Object recommendation method and device, equipment, storage medium and program product

Through multiple conversations and interactions, the initial problem is generated and dynamically adjusted, and the problem of low user portrait portrayal accuracy in the prior art is solved, which improves the accuracy and user experience of the recommendation system.

CN118886979APending Publication Date: 2024-11-01CHINA CONSTRUCTION BANK +1
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202410763363.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-06-13
Publication Date
2024-11-01

AI Technical Summary

Technical Problem

The existing recommendation system asks users questions through questions set in advance, resulting in low accuracy in user portrait portrayals, which in turn affects the accuracy of recommended content.

Method used

After the user logs in for the first time, the initial question is generated through multiple conversation interactions, and the questions are dynamically adjusted according to the user's answers and dialogue interaction information until the convergence conditions are met, and a more accurate user portrait is generated.

Benefits of technology

It improves the accuracy of user portraits, enhances the accuracy of recommending objects to users, and improves the user experience.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118886979A_ABST
    Figure CN118886979A_ABST
Patent Text Reader

Abstract

The embodiment of the invention provides an object recommendation method and device, equipment, a storage medium and a program product, and the method comprises the steps: determining multiple pieces of object information of multiple objects corresponding to a target application program after detecting that a target user logs in the target application program for the first time through terminal equipment; determining registration information of the target user in the target application program, generating an initial problem according to the multiple pieces of object information and the registration information, and sending the initial problem to the terminal equipment; receiving an initial answer corresponding to the initial question sent by the terminal equipment; according to the multiple pieces of object information and the initial answer, performing multiple dialogue interactions with the terminal equipment to obtain dialogue interaction information; and generating a user portrait of the target user according to the dialogue interaction information, determining a target object to be recommended to the target user in the plurality of objects according to the user portrait, and sending object information of the target object to the terminal equipment. When the content is recommended to the user through the object recommendation method, the accuracy of the recommended content is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to an object recommendation method, device, equipment, storage medium and program product. Background Art

[0002] The recommendation system can characterize the user's profile after the user logs into the software (for example, shopping software, entertainment software) for the first time, and recommend objects (products, entertainment information, etc.) to the user based on the user profile.

[0003] In the related art, after a user logs into the software for the first time, the user is asked questions set in advance, and the user's answer data is collected, and the user's user profile is portrayed based on the collected answer data. However, asking the user questions set in advance limits the understanding of the user, resulting in a low accuracy in the user profile portrayal, which in turn leads to a low accuracy in the content recommended to the user. Summary of the invention

[0004] The embodiments of the present application provide an object recommendation method, apparatus, device, storage medium and program product to solve the problem that when asking users questions set in advance, the accuracy of user portraits is low, which leads to low accuracy of content recommended to users.

[0005] In a first aspect, an embodiment of the present application provides an object recommendation method, the method comprising:

[0006] After detecting that a target user logs in to a target application for the first time through a terminal device, determining a plurality of object information of a plurality of objects corresponding to the target application;

[0007] Determine the registration information of the target user in the target application, generate an initial question according to the plurality of object information and the registration information, and send the initial question to the terminal device;

[0008] Receiving an initial answer corresponding to the initial question sent by the terminal device;

[0009] Perform multiple dialogue interactions with the terminal device according to the multiple object information and the initial answer to obtain dialogue interaction information;

[0010] A user portrait of the target user is generated according to the conversation interaction information, and a target object to be recommended to the target user is determined from the multiple objects according to the user portrait, and object information of the target object is sent to the terminal device.

[0011] In a possible implementation, performing multiple dialogue interactions with the terminal device according to the multiple object information and the initial answer to obtain dialogue interaction information includes:

[0012] Determine the (i+1)th question according to the plurality of object information, the first i questions and the first i answers, wherein the first answer is the initial answer;

[0013] Sending the i+1th question to the terminal device, and receiving the i+1th answer corresponding to the i+1th question;

[0014] Determining whether the dialogue interaction with the terminal device meets a convergence condition based on the first i+1 questions and the first i+1 answers;

[0015] The i is sequentially 1, 2, ... until the dialogue interaction satisfies the convergence condition, and the dialogue interaction information is obtained, wherein the dialogue interaction information includes multiple questions and an answer corresponding to each question.

[0016] In a possible implementation, determining the (i+1)th question according to the plurality of object information, the first i questions, and the first i answers includes:

[0017] Determine the matching degree between the target user and each object according to the plurality of object information, the first i questions and the first i answers;

[0018] Determine a candidate object from the multiple objects according to the matching degree between the target user and each object, wherein the matching degree between the target user and the candidate object is greater than or equal to a preset threshold;

[0019] The (i+1)th question is generated according to the object information of the object to be selected.

[0020] In a possible implementation, determining the matching degree between the target user and each object according to the plurality of object information, the first i questions, and the first i answers includes:

[0021] Performing semantic analysis on the first i questions and the first i answers to obtain conversation semantic information;

[0022] Determining preference information of the target user according to the conversation semantic information;

[0023] Associating and matching the preference information with the object information of each object to obtain a matching degree between the preference information and each object;

[0024] The matching degree between the preference information and each object is determined as the matching degree between the target user and each object.

[0025] In a possible implementation, determining whether the dialog interaction with the terminal device satisfies a convergence condition according to the first i+1 questions and the first i+1 answers includes:

[0026] Determining whether a conversation ending instruction sent by the terminal device is received, wherein the conversation ending instruction is an instruction input by the target user on the conversation interface of the terminal device for ending the conversation interaction;

[0027] If so, determining that the dialogue interaction with the terminal device satisfies the convergence condition;

[0028] If not, determine the time interval between each answer and the corresponding question, and the user emotion type corresponding to each answer, and determine whether the dialogue interaction with the terminal device meets the convergence conditions based on the time interval between each answer and the corresponding question, and the user emotion type corresponding to each answer.

[0029] In a possible implementation, determining whether the dialog interaction with the terminal device satisfies a convergence condition according to the time interval between each answer and the corresponding question and the user emotion type corresponding to each answer includes:

[0030] Determining the answer interest index of the target user according to the time interval between each answer and the corresponding question;

[0031] If the answer interest index is less than or equal to a preset index, and / or the user emotion type is a preset emotion type, it is determined that the dialogue interaction with the terminal device meets the convergence condition.

