Object recommendation method and device, equipment and storage medium

Abstract

The embodiment of the invention relates to an object recommendation method and device, equipment and a storage medium, and the method comprises the steps: after recommendation demand information inputted in a session window is received, determining recommendation objects according to demand elements indicated by the recommendation demand information, and displaying the recommendation objects in the session window. When a preset trigger operation for the first recommendation object is received, object detail information is generated according to a demand element indicated by the recommendation demand information and the first recommendation object, the object detail information of the first recommendation object is displayed on an information window on the first page, and the object detail information comprises demand matching information corresponding to the first recommendation object; the demand matching information is used for representing the matching degree of the first recommendation object and the demand elements indicated by the recommendation demand information. The object detail information of the recommendation object can be generated in combination with the recommendation demand information input by the user, so that the object detail information displayed in the information window can correspond to the recommendation demand of the user, and the decision-making efficiency of the user is improved.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of computer, and particularly relates to an object recommendation method and device, equipment and storage medium. BACKGROUND

[0002] With the continuous development of computer technology, artificial intelligence models have played a very important role in various fields. For example, in the e-commerce shopping field, the artificial intelligence model can recommend goods meeting the needs of users according to the shopping needs of the users, thereby improving the decision-making efficiency of the users.

[0003] At present, in the scene of using an artificial intelligence model to recommend an object, if a user triggers a detail information viewing operation of a recommended object, the detail information of the recommended object is usually displayed for the user based on a fixed merchant template, which is one-size-fits-all and cannot meet the needs of the user. SUMMARY

[0004] In order to solve the above technical problems or at least partially solve the above technical problems, the present disclosure provides an object recommendation method, device, equipment and storage medium.

[0005] In a first aspect, an object recommendation method is provided, and the method comprises: In response to recommendation requirement information input in a conversation window on a first page, at least one recommended object is displayed in the conversation window, wherein the at least one recommended object is determined according to a requirement element indicated by the recommendation requirement information. In response to a preset trigger operation on a first recommended object in the at least one recommended object, object detail information corresponding to the first recommended object is displayed in an information window on the first page, wherein the object detail information is generated according to the requirement element indicated by the recommendation requirement information and the first recommended object, and the object detail information comprises requirement matching information corresponding to the first recommended object, and the requirement matching information is used to represent a matching degree between the first recommended object and the requirement element indicated by the recommendation requirement information.

[0006] In an optional implementation, the object detail information further comprises object evaluation content corresponding to the first recommended object, the object evaluation content comprises at least one of evaluation text, evaluation video and evaluation image, and the object evaluation content is extracted from evaluation data of the first recommended object for the requirement element indicated by the recommendation requirement information.

[0007] In an alternative implementation, the demand matching information corresponding to the first recommended object comprises a demand matching analysis table, wherein the demand matching analysis table comprises analysis information of the first recommended object in a target attribute dimension, and the target attribute dimension is obtained by mapping demand elements indicated by the recommended demand information.

[0008] In an alternative implementation, the at least one recommended object comprises a recommended object combination, the first recommended object and the second recommended object belong to the same recommended object combination, and the object detail information corresponding to the first recommended object further comprises combination effect analysis information, and the combination effect analysis information is used to describe a combination effect between the first recommended object and the second recommended object.

[0009] In an alternative implementation, the at least one recommended object comprises a recommended object combination, the first recommended object and the second recommended object belong to the same recommended object combination, and the object detail information corresponding to the first recommended object further comprises combination effect analysis information, and the combination effect analysis information is used to describe a combination effect between the first recommended object and the second recommended object. In an alternative implementation, the at least one recommended object comprises a recommended object combination, the first recommended object and the second recommended object belong to the same recommended object combination, and the object detail information corresponding to the first recommended object further comprises combination effect analysis information, and the combination effect analysis information is used to describe a combination effect between the first recommended object and the second recommended object. According to the demand elements, at least one recommended object is obtained, and the at least one recommended object is displayed in the form of a resource card in the conversation window.

[0010] In an alternative implementation, the at least one recommended object comprises a recommended object combination, the first recommended object and the second recommended object belong to the same recommended object combination, and the object detail information corresponding to the first recommended object further comprises combination effect analysis information, and the combination effect analysis information is used to describe a combination effect between the first recommended object and the second recommended object. If the demand elements indicate a combination recommended demand, at least one recommended object combination is obtained according to the demand elements; wherein a plurality of recommended objects are included in the same recommended object combination. In the conversation window, the recommended objects included in the at least one recommended object combination are displayed in the form of a resource card, and the recommended reason information corresponding to the at least one recommended object combination is displayed; wherein the recommended reason information is used to represent a recommended reason of the corresponding recommended object combination.

