster in the second position is allocated to the second attribute set, and then the attribute cluster in the third position is allocated to the first attribute set, the attribute cluster in the fourth position is allocated to the second attribute set, and so on.

[0046] As an optional embodiment, after sorting the attribute items in the user preference attribute table in descending order of selection frequency, the method further includes: detecting empty attribute items in the user preference attribute table in descending order of selection frequency, wherein the empty attribute items are attribute items that do not exist in the products to be recommended in the set of products to be recommended.

[0047] In the above embodiments of the present invention, attribute items selected less frequently represent attribute items that users are not interested in. The attribute items recorded in the user preference attribute table can be arranged in descending order of selection frequency, and then the attribute items arranged in descending order are compared with the product attributes of the product to be recommended in turn.

[0048] For example, the attribute information of the product to be recommended includes: attribute item A, attribute item B, attribute item C, and attribute item N. If the descending order of the attribute items in the user preference attribute table is: attribute item A, attribute item B, attribute item C, and attribute item D, according to the user preference attribute table, the target audience does not care about attribute item N. Therefore, when recommending products to the target audience, there is no need to consider attribute item N. By checking the attribute information of the product to be recommended according to the descending order of the attribute items in the user preference attribute table, attribute items that the target audience does not care about, such as attribute item N, can be eliminated.

[0049] As an optional embodiment, after selecting the first product to be recommended and the first product to be compared as a pair of products to be compared, the method further includes: recording the number of times the pair of products to be compared is selected; and determining a recommendation score for each product to be recommended if the number of selections exceeds a preset selection threshold.

[0050] In the above embodiments of the present invention, the process of updating the user preference attribute table cannot be performed indefinitely, and each update of the user preference attribute table requires the target object to select from the product pair to be compared. Therefore, by setting the number of times the target object can select from the product pair to be compared, the number of times the user preference attribute table can be updated can be limited.

[0051] As an optional embodiment, determining the attribute information of each product to be recommended in the set of products to be recommended based on the user preference attribute table includes: identifying at least one recommended attribute item for each product to be recommended, and querying the selection count of each recommended attribute item in the user preference attribute table; determining the recommendation score based on the attribute information of each product to be recommended includes: determining the sum of the selection counts of at least one recommended attribute item in the same product to be recommended as the recommendation score.

[0052] For example, the user preference attribute table records that the attribute "red" was selected 2 times, the attribute "white" was selected 3 times, the attribute "home appliances" was selected 2 times, the attribute "daily necessities" was selected 1 time, the attribute "plastic" was selected 4 times, and the attribute "metal" was selected 6 times. Therefore, if a product to be recommended has the attributes "red", "daily necessities", and "plastic", its score will be 2 + 1 + 4 = 7 points.

[0053] As an optional embodiment, recommending products to a target object based on recommendation scores includes: recommending products to a target object whose recommendation scores are higher than a preset score threshold.

[0054] Optionally, recommending products to the target audience based on recommendation ratings also includes: arranging the products to be recommended in descending order of their ratings, and then selecting the products ranked highest by a preset number to recommend to the target audience.

[0055] The present invention also provides a preferred embodiment, which provides a question-and-answer type recommendation system.

[0056] Step 1: Obtain all users' historical clicked products (and browsed products) and purchased products as interaction data; obtain the attributes of each product as product data (i.e., attribute information). Let c be the total number of browsed products and b be the total number of purchased products for all preset objects in the preset shopping platform. Each browse is equivalent to b / c purchases, where b / c is the first selection weight, and the second selection weight is 1. The first and second selection weights can also be manually set. Convert the number of clicks into the number of purchases, add this to the original purchase quantity, and use this as the purchase count as described below.

[0057] Step 2: Select the top N products with the most historical purchases from all preset objects on the preset shopping platform as recommendation candidates (i.e., determine the set of products to be recommended).

[0058] Step 3: Randomly select one product from the recommended candidate products (i.e., the set of products to be recommended); then, select another product that is least similar to it from the recommended candidate products. These two products are used as the initial product pair to be compared, and the user (i.e., the target audience) chooses the one they prefer.

