Commodity and object pushing method, medium, computer equipment and program product

Abstract

The embodiment of the invention discloses a commodity and object pushing method, a medium, computer equipment and a program product. The method comprises the steps that a target area where a target user is located is determined; target commodity features associated with a target area are obtained, the target commodity features are features of commodities on an e-commerce platform, and the target commodity features are matched with regional features of the target area and used for reflecting commodity features preferred by user groups in the target area; determining at least one target commodity on the e-commerce platform based on the target commodity features; and pushing the commodity information of the at least one target commodity to the target user.

Description

Technical Field

[0001] The present application relates to the field of Internet technology, and in particular to a method, medium, computer device and program product for pushing goods and objects. Background Art

[0002] In the related art, the service platform can push the object information of the service objects on the platform to the user. Usually, the object push process is implemented based on the user's historical behavior sequence. However, in some cases, the user may be a new user of the service platform, and his behavior sequence is relatively sparse. When the user's behavior sequence is sparse, it is difficult for the service platform to accurately determine the user's needs and preferences, resulting in the pushed service objects not meeting the user's needs and preferences, and the push accuracy is low. Summary of the invention

[0003] In a first aspect, an embodiment of the present application provides a product push method, the method comprising: determining a target area where a target user is located; obtaining target product characteristics associated with the target area, the target product characteristics being characteristics of products on an e-commerce platform, and the target product characteristics matching the regional characteristics of the target area, for reflecting product characteristics preferred by a user group in the target area; determining at least one target product on the e-commerce platform based on the target product characteristics; and pushing product information of the at least one target product to the target user.

[0004] In a second aspect, an embodiment of the present application provides an object push method, the method comprising: determining a target area where a target user is located; obtaining target object characteristics associated with the target area, the target object characteristics being characteristics of a service object provided by a service platform, and the target object characteristics matching the regional characteristics of the target area, for reflecting object characteristics preferred by a user group in the target area; determining at least one target service object on the service platform based on the target object characteristics; and pushing object information of the at least one target service object to the target user.

[0005] In a third aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any embodiment of the present application.

[0006] In a fourth aspect, an embodiment of the present application provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in any embodiment of the present application when executing the program.

[0007] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the method described in any embodiment of the present application.

[0008] Considering that the object characteristics of the service objects of user needs and preferences often have a certain correlation with the regional characteristics of the user's area, the embodiment of the present application obtains the target object characteristics associated with the target area where the user is located, and determines and pushes the target service object based on the target object characteristics. When the user behavior sequence is sparse, the above method can push the target service object whose object characteristics match the regional characteristics of the user's area, so that the object characteristics of the pushed target service object are more in line with the user's needs and preferences, and improves the push accuracy when the user behavior sequence is sparse.

[0009] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The drawings herein are incorporated into the specification and constitute a part of the present application. These drawings illustrate embodiments consistent with the present application and are used together with the specification to illustrate the technical solutions of the present application.

[0011] Figure 1 It is a schematic diagram of an application scenario of an embodiment of the present application.

[0012] Figure 2 It is a flowchart of the object push method of an embodiment of the present application.

[0013] Figure 3 It is a schematic diagram of regional features output by a large language model according to an embodiment of the present application.

[0014] Figure 4 It is a schematic diagram of object features matched with regional features output by a large language model according to an embodiment of the present application.

[0015] Figure 5 It is a flow chart of the commodity push method of an embodiment of the present application.

[0016] Figure 6 It is a schematic diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0017] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0018] The terms used in this application are only for the purpose of describing specific embodiments, and are not intended to limit the application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in this article refers to and includes any or all possible combinations of one or more associated listed items. In addition, the term "at least one" herein represents any combination of at least two of any one or more of a variety of.

[0019] It should be understood that although the terms first, second, third, etc. may be used in the present application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0020] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present application and to make the above-mentioned purposes, features and advantages of the embodiments of the present application more obvious and understandable, the technical solutions in the embodiments of the present application are further described in detail below in conjunction with the accompanying drawings.

[0021] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0022] Figure 1 The schematic diagram of the application scenario of the present application is exemplarily shown, and the application scenario includes a service platform 10 and a client 20. The service platform 10 can push a push sequence including information of at least one service object to the client 20 for display. Optionally, the service platform 10 can be an e-commerce platform; accordingly, the pushed service object can be a product on the e-commerce platform. In some embodiments, the user can enter search information on the client 20, such as Figure 1As shown, the search information is "women's clothing". The client 20 can send a browsing request carrying the search information to the service platform 10. The service platform 10 can obtain a push sequence in response to the browsing request and push the push sequence to the client 20. In other embodiments, the service platform 10 can also obtain a push sequence and push it according to the user's historical behavior sequence (for example, browsing, liking, collecting, purchasing, adding to a shopping cart, forwarding, commenting, etc.).