[0032] In a possible implementation, generating an initial question according to the plurality of object information and the registration information includes:

[0033] Predicting predicted user information of the target user based on the registration information;

[0034] Determining, according to the predicted user information and the plurality of object information, a predicted object of interest to the target user from among the plurality of objects;

[0035] The initial question is generated according to the object information of the prediction object and the prediction user information.

[0036] In a possible implementation, the method further includes:

[0037] Obtaining the target user's operation record on the target application;

[0038] The user portrait is updated according to the operation record.

[0039] In a second aspect, an embodiment of the present application provides an object recommendation device, the device comprising:

[0040] A detection module, configured to determine, after detecting that a target user logs into a target application for the first time through a terminal device, a plurality of object information of a plurality of objects corresponding to the target application;

[0041] a determination module, configured to determine the registration information of the target user in the target application, generate an initial question according to the plurality of object information and the registration information, and send the initial question to the terminal device;

[0042] A receiving module, configured to receive an initial answer corresponding to the initial question sent by the terminal device;

[0043] A dialogue interaction module, configured to perform multiple dialogue interactions with the terminal device according to the multiple object information and the initial answer, and obtain dialogue interaction information;

[0044] A generation module generates a user portrait of the target user based on the conversation interaction information, determines a target object to be recommended to the target user from among the multiple objects based on the user portrait, and sends object information of the target object to the terminal device.

[0045] In a possible implementation, the dialogue interaction module is specifically used to:

[0046] Determine the (i+1)th question according to the plurality of object information, the first i questions and the first i answers, wherein the first answer is the initial answer;

[0047] Sending the i+1th question to the terminal device, and receiving the i+1th answer corresponding to the i+1th question;

[0048] Determining whether the dialogue interaction with the terminal device meets a convergence condition based on the first i+1 questions and the first i+1 answers;

[0049] The i is sequentially 1, 2, ... until the dialogue interaction satisfies the convergence condition, and the dialogue interaction information is obtained, wherein the dialogue interaction information includes multiple questions and an answer corresponding to each question.

[0050] In a possible implementation, the dialogue interaction module is specifically used to:

[0051] Determine the matching degree between the target user and each object according to the plurality of object information, the first i questions and the first i answers;

[0052] Determine a candidate object from the multiple objects according to the matching degree between the target user and each object, wherein the matching degree between the target user and the candidate object is greater than or equal to a preset threshold;

[0053] The (i+1)th question is generated according to the object information of the object to be selected.

[0054] In a possible implementation, the dialogue interaction module is specifically used to:

[0055] Performing semantic analysis on the first i questions and the first i answers to obtain conversation semantic information;

[0056] Determining preference information of the target user according to the conversation semantic information;

[0057] Associating and matching the preference information with the object information of each object to obtain a matching degree between the preference information and each object;

[0058] The matching degree between the preference information and each object is determined as the matching degree between the target user and each object.

[0059] In a possible implementation, the dialogue interaction module is specifically used to:

[0060] Determining whether a conversation ending instruction sent by the terminal device is received, wherein the conversation ending instruction is an instruction input by the target user on the conversation interface of the terminal device for ending the conversation interaction;

[0061] If so, determining that the dialogue interaction with the terminal device satisfies the convergence condition;

[0062] If not, determine the time interval between each answer and the corresponding question, and the user emotion type corresponding to each answer, and determine whether the dialogue interaction with the terminal device meets the convergence conditions based on the time interval between each answer and the corresponding question, and the user emotion type corresponding to each answer.

[0063] In a possible implementation, the dialogue interaction module is specifically used to:

[0064] Determining the answer interest index of the target user according to the time interval between each answer and the corresponding question;

[0065] If the answer interest index is less than or equal to a preset index, and / or the user emotion type is a preset emotion type, it is determined that the dialogue interaction with the terminal device meets the convergence condition.

[0066] In a possible implementation, the determination module is specifically used for:

[0067] Predicting predicted user information of the target user based on the registration information;

[0068] Determining, according to the predicted user information and the plurality of object information, a predicted object of interest to the target user from among the plurality of objects;

[0069] The initial question is generated according to the object information of the prediction object and the prediction user information.

[0070] In a possible implementation, the device further includes an acquisition module, wherein the acquisition module is specifically configured to:

[0071] Obtaining the target user's operation record on the target application;

[0072] The user portrait is updated according to the operation record.

[0073] In a third aspect, an embodiment of the present application provides a terminal device, including:

[0074] at least one processor; and

[0075] a memory communicatively connected to the at least one processor; wherein,

[0076] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the object recommendation method described in any one of the first aspects.

[0077] In a fourth aspect, the present application provides a chip having a computer program stored thereon, wherein when the computer program is executed by the chip, the object recommendation method as described in any one of the first aspects is implemented.

[0078] In a fifth aspect, the present application provides a chip module having a computer program stored thereon, and when the computer program is executed by the chip module, the object recommendation method as described in any one of the first aspects is implemented.

[0079] In a sixth aspect, an embodiment of the present application provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable the computer to execute the object recommendation method described in any one of the first aspects.

[0080] In a seventh aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the object recommendation method described in any one of the first aspects.

[0081] The object recommendation method, device, equipment, storage medium and program product provided in the embodiments of the present application generate an initial question based on the target user's registration information and the object information of the target application, and use the initial question as the first question to start multiple dialogue interactions with the target user. The question of each dialogue interaction is related to the previous dialogue interaction, so that the dialogue interaction is more appropriate to the user's own situation. The dialogue interaction information obtained from the above dialogue interaction can better reflect the target user's own situation, generate a more accurate user portrait, and thus improve the accuracy of recommending objects to the target user based on the user portrait. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] In order to more clearly illustrate the technical solutions in the present application, a brief introduction will be given below to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0083] Figure 1 A schematic diagram of the system architecture provided for an embodiment of the present application;

[0084] Figure 2 A flowchart of an object recommendation method provided in an embodiment of the present application;

[0085] Figure 3 A flowchart of another object recommendation method provided in an embodiment of the present application;

[0086] Figure 4 A schematic diagram of the object recommendation process provided in an embodiment of the present application;

[0087] Figure 5 A schematic diagram of the structure of an object recommendation device provided in an embodiment of the present application;

[0088] Figure 6 A schematic diagram of the structure of another object recommendation device provided in an embodiment of the present application;

[0089] Figure 7 A schematic diagram of the structure of a terminal device provided in an embodiment of the present application.

