Product data processing method and device, medium, program product and electronic equipment

Abstract

The invention relates to the technical field of data processing, and provides a product data processing method and device, a medium, a program product and electronic equipment. The product data processing method comprises the following steps: determining a target cluster to which a first purchaser belongs according to historical purchase data and historical promotion data of the first purchaser of a product; determining preference weights of the first purchaser for different attribute features of different attributes of the product based on the preference labels of the target cluster for different attributes of the product; according to the preference weight of the first purchaser for different attribute characteristics of different attributes of the product, determining a purchase interest value of the first purchaser for the to-be-purchased product; determining a target to-be-purchased product recommended to the first purchaser from the to-be-purchased products based on the purchasing interest value; and determining product promotion resources allocated to the first purchaser according to the purchase condition of the first purchaser for the target to-be-purchased product. According to the scheme, the accuracy of product popularization resource allocation can be improved.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular, to a product data processing method, a product data processing device, a computer-readable storage medium, a computer program product, and an electronic device. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the disclosure that are recited in the claims, and no description herein is admitted to be prior art by inclusion in this section.

[0003] Existing product data processing methods lack a solution for personalized allocation based on the characteristics of the purchaser and the characteristics of the purchased products when allocating products to be purchased and product promotion resources to each purchaser. Summary of the invention

[0004] However, the above scheme does not make personalized allocations based on the characteristics of the purchaser and the characteristics of the products, resulting in low accuracy in the allocated products to be purchased and promotion resources, which in turn leads to low resource utilization.

[0005] Therefore, a product data processing method is very much needed to improve the accuracy of the allocation of products to be purchased and the allocation of promotion resources, and improve the resource utilization rate.

[0006] In this context, embodiments of the present invention are intended to provide a product data processing method, a product data processing device, a computer-readable storage medium, a computer program product, and an electronic device.

[0007] According to a first aspect of an embodiment of the present disclosure, a product data processing method is provided, including: determining a target cluster to which a first purchaser belongs based on historical purchase data and historical promotion data of the first purchaser of the product; determining the preference weights of the first purchaser for different attribute characteristics of different attributes of the product based on preference labels of the target cluster for different attributes of the product; determining the purchasing interest value of the first purchaser for the product to be purchased based on the preference weights of the first purchaser for different attribute characteristics of different attributes of the product and the target attribute characteristics of different attributes of the product to be purchased; determining the target product to be purchased corresponding to the first purchaser from the products to be purchased based on the purchasing interest value, and recommending the target product to be purchased to the first purchaser; and determining the product promotion resources allocated to the first purchaser based on the purchasing situation of the first purchaser for the target product to be purchased.

[0008] Optionally, determining the target cluster to which the first purchaser belongs based on the historical purchase data and historical promotion data of the first purchaser of the product includes: clustering the first purchasers based on the historical purchase data and historical promotion data of each first purchaser of the product; and obtaining the target cluster to which the first purchaser belongs based on the clustering results.

[0009] Optionally, clustering the first purchasers according to the historical purchase data and historical promotion data of each first purchaser of the product includes: obtaining a first purchase feature of each first purchaser according to the first historical purchase data of each first purchaser of the product, the first purchase feature including attribute features of different attributes of historically purchased products; performing statistical analysis on the second historical purchase data of each first purchaser of the product, and obtaining a purchase preference feature of each first purchaser according to the statistical analysis result, the purchase preference feature being used to indicate the first purchaser's purchase interest in different products, the historical duration of the second historical purchase data being shorter than the historical duration of the first historical purchase data; obtaining a promotion preference feature of each first purchaser according to the historical promotion data of each first purchaser of the product, the promotion preference feature being used to indicate the first purchaser's promotion interest in different products; clustering the first purchasers according to the first purchase feature, a first weight corresponding to the first purchase feature, the purchase preference feature, a second weight corresponding to the purchase preference feature, the promotion preference feature, and a third weight corresponding to the promotion preference feature.

[0010] Optionally, determining the preference labels of the target cluster for different attributes of the product includes: obtaining the preference labels of the target cluster for different attributes of the product according to attribute features of the cluster center of the target cluster in different attributes of the product.

[0011] Optionally, based on the preference labels of the target cluster for different attributes of the product, determining the preference weights of the first purchaser for the attribute characteristics of different attributes of the product includes: for each attribute characteristic of each attribute, calculating the degree of match between the attribute characteristic and the first purchaser's preference label for the attribute, and obtaining the preference weights of the first purchaser for the attribute characteristics of the attribute of the product based on the degree of match.

[0012] Optionally, determining the purchasing interest value of the first purchaser in the product to be purchased based on the first purchaser's preference weights for different attribute characteristics of different attributes of the product and target attribute characteristics of different attributes of the product to be purchased includes: determining the target preference weights of the target attribute characteristics of the product to be purchased by the first purchaser based on the first purchaser's preference weights for different attribute characteristics of different attributes of the product; calculating the first product of each target attribute characteristic of the product to be purchased and the target preference weight of the target attribute characteristic; and determining the interest value of the first purchaser in the product to be purchased based on the sum of the first products.

[0013] Optionally, determining the target product to be purchased corresponding to the first purchaser from the products to be purchased based on the purchasing interest value includes: sorting the products to be purchased in descending order of the purchasing interest value to obtain a sorting result; and determining the first N products to be purchased in the sorting result as the target products to be purchased corresponding to the first purchaser.

[0014] Optionally, determining the product promotion resources to be allocated to the first purchaser based on the purchase situation of the target product to be purchased by the first purchaser includes: determining a virtual score of the first purchaser based on the purchase situation of the target product to be purchased by the first purchaser; and determining the product promotion resources to be allocated to the first purchaser based on the virtual score of the first purchaser.

[0015] Optionally, determining the virtual score of the first purchaser based on the purchase situation of the target product to be purchased by the first purchaser includes: determining the virtual score of the first purchaser based on one or more of a first quantity of the target product to be purchased successfully purchased by the first purchaser and feedback behavior data of the first purchaser on the purchase results of the target product to be purchased.

[0016] Optionally, determining the virtual score of the first purchaser based on the purchase situation of the target product to be purchased by the first purchaser includes: obtaining first promotion data of the target product to be purchased successfully purchased by the first purchaser, the first promotion data including one or more of the number of shares and increased exposure; determining the virtual score of the first purchaser based on the purchase situation of the target product to be purchased by the first purchaser and the first promotion data.

[0017] Optionally, the first purchaser has multiple first purchasers, and the determining of the product promotion resources allocated to the first purchaser based on the virtual score of the first purchaser includes: determining allocation priorities of multiple first purchasers according to the virtual score of the first purchaser, and allocating product promotion resources to the first purchaser based on the allocation priorities; and / or in response to a first consumption request of the first purchaser for the virtual score, determining the promotion traffic matching the virtual score in the first consumption request, and allocating the promotion traffic to the first purchaser; and / or in response to a second consumption request of the first purchaser for the virtual score, determining the promotion tool corresponding to the second consumption request, and allocating the promotion tool to the first purchaser.

[0018] Optionally, the method further includes: predicting the explosive potential value of the successfully purchased product based on user behavior data of the successfully purchased product; determining the next state of the current state of the successfully purchased product based on the explosive potential value of the successfully purchased product; and allocating promotion resources to the successfully purchased product in the current state based on the promotion strategy corresponding to the next state.

[0019] According to a second aspect of the present disclosure, a product data processing device is provided, including: a cluster determination module, configured to determine a target cluster to which a first purchaser belongs based on the historical purchase data and historical promotion data of the first purchaser of the product; a preference weight determination module, configured to determine the preference weights of the first purchaser for different attribute characteristics of different attributes of the product based on the preference labels of the target cluster for different attributes of the product; a purchase interest value determination module, configured to determine the purchase interest value of the first purchaser for the product to be purchased based on the preference weights of the first purchaser for different attribute characteristics of different attributes of the product and the target attribute characteristics of different attributes of the product to be purchased; a recommendation module, configured to determine the target product to be purchased corresponding to the first purchaser from the products to be purchased based on the purchase interest value, and recommend the target product to be purchased to the first purchaser; a promotion resource allocation module, configured to determine the product promotion resources allocated to the first purchaser based on the purchase situation of the first purchaser for the target product to be purchased.