[0011] In an alternative implementation, the at least one recommended object comprises a recommended object combination, the first recommended object and the second recommended object belong to the same recommended object combination, and the object detail information corresponding to the first recommended object further comprises combination effect analysis information, and the combination effect analysis information is used to describe a combination effect between the first recommended object and the second recommended object. In response to a replacement operation on a third recommended object in the first recommended object combination, a fourth recommended object is determined according to the demand elements and the recommended objects in the first recommended object combination. After the fourth recommended object is used to replace the third recommended object in the first recommended object combination, a second recommended object combination is obtained; The recommended objects included in the second recommended object combination are displayed in the form of resource cards on the conversation window, and the recommended reason information corresponding to the second recommended object combination is displayed.

[0012] In a second aspect, the present disclosure provides an object recommendation device, and the device comprises: A first display module is configured to display at least one recommended object on a conversation window in response to recommendation demand information input on a first page, wherein the at least one recommended object is determined according to demand elements indicated by the recommendation demand information. A second display module is configured to display object detail information corresponding to a first recommended object in the at least one recommended object on an information window on the first page in response to a preset trigger operation on the first recommended object, wherein the object detail information is generated according to the demand elements indicated by the recommendation demand information and the first recommended object, and the object detail information comprises demand matching information corresponding to the first recommended object, and the demand matching information is used to represent a matching degree between the first recommended object and the demand elements indicated by the recommendation demand information.

[0013] In a third aspect, the present disclosure provides an electronic device, and the electronic device comprises: a processor; a memory for storing executable instructions of the processor; and the processor is configured to read the executable instructions from the memory and execute the instructions to implement the object recommendation method provided by the embodiments of the present disclosure.

[0014] In a fourth aspect, the present disclosure provides a computer readable storage medium, and the storage medium stores a computer program, and the computer program is used to execute the object recommendation method provided by the embodiments of the present disclosure.

[0015] In a fifth aspect, the present disclosure provides a computer program product, and the computer program product comprises computer programs / instructions, and the computer programs / instructions are executed by a processor to implement the method described above.

[0016] Compared with the prior art, the technical solutions provided by the embodiments of the present disclosure have at least the following advantages: In the object recommendation method provided by the embodiments of the present disclosure, after receiving the recommendation demand information input in the conversation window on the first page, at least one recommended object is determined according to the demand elements indicated by the recommendation demand information, and each recommended object is displayed in the conversation window. When a preset trigger operation for the first recommended object is received, object detail information of the first recommended object is generated according to the demand elements indicated by the recommendation demand information and the first recommended object, and the object detail information of the first recommended object is displayed in the information window on the first page. The object detail information includes demand matching information corresponding to the first recommended object, and the demand matching information is used to represent the matching degree between the first recommended object and the demand elements indicated by the recommendation demand information.

[0017] After receiving a preset trigger operation for the recommended object in the conversation window, the embodiments of the present disclosure can generate the object detail information of the recommended object in combination with the recommendation demand information input by the user, so that the object detail information displayed in the information window can correspond to the recommendation demand of the user, and the decision efficiency of the user is improved. BRIEF DESCRIPTION OF DRAWINGS

[0018] The above and other features, advantages, and aspects of the present disclosure will become more apparent by describing in detail the embodiments thereof with reference to the attached drawings. Throughout the drawings, the same or similar reference numerals can refer to the same or similar elements. It should be understood that the drawings are schematic and elements and features are not necessarily drawn to scale.

[0019] Figure 1 A flowchart of an object recommendation method provided by the embodiments of the present disclosure; Figure 2 A schematic diagram of a first page provided by the embodiments of the present disclosure; Figure 3 A schematic diagram of another first page provided by the embodiments of the present disclosure; Figure 4 A structural schematic diagram of an object recommendation device provided by the embodiments of the present disclosure; Figure 5 A structural schematic diagram of an electronic device provided by the embodiments of the present disclosure. DETAILED DESCRIPTION

[0020] Embodiments of the present disclosure will be described in more detail by making reference to the drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms, and should not be interpreted as being limited to the embodiments set forth herein, but rather, these embodiments are provided to make the present disclosure more thorough and complete. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes, and are not intended to limit the protection scope of the present disclosure.