[0023] Understandably, Figure 1 The e-commerce scenarios are only illustrative and are not intended to limit this application. In other examples, the service platform 10 and the pushed service objects may also be of other types. For example, the service platform 10 is a video playback platform, and the pushed service object is a video file; or the service platform 10 is a news platform, and the pushed service object is news; or the service platform 10 is a music playback platform, and the pushed service object is an audio file; or the service platform 10 is an e-book platform, and the pushed service object is an e-book; and so on. For ease of description, the following mainly takes the example of the service platform 10 being an e-commerce platform, and the pushed service object being the goods of the e-commerce platform as an example.

[0024] Generally, the object push process is implemented based on the user's historical behavior sequence. However, in some cases, the user may be a new user of the service platform 10, and his behavior sequence is relatively sparse. When the user's behavior sequence is sparse, it is difficult for the service platform 10 to accurately determine the user's needs and preferences, resulting in the pushed service objects not meeting the user's needs and preferences, and the push accuracy is low.

[0025] Based on this, an embodiment of the present application provides an object push method. When the user behavior sequence is sparse, considering that the object characteristics preferred by the user are affected by the regional characteristics of the area where the user is located, object push can be performed based on the regional characteristics of the user's area, so that the pushed object matches the regional characteristics of the user's area, thereby improving the push accuracy when the user behavior sequence is sparse.

[0026] like Figure 2 As shown, the object push method of the embodiment of the present application includes:

[0027] Step S12: Determine the target area where the target user is located;

[0028] Step S14: Acquire target object features associated with the target area, where the target object features are features of the service objects provided by the service platform 10, and the target object features match the regional features of the target area, and are used to reflect the object features preferred by the user group in the target area;

[0029] Step S16: determining at least one target service object on the service platform 10 based on the target object characteristics;

[0030] Step S18: Pushing object information of at least one target service object to the target user.

[0031] The method of the embodiment of the present application can be Figure 1 The service platform 10 shown executes.

[0032] In step S12, the target user may be any user of the service platform 10. The target region where the target user is located may be an administrative region, such as a country, province or city, etc., or may be a region determined in other ways.

[0033] In some embodiments, the location information of the target user collected by the target user's electronic device can be obtained, and the target area where the target user is located is determined based on the location information. For example, a GPS module can be installed on the electronic device to collect the longitude and latitude coordinates of the user. In addition, the longitude and latitude ranges of each area can also be predetermined. If the longitude and latitude coordinates collected by the GPS module fall within the longitude and latitude range of a certain area, it can be determined that the area is the target area where the target user is located.

[0034] In other embodiments, the target area where the target user is located can be determined based on the location information pre-stored by the service platform 10. For example, when the service platform 10 is an e-commerce platform, the location information pre-stored by the service platform 10 can be the delivery address submitted by the user in advance on the service platform 10. The delivery address may include description information of the target area or a sub-area in the target area. For example, assuming that the target area is a national administrative area, the delivery address may include description information of the country, such as "China", "Japan", etc., and may also include description information of the province or city in the country, such as "Guangdong Province" or "Beijing City", etc. When the delivery address includes description information of the target area, the area described by the description information of the target area in the delivery address can be directly determined as the target area where the target user is located. When the delivery address includes description information of a sub-area in the target area, the sub-area described by the description information in the delivery address can be determined. If the sub-area is located in a certain area, the area is determined as the target area where the target user is located.

[0035] In some other embodiments, the target area where the target user is located can be determined based on the location information selected or input by the target user in real time. For example, the service platform 10 can communicate with the client 20 of the target user, and the client 20 can provide a user interface, and the user can select an option corresponding to a certain area in real time on the user interface, or enter the name or longitude and latitude of a certain area in the input box on the user interface. The area corresponding to the above option or the area corresponding to the above identification information is the target area where the target user is located.

[0036] In step S14, the target object features associated with the target area are obtained. The target object features are features that match the regional features of the target area. The target object features can reflect the object features of the service objects preferred by the user groups in the target area, and the preferences of the user groups in the same area often have certain similarities. Therefore, the target object features can reflect the object features of the service objects preferred by the target users to a certain extent.