[0020] According to a third aspect of the present disclosure, a computer program product comprising instructions is provided, which, when executed on a computer, enables the computer to execute the steps of the product data processing method as described in the first aspect.

[0021] According to a fourth aspect of an embodiment of the present disclosure, there is provided a computer-readable storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the steps of the product number processing method as described in the first aspect above are implemented.

[0022] According to the fifth aspect of the embodiment of the present disclosure, there is provided an electronic device, comprising: a processor; and a storage device for storing one or more programs, which, when executed by the one or more processors, enables the one or more processors to implement the product data processing method as described in the first aspect of the above embodiment.

[0023] According to the product data processing method, product data processing device, computer-readable storage medium, computer program product and electronic device of the embodiment of the present disclosure, the target cluster of the purchaser is determined according to the historical purchase data and historical promotion data of the purchaser of the product, and the preference weights of the purchaser for different attribute characteristics of different attributes of the product are determined based on the preference labels of the target cluster, so as to recommend products to be purchased to the purchaser according to the preference weights, and allocate product promotion resources to the purchaser according to the purchase situation of the purchaser for the purchased products. On the one hand, the present disclosure can portray the purchaser's portrait according to the purchaser's historical purchase data and historical promotion data, so as to allocate products to be purchased to the purchaser according to the purchase interest of the purchaser, and improve the accuracy of the allocation of products to be purchased; on the other hand, the present disclosure allocates product promotion resources to the purchaser according to the purchase situation of the purchaser for the recommended products to be purchased, and can reasonably allocate promotion resources to the purchaser according to the purchase enthusiasm of the purchaser, improve the accuracy of the allocation of promotion resources, and improve the utilization rate of promotion resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, in which:

[0025] Figure 1 A schematic diagram showing an exemplary system architecture to which embodiments of the present disclosure may be applied;

[0026] Figure 2 A schematic diagram showing a flow chart of a promotion data processing method in an exemplary embodiment of the present disclosure;

[0027] Figure 3 A schematic diagram showing a flow chart of a method for determining a target cluster in an exemplary embodiment of the present disclosure;

[0028] Figure 4 A schematic flow chart showing a method for clustering purchasers in an exemplary embodiment of the present disclosure;

[0029] Figure 5 A flowchart showing a method for determining a purchase interest value in an exemplary embodiment of the present disclosure is shown;

[0030] Figure 6 A flow chart showing a method for allocating product promotion resources in an exemplary embodiment of the present disclosure;

[0031] Figure 7 A flow chart showing a method for determining a virtual score of a purchaser in an exemplary embodiment of the present disclosure;

[0032] Figure 8 A flowchart diagram showing another method for allocating product promotion resources in an exemplary embodiment of the present disclosure;

[0033] Fig. 9 A schematic diagram showing the composition of a product data processing device in an exemplary embodiment of the present disclosure;

[0034] Fig.10 A schematic structural diagram of an electronic device in an exemplary embodiment of the present disclosure is shown.

[0035] In the drawings, the same or corresponding reference numerals represent the same or corresponding parts. DETAILED DESCRIPTION

[0036] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present invention, and are not intended to limit the scope of the present invention in any way. On the contrary, these embodiments are provided to make the present invention more thorough and complete, and to fully convey the scope of the present invention to those skilled in the art.

[0037] Those skilled in the art know that the embodiments of the present invention can be implemented as a system, device, apparatus, method or computer program product. Therefore, the present invention can be specifically implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0038] According to an embodiment of the present invention, a product data processing method, a product data processing device, a computer-readable storage medium, a computer program product, and an electronic device are provided.

[0039] In this document, any number of elements in the drawings is used for illustration rather than limitation, and any naming is used only for distinction and does not have any limiting meaning.

[0040] The principle and spirit of the present invention are described in detail below with reference to several representative embodiments of the present invention. SUMMARY OF THE INVENTION

[0042] The inventors of the present disclosure discovered that the related art lacks a solution for allocating products to be purchased and product promotion resources to the purchaser based on the characteristics of the purchaser and the characteristics of the products, resulting in low accuracy in the allocation of products to be purchased and product promotion resources, and in turn resulting in low resource utilization.

[0043] In view of the above content, the basic idea of ​​the present disclosure is to provide a product data processing method, a product data processing device, a computer-readable storage medium, a computer program product and an electronic device, determine the target cluster of the purchaser according to the historical purchase data and historical promotion data of the purchaser of the product, determine the preference weights of the purchaser for different attribute characteristics of different attributes of the product based on the preference labels of the target cluster, so as to recommend the products to be purchased to the purchaser according to the preference weights, and allocate product promotion resources to the purchaser according to the purchase situation of the purchaser for the purchased products. On the one hand, the present disclosure can portray the purchaser's portrait according to the purchaser's historical purchase data and historical promotion data, so as to allocate products to be purchased to the purchaser according to the purchase interest of the purchaser, and improve the accuracy of the allocation of products to be purchased; on the other hand, the present disclosure allocates product promotion resources to the purchaser according to the purchase situation of the purchaser for the recommended products to be purchased, and can reasonably allocate promotion resources to the purchaser according to the purchase enthusiasm of the purchaser, improve the accuracy of the allocation of promotion resources, and improve the utilization rate of promotion resources.

[0044] After introducing the basic principles of the present invention, various non-limiting embodiments of the present invention are described in detail below.

[0045] Application Scenario Overview

[0046] It should be noted that the following application scenarios are only shown to facilitate understanding of the spirit and principle of the present invention, and the embodiments of the present invention are not limited in this respect. On the contrary, the embodiments of the present invention can be applied to any applicable scenario.

[0047] In an exemplary application scenario, taking the purchaser as a music studio on a music platform and the product as a song, when it is necessary to purchase songs, each music studio can be clustered according to its historical purchase data and historical promotion data, so as to determine the target cluster to which each music studio belongs, and then determine the preference weights of each music studio for different attributes of the song based on the preference labels of the target cluster for different attributes of the song. Based on the preference weights of each music studio for different attributes of the song, the target songs to be purchased recommended for each music studio are determined from the songs to be purchased, and the information of the target songs to be purchased is distributed to each music studio. After receiving the information of the target songs to be purchased, each music studio can conduct purchase negotiations for the target songs to be purchased, etc. At the same time, the purchase and promotion status of the target songs to be purchased by each music studio can be tracked, and promotion resources can be allocated to each music studio based on the purchase status and promotion status.

[0048] Exemplary System Architecture

[0049] First, refer to Figure 1 The system architecture of an exemplary application environment of the present disclosure is described.

[0050] like Figure 1 As shown, the system architecture 100 may include a terminal device 110 and a server 120. The terminal device 110 may be a terminal device such as a smart phone, a tablet computer, a desktop computer, a laptop computer, a smart wearable device, etc. The server 120 generally refers to a background system that provides services related to the product data processing method in this exemplary embodiment, and may be a server or a cluster formed by multiple servers. The terminal 110 and the server 120 may be connected via a wired or wireless communication link to perform data exchange.

[0051] In an exemplary embodiment, the above-mentioned product data processing method can be executed by the terminal device 110. Accordingly, the product data processing device can be set in the terminal device 110 to realize the corresponding module functions. For example, the historical purchase data and historical promotion data of the first purchaser of the product are processed in the terminal device 110 to obtain the preference weights of the first purchaser for different attribute characteristics of different attributes of the product, and then the target product to be purchased recommended for the first purchaser is determined based on the preference weights, so as to recommend the target product to be purchased to the first purchaser. After the recommendation is completed, the terminal device 110 can also continue to obtain the purchase situation of the first purchaser for the target product to be purchased, and allocate product promotion resources to the first purchaser according to the purchase situation.