[0021] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0022] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0023] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0024] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0025] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0026] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained. With the development of large language models and multimodal generation technologies, the recommendation and content generation capabilities of artificial intelligence models in e-commerce shopping scenarios have been significantly improved. However, in scenarios where AI models are used for shopping recommendations, if a user triggers a view of the details for a recommended product, the existing technologies can only display the product details based on a fixed merchant template, which has insufficient influence on the user's purchasing decision.

[0027] Therefore, the embodiment of the present disclosure provides an object recommendation method. After receiving recommendation demand information input in a conversation window on a first page, at least one recommended object is determined according to demand elements indicated by the recommendation demand information, and each recommended object is displayed in the conversation window. When a preset trigger operation for a first recommended object is received, object detail information of the first recommended object is generated according to the demand elements indicated by the recommendation demand information and the first recommended object, and the object detail information of the first recommended object is displayed in an information window on the first page. The object detail information includes demand matching information corresponding to the first recommended object, which represents the matching degree between the first recommended object and the demand elements indicated by the recommendation demand information.

[0028] After receiving a preset trigger operation for a recommended object in the conversation window, the embodiment of the present disclosure can generate object detail information of the recommended object in combination with the recommendation demand information input by the user, so that the object detail information displayed in the information window can correspond to the recommendation demand of the user, and the decision efficiency of the user is improved.

[0029] For ease of understanding, the embodiment of the present disclosure provides an object recommendation method, which can be executed by an object recommendation device. The device can be implemented by software and / or hardware, and can be integrated in an electronic device. Referring to Figure 1 The embodiment of the present disclosure provides a flowchart of an object recommendation method, and the method includes the following steps. S101: In response to recommendation demand information input in a conversation window on a first page, at least one recommended object is displayed in the conversation window.

[0030] The at least one recommended object is determined according to demand elements indicated by the recommendation demand information.

[0031] In the embodiment of the present disclosure, the first page includes a conversation window and an information window. The conversation window is used to receive recommendation demand information input by the user, and display recommended result content corresponding to the recommendation demand information. The information window is used to display information in response to an interactive operation triggered by the conversation window.

[0032] Referring to Figure 2 The embodiment of the present disclosure provides a schematic diagram of a first page, which includes a conversation window 201 and an information window 202. In actual application, the user inputs recommendation demand information in an input box 203 of the conversation window 201. The recommendation demand information can be a natural language description of recommendation demand text, and the recommendation demand information can include multi-modal information, such as recommendation reference images, recommendation reference videos, and recommendation reference charts, which can represent multi-modal content of the user's recommendation demand.

[0033] In one optional implementation, in response to recommendation request information input in a session window on a first page, the recommendation request information is parsed using a first model to obtain at least one semantic element, which serves as the request element indicated by the recommendation request information; wherein, the semantic element includes at least one of scenario element, budget element, preference element, and intent element. Specifically, the scenario element is used to characterize the user's object recommendation scenario request, the budget element is used to characterize the user's object recommendation budget request, the preference element is used to characterize the user's object recommendation preference request, and the intent element is used to characterize the user's object recommendation intent request, i.e., the user's shopping intent.

[0034] Then, the first model performs object retrieval based on each requirement element, obtains at least one recommended object, and displays each recommended object in the form of a resource card in the session window on the first page. For example... Figure 2 As shown, three recommended objects are displayed in the session window 201.

[0035] In practical applications, the first model can be a trained large language model. After receiving the user's input recommendation request information, the model inputs this information and parses it to identify the indicated requirement elements. Based on these elements, the model performs object retrieval to obtain recommended objects that meet the user's needs. The requirement elements represent one or more dimensions of the recommendation request information.

[0036] In one alternative implementation, the first model can also perform object retrieval by combining the context of the recommendation request information entered in the session window, so as to identify the recommendation object that is more able to meet the user's needs.

[0037] S102: In response to a preset trigger operation for the first recommended object among the at least one recommended object, display the object details information corresponding to the first recommended object in the information window on the first page.

[0038] The object details information is generated based on the demand elements indicated by the recommendation demand information and the object information of the first recommended object. The object details information includes the demand matching information corresponding to the first recommended object, and the demand matching information is used to characterize the degree of matching between the first recommended object and the demand elements indicated by the recommendation demand information.