[0037] Regional characteristics refer to the unique and significant local characteristics of a specific region compared with other regions. There are often certain differences between the regional characteristics of different regions. Regional characteristics may include but are not limited to at least some of the following characteristics: location characteristics, cultural characteristics, language characteristics, climate characteristics, economic characteristics, historical characteristics, population characteristics, etc. Location characteristics can reflect the specific location and spatial layout of a region, including latitude and longitude, altitude, topography and other information, so as to facilitate the determination of the region's transportation convenience, climate and environmental conditions and resource distribution. Cultural characteristics refer to the unique cultural elements and social customs of the region. Cultural characteristics are not only a symbol of the unique identity and recognition of a region, but also an important window for understanding and experiencing the local society, history and humanistic spirit. Language characteristics can reflect the language usage habits of users in a region, which is directly related to communication and cultural inheritance within the society. Climate characteristics directly affect people's lifestyles and economic activities, such as agricultural types, choices of food, clothing, housing and transportation, etc. Economic characteristics reflect the level of development of a region and the quality of life of residents, including income levels, employment conditions, social welfare, etc. Historical characteristics reflect the cultural traditions, values ​​and historical memories of a region in the process of formation and development. Population characteristics reflect the population structure, population density, and migration and flow of a region.

[0038] The above factors may affect the user's needs and preferences for service objects. For example, assuming that an area is in the tropics and the climate is relatively hot all year round, the users in this area are likely to have a greater demand for cool-style clothing, and a smaller demand for down jackets, sweaters and other clothing. For another example, assuming that a region has cultural customs for specific festivals, the users in this region may have a higher demand for products with specific festival elements. The embodiment of the present application extracts regional features and determines that they match the regional features of the target area, so that the object features of the pushed target object meet the needs and preferences of users in a specific area.

[0039] In some embodiments, the target object features are obtained based on a pre-established association relationship between a region and an object feature, and the association relationship can be obtained based on a matching result of a large language model between regional features of at least one region and object features of at least one service object to be pushed on the service platform 10.

[0040] For example, see Figure 3 , the first prompt information can be input to the large language model so that the large language model outputs the regional characteristics of each region based on the first prompt information. The first prompt information may include the identification information of the region and the category information of the required regional characteristics, such as location characteristics, cultural characteristics, language characteristics, etc. Figure 3 In the example shown, the first prompt information is "Please tell me the location characteristics and climate characteristics of China and Japan", which includes the country name (ie, the identification information of the region) and the category information of the regional characteristics (such as location characteristics and climate characteristics).

[0041] After obtaining the regional features of each region, the large language model can be used to output object features that match the regional features of each region, and establish an association between the regional features and the object features that match them. The object features include but are not limited to at least part of the following: object category, color, material, model, purpose, size, applicable scene, applicable population, etc.

[0042] For example, see Figure 4 , the second prompt information can be input to the large language model so that the large language model outputs object features that match the regional features of each region based on the second prompt information. The second prompt information may include the identification information of the region, the category information of the regional features, and the category information of the object features to be output. Figure 4 In the example shown, the second prompt information is "Malaysia's climate characteristics are "no four seasons - hot all year round", which of the categories such as down jackets, thermal underwear, and T-shirts are more in line with user needs", which includes the country name (i.e., the identification information of the region), category information of regional characteristics (such as the climate characteristics are "no four seasons - hot all year round"), and category information of object characteristics (such as the category of the object, here including three categories of down jackets, thermal underwear, and T-shirts).

[0043] The target area may have the same or different regional characteristics in different time periods. If the target area has different regional characteristics in different time periods, the above-mentioned association relationship can be obtained based on the matching result of the large language model between the regional characteristics of at least one area in the specified time period and the object characteristics of at least one service object to be pushed on the service platform 10. On this basis, the target object characteristics are object characteristics that match the regional characteristics of the target area in the specified time period. Taking the regional characteristics including climate characteristics as an example, assuming that the service object is clothing, the object characteristics include the material of the clothing, and assuming that the temperature and humidity of a certain area (hereinafter referred to as area A) in winter are completely different from the temperature in summer. Therefore, the regional characteristics of the area in this winter time period can be "low temperature and cold", and the regional characteristics in this summer time period can be "high temperature and hot". Furthermore, the object characteristics that match the regional characteristics of the area A in the winter time period can be "warm and cold protection", and the object characteristics that match the regional characteristics of the area A in the summer time period can be "light and sweat-absorbent".

[0044] In this embodiment, when pushing objects based on regional characteristics, taking into account the variability of regional characteristics in different time periods, the target object characteristics can be determined according to the specified time period, so that the determined target object characteristics conform to the characteristics of the target area in the specified time period, thereby improving the accuracy of the determined target object characteristics.

[0045] The above-mentioned “time period” may be a time period such as a year, a quarter, a month, or other time periods defined manually. Optionally, the specified time period may be the current time period. For example, assuming that the current time period is July, the specified time period may also be July. Alternatively, if the current time period is summer, the specified time period may also be summer.

