Commodity information sharing method and related equipment

Abstract

The invention provides a commodity information sharing method, and the method comprises the steps: receiving a sharing request of a target user, the sharing request comprising a target sharing object and the commodity information of a target sharing commodity; obtaining historical sharing information received by the target sharing object in a preset time period, wherein the historical sharing information comprises commodity information of historical sharing commodities and purchase information of the historical sharing commodities; generating target sharing information corresponding to the target sharing commodity based on the commodity information of the target sharing commodity and the historical sharing information; and sharing the target sharing information to the target sharing object in a link form. According to the method, the sharing record and the purchase conversion data received by the target sharing object recently are analyzed, and the personalized sharing information is dynamically generated in combination with the target commodity information that the target user wants to share, so that the target sharing information more conforms to the target sharing object while visually representing the target commodity information, and the user experience is improved. And the user experience of the target sharing object is improved.

Description

Technical Field

[0001] The present invention relates to the field of information processing, and in particular to a commodity information sharing method and related equipment. Background Art

[0002] The emergence of online shopping has brought great convenience to people's shopping life. In the online shopping scene, due to the wide variety of items, people need to spend a long time to choose the desired products. In order to reduce the user's selection time, online shopping malls use sharing to share product information with users, that is, users can send a link of a product to another user. The link is a website link. The shared user needs to click in to jump to the specific product interface to browse the product information. In some cases where there is no condition to click on the link, the user cannot know the product information corresponding to the link, and the user experience is poor. Summary of the invention

[0003] The embodiment of the present invention provides a method for sharing product information, aiming to solve the problem that the existing product information sharing method cannot intuitively know the product information corresponding to the link. The present invention analyzes the sharing records and purchase conversion data recently received by the target sharing object, combines the target product information that the target user wants to share, and dynamically generates personalized sharing information, so that the target sharing information can intuitively represent the target product information while being more consistent with the target sharing object, thereby improving the user experience of the target sharing object.

[0004] In a first aspect, an embodiment of the present invention provides a method for sharing product information, the method comprising the following steps:

[0005] Receive a sharing request from a target user, the sharing request including the target sharing object and product information of the target sharing product;

[0006] Acquire historical sharing information received by the target sharing object within a preset time period, wherein the historical sharing information includes commodity information of historically shared commodities and purchase information of historically shared commodities;

[0007] Based on the product information of the target shared product and the historical sharing information, generating target sharing information corresponding to the target shared product;

[0008] The target sharing information is shared with the target sharing object in the form of a link.

[0009] Optionally, the acquiring of historical sharing information received by the target sharing object within a preset time period includes:

[0010] In the preset time period, query whether the target sharing object has received the historical sharing information shared by the target user;

[0011] If the target sharing object has received historical sharing information shared by the target user, obtain first historical sharing information, where the first historical sharing information includes the historical sharing information shared by the target user with the target sharing object and the historical sharing information shared by a first other user with the target object;

[0012] If the target sharing object has not received historical sharing information shared by the target user, obtain second historical sharing information, where the second historical sharing information includes the historical sharing information shared by a second other user with the target sharing object.

[0013] Optionally, the obtaining of the first historical sharing information includes:

[0014] Determine a first user group that has shared sharing information with the target sharing object within the preset time period, where the first user group includes the target user;

[0015] Based on the sharing information shared by the first user group with the target sharing object and the purchase information of the target sharing object for the sharing information, obtain the first historical sharing information.

[0016] Optionally, the obtaining of the second historical sharing information includes:

[0017] Determine a first user portrait corresponding to the target user and a second user portrait of the target sharing object;

[0018] According to the first user portrait and the second user portrait, determine a second user group that has shared sharing information with the target sharing object within the preset time period;

[0019] Based on the sharing information shared by the second user group with the target sharing object and the purchase information of the target sharing for the sharing information, obtain the second historical sharing information.

[0020] Optionally, the determining, according to the first user portrait and the second user portrait, of a second user group that has shared sharing information with the target sharing object within the preset time period includes:

[0021] Determine a third user group that has shared sharing information with the target sharing within the preset time period, where the third user group includes multiple candidate users;

[0022] According to the multiple first similarities between the user portraits corresponding to each candidate user in the third user group and the first user portrait, and according to the multiple second similarities between the user portraits corresponding to each candidate user in the third user group and the second user portrait, each of the first similarities corresponds to one of the candidate users, and each of the second similarities corresponds to one of the candidate users;

[0023] Based on the first similarity and the second similarity, a second user group is determined among the multiple candidate users.

[0024] Optionally, the generating the target sharing information corresponding to the target sharing commodity based on the commodity information of the target sharing commodity and the historical sharing information includes:

[0025] If the historical sharing information is the first historical sharing information, the historical sharing information corresponding to the target user is taken as the main, and the historical information corresponding to the first other user is taken as the supplement to construct a first knowledge graph for the target sharing object;

[0026] Based on the first knowledge graph and the target sharing commodity information, the target sharing information corresponding to the target sharing commodity is generated.