[0090] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0091] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in the embodiments of this application will be clearly and completely described below in combination with the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0092] The method shown in the embodiment of the present application can be used to recommend content that the target user is interested in to the target user who logs in to the target application for the first time. For example, the target application includes but is not limited to: shopping system, entertainment system, social system, etc.

[0093] For ease of understanding, the following Figure 1 , the system architecture applicable to the embodiments of the present application is described.

[0094] Figure 1 This is a schematic diagram of the system architecture provided by the embodiment of this application. Figure 1 , including a terminal device and a server, wherein the terminal device is provided with a target application. The terminal device may be a mobile phone, a tablet, a computer, etc., the target application may be a shopping system, an entertainment system, a social system, and the server is a background server of the target application.

[0095] In actual application, the terminal device can interact with the server in a dialogue. For example, the terminal device 1 can interact with the server 1 in a dialogue.

[0096] For any target application, after the target user logs in to the target application for the first time through the terminal device, the server and the terminal device conduct multiple dialogue interactions to obtain dialogue interaction information. The server can generate a user profile of the target user based on the dialogue interaction information, and determine the target object recommended to the target user based on the user profile of the target user.

[0097] For example, assuming that target application 1 is set in terminal device 1, when target user 1 logs in to target application 1 for the first time through terminal device 1, server 1 performs multiple dialogue interactions with terminal device 1 to obtain dialogue interaction information 1. Server 1 can generate a user profile of target user 1 based on interactive dialogue information 1, and determine the target object recommended to target user 1 based on the user profile of target user 1.

[0098] It should be noted that Figure 1 It is just an example to illustrate a system architecture diagram, and it is not a limitation of the system architecture diagram.

[0099] In the related art, after the target user logs in to the target application for the first time through the terminal device, questions set in advance are asked to the target user to obtain answer information, and a user profile of the target user is generated based on the answer information, resulting in a low accuracy in generating the user profile of the target user, thereby affecting the accuracy in determining the recommended target object for the target user.

[0100] In an embodiment of the present application, after the target user logs in to the target application for the first time through the terminal device, multiple dialogue interactions can be carried out with the user. The questions in the first dialogue interaction are related to the user's registration information, and the questions in subsequent dialogue interactions are related to the user's previous dialogue interactions, so that the dialogue interaction is more relevant to the user's own situation. Based on such dialogue interactions, a more accurate user portrait can be generated, thereby improving the accuracy of recommending objects to users based on the user portrait.

[0101] The object recommendation method shown in the present application is described in detail below through specific embodiments. It should be noted that the following embodiments can exist independently or in combination with each other, and the same or similar contents will not be described repeatedly in different embodiments.

[0102] Figure 2 This is a flowchart of an object recommendation method provided in an embodiment of the present application. Figure 2 , the method may include:

[0103] S201: Detecting that a target user logs into a target application for the first time through a terminal device, and determining multiple object information of multiple objects corresponding to the target application.

[0104] The target application may be installed in the terminal device, and the user may log in to the application through the terminal device. The target application has its corresponding server.

[0105] The execution subject of the embodiment of the present application may be a server corresponding to the target application, or may be an object recommendation device set in the server. The object recommendation device may be implemented by software, or by a combination of software and hardware.

[0106] The objects corresponding to the target application may be: objects that can be displayed in the target application, objects that can be traded, etc. For example, if the target application is a shopping software, the multiple objects are items that can be traded in the shopping software. If the target application is a financial application, the multiple objects may be financial products. If the target application is a news software, the multiple objects may be news.

[0107] The object information may include object type, attribute information (price, color, shape, size, etc.), etc.

[0108] For example, assuming that the target application 1 is a shopping software, the objects corresponding to the target application are clothing, daily necessities, and electronic products, respectively. The multiple object information corresponding to clothing is price, style, and color, the multiple object information corresponding to daily necessities is price and material, and the multiple object information corresponding to electronic products is price and brand. When the target user 1 logs in to the shopping software for the first time through the terminal device 1, the price, style, and color information corresponding to clothing, the price and material information corresponding to daily necessities, and the price and brand information corresponding to electronic products in the shopping software are determined.

[0109] S202: Determine the registration information of the target user in the target application.

[0110] The registration information is the information filled in by the target user when registering the target application.

[0111] The registration information may include basic information of the user, such as user name, gender, age, region, etc.

[0112] For example, assuming that the information filled in by target user 1 when registering the target application is user name, date of birth information, and contact information, the registration information of target user 1 in target application 1 is determined to be user name, date of birth information, and contact information of target user 1.

[0113] S203: Generate an initial question based on multiple object information and registration information, and send the initial question to the terminal device.

[0114] The initial question is the question asked during the first conversation interaction with the target user.

[0115] The initial question may be generated in the following manner: predicting predicted user information of the target user based on registration information; determining the predicted object of interest to the target user from among multiple objects based on the predicted user information and multiple object information; generating the initial question based on the object information and predicted user information of the predicted object.

[0116] The predicted user information may be gender information, zodiac sign information, etc. of the predicted target user. The predicted object is an object that the predicted target user is interested in in the target application.

[0117] For example, suppose that the registration information of target user 1 includes user name information and date of birth information, and the predicted user information of target user 1 includes gender information, age information, and zodiac sign information. Target application 1 is a shopping software, and the multiple objects are clothing, jewelry, and electronic devices. The object information corresponding to clothing is style and color, the object information corresponding to jewelry is material and price, and the object information corresponding to electronic devices is brand.

[0118] The user name of target user 1 is Xiaomei, and her date of birth is May 4, 2004. It is predicted that the gender of target user 1 is female, the age is 20 years old, and the constellation is Taurus. Based on the gender, age, constellation and multiple object information (object information of clothing, jewelry, and electronic equipment) of target user 1, the predicted objects of interest to target user 1 are determined to be clothing and jewelry among clothing, jewelry, and electronic equipment. Based on the multiple object information corresponding to clothing and jewelry, as well as the gender information, age information, and constellation information of target user 1, generate initial question 1: Hello, young lady, in order to better understand your preferences, please help answer the following questions: Do you have a favorite or dislike clothing color? Are you allergic to or have a special preference for jewelry made of certain materials?