[0046] Alternatively, the time difference between the specified time period and the current time is within a preset time range, and the current time is before the specified time period. For example, the current time period is July, and the specified time period is one month after the current time period, so the specified time period is August. Alternatively, the current time period is summer, and the specified time period is the next season of the current time period, that is, the specified time period is autumn. Users may have the need to obtain service objects in advance. For example, when the service object is a product on an e-commerce platform, the user may purchase clothing for the next season in advance before the season changes. Therefore, before the current time period reaches the specified time period, service objects whose object characteristics match the regional characteristics of the specified time period can be pushed to users in advance, thereby facilitating users to obtain service objects in advance.

[0047] In some embodiments, the regional characteristics of an area in any time period are related to the regional events that occur in the area during the time period. Among them, regional events refer to events that occur within a specific area. Regional events only affect or occur in a specific geographical area, and have little correlation with other geographical areas. Regional events that occur in the target area within a certain time period may include, but are not limited to, festival events (such as Spring Festival, Easter, Halloween, etc.), climate events (such as entering the rainy season or dry season, etc.), social and cultural events (such as concerts, art exhibitions, etc.), sports events (such as marathons, championships, etc.) and / or economic activities (such as trade fairs, etc.) in the target area during the time period. Regional events will have a certain impact on user demand. Taking the e-commerce scenario as an example, during the occurrence of festival events, users may buy goods with festival elements, such as users often buy couplets during the Spring Festival; when the rainy season is about to enter, due to the humid weather, users may have the need to buy humidifiers; when holding concerts or sports events, users may buy tickets for concerts or sports events. Therefore, the regional characteristics of the target area in a certain time period can be determined based on the regional events that occur in the target area within a certain time period.

[0048] The number of regional events that occur in the target area within the specified time period can be greater than or equal to 1. If the number of regional events that occur in the target area within the specified time period is greater than 1, the priorities of multiple regional events that occur in the target area within the specified time period can also be obtained, and the target regional event with the highest priority that occurs in the specified time period is determined from the multiple regional events, and the regional characteristics related to the target regional event are determined as the regional characteristics of the target area in the specified time period. The above-mentioned priority can be determined based on the importance of each regional event, for example, it can be determined manually, or automatically determined by a large language model. Since regional events with higher importance often have a greater impact on user needs, therefore, this embodiment determines the priority of each regional event based on the importance of each regional event, and screens out the regional event with the highest priority to determine the regional characteristics of the target area in the specified time period, which can determine the regional characteristics that have a greater impact on user needs, so that the final push result is more in line with user needs.

[0049] For example, if multiple holiday events occur in the target area within a specified time period (two holiday events, respectively recorded as holiday event X and holiday event Y), the priorities of holiday leave X and holiday leave Y can be pre-determined. Assuming that the priority of holiday leave X is higher than the priority of holiday leave Y, holiday event X can be determined as the target regional event, and the regional characteristics related to holiday event X can be determined as the regional characteristics of the target area in the specified time period.

[0050] In some embodiments, each time period can be pre-associated with tag information, and the tag information is used to indicate the regional events that occur in each area within the corresponding specified time period. For example, assuming that a certain area is in the thunderstorm season in March and a festival event occurs in October, tag information indicating that "the area is in the thunderstorm season in March" can be generated for the time period in March, and tag information indicating that "the area has a festival event in October" can be generated for the time period in October. Based on this, the tag information associated with the specified time period of the target area can be obtained, and the tag information is used to indicate the regional events that occur in the target area within the specified time period, and the regional events that occur in the target area within the specified time period are determined based on the obtained tag information. Continuing with the previous example, when the tag information associated with March is obtained as the tag information indicating that "the target area is in the thunderstorm season in March", it can be determined that the regional event that occurs in the target area in March is the entry of the thunderstorm season. When the tag information associated with October is obtained as the tag information indicating that "the target area has a festival event in October", it can be determined that the regional event that occurs in the target area in October is the occurrence of a certain festival event.

[0051] In step S16, at least one target service object on the service platform 10 may be determined based on the target object characteristics. For example, when the service platform 10 is an e-commerce platform and the service object is a commodity, at least one target commodity on the e-commerce platform may be determined based on the target object characteristics.