[0027] Optionally, the generating the target sharing information corresponding to the target sharing commodity based on the commodity information of the target sharing commodity and the historical sharing information includes:

[0028] If the historical sharing information is the second historical sharing information, the historical information corresponding to the second other user is used to construct a second knowledge graph for the target sharing object;

[0029] Based on the second knowledge graph and the target sharing commodity information, the target sharing information corresponding to the target sharing commodity is generated.

[0030] In a second aspect, an embodiment of the present invention further provides a commodity information sharing device, and the commodity information sharing device includes:

[0031] A receiving module, configured to receive a sharing request of a target user, where the sharing request includes a target sharing object and commodity information of a target sharing commodity;

[0032] An obtaining module, configured to obtain historical sharing information received by the target sharing object within a preset time period, where the historical sharing information includes commodity information of a historical sharing commodity and purchase information of the historical sharing commodity;

[0033] A generating module, configured to generate target sharing information corresponding to the target sharing commodity based on the commodity information of the target sharing commodity and the historical sharing information;

[0034] A sharing module, configured to share the target sharing information in the form of a link with the target sharing object.

[0035] In a third aspect, an embodiment of the present invention provides an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where when the processor executes the computer program, the steps in the commodity information sharing method provided by the embodiment of the present invention are implemented.

[0036] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps in the commodity information sharing method provided by the embodiment of the invention are implemented.

[0037] In an embodiment of the present invention, a sharing request of a target user is received, the sharing request includes a target sharing object and commodity information of a target sharing commodity; historical sharing information received by the target sharing object within a preset time period is obtained, the historical sharing information includes commodity information of historical sharing commodities and purchase information of historical sharing commodities; based on the commodity information of the target sharing commodity and the historical sharing information, target sharing information corresponding to the target sharing commodity is generated; and the target sharing information is shared with the target sharing object in the form of a link. By analyzing the sharing records and purchase conversion data recently received by the target sharing object and combining the commodity information of the target commodity that the target user wants to share, the present invention dynamically generates personalized sharing information, so that while the target sharing information intuitively represents the commodity information of the target commodity, it is more in line with the target sharing object, improving the user experience of the target sharing object. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required to be used in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings without creative efforts based on these drawings.

[0039] Figure 1 is a flowchart of a commodity information sharing method provided by an embodiment of the present invention;

[0040] Figure 2 is a schematic structural diagram of a commodity information sharing device provided by an embodiment of the present invention;

[0041] Figure 3 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0042] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0043] As Figure 1 shown, Figure 1 is a flowchart of a method for sharing commodity information provided by an embodiment of the present invention. The method for sharing commodity information includes the steps:

[0044] 101. Receive a sharing request from a target user.

[0045] In an embodiment of the present invention, the above method for sharing commodity information can be applied to a server. The server is communicatively connected to a user terminal. The user terminal includes a terminal interface for displaying commodity information of an online shopping mall.

[0046] The above target user is the user operating the user terminal.

[0047] The above sharing request is triggered by the target user through the user terminal and uploaded to the server. The sharing request may include the target sharing object and the commodity information of the target sharing commodity. The target sharing object may be one or more (groups), and the target sharing object is the user object that the target user wants to share with. The target sharing commodity is the commodity that the target user wants to share, which may be a commodity that the target user has purchased, a commodity that the target user is browsing, etc. The commodity information is used to describe the specific information of the commodity, such as commodity ID, commodity name, commodity category, commodity price, commodity discount, commodity details, etc. The commodity information may also be the uniform resource locator of the target sharing commodity.

[0048] Specifically, when the target user browses a commodity or an order, the target user can trigger a commodity information sharing operation through the commodity sharing button on the terminal interface, that is, the target user clicks or touches the commodity sharing button on the terminal interface to trigger the commodity information sharing operation, generate a sharing request, and send the sharing request to the server. After receiving the sharing request, the server parses the sharing request to obtain the commodity information of the target sharing commodity.

[0049] 102. Obtain the historical sharing information received by the target sharing object within a preset time period.

[0050] In an embodiment of the present invention, the above historical sharing information includes the commodity information of the historical sharing commodity and the purchase information of the historical sharing commodity. The purchase information can be understood as the conversion behavior of the target sharing object for the historical sharing commodity, such as click, add to cart, place an order, pay, etc.

[0051] Specifically, a user database can be established. The user database records the user portraits of each user and the sharing information received by each user. The above sharing information may include sharer information, product information, purchase information, etc.

[0052] In the user database, the historical sharing information received by the target sharing object within a preset time period can be queried with the preset time period as the query time period and the target sharing object as the query object.

[0053] The above preset time period can be set according to user needs. For example, it can be one month, two months, etc.

[0054] 103. Generate target sharing information corresponding to the target sharing product based on the product information and historical sharing information of the target sharing product.

[0055] In the embodiments of the present invention, customized content is dynamically generated by combining the target product information with historical data. For example, if the historical sharing product and the target product belong to the same category, such as "sports shoes", the differential advantages of the target product, such as lower price, function upgrade, etc., are highlighted.

