Object recommendation method and apparatus, device, and medium

Abstract

Provided are an object recommendation method and apparatus, a device, and a medium. The object recommendation method comprises: acquiring an order inquiry request sent by a user, the order inquiry request comprising: order inquiry information (S101); on the basis of the order inquiry information, acquiring target order information and a first object to be recommended, the target order information being any historical order information of the user (S102); on the basis of the target order information, acquiring a second object to be recommended (S103); and displaying the target order information, the first object to be recommended, and the second object to be recommended, so as to recommend objects to the user (S104). Targeted object recommendation is performed for users on the basis of their immediate needs, thereby improving object recommendation accuracy and improving user experience.

Description

Object recommendation method, device, apparatus and medium

[0001] This application claims priority to Chinese Patent Application No. 202410733365.9, filed on June 6, 2024, the disclosure of which is incorporated herein in its entirety as part of the present application. TECHNICAL FIELD

[0002] Embodiments of the present disclosure relate to an object recommendation method, device, apparatus and medium. BACKGROUND

[0003] With the development of the Internet, online shopping is more convenient and cost-effective than traditional offline shopping, and has become an important form of shopping at present. At present, when online shopping, e-commerce platforms usually recommend goods to users according to user behavior data, especially when users query orders, the e-commerce platforms will recommend goods to users according to the goods purchased by the users. However, the goods recommended to users by the traditional goods recommendation method cannot meet the immediate needs of users, resulting in inaccurate recommendations and affecting the user experience. SUMMARY

[0004] Embodiments of the present disclosure provide an object recommendation method, device, apparatus and medium, which realizes targeted object recommendation to users according to their immediate needs, thereby improving the accuracy of object recommendation and enhancing the user experience.

[0005] In a first aspect, embodiments of the present disclosure provide an object recommendation method, comprising:

[0006] obtaining an order query request sent by a user, the order query request comprising order query information;

[0007] obtaining target order information and a first object to be recommended according to the order query information, the target order information being any historical order information of the user;

[0008] obtaining a second object to be recommended according to the target order information;

[0009] displaying the target order information, the first object to be recommended and the second object to be recommended to recommend objects to the user.

[0010] In a second aspect, embodiments of the present disclosure provide an object recommendation device, comprising:

[0011] a request obtaining module configured to obtain an order query request sent by a user, the order query request comprising order query information;

[0012] An information obtaining module is configured to obtain target order information and a first to-be-recommended object according to the order query information, the target order information being any historical order information of the user;

[0013] An object obtaining module is configured to obtain a second to-be-recommended object according to the target order information.

[0014] An object recommendation module is configured to display the target order information, the first to-be-recommended object and the second to-be-recommended object to recommend an object to the user.

[0015] In a third aspect, an electronic device is provided, including:

[0016] A processor and a memory, the memory being configured to store a computer program, and the processor being configured to invoke and run the computer program stored in the memory to execute the object recommendation method as described in the foregoing first aspect.

[0017] In a fourth aspect, a computer readable storage medium is provided, configured to store a computer program, the computer program causing a computer to execute the object recommendation method as described in the foregoing first aspect.

[0018] In a fifth aspect, a computer program product containing program instructions is provided, the program instructions causing an electronic device to execute the object recommendation method as described in the foregoing first aspect when the program instructions are run on the electronic device. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings needed to be used in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present disclosure, and other drawings can be obtained by those skilled in the art without creative effort based on these drawings.

[0020] FIG. 1 is a flowchart of an object recommendation method provided by an embodiment of the present disclosure;

[0021] FIG. 2a is a schematic diagram of different display areas in an order query page provided by an embodiment of the present disclosure;

[0022] FIG. 2b is a schematic diagram of displaying target order information and to-be-recommended objects in different display areas provided by an embodiment of the present disclosure;

[0023] FIG. 2c is another schematic diagram of displaying target order information and to-be-recommended objects in different display areas provided by an embodiment of the present disclosure;

[0024] FIG. 3 is a flowchart of another object recommendation method according to an embodiment of the present disclosure;

[0025] FIG. 4 is a flowchart of still another object recommendation method according to an embodiment of the present disclosure;

[0026] FIG. 5 is a schematic block diagram of an object recommendation apparatus according to an embodiment of the present disclosure; and

[0027] FIG. 6 is a schematic block diagram of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0028] The technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative work fall within the scope of the present disclosure.

[0029] It should be noted that the terms "first", "second", and the like in the description, claims, and above-mentioned drawings of the present disclosure are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present disclosure described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product, or server including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to the process, method, product, or device.

[0030] In the embodiments of the present disclosure, the word "exemplary" or "for example" is used to mean serving as an example, instance, or illustration, any embodiment or aspect described as "exemplary" or "for example" in the embodiments of the present disclosure is not necessarily to be construed as preferred or advantageous over other embodiments or aspects. Rather, use of the word "exemplary" or "for example" is intended to present concepts in a concrete manner.

[0031] In the description of the embodiments of the present disclosure, "a plurality of" means two or more, that is, at least two, unless otherwise specified. "At least one" means one or more. "Any" means any one or any combination of more than one.

[0032] In order to facilitate understanding of the embodiments of the present disclosure, before describing the various embodiments of the present disclosure, some concepts involved in all embodiments of the present disclosure are first explained appropriately, as follows.

[0033] Order: In an e-commerce platform, each transaction generated by a user is recorded in the background system (such as a transaction database, etc.), and the transaction is an order, and each order has a unique number. The number here can be understood as an order number, etc.

[0034] Order query (order search): a kind of search system, the search information is generally text information, and the search content is the user's own historical order information.