[0119] S204: Receive an initial answer corresponding to the initial question sent by the terminal device.

[0120] Among them, the initial answer is the answer corresponding to the initial question.

[0121] S205. Perform multiple dialogue interactions with the terminal device according to the multiple object information and the initial answer to obtain dialogue interaction information.

[0122] The dialogue interaction information includes multiple questions in the dialogue interaction process with the user and the corresponding answer to each question.

[0123] Multiple dialogue interactions may be performed with the terminal device in the following manner: determining the i+1th question according to multiple object information, the first i questions and the first i answers, wherein the first answer is the initial answer; sending the i+1th question to the terminal device, and receiving the i+1th answer corresponding to the i+1th question; determining whether the dialogue interaction with the terminal device meets the convergence condition according to the first i+1 questions and the first i+1 answers;

[0124] Here, i is 1, 2, ... in sequence until the dialogue interaction meets the convergence condition, and the dialogue interaction information is obtained, which includes multiple questions and the answer corresponding to each question.

[0125] For example, suppose i is 1, target application 1 is a shopping software, and multiple objects are clothing and jewelry. The object information corresponding to clothing is price and color, and the object information corresponding to jewelry is material and price. The first question is: Hello, young lady, in order to better understand your preferences, please help answer the following questions: Do you have a favorite or dislike color of women's clothing? Are you allergic to or have a special preference for jewelry made of certain materials? The first answer to the first question is: I like purple, green, and blue clothes, and I like jewelry made of gold and silver. Based on multiple object information: clothing color, style, jewelry material, price, the first question, and the first answer to the first question, generate the second question: What is your usual budget for buying clothing and jewelry? Do you have any brands or designers that you pay special attention to?

[0126] The second question is sent to terminal device 1, and the second answer corresponding to the second question is received. According to the first two questions and the first two answers, it is determined whether the dialogue interaction with terminal device 1 meets the convergence condition. If the dialogue interaction meets the convergence condition, dialogue interaction information 1 is obtained, and dialogue interaction information 1 includes the first question, the first answer corresponding to the first question, the second question, and the second answer corresponding to the second question.

[0127] S206. Generate a user portrait of the target user based on the conversation interaction information, determine a target object to be recommended to the target user from multiple objects based on the user portrait, and send object information of the target object to the terminal device.

[0128] Among them, user portrait represents a user preference model abstracted from conversation interaction information.

[0129] For example, assuming that target application 1 is a shopping software, and multiple objects in target application 1 are clothing, jewelry, electronic equipment, and household items, the dialogue interaction information 1 includes question 1, answer 1, question 2, and answer 2. Question 1 is: Hello, young lady, in order to better understand your preferences, please help answer the following questions: Do you have a favorite or dislike color of women's clothing, are you allergic to or have a special preference for jewelry made of certain materials? Answer 1 is: I like purple, green, and blue clothes, and I like jewelry made of gold and silver. Question 2 is: What is your usual budget for buying clothing and jewelry, and do you have a special brand or designer that you pay attention to? Answer 2 is: The budget for clothing is 500-1000, and the brand I pay attention to is brand X. The budget for jewelry is 1000-5000, and the brand I like is brand Y.

[0130] According to the conversation interaction information 1, the user profile 1 of the target user 1 is generated as follows: the user likes clothes of cool colors and brand X, and the acceptable price range is 500-1000; the user likes jewelry of gold and silver materials and brand Y, and the acceptable price range is 1000-5000.

[0131] According to the user portrait 1 of the target user 1, the target objects to be recommended to the target user 1 are determined to be clothing and jewelry among the multiple objects (clothing, jewelry, electronic equipment, household items) in the target application 1, and the object information of clothing and jewelry is sent to the terminal device 1.

[0132] After generating the user portrait of the target user, you can also obtain the target user's operation records in the target application and update the user portrait based on the operation records.

[0133] The operation records may include the target user's purchase, viewing, liking, blocking, and other behaviors of the target object in the target application, as well as the target user's search behavior in the target application.

[0134] For example, assuming that target application 1 is a shopping software, target user 1 recommends clothing and jewelry, and user profile 1 of target user 1 is: likes clothes of cool colors and brand X, and accepts a price range of 500-1000; likes jewelry of gold and silver materials and brand Y, and accepts a price range of 1000-5000. The operation record of target user 1 in target application 1 is obtained as target user 1 searches for sports equipment in target application 1, and has a high click rate for outdoor sports equipment of brand Z with a price range of 200-500. According to this operation record of target user 1, the user profile of target user 1 is updated based on user profile 1 as: likes clothes of cool colors and brand X, and accepts a price range of 500-1000; likes jewelry of gold and silver materials and brand Y, and accepts a price range of 1000-5000; likes outdoor sports equipment of brand Z, and accepts a price range of 200-500.

[0135] exist Figure 2 In the embodiment shown, an initial question is generated through multiple object information of the target application and the registration information of the target user, a dialogue interaction is started with the target user using the initial question, and the target user's answer is collected to obtain dialogue interaction information. A user profile of the target user is generated based on the dialogue interaction information, which improves the accuracy of the user profile of the target user, thereby improving the accuracy of determining the target object recommended to the target user based on the user profile.

[0136] Based on the above embodiments, Figure 3 The illustrated embodiment further illustrates the object recommendation method.

[0137] Figure 3 For a flow chart of another object recommendation method provided in an embodiment of the present application, see Figure 3 , the method may include:

[0138] S301. After detecting that a target user logs in to a target application for the first time through a terminal device, determine a plurality of object information of a plurality of objects corresponding to the target application.

[0139] It should be noted that the execution process of S301 can be found in Figure 2 The step S201 in the illustrated embodiment will not be described in detail here.

[0140] S302: Determine the registration information of the target user in the target application.

[0141] It should be noted that the execution process of S302 can be found in Figure 2 The step S202 in the illustrated embodiment will not be described in detail here.

[0142] S303: Generate an initial question based on multiple object information and registration information.

[0143] It should be noted that the execution process of S303 can be found in Figure 2 The step S203 in the illustrated embodiment will not be described in detail here.

[0144] S304: Send an initial question to the terminal device.

[0145] S305: Receive an initial answer corresponding to the initial question sent by the terminal device.

[0146] S306. Initialize i to 1.

