Searching method and device, electronic equipment and storage medium

Abstract

The invention provides a search method and device, electronic equipment and a storage medium, and belongs to the technical field of computers. The method comprises the following steps: displaying a search page; acquiring natural language description information input in the search page; based on object features obtained through analysis of the natural language description information, information items of a first target object are displayed, and the first target object is matched with the object features; and displaying a recombination name of the first target object on the information item of the first target object, the recombination name comprising information corresponding to the object feature in the object information of the first target object. Wherein the natural language description information can reflect user requirements, and the object features analyzed from the natural language description information can reflect the emphasis of user attention. As the recombination name of the first target object comprises the information corresponding to the object characteristics, the recombination name can visually display the information corresponding to the emphasis concerned by the user to the user, and the information display efficiency is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technologies, and particularly to a search method, apparatus, electronic device, and storage medium. Background Art

[0002] With the development of Internet technologies, when users search for required information through various platforms, they often face the problem of information overload due to obtaining a large amount of invalid information, which increases the time cost for users to obtain effective information. In traditional search methods, users enter keywords in a search page to determine objects that match the keyword descriptions and obtain some brief information about the objects, such as the prices of the objects and the quantities of the objects sold. However, the above-mentioned brief information may not be the content that users focus on. In this case, users cannot compare different objects from their own focus points by browsing the brief information. Therefore, how to intuitively display the information that users focus on and improve the information display efficiency is a problem that needs to be solved. Summary of the Invention

[0003] The present disclosure provides a search method, apparatus, electronic device, and storage medium, in which the information that users focus on is intuitively displayed, and the information display efficiency is improved. The technical solutions of the present disclosure are as follows.

[0004] According to one aspect of the embodiments of the present disclosure, a search method is provided, and the method includes:

[0005] Display a search page;

[0006] Obtain natural language description information input in the search page;

[0007] Based on object features parsed from the natural language description information, display information items of a first target object that matches the object features;

[0008] On the information items of the first target object, display a restructured name of the first target object, where the restructured name includes information in the object information of the first target object that corresponds to the object features.

[0009] According to another aspect of the embodiments of the present disclosure, a search apparatus is provided, and the apparatus includes:

[0010] A first display unit configured to display a search page;

[0011] An obtaining unit configured to obtain natural language description information input in the search page;

[0012] A second display unit, configured to display information items of a first target object based on object features parsed from the natural language description information, where the first target object matches the object features;

[0013] The second display unit is further configured to display a recombined name of the first target object on the information items of the first target object, where the recombined name includes information corresponding to the object features in the object information of the first target object.

[0014] In some embodiments, the object features include at least one feature dimension;

[0015] The second display unit is configured to display, in the recombined name of the first target object, information corresponding to each feature dimension in the object information of the first target object in the order from front to back according to the word order corresponding to the at least one feature dimension in the natural language description information.

[0016] In some embodiments, the object features include at least one feature dimension;

[0017] The second display unit is configured to display, in the recombined name of the first target object, information corresponding to each feature dimension in the object information of the first target object in the order from front to back according to the preset word order of each feature dimension under the object category of the first target object.

[0018] In some embodiments, the second display unit is configured to, in response to dragging information corresponding to a first feature dimension to a position before or after the word order position corresponding to a second feature dimension, display an updated recombined name of the first target object, where the information corresponding to the first feature dimension in the updated recombined name is displayed before or after the information corresponding to the second feature dimension, and the first feature dimension and the second feature dimension are different feature dimensions among the at least one feature dimension.

[0019] In some embodiments, the second display unit is configured to highlight information corresponding to the object features in the object information of the first target object in the recombined name of the first target object.

[0020] In some embodiments, the object features include at least one feature dimension;

[0021] The second display unit is further configured to, in response to a trigger operation on information corresponding to any feature dimension in the recombined name of the first target object, display a detail page of the first target object, where information describing the first target object under the feature dimension is displayed in the detail page.

[0022] In some embodiments, a target image corresponding to the first target object is further displayed on the information item of the first target object, and the degree of association between the target image and the object feature meets a preset condition.

[0023] In some embodiments, the object feature includes at least one feature dimension, and recombination information under a third feature dimension is further displayed on the information item of the first target object. The third feature dimension is any one of the at least one feature dimension, and the recombination information under the third feature dimension is used to describe the first target object under the third feature dimension; the recombination information includes at least one of text, table, image, and video.

[0024] In some embodiments, the recombination information under the third feature dimension is displayed in a slidable component in the information item of the first target object;

[0025] The second display unit is further configured to, in response to a sliding operation in the slidable component, display recombination information under a fourth feature dimension in the slidable component, where the fourth feature dimension is another feature dimension among the at least one feature dimension except the third feature dimension.