[0039] In this embodiment of the disclosure, when a user's preset trigger operation is received for each recommended object displayed in the session window, the object details information corresponding to the first recommended object is displayed in the information window on the first page. The first recommended object can be any recommended object displayed in the session window. The preset trigger operation may include a selection operation on the first recommended object, such as clicking to select the first recommended object.

[0040] It is worth noting that, in this embodiment of the present disclosure, the object details information of the recommended object displayed in the information window is generated in real time based on the recommendation request information entered this time. Differentiated content can be displayed for different users to meet the different recommendation needs of different users and improve the content relevance between the displayed object details information and the recommendation request information entered by the user.

[0041] The object details information of the first recommended object displayed in the information window in this embodiment is generated based on the recommendation request information entered by the user and the object information of the first recommended object. In other words, different object details information can be generated for the same recommended object corresponding to different recommendation request information.

[0042] The object details information of the first recommended object may include a set of images of the first recommended object, including images taken from various angles of the first recommended object, and may also include object description information of the first recommended object, used to describe the characteristics of the first recommended object.

[0043] In one optional implementation, after the large language model extracts the demand elements indicated by the recommendation demand information, it generates object detail information of the first recommended object based on each demand element and the object information of the selected first recommended object. In this embodiment of the disclosure, the object details information of the first recommended object includes the demand matching information corresponding to the first recommended object. The demand matching information characterizes the degree of matching between the first recommended object and the demand elements indicated by the currently input recommendation demand information. Through the demand matching information of the first recommended object, it can be determined whether the first recommended object meets the user's recommendation needs, and from which dimensions it meets the user's recommendation needs.

[0044] In one optional implementation, the demand matching information corresponding to the first recommended object includes a demand matching analysis table. This table includes analysis information for the first recommended object across target attribute dimensions. The target attribute dimensions are mapped from the demand elements indicated by the currently input recommendation demand information. For example, the scenario element indicated by the recommendation demand information maps to the usage dimension, the budget element maps to the price dimension, and the preference element maps to the style dimension, etc. The demand matching analysis table for the first recommended object includes analysis information for the first recommended object across one or more of these attribute dimensions, indicating which attribute dimensions the first recommended object matches the user's recommendation needs and the degree to which it matches those needs. This demand matching analysis table for the first recommended object provides a more intuitive view of the correspondence between the recommended object's attributes and the user's demand dimensions, thereby improving user decision-making efficiency.

[0045] In another optional implementation, the object details information of the first recommended object displayed in the information window may further include the object evaluation content corresponding to the first recommended object. The object evaluation content may include at least one of evaluation text, evaluation video, and evaluation image. The object evaluation content corresponding to the first recommended object is extracted from the evaluation data of the first recommended object based on the demand elements indicated by the currently input recommendation demand information.

[0046] Specifically, the evaluation text and evaluation images can be extracted by the large language model from the user evaluation content of the first recommended object on various business platforms based on the demand elements indicated by the recommendation demand information. In other words, the object evaluation content of the first recommended object displayed in the information window is extracted by combining the recommendation demand information input this time, which can correspond to the user's recommendation needs and help the user make object acquisition decisions.

[0047] In one optional implementation, the evaluation content of the first recommended object may include a highly readable evaluation summary generated by a large language model after aggregating evaluation data for the first recommended object from multiple business platforms.

[0048] In addition, the evaluation video in the evaluation content of the first recommended object can be determined by the large language model from the video content of each business platform based on the demand elements indicated by the recommendation demand information. For example, the evaluation video in the evaluation content of the first recommended object can be a video that evaluates the first recommended object based on the above-mentioned demand elements.

[0049] In one optional implementation, in order to improve the user's decision-making efficiency, the object evaluation content corresponding to the first recommended object can be displayed in categories. Optionally, the object evaluation content corresponding to the first recommended object can be displayed in categories according to the advantages and disadvantages used to evaluate the first recommended object. In addition, each object evaluation content displayed in the information window can be marked with its source to identify the business platform to which it belongs.

[0050] In the object recommendation method provided in this embodiment, after receiving recommendation request information input in a session window on a first page, at least one recommended object is determined based on the requirement elements indicated by the recommendation request information, and each recommended object is displayed in the session window. Upon receiving a preset trigger operation for a first recommended object, object details information of the first recommended object is generated based on the requirement elements indicated by the recommendation request information and the object information of the first recommended object, and the object details information of the first recommended object is displayed in an information window on the first page. The object details information includes requirement matching information corresponding to the first recommended object, which characterizes the degree of matching between the first recommended object and the requirement elements indicated by the recommendation request information.