[0147] S307: Determine the matching degree between the target user and each object according to the multiple object information, the first i questions and the first i answers.

[0148] Among them, the first answer is the initial answer.

[0149] The matching degree between the target user and each object indicates the target user's preference for each object in the target application, which can be expressed in the form of percentage or the like.

[0150] The matching degree between the target user and each object can be determined in the following way: semantic analysis is performed on the first i questions and the first i answers to obtain the conversation semantic information; the preference information of the target user is determined based on the conversation semantic information; the preference information is associated and matched with the object information of each object to obtain the matching degree between the preference information and each object; the matching degree between the preference information and each object is determined as the matching degree between the target user and each object.

[0151] For example, suppose i is 1, target application 1 is a shopping software, and multiple objects are clothing and jewelry. The object information corresponding to clothing is price and color, and the object information corresponding to jewelry is material and price. The first question is question 1, and the first answer is answer 1. Question 1 is: Hello, young lady, in order to better understand your preferences, please help answer the following questions: Do you have a favorite or dislike color of women's clothing? Do you have an allergy or special preference for jewelry made of certain materials? Answer 1 is: I like purple, green, and blue clothes, and I like jewelry made of gold and silver.

[0152] The first question and the first answer are semantically analyzed to obtain dialogue semantic information 1. According to dialogue semantic information 1, preference information 1 of target user 1 is determined as: cold-colored clothing and gold and silver jewelry. Preference information 1 is associated and matched with the object information corresponding to clothing and jewelry, and the matching degree between preference information 1 and clothing is 80%, and the matching degree between preference information 1 and jewelry is 68%. The matching degree between preference information 1 and clothing is 80% as the matching degree between target user 1 and clothing, and the matching degree between preference information 1 and jewelry is 68% as the matching degree between target user 1 and jewelry.

[0153] S308: Determine a candidate object from among multiple objects according to the matching degree between the target user and each object, and the matching degree between the target user and the candidate object is greater than or equal to a preset threshold.

[0154] The objects to be selected are objects that are likely to be recommended to the target user among all objects of the target application.

[0155] The preset threshold is a pre-set matching value between the target user and the object. When the matching degree between the target user and the object is greater than or equal to the preset threshold, the object is determined as a candidate object.

[0156] For example, assuming that the target application 1 is a shopping software, and the multiple objects in the target application 1 are clothing, jewelry, furniture, household goods, and electronic devices, the matching degree between the target user 1 and clothing is 70%, the matching degree between the target user 1 and jewelry is 85%, the matching degree between the target user 1 and furniture is 20%, the matching degree between the target user 1 and household goods is 65%, the matching degree between the target user 1 and electronic devices is 55%, and the preset threshold is 60%. According to the matching degree between the target user 1 and each object, the objects to be selected are determined to be clothing, jewelry, and household goods among the multiple objects of clothing, jewelry, furniture, household goods, and electronic devices.

[0157] S309: Generate the (i+1)th question according to the object information of the object to be selected.

[0158] For example, suppose i is 2, and the objects to be selected are clothing and jewelry. The object information corresponding to clothing is price, color, and style, and the object information corresponding to jewelry is price and material. Based on the object information of clothing and jewelry, the third question is generated: What style of clothes do you usually like, and what price range of jewelry do you prefer?

[0159] S310. Send the (i+1)th question to the terminal device.

[0160] S311. Receive the i+1th answer corresponding to the i+1th question.

[0161] S312: Determine whether the dialogue interaction with the terminal device meets the convergence condition based on the first i+1 questions and the first i+1 answers.

[0162] Whether the dialogue interaction with the terminal device meets the convergence condition can be determined in the following manner: judging whether a dialogue ending instruction sent by the terminal device is received, wherein the dialogue ending instruction is an instruction input by the target user in the dialogue interface of the terminal device for ending the dialogue interaction.

[0163] If so, it is determined that the dialogue interaction with the terminal device meets the convergence condition.

[0164] If not, determine the time interval between each answer and the corresponding question, and the user emotion type corresponding to each answer, and determine whether the dialogue interaction with the terminal device meets the convergence conditions based on the time interval between each answer and the corresponding question, and the user emotion type corresponding to each answer.

[0165] Based on the time interval between each answer and the corresponding question, and the user emotion type corresponding to each answer, the method for determining whether the dialogue interaction with the terminal device meets the convergence condition is as follows: based on the time interval between each answer and the corresponding question, determine the answer interest index of the target user; if the answer interest index is less than or equal to the preset index, and / or the user emotion type is the preset emotion type, then determine that the dialogue interaction with the terminal device meets the convergence condition.

[0166] The user emotion type refers to the emotion of the target user during the dialogue interaction process, which may include excitement, fun, surprise, irritability, anger, and other emotion types.

[0167] The interest index indicates the target user's interest in the question during the dialogue interaction process, and can be expressed in the form of percentage.

[0168] The preset index refers to the interest index value of the target user during the dialogue interaction process set in advance. When the interest index of the target user is less than or equal to the preset threshold, it is judged that the target user is not interested in the question.

[0169] Preset emotion types refer to emotion types that are set in advance, which can be negative emotions such as anger, irritability, and impatience.

[0170] For any answer, the time interval between the answer and the corresponding question refers to the time difference between the time when the terminal device receives the answer and the time when the terminal device displays the question. The larger the time interval, the less active the user is in answering the question, and the smaller the time interval, the more active the user is in answering the question.

[0171] The answer interest index can be determined in the following manner: the average time interval can be determined based on the time interval between each answer and the corresponding question, and the answer interest index can be determined based on the average time interval and a preset corresponding relationship, wherein the preset corresponding relationship includes multiple time intervals and the answer interest index corresponding to each time interval.

[0172] For example, assuming that the preset interest index is 50% and the preset emotion types are anger, irritability, and impatience, when interacting with terminal device 1, if a conversation ending instruction sent by terminal device 1 is received, it is determined that the conversation interaction with terminal device 1 meets the convergence condition.

[0173] During the dialogue interaction with terminal device 2, no dialogue end instruction sent by terminal device 2 was received, and the time intervals corresponding to each answer were 1 minute and 50 seconds respectively. The answer interest index of target user 2 was determined to be 70%, and the user emotion type corresponding to each answer was excitement and fun respectively. The answer interest index of target user 2 was greater than the preset index, and the emotion type of target user 2 was not the preset emotion type, then it was determined that the dialogue interaction with terminal device 1 did not meet the convergence conditions.