[0059] Step 4: After the user (i.e., the target audience) makes a selection, update the "User Preference Attribute Table" by incrementing the selection count of the corresponding attribute of the product selected by the user (i.e., the target audience) by 1. For example, the current User Preference Attribute Table is as follows:

[0060] Attributes: Red, White, Home Appliances, Daily Chemicals, Plastic, Metal; Number of selections: 221145 surface

[0061] The product attribute selected by the current user (i.e., the target object) is (0 for no, 1 for yes):

[0062]

[0063]

[0064] The updated user preference attribute table is as follows:

[0065]

[0066] Step 5: From the current user preference attribute table, distribute the attributes to both sides in a serpentine manner according to the number of selections (the top 1 selected attribute is distributed to the left side, the top 2 and 3 to the right side, the top 4 and 5 to the left side, and so on). At the same time, continuously check whether there are still products on both sides that satisfy all the assigned attributes, until one side has no products.

[0067] For example, regarding the updated user preference attribute table mentioned above:

[0068] Attributes: Red, White, Home Appliances, Daily Chemicals, Plastic, Metal; Number of selections: 232146 surface

[0069] The left side (i.e., the first attribute set) is assigned "metal". There are products with the attribute "metal". Continue;

[0070] The right side (i.e., the second attribute set) is assigned "plastic" and "white". There are products with the attributes "plastic" and "white", so continue;

[0071] The left side (i.e., the first attribute set) is assigned "red" and "home appliances". There are products with the attributes "metal", "red" and "home appliances". Continue;

[0072] If the right side (i.e., the second attribute set) is assigned to "daily chemical products", and there are no products with the attributes "plastic", "white", or "daily chemical products", then stop.

[0073] The final left-side attributes (i.e., the first set of attributes) are "metal", "red", and "home appliance", while the right-side attributes (i.e., the second set of attributes) are "plastic" and "white".

[0074] Step 6: Randomly select one product from the left and right sides (i.e., the first attribute set and the second attribute set) that meets the attribute requirements, and use it as a new pair of products to be compared, allowing the user to choose the one they prefer.

[0075] Step 7: Go to step 4 and continue until the preset number of times K is reached (i.e., the cycle ends when the number of selections exceeds the preset selection threshold).

[0076] Step 8: For each product, score it according to the final user preference attribute table. The score for each product is equal to the sum of the number of times each attribute of the product is selected in the user preference attribute table. For example, if a product has the attributes "red", "daily chemical", and "plastic", its score is 2 + 1 + 4 = 7 points (that is, the sum of the number of times at least one attribute item of the same product to be recommended is the recommendation score).

[0077] Step 9: Recommend the M products with the highest scores to the user (that is, recommend the products with scores higher than the preset score threshold to the target audience).

[0078] The question-and-answer recommendation system provided by this invention allows users to select their preferred product from two options provided by the system, repeating this process multiple times until the system understands the user's preferences and provides a better recommendation experience.

[0079] According to an embodiment of the present invention, a product recommendation device embodiment is also provided. It should be noted that the product recommendation device can be used to execute the product recommendation method in the embodiments of the present invention, and the product recommendation method in the embodiments of the present invention can be executed in the product recommendation device.

[0080] Figure 2 is a schematic diagram of a product recommendation device according to an embodiment of the present invention. As shown in Figure 2, the device may include: an acquisition module 22, used to acquire a set of products to be recommended for a target object; a first determination module 24, used to determine the attribute information of each product to be recommended in the set of products to be recommended according to a user preference attribute table, wherein the user preference attribute table is used to record the attribute information of historical products selected by the target object; a second determination module 26, used to determine a recommendation score according to the attribute information of each product to be recommended, wherein the recommendation score is used to quantify the target object's preference for product attributes; and a recommendation module 28, used to recommend products to be recommended to the target object according to the recommendation score.

[0081] It should be noted that the acquisition module 22 in this embodiment can be used to execute step S102 in this application embodiment, the first determination module 24 in this embodiment can be used to execute step S104 in this application embodiment, the second determination module 26 in this embodiment can be used to execute step S106 in this application embodiment, and the recommendation module 28 in this embodiment can be used to execute step S108 in this application embodiment. The examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the content disclosed in the above embodiments.