[0035] Instant interest: refers to the theme or field that the user is interested in at the current moment, which is a manifestation of the user's short-term interest, and is usually triggered by the user's current situation, demand or behavior. For example, when the user inputs a keyword in the search engine, the user's instant interest is the content related to the keyword; when the user browses each specific topic on social media, the user's instant interest is the content related to the specific topic.

[0036] Long-term interest: refers to the theme or field that the user is interested in for a long time. These interests may be related to the user's occupation, hobbies, and lifestyle, and usually do not change significantly in a short period of time.

[0037] Short-term interest: refers to the theme or field that the user is interested in for a short period of time. Unlike long-term interest, short-term interest is usually caused by a specific event, situation or demand, and may change in a short period of time. For example, in the tourism field, the user's short-term interest may be a specific destination or activity; in the news field, the user's short-term interest may be a sudden event or hot topic, etc.

[0038] At present, when users shop online, e-commerce platforms usually recommend goods to users based on user behavior data. However, such goods recommended based on user behavior data cannot meet the user's instant demand, resulting in inaccurate recommendations and affecting the user's experience.

[0039] In order to solve the above technical problems, the present disclosure provides an object recommendation method, device, equipment and medium to solve the problem that goods recommended based on user behavior data cannot meet the user's instant demand, resulting in inaccurate recommendations and affecting the user's experience.

[0040] The technical solutions of the present disclosure will be described in detail below through some embodiments. The embodiments described below can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0041] FIG. 1 is a flowchart of an object recommendation method provided by an embodiment of the present disclosure. The object recommendation method of the present embodiment can be executed by an object recommendation device, which can be composed of hardware and / or software and can be integrated into an electronic device installed with an e-commerce platform. In the present disclosure, the electronic device can be, but is not limited to, a smartphone, a tablet computer, a desktop computer, a computer device, etc., and the type of the electronic device is not specifically limited herein.

[0042] As shown in FIG. 1, the method can include the following steps:

[0043] S101, obtaining an order query request sent by a user, the order query request including order query information.

[0044] It should be understood that the order query request refers to a request of the user to query his / her own order information on the e-commerce platform.

[0045] In addition, the order query request usually carries order query information, which refers to order search information input by the user, such as order name, order logistics number, or object name, etc.

[0046] It should be understood that the above-mentioned objects can be e-commerce search results of different genres, such as goods (items), video goods, e-commerce live streaming, e-commerce live streaming slices and playback, etc., and the present disclosure does not specifically limit the categories of the above-mentioned objects. The above-mentioned e-commerce search results of different genres can be represented as (Document, abbreviated as Doc).

[0047] In some optional embodiments, the user can generate various orders when performing a purchase operation on the e-commerce platform, and for these orders, the user can have a demand for order query. When the user needs to query any order, the user can input order query information in the search bar provided on the order query page of the e-commerce platform, so that the e-commerce platform can obtain the order query request sent by the user, and then perform order query and other operations based on the order query request. The order query information can be represented as query.

[0048] The above-mentioned various orders can include ongoing orders, completed orders, and closed orders. The ongoing orders can include to-be-shipped orders, to-be-paid orders, shipped orders, and refund / sales order, etc. The closed orders can include unpaid orders and refund cost orders, etc.

[0049] S102, obtaining target order information and a first to-be-recommended object according to the order query information, the target order information being any historical order information of the user.

[0050] It should be understood that the above-mentioned historical order information can be understood as any order information of various orders generated on the e-commerce platform.

[0051] The order information can include object identification information, store identification information, purchase quantity, object picture or video, order status, and object price, and the like. The object identification information can be understood as unique information of the object, such as an object name, and the like. Similarly, the store identification information can be understood as unique information of the store, such as a store name, and the like, which is not specifically limited herein.

[0052] In some optional embodiments, the present disclosure can first parse the obtained order query request to obtain order query information carried in the order query request. Then, according to the order query information, target order information is obtained from the order database, and according to the order query information, a first to-be-recommended object is obtained from the object database. The number of target order information and the first to-be-recommended object is at least one.

[0053] In the present disclosure, the order database can be understood as a database for storing various orders, and each order stored in the order database corresponds to an order identification information, so that the identity of the order can be uniquely identified by the order identification information.

[0054] The object database can be understood as a database for storing various types of e-commerce search results, and the object database is used to provide object information data.

[0055] In some optional embodiments, the present disclosure obtains target order information from the order database according to the order query information, and optionally queries an order including the order query information from the order database according to the order query information, or an order related to the order query information from the order database. Then, all the orders queried are determined as the target order information.

[0056] In some optional embodiments, the present disclosure obtains a first to-be-recommended object from the object database according to the order query information, and optionally queries an object including the order query information from the object database, and the object queried is taken as the first to-be-recommended object, or an object related to the order query information from the object database, and the object queried is taken as the first to-be-recommended object.

[0057] In consideration of the order query information can be a query statement with a certain character length, in order to accurately obtain the target order information and the first to-be-recommended object corresponding to the order query information, the disclosure can optionally first perform word segmentation and stop word removal on the order query information, to obtain at least one query keyword. The query keyword can be understood as the key information in the order query information. Then, the orders related to each query keyword are queried from the order database, and the queried orders are taken as the target order information. In addition, the objects related to each query keyword are also queried from the object database, and the queried objects are taken as the first to-be-recommended object.

[0058] That is, the disclosure can extract at least one query keyword from the order query information, and then obtain the target order information from the order database according to the query keyword, and obtain the first to-be-recommended object from the object database.