[0056] According to the purchase information in the historical sharing information, determine the purchase conversion rate of the target sharing object for the historical sharing product. If the purchase conversion rate of the target sharing object for the historical sharing product is high, then strengthen the promotion information, such as limited-time discount. The purchase conversion rate is obtained by integrating and weighting according to purchase information such as click, add to cart, place an order, and payment.

[0057] In a possible embodiment, for the target product shared by the target user to the target sharing object, it can be queried in the user database whether the target user has shared the target product to the target sharing object within the preset time period, that is, whether the target sharing object has received the sharing information of the target product within the preset time period. If the sharing information of the target product has been received, it means that a user has shared the target product to the target sharing object within the preset time period. At this time, if the target sharing object has purchased the target product according to the historical sharing information, the historical sharing information corresponding to the target sharing object when purchasing the target product can be determined as the target sharing information. If the target sharing object has not purchased the target product according to the historical sharing information, then based on the historical sharing information corresponding to the target product, the promotion information, such as limited-time discount, can be strengthened to obtain the target sharing information.

[0058] 104. Share the target sharing information to the target sharing object in the form of a link.

[0059] In an embodiment of the present invention, the generated target sharing information is used as the display content of an interactive link. The essence of this display content is the link address of the target commodity, that is, the target sharing information can be intuitively displayed on the user terminal of the target sharing object, rather than a link address with an unclear meaning. The target sharing object can view the target sharing information without clicking to jump, and thus can understand the commodity information of the target commodity in advance.

[0060] When the target sharing object clicks or touches the target sharing information in the terminal interface, the corresponding link address will be triggered and it will jump to the shopping interface of the target commodity.

[0061] In an embodiment of the present invention, a sharing request from a target user is received. The sharing request includes the target sharing object and the commodity information of the target sharing commodity; historical sharing information received by the target sharing object within a preset time period is obtained. The historical sharing information includes the commodity information of the historical sharing commodity and the purchase information of the historical sharing commodity; based on the commodity information of the target sharing commodity and the historical sharing information, target sharing information corresponding to the target sharing commodity is generated; and the target sharing information is shared with the target sharing object in the form of a link. By analyzing the sharing records and purchase conversion data recently received by the target sharing object, and combining with the commodity information of the target commodity that the target user wants to share, the present invention dynamically generates personalized sharing information, so that while the target sharing information intuitively represents the commodity information of the target commodity, it is more in line with the target sharing object, improving the user experience of the target sharing object.

[0062] It can be understood that in the specific implementation of the present application, relevant data such as commodity information, user information, and purchase information are involved. When the embodiments in the present application are applied to specific products or technologies, user permission or consent needs to be obtained, and the collection, use, and processing of relevant data, as well as the training, deployment, and invocation of algorithm models, all need to comply with relevant laws, regulations, and standards of relevant countries and regions.

[0063] Optionally, in the step of obtaining the historical sharing information received by the target sharing object within a preset time period, it can be queried whether the target sharing object has received the historical sharing information shared by the target user within the preset time period; if the target sharing object has received the historical sharing information shared by the target user, the first historical sharing information is obtained. The first historical sharing information includes the historical sharing information shared by the target user with the target sharing object and the historical sharing information shared by the first other user with the target object; if the target sharing object has not received the historical sharing information shared by the target user, the second historical sharing information is obtained. The second historical sharing information includes the historical sharing information shared by the second other user with the target sharing object.

[0064] In the embodiments of the present invention, after the server parses the sharing request of the target user, it uses the target sharing object as an index to perform the following queries in the user database:

[0065] Query fields: sharer ID (i.e., target user ID), recipient ID (i.e., target sharing object ID).

[0066] Filtering rule: Whether there is a sharing record initiated by the target user to the target sharing object within a preset time period (e.g., the past 30 days).

[0067] For example, if user A (target user) has shared a product with user B (target sharing object) within 30 days, it is marked as "there is historical sharing"; then it can be determined that the target sharing object has received the historical sharing information shared by the target user. If there has never been a sharing, it is marked as "no historical sharing"; then it can be determined that the target sharing object has not received the historical sharing information shared by the target user.

[0068] In the case where it is determined that the target sharing object has received the historical sharing information shared by the target user, all product information shared by the target user to the target sharing object within the preset time period and the corresponding purchase behaviors (such as clicks, add-to-cart, payments, etc.) of the target sharing object can be obtained. At the same time, product information shared by the first other users (such as user C, user D) other than the target user to the target sharing object within the same time period and the corresponding purchase behaviors of the target sharing object are obtained. The obtained historical sharing information is sorted to obtain the first historical sharing information.

[0069] It can be sorted by priority. In this embodiment, the weight of the historical data of the target user is higher than that of other users.

[0070] For example: User A shares product X, and user B clicks but does not purchase;

[0071] User C shares product Y, and user B places an order and pays.

[0072] The first historical sharing information will include the data of both products X and Y, but the sharing record of user A will be marked as "primary association".