[0026] In some embodiments, at least one of a filtering label determined based on the object feature and a preset filtering label corresponding to the object category of the first target object is further displayed on the page for displaying the information item of the first target object:

[0027] The apparatus further includes:

[0028] A third display unit, configured to, in response to a triggering operation on any filtering label, display a second target object in the first target object, where the second target object matches both the object feature and the feature indicated by the filtering label; on the information item of the second target object, display a recombined name of the second target object, where the recombined name includes information corresponding to the object feature in the object information of the second target object.

[0029] In some embodiments, the recombined name further includes information corresponding to the feature indicated by the filtering label in the object information of the second target object.

[0030] In some embodiments, recombination information under the feature dimension corresponding to the filtering label is further displayed on the information item of the second target object, and the recombination information is used to describe the second target object under the feature dimension corresponding to the filtering label.

[0031] In some embodiments, the apparatus further includes:

[0032] A fourth display unit, configured to display adjustment prompt information based on object features parsed from the natural language description information, where the adjustment prompt information is used to prompt an adjustment operation on the natural language description information for at least one feature dimension, and the adjustment operation includes at least one of an addition operation, a deletion operation, and a replacement operation on the natural language description information under any feature dimension.

[0033] According to another aspect of the embodiments of the present disclosure, there is provided an electronic device, which includes:

[0034] One or more processors;

[0035] A memory for storing executable program code of the processor;

[0036] Wherein, the processor is configured to execute the program code to implement the above search method.

[0037] According to another aspect of the embodiments of the present disclosure, there is provided a computer-readable storage medium, when instructions in the computer-readable storage medium are executed by a processor of an electronic device, enabling the electronic device to execute the above search method.

[0038] According to another aspect of the embodiments of the present disclosure, there is provided a computer program product, including a computer program, where the computer program implements the above search method when executed by a processor.

[0039] The embodiments of the present disclosure provide a search method. In this method, natural language description information input by a user on a search page is obtained, object features parsed from the natural language description information are used as a search basis to obtain a first target object that matches the object features, and a recombined name of the first target object is displayed on an information item of the first target object. Among them, the natural language description information can reflect the user's needs, and the object features can reflect the user's focus. Since the recombined name of the first target object includes information corresponding to the object features, the recombined name can intuitively display information corresponding to the user's focus to the user, which improves the information display efficiency, is conducive to the user quickly obtaining the information they focus on by browsing the recombined name of the first target object, thereby comparing different objects and assisting in decision-making, improving the efficiency of the user obtaining information, and enhancing the user experience.

[0040] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings here are incorporated into the description and form a part of this description, showing embodiments consistent with the present disclosure, and are used together with the description to explain the principles of the present disclosure, and do not constitute an undue limitation of the present disclosure.

[0042] Figure 1 is a schematic diagram of an implementation environment of a search method shown according to an exemplary embodiment;

[0043] Figure 2 is a flowchart of a search method shown according to an exemplary embodiment;

[0044] Figure 3 is a flowchart of another search method shown according to an exemplary embodiment;

[0045] Figure 4 is a schematic diagram of a search page shown according to an exemplary embodiment;

[0046] Figure 5 is a schematic diagram of a page displaying information items shown according to an exemplary embodiment;

[0047] Figure 6 is a schematic diagram of another page displaying information items shown according to an exemplary embodiment;

[0048] Figure 7 is a schematic diagram of a details page shown according to an exemplary embodiment;

[0049] Figure 8 is a schematic diagram of an overall process shown according to an exemplary embodiment;

[0050] Figure 9 is a block diagram of a search device shown according to an exemplary embodiment;

[0051] Figure 10 is a block diagram of another search device shown according to an exemplary embodiment;

[0052] Figure 11 is a block diagram of an electronic device shown according to an exemplary embodiment. Detailed implementation manners

[0053] To enable those of ordinary skill in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0054] It should be noted that the terms "first", "second", etc. in the specification, claims and above-mentioned drawings of the present disclosure are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present disclosure described herein can be implemented in an order different from those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0055] It should be noted that the information (including but not limited to user equipment information, user personal information, etc.), data (including but not limited to data for analysis, stored data, displayed data, etc.) and signals involved in the present disclosure are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions. For example, the natural language description information involved in the present disclosure is obtained under full authorization.

[0056] Figure 1 It is a schematic diagram of the implementation environment of a search method shown according to an exemplary embodiment. Refer to Figure 1 This implementation environment specifically includes: a terminal 101 and a server 102. The terminal 101 can be connected to the server 102 through a wireless network or a wired network.