[0082] In this embodiment of the invention, a set of products to be recommended to the target object is obtained; the attribute information of each product to be recommended in the set of products to be recommended is determined according to a user preference attribute table, wherein the user preference attribute table is used to record the attribute information of historical products selected by the target object; a recommendation score is determined according to the attribute information of each product to be recommended, wherein the recommendation score is used to quantify the target object's preference for product attributes; and products to be recommended are recommended to the target object according to the recommendation score, thereby achieving the purpose of recommending products to the target object based on the target object's preference for product attributes, thus achieving the technical effect of accurately recommending products to the target object, and thus solving the technical problem of inaccurate product recommendation.

[0083] As an optional embodiment, the apparatus further includes: a first acquisition unit, configured to acquire a set of products to be recommended for the target object, including: acquiring product browsing records and product purchase records of all preset objects in a preset shopping platform, wherein the product browsing records are used to represent the browsed products of all preset objects in the preset shopping platform, and the product purchase records are used to identify the purchased products of all preset objects in the preset shopping platform; a first determination unit, configured to determine a first selection weight for the browsed products and a second selection weight for the purchased products; a second determination unit, configured to determine a selection score for the browsed products based on the first selection weight and a selection score for the purchased products based on the second selection weight, wherein the selection score is used to quantify the target object's preference for products; and a third determination unit, configured to determine a set of products to be recommended for the target object based on the selection scores for the browsed products and the selection scores for the purchased products.

[0084] As an optional embodiment, the apparatus further includes: a selection unit, configured to select a pair of products to be compared in the set of products to be recommended before determining the attribute information of each product to be recommended in the set of products to be recommended based on the user preference attribute table, wherein the pair of products to be compared consists of the two products with the greatest similarity difference in the set of products to be recommended; a second acquisition unit, configured to acquire the target product selected by the target object from the pair of products to be compared; and a fourth determination unit, configured to determine the user preference attribute table based on the attribute information of the target product.

[0085] As an optional embodiment, the attribute information includes: attribute items, and the fourth determining unit includes: a first obtaining subunit, used to obtain the target attribute items of the target product; and an updating subunit, used to update the selection count corresponding to the target attribute items in the user preference attribute table.

[0086] As an optional embodiment, the apparatus further includes: an arranging subunit, configured to arrange the attribute items in the user preference attribute table in descending order of selection count after updating the selection count of the target attribute item in the user preference attribute table; an allocation subunit, configured to allocate the descendingly arranged attribute items to a first attribute set and a second attribute set in a serpentine manner; a selection subunit, configured to select a first product to be recommended that satisfies the first attribute set and a second product to be recommended that satisfies the second attribute set from the set of products to be recommended; and a first determining subunit, configured to treat the first product to be recommended and the second product to be recommended as a product pair to be compared.

[0087] As an optional embodiment, the apparatus further includes: a detection subunit, configured to detect empty attribute items in the user preference attribute table in descending order of selection count after sorting the attribute items in the user preference attribute table in descending order of selection count, wherein the empty attribute items are attribute items that do not exist in the products to be recommended in the set of products to be recommended.

[0088] As an optional embodiment, the apparatus further includes: a recording subunit, configured to record the number of times the product pair to be compared is selected after the first product to be recommended and the first product to be recommended are selected as a product pair to be compared; and a second determining subunit, configured to determine a recommendation score for each product to be recommended if the number of selections exceeds a preset selection threshold.

[0089] As an optional embodiment, the first determining module includes: an identification submodule, used to identify at least one recommended attribute item for each product to be recommended, and to query the selection count of each recommended attribute item in the user preference attribute table; the second determining module includes: a determining submodule, used to determine the sum of the selection counts of at least one recommended attribute item in the same product to be recommended as the recommendation score.

[0090] As an optional embodiment, the recommendation module includes a recommendation submodule, used to recommend products with a recommendation score higher than a preset score threshold to the target object.

[0091] Embodiments of the present invention can provide a computer terminal, which can be any computer terminal device in a group of computer terminals. Optionally, in this embodiment, the computer terminal can also be replaced by a mobile terminal or other terminal device.

[0092] Optionally, in this embodiment, the computer terminal may be located in at least one of a plurality of network devices in a computer network.