[0073] In the case where it is determined that the target sharing object has not received the historical sharing information shared by the target user, users similar to the target user and / or the target sharing object are filtered. These users are the second other users, and the products shared by the second other users to the target sharing object within the preset time period and the corresponding purchase behaviors of the target sharing object are obtained.

[0074] It should be noted that the above-mentioned first other users are users who have shared product information with the target sharing object within a preset time; the above-mentioned second other users are users who have shared product information with the target sharing object within a preset time and are similar to the target user and / or the target sharing object.

[0075] For example, if user A shares a product with user B for the first time, and user B has received products Z and W shared by users C and D in the past, then the second historical sharing information only includes the data of products Z and W.

[0076] In the embodiments of the present invention, by judging the historical relationship between the target user and the sharing object, the data source is dynamically adjusted; in the case of historical interaction, the direct behavior data of the target user can be utilized to improve the recommendation relevance (for example, user B trusts the recommendation of user A more); in the case of no historical interaction, the cold start problem can be filled by the indirect data of other users to avoid the recommendation blind area.

[0077] Optionally, in the step of obtaining the first historical sharing information, a first user group that has shared sharing information with the target sharing object within a preset time can be determined, and the first user group includes the target user; based on the sharing information shared by the first user group with the target sharing object and the purchase information of the target sharing object for the sharing information, the first historical sharing information is obtained.

[0078] In the embodiments of the present invention, the above-mentioned first user group is multiple users who have shared sharing information with the target sharing object within a preset time, and the multiple users also include the target user.

[0079] When the target sharing object has received the sharing information of the target user within a preset time period, in the user database, with the target sharing object as the recipient, all users who have shared products with it within the preset time period are screened.

[0080] The screening conditions are specifically as follows:

[0081] Sharer ID (user unique identifier);

[0082] Sharing time (within the preset time period);

[0083] Recipient ID (i.e., the target sharing object ID).

[0084] The users (sharers) who meet the screening conditions are the first user group, and the above-mentioned first user group specifically includes the target user and the first other users.

[0085] For example, if user B (target sharing object) has received the sharing records of user A (target user), user C, and user D in the past 30 days, then it is {A, C, D}.

[0086] After determining the first user group, obtain the product information shared by each user in the first user group and the purchase information corresponding to the target sharing object from the user database.

[0087] Perform post-processing on the historical sharing information corresponding to each user in the first user group. The post-processing includes marking the sharing records of the target user (User A) as core data and the data of the first other users (C, D) as auxiliary supplements. In the first historical sharing information, each historical sharing record is sorted by the target user and the first other users, and each historical sharing record corresponding to the first other users is sorted in chronological order of sharing time.

[0088] In one possible embodiment, the post-processing further includes assigning higher weights to products with high purchase conversion rates. For example, if the product Y shared by user C is purchased by user B, the sharing information of product Y will be highlighted during integration.

[0089] Generate the first historical sharing information. In the first historical sharing information, each historical sharing record includes fields: sharer ID, product ID, sharing time, purchase status (click / add to cart / place an order / payment), etc.

[0090] Arrange the sharing records of the first user group in reverse chronological order and associate the purchase status.

[0091] For example:

[0092] User A shares product X (user B clicks but does not purchase);

[0093] User C shares product Y (user B places an order and pays);

[0094] User D shares product Z (user B does not take any action).

[0095] That is, the first historical sharing information includes records of users A, C, D, products X, Y, Z, but product Y will be marked as high priority due to its high conversion rate.

[0096] In the embodiments of the present invention, on the basis of the existing sharing records of the target user, introducing the sharing data of other users can expand the scope of sharing data and increase the accuracy of sharing information.

[0097] Optionally, in the step of obtaining the second historical sharing information, the first user portrait corresponding to the target user and the second user portrait of the target sharing object can be determined; according to the first user portrait and the second user portrait, determine the second user group that has shared sharing information with the target sharing object within a preset time; based on the sharing information shared by the second user group with the target sharing object and the purchase information of the target sharing object for the sharing information, obtain the second historical sharing information.

[0098] In an embodiment of the present invention, the above user portrait can be determined based on the user's historical behavior data (such as browsing, collection, purchase, sharing records), demographic attributes (age, gender, region), interest tags (such as "technology enthusiasts", "maternal and child users"), etc.

[0099] The above user portrait is recorded in the user database. According to the user ID of the target user and the user ID of the target sharing object, the first user portrait corresponding to the target user and the second user portrait of the target sharing object can be found in the user database.

[0100] Specifically, within a preset time period, a set of users who have shared products with the target sharing object is determined. This set of users includes multiple candidate users (such as users C, D, and E).

[0101] According to the portrait similarity between the candidate users (such as C, D, E) and the target user (A), users with a similarity greater than the first preset similarity are selected as the second user group. Among them, the portrait similarity measurement criteria include consumption level, interest overlap rate, etc.