[0052] In an exemplary embodiment, the above-mentioned product data processing method can be executed by the server 120. Accordingly, the product data processing device can be set in the server 120 to realize the corresponding module functions. For example, the historical purchase data and historical promotion data of the first purchaser of the product are processed in the server 120 to obtain the preference weights of the first purchaser for different attribute characteristics of different attributes of the product, and then the target product to be purchased recommended for the first purchaser is determined according to the preference weights, so as to recommend the target product to be purchased to the first purchaser. After the recommendation is completed, the server 120 can also continue to obtain the purchase situation of the first purchaser for the target product to be purchased, and allocate product promotion resources to the first purchaser according to the purchase situation.

[0053] It should be understood that Figure 1 The number of terminal devices and servers in the example is only illustrative. Any number of terminal devices and servers may be provided as required. For example, the server 120 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms.

[0054] It is easy for those skilled in the art to understand that the above application scenarios are only used as examples and are not limited to the present exemplary embodiment.

[0055] Exemplary Methods

[0056] Figure 2 A flowchart showing a method for processing product data in an exemplary embodiment of the present disclosure is shown. Figure 2 , the method comprising:

[0057] Step S210, determining a target cluster to which a first purchaser belongs based on historical purchase data and historical promotion data of the first purchaser of the product;

[0058] Step S220, determining the preference weights of the first purchaser for different attribute features of different attributes of the product based on the preference labels of the target cluster for different attributes of the product;

[0059] Step S230, determining the purchase interest value of the first purchaser for the product to be purchased according to the preference weights of the first purchaser for different attribute characteristics of different attributes of the product and the target attribute characteristics of different attributes of the product to be purchased;

[0060] Step S240, based on the purchase interest value, determining a target product to be purchased corresponding to the first purchaser from the products to be purchased, and recommending the target product to be purchased to the first purchaser;

[0061] Step S250: determining product promotion resources to be allocated to the first purchaser according to the purchase situation of the target product to be purchased by the first purchaser.

[0062] Next, the specific implementation method of "step S210, determining the target cluster to which the first purchaser belongs based on the historical purchase data and historical promotion data of the first purchaser of the product" is described in detail.

[0063] In an exemplary embodiment, the purchaser in the present disclosure can be understood as the party that purchases the product. For example, in a music platform, songs can be purchased through various music studios, and the music studio is the purchaser and the song is the product. Each song has a copyright, and the process of purchasing a song can be understood as the process of negotiating with the copyright owner of the song and purchasing the copyright of the song.

[0064] For example, the process of purchasing songs by a music studio can be divided into three stages: before signing, during signing, and after signing. In the pre-signing stage, the music studio determines which songs need to be signed, and obtains the songs to be signed (i.e., songs to be purchased); in the signing stage, the music studio negotiates with the copyright owner of the songs to be signed based on the information of the songs to be signed. After the negotiation is successful, the songs can be signed (i.e., copyright purchase contracts are signed, etc.). After the signing is successful, it enters the post-signing stage.

[0065] In the present disclosure, before signing a contract, the songs to be signed can be recommended to the music studios by portraying the portraits of different music studios. For example, the music studios can be clustered, and the target cluster of the music studios can be determined based on the clustering results. The music studios in each cluster have different preference labels, and different preference labels represent the preference weights of the music studios for songs with different attributes. Determining the preference weights of the music studios by clustering can smooth out the influence of the personal preferences of different staff members in the studio on the overall preferences of the music studio, improve the accuracy of the portrait portrayal of the music studio, and thus help improve the accuracy of the recommended songs to be signed.

[0066] Of course, the purchaser in the present disclosure can be any other department or unit that has the responsibility to purchase products, and the products can also be any resources, such as songs, audio books, videos, clothes, etc. For example, in a shopping platform, the purchaser can be the various purchasing departments of the shopping platform, and the products can be the goods in the shopping platform.

[0067] For example, Figure 3 A schematic diagram of a method for determining a target cluster in an exemplary embodiment of the present disclosure is shown. Figure 3 , the method may include steps S310 to S320.

[0068] in:

[0069] In step S310, the first purchasers of the product are clustered according to their historical purchase data and historical promotion data.

[0070] In an exemplary implementation, historical purchase data includes attribute information of historically purchased products. For example, taking songs as an example, historical purchase data includes data such as the style, theme, and type of singers of songs that have been signed by music studios in the past. Historical promotion data may include attribute information of historically promoted products. For example, taking songs as an example, historical promotion data includes data such as the style, theme, and type of singers of songs that have been historically promoted. It may also include data such as the style, theme, and type of singers of songs that have been successfully promoted in the past.

[0071] For example, Figure 4 A flow chart of a method for clustering purchasers in an exemplary embodiment of the present disclosure is shown. Figure 4 , the method may include steps S410 to S440.

[0072] in:

[0073] In step S410, a first purchasing feature of each first purchaser is obtained based on the first historical purchasing data of each first purchaser of the product.

[0074] In an exemplary embodiment, a product may have multiple purchasers, for example, multiple music studios may purchase songs, thereby improving song purchasing efficiency.

[0075] In an exemplary embodiment, the first historical purchase data may include purchase data of the first historical period. The first historical purchase data may include the full amount of historical purchase data of the first purchaser, that is, data of all purchased products of the first purchaser. In other words, the first historical period may include the period between the first purchaser's first purchase and the most recent purchase before the clustering moment. Of course, the first historical period may also include the period corresponding to the most recent first historical duration, such as the most recent three months.

[0076] For example, the data of the preset attributes in the first historical purchase data of the first purchaser can be used as the first purchase feature of the first purchaser. For any product, it can include multiple attributes, and the preset attributes that can represent the characteristics of the product can be determined from the multiple attributes. The preset attributes can be customized according to needs or experience, or all descriptive attributes of the product can be used as preset attributes. Each preset attribute has a corresponding attribute feature, and the attribute feature of each preset attribute can include one or more, which are related to the characteristics of the attribute itself. For example, the gender attribute includes two attribute features, male and female, and the style attribute of the song can include two attribute features, classical and popular. In other words, the first purchase feature includes the attribute features corresponding to the preset attributes of the historical purchase products of the first purchaser.

[0077] For example, if the product is a song and the purchaser is a music studio, the attributes of the song may include the style, theme, singer, singer gender, singer type, song emotion type, etc. The style, theme, singer type, and song emotion type of the songs purchased by the music studio may be obtained and used as the first purchase feature of the first purchaser.

[0078] In step S420, statistical analysis is performed on the second historical purchase data of each first purchaser of the product, and the purchase preference characteristics of each first purchaser are obtained according to the statistical analysis results.

[0079] In an exemplary embodiment, the purchasing preference feature is used to indicate the purchasing interest of the first purchaser in different products, and the historical duration of the second historical purchasing data is shorter than the historical duration of the first historical purchasing data.

[0080] For example, compared with the first historical purchase data, the second historical purchase data may be data closer to the clustering time, which can better reflect the purchase preferences of the first purchaser in the recent period. For example, the first historical data is information about products purchased in the last three months, and the second historical purchase data may be information about products purchased in the last month.

[0081] The second historical purchase data of the first purchaser can be statistically analyzed, such as counting the number of products with various attribute characteristics among the products purchased in the second historical purchase data. Taking songs as an example, the number of songs of different styles, the number of songs of different themes, the number of songs of different singer types, and the number of songs of different emotional types purchased in the past month can be counted, and the attribute feature with the largest number in each attribute is used as the purchase preference feature. For example, if the most purchased songs are songs of style A, theme B, singer type C, and emotional type D, then the purchase preference feature is ABCD; if the most purchased songs are songs of song A1, theme B1, singer type C1, and emotional type D1, then the purchase preference feature is A1B1C1D1.