[0052] In some embodiments, it is also possible to obtain historical behavior features on the service platform 10, obtain object features that match the historical behavior features, fuse the target object features and the object features that match the historical behavior features to obtain fused features, and determine at least one target service object on the service platform 10 based on the fused features. Among them, the historical behavior features can be obtained by extracting features from the historical behavior sequence of the target user on the service platform 10. By adopting the historical behavior features, the needs and preferences of the target user for the service objects on the service platform 10 can be determined from the dimension of the target user's own behavior pattern; by adopting the target object features, the needs and preferences of the target user for the service objects on the service platform 10 can be determined from the dimension of the target user's area. Therefore, the embodiments of the present application can simultaneously determine the needs and preferences of the target user for the service objects on the service platform 10 from two different dimensions, thereby obtaining more accurate push results.

[0053] In some embodiments, the target object features and the object features that match the historical behavior features may be weighted to obtain fused features.

[0054] The first weight corresponding to the target object feature and the second weight corresponding to the object feature that matches the historical behavior feature can be set to a fixed value, or can be dynamically adjusted according to actual needs. In some embodiments, the above-mentioned first weight and second weight can be determined based on preset conditions, and the target object feature and the object feature that matches the historical behavior feature can be weighted based on the determined first weight and second weight. This embodiment dynamically adjusts the first weight and the second weight according to the preset conditions, and can change the degree of influence of the target object feature and the object feature that matches the historical behavior feature on the push result according to different actual application scenarios, so that the push result is more in line with the actual application scenario.

[0055] Specifically, the preset conditions may include but are not limited to at least one of the following:

[0056] (1) The registration duration of the target user on the service platform 10. The registration duration can reflect whether the target user is a new user or an old user. If the target user is a new user, the historical behavior sequence of the target user on the service platform 10 may be relatively sparse. Therefore, the needs and preferences of the user reflected by the historical behavior characteristics may not be accurate enough. Therefore, the second weight can be reduced and the first weight can be increased, so that the push result is mainly affected by the characteristics of the target object. Specifically, the first weight can be greater than the second weight.

[0057] (2) The current push scenario of pushing the service object to the target user. The current push scenario can reflect the user's intention to a certain extent. For example, assuming that the current push scenario is a search scenario, that is, the user searches for the service object on the service platform 10 by searching keywords, the user has a relatively clear and definite intention, so the historical behavior characteristics often have a greater impact on the push results. Therefore, in the search scenario, the second weight can be greater than the first weight. In the recommendation scenario, if the user enters the recommendation page of the service platform 10, the user may not have a clear and definite intention for the service object of the service platform 10, especially in the recommendation scenario of recommending the service object to a new user, it is difficult to effectively determine the user's intention due to incomplete user information. Therefore, in the recommendation scenario, the impact of the historical behavior characteristics on the push results may be relatively small, so it can be determined that the first weight is greater than the second weight. In addition to the above-mentioned application scenarios, the embodiments of the present application may also involve other push scenarios. In the corresponding push scenarios, the first weight and the second weight can be determined according to the characteristics of the actual push scenario, which will not be listed here one by one.

[0058] (3) The length of the historical behavior sequence of the target user on the service platform 10. The historical behavior sequence can reflect the user's preference to a certain extent. When the historical behavior sequence is long (for example, greater than a preset length threshold), the service platform 10 can obtain rich historical behavior features, so that the user's preference can be determined more accurately. At this time, the second weight can be increased and the first weight can be reduced, so that the push result is mainly affected by the historical behavior features. Specifically, the first weight can be smaller than the second weight. When the historical behavior sequence is short (for example, less than or equal to a preset length threshold), the historical behavior features obtained by the service platform 10 are relatively sparse, and it is difficult to accurately determine the user's preference. At this time, the first weight can be increased and the second weight can be reduced, so that the push result is mainly affected by the characteristics of the target object. Specifically, the second weight can be smaller than the first weight.

[0059] The relationship between the first weight and the second weight may also be determined based on other factors, which are not listed here one by one.

[0060] In step S18, the object information of the at least one target service object determined may be pushed to the client 20 of the target user. For example, a push sequence including the object information of the at least one target service object may be generated, and the push sequence may be pushed to the client 20 of the target user. For example, in an e-commerce scenario, the push sequence may be displayed in the form of a product waterfall on the client 20. The product waterfall is a web page design layout, which is characterized in that in a vertically scrolling page, products are displayed in sequence in a waterfall-like manner, and users can browse different products by scrolling the page.

[0061] The present application also provides a method for pushing a product. Figure 5 , the method comprising:

[0062] Step S22: determining the target area where the target user is located;

[0063] Step S24: acquiring target product features associated with the target area, wherein the target product features are features of products on the e-commerce platform, and the target product features match the regional features of the target area, and are used to reflect product features preferred by the user group in the target area;

[0064] Step S26: determining at least one target product on the e-commerce platform based on the target product characteristics;

[0065] Step S28: Pushing product information of the at least one target product to the target user.