[0059] In consideration of the fact that the at least one query keyword extracted from the order query information and the objects in the object database do not match, resulting in the problem of missing recall of the first to-be-recommended object obtained from the object database according to each query keyword, thereby affecting the effect of recommending objects to the user.

[0060] Therefore, the disclosure can perform rewriting processing on each query keyword to obtain the synonym, the near-synonym, and / or the intent word corresponding to each query keyword. Then, the first to-be-recommended object is obtained from the object database according to each query keyword and the synonym, the near-synonym, and / or the intent word corresponding to each query keyword. The rewriting processing on each query keyword can also be referred to as the expansion processing of each query keyword.

[0061] For example, assuming that any query keyword is "cherry", the rewriting of the query keyword "cherry" can obtain the synonym "big cherry".

[0062] For another example, assuming that any query keyword is "clothes", the rewriting of the query keyword "clothes" can obtain the near-synonyms "clothing", "clothing", and "clothing", etc.

[0063] That is, the disclosure expands the rewritten word with high association degree with the user query demand for each query keyword, to perform object retrieval processing in the object database according to the rewritten word and each query keyword, to obtain more first to-be-recommended objects meeting the user query demand.

[0064] It should be understood that the synonym, the near-synonym and / or the intent word corresponding to each query keyword refer to at least one of the synonym, the near-synonym and the intent word corresponding to each query keyword. For example, the synonym corresponding to each query keyword; or the near-synonym corresponding to each query keyword; or the intent word corresponding to each query keyword; or the synonym and the near-synonym corresponding to each query keyword; or the near-synonym and the intent word corresponding to each query keyword; or the synonym and the near-synonym corresponding to each query keyword; or the synonym, the near-synonym and the intent word corresponding to each query keyword, and the present disclosure does not make specific limitations thereon.

[0065] S103, obtaining a second to-be-recommended object according to the target order information.

[0066] It should be understood that the order can include various information, such as object identification information, store identification information, object pictures or videos, and object prices. Therefore, the present disclosure can obtain object information from the target order information, and then obtain a second to-be-recommended object from the object database according to the object information. The number of the second to-be-recommended object is at least one.

[0067] The above object information can be at least one of object identification information and object pictures / videos.

[0068] In some optional embodiments, the second to-be-recommended object is obtained from the object database according to the object information, which can be optional. The object database is queried for an object related to the object information, and the queried object is taken as the second to-be-recommended object.

[0069] For example, assuming that the object information is an object name, and the object name is "cherry", all objects related to "cherry" are queried from the object database, and all the objects are taken as the second to-be-recommended object.

[0070] For another example, assuming that the object information is an object picture, and the object picture is a picture of trousers, the picture of trousers can be identified to obtain the information of the trousers in the picture, and then all objects related to the trousers are queried from the object database according to the information of the trousers, and all the objects are taken as the second to-be-recommended object.

[0071] S104, displaying the target order information, the first to-be-recommended object and the second to-be-recommended object to recommend the object to the user.

[0072] After obtaining the target order information, the first to-be-recommended object and the second to-be-recommended object corresponding to the order query information, the present disclosure can display the target order information, the first to-be-recommended object and the second to-be-recommended object in the order query page, so as to recommend multiple to-be-recommended objects associated with the order query information and the target order information to the user while the user queries the historical order information, and achieve the object recommendation accuracy and improve the user experience.

[0073] In some optional embodiments, the order query page can include multiple display areas, such as an order query result display area and a recommended object display area, as shown in FIG. 2a. Then, when the present disclosure displays the target order information, the first to-be-recommended object and the second to-be-recommended object, the target order information can be displayed in the order query result display area, and the first to-be-recommended object and the second to-be-recommended object can be displayed in the recommended object display area, as shown in FIG. 2b.

[0074] In some optional embodiments, the order query page can include multiple display areas, such as an order query result display area and a recommended object display area, as shown in FIG. 2a. Then, when the present disclosure displays the target order information, the first to-be-recommended object and the second to-be-recommended object, the target order information can be displayed in the order query result display area, and the first to-be-recommended object and the second to-be-recommended object can be displayed in the recommended object display area, as shown in FIG. 2b.

[0075] The technical solution disclosed in the embodiments of the present disclosure obtains the order query request sent by the user, obtains the target order information and the first to-be-recommended object according to the order query information in the order query request, then obtains the second to-be-recommended object according to the target order information, and displays the target order information, the first to-be-recommended object and the second to-be-recommended object to the user for object recommendation. The present disclosure can obtain the to-be-recommended object meeting the immediate demand of the user according to the immediate interest of the user represented by the order query information sent by the user and the target order information corresponding to the order query information, and display the obtained to-be-recommended object and the target order information to the user, so as to realize the targeted object recommendation according to the immediate demand of the user, improve the object recommendation accuracy, and improve the user experience.

[0076] In some optional embodiments, the order query request sent by the user can also include user identification information, so the present disclosure can also obtain the to-be-recommended object according to the user identification information. The following will be further explained in combination with FIG. 3.

[0077] As shown in FIG. 3, the method can include the following steps:

[0078] S201, acquire an order query request sent by a user, the order query request comprising: order query information and user identification information.

[0079] S202, acquire target order information and a first to-be-recommended object according to the order query information, the target order information being any historical order information of the user.

[0080] S203, acquire a second to-be-recommended object according to the target order information.

[0081] S204, acquire user historical behavior data authorized by the user according to the user identification information.

[0082] In the present disclosure, the user identification information can be understood as unique information of the user.