[0057] The terminal 101 can be at least one of devices such as a smart phone, a smart watch, a desktop computer, a laptop computer, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV) player, and a laptop portable computer. An application program can be installed and run on the terminal 101, and the application program can display search results in response to a search operation. The application program can be a shopping application program, a video application program, a social application program, etc., which are not limited herein. The application program is associated with the server 102, and the server 102 provides background services to the terminal 101.

[0058] The terminal 101 can generally refer to one of multiple terminals, and the terminal 101 is used as an example in this embodiment. Those skilled in the art can know that the number of the above terminals can be more or less. For example, the above terminals can be several, or the above terminals can be dozens or hundreds, or more, and the present disclosure embodiments do not limit the number and device type of the terminals.

[0059] The server 102 is at least one of a single server, multiple servers, a cloud computing platform, and a virtualization center. Optionally, the number of the above-mentioned servers may be more or less, and the embodiments of the present disclosure do not limit this. Of course, the server 102 may further include other functional servers to provide more comprehensive and diverse services. In some embodiments, the server 102 undertakes the main computing work, and the terminal 101 undertakes the secondary computing work; or, the server 102 undertakes the secondary computing work, and the terminal 101 undertakes the main computing work; or, the server 102 and the terminal 101 adopt a distributed computing architecture for collaborative computing. The server 102 can be connected to the terminal 101 and other terminals through a wireless network or a wired network. Optionally, the number of the above-mentioned servers may be more or less, and the embodiments of the present disclosure do not limit this.

[0060] Figure 2 is a flowchart of a search method shown according to an exemplary embodiment, as Figure 2 shown, and this method is executed by the terminal and includes the following steps.

[0061] In step S201, the terminal displays a search page.

[0062] In the embodiments of the present disclosure, the search page refers to a page for a user to input information to search for specific information. The embodiments of the present disclosure do not limit the display scenarios of the search page. For example, the search page can be a search page in various application programs such as an e-commerce platform, a social media platform, and an online music platform. Correspondingly, the objects to be searched for in the search page can be items, services, and multimedia resources, etc. The embodiments of the present disclosure take searching for items in the search page as an example for illustration.

[0063] In step S202, the terminal obtains the natural language description information input in the search page.

[0064] In the embodiments of the present disclosure, the natural language description information refers to the information input by the user in the search page in the form of natural language. The natural language description information allows the object to be searched for to be described in a more natural and intuitive form, so as to express the user's needs. The terminal collects the natural language description information input in the search page in real time for subsequent data processing and information display.

[0065] Compared with the traditional method where accurate keywords must be input, the natural language description information in the embodiments of the present disclosure does not need to follow strict grammar and can be inaccurate or more colloquial. For example, the natural language description information does not need to include information such as brand, model, and performance parameters, but only includes information indicating the search intention. For example, the natural language description information is "I want a lightweight camera suitable for traveling", or the natural language description information is "A painting course suitable for children to watch, with rich and interesting content", or the natural language description information is "Search for the latest news about climate change".

[0066] In step S203, the terminal displays the information items of the first target object based on the object features parsed from the natural language description information, and the first target object matches the object features.

[0067] In the embodiments of the present disclosure, the object features refer to the information obtained by parsing the natural language description information through natural language processing technology (Natural Language Processing, NLP). The object features are the basis for subsequent precise search and screening. The number of object features can be one or multiple, and the embodiments of the present disclosure do not limit this. Optionally, the object features are the keywords extracted from the natural language description information. For example, if the natural language description information is "I want a lightweight camera suitable for traveling", the object features are "traveling", "lightweight", and "camera", etc. Or, the object features are the keywords obtained by further abstracting, generalizing, and appropriately expanding the keywords extracted from the natural language description information. For example, if the natural language description information is "I want a lightweight camera suitable for traveling", the object features are "traveling", "high definition", "scenery", "portable", "camera", etc. Different object features can have different priorities to facilitate subsequent search and display according to them. For example, the priority of the object feature indicating the object category is higher than the priority of the object feature indicating the object color.

[0068] Among them, the first target object conforms to the description of the object features. The embodiments of the present disclosure do not limit the number of the first target objects. It should be noted that each first target object can match all the object features or only some of the object features among all the object features. That is to say, the terminal supports fuzzy search according to the natural language description information. Optionally, the first target object that matches all the object features is preferably displayed over the first target object that matches only some of the object features.

[0069] Among them, the information item of the first target object is used to trigger a jump to the detail page of the first target object, and the detail page is used to display the object information of the first target object in detail and to obtain the first target object. It should be noted that the information item of the first target object can be displayed on the search page or on other pages other than the search page. The embodiments of the present disclosure do not limit this.