[0066] In some embodiments, the target product features are obtained based on a pre-established association relationship between region and product features, and the association relationship is obtained based on a matching result of a large language model between regional features of at least one region and product features of at least one product to be pushed on the e-commerce platform.

[0067] In some embodiments, the target area has different regional characteristics in different time periods; the association relationship is obtained based on the matching result of the large language model between the regional characteristics of at least one area in a specified time period and the product characteristics of at least one product to be pushed on the e-commerce platform.

[0068] In some embodiments, the regional characteristics of the at least one area are related to regional events occurring in the at least one area within a specified time period.

[0069] In some embodiments, determining at least one target product on the e-commerce platform based on the target product characteristics includes: obtaining historical behavior characteristics of users on the e-commerce platform; obtaining product characteristics that match the historical behavior characteristics; fusing the target product characteristics and the product characteristics that match the historical behavior characteristics to obtain a fused characteristic; and determining at least one target product on the e-commerce platform based on the fused characteristic.

[0070] The e-commerce platform in the embodiment of the present application corresponds to the service platform 10 in the above embodiment, and the commodity in the embodiment of the present application corresponds to the service object in the above embodiment. The specific details of the embodiment of the present application can be found in the above embodiment, and will not be repeated here.

[0071] The overall process of this application is illustrated below with reference to a specific embodiment.

[0072] Some e-commerce platforms, especially cross-border e-commerce platforms, aim to provide high-quality cross-border transaction services for global merchants and consumers. With the continuous development of globalization, more and more consumers are beginning to pay attention to the culture and characteristics of different countries. Therefore, providing goods and services that meet the needs of consumers in different countries has become one of the important tasks of e-commerce platforms.

[0073] On e-commerce platforms, users come from all over the world. National culture and geographical characteristics have a significant impact on a country's agricultural production, energy consumption, clothing habits, architectural design, etc., which directly affects the purchase categories and category preferences on e-commerce platforms. Consumers in different countries have very different needs and preferences for goods and services. Therefore, in order to provide more localized recommendation services, it is necessary to recommend goods and services that meet their localized needs based on the user's country and region information.

[0074] This solution aims to provide e-commerce platforms with country-localized category recommendation services. By using large language models (such as AIGC), localized knowledge (i.e., regional characteristics) such as the country's geography (seasonal climate), culture (religion), and the user demand categories and product characteristics that localized knowledge will affect in the e-commerce platform field are accumulated as knowledge reserves for localized recommendations in the global e-commerce field. At the same time, by inputting the "country-product characteristics" (including product categories, colors, materials, etc.) mapping relationship into the push algorithm and e-commerce platform, more products that meet the country's localization are recommended in the waterfall product recommendations in the recommendation field; category themes that meet the country's localization are recommended in the discovery themes in the recommendation field, which can provide users with products that are more in line with local habits and preferences, especially for new users who have not accumulated any personalized behavior on the e-commerce platform.

[0075] The specific process of the embodiment of this application is as follows:

[0076] (1) Using a large language model to output objective knowledge related to regional characteristics, such as a country's population knowledge, national cultural knowledge, a country's geographical location, season types, average temperature, maximum temperature, minimum temperature knowledge of the four seasons, or part or all of the knowledge. The regional characteristics in some embodiments are shown in the following table:

[0077] Country Code population Language Number Spring maximum temperature Spring minimum temperature Summer maximum temperature Summer minimum temperature Maximum temperature in autumn The lowest temperature in autumn Maximum temperature in winter Minimum winter temperature K1 2.2 billion L1 25 11 36 23 33 20 21 6 K2 35.5 million L2 26 15 23 11 23 12 25 14 K3 23.5 million L3 31 22 30 24 30 23 28 22 K4 17.8 million L4 6 1 19 11 19 11 9 4

[0078] Based on the above table, we can determine the population, language, temperature and other characteristics of countries numbered K1, K2, K3 and K4.

[0079] (2) Input all product categories in the e-commerce platform into the large language model, and let the large language model output product categories affected by regional characteristics (for example, product categories affected by religion include clothing, home furnishings, handicrafts, etc., and product categories affected by seasonal climate include clothing categories). The product categories that need to be personalized according to regional characteristics in the e-commerce platform are obtained, as shown in the following table:

[0080] Season Type Product Category Code Country Code No seasons - cool all year round C1, C2 K1, K2 No seasons - hot weather all year round C1, C2 K3 There are four seasons C1, C2 K4, K5 Two seasons C1, C2 K6, K7, K8

[0081] According to the above table, it can be determined that the commodity categories with commodity category numbers C1 and C2 are affected by the season type, as well as the respective season types of the countries with country numbers K1 to K8.