[0093] In this embodiment, the computer terminal described above can execute the program code for the following steps in the product recommendation method: obtaining a set of products to be recommended for the target object; determining the attribute information of each product to be recommended in the set of products to be recommended based on a user preference attribute table, wherein the user preference attribute table is used to record the attribute information of historical products selected by the target object; determining a recommendation score based on the attribute information of each product to be recommended, wherein the recommendation score is used to quantify the target object's preference for product attributes; and recommending products to be recommended to the target object based on the recommendation score.

[0094] Optionally, FIG3 is a structural block diagram of a computer terminal according to an embodiment of the present invention. As shown in FIG3, the computer terminal 30 may include: one or more (only one is shown in the figure) processors 32 and memory 34.

[0095] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the product recommendation method and apparatus in this embodiment of the invention. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby realizing the aforementioned product recommendation method. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to terminal A via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0096] The processor can access information and application programs stored in memory via a transmission device to perform the following steps: obtaining a set of products to be recommended for the target object; determining the attribute information of each product to be recommended in the set of products to be recommended based on a user preference attribute table, wherein the user preference attribute table is used to record the attribute information of historical products selected by the target object; determining a recommendation score based on the attribute information of each product to be recommended, wherein the recommendation score is used to quantify the target object's preference for product attributes; and recommending products to be recommended to the target object based on the recommendation score.

[0097] Optionally, the processor may also execute program code for the following steps: obtaining product browsing records and product purchase records of all preset objects in a preset shopping platform, wherein the product browsing records are used to represent the browsed products of all preset objects in the preset shopping platform, and the product purchase records are used to identify the purchased products of all preset objects in the preset shopping platform; determining a first selection weight for browsed products and a second selection weight for purchased products; determining a selection score for browsed products based on the first selection weight, and determining a selection score for purchased products based on the second selection weight, wherein the selection score is used to quantify the target object's preference for products; and determining a set of products to be recommended to the target object based on the selection scores for browsed products and the selection scores for purchased products.

[0098] Optionally, the processor may also execute program code for the following steps: before determining the attribute information of each product to be recommended in the set of products to be recommended based on the user preference attribute table, selecting a pair of products to be compared in the set of products to be recommended, wherein the pair of products to be compared consists of the two products with the greatest similarity difference in the set of products to be recommended; obtaining the target product selected by the target object from the pair of products to be compared; and determining the user preference attribute table based on the attribute information of the target product.

[0099] Optionally, the attribute information includes: attribute items. The processor may also execute program code that performs the following steps: obtains the target attribute items of the target product; updates the selection count corresponding to the target attribute items in the user preference attribute table.

[0100] Optionally, the processor may also execute program code that performs the following steps: after updating the selection count of the target attribute item in the user preference attribute table, sorting the attribute items in the user preference attribute table in descending order of selection count; distributing the descendingly sorted attribute items to the first attribute set and the second attribute set in a serpentine manner; selecting a first recommended product that satisfies the first attribute set and a second recommended product that satisfies the second attribute set from the set of recommended products; and using the first recommended product and the second recommended product as a pair of products to be compared.

[0101] Optionally, the processor may also execute program code that performs the following steps: after sorting the attribute items in the user preference attribute table in descending order of selection count, detects the empty attribute items in the user preference attribute table in descending order of selection count, wherein the empty attribute items are attribute items that do not exist in the products to be recommended in the set of products to be recommended.

[0102] Optionally, the processor may also execute program code that performs the following steps: after selecting the first product to be recommended and the first product to be compared as a pair of products to be compared, record the number of times the pair of products to be compared is selected; if the number of selections exceeds a preset selection threshold, determine the recommendation score for each product to be recommended.

[0103] Optionally, the processor may also execute program code that performs the following steps: identifies at least one recommended attribute for each product to be recommended, and queries the user preference attribute table for the number of selections of each recommended attribute; and determines the sum of the number of selections of at least one recommended attribute for the same product to be recommended as the recommendation score.

[0104] Optionally, the processor may also execute program code that recommends products with a recommendation score higher than a preset score threshold to the target object.

[0105] This invention provides a product recommendation scheme. It involves: acquiring a set of products to be recommended to a target user; determining the attribute information of each product in the set based on a user preference attribute table, where the user preference attribute table records the attribute information of historically selected products by the target user; determining a recommendation score based on the attribute information of each product, where the recommendation score quantifies the target user's preference for product attributes; and recommending products to the target user based on the recommendation score. This achieves the goal of recommending products to the target user based on their preference for product attributes, thus realizing the technical effect of accurately recommending products to the target user and solving the technical problem of inaccurate product recommendation.