[0083] In some optional embodiments, after the order query request is parsed, the order query information and the user identification information can be acquired from the order query request. Furthermore, the present disclosure can acquire the user historical behavior data authorized by the user corresponding to the user identification information from the behavior log database according to the user identification information.

[0084] The user historical behavior data authorized by the user mentioned above refers to all interactive behavior data of the user on the e-commerce voucher, such as purchase behavior data, click behavior data, browsing behavior data, collection behavior data, and sharing behavior data, etc.

[0085] The behavior log database is used to store all interactive behavior data of each user on the e-commerce platform, such as purchase behavior data, etc.

[0086] It should be understood that, before using the technical solutions disclosed in the embodiments of the present disclosure, the type of personal information involved in the present disclosure, the use range, the use scenario, etc. should be informed to the user and the authorization of the user should be obtained through appropriate means according to relevant laws and regulations. For example, when responding to the active request of the user, a prompt information is sent to the user to explicitly prompt the user that the operation requested to be executed will need to acquire and use the personal information of the user. Thus, the user can voluntarily choose whether to provide the personal information to the software or hardware such as electronic device, application program, server or storage medium, etc. that executes the operation of the technical solutions of the present disclosure according to the prompt information.

[0087] As an optional but non-limiting implementation, in response to receiving the active request of the user, the manner of sending the prompt information to the user may be, for example, a pop-up window manner in which the prompt information can be presented in a textual manner. In addition, the pop-up window can also carry a selection control for the user to select "agree" or "disagree" to provide personal information to the electronic device. It can be understood that the above notification and obtaining of user authorization process is only illustrative and does not limit the implementation of the present disclosure. Other manners that meet the relevant laws and regulations can also be applied to the implementation of the present disclosure. It can be understood that the user personal information data involved in the technical solutions of the present disclosure (including but not limited to the data itself, the acquisition, storage and use of the data) should comply with the requirements of the relevant laws and regulations and related provisions, and should not violate public order and good customs.

[0088] S205, obtaining, from the object database, a third to-be-recommended object according to the user historical behavior data authorized by the user.

[0089] It can be understood that based on the user historical behavior data authorized by the user, the user's preferences or preferences, such as long-term interests and short-term interests, can be understood. Therefore, the present disclosure can determine the long-term interests and / or short-term interests of the user according to the user historical behavior data authorized by the user. Then, according to the long-term interests and / or short-term interests of the user, the third to-be-recommended object is obtained from the object database. The number of the third to-be-recommended object is at least one.

[0090] In some optional embodiments, when determining the long-term interests and / or short-term interests of the user, the user historical behavior data authorized by the user can be analyzed to determine the long-term interests of the user, such as objects that the user continuously pays attention to or is interested in for a long time, and the short-term interests of the user, such as objects that the user is interested in for a short time.

[0091] Further, all objects related to the long-term interests and / or short-term interests of the user are obtained from the object database, and all objects are taken as the third to-be-recommended object.

[0092] It should be noted that the execution order of obtaining the first to-be-recommended object and the third to-be-recommended object can be to execute obtaining the first to-be-recommended object first and then execute obtaining the third to-be-recommended object; or, it can also be to execute obtaining the third to-be-recommended object first and then execute obtaining the first to-be-recommended object; or, it can also be to execute obtaining the first to-be-recommended object and obtaining the third to-be-recommended object in parallel, and the present disclosure does not limit this.

[0093] S206, displaying the target order information, the first to-be-recommended object, the second to-be-recommended object and the third to-be-recommended object to recommend the object to the user.

[0094] Optionally, the disclosure can display the target order information, the first to-be-recommended object, the second to-be-recommended object and the third to-be-recommended object in an order query page.

[0095] In some optional embodiments, the order query page can include a plurality of display areas, such as an order query result display area and a recommended object display area, as shown in FIG. 2a. Then, when the disclosure displays the target order information, the first to-be-recommended object, the second to-be-recommended object and the third to-be-recommended object, the target order information can be displayed in the order query result display area, and the first to-be-recommended object, the second to-be-recommended object and the third to-be-recommended object can be displayed in the recommended object display area, as shown in FIG. 2c.

[0096] When the first to-be-recommended object, the second to-be-recommended object and the third to-be-recommended object are displayed in the recommended object display area, they can be displayed in the order of first displaying the first to-be-recommended object, then displaying the second to-be-recommended object, and finally displaying the third to-be-recommended object, or they can be displayed in the order of first displaying the second to-be-recommended object, then displaying the first to-be-recommended object, and finally displaying the third to-be-recommended object; or they can be displayed in a mixed display manner, and the disclosure does not make any limitation in this regard.

[0097] The technical solutions disclosed in the embodiments of the disclosure are as follows: an order query request sent by a user is acquired, target order information and a first to-be-recommended object are acquired according to order query information in the order query request, a second to-be-recommended object is acquired according to the target order information, and then the target order information, the first to-be-recommended object and the second to-be-recommended object are displayed to recommend objects to the user. The disclosure characterizes the instant interest of the user by the order query information sent by the user, acquires to-be-recommended objects that meet the instant demand of the user according to the instant interest of the user and the target order information corresponding to the order query information, and displays the to-be-recommended objects and the target order information acquired to the user, thereby realizing targeted object recommendation to the user according to the instant demand of the user, improving the accuracy of object recommendation, and improving the use experience of the user. In addition, the disclosure acquires user historical behavior data authorized by the user according to the user identifier information, determines the long-term interest and / or short-term interest of the user according to the user historical behavior data authorized by the user, and then performs more object recommendation to the user according to the long-term interest and / or short-term interest of the user on the basis of the order query information and the target order information, thereby providing more recommended objects that meet the demands of the user to the user according to the preferences of the user, improving the shopping experience of the user, and providing favorable conditions for improving the object conversion rate.