[0051] Upon receiving a preset trigger operation for a recommended object within a session window, this embodiment of the present disclosure can generate object details information for the recommended object by combining the user's input recommendation needs information, so that the object details information displayed in the information window can correspond to the user's recommendation needs, thereby improving the user's decision-making efficiency.

[0052] Based on the above embodiments, this disclosure can also determine a combination of recommended objects based on the recommendation request information input in the session window. Specifically, after parsing the input recommendation request information using a large language model to obtain the request elements, if the request elements indicate a combined recommendation request, the large language model obtains at least one combination of recommended objects based on the parsed request elements. The same combination of recommended objects includes multiple recommended objects with related relationships.

[0053] In this embodiment of the disclosure, the combined recommendation requirement refers to the recommendation requirement information input by the user that includes a group of related recommended objects, such as a combination of keywords such as "group" or "set".

[0054] In this embodiment of the disclosure, after obtaining at least one combination of recommended objects, the recommended objects included in each combination are displayed in the session window in the form of resource cards, along with the recommendation reason information corresponding to each combination. The recommendation reason information is used to characterize the reason for recommending the corresponding combination of recommended objects. For example, a certain combination of recommended objects may meet the scenario requirements indicated by the currently input recommendation requirement information.

[0055] likeFigure 3 The diagram shown illustrates another first page provided in an embodiment of this disclosure. The session window displays a first recommended object combination and a second recommended object combination. It is assumed that the first recommended object and the second recommended object belong to the same recommended object combination. Figure 3 The first recommended object combination shown, when a preset trigger operation is received for the first recommended object, the object details information corresponding to the first recommended object displayed in the information window on the first page not only includes the demand matching information and object evaluation content in the above embodiment, but may also include combination effect analysis information 301. The combination effect analysis information corresponding to the first recommended object is used to describe the combination effect between the first recommended object and the second recommended object in the same group, such as the first recommended object and the second recommended object being used together to have a doubled effect on a certain skin type.

[0056] In practical applications, if one of the recommended objects in a certain combination does not meet the user's needs, this embodiment of the disclosure supports the user in triggering a replacement operation for that recommended object in the combination.

[0057] In one optional implementation, in response to the replacement operation of the third recommended object in the first recommended object combination, a fourth recommended object is determined based on the requirement elements indicated by the currently input recommendation requirement information and the recommended objects in the first recommended object combination. Then, the determined fourth recommended object is used to replace the third recommended object in the first recommended object combination to obtain a second recommended object combination. Subsequently, the recommended objects included in the regenerated second recommended object combination are displayed in the session window as resource cards, along with the recommendation reason information corresponding to the second recommended object combination.

[0058] This disclosure provides an object recommendation method in which, upon receiving a preset trigger operation for a recommended object within a session window, object details of the recommended object are generated by combining the user's input recommendation needs information. This allows the object details displayed in the information window to correspond to the user's recommendation needs, thereby improving the user's decision-making efficiency.

[0059] Based on this, the embodiments of this disclosure can also identify the combined recommendation requirements indicated by the recommendation requirement information, display the combination of recommended objects to the user, and support the user to view the combination effect between recommended objects in the same combination, thereby improving the user's decision-making efficiency for the combination of recommended objects.

[0060] To implement the above embodiments, this disclosure also proposes an object recommendation device. Figure 4 This is a schematic diagram of an object recommendation device provided in an embodiment of this disclosure. The device can be implemented by software and / or hardware and is generally integrated into an electronic device. Figure 4 As shown, the device includes: The first display module 401 is configured to display at least one recommended object in response to recommendation request information input in a session window on a first page; wherein the at least one recommended object is determined based on the requirement elements indicated by the recommendation request information. The second display module 402 is used to respond to a preset trigger operation for the first recommended object among the at least one recommended object, and to display object details information corresponding to the first recommended object in an information window on the first page; wherein, the object details information is generated based on the demand elements indicated by the recommendation demand information and the first recommended object, and the object details information includes demand matching information corresponding to the first recommended object, and the demand matching information is used to characterize the degree of matching between the first recommended object and the demand elements indicated by the recommendation demand information.