[0082] (3) Using the big language model, the product characteristics affected by regional characteristics in the e-commerce platform and the regional characteristics of each country are input into the big language model, so that the big language model can output product characteristics that match the regional characteristics of each country, such as product categories (such as dresses, carpets, etc.) and attribute items and attribute values ​​under each product category (such as length: short; material: silk). According to the results returned by the big language model, the relationship data of "country-product characteristics" (including "country-product category" and "country-product category-attribute items and attribute values") is established (i.e., the association relationship in the above embodiment), indicating the demand range and preference characteristics of the country-localized characteristic categories.

[0083] (4) After the buyer arrives at the recommendation scene, recommend products and content that are more in line with the country's local characteristics.

[0084] 1) Input the "country-product feature" relationship data into the push algorithm model, and push more products that are in line with the country's localization in the waterfall product recommendation in the recommendation field. For example, the pajamas recommended to users in the country "Malaysia" are more cool styles, and the pajamas recommended to users in the country "Australia" (now in winter) are more warm styles.

[0085] 2) Connect the "country-product characteristics" relationship data to the theme delivery operation platform, and recommend category themes that are in line with national localization in the discovery-type themes in the recommendation field. For example, the pajamas recommended to users in the country "Malaysia" are mostly cool styles, and the pajamas recommended to users in the country "Australia" (now in winter) are mostly warm styles.

[0086] This solution submits regional characteristics and product categories affected by regional characteristics as inputs to the algorithm and operations. For example, different climate characteristics will lead to different clothing thickness requirements, and different religions will have different preferences for home furnishings and handicraft styles.

[0087] In the field of algorithm recommendation, the embodiments of the present application can add localized feature dimensions to the user's own personalized feature dimensions to make corresponding category recommendations, and can more accurately recommend national localized categories and preferred feature products, so that the recommendation scenarios of globalized e-commerce platforms can respect the regional characteristics such as living habits and cultural atmosphere of each country when recommending categories and products. When making discovery-type operation themes in the recommendation scenario, themes can be recommended according to these localized feature dimensions.

[0088] An embodiment of the present application further provides a computer device, which comprises at least a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method described in any of the foregoing embodiments is implemented.

[0089] Figure 6 A more specific hardware structure diagram of a computer device provided in an embodiment of the present application is shown, and the device may include: a processor 202, a memory 204, an input / output interface 206, a communication interface 208, and a bus 210. The processor 202, the memory 204, the input / output interface 206, and the communication interface 208 are connected to each other in communication within the device through the bus 210.

[0090] The processor 202 can be implemented by a general central processing unit (CPU), a microprocessor, an application specific integrated circuit (ASIC), or one or more integrated circuits, etc., for executing related programs to implement the technical solutions provided in the embodiments of the present application. The processor 202 can also include a graphics card, which can be a Nvidia titan X graphics card or a 1080Ti graphics card, etc.

[0091] The memory 204 can be implemented in the form of a read-only memory (ROM), a random access memory (RAM), a static storage device, a dynamic storage device, etc. The memory 204 can store an operating system and other application programs. When the technical solution provided in the embodiment of the present application is implemented by software or firmware, the relevant program code is stored in the memory 204 and called and executed by the processor 202.

[0092] The input / output interface 206 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0093] The communication interface 208 is used to connect a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, Wi-Fi, Bluetooth, etc.).

[0094] The bus 210 comprises a pathway for transmitting information between the various components of the device, such as the processor 202 , the memory 204 , the input / output interface 206 , and the communication interface 208 .

[0095] It should be noted that, although the above device only shows the processor 202, the memory 204, the input / output interface 206, the communication interface 208 and the bus 210, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiment of the present application, and does not necessarily include all the components shown in the figure.

[0096] An embodiment of the present application provides a computer program product, including a computer program, which implements the method described in any embodiment of the present application when executed by a processor.

[0097] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any of the foregoing embodiments.

[0098] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computer device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0099] Each embodiment in the present application is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts refer to the partial description of the method embodiment. The device embodiment described above is merely schematic, wherein the modules described as separate components may or may not be physically separated, and the functions of each module can be implemented in the same one or more software and / or hardware when implementing the embodiment scheme of the present application. It is also possible to select some or all of the modules according to actual needs to achieve the purpose of the embodiment scheme. Those of ordinary skill in the art can understand and implement it without paying creative work.

[0100] The above is only a specific implementation of the embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the embodiment of the present application. These improvements and modifications should also be regarded as the protection scope of the embodiment of the present application.