[0098] In some optional embodiments, in order to place the recommended object most relevant to the user's immediate needs in a front position to improve the object recommendation effect, after obtaining the recommended object, the disclosure can further determine the ranking score of each recommended object, and then sort the obtained multiple recommended objects according to the ranking score to obtain a sorting result, and then recommend the object to the user according to the sorting result. The above scheme provided by the embodiments of the disclosure will be described in detail below in combination with FIG. 4.

[0099] As shown in FIG. 4, the method can include the following steps:

[0100] S301, obtaining an order query request sent by a user, the order query request including order query information and user identification information.

[0101] S302, obtaining target order information and a first recommended object according to the order query information, the target order information being any historical order information of the user.

[0102] S303, obtaining a second recommended object according to the target order information.

[0103] S304, determining a ranking score of each recommended object.

[0104] In the disclosure, in addition to obtaining the first recommended object and the second recommended object, a third recommended object can also be obtained. The specific implementation manner of obtaining the third recommended object can be referred to the foregoing embodiments, which will not be described here in detail.

[0105] That is, the recommended object of the disclosure is the first recommended object and the second recommended object, or the first recommended object, the second recommended object and the third recommended object.

[0106] In some optional embodiments, determining the ranking score of each recommended object can include the following steps:

[0107] Step 11, determining a first relevance score between each recommended object and the order query information.

[0108] Optionally, the semantic similarity between each recommended object and the order query information can be calculated, and the semantic similarity is taken as the first relevance score between each recommended object and the order query information.

[0109] That is, the first relevance score is a semantic relevance score.

[0110] In some optional embodiments, determining the semantic relevance score between each recommended object and the order query information can include the following manner:

[0111] In a first mode, each to-be-recommended object and the order query information are input into the semantic correlation model as input data, so that the semantic correlation model processes each to-be-recommended object and the order query information to output a semantic correlation score between each to-be-recommended object and the order query information.

[0112] The semantic correlation model can be any model capable of determining semantic correlation between a to-be-recommended object and order query information, and the network structure of the semantic correlation model is not specifically limited in the present disclosure. That is, the semantic correlation model can be a trained model or a specially trained model.

[0113] In a second mode, a similarity algorithm is used to calculate the similarity between each to-be-recommended object and the order query information, and the similarity is taken as the first correlation score.

[0114] The similarity algorithm can be, but is not limited to, a cosine similarity algorithm and an edit distance similarity.

[0115] In step 12, a second correlation score between each to-be-recommended object and the target order information is determined.

[0116] Optionally, a style similarity between each to-be-recommended object and the target order information can be calculated, and the style similarity is taken as the second correlation score between each to-be-recommended object and the order query information.

[0117] That is, the second correlation score is a style correlation score.

[0118] In some optional embodiments, determining the style correlation score between each to-be-recommended object and the target order information can include the following modes:

[0119] In a first mode, each to-be-recommended object and the target order information are input into the style correlation model as input data, so that the style correlation model processes each to-be-recommended object and the target order information to output a style correlation score between each to-be-recommended object and the target order information.

[0120] The style correlation model can be any model capable of determining style correlation between a to-be-recommended object and target order information, and the network structure of the style correlation model is not specifically limited in the present disclosure. That is, the style correlation model can be a trained model or a specially trained model.

[0121] In a second mode, a similarity algorithm is used to calculate the similarity between each to-be-recommended object and the target order information, and the similarity is taken as the second correlation score.

[0122] The similarity algorithm can be, but is not limited to, a cosine similarity algorithm and an edit distance similarity.

[0123] Step 13, determining the conversion score, the quality score and the price score of each to-be-recommended object.

[0124] In the present disclosure, the conversion score includes the click rate and the conversion rate.

[0125] In some optional embodiments, each to-be-recommended object, order query information, target order information and user historical behavior data authorized by the user can be input into the conversion prediction model as input data, so as to process and analyze each to-be-recommended object, order query information, target order information and user historical behavior data authorized by the user through the conversion prediction model, and output the conversion score of each to-be-recommended object.

[0126] The conversion score of each to-be-recommended object is specifically calculated according to the click rate and the conversion rate. As an optional implementation manner, the conversion score can be a product of the click rate and the conversion rate.

[0127] It should be noted that the conversion prediction model can be any model capable of determining the conversion score of the to-be-recommended object, and the network structure of the conversion prediction model is not limited in the present disclosure.

[0128] In some optional embodiments, the quality score of each to-be-recommended object can be determined by obtaining evaluation information, return condition, sales condition and store evaluation information of each to-be-recommended object, and inputting these data into the quality prediction model to output the quality score of each to-be-recommended object through the quality prediction model. The quality prediction model can be any network model capable of predicting the quality of the to-be-recommended object, and the present disclosure does not make any limitation thereon.

[0129] In some optional embodiments, the price score of each to-be-recommended object can be determined by determining the same type object of each to-be-recommended object, and then determining the price information of each to-be-recommended object in the same type object. Then, the price information of each to-be-recommended object is taken as the price score of each to-be-recommended object.

[0130] The same type object can be understood as a product of the same type as the to-be-recommended object or a product similar to the to-be-recommended object. That is, the same type object includes the same object or the similar object.

[0131] Step 14, determining the ranking score of each to-be-recommended object according to the first correlation score, the second correlation score, the conversion score, the quality score and the price score.