[0106] Those skilled in the art will understand that the structure shown in Figure 3 is merely illustrative, and the computer terminal may also be a smartphone (such as an Android phone, an iOS phone, etc.), a tablet computer, a point-and-shoot computer, a mobile internet device (MID), a PAD, or other terminal device. Figure 3 does not limit the structure of the aforementioned electronic device. For example, the computer terminal 3 may also include more or fewer components (such as a network interface, a display device, etc.) than shown in Figure 3, or have a different configuration than that shown in Figure 3.

[0107] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0108] Embodiments of the present invention also provide a storage medium. Optionally, in this embodiment, the computer-readable storage medium described above can be used to store the program code executed by the product recommendation method provided in the above embodiments.

[0109] Optionally, in this embodiment, the computer-readable storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0110] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: obtaining a set of products to be recommended for a target object; determining the attribute information of each product to be recommended in the set of products to be recommended according to a user preference attribute table, wherein the user preference attribute table is used to record the attribute information of historical products selected by the target object; determining a recommendation score based on the attribute information of each product to be recommended, wherein the recommendation score is used to quantify the target object's preference for product attributes; and recommending products to be recommended to the target object based on the recommendation score.

[0111] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: obtaining product browsing records and product purchase records of all preset objects in a preset shopping platform, wherein the product browsing records are used to represent the browsed products of all preset objects in the preset shopping platform, and the product purchase records are used to identify the purchased products of all preset objects in the preset shopping platform; determining a first selection weight for browsed products and a second selection weight for purchased products; determining a selection score for browsed products based on the first selection weight, and determining a selection score for purchased products based on the second selection weight, wherein the selection score is used to quantify the target object's preference for products; and determining a set of products to be recommended to the target object based on the selection scores for browsed products and the selection scores for purchased products.

[0112] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: before determining the attribute information of each product to be recommended in the set of products to be recommended according to the user preference attribute table, selecting a pair of products to be compared in the set of products to be recommended, wherein the pair of products to be compared is the two products with the greatest similarity difference in the set of products to be recommended; obtaining the target product selected by the target object in the pair of products to be compared; and determining the user preference attribute table according to the attribute information of the target product.

[0113] Optionally, in this embodiment, the attribute information includes: attribute items, and the computer-readable storage medium is configured to store program code for performing the following steps: obtaining target attribute items of the target product; updating the selection count corresponding to the target attribute items in the user preference attribute table.

[0114] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: after updating the selection count of the target attribute item in the user preference attribute table, sorting the attribute items in the user preference attribute table in descending order of the selection count; distributing the descendingly sorted attribute items to the first attribute set and the second attribute set in a serpentine manner; selecting a first recommended product that satisfies the first attribute set and a second recommended product that satisfies the second attribute set from the set of recommended products; and using the first recommended product and the second recommended product as a product pair to be compared.

[0115] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: after sorting the attribute items in the user preference attribute table in descending order of the number of selections, detecting the empty attribute items in the user preference attribute table in descending order of the number of selections, wherein the empty attribute items are attribute items that do not exist in the products to be recommended in the set of products to be recommended.

[0116] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: after selecting the first product to be recommended and the first product to be compared as a pair of products to be compared, recording the number of selections of the pair of products to be compared; if the number of selections exceeds a preset selection threshold, determining a recommendation score for each product to be recommended.

[0117] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: identifying at least one recommended attribute item for each product to be recommended, and querying the selection count of each recommended attribute item in the user preference attribute table; determining the sum of the selection counts of at least one recommended attribute item in the same product to be recommended as the recommendation score.

[0118] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: recommending products with a recommendation score higher than a preset score threshold to the target object.