[0070] In step S204, the terminal displays the recombined name of the first target object on the information item of the first target object, and the recombined name includes the information corresponding to the object characteristics in the object information of the first target object.

[0071] In the embodiments of the present disclosure, the recombined name is different from the original name. The original name of the first target object refers to the name preset for the first target object by the provider of the first target object. For example, the provider of the first target object can be a merchant selling the first target object. At this time, the original name of the first target object refers to the name set by the merchant when creating the selling link of the first target object. The recombined name can be displayed at any position of the information item of the first target object. In addition to the recombined name, the original name of the first target object can also be displayed in the information item of the first target object. The embodiments of the present application do not limit the display position relationship between the recombined name and the original name of the first target object.

[0072] Among them, in the recombined name, the information corresponding to the object characteristics in the object information of the first target object can be keywords directly extracted from the object information of the first target object; it can also be object characteristics parsed from the object information of the first target object combined with natural language description information and then processed by artificial intelligence to obtain keywords. The embodiments of the present disclosure do not limit the acquisition method of the recombined name. For example, the natural language description information is "blue, good for taking pictures, long battery life mobile phone". At this time, the recombined name of the first target object 1 can include "sky blue, 5000W pixels, 36-hour battery life"; the recombined name of the first target object 2 can include "dream blue, 8000W pixels, 48-hour battery life"; the recombined name of the first target object 3 can include "starry sky blue, 100 million pixels, 24-hour battery life".

[0073] Embodiments of the present disclosure provide a search method. In this method, natural language description information input by a user on a search page is obtained, and object features parsed from the natural language description information are used as search criteria to obtain a first target object that matches the object features, and a restructured name of the first target object is displayed on the information item of the first target object. Among them, the natural language description information can reflect the user's needs, and the object features can reflect the focus points that the user is concerned about. Since the restructured name of the first target object includes information corresponding to the object features, the restructured name can intuitively display the information corresponding to the focus points that the user is concerned about to the user, which improves the information display efficiency. It is beneficial for the user to quickly obtain the information that they focus on by browsing the restructured name of the first target object, so as to compare different objects and assist in making decisions, improving the efficiency of the user to obtain information and enhancing the user experience.

[0074] In some embodiments, the object features include at least one feature dimension;

[0075] Displaying the restructured name of the first target object on the information item of the first target object includes:

[0076] In the restructured name of the first target object, the information corresponding to each feature dimension in the object information of the first target object is displayed from front to back according to the word order corresponding to at least one feature dimension in the natural language description information.

[0077] In the embodiments of the present disclosure, since the display order of the information corresponding to at least one feature dimension is the same as the word order of at least one feature dimension in the natural language description information, the information displayed first in the restructured name corresponds to the feature dimension that the user gives priority to considering in the natural language description information, which may be the information that the user is more concerned about, and the information displayed later in the restructured name corresponds to the feature dimension that the user inputs subsequently in the natural language description information, which may be the information that the user pays less attention to. This display method may be more in line with the user's demand focus and also more in line with the user's reading habit, improving the information display efficiency and also improving the efficiency of the user to obtain information.

[0078] In some embodiments, the object features include at least one feature dimension;

[0079] Displaying the restructured name of the first target object on the information item of the first target object includes:

[0080] In the restructured name of the first target object, the information corresponding to each feature dimension in the object information of the first target object is displayed from front to back according to the preset word order of each feature dimension under the object category of the first target object.

[0081] In the embodiments of the present disclosure, since the display order of the information corresponding to at least one feature dimension is the same as the preset word order of each feature dimension under the object category of the first target object, therefore, the information displayed at the front in the recombined name corresponds to the feature dimension with the preset word order at the front under the object category, which may be the information that is more helpful for assisting the user in making decisions, and the information displayed at the back in the recombined name corresponds to the feature dimension with the preset word order at the back under the object category, which may be the information that is less helpful for assisting the user in making decisions. This display method improves the orderliness of information display.

[0082] In some embodiments, the method further includes:

[0083] In response to dragging the information corresponding to the first feature dimension to the previous word order position or the next word order position of the information corresponding to the second feature dimension, display the updated recombined name of the first target object, and in the updated recombined name, the information corresponding to the first feature dimension is displayed before or after the information corresponding to the second feature dimension, and the first feature dimension and the second feature dimension are different feature dimensions among at least one feature dimension.

[0084] In the embodiments of the present disclosure, since it is supported to modify the word order position of the information corresponding to different feature dimensions in the recombined name through a drag operation, this enables the user to customize the word order position according to their attention degree to the information corresponding to different feature dimensions, which is more flexible and can better meet the personalized needs of the user.