Claims

1. A product push method, the method comprising: Determine the target area where the target users are located; Acquire target product features associated with the target area, wherein the target product features are features of products on the e-commerce platform, and the target product features match the regional features of the target area, and are used to reflect the product features preferred by the user group in the target area; Determine at least one target product on the e-commerce platform based on the target product characteristics; Push product information of the at least one target product to the target user.

2. According to the method according to claim 1, the target product characteristics are obtained based on a pre-established association relationship between region and product characteristics, and the association relationship is obtained based on a matching result of a large language model between regional characteristics of at least one region and product characteristics of at least one product to be pushed on the e-commerce platform.

3. According to the method of claim 2, the target area has different regional characteristics in different time periods; the association relationship is obtained based on the matching result of the large language model between the regional characteristics of at least one area in a specified time period and the product characteristics of at least one product to be pushed on the e-commerce platform. 4 . The method according to claim 2 , wherein the regional characteristics of the at least one area are related to regional events occurring in the at least one area within a specified time period.

5. According to the method of claim 1, determining at least one target product on the e-commerce platform based on the target product characteristics comprises: Obtaining historical behavior characteristics of users on the e-commerce platform; Acquire product features that match the historical behavior features; The target product feature and the product feature that matches the historical behavior feature are fused to obtain a fused feature; At least one target product on the e-commerce platform is determined based on the fusion feature.

6. A method for pushing an object, the method comprising: Determine the target area where the target users are located; Acquire target object features associated with the target area, wherein the target object features are features of service objects provided by the service platform, and the target object features match the regional features of the target area, and are used to reflect the object features preferred by the user group of the target area; Determine at least one target service object on the service platform based on the target object characteristics; Pushing object information of the at least one target service object to the target user.

7. The method according to claim 6, wherein determining the target area where the target user is located comprises: The target region where the target user is located is determined based on at least one of the following: Location information collected by the target user's electronic device; The location information pre-stored on the service platform; The location information selected or input by the target user in real time.

8. According to the method of claim 6, the target object features are obtained based on a pre-established association relationship between a region and an object feature, and the association relationship is obtained based on a matching result of a large language model between regional features of at least one region and object features of at least one service object to be pushed on the service platform.

9. According to the method of claim 8, the target area has different regional characteristics in different time periods; the association relationship is obtained based on the matching result of the large language model between the regional characteristics of at least one area in a specified time period and the object characteristics of at least one service object to be pushed on the service platform.

10. The method according to claim 6, wherein the regional characteristics of the at least one area are related to regional events occurring in the at least one area within a specified time period.

11. The method according to claim 10, wherein the number of regional events occurring in the target area within a specified time period is greater than 1; the method further comprising: Obtaining priorities of multiple regional events occurring in the target area within the specified time period; Determining, from among the plurality of regional events, a target regional event with the highest priority occurring within the specified time period; The regional characteristics associated with the target regional event are determined as the regional characteristics of the target area. 12 . The method according to claim 10 , wherein the time difference between the designated time period and the current time is within a preset time range, and the current time is before the designated time period.

13. The method according to claim 10, further comprising: Acquire tag information of the target area associated with the specified time period, where the tag information is used to indicate a regional event occurring in the target area within the specified time period; A regional event occurring in the target area within the specified time period is determined based on the tag information.

14. The method according to claim 6, wherein determining at least one target service object on the service platform based on the target object characteristics comprises: Obtaining historical behavior characteristics of users on the service platform; Acquire object features that match the historical behavior features; Fusing the target object feature and the object feature matching the historical behavior feature to obtain a fused feature; At least one target service object on the service platform is determined based on the fusion feature.

15. The method according to claim 14, wherein the step of fusing the target object feature and the object feature matching the historical behavior feature to obtain the fused feature comprises: The target object features and the object features matching the historical behavior features are weighted to obtain fusion features.

16. The method according to claim 15, wherein weighting the target object feature and the object feature matching the historical behavior feature comprises: Determine, based on a preset condition, a first weight corresponding to the target object feature and a second weight corresponding to the object feature matching the historical behavior feature; weighting the target object feature and the object feature matching the historical behavior feature based on the first weight and the second weight; The preset condition includes at least one of the following: The registration duration of the target user on the service platform; Push the current push scenario of the service object to the target user; The length of the historical behavior sequence of the target user on the service platform.

17. A computer-readable storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the method according to any one of claims 1 to 16 is implemented.

18. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 16 when executing the program.

19. A computer program product, comprising a computer program, which implements the method according to any one of claims 1 to 16 when executed by a processor.

Images