[0061] In one optional implementation, the object details information further includes object evaluation content corresponding to the first recommended object. The object evaluation content includes at least one of evaluation text, evaluation video, and evaluation image. The object evaluation content is extracted from the evaluation data of the first recommended object based on the demand elements indicated by the recommendation demand information.

[0062] In one optional implementation, the demand matching information corresponding to the first recommended object includes a demand matching analysis table, which includes analysis information for the first recommended object in the target attribute dimension, wherein the target attribute dimension is mapped according to the demand elements indicated by the recommendation demand information.

[0063] In one optional implementation, the at least one recommended object includes a combination of recommended objects, the first recommended object and the second recommended object belong to the same combination of recommended objects, and the object details information corresponding to the first recommended object further includes combination effect analysis information, which is used to describe the combination effect between the first recommended object and the second recommended object.

[0064] In one optional implementation, the first display module includes: The parsing submodule is used to respond to the recommendation request information input in the session window on the first page, and use the first model to parse the recommendation request information to obtain at least one semantic element as the requirement element indicated by the recommendation request information; wherein, the semantic element includes at least one of scene element, budget element, preference element and intent element; The first display submodule is used to obtain at least one recommended object based on the required elements, and to display the at least one recommended object in the form of a resource card in the session window.

[0065] In one optional implementation, the first display submodule includes: The first acquisition module is configured to acquire at least one combination of recommended objects based on the demand element if the demand element indicates a demand for combined recommendations; wherein the same combination of recommended objects includes multiple recommended objects. The second display submodule is used to display, in the form of resource cards, the recommended objects included in the at least one combination of recommended objects in the session window, and to display the recommendation reason information corresponding to the at least one combination of recommended objects; wherein, the recommendation reason information is used to characterize the recommendation reason for the corresponding combination of recommended objects.

[0066] In one optional embodiment, the apparatus further includes: The determination module is used to determine a fourth recommended object in response to a replacement operation for a third recommended object in the first recommended object combination, based on the demand element and the object information of the recommended objects in the first recommended object combination. The replacement module is used to replace the third recommended object in the first recommended object combination with the fourth recommended object to obtain a second recommended object combination; The third display module is used to display the recommended objects included in the second recommended object combination in the form of resource cards on the session window, and to display the recommendation reason information corresponding to the second recommended object combination.

[0067] In the object recommendation device provided in this embodiment, after receiving recommendation request information input in a session window on a first page, at least one recommended object is determined based on the requirement elements indicated by the recommendation request information, and each recommended object is displayed in the session window. Upon receiving a preset trigger operation for a first recommended object, object details information of the first recommended object is generated based on the requirement elements indicated by the recommendation request information and the object information of the first recommended object, and the object details information of the first recommended object is displayed in an information window on the first page. The object details information includes requirement matching information corresponding to the first recommended object, which characterizes the degree of matching between the first recommended object and the requirement elements indicated by the recommendation request information.

[0068] Upon receiving a preset trigger operation for a recommended object within a session window, this embodiment of the present disclosure can generate object details information for the recommended object by combining the user's input recommendation needs information, so that the object details information displayed in the information window can correspond to the user's recommendation needs, thereby improving the user's decision-making efficiency.

[0069] In addition to the methods and apparatus described above, embodiments of this disclosure also provide a computer-readable storage medium storing instructions that, when executed on a terminal device, cause the terminal device to implement the object recommendation method described in embodiments of this disclosure.

[0070] This disclosure also provides a computer program product, which includes a computer program / instructions that, when executed by a processor, implement the object recommendation method described in this disclosure.

[0071] In addition, this disclosure also provides an electronic device, see [link to relevant documentation]. Figure 5 As shown, it may include: The electronic device includes a processor 501, a memory 502, an input device 503, and an output device 504. The number of processors 501 in the electronic device can be one or more. Figure 5 Taking a processor as an example. In some embodiments of this disclosure, the processor 501, memory 502, input device 503, and output device 504 can be connected via a bus or other means, wherein, Figure 5 Taking the example of a connection between China and Israel via a bus.

[0072] The memory 502 can be used to store software programs and modules. The processor 501 executes various functional applications and data processing of the electronic device by running the software programs and modules stored in the memory 502. The memory 502 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function, etc. In addition, the memory 502 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. The input device 503 can be used to receive input digital or character information, and to generate signal inputs related to user settings and function control of the electronic device.

[0073] Specifically in this embodiment, the processor 501 loads the executable files corresponding to the processes of one or more applications into the memory 502 according to the following instructions, and the processor 501 runs the applications stored in the memory 502 to realize the various functions of the above-mentioned electronic device.