[0085] In some embodiments, on the information item of the first target object, displaying the recombined name of the first target object includes:

[0086] In the recombined name of the first target object, prominently display the information corresponding to the object features in the object information of the first target object.

[0087] In the embodiments of the present disclosure, by prominently displaying the information corresponding to the object features, the information display becomes more intuitive and prominent, and it also forms a contrast with the remaining information in the recombined name, facilitating the user to quickly locate the information corresponding to the object features in the recombined name, improving the efficiency and intuitiveness of information display, and improving the efficiency of the user to obtain information.

[0088] In some embodiments, the object features include at least one feature dimension;

[0089] The method further includes:

[0090] In response to a trigger operation on the information corresponding to any feature dimension in the recombined name of the first target object, display the detailed page of the first target object, and the detailed page displays the information describing the first target object under the feature dimension.

[0091] In the embodiments of the present disclosure, when a user triggers information corresponding to any feature dimension in the recombined name, by directly jumping to the detail page and displaying the information describing the first target object under that feature dimension, a function of quickly obtaining the detailed information under that feature dimension is provided, without the user having to locate the detailed information under that feature dimension by themselves after jumping to the detail page, thereby improving the human-computer interaction efficiency.

[0092] In some embodiments, a target image corresponding to the first target object is further displayed on the information item of the first target object, and the degree of association between the target image and the object feature meets a preset condition.

[0093] In the embodiments of the present disclosure, the degree of association between the target image and the object feature meets a preset condition, and the target image can more intuitively reflect the information that the user is concerned about. This enables the user to quickly determine whether the object meets their own needs by browsing the target image, which not only improves the intuitiveness and readability of the information, but also reduces the time for obtaining key information, thereby improving the information display and acquisition efficiency.

[0094] In some embodiments, the object feature includes at least one feature dimension, and recombined information under a third feature dimension is further displayed on the information item of the first target object, where the third feature dimension is any one of the at least one feature dimension, and the recombined information under the third feature dimension is used to describe the first target object under the third feature dimension; the recombined information includes at least one of text, table, image, and video.

[0095] In the embodiments of the present disclosure, since the recombined information describes the first target object under the feature dimension that the user is concerned about, the key information that the user focuses on can be more detailedly displayed to the user through the recombined information, without the user having to search for the corresponding information in the detail page of the first target object by themselves, which improves the information display and acquisition efficiency.

[0096] In some embodiments, the recombined information under the third feature dimension is displayed in a slidable component in the information item of the first target object;

[0097] The method further includes:

[0098] In response to a sliding operation in the slidable component, recombined information under a fourth feature dimension is displayed in the slidable component, where the fourth feature dimension is another feature dimension among the at least one feature dimension other than the third feature dimension.

[0099] In the embodiments of the present disclosure, by displaying a slidable component, it is supported to switch and view the recombined information under different feature dimensions through a sliding operation without changing the existing layout in the page. This enables users to quickly obtain different key information, and further judge whether the first target object meets their own needs from multiple feature dimensions, which not only improves the information display efficiency, but also improves the human-computer interaction efficiency.

[0100] In some embodiments, at least one of a filtering label determined based on object features and a preset filtering label corresponding to the object category of the first target object is also displayed on the page showing the information items of the first target object:

[0101] The method further includes:

[0102] In response to a triggering operation on any filtering label, display a second target object in the first target object, where the second target object matches both the object features and the features indicated by the filtering label;

[0103] On the information item of the second target object, display a recombined name of the second target object, where the recombined name includes the information corresponding to the object features in the object information of the second target object.

[0104] In the embodiments of the present disclosure, by displaying at least one type of filtering label, a further quick filtering function is provided. The filtering label determined according to object features is more in line with the user's search preferences or search needs, and the preset filtering label corresponding to the object category can be used to supplement the content already input by the user, which is beneficial to improving the flexibility and search efficiency of information search.

[0105] In some embodiments, the recombined name further includes the information corresponding to the features indicated by the filtering label in the object information of the second target object.

[0106] In the embodiments of the present disclosure, after further quick filtering, the organization name is recombined according to the filtering label selected by the user to obtain a recombined name including the information corresponding to the features indicated by the filtering label. This realizes the timely follow-up of the user's needs, reduces the time for obtaining key information, facilitates the user to quickly obtain information, and improves the flexibility and search efficiency of information search.

[0107] In some embodiments, recombined information under the feature dimension corresponding to the filtering label is also displayed on the information item of the second target object, and the recombined information is used to describe the second target object under the feature dimension corresponding to the filtering label.