[0082] The purchasing preference characteristics may also be obtained according to the proportion of different attribute characteristics of the preset attributes. The purchasing interest of the purchaser in different products may also be reflected through other statistical results of the second historical purchasing data, which is not particularly limited in this exemplary embodiment.

[0083] In step S430, the promotion preference characteristics of each first purchaser are obtained based on the historical promotion data of each first purchaser of the product.

[0084] In an exemplary embodiment, the promotion preference feature is used to indicate the first purchaser's interest in promotion of different products.

[0085] For example, the promotion preference characteristics can be obtained based on the information of the products promoted by the first purchaser, or based on the information of the products successfully promoted by the first purchaser. For example, the promotion preference characteristics of the first purchaser for songs can be obtained based on the statistical analysis results of the genre, theme, singer type, emotional type and promotion results of the songs promoted by the first purchaser. For example, the promotion preference characteristics can include the genre of the songs most promoted by the first purchaser, the theme of the songs most promoted, the type of singers most promoted, the emotional type most promoted, the genre of the songs successfully promoted, the theme of the songs successfully promoted, etc.

[0086] In step S440, the first purchasers are clustered according to the first purchase feature, the first weight corresponding to the first purchase feature, the purchase preference feature, the second weight corresponding to the purchase preference feature, the promotion preference feature, and the third weight corresponding to the promotion preference feature.

[0087] For example, weights can be configured in advance for different types of features, such as configuring a first weight for the first purchasing feature, a second weight for the purchasing preference feature, and a third weight for the promotion preference feature. The size of the weight can be determined based on the importance of the feature's impact on the preference. The importance of the feature's impact on the preference can be determined based on experience. For example, if the purchaser is willing to promote a certain song, it means that the purchaser is very interested in the song, so the third weight is the largest. Since the purchasing preference feature can better reflect the purchaser's purchasing interest in the recent period than the first purchasing feature, the second weight is second and the first weight is the smallest.

[0088] The first purchase feature, the purchase preference feature, and the promotion preference feature can be weighted and fused by the first weight, the second weight, and the third weight, and the target purchase feature of the purchaser can be obtained according to the weighted fusion result, and the first purchaser can be clustered according to the target purchase feature. For example, clustering can be performed by the following formula (1):

[0089]

[0090] In formula (1), Ci represents the set of buyers of the ith cluster, x represents the buyer feature vector, μ i is the center of the ith cluster.

[0091] In an exemplary implementation, the above formula (1) may be used based on a K-means clustering algorithm or a hierarchical clustering algorithm. The specific processes of the K-means clustering algorithm and the hierarchical clustering algorithm may refer to the prior art and will not be described in detail herein.

[0092] Through the above-mentioned steps S410 to S430, purchasers can be clustered according to characteristics of multiple dimensions. For example, the first purchasing feature can represent the long-term purchasing interest of the purchaser, the second purchasing feature can represent the recent purchasing interest of the purchaser, and the promotion preference feature can represent the key purchasing interest of the first purchaser, thereby mining the purchasing preferences of the purchasers based on data of different dimensions to improve the accuracy and reliability of clustering.

[0093] Next, in step S320, the target cluster to which the first purchaser belongs is obtained according to the clustering result.

[0094] After clustering through the above steps S410 to S430, a clustering result can be obtained. According to the first purchaser in each cluster in the clustering result, the target cluster to which each first purchaser belongs is obtained. For example, if the first purchaser 1 and the first purchaser 2 belong to cluster 2, then the target clusters to which the first purchaser and the second purchaser belong are both cluster 2.

[0095] The specific implementation method of "step S220, determining the preference weights of the first purchaser for different attribute features of different attributes of the product based on the preference labels of the target cluster for different attributes of the product" is described in detail below.

[0096] In an exemplary embodiment, determining the preference labels of the target clustering cluster for different attributes of the product includes: obtaining the preference labels of the target clustering cluster for different attributes of the product according to the attribute characteristics of the cluster center of the target clustering cluster in different attributes of the product.

[0097] Taking the product as a song as an example, we can obtain the preference labels of the target clustering cluster for different attributes of the song based on the attribute characteristics of the cluster center of the target clustering cluster in the preset attributes of the song. For example, if the style of the song corresponding to a certain clustering center is A, the theme is B1, the singer type is C2, and the emotional type is D1, then the preference label of the song for the target clustering cluster to which the clustering center belongs is style A, theme B1, singer type C2, and emotional type D1.

[0098] Exemplarily, an exemplary implementation of step S220 may include: for each attribute feature of each attribute, calculating the degree of match between the attribute feature and the first purchaser's preference label for the attribute, and obtaining the first purchaser's preference weight for the attribute feature of the attribute of the product based on the degree of match.

[0099] As mentioned above, the attributes of a product refer to the characteristics that can be described of the product, and the attribute characteristics of an attribute refer to the attribute values ​​included in the attribute. For example, for a song, its attributes include style, theme, singer type, and emotional type. For example, the styles of all existing songs can be divided into three categories: style A, style A1, and style A2. The attribute characteristics of the style attribute include A, A1, and A2. For the theme, all existing song themes can be divided into two categories: theme B and theme B1. The attribute characteristics of the theme attribute include B and B1. Other attributes are similar and will not be repeated here.

[0100] For example, for any attribute feature of the genre attribute, the matching degree between the attribute feature and the first purchaser's preference label for the genre attribute can be calculated, and the matching degree can be used as the first purchaser's preference weight for the attribute feature. For example, the attribute features of the genre include A, A1, and A2, and the genre labels of a certain music studio are A genre and A1 genre. For the genre attribute feature A, the matching degree between the A genre in the genre label and the genre attribute feature A is 1, and the first purchaser's preference weight for the genre attribute feature A is 1; for the genre attribute feature A1, the matching degree between the A1 genre in the genre label and the genre attribute feature A1 is 1, and the first purchaser's preference weight for the genre attribute feature A1 is 1; for the genre attribute feature A2, the matching degree between the A genre and the A1 genre in the genre label and the genre attribute feature A2 is 0, and the first purchaser's preference weight for the genre attribute feature A2 is 0. The first purchaser's preference weights for different attribute features of other attributes can also be determined in a similar manner.

[0101] In an exemplary implementation, the attribute features corresponding to different attributes may also be quantified, and then the matching degree is calculated based on the quantification result. The quantization method may be freely selected, and this exemplary implementation does not impose any special limitation on this.

[0102] In another exemplary embodiment, a first text vector corresponding to the preference tag and a second text vector corresponding to the attribute feature may be determined by a large language model, and then the similarity between the two text vectors may be calculated and used as the preference weight.

[0103] Below, the specific implementation method of "step S230, determining the purchasing interest value of the first purchaser for the product to be purchased based on the preference weights of the first purchaser for different attribute characteristics of different attributes of the product and the target attribute characteristics of different attributes of the product to be purchased" is described in detail.

[0104] Exemplary, combined Figure 5 The specific implementation of step S230 is described. Figure 5 A flowchart of a method for determining a purchase interest value in an exemplary embodiment of the present disclosure is shown. Figure 5 , the method may include steps S510 to S530. Wherein:

[0105] In step S510, the target preference weight of the first purchaser for the target attribute feature of the product to be purchased is determined from the preference weights of the first purchaser for different attribute features of different attributes of the product.

[0106] For example, for any product, its attribute characteristics are determined. For example, for song A, it is determined which one or several of the A style, A1 style, and A2 style it belongs to. The attribute characteristics of the product to be purchased can be collectively referred to as target attribute characteristics. For example, the genre attribute characteristics of song 1 are A style and A1 style, then the target attribute characteristics of song 1 for the attribute of genre include A style and A1 style. From the first purchaser's preference weights for different attribute characteristics of the song, the first purchaser's preference weights for the A style and A1 style of the song are determined and used as the target preference weight for the A style of the song and the target preference weight for the A style of the song. For each target attribute characteristic of the song, a similar method can be used to determine the target preference weight for the target attribute characteristic from the first purchaser's preference weights for different attribute characteristics of different attributes of the product.