[0102] According to the portrait similarity between the candidate users (such as C, D, E) and the target sharing object (B), users with a similarity greater than the second preset similarity are selected as the second user group. Among them, the portrait similarity measurement criteria include consumption level, interest overlap rate, etc.

[0103] In a possible embodiment, according to the portrait similarity between the candidate users (such as C, D, E) and the target user (A) and the portrait similarity with the target sharing object (B), users with a comprehensive similarity greater than the third preset similarity are selected to join the second user group. Weights can be set according to business requirements. For example, the portrait similarity between the candidate user and the target user is 40%, and the portrait similarity between the candidate user and the target sharing object is 60%. The comprehensive similarity is calculated, and the top-N candidate users are selected as the second user group.

[0104] It should be noted that the above first user group includes the target user, and the second user group does not include the target user.

[0105] In an embodiment of the present invention, when there is no direct historical interaction between the target user and the sharing object, indirect data is screened through portrait similarity to avoid recommendation blind spots. For example, when sharing for the first time, other user data that is similar to the consumption habits of the target user and / or the target sharing object and matches the interests of the sharing object is used to improve the accuracy of the shared information.

[0106] Optionally, in the step of determining, according to the first user portrait and the second user portrait, the second user group that has shared sharing information with the target sharing object within a preset time, a third user group that has shared sharing information with the target sharing object within the preset time can be determined. The third user group includes multiple candidate users; according to multiple first similarities between the user portraits corresponding to each candidate user in the third user group and the first user portrait, and according to multiple second similarities between the user portraits corresponding to each candidate user in the third user group and the second user portrait, each first similarity corresponds to a candidate user, and each second similarity corresponds to a candidate user; based on the first similarity and the second similarity, the second user group is determined from multiple candidate users.

[0107] In the embodiment of the present invention, through the user database, within a preset time period, the user set that has shared goods with the target sharing object is found, that is, the third user group, and the third user group includes multiple candidate users.

[0108] Cosine similarity can be used to calculate multiple first similarities between the user portraits corresponding to each candidate user in the third user group and the first user portrait, and each candidate user's user portrait and the first user portrait are calculated once.

[0109] Similarly, cosine similarity can be used to calculate multiple second similarities between the user portraits corresponding to each candidate user in the third user group and the second user portrait, and each candidate user's user portrait and the second user portrait are calculated once.

[0110] Users with a first similarity greater than the first preset similarity can be selected as the second user group according to the first similarity between the candidate user and the target user, where the portrait similarity measurement criteria include consumption level, interest overlap rate, etc.

[0111] Users with a second similarity greater than the second preset similarity can be selected as the second user group according to the second similarity between the candidate user and the target sharing object, where the portrait similarity measurement criteria include consumption level, interest overlap rate, etc.

[0112] It is also possible to select users with a comprehensive similarity greater than the third preset similarity and add them to the second user group according to the first similarity between the candidate user and the target user and the second similarity between the candidate user and the target sharing object respectively. The weight can be set according to business requirements. For example, the weight of the first similarity between the candidate user and the target user is 40%, and the weight of the second similarity between the candidate user and the target sharing object is 60%. Calculate the comprehensive similarity and screen the top-N candidate users as the second user group.

[0113] In the embodiments of the present invention, candidate users with shopping styles similar to or the same as that of the target user can be screened out through the first similarity to serve as the second user group; candidate users with shopping styles similar to or the same as that of the target sharing object can be screened out through the second similarity to serve as the second user group; candidate users with shopping styles similar to or the same as that of the target user and the target sharing object can be screened out through the first similarity and the second similarity together to serve as the second user group, which can further improve the personalization degree of the personalized sharing information and enhance the user experience of the sharing object.

[0114] Optionally, in the step of generating the target sharing information corresponding to the target sharing commodity based on the commodity information of the target sharing commodity and the historical sharing information, if the historical sharing information is the first historical sharing information, the historical sharing information corresponding to the target user shall be the main, and the historical information corresponding to the first other user shall be the supplement to construct the first knowledge graph for the target sharing object; based on the first knowledge graph and the target sharing commodity information, the target sharing information corresponding to the target sharing commodity is generated.

[0115] In the embodiments of the present invention, with the historical sharing information corresponding to the target user as the core node, the historical sharing information corresponding to the first other user as the auxiliary node, and the user behavior and commodity attributes as the association relationships between the nodes, the first knowledge graph is constructed.

[0116] For example, user A shares commodity X (sports shoes), and user B clicks but does not purchase;

[0117] User C shares commodity Y (sports socks), and user B purchases;

[0118] User D shares commodity Z (running shoes), and user B has no operation.

[0119] The first knowledge graph is constructed as follows:

[0120] Core node: User A (shares commodity X)

[0121] Association relationship 1: User D → User A (sharing of similar commodities, the association value is the ratio of the number of times user A and user D share commodity X to the number of times they share similar commodities (similar commodities to commodity X)).

[0122] Association relationship 2: User C → User A (sharing of complementary commodities, the association value is the ratio of the number of times user A and user C share commodity X to the number of times they share complementary commodities (complementary commodities to commodity X)).