[0174] During the dialogue interaction with terminal device 3, no dialogue end instruction sent by terminal device 3 was received, and the time intervals corresponding to each answer were 2 minutes and 5 minutes respectively. The answer interest index of target user 3 was determined to be 30%, and the user emotion types corresponding to each answer were irritability and impatience respectively. The answer interest index of target user 3 was less than the preset index, and the emotion type of target user 3 was the preset emotion type. It was determined that the dialogue interaction with terminal device 3 met the convergence conditions.

[0175] If yes, execute S314.

[0176] If not, execute S313.

[0177] S313. Update i to i+1.

[0178] After S313, S307 is executed.

[0179] S314: Generate a user profile of the target user based on the conversation interaction information.

[0180] It should be noted that the execution process of S313 can be found in Figure 2 The step S206 in the illustrated embodiment will not be described in detail here.

[0181] S315. Determine a target object to be recommended to the target user from among multiple objects according to the user portrait.

[0182] It should be noted that the execution process of S314 can be found in Figure 2 The step S206 in the illustrated embodiment will not be described in detail here.

[0183] S316: Send object information of the target object to the terminal device.

[0184] exist Figure 3 In the embodiment shown, the i+1th question is determined based on the first i questions and the first i answers in the dialogue interaction with the target user, so that the user's preference information can be more accurately understood during the dialogue interaction, and the matching degree between the target user and multiple objects can be determined based on the user's preference information, thereby improving the accuracy of recommending objects to the target user. At the same time, the target user is provided with an opportunity to actively end the dialogue interaction, and the target user's emotions and feelings during the dialogue interaction are taken into consideration, thereby ensuring the user experience of the target user.

[0185] Based on any of the above embodiments, Figure 4 , the object recommendation process is explained through a specific embodiment.

[0186] Figure 4 This is a schematic diagram of the object recommendation process provided by the embodiment of the present application. Figure 4 In the embodiment shown in the figure, the target application is a shopping software as an example for description. Figure 4 After target user 1 logs in to target application 1 for the first time, it is determined that multiple objects corresponding to target application 1 are clothing, jewelry, electronic equipment, and shoes and hats. The object information corresponding to clothing is style, color, and price. The object information corresponding to jewelry is material and price. The object information corresponding to electronic equipment is brand and price. The object information corresponding to shoes and hats is color, style, and price. The registration information of target user 1 in target application 1 is determined as user name: Xiaomei, date of birth: May 2004, mobile phone number: 159…

[0187] According to the registration information of target user 1, the predicted user information of target user 1 is predicted to be gender information, age information, and region information. The gender information is female, the age information is 20 years old, and the region information is City A. According to the predicted user information of target user 1 and multiple object information of target application 1, it is determined that the predicted objects that target user 1 is interested in are: clothing, jewelry, shoes and hats. According to the object information of clothing, jewelry, shoes and hats and the gender information, age information and region information of target user 1, the initial question is generated: Hello, young lady, in order to better understand your preferences, please help answer the following questions: Do you have a favorite or dislike clothing color, are you allergic to or have a special preference for jewelry made of certain materials, and which color of shoes and hats do you prefer?

[0188] An initial question is sent to terminal device 1, and an initial answer corresponding to the initial question sent by terminal device 1 is received. The initial answer is: I like purple, green, and blue clothes, gold, silver jewelry, and white shoes and hats.

[0189] The first question and the first answer are semantically analyzed to obtain dialogue semantic information 1, and the preference information 1 of target user 1 is determined based on dialogue semantic information 1 as follows: cold-colored clothing, gold and silver jewelry, and light-colored shoes and hats. Preference information 1 is associated and matched with the object information of clothing, jewelry, and shoes and hats, and the matching degree between preference information 1 and clothing is 80%, the matching degree between preference information 1 and jewelry is 78%, and the matching degree between preference information 1 and shoes and hats is 40%. The matching degrees between preference information 1 and clothing, jewelry, and shoes and hats are used as the matching degrees between target user 1 and clothing, jewelry, and shoes and hats, respectively.

[0190] Assuming the preset threshold is 60%, the target objects are determined to be clothing and jewelry based on the matching degree between target user 1 and clothing, jewelry, and shoes and hats. And based on the object information of clothing and jewelry, the second question is generated: What is your usual budget for buying clothing and jewelry? Do you have any special brands or designers?

[0191] The second question is sent to terminal device 1, and the second answer corresponding to the second question sent by terminal device 1 is received. The second answer is: the clothing budget is 500-1000, the brand of interest is brand X, the jewelry budget is 1000-5000, and the favorite brand is brand Y.

[0192] It is determined that no instruction input by the target user 1 on the dialogue interface of the terminal device 1 for ending the dialogue interaction is received.

[0193] The time interval between the first answer and the question is 3 minutes, the time interval between the second answer and the second question is 5 minutes, the answer interest index of target user 1 is determined to be 50%, the preset index is 60%, the user emotion type of the first answer is impatience, the user emotion type of the second answer is irritation, and the preset emotion types are angry, irritation, and impatience. According to the answer interest index of target user 1 being less than the preset index and the user emotion type being the preset emotion type, it is determined that the dialogue interaction with terminal device 1 meets the convergence condition.

[0194] The dialogue interaction information 1 is obtained, and the dialogue interaction information 1 includes the first question, the first answer, the second question, and the second answer. Based on the dialogue interaction information 1, a user profile 1 of the target user 1 is generated: the user likes clothes of brand X in cool colors and accepts a price range of 500-1000; the user likes jewelry of brand Y in gold and silver materials and accepts a price range of 1000-5000.

[0195] According to the user portrait 1 of the target user 1, the target objects to be recommended to the target user 1 are determined to be clothing and jewelry among the multiple objects (clothing, jewelry, electronic equipment, shoes and hats) in the target application 1, and the object information of clothing and jewelry is sent to the terminal device 1.

[0196] Assume that target user 1 searches for sports equipment in application 1, and has a high click rate for outdoor sports equipment of brand Z with a price range of 200-500. According to this operation record of target user 1, the user profile of target user 1 is updated on the basis of user profile 1 as follows: he likes clothes of brand X with cool colors, and his acceptable price range is 500-1000; he likes jewelry of brand Y with gold and silver materials, and his acceptable price range is 1000-5000; he likes outdoor sports equipment of brand Z, and his acceptable price range is 200-500.