[0108] In the embodiments of the present disclosure, after the screening tag is triggered, the recombined information under the corresponding feature dimension is displayed on the information items of the second target object obtained by screening. This enables the user to quickly obtain the key information corresponding to the screening tag, and then determine whether the second target object meets their own needs, which not only improves the intuitiveness and readability of the information, but also reduces the time to obtain the key information and improves the information display and acquisition efficiency.

[0109] In some embodiments, the method further includes:

[0110] Based on the object features parsed from the natural language description information, adjustment prompt information is displayed. The adjustment prompt information is used to prompt an adjustment operation on the natural language description information for at least one feature dimension. The adjustment operation includes at least one of an addition operation, a deletion operation, and a replacement operation on the natural language description information under any feature dimension.

[0111] In the embodiments of the present disclosure, by displaying the adjustment prompt information, modification suggestions for the input natural language description information are provided to the user, which is beneficial to improving the flexibility of information search and the overall search efficiency.

[0112] The above Figure 2 The following is a flowchart of a search method of the present disclosure. The search solution provided by the present disclosure will be further elaborated below. Figure 3 is a flowchart of another search method shown according to an exemplary embodiment. Refer to Figure 3 , which is executed by the terminal and includes the following steps.

[0113] In step S301, the terminal displays a search page.

[0114] In the embodiments of the present disclosure, the principle of the terminal displaying the search page in step S301 is the same as that in step S201, and will not be elaborated here.

[0115] In step S302, the terminal obtains the natural language description information input in the search page.

[0116] In the embodiments of the present disclosure, the principle of the terminal obtaining the natural language description information in step S302 is the same as that in step S202, and will not be elaborated here.

[0117] In some embodiments, the terminal supports text input and voice input. Correspondingly, in the text input scenario, the terminal obtains the natural language description text input in the search page; or, in the voice input scenario, the terminal collects the voice input in the search page and converts the voice into a natural language description text.

[0118] Optionally, at least one of a search box or a voice input control is displayed on the search page. Correspondingly, when the search box is displayed on the search page, the terminal responds to the text input operation in the search box and displays the input natural language description text in the search box; when the voice input control is displayed on the search page, the terminal responds to the triggering operation on the voice input control, collects the input voice, and displays the natural language description text obtained by converting the voice on the search page.

[0119] Optionally, input prompt information is associated and displayed at the search box or the voice input control. The input prompt information is used to prompt the user to describe the content to be searched for the terminal to match the corresponding information. For example, the input prompt information is "Describe the item you want to see, and AI will help you find it", or "Describe the query content, and intelligent recommendations will be provided for you". Here, AI is Artificial Intelligence, that is, artificial intelligence.

[0120] In some embodiments, the terminal jumps from the recommendation page to the search page. Correspondingly, the terminal responds to the triggering operation on the search box on the recommendation page and displays the search page; or, the terminal responds to the voice input on the recommendation page and displays the search page. The recommendation page displays information about the object to be recommended for browsing.

[0121] For the convenience of describing the search page, see Figure 4 as shown Figure 4 is a schematic diagram of a search page shown according to an exemplary embodiment. Figure 4 (a) is the recommendation page. 401 is the search box on the recommendation page, and input prompt information is displayed in the search box. The terminal responds to the triggering operation on 401 and displays Figure 4 (b) the search page shown. 402 is the search box on the search page. Before the user inputs natural language description information, 402 can be displayed as blank, input prompt information, or recommended search information; after the user inputs natural language description information, the natural language description information input by the user is displayed in 402.

[0122] It should be noted that the terminal supports multiple input methods such as text input and voice input, making the input process of natural language description information more flexible and diverse, improving the convenience and efficiency of searching, and improving the human-computer interaction efficiency and the flexibility of searching.

[0123] In step S303, the terminal displays the information items of the first target object based on the object features parsed from the natural language description information, and the first target object matches the object features.

[0124] In the embodiments of the present disclosure, the principle of the terminal displaying the information item of the first target object in step S303 is the same as that in step S203, and will not be elaborated herein.

[0125] In some embodiments, the first target object is determined through a series of data processing procedures. Accordingly, natural language processing technology is adopted to parse the natural language description information to obtain the object features described by the natural language description information; based on the object features, a search is performed to obtain multiple candidate objects that match the object features; and the first target object is selected from the multiple candidate objects. This makes it more likely that the first target object displayed by the terminal for the user meets the user's needs and preferences, and improves the personalization level of the search.