[0123] After obtaining the first knowledge graph, the association between the historical sharing commodity and the target commodity can be mined through the multi-dimensional relationship mining of the knowledge graph, and the behavioral association between users can be mined, so as to generate the sharing information of the target commodity that is more in line with the target sharing user.

[0124] Specifically, the construction of the above first knowledge graph is only based on the target user and the first other user, which can reduce the data volume of the knowledge graph and improve the calculation speed of the first knowledge graph.

[0125] In a possible embodiment, after obtaining the first knowledge graph, the first knowledge graph and the product information of the target shared product can be used as the input of a large language model (LLM). Using prompt engineering, the large language model is prompted to generate corresponding sharing information according to the input first knowledge graph and the product information of the target shared product, with the number of words not exceeding N, where N is set by the user according to needs. The above large language model can be a commercial large language model (such as GPT, Wenxin Yiyan, Tongyi Qianwen, etc.), which is called through an interface, or a self-trained large language model, which is obtained after training with the received product information, the first knowledge graph, and the sharing information as training corpora.

[0126] Optionally, in the step of generating the target sharing information corresponding to the target shared product based on the product information of the target shared product and the historical sharing information, if the historical sharing information is the second historical sharing information, then the historical information corresponding to the second other user is used to construct a second knowledge graph for the target sharing object; based on the second knowledge graph and the target shared product information, the target sharing information corresponding to the target shared product is generated.

[0127] In the embodiment of the present invention, when it is determined that the target sharing object has not received the sharing information of the target user within a preset time period, the system constructs the second knowledge graph according to the second historical sharing information.

[0128] Among them, the core node of the second knowledge graph is the target product, and the associated nodes are the historical sharing information corresponding to the second user group. The association relationships can be collaborative product association and group behavior association. The collaborative product association can be complementary relationship (such as mobile phone and charger), substitution relationship (such as similar products of different brands), and matching relationship (such as shirt and tie). Different relationships correspond to different association values. The group behavior association can be the conversion behavior of the target sharing object to the products shared by other users, such as frequently clicking on a certain type of product, purchasing a shared product, etc.

[0129] For example, for the second historical sharing information as follows: User C shares product P (smartphone), and User B clicks but does not purchase;

[0130] User E shares product Q (wireless charger), and User B purchases;

[0131] User D shares product R (phone case of the same brand), and User B takes no action.

[0132] The second knowledge graph is constructed as follows:

[0133] Core node: Target product S (the smartphone shared by User A).

[0134] Association relationship 1: Complementary product → Product Q (the wireless charger shared by User E).

[0135] Association relationship 2: Substitute product → Product P (the smartphone shared by User C).

[0136] Furthermore, if the product shared by the second user group has a synergistic relationship (matching relationship) with the target product, and the target sharing object has a purchase behavior, then a group behavior label is generated, such as "User XX shared the XX product that matches the XX accessory you purchased. Click to view".

[0137] If the conversion rate of the target sharing object for the synergistic product is high, then an associated promotion is designed for the target product, such as "User XX shared the XX mobile phone he purchased. Now, when you purchase the XX mobile phone, you will get a charger for free".

[0138] In the embodiment of the present invention, when there is no historical sharing record of the target user, the group behavior data is used to fill the information gap to avoid the fixation of sharing content. By identifying the complementary and substitution relationships between products through the second knowledge graph, cross-product information sharing is realized, further improving the user experience.

[0139] As Figure 2 shown, the embodiment of the present invention provides a product information sharing device, and the product information sharing device includes:

[0140] A receiving module 201, configured to receive a sharing request of a target user, where the sharing request includes a target sharing object and product information of a target sharing product;

[0141] An obtaining module 202, configured to obtain historical sharing information received by the target sharing object within a preset time period, where the historical sharing information includes product information of a historical sharing product and purchase information of the historical sharing product;

[0142] A generating module 203, configured to generate target sharing information corresponding to the target sharing product based on the product information of the target sharing product and the historical sharing information;

[0143] A sharing module 204, configured to share the target sharing information with the target sharing object in the form of a link.

[0144] Optionally, the obtaining module 202 is further configured to query, within the preset time period, whether the target sharing object has received historical sharing information shared by the target user; if the target sharing object has received the historical sharing information shared by the target user, obtain first historical sharing information, where the first historical sharing information includes the historical sharing information shared by the target user with the target sharing object and the historical sharing information shared by a first other user with the target object; if the target sharing object has not received the historical sharing information shared by the target user, obtain second historical sharing information, where the second historical sharing information includes the historical sharing information shared by a second other user with the target sharing object.

[0145] Optionally, the obtaining module 202 is further configured to determine a first user group that has shared sharing information with the target sharing object within the preset time, where the first user group includes the target user; based on the sharing information shared by the first user group with the target sharing object and the purchase information of the target sharing object for the sharing information, obtain first historical sharing information.