[0132] In some optional embodiments, the disclosure can fuse the first relevance score, the second relevance score, the conversion score, the quality score and the price score of each object to be recommended to obtain a comprehensive score corresponding to each object to be recommended, and take the comprehensive score as the ranking score of each object to be recommended.

[0133] As an optional implementation, the disclosure can add the first relevance score, the second relevance score, the conversion score, the quality score and the price score of each object to be recommended, and take the sum as the ranking score of each object to be recommended. Alternatively, the first relevance score, the second relevance score, the conversion score, the quality score and the price score of each object to be recommended can also be multiplied, and the product is taken as the ranking score of each object to be recommended.

[0134] Considering directly fusing the first relevance score, the second relevance score, the conversion score, the quality score and the price score of each object to be recommended to calculate the ranking score of each object to be recommended, it is easy to cause the ranking score to appear an extreme value, resulting in poor stability of object recommendation.

[0135] Therefore, before determining the ranking score of each object to be recommended, the disclosure can first convert the first relevance score, the second relevance score, the conversion score, the quality score and the price score of each object to be recommended respectively, so that the first relevance score, the second relevance score, the conversion score, the quality score and the price score of each object to be recommended are all in a fixed score interval. Then, the converted first relevance score, the second relevance score, the conversion score, the quality score and the price score of each object to be recommended are fused to obtain the ranking score of each object to be recommended, thereby improving the stability of object recommendation.

[0136] In some optional embodiments, the ranking score of each object to be recommended can be determined by the following formula:

[0137] Wherein, score i is the ranking score of the i th object to be recommended, is the first relevance score of the i th object to be recommended, is the second relevance score of the i th object to be recommended, is the conversion score of the i th object to be recommended, is the quality score of the i th object to be recommended, is the price score of the i th object to be recommended, β rel_1 and β rei_y are two adjustable parameters corresponding to the first relevance score, β rel_f and α rei_fβ and a are two adjustable parameters corresponding to the first correlation score h β and a are two adjustable parameters corresponding to the first correlation score h β and a are two adjustable parameters corresponding to the conversion score z β and a are two adjustable parameters corresponding to the conversion score z β and a are two adjustable parameters corresponding to the quality score j β and a are two adjustable parameters corresponding to the quality score j β and a are two adjustable parameters corresponding to the price score, and each adjustable parameter is set flexibly according to actual application requirements, which is not limited here.

[0138] It should be noted that the above indicates the implementation manner of the conversion processing on the first correlation score, the above indicates the implementation manner of the conversion processing on the second correlation score, the above indicates the implementation manner of the conversion processing on the conversion score, the above indicates the implementation manner of the conversion processing on the quality score, and the above indicates the implementation manner of the conversion processing on the price score.

[0139] S305, sorting the plurality of to-be-recommended objects according to the sorting scores to obtain a sorting result.

[0140] In some optional embodiments, the plurality of to-be-recommended objects are sorted to obtain a sorting result, and the plurality of to-be-recommended objects are sorted in descending order of the sorting scores.

[0141] It should be understood that when the to-be-recommended objects are the first to-be-recommended object and the second to-be-recommended object, the disclosure sorts the first to-be-recommended object and the second to-be-recommended object in descending order of the sorting scores to obtain a sorting result. When the to-be-recommended objects are the first to-be-recommended object, the second to-be-recommended object and the third to-be-recommended object, the disclosure sorts the first to-be-recommended object, the second to-be-recommended object and the third to-be-recommended object in descending order of the sorting scores to obtain a sorting result.

[0142] S306, displaying the target order information and the sorting result to recommend the objects to the user.

[0143] In the embodiments of the disclosure, the sorting result can be displayed in the recommended object display area.

[0144] The technical scheme disclosed by the embodiments of the present disclosure comprises: obtaining an order query request sent by a user, obtaining target order information and a first to-be-recommended object according to order query information in the order query request, then obtaining a second to-be-recommended object according to the target order information, and then displaying the target order information, the first to-be-recommended object and the second to-be-recommended object to recommend an object to the user. The present disclosure characterizes the instant interest of the user by the order query information sent by the user, obtains a to-be-recommended object that meets the instant demand of the user according to the instant interest of the user and the target order information corresponding to the order query information, and displays the obtained to-be-recommended object and the target order information to the user, thereby realizing targeted object recommendation to the user according to the instant demand of the user, improving the accuracy of object recommendation, and improving the user experience. In addition, the present disclosure determines the ranking score of each to-be-recommended object, ranks all to-be-recommended objects according to the ranking score to obtain a ranking result, and then displays the ranking result of the to-be-recommended object to the user, so as to realize the ranking of the most relevant recommended object to the instant demand of the user, so that the user can obtain the object that the user wants to purchase from the recommended object, thereby further improving the recommendation effect of the object.

[0145] With reference to FIG. 5, an object recommendation device provided by the embodiments of the present disclosure is described. As shown in FIG. 5, the object recommendation device 400 comprises: a request obtaining module 410, an information obtaining module 420, an object obtaining module 430 and an object recommendation module 440.

[0146] The request obtaining module 410 is configured to obtain an order query request sent by a user, wherein the order query request comprises order query information.

[0147] The information obtaining module 420 is configured to obtain target order information and a first to-be-recommended object according to the order query information, wherein the target order information is any historical order information of the user.

[0148] The object obtaining module 430 is configured to obtain a second to-be-recommended object according to the target order information.

[0149] The object recommendation module 440 is configured to display the target order information, the first to-be-recommended object and the second to-be-recommended object to recommend an object to the user.