[0126] Optionally, a comprehensive search is performed based on multiple data such as object characteristics, user evaluations, and the number of times the object is obtained to match multiple candidate objects, which ensures the relevance and accuracy of the search results. Optionally, based on the historical behavior data of the object logged in by the terminal, combined with multiple data such as object characteristics, user evaluations, and the number of times the object is obtained, the search results are sorted and filtered, and the first target object is selected from the multiple candidate objects. For example, a comprehensive score is determined based on the above information, and the candidate objects are sorted from high to low according to the comprehensive score, and the top 10 objects are selected from the multiple candidate objects for display. Among them, the historical behavior data is used to indicate the historical data of the object logged in by the current terminal interacting with the object in the application where the search page is located.

[0127] It should be noted that the above data processing procedure can be executed independently by the terminal or the server, or can be executed interactively by the terminal and the server. The embodiments of the present disclosure do not limit this. For example, taking the above data processing procedure being executed by the server as an example for illustration. After the terminal obtains the natural language description information input in the search page, it sends the natural language description information to the corresponding server. After the server processes the data to determine the first target object, it sends the first target object and the corresponding information to the terminal for subsequent display by the terminal.

[0128] In step S304, the terminal displays the recombined name of the first target object on the information item of the first target object, and the recombined name includes the information corresponding to the object features in the object information of the first target object.

[0129] In the embodiments of the present disclosure, the principle of the terminal displaying the recombined name of the first target object in step S304 is the same as that in step S204, and will not be elaborated herein.

[0130] In some embodiments, in the reorganized name of the first target object, the information corresponding to the object features in the object information of the first target object is highlighted. The highlighting forms include, but are not limited to, highlighting, bolding, jittering, color-changing, adding borders, adding background colors, etc. It should be noted that by highlighting the information corresponding to the object features, the information display becomes more intuitive and prominent, and it also forms a contrast with the remaining information in the reorganized name, facilitating the user to quickly locate the information corresponding to the object features in the reorganized name, improving the efficiency and intuitiveness of information display, and improving the efficiency of the user to obtain information.

[0131] Optionally, the object features include at least one feature dimension. For example, if the object features are "blue, light, good battery life", the feature dimensions included in the object features include color, weight, and battery life.

[0132] In some embodiments, the terminal displays the information corresponding to each feature dimension in a specific word order in the reorganized name of the first target object.

[0133] Correspondingly, in the reorganized name of the first target object, the terminal displays the information corresponding to each feature dimension in the object information of the first target object in the order from front to back according to the word order corresponding to at least one feature dimension in the natural language description information. For example, the natural language description information is "a blue, good-looking camera, good battery life mobile phone", the multiple feature dimensions include color, pixel, and battery life, and the word order of the color feature dimension is before the word order of the pixel feature dimension, and the word order of the pixel feature dimension is before the word order of the battery life feature dimension. Therefore, in the reorganized name, "sky blue" is displayed first, then "5000W pixels" is displayed, and finally "36-hour battery life" is displayed.

[0134] In the above manner, since the display order of the information corresponding to at least one feature dimension is the same as the word order of at least one feature dimension in the natural language description information, the information displayed first in the reorganized name corresponds to the feature dimension that the user first considers in the natural language description information, which may be the information that the user pays more attention to, and the information displayed later in the reorganized name corresponds to the feature dimension that the user inputs later in the natural language description information, which may be the information that the user pays less attention to. This display method may be more in line with the user's demand focus and also more in line with the user's reading habit, improving the information display efficiency and also improving the efficiency of the user to obtain information.

[0135] Accordingly, in the recombined name of the first target object, the information corresponding to each feature dimension in the object information of the first target object is displayed from front to back according to the preset word order of each feature dimension under the object category of the first target object. For example, the natural language description information is "a mobile phone that is blue, takes good pictures, and has good battery life". The multiple feature dimensions include color, pixel, and battery life. Under the object category of mobile phone, the preset word order of the feature dimension of pixel is before the preset word order of the feature dimension of battery life, and the preset word order of the feature dimension of battery life is before the preset word order of the feature dimension of color. Therefore, "5000W pixels" is displayed first in the recombined name, then "36-hour battery life" is displayed, and finally "sky blue" is displayed.

[0136] In the above method, since the display order of the information corresponding to at least one feature dimension is the same as the preset word order of each feature dimension under the object category of the first target object, therefore, the information displayed earlier in the recombined name corresponds to the feature dimension with a preset word order earlier under the object category, which may be the information that helps the user make decisions more, and the information displayed later in the recombined name corresponds to the feature dimension with a preset word order later under the object category, which may be the information that helps the user make decisions less. This display method improves the orderliness of information display.