[0197] exist Figure 4 In the illustrated embodiment, the predicted object that the target user may be interested in is determined based on the predicted user information of the target user and multiple objects of the target application, and the initial question is generated based on the predicted user information and the object information of the predicted object, and the dialogue interaction begins. During the dialogue interaction, the form and details of the question are adjusted at any time based on the previous questions and answers, which can more accurately portray the user portrait of the target user and improve the accuracy of recommending objects to the target user. At the same time, the target user's emotions are taken into account during the dialogue process, which improves the target user's experience of the target application.

[0198] Figure 5 This is a schematic diagram of the structure of an object recommendation device provided in an embodiment of the present application. Figure 5 , the object recommendation device 10 may include:

[0199] A detection module 11 is used to determine multiple object information of multiple objects corresponding to the target application after detecting that the target user logs in to the target application for the first time through the terminal device;

[0200] A determination module 12, used to determine the registration information of the target user in the target application, and generate an initial question based on the multiple object information and the registration information, and send the initial question to the terminal device;

[0201] A receiving module 13, configured to receive an initial answer corresponding to an initial question sent by a terminal device;

[0202] A dialogue interaction module 14, configured to perform multiple dialogue interactions with the terminal device according to the multiple object information and the initial answer, and obtain dialogue interaction information;

[0203] The generation module 15 generates a user portrait of the target user according to the dialogue interaction information, determines a target object to be recommended to the target user from multiple objects according to the user portrait, and sends object information of the target object to the terminal device.

[0204] The object recommendation device provided in the embodiment of the present application can execute the technical solution shown in the above method embodiment, and its implementation principle and beneficial effects are similar, which will not be repeated here.

[0205] In a possible implementation, the dialogue interaction module 14 is specifically used to:

[0206] Determine the i+1th question according to the multiple object information, the first i questions and the first i answers, wherein the first answer is the initial answer;

[0207] Send the i+1th question to the terminal device and receive the i+1th answer corresponding to the i+1th question;

[0208] Determine whether the dialogue interaction with the terminal device meets the convergence condition based on the first i+1 questions and the first i+1 answers;

[0209] Here, i is sequentially 1, 2, ... until the dialogue interaction meets the convergence condition, and the dialogue interaction information is obtained, which includes multiple questions and the answer corresponding to each question.

[0210] In a possible implementation, the dialogue interaction module 14 is specifically used to:

[0211] Determine the matching degree between the target user and each object based on multiple object information, the previous i questions and the previous i answers;

[0212] According to the matching degree between the target user and each object, a candidate object is determined from multiple objects, and the matching degree between the target user and the candidate object is greater than or equal to a preset threshold;

[0213] Generate the i+1th question based on the object information of the object to be selected.

[0214] In a possible implementation, the dialogue interaction module 14 is specifically used to:

[0215] Perform semantic analysis on the first i questions and first i answers to obtain the conversation semantic information;

[0216] Determine the target user's preference information based on the conversation semantic information;

[0217] Associating and matching the preference information with the object information of each object to obtain the matching degree between the preference information and each object;

[0218] The matching degree between the preference information and each object is determined as the matching degree between the target user and each object.

[0219] In a possible implementation, the dialogue interaction module 14 is specifically used to:

[0220] Determining whether a conversation ending instruction sent by the terminal device is received, where the conversation ending instruction is an instruction input by the target user on the conversation interface of the terminal device for ending the conversation interaction;

[0221] If so, it is determined that the dialogue interaction with the terminal device meets the convergence condition;

[0222] If not, determine the time interval between each answer and the corresponding question, and the user emotion type corresponding to each answer, and determine whether the dialogue interaction with the terminal device meets the convergence conditions based on the time interval between each answer and the corresponding question, and the user emotion type corresponding to each answer.

[0223] In a possible implementation, the dialogue interaction module 14 is specifically used to:

[0224] Determine the target user's answer interest index based on the time interval between each answer and the corresponding question;

[0225] If the answer interest index is less than or equal to a preset index, and / or the user emotion type is a preset emotion type, it is determined that the dialogue interaction with the terminal device meets the convergence condition.

[0226] In a possible implementation, the determination module 12 is specifically configured to:

[0227] Predict the predicted user information of the target user based on the registration information;

[0228] Determining, based on the predicted user information and the plurality of object information, a predicted object of interest to the target user from among the plurality of objects;

[0229] Generate an initial question based on the object information of the prediction object and the prediction user information.

[0230] The object recommendation device provided in the embodiment of the present application can execute the technical solution shown in the above method embodiment, and its implementation principle and beneficial effects are similar, which will not be repeated here.

[0231] Figure 6 A schematic diagram of the structure of another object recommendation device provided in an embodiment of the present application, Figure 6 Based on the examples shown, see Figure 6 The device further includes an acquisition module 26, wherein the acquisition module 26 is specifically used for:

[0232] Obtain the target user's operation records on the target application;

[0233] Update user portrait based on operation records.

[0234] The object recommendation device provided in this embodiment can be used to execute the technical solution shown in the above method embodiment. Its implementation principle and technical effect are similar and will not be described in detail here.

[0235] Figure 7 A schematic diagram of the structure of a terminal device provided in an embodiment of the present application. Figure 7 As shown, the terminal device 30 may include: a memory 31 and at least one processor 32. Exemplarily, the memory 31 and at least one processor 32 are interconnected via a bus 33.

[0236] The memory 31 is used to store program instructions;

[0237] At least one processor 32 is used to execute the program instructions stored in the memory, so as to enable the terminal device 30 to execute the method shown in the above method embodiment.

[0238] Optionally, the processor may be a central processing unit (CPU), a graphics processing unit (GPU), other general-purpose processors, a digital signal processor (DSP), or an application-specific integrated circuit (ASIC). A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of the present application may be directly implemented as being executed by a hardware processor, or may be implemented by a combination of hardware and software modules in the processor.

[0239] The terminal device provided in the embodiment of the present application can execute the technical solution shown in the above method embodiment, and its implementation principle and beneficial effects are similar, which will not be repeated here.