[0150] In an optional implementation of the embodiments of the present disclosure, the information obtaining module 420 is specifically configured to:

[0151] extract at least one query keyword from the order query information;

[0152] obtain target order information from an order database and obtain a first to-be-recommended object from an object database according to each query keyword.

[0153] In an optional implementation of the embodiments of the present disclosure, the information obtaining module 420 is further configured to perform rewriting processing on each of the query keywords to obtain synonym words, near-synonym words and / or intent words corresponding to each of the query keywords.

[0154] The first to-be-recommended object is obtained from the object database according to each of the query keywords and the synonym words, the near-synonym words and / or the intent words corresponding to each of the query keywords.

[0155] In an optional implementation of the embodiments of the present disclosure, the object obtaining module 430 is specifically configured to:

[0156] obtain object information from the target order information;

[0157] obtain a second to-be-recommended object from the object database according to the object information.

[0158] In an optional implementation of the embodiments of the present disclosure, the order query request further includes user identification information, and the object obtaining module 430 is specifically configured to:

[0159] obtain user historical behavior data authorized by the user according to the user identification information;

[0160] obtain a third to-be-recommended object from the object database according to the user historical behavior data authorized by the user.

[0161] In an optional implementation of the embodiments of the present disclosure, the object obtaining module 430 is further configured to determine long-term interests and / or short-term interests of the user, and obtain the third to-be-recommended object from the object database according to the long-term interests and / or the short-term interests of the user.

[0162] In an optional implementation of the embodiments of the present disclosure, the object recommendation module 440 is specifically configured to:

[0163] display the target order information, the first to-be-recommended object, the second to-be-recommended object and the third to-be-recommended object to recommend the object to the user.

[0164] In an optional implementation of the embodiments of the present disclosure, the apparatus 400 further includes:

[0165] a score determining module configured to determine a ranking score of each to-be-recommended object;

[0166] a ranking module configured to rank a plurality of to-be-recommended objects according to the ranking scores to obtain a ranking result;

[0167] The objects to be recommended are either the first object to be recommended and the second object to be recommended, or the first object to be recommended, the second object to be recommended, and the third object to be recommended.

[0168] In one optional implementation of this disclosure, the score determination module is specifically used for:

[0169] Determine the first relevance score between each target item and the order query information;

[0170] Determine a second relevance score between each target object and the target order information;

[0171] Determine the conversion score, quality score, and price score for each item to be recommended;

[0172] A ranking score is determined for each object to be recommended based on the first relevance score, the second relevance score, the conversion score, the quality score, and the price score.

[0173] In one optional implementation of this disclosure, the object recommendation module 440 is specifically used for:

[0174] The target order information and the sorting results are displayed to recommend objects to the user.

[0175] It should be understood that the device embodiments and the foregoing method embodiments can correspond to each other, and similar descriptions can be referred to the method embodiments. To avoid repetition, they will not be repeated here. Specifically, the device 400 shown in FIG5 can execute the method embodiment corresponding to FIG1, and the foregoing and other operations and / or functions of each module in the device 400 are respectively to implement the corresponding processes in each method in FIG1. ​​For the sake of brevity, they will not be repeated here.

[0176] The apparatus 400 of this disclosure embodiment has been described above from the perspective of functional modules in conjunction with the accompanying drawings. It should be understood that this functional module can be implemented in hardware, in software instructions, or in a combination of hardware and software modules. Specifically, the steps of the first aspect method embodiment of this disclosure can be completed by integrated logic circuits in the processor's hardware and / or by software instructions. The steps of the first aspect method disclosed in this disclosure can be directly embodied as being executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. Optionally, the software module can be located in a mature storage medium in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the first aspect method embodiment described above.

[0177] FIG. 6 is a schematic block diagram of an electronic device according to an embodiment of the present disclosure. As shown in FIG. 6, the electronic device 500 can include a memory 510 and a processor 520, the memory 510 being configured to store a computer program and transmit the program code to the processor 520. In other words, the processor 520 can invoke and run the computer program from the memory 510 to implement the object recommendation method according to the first aspect of the present disclosure.

[0178] For example, the processor 520 can be configured to execute the above-mentioned object recommendation method according to the instructions in the computer program.

[0179] In some embodiments of the present disclosure, the processor 520 can include but is not limited to:

[0180] A general processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, and the like.

[0181] In some embodiments of the present disclosure, the memory 510 includes but is not limited to:

[0182] The non-volatile memory can be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically EPROM (EEPROM), or a flash memory. The volatile memory can be a Random Access Memory (RAM) used as an external cache. By way of example, and not limitation, many forms of RAM are available, such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDR SDRAM), Enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct Rambus RAM (DR RAM).

[0183] In some embodiments of the present disclosure, the computer program can be divided into one or more modules, which are stored in the memory 510 and executed by the processor 520 to complete the object recommendation method provided by the present disclosure. The one or more modules can be a series of computer program instruction segments capable of completing a specific function, which are used to describe the execution process of the computer program in the electronic device.

[0184] As shown in FIG. 6, the electronic device 500 can further include:

[0185] The transceiver 530 can be connected to the processor 520 or the memory 510.

[0186] The processor 520 can control the transceiver 530 to communicate with other devices, specifically, can send information or data to other devices, or receive information or data sent by other devices. The transceiver 530 can include a transmitter and a receiver. The transceiver 530 can further include an antenna, and the number of antennas can be one or more.

[0187] It should be understood that various components in the electronic device are connected through a bus system, wherein the bus system includes, in addition to a data bus, a power supply bus, a control bus, and a status signal bus.