[0107] In step S520, a first product of each target attribute feature of the product to be purchased and the target preference weight of the target attribute feature is calculated.

[0108] For example, after the target attribute feature is quantified, the first product of the quantization result of the target attribute feature and the target preference weight of the target attribute feature is calculated.

[0109] In step S530, the interest value of the first purchaser in the product to be purchased is determined according to the sum of the first products.

[0110] Exemplarily, the sum of the first product of each target attribute feature and the target preference weight of the target attribute feature may be calculated, and the sum may be used as the interest value of the first purchaser in the product to be purchased.

[0111] For example, the purchaser's interest value in the purchased product can be calculated by the following formula (2):

[0112]

[0113] In formula (2), Score(s) is the purchaser's interest in the purchased product, and f j (S) is the performance of the product to be purchased on the jth feature dimension (i.e., the target attribute feature of the jth attribute of the product to be purchased), ω j is the preference weight of the first purchaser for the target attribute feature of the jth attribute.

[0114] Through the above steps S510 to S530, the first purchaser's preference for the product can be measured from multiple dimensions based on the first purchaser's preference for the attribute characteristics of different attributes of the product, thereby improving the accuracy and reliability of determining the interest value.

[0115] The specific implementation method of "step S240, determining the target product to be purchased corresponding to the first purchaser from the products to be purchased based on the purchase interest value, and recommending the target product to be purchased to the first purchaser" is described in detail below.

[0116] Exemplarily, a specific implementation of step S240 may include: sorting the products to be purchased in descending order of the purchasing interest values ​​to obtain a sorting result; and determining the first N products to be purchased in the sorting result as the target products to be purchased corresponding to the first purchaser.

[0117] For example, N products to be purchased that the first purchaser is most interested in may be selected and used as target products to be purchased recommended to the first purchaser, where N is an integer greater than 0 and less than or equal to the number of products to be purchased.

[0118] The specific implementation method of "step S250, determining the product promotion resources to be allocated to the first purchaser according to the purchase situation of the target product to be purchased by the first purchaser" is described in detail below.

[0119] Taking the purchaser as a music studio and the product as a song as an example, in the present disclosure, before the song is signed, personalized recommendations for songs to be signed can be made for different music studios based on the preferences of the music studios, and each music studio can screen the recommended songs to be signed, so as to negotiate the signing of songs to be signed that meet its requirements. During the song signing process, the music studio can negotiate with the copyright holder of the song based on information such as the development potential of the song to be signed, and sign a contract for the song to be signed for the song that has been successfully negotiated. After the signing, the promotion of the successfully signed song by the music studio can be tracked, and the virtual score of the music studio can be determined based on the promotion situation, so as to determine the song promotion resources allocated to the music studio based on the virtual score of the music studio.

[0120] Next, combine Figure 6 and Figure 7 The specific implementation of step S250 is described in detail. For example, Figure 6 A flowchart of a method for allocating product promotion resources in an exemplary embodiment of the present disclosure is shown. Figure 6 , the method may include steps S610 to S620. Wherein:

[0121] In step S610, a virtual score of the first purchaser is determined according to the purchase status of the target purchase product by the first purchaser.

[0122] Exemplarily, an implementation of step S610 may include: determining the virtual score of the first purchaser based on one or more of the first quantity of the target product to be purchased successfully purchased by the first purchaser and feedback behavior data of the first purchaser on the purchase result of the target product to be purchased.

[0123] For example, the first quantity of the target products to be purchased successfully purchased by the first purchaser can be used as the first virtual score. During the purchase process, if the first purchaser provides feedback on the purchase results of the target products to be purchased, such as feedback on which target products to be purchased were successfully purchased, which target products to be purchased failed to be purchased, and the reasons for the failure, each piece of purchase result feedback data corresponds to a second virtual score, such as feedback on which target products to be purchased were successfully purchased corresponding to the second virtual score X1, feedback on which target products to be purchased failed to be purchased corresponding to the second virtual score X2, feedback on the reasons for the purchase failure corresponding to the second virtual score X3, etc. The sum of the first virtual score and the second virtual score can be used as the virtual score of the first purchaser.

[0124] For example, if the product to be purchased is a song, the first virtual score can be determined according to the potential value of the song. For example, if a song is successfully signed, the greater the potential value of the song, the greater the first virtual score. The potential value represents the degree to which the song can be accepted by the public. The greater the potential value, the more people will like the song.

[0125] For example, another exemplary implementation of step S610 may be as follows: Figure 7 shown. Figure 7 A flowchart of a method for determining a virtual score of a purchaser in an exemplary embodiment of the present disclosure is shown. Figure 7 , the method may include steps S710 to S720.

[0126] in:

[0127] In step S710, first promotion data of the target product to be purchased successfully purchased by the first purchaser is obtained.

[0128] In an exemplary embodiment, the first promotion data includes one or more of the number of shares and the increased exposure. Of course, the first promotion data may also include other data supporting the promotion of the target product to be purchased, which is not specifically limited in this exemplary embodiment.

[0129] In step S720, a virtual score of the first purchaser is determined according to the purchase status of the target product to be purchased by the first purchaser and the first promotion data.

[0130] In an exemplary implementation, the third virtual score may be determined based on the first promotion behavior data of the target product to be purchased successfully purchased by the first purchaser. For example, taking the song of the target product as an example, because the promotion behavior of the first purchaser leads to an increase in the number of plays of the song, a third virtual score Y4 is corresponding, and the first purchaser shares the song to promote the song, and each share corresponds to a third virtual score Y5.

[0131] Exemplarily, an exemplary implementation of step S720 may include: the virtual score of the first purchaser may be determined based on one or more of the first virtual score and the second virtual score, and the third virtual score. For example, the virtual score of the first purchaser may be obtained based on the sum of the first virtual score, the second virtual score and the third virtual score.

[0132] For example, the virtual score of the purchaser can be dynamically determined based on the purchaser's contribution to the product at each stage of the product. Taking the product as a song, for example, the virtual score of the music studio can be determined based on the music studio's contribution to the song at different growth stages of the song. For example, in the pre-signing stage of a song, the virtual score of the music studio in the pre-signing stage can be determined based on the music studio's active selection of songs to be signed. For example, the virtual score of the music studio increases with each active selection; in the signing stage, the virtual score of the music studio can be adjusted based on the number of songs successfully signed by the music studio and the potential value of the successfully signed songs; in the promotion stage, the virtual score of the music studio can be adjusted based on the music studio's promotion of the successfully signed songs, thereby dynamically determining the virtual score of the music studio based on the growth of the song.

[0133] Continue to refer Figure 6 In step S620, product promotion resources allocated to the first purchaser are determined based on the virtual score of the first purchaser.

[0134] As mentioned above, there are multiple first purchasers. Based on this, an exemplary implementation of step S620 may include: determining allocation priorities of multiple first purchasers according to the virtual score of the first purchaser, and allocating product promotion resources to the first purchaser based on the allocation priority; and / or in response to the first purchaser's first consumption request for the virtual score, determining the promotion traffic matching the virtual score in the first consumption request, and allocating the promotion traffic to the first purchaser; and / or in response to the first purchaser's second consumption request for the virtual score, determining the promotion tool corresponding to the second consumption request, and allocating the promotion tool to the first purchaser.

[0135] For example, the priority of the first purchaser can be determined according to the virtual score. For example, the priority of the first purchaser with a high virtual score is higher than that of the first purchaser with a low virtual score. In this way, when allocating promotion resources, if the promotion resources are limited, the promotion resources can be allocated to the first purchaser with a high priority first. Continuing with the example of the product being the above-mentioned song, when the target clusters of multiple music studios are the same, the target songs to be purchased recommended to multiple music studios may be the same. At this time, the target songs to be purchased can be screened a second time, and the popular songs or songs with high potential values ​​among the target songs to be purchased can be recommended to the music studios with high priority among multiple music studios of the same category, and the remaining songs can be recommended to the music studios with low priority.