[0240] An embodiment of the present application provides a non-transitory computer-readable storage medium storing computer instructions, wherein the non-transitory computer-readable storage medium storing computer instructions stores computer execution instructions, and when the computer execution instructions are executed by an electronic device, they are used to implement the object recommendation method involved in the above method embodiment.

[0241] An embodiment of the present application provides a computer program product, including a computer program, which, when executed by an electronic device, implements the object recommendation method involved in the above method embodiment.

[0242] An embodiment of the present application provides a chip having a computer program stored thereon. When the computer program is executed by the chip, the object recommendation method in the above method embodiment is implemented.

[0243] An embodiment of the present application provides a chip module, on which a computer program is stored. When the computer program is executed by the chip module, the object recommendation method in the above method embodiment is implemented.

[0244] All or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a readable memory. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned memory (storage medium) includes: read-only memory (English: read-only memory, abbreviated: ROM), RAM, flash memory, hard disk, solid state drive, magnetic tape (English: magnetic tape), floppy disk (English: floppy disk), optical disc (English: optical disc) and any combination thereof.

[0245] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable terminal device to generate a machine, so that the instructions executed by the processing unit of the computer or other programmable terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0246] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0247] These computer program instructions can also be loaded onto a computer or other programmable terminal device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0248] Obviously, those skilled in the art can make various changes and modifications to the embodiments of the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the embodiments of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. An object recommendation method, characterized in that: include: After detecting that a target user logs in to a target application for the first time through a terminal device, determining a plurality of object information of a plurality of objects corresponding to the target application; Determine the registration information of the target user in the target application, generate an initial question according to the plurality of object information and the registration information, and send the initial question to the terminal device; Receiving an initial answer corresponding to the initial question sent by the terminal device; Perform multiple dialogue interactions with the terminal device according to the multiple object information and the initial answer to obtain dialogue interaction information; A user portrait of the target user is generated according to the conversation interaction information, and a target object to be recommended to the target user is determined from the multiple objects according to the user portrait, and object information of the target object is sent to the terminal device.

2. The method according to claim 1, characterized in that According to the multiple object information and the initial answer, multiple dialogue interactions are performed with the terminal device to obtain dialogue interaction information, including: Determine the (i+1)th question according to the plurality of object information, the first i questions and the first i answers, wherein the first answer is the initial answer; Sending the i+1th question to the terminal device, and receiving the i+1th answer corresponding to the i+1th question; Determining whether the dialogue interaction with the terminal device meets a convergence condition based on the first i+1 questions and the first i+1 answers; The i is sequentially 1, 2, ... until the dialogue interaction satisfies the convergence condition, and the dialogue interaction information is obtained, wherein the dialogue interaction information includes multiple questions and an answer corresponding to each question.

3. The method according to claim 2, characterized in that Determining the (i+1)th question according to the plurality of object information, the first i questions and the first i answers includes: Determine the matching degree between the target user and each object according to the plurality of object information, the first i questions and the first i answers; Determine a candidate object from the multiple objects according to the matching degree between the target user and each object, wherein the matching degree between the target user and the candidate object is greater than or equal to a preset threshold; The (i+1)th question is generated according to the object information of the object to be selected.

4. The method according to claim 3, characterized in that Determining the matching degree between the target user and each object according to the plurality of object information, the first i questions and the first i answers, including: Performing semantic analysis on the first i questions and the first i answers to obtain conversation semantic information; Determining preference information of the target user according to the conversation semantic information; Associating and matching the preference information with the object information of each object to obtain a matching degree between the preference information and each object; The matching degree between the preference information and each object is determined as the matching degree between the target user and each object.

5. The method according to any one of claims 2 to 4, characterized in that: Determining whether the dialogue interaction with the terminal device satisfies a convergence condition according to the first i+1 questions and the first i+1 answers includes: Determining whether a conversation ending instruction sent by the terminal device is received, wherein the conversation ending instruction is an instruction input by the target user on the conversation interface of the terminal device for ending the conversation interaction; If so, determining that the dialogue interaction with the terminal device satisfies the convergence condition; If not, determine the time interval between each answer and the corresponding question, and the user emotion type corresponding to each answer, and determine whether the dialogue interaction with the terminal device meets the convergence conditions based on the time interval between each answer and the corresponding question, and the user emotion type corresponding to each answer.

6. The method according to claim 5, characterized in that Determining whether the dialogue interaction with the terminal device meets a convergence condition according to the time interval between each answer and the corresponding question and the user emotion type corresponding to each answer includes: Determining the answer interest index of the target user according to the time interval between each answer and the corresponding question; If the answer interest index is less than or equal to a preset index, and / or the user emotion type is a preset emotion type, it is determined that the dialogue interaction with the terminal device meets the convergence condition.

7. The method according to any one of claims 1 to 6, characterized in that: Generating an initial question according to the plurality of object information and the registration information, including: Predicting predicted user information of the target user based on the registration information; Determining, according to the predicted user information and the plurality of object information, a predicted object of interest to the target user from among the plurality of objects; The initial question is generated according to the object information of the prediction object and the prediction user information.

8. The method according to any one of claims 1 to 7, characterized in that: The method further comprises: Obtaining the target user's operation record on the target application; The user portrait is updated according to the operation record.

9. An object recommendation device, characterized in that: The device comprises: A detection module, configured to determine, after detecting that a target user logs into a target application for the first time through a terminal device, a plurality of object information of a plurality of objects corresponding to the target application; a determination module, configured to determine the registration information of the target user in the target application, generate an initial question according to the plurality of object information and the registration information, and send the initial question to the terminal device; A receiving module, configured to receive an initial answer corresponding to the initial question sent by the terminal device; A dialogue interaction module, configured to perform multiple dialogue interactions with the terminal device according to the multiple object information and the initial answer, and obtain dialogue interaction information; A generation module generates a user portrait of the target user based on the conversation interaction information, determines a target object to be recommended to the target user from among the multiple objects based on the user portrait, and sends object information of the target object to the terminal device.

10. A terminal device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the object recommendation method according to any one of claims 1 to 8.

11. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: in, The computer instructions are used to enable a computer to execute the object recommendation method according to any one of claims 1 to 8.

12. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the object recommendation method according to any one of claims 1 to 8 is implemented.

Citation Information

Cited By

  • Travel itinerary recommendation method and device, electronic equipment and storage medium

    CN120336385A