[0119] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0120] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0121] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0122] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0123] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0124] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0125] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A product recommendation method, characterized in that, include: The method involves: obtaining a set of products to be recommended for the target object; determining the attribute information of each product in the set of products to be recommended based on a user preference attribute table, wherein the user preference attribute table records the attribute information of historical products selected by the target object; determining a recommendation score based on the attribute information of each product to be recommended, wherein the recommendation score quantifies the target object's preference for product attributes; recommending the products to be recommended to the target object based on the recommendation score; wherein, before determining the attribute information of each product in the set of products to be recommended based on the user preference attribute table, the method further includes: selecting a pair of products to be compared in the set of products to be recommended, wherein the pair of products to be compared consists of the two products with the greatest similarity difference in the set of products to be recommended; and obtaining the target product selected by the target object from the pair of products to be compared. The method involves determining a user preference attribute table based on the attribute information of the target product, wherein the attribute information includes attribute items, and determining the user preference attribute table based on the attribute information of the target product includes: obtaining target attribute items of the target product; updating the selection count corresponding to the target attribute item in the user preference attribute table; wherein, after updating the selection count of the target attribute item in the user preference attribute table, the method further includes: sorting the attribute items in the user preference attribute table in descending order of the selection count; distributing the descendingly sorted attribute items to a first attribute set and a second attribute set in a serpentine manner; selecting a first product to be recommended that satisfies the first attribute set and a second product to be recommended that satisfies the second attribute set from the set of products to be recommended; and using the first product to be recommended and the second product to be recommended as the product pair to be compared.

2. The method according to claim 1, characterized in that, Obtaining the set of products to be recommended for the target object includes: obtaining the product browsing records and product purchase records of all preset objects in a preset shopping platform, wherein the product browsing records are used to represent the browsed products of all preset objects in the preset shopping platform, and the product purchase records are used to identify the purchased products of all preset objects in the preset shopping platform; determining a first selection weight for the browsed products and a second selection weight for the purchased products; determining a selection score for the browsed products based on the first selection weight, and determining a selection score for the purchased products based on the second selection weight, wherein the selection score is used to quantify the target object's preference for products; and determining the set of products to be recommended for the target object based on the selection scores for the browsed products and the selection scores for the purchased products.

3. The method according to claim 1, characterized in that, After sorting the attribute items in the user preference attribute table in descending order of the number of selections, the method further includes: detecting empty attribute items in the user preference attribute table in descending order of the number of selections, wherein the empty attribute items are attribute items that do not exist in the products to be recommended in the set of products to be recommended.

4. The method according to claim 1, characterized in that, After selecting the first product to be recommended and the first product to be compared as the product pair to be compared, the method further includes: recording the number of times the product pair to be compared is selected; and determining a recommendation score for each product to be recommended if the number of selections exceeds a preset selection threshold.

5. A product recommendation device, characterized in that, include: The acquisition module is used to acquire the set of products to be recommended for the target object; A first determining module is used to determine the attribute information of each product to be recommended in the set of products to be recommended based on a user preference attribute table, wherein the user preference attribute table is used to record the attribute information of historical products selected by the target object; a second determining module is used to determine a recommendation score based on the attribute information of each product to be recommended, wherein the recommendation score is used to quantify the target object's preference for product attributes; a recommending module is used to recommend the products to be recommended to the target object based on the recommendation score; wherein the device further includes: a selection unit, used to select a pair of products to be compared in the set of products to be recommended before determining the attribute information of each product to be recommended based on the user preference attribute table, wherein the pair of products to be compared is the two products with the greatest similarity difference in the set of products to be recommended; a second obtaining unit, used to obtain the target product selected by the target object in the pair of products to be compared; a fourth determining unit, used to The user preference attribute table is determined based on the attribute information of the target product; wherein the attribute information includes attribute items; the fourth determining unit includes: a first obtaining subunit, used to obtain the target attribute items of the target product; an updating subunit, used to update the selection count corresponding to the target attribute item in the user preference attribute table; wherein the device further includes: an arranging subunit, used to arrange the attribute items in the user preference attribute table in descending order of the selection count after updating the selection count of the target attribute item in the user preference attribute table; an allocation subunit, used to allocate the descendingly arranged attribute items to a first attribute set and a second attribute set in a serpentine manner; a selection subunit, used to select a first recommended product that satisfies the first attribute set and a second recommended product that satisfies the second attribute set from the set of products to be recommended; and a first determining subunit, used to take the first recommended product and the first recommended product as the product pair to be compared.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store a program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform the product recommendation method according to any one of claims 1 to 4.

7. A processor, characterized in that, The processor is used to run a program, wherein the program executes the product recommendation method according to any one of claims 1 to 4 when it runs.

Images