[0136] For example, a mapping relationship between virtual scores and promotion traffic can be preset, and the promotion traffic corresponding to different virtual scores can be determined through the mapping relationship. Then, the target promotion traffic corresponding to the virtual score in the first consumption request of the first purchaser is determined through the mapping relationship, and the target promotion traffic is allocated to the first purchaser. For example, a music studio can obtain more promotion traffic support by consuming a certain amount of virtual scores, such as increasing the exposure of songs purchased by the music studio.

[0137] Exemplarily, virtual scores corresponding to different specific promotional tools may be preset, and the first purchaser may obtain the specific promotional tool he wants by consuming the virtual scores. For example, in response to the first purchaser's selection operation of the target promotional tool in the promotional tool selection page, the target virtual score corresponding to the target promotional tool is determined, and then the target promotional tool is allocated to the first purchaser after the first purchaser's virtual score is subtracted from the target virtual score. Different first purchasers may use the same promotional tool for product promotion.

[0138] Taking the example of a song being the product and a music studio being the purchaser, the music studio can redeem certain rights and interests through virtual points, such as obtaining priority selection rights for popular songs or potential songs by consuming virtual points, or obtaining more traffic promotion support by consuming virtual points, or obtaining customized promotional content, exclusive operation support and other promotional tools by consuming virtual points.

[0139] For example, Figure 8 A flowchart showing another method for allocating product promotion resources in an exemplary embodiment of the present disclosure is shown. Figure 8 , the method may include steps S810 to S830. Wherein:

[0140] In step S810, the explosive potential value of the successfully purchased product is predicted based on the user behavior data of the successfully purchased product.

[0141] For example, the explosive potential value of a product can be predicted based on the user's browsing, clicking, purchasing and other behavioral data of the product. Continuing with the example of songs, the explosive potential value of a song can be predicted based on the number of views, clicks, and purchases of the song within a preset time. The greater the number of views, clicks, and purchases within the preset time, the higher the explosive potential value of the song. A burst potential value prediction model can be trained, and the explosive potential value of a product can be predicted by combining the burst potential value prediction model with the current user behavior data of the product.

[0142] In step S820, the next state of the current state of the successfully purchased product is determined according to the explosion potential value of the successfully purchased product.

[0143] For example, a product's complete life cycle may include multiple states, such as cold start, growth period, outbreak period, maturity period, and decline period. In other words, a product's complete life cycle may need to go through at least two of the cold start, growth period, outbreak period, maturity period, and decline period.

[0144] For example, the burst potential values ​​corresponding to all the next possible states under the current state can be preset. For example, in the cold start phase, the burst potential values ​​between 100-200 will enter the growth phase, and the burst potential values ​​above 500 will enter the burst phase, etc. In this way, under the current state, the burst potential value of the successfully purchased product can be predicted based on the user behavior data, and then the next state of the product under the current state can be determined based on the burst potential value.

[0145] In step S830, based on the promotion strategy corresponding to the next state, promotion resources are allocated to the successfully purchased products in the current state.

[0146] For example, different promotion strategies correspond to different states, and different promotion strategies correspond to different investment intensities and types of promotion resources. Promotion strategies corresponding to different states can be pre-configured. For example, in the cold start phase, the promotion strategy is to invest more exposure resources to increase the initial playback volume; in the growth phase, the promotion strategy is to increase social media promotion resources to further increase the popularity of the song; in the outbreak phase, the promotion strategy is to allocate high-exposure resources such as recommendation positions and homepage displays to maintain traffic peaks; in the mature phase, the promotion strategy is to reduce promotion resources to ensure the sustainability of the promotion; in the decline phase, the promotion strategy is to extend the life cycle of the song through precise recommendations to specific groups of people.

[0147] After predicting the next state of the current state, promotion resources can be allocated to the product in the current state according to the promotion strategy of the next state, so as to dynamically adjust the promotion resources of the product according to the growth status of the product.

[0148] Through the above-mentioned steps S810 to S830, promotional resources can be dynamically matched according to the growth status and potential value of the product. Songs with different growth statuses correspond to different promotional resources, ensuring the rationality of promotional resource allocation and improving the utilization efficiency of promotional resources.

[0149] In the present disclosure, by identifying the preferences of the purchaser, personalized purchase product recommendations are made to the purchaser, the accuracy of purchase product allocation is improved, and the probability of successful purchase of purchase products is assisted in increasing; by dynamically adjusting the purchaser's virtual score according to the purchaser's contribution to the product at each growth stage of the product, and allocating promotion resources to the purchaser through the virtual score, the purchaser's purchasing enthusiasm and the rationality of promotion resource allocation can be improved; by predicting the growth status of the product and allocating corresponding promotion resources to the product in advance, it can assist in rapid promotion of the product and improve the utilization efficiency of promotion resources.

[0150] In addition, it should be noted that the above-mentioned figures are only schematic illustrations of the processes included in the method according to an exemplary embodiment of the present invention, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0151] Exemplary Devices

[0152] The exemplary embodiment of the present disclosure also provides a product data processing device. Fig. 9As shown, the product data processing device 900 may include the following program modules: a cluster determination module 910, configured to determine the target cluster to which the first purchaser belongs based on the historical purchase data and historical promotion data of the first purchaser of the product; a preference weight determination module 920, configured to determine the preference weights of the first purchaser for different attribute characteristics of different attributes of the product based on the preference labels of the target cluster for different attributes of the product; a purchase interest value determination module 930, configured to determine the purchase interest value of the first purchaser for the product to be purchased based on the preference weights of the first purchaser for different attribute characteristics of different attributes of the product and the target attribute characteristics of different attributes of the product to be purchased; a recommendation module 940, configured to determine the target product to be purchased corresponding to the first purchaser from the products to be purchased based on the purchase interest value, and recommend the target product to be purchased to the first purchaser; a promotion resource allocation module 950, configured to determine the product promotion resources allocated to the first purchaser based on the purchase situation of the first purchaser for the target product to be purchased.

[0153] In an optional embodiment, based on the aforementioned embodiment, the cluster determination module 910 may be specifically configured as follows: clustering the first purchasers of the product according to their historical purchase data and historical promotion data; and obtaining the target cluster to which the first purchasers belong based on the clustering results.

[0154] In an optional embodiment, based on the aforementioned embodiment, clustering the first purchasers according to the historical purchase data and historical promotion data of each first purchaser of the product includes: obtaining a first purchase feature of each first purchaser according to the first historical purchase data of each first purchaser of the product, the first purchase feature including attribute features of different attributes of historically purchased products; performing statistical analysis on the second historical purchase data of each first purchaser of the product, and obtaining a purchase preference feature of each first purchaser according to the statistical analysis result, the purchase preference feature being used to indicate the first purchaser's purchase interest in different products, the historical duration of the second historical purchase data being shorter than the historical duration of the first historical purchase data; obtaining a promotion preference feature of each first purchaser according to the historical promotion data of each first purchaser of the product, the promotion preference feature being used to indicate the first purchaser's promotion interest in different products; clustering the first purchasers according to the first purchase feature, a first weight corresponding to the first purchase feature, the purchase preference feature, a second weight corresponding to the purchase preference feature, the promotion preference feature, and a third weight corresponding to the promotion preference feature.

[0155] In an optional embodiment, based on the aforementioned embodiment, determining the preference labels of the target clustering cluster for different attributes of the product includes: obtaining the preference labels of the target clustering cluster for different attributes of the product according to the attribute characteristics of the cluster center of the target clustering cluster in the different attributes of the product.

[0156] In an optional embodiment, based on the aforementioned embodiment, the preference weight determination module 920 may be specifically configured as follows: for each attribute feature of each attribute, calculating the degree of match between the attribute feature and the first purchaser's preference label for the attribute, and obtaining the first purchaser's preference weight for the attribute feature of the attribute of the product based on the degree of match.