[0146] Optionally, the obtaining module 202 is further configured to determine a first user portrait corresponding to the target user and a second user portrait of the target sharing object; according to the first user portrait and the second user portrait, determine a second user group that has shared sharing information with the target sharing object within the preset time; based on the sharing information shared by the second user group with the target sharing object and the purchase information of the target sharing object for the sharing information, obtain second historical sharing information.

[0147] Optionally, the obtaining module 202 is further configured to determine a third user group that has shared sharing information with the target sharing object within the preset time, where the third user group includes multiple candidate users; according to multiple first similarities between the user portraits corresponding to each candidate user in the third user group and the first user portrait, and according to multiple second similarities between the user portraits corresponding to each candidate user in the third user group and the second user portrait, each first similarity corresponds to one candidate user, and each second similarity corresponds to one candidate user; based on the first similarity and the second similarity, determine a second user group from multiple candidate users.

[0148] Optionally, the generating module 203 is further configured to, if the historical sharing information is the first historical sharing information, construct a first knowledge graph for the target sharing object with the historical sharing information corresponding to the target user as the main and the historical information corresponding to the first other user as the supplement; and generate the target sharing information corresponding to the target sharing commodity based on the first knowledge graph and the target sharing commodity information.

[0149] Optionally, the generating module 203 is further configured to, if the historical sharing information is the second historical sharing information, construct a second knowledge graph for the target sharing object with the historical information corresponding to the second other user; and generate the target sharing information corresponding to the target sharing commodity based on the second knowledge graph and the target sharing commodity information.

[0150] As Figure 3 shown, an embodiment of the present invention further provides an electronic device, including a processor, and the above-mentioned processor can execute any one of the above-mentioned commodity information sharing methods.

[0151] Specifically, it includes a processor 301 and a memory 302, and a computer program for executing the commodity information sharing method stored on the memory 302 and capable of running on the processor 301, where:

[0152] The processor 301 runs the calculator program of the commodity information sharing method stored in the memory 302 and executes the following steps:

[0153] Receive a sharing request from a target user, where the sharing request includes a target sharing object and commodity information of a target sharing commodity;

[0154] Obtain the historical sharing information received by the target sharing object within a preset time period, where the historical sharing information includes commodity information of a historical sharing commodity and purchase information of the historical sharing commodity;

[0155] Generate the target sharing information corresponding to the target sharing commodity based on the commodity information of the target sharing commodity and the historical sharing information;

[0156] Share the target sharing information in the form of a link to the target sharing object.

[0157] Optionally, the obtaining the historical sharing information received by the target sharing object within a preset time period executed by the processor 301 includes:

[0158] Within the preset time period, query whether the target sharing object has received the historical sharing information shared by the target user;

[0159] If the target sharing object has received the historical sharing information shared by the target user, obtain the first historical sharing information, where the first historical sharing information includes the historical sharing information shared by the target user to the target sharing object and the historical sharing information shared by the first other user to the target object;

[0160] If the target sharing object has not received the historical sharing information shared by the target user, obtain the second historical sharing information, where the second historical sharing information includes the historical sharing information shared by the second other user to the target sharing object.

[0161] Optionally, the obtaining of the first historical sharing information executed by the processor 301 includes:

[0162] Determine the first user group that has shared sharing information to the target sharing object within the preset time, where the first user group includes the target user;

[0163] Based on the sharing information shared by the first user group to the target sharing object and the purchase information of the target sharing object for the sharing information, obtain the first historical sharing information.

[0164] Optionally, the obtaining of the second historical sharing information executed by the processor 301 includes:

[0165] Determine the first user portrait corresponding to the target user and the second user portrait of the target sharing object;

[0166] According to the first user portrait and the second user portrait, determine the second user group that has shared sharing information to the target sharing object within the preset time;

[0167] Based on the sharing information shared by the second user group to the target sharing object and the purchase information of the target sharing for the sharing information, obtain the second historical sharing information.

[0168] Optionally, the determining of the second user group that has shared sharing information to the target sharing object within the preset time according to the first user portrait and the second user portrait executed by the processor 301 includes:

[0169] Determine the third user group that has shared sharing information to the target sharing within the preset time, where the third user group includes multiple candidate users;

[0170] Based on multiple first similarities between the user portraits corresponding to each candidate user in the third user group and the first user portrait, and based on multiple second similarities between the user portraits corresponding to each candidate user in the third user group and the second user portrait, each of the first similarities corresponds to one of the candidate users, and each of the second similarities corresponds to one of the candidate users;

[0171] Based on the first similarity and the second similarity, determine a second user group from multiple candidate users.

[0172] Optionally, the generating, by the processor 301, of the target sharing information corresponding to the target sharing commodity based on the commodity information of the target sharing commodity and the historical sharing information includes:

[0173] If the historical sharing information is the first historical sharing information, construct a first knowledge graph for the target sharing object mainly based on the historical sharing information of the target user and supplemented by the historical information of the first other user;

[0174] Generate the target sharing information corresponding to the target sharing commodity based on the first knowledge graph and the target sharing commodity information.