[0074] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0075] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An object recommendation method, characterized in that, The method includes: In response to recommendation request information entered in a session window on a first page, at least one recommendation object is displayed in the session window; wherein the at least one recommendation object is determined based on the requirement elements indicated by the recommendation request information; In response to a preset trigger operation for a first recommended object among the at least one recommended objects, object details information corresponding to the first recommended object is displayed in an information window on the first page; wherein, the object details information is generated based on the demand elements indicated by the recommendation demand information and the first recommended object, and the object details information includes demand matching information corresponding to the first recommended object, the demand matching information being used to characterize the degree of matching between the first recommended object and the demand elements indicated by the recommendation demand information.

2. The object recommendation method according to claim 1, characterized in that, The object details information also includes object evaluation content corresponding to the first recommended object. The object evaluation content includes at least one of evaluation text, evaluation video, and evaluation image. The object evaluation content is extracted from the evaluation data of the first recommended object based on the demand elements indicated by the recommendation demand information.

3. The object recommendation method according to claim 1, characterized in that, The demand matching information corresponding to the first recommended object includes a demand matching analysis table, which includes analysis information on the target attribute dimension for the first recommended object. The target attribute dimension is obtained by mapping the demand elements indicated by the recommendation demand information.

4. The object recommendation method according to claim 1, characterized in that, The at least one recommended object includes a combination of recommended objects, the first recommended object and the second recommended object belong to the same combination of recommended objects, and the object details information corresponding to the first recommended object also includes combination effect analysis information, which is used to describe the combination effect between the first recommended object and the second recommended object.

5. The object recommendation method according to claim 1, characterized in that, The response to the recommendation request information entered in the session window on the first page, displaying at least one recommended object in the session window, includes: In response to the recommendation request information entered in the session window on the first page, the recommendation request information is parsed using a first model to obtain at least one semantic element as the request element indicated by the recommendation request information; wherein, the semantic element includes at least one of scenario element, budget element, preference element and intent element; At least one recommended object is obtained based on the required elements, and the at least one recommended object is displayed in the session window in the form of a resource card.

6. The object recommendation method according to claim 5, characterized in that, The step of obtaining at least one recommended object based on the demand elements and displaying the at least one recommended object in the session window as a resource card includes: If the demand element indicates a demand for combined recommendations, then at least one combination of recommended objects is obtained based on the demand element; wherein, the same combination of recommended objects includes multiple recommended objects; The session window displays the recommended objects included in the at least one combination of recommended objects in the form of resource cards, and displays the recommendation reason information corresponding to the at least one combination of recommended objects; wherein, the recommendation reason information is used to characterize the recommendation reason for the corresponding combination of recommended objects.

7. The object recommendation method according to claim 6, characterized in that, After displaying the recommended objects included in the at least one recommended object combination in the form of resource cards in the session window, and displaying the recommendation reason information corresponding to the at least one recommended object combination, the method further includes: In response to a replacement operation for a third recommended object in the first recommended object combination, a fourth recommended object is determined based on the demand element and the recommended objects in the first recommended object combination. After replacing the third recommended object in the first recommended object combination with the fourth recommended object, a second recommended object combination is obtained; The recommended objects included in the second recommended object combination are displayed in the form of resource cards on the session window, along with the recommendation reason information corresponding to the second recommended object combination.

8. An object recommendation device, characterized in that, The device includes: A first display module is configured to display at least one recommended object in response to recommendation request information entered in a session window on a first page; wherein the at least one recommended object is determined based on the requirement elements indicated by the recommendation request information. The second display module is used to respond to a preset trigger operation for the first recommended object among the at least one recommended object, and to display object details information corresponding to the first recommended object in an information window on the first page; wherein, the object details information is generated based on the demand elements indicated by the recommendation demand information and the first recommended object, and the object details information includes demand matching information corresponding to the first recommended object, and the demand matching information is used to characterize the degree of matching between the first recommended object and the demand elements indicated by the recommendation demand information.

9. An electronic device, characterized in that, The electronic device includes: processor; Memory used to store the processor's executable instructions; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The storage medium stores a computer program for performing the method as described in any one of claims 1-7.

11. A computer program product, characterized in that, The computer program product includes a computer program / instruction that, when executed by a processor, implements the method as described in any one of claims 1-7.

Images