[0188] The present disclosure also provides a computer storage medium, having stored thereon a computer program, which, when executed by a computer, enables the computer to perform the object recommendation method of the first aspect.

[0189] When implemented using software, the functions can be totally or partially executed by one or more computer program products. The computer program product includes one or more computer instructions. When loaded and executed by a computer, the computer program instructions totally or partially generate the processes or functions described in the embodiments of the present disclosure. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable apparatus. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center through a wired (for example, coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (for example, infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server, data center, etc. integrated with one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a digital video disc (DVD)), or a semiconductor medium (for example, a solid state disk (SSD)), etc.

[0190] Those skilled in the art can realize that the modules and algorithm steps of the examples described in combination with the embodiments disclosed in the present disclosure can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present disclosure.

[0191] In several embodiments provided in the present disclosure, it should be understood that the disclosed system, device and method can be implemented in other manners. For example, the described device embodiments are merely illustrative. For example, the division of the modules is merely logical function division. In actual implementation, a plurality of modules or components can be combined or integrated into another system, or some features can be ignored or not implemented. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between different modules can be indirect couplings or communication connections through some interfaces, devices or modules, and can be in electrical, mechanical or other forms.

[0192] The modules illustrated as separated components can or can not be physically separated, and the components illustrated as modules can or can not be physical modules, i.e., can be located in one place or distributed on a plurality of network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiments. For example, the functional modules in the various embodiments of the present disclosure can be integrated into a processing module, or each module can be physically present separately, or two or more modules can be integrated into one module.

[0193] In the embodiments of the present disclosure, the term "module" or "unit" refers to a computer program or a part of a computer program with a predetermined function, and works with other related parts to achieve a predetermined target, and can be implemented entirely or partially by using software, hardware (such as a processing circuit or a memory) or a combination thereof. Similarly, one processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be a part of an overall module or unit that includes the functions of the module or unit.

[0194] The above describes only specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical range disclosed in the present disclosure, which should be covered within the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims

1. A method for object recommendation, comprising: obtaining an order query request sent by a user, the order query request comprising order query information; obtaining target order information and first to-be-recommended objects according to the order query information, the target order information being any historical order information of the user; obtaining second to-be-recommended objects according to the target order information; displaying the target order information, the first to-be-recommended objects and the second to-be-recommended objects to recommend objects to the user.

2. The method of claim 1, wherein, The step of obtaining the target order information and the first to-be-recommended objects according to the order query information comprises: extracting at least one query keyword from the order query information; obtaining target order information from an order database and first to-be-recommended objects from an object database according to each query keyword. 3.The method of claim 2, further comprising: rewriting each query keyword to obtain synonyms, near-synonyms and / or intent words corresponding to each query keyword; obtaining first to-be-recommended objects from an object database according to each query keyword and synonyms, near-synonyms and / or intent words corresponding to each query keyword.

4. The method of any one of claims 1-3, wherein, The step of obtaining the second to-be-recommended objects according to the target order information comprises: obtaining object information from the target order information; obtaining second to-be-recommended objects from an object database according to the object information.

5. The method of any one of claims 1-4, wherein, The order query request further comprises user identification information, and the method further comprises: obtaining user historical behavior data according to the user identification information; obtaining third to-be-recommended objects from an object database according to the user historical behavior data.

6. The method of claim 5, wherein, The step of obtaining the third to-be-recommended objects from an object database according to the user historical behavior data comprises: determining long-term interests and / or short-term interests of the user; obtaining third to-be-recommended objects from an object database according to the long-term interests and / or short-term interests of the user. 7.The method of claim 5 or 6, further comprising: displaying the target order information, the first to-be-recommended objects, the second to-be-recommended objects and the third to-be-recommended objects to recommend objects to the user. 8.The method of any one of claims 1-7, further comprising: determining ranking scores of each to-be-recommended object; ranking a plurality of to-be-recommended objects according to the ranking scores to obtain a ranking result; wherein the to-be-recommended objects are the first to-be-recommended objects and the second to-be-recommended objects, or the first to-be-recommended objects, the second to-be-recommended objects and the third to-be-recommended objects.

9. The method of claim 8, wherein, The step of determining the ranking scores of each to-be-recommended object comprises: determining first relevance scores between each to-be-recommended object and the order query information; determining second relevance scores between each to-be-recommended object and the target order information; determining conversion scores, quality scores and price scores of each to-be-recommended object; determining ranking scores of each to-be-recommended object according to the first relevance scores, the second relevance scores, the conversion scores, the quality scores and the price scores.

10. The method of claim 8 or 9, wherein, The step of recommending objects to the user comprises: display the target order information and the ranking result to recommend the object to the user. 11.An object recommendation apparatus, comprising: a request acquisition module configured to acquire an order query request sent by a user, the order query request comprising order query information; an information acquisition module configured to acquire target order information and a first object to be recommended according to the order query information, the target order information being any historical order information of the user; an object acquisition module configured to acquire a second object to be recommended according to the target order information; an object recommendation module configured to display the target order information, the first object to be recommended and the second object to be recommended to recommend the object to the user. 12.An electronic device, comprising: a processor and a memory, wherein the memory stores a computer program, and the processor is configured to invoke and run the computer program stored in the memory to execute the object recommendation method according to any one of claims 1 to 10.

13. A computer readable storage medium storing a computer program, wherein, The computer program causes a computer to execute the object recommendation method according to any one of claims 1 to 10.

14. A computer program product comprising program instructions, wherein, The program instructions, when running on an electronic device, cause the electronic device to execute the object recommendation method according to any one of claims 1 to 10.

Images