[0157] In an exemplary embodiment, based on the aforementioned embodiment, the purchasing interest value determination module 930 can be specifically configured as: determining the target preference weight of the first purchaser for the target attribute characteristics of the product to be purchased from the preference weights of the first purchaser for different attribute characteristics of different attributes of the product; calculating the first product of each target attribute characteristic of the product to be purchased and the target preference weight of the target attribute characteristic; and determining the interest value of the first purchaser for the product to be purchased based on the sum of the first products.

[0158] In an exemplary embodiment, based on the aforementioned embodiment, the recommendation module 940 may be specifically configured as follows: sorting the products to be purchased in descending order of the purchasing interest values ​​to obtain a sorting result; and determining the first N products to be purchased in the sorting result as the target products to be purchased corresponding to the first purchaser.

[0159] In an exemplary embodiment, based on the aforementioned embodiment, the promotion resource allocation module 950 may be specifically configured as follows: determining the virtual score of the first purchaser according to the purchase situation of the target purchase product by the first purchaser; and determining the product promotion resources allocated to the first purchaser based on the virtual score of the first purchaser.

[0160] In an exemplary embodiment, based on the aforementioned embodiment, determining the virtual score of the first purchaser according to the purchasing situation of the target product to be purchased by the first purchaser includes: determining the virtual score of the first purchaser according to one or more of the first quantity of the target product to be purchased successfully purchased by the first purchaser and the feedback behavior data of the first purchaser on the purchasing results of the target product to be purchased.

[0161] In an exemplary embodiment, based on the aforementioned embodiment, determining the virtual score of the first purchaser according to the purchase situation of the target product to be purchased by the first purchaser includes: obtaining first promotional data of the target product to be purchased successfully purchased by the first purchaser, the first promotional data including one or more of the number of shares and increased exposure; determining the virtual score of the first purchaser according to the purchase situation of the target product to be purchased by the first purchaser and the first promotional data.

[0162] In an exemplary embodiment, based on the aforementioned embodiment, the first purchaser has multiple first purchasers, and the product promotion resources allocated to the first purchaser based on the virtual score of the first purchaser includes: determining the allocation priorities of multiple first purchasers according to the virtual score of the first purchaser, and allocating product promotion resources to the first purchaser based on the allocation priorities; and / or in response to a first consumption request of the first purchaser for the virtual score, determining the promotion traffic matching the virtual score in the first consumption request, and allocating the promotion traffic to the first purchaser; and / or in response to a second consumption request of the first purchaser for the virtual score, determining the promotion tool corresponding to the second consumption request, and allocating the promotion tool to the first purchaser.

[0163] In an exemplary embodiment, based on the aforementioned embodiment, the device further includes a state prediction module, which may be specifically configured to: predict the explosive potential value of the successfully purchased product based on user behavior data of the successfully purchased product; determine the next state of the current state of the successfully purchased product based on the explosive potential value of the successfully purchased product; and allocate promotion resources to the successfully purchased product in the current state based on the promotion strategy corresponding to the next state.

[0164] The specific details of each part of the above-mentioned device have been described in detail in the implementation of the corresponding method part above. The undisclosed details can be found in the implementation of the method part above, and will not be repeated here.

[0165] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the exemplary embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0166] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0167] Exemplary Storage Media

[0168] The storage medium according to the exemplary embodiment of the present invention is described below.

[0169] In this exemplary embodiment, the above method can be implemented by a program product, such as a portable compact disk read-only memory (CD-ROM) and including program code, and can be run on a device, such as a personal computer. However, the program product of the present invention is not limited to this. In this document, a readable storage medium can be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, an apparatus or a device.

[0170] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0171] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0172] The program code contained on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RE, etc., or any suitable combination of the foregoing.

[0173] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user computing device, partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0174] Exemplary computer program products

[0175] The exemplary embodiments of the present disclosure also provide a computer program product, which includes a computer program, and when the computer program is executed by a processor, the product data processing method described above is implemented.

[0176] In one embodiment, the computer program product may be a tangible product containing a computer program, such as a computer-readable storage medium storing a computer program. The readable storage medium may be a storage medium based on electrical, magnetic, optical, electromagnetic, infrared, or other signals, including but not limited to: random access memory (RAM), read-only memory (ROM), magnetic tape, floppy disk, flash memory (Flash), mechanical hard disk (HDD), solid-state drive (SSD), and the like. Exemplarily, the computer program product may be implemented as a non-volatile storage medium storing a computer program, such as a read-only memory, a NAND flash memory, and the like.

[0177] In one embodiment, the computer program product may be an intangible product including a computer program. Exemplarily, the computer program product may be implemented as a virtual digital product, such as a digital file storing an executable file, an installation package, etc. of the computer program.

[0178] The code of the computer program can be written in one or more programming languages. Programming languages ​​such as C language, Java, C++, Python, etc. The program code can be executed entirely on the user computing device, or partially on the user computing device, or as a separate software package, or partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, such as a local area network (LAN), a wide area network (WAN), etc., or can be connected to an external computing device (e.g., an Internet connection provided by an operator).

[0179] The computer program can be carried or transmitted through electrical, magnetic, optical, electromagnetic, infrared and other signals. The electronic device can convert the signal carrying the computer program into a digital signal, and then run the computer program. When the computer program runs on the electronic device, its code is used to make the electronic device execute (more specifically, the processor of the electronic device can execute) the method steps of various exemplary embodiments of the present disclosure, such as the above-mentioned product data processing method, which includes the following steps: according to the historical purchase data and historical promotion data of the first purchaser of the product, determine the target cluster to which the first purchaser belongs; based on the preference labels of the target cluster for different attributes of the product, determine the preference weights of the first purchaser for different attribute characteristics of different attributes of the product; according to the preference weights of the first purchaser for different attribute characteristics of different attributes of the product and the target attribute characteristics of different attributes of the product to be purchased, determine the purchase interest value of the first purchaser to be purchased; based on the purchase interest value, determine the target product to be purchased corresponding to the first purchaser from the products to be purchased, and recommend the target product to be purchased to the first purchaser; according to the purchase situation of the first purchaser for the target product to be purchased, determine the product promotion resources allocated to the first purchaser.

[0180] By executing the above method steps through a computer program, on the one hand, a portrait of the purchaser can be portrayed based on the purchaser's historical purchasing data and historical promotion data, so as to allocate products to the purchaser based on the purchaser's purchasing interests, thereby improving the accuracy of allocation of products to be purchased; on the other hand, product promotion resources can be allocated to the purchaser based on the purchaser's purchasing situation of the recommended products to be purchased, and promotion resources can be reasonably allocated to the purchaser based on the purchaser's purchasing enthusiasm, etc., thereby improving the accuracy of promotion resource allocation and improving the utilization rate of promotion resources.

[0181] Exemplary Electronic Devices

[0182] refer to Fig.10An electronic device of an exemplary embodiment of the present disclosure is described. The electronic device may be the terminal device 110 or the server 120 described above. The electronic device may include a processor and a memory. The memory stores executable instructions of the processor, such as a computer program. The processor executes the method steps of various exemplary embodiments of the present disclosure by executing the executable instructions. In addition, the electronic device may also include a display for displaying a graphical user interface.

[0183] Reference below Fig.10 , the electronic device is exemplarily described in the form of a general-purpose computing device. It should be understood that Fig.10 The electronic device 1000 shown is only an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0184] like Fig.10 As shown, the electronic device 1000 may include: a processor 1010 , a memory 1020 , a bus 1030 , an I / O (input / output) interface 1040 , a network adapter 1050 , and a display 1060 .

[0185] The memory 1020 may include a volatile memory, such as a RAM 1021, a cache unit 1022, and may also include a non-volatile memory, such as a ROM 1023. The memory 1020 may also include one or more program modules 1024, such program modules 1024 include but are not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or a combination thereof may include the implementation of a network environment. For example, the program module 1024 may include each module in the above-mentioned device.