[0175] Optionally, the generating, by the processor 301, of the target sharing information corresponding to the target sharing commodity based on the commodity information of the target sharing commodity and the historical sharing information includes:

[0176] If the historical sharing information is the second historical sharing information, construct a second knowledge graph for the target sharing object based on the historical information of the second other user;

[0177] Generate the target sharing information corresponding to the target sharing commodity based on the second knowledge graph and the target sharing commodity information.

[0178] The embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it realizes each process of the commodity information sharing method provided by the embodiment of the present invention and can achieve the same technical effect. To avoid repetition, it will not be described here again.

[0179] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above various methods. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM), etc.

[0180] The above-disclosed are only the preferred embodiments of the present invention. Of course, the scope of the rights of the present invention cannot be limited thereby. Therefore, equivalent changes made according to the claims of the present invention still fall within the scope covered by the present invention.

Claims

1. A method for sharing commodity information, characterized in that, The method includes the following steps: Receiving a sharing request from a target user, where the sharing request includes a target sharing object and product information of a target sharing product; Obtaining historical sharing information received by the target sharing object within a preset time period, where the historical sharing information includes product information of historical sharing products and purchase information of historical sharing products; Generating target sharing information corresponding to the target sharing product based on the product information of the target sharing product and the historical sharing information; Sharing the target sharing information in the form of a link with the target sharing object.

2. The method for sharing product information according to claim 1, wherein, The obtaining of the historical sharing information received by the target sharing object within a preset time period includes: Within the preset time period, querying whether the target sharing object has received historical sharing information shared by the target user; If the target sharing object has received historical sharing information shared by the target user, obtaining first historical sharing information, where the first historical sharing information includes historical sharing information shared by the target user with the target sharing object and historical sharing information shared by a first other user with the target object; If the target sharing object has not received historical sharing information shared by the target user, obtaining second historical sharing information, where the second historical sharing information includes historical sharing information shared by a second other user with the target sharing object.

3. The method for sharing product information according to claim 2, wherein The obtaining of the first historical sharing information includes: Determining a first user group that has shared sharing information with the target sharing object within the preset time period, where the first user group includes the target user; Obtaining the first historical sharing information based on the sharing information shared by the first user group with the target sharing object and the purchase information of the target sharing object for the sharing information.

4. The method for sharing product information according to claim 2, wherein, The obtaining of the second historical sharing information includes: Determining a first user portrait corresponding to the target user and a second user portrait of the target sharing object; Determining a second user group that has shared sharing information with the target sharing object within the preset time period according to the first user portrait and the second user portrait; Obtaining the second historical sharing information based on the sharing information shared by the second user group with the target sharing object and the purchase information of the target sharing object for the sharing information.

5. The method for sharing product information according to claim 4, wherein The determining of the second user group that has shared sharing information with the target sharing object within the preset time period according to the first user portrait and the second user portrait includes: Determining a third user group that has shared sharing information with the target sharing within the preset time period, where the third user group includes a plurality of candidate users; According to a plurality of first similarities between the user portraits corresponding to each candidate user in the third user group and the first user portrait, and according to a plurality of second similarities between the user portraits corresponding to each candidate user in the third user group and the second user portrait, each of the first similarities corresponds to a candidate user, and each of the second similarities corresponds to a candidate user; Determine a second user group from multiple candidate users based on the first similarity and the second similarity.

6. The commodity information sharing method according to any one of claims 2 to 5, characterized in that, The generating the target sharing information corresponding to the target sharing product based on the product information of the target sharing product and the historical sharing information includes: If the historical sharing information is the first historical sharing information, construct a first knowledge graph for the target sharing object mainly based on the historical sharing information of the target user and supplemented by the historical information of the first other user. Generate the target sharing information corresponding to the target sharing product based on the first knowledge graph and the target sharing product information.

7. The method for sharing product information according to any one of claims 2 to 5, characterized in that, The generating the target sharing information corresponding to the target sharing product based on the product information of the target sharing product and the historical sharing information includes: If the historical sharing information is the second historical sharing information, construct a second knowledge graph for the target sharing object based on the historical information of the second other user. Generate the target sharing information corresponding to the target sharing product based on the second knowledge graph and the target sharing product information.

8. A commodity information sharing device, characterized in that, The product information sharing device includes: A receiving module, configured to receive a sharing request from a target user, where the sharing request includes a target sharing object and product information of a target sharing product. An obtaining module, configured to obtain historical sharing information received by the target sharing object within a preset time period, where the historical sharing information includes product information of historical sharing products and purchase information of historical sharing products. A generating module, configured to generate target sharing information corresponding to the target sharing product based on the product information of the target sharing product and the historical sharing information. A sharing module, configured to share the target sharing information with the target sharing object in the form of a link.

9. An electronic device, characterized in that, including: A memory, a processor, and a computer program stored on the memory and executable on the processor, where when the processor executes the computer program, the steps in the product information sharing method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps in the product information sharing method according to any one of claims 1 to 7 are implemented.

Images