[0186] The processor 1010 may include one or more processing units. For example, the processor 1010 may include an AP (Application Processor), a modem processor, a GPU (Graphics Processing Unit), an ISP (Image Signal Processor), a controller, an encoder, a decoder, a DSP (Digital Signal Processor), a baseband processor and / or an NPU (Neural-Network Processing Unit), etc.

[0187] Processor 1010 can be used to execute executable instructions stored in memory 1020, such as the above-mentioned product data processing method, which includes the following steps: determining the target cluster to which the first purchaser belongs based on the historical purchase data and historical promotion data of the first purchaser of the product; determining the preference weights of the first purchaser for different attribute characteristics of different attributes of the product based on the preference labels of the target cluster for different attributes of the product; determining the purchasing interest value of the first purchaser for the product to be purchased based on the preference weights of the first purchaser for different attribute characteristics of different attributes of the product and the target attribute characteristics of different attributes of the product to be purchased; determining the target product to be purchased corresponding to the first purchaser from the products to be purchased based on the purchasing interest value, and recommending the target product to be purchased to the first purchaser; determining the product promotion resources allocated to the first purchaser based on the purchasing situation of the first purchaser for the target product to be purchased.

[0188] By implementing the above method through a computer program, on the one hand, a portrait of the purchaser can be portrayed based on the purchaser's historical purchasing data and historical promotion data, thereby allocating products to be purchased to the purchaser based on the purchaser's purchasing interests, thereby improving the accuracy of allocation of products to be purchased; on the other hand, product promotion resources can be allocated to the purchaser based on the purchaser's purchasing situation of the recommended products to be purchased, and promotion resources can be reasonably allocated to the purchaser based on the purchaser's purchasing enthusiasm, etc., thereby improving the accuracy of promotion resource allocation and improving the utilization rate of promotion resources.

[0189] The bus 1030 is used to realize the connection between different components of the electronic device 1000, and may include a data bus, an address bus, and a control bus.

[0190] The electronic device 1000 can communicate with one or more external devices 1100 (eg, a keyboard, a mouse, an external controller, etc.) through the I / O interface 1040 .

[0191] The electronic device 1000 can communicate with one or more networks through the network adapter 1050. For example, the network adapter 1050 can provide mobile communication solutions such as 3G / 4G / 5G, or provide wireless communication solutions such as wireless LAN, Bluetooth, near field communication, etc. The network adapter 1050 can communicate with other modules of the electronic device 1000 through the bus 1030.

[0192] The electronic device 1000 may display a graphical user interface through the display 1060 , such as a graphical user interface displaying the above-mentioned recommended target products to be purchased.

[0193] although Fig.10Not shown, other hardware and / or software modules may also be provided in the electronic device 1000, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0194] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present disclosure, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0195] As can be seen from the above, the technical solution of the present disclosure can be implemented as a method, a system, a computer program product, a computer-readable storage medium, an electronic device, etc. Those skilled in the art can understand that various aspects of the present disclosure can be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software, such as being respectively referred to as a "circuit", "module" or "device".

[0196] It should be understood that the present disclosure is not limited to the specific method steps or structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from the scope thereof. Those skilled in the art will easily think of other embodiments based on the specific embodiments provided by the present disclosure. Therefore, the specific embodiments provided by the present disclosure are only exemplary, and the scope and spirit of the present disclosure are indicated by the claims, and any variations, uses or adaptive changes of the present disclosure should be covered, which follow the general principles of the present disclosure and include common knowledge or customary technical means in the technical field that are not disclosed in the present disclosure.

Claims

1. A product data processing method, characterized in that: include: Determine the target cluster to which the first purchaser belongs based on historical purchase data and historical promotion data of the first purchaser of the product; Determining the preference weights of the first purchaser for different attribute features of different attributes of the product based on the preference labels of the target cluster for different attributes of the product; Determining the purchasing interest value of the first purchaser for the product to be purchased according to the preference weights of the first purchaser for different attribute characteristics of different attributes of the product and the target attribute characteristics of different attributes of the product to be purchased; Based on the purchase interest value, determining a target product to be purchased corresponding to the first purchaser from the products to be purchased, and recommending the target product to be purchased to the first purchaser; According to the purchasing situation of the target product to be purchased by the first purchaser, product promotion resources allocated to the first purchaser are determined.

2. The method according to claim 1, characterized in that The determining, based on the historical purchase data and historical promotion data of the first purchaser of the product, the target cluster to which the first purchaser belongs includes: Clustering each first purchaser of the product according to the historical purchase data and historical promotion data of the first purchaser; According to the clustering result, the target cluster to which the first purchaser belongs is obtained.

3. The method according to claim 2, characterized in that The clustering of the first purchasers according to the historical purchase data and historical promotion data of each first purchaser of the product comprises: According to the first historical purchase data of each first purchaser of the product, a first purchase feature of each first purchaser is obtained, wherein the first purchase feature includes attribute features of different attributes of the historically purchased product; Performing statistical analysis on the second historical purchase data of each first purchaser of the product, and obtaining a purchase preference feature of each first purchaser according to the statistical analysis result, wherein the purchase preference feature is used to indicate the purchase interest of the first purchaser in different products, and the historical length of the second historical purchase data is shorter than the historical length of the first historical purchase data; Obtaining promotion preference characteristics of each first purchaser according to historical promotion data of each first purchaser of the product, wherein the promotion preference characteristics are used to indicate the first purchaser's promotion interest in different products; The first purchasers are clustered according to the first purchasing feature, the first weight corresponding to the first purchasing feature, the purchasing preference feature, the second weight corresponding to the purchasing preference feature, the promotion preference feature, and the third weight corresponding to the promotion preference feature.

4. The method according to claim 1, characterized in that: Determining the preference labels of the target cluster for different attributes of the product includes: According to the attribute characteristics of the cluster center of the target cluster in different attributes of the product, the preference labels of the target cluster for different attributes of the product are obtained.

5. The method according to claim 1, characterized in that Determining the preference weights of the first purchaser for the attribute features of the different attributes of the product based on the preference labels of the target cluster for the different attributes of the product includes: For each attribute feature of each attribute, the matching degree between the attribute feature and the first purchaser's preference label for the attribute is calculated, and the first purchaser's preference weight for the attribute feature of the attribute of the product is obtained according to the matching degree.

6. The method according to claim 1, characterized in that Determining the purchasing interest value of the first purchaser for the product to be purchased according to the preference weights of the first purchaser for different attribute characteristics of different attributes of the product and the target attribute characteristics of different attributes of the product to be purchased includes: Determining a target preference weight of a target attribute feature of a product to be purchased by the first purchaser from the preference weights of different attribute features of different attributes of the product by the first purchaser; Calculate a first product of each target attribute feature of the product to be purchased and the target preference weight of the target attribute feature; The interest value of the first purchaser in the product to be purchased is determined according to the sum of the first products.

7. A product data processing device, characterized in that: include: A cluster determination module, configured to determine a target cluster to which a first purchaser belongs based on historical purchase data and historical promotion data of the first purchaser of the product; a preference weight determination module, configured to determine the preference weights of the first purchaser for different attribute features of different attributes of the product based on the preference labels of the target cluster for different attributes of the product; a purchasing interest value determination module, configured to determine the purchasing interest value of the first purchaser for the product to be purchased according to the preference weights of the first purchaser for different attribute characteristics of different attributes of the product and the target attribute characteristics of different attributes of the product to be purchased; a recommendation module configured to determine, based on the purchase interest value, a target product to be purchased corresponding to the first purchaser from the products to be purchased, and recommend the target product to be purchased to the first purchaser; The promotion resource allocation module is configured to determine the product promotion resources allocated to the first purchaser according to the purchase situation of the target product to be purchased by the first purchaser.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, enables the one or more processors to implement the method according to any one of claims 1 to 6.

Images