[0137] It should be noted that the above specific word order is only for illustrative purposes. The terminal can also configure weights for the ranking of the word order positions corresponding to each feature dimension in the natural language description information, and the ranking of the preset word order positions of each feature dimension under the object category of the first target object, respectively, so as to determine the display order of the information corresponding to each feature dimension in the recombined name of the first target object by means of weighted summation.

[0138] In some embodiments, the terminal supports the user to adjust the display order of the information corresponding to the feature dimension. Accordingly, in response to dragging the information corresponding to the first feature dimension to the previous word order position or the next word order position of the information corresponding to the second feature dimension, the terminal displays the updated recombined name of the first target object. In the updated recombined name, the information corresponding to the first feature dimension is displayed before or after the information corresponding to the second feature dimension. The first feature dimension and the second feature dimension are different feature dimensions among at least one feature dimension. For example, the recombined name is "A brand mobile phone 5000W pixels sky blue", and the updated recombined name is "5000W pixels sky blue A brand mobile phone".

[0139] It should be noted that since it supports modifying the word order positions of the information corresponding to different feature dimensions in the recombined name through a drag operation, this enables the user to customize the word order positions according to their degree of attention to the information corresponding to different feature dimensions, which is more flexible and can better meet the personalized needs of the user.

[0140] In some embodiments, the terminal supports jumping to the corresponding position on the detail page by triggering the information in the recombined name. Accordingly, in response to a trigger operation on the information corresponding to any feature dimension in the recombined name of the first target object, the terminal displays the detail page of the first target object, and the information describing the first target object under the feature dimension is displayed on the detail page. For example, if the recombined name is "sky blue 5000W pixel battery life 36 hours", after triggering the keyword "battery life 36 hours", the terminal jumps to the detail page and displays the battery parameters on the detail page for the user to understand the information under the feature dimension of the battery life in detail.

[0141] It should be noted that when the user triggers the information corresponding to any feature dimension in the recombined name, by directly jumping to the detail page and displaying the information describing the first target object under this feature dimension, a function of quickly obtaining the detail information under this feature dimension is provided, without the user having to locate the detail information under this feature dimension by themselves after jumping to the detail page, improving the human-computer interaction efficiency.

[0142] In some embodiments, a target image corresponding to the first target object is also displayed on the information item of the first target object, and the degree of association between the target image and the object feature meets a preset condition. Optionally, the degree of association between the target image and the object feature is higher than that between other reference images corresponding to the first target object and the object feature. For example, the target image corresponding to the first target object is an image of a blue mobile phone among the images of mobile phones of multiple colors included in the first target object.

[0143] It should be noted that since the degree of association between the target image and the object feature meets the preset condition, the target image can more intuitively reflect the information that the user is concerned about. This enables the user to quickly judge whether the object meets their own needs by browsing the target image, not only improving the intuitiveness and readability of the information, but also reducing the time to obtain key information and improving the information display and acquisition efficiency.

[0144] In step S305, the terminal displays the recombined information under any feature dimension in the object features on the information item of the first target object, and the recombined information under this feature dimension is used to describe the first target object under this feature dimension.

[0145] In the embodiments of the present disclosure, for the convenience of description, this feature dimension is referred to as the third feature dimension. Among them, the recombined information includes at least one of text, table, image, and video.

[0146] For example, the first target object is a mobile phone, and the third feature dimension is the shooting ability. At this time, the recombined information of the first target object 1 includes the words "suitable for shooting landscapes and sports" and the photographic works taken by this mobile phone; the recombined information of the first target object 2 includes the words "suitable for shooting portraits and macro" and the photographic works taken by this mobile phone; the recombined information of the first target object 3 includes the words "ranked first in the pixel list" and the photographic works taken by this mobile phone.

[0147] It should be noted that since the recombined information describes the information of the first target object under the feature dimension concerned by the user, the key information that the user focuses on can be shown to the user in more detail through the recombined information, without the user having to search for the corresponding information on the details page of the first target object by themselves, which improves the information display and acquisition efficiency.

[0148] For the convenience of describing the information items of the first target object, see Figure 5 shown in Figure 5 is a schematic diagram of a page showing information items according to an exemplary embodiment. Among them, in the area 501 are the information items of the first target object. 5011 is the object name of the first target object, 5012 is the representative image of the first target object, and in the area 5013 is the recombined information of the first target image.

[0149] It should be noted that the embodiments of the present disclosure do not limit the display form of the recombined information. In addition to directly displaying the recombined information, the terminal can also control the display of the recombined information by any one of the following methods A and B.

[0150] Method A: Control the display of the recombined information under the third feature dimension through a display component. The terminal displays an expansion component on the information item of the first target object; in response to a trigger operation on the expansion component, the recombined information under the third feature dimension is displayed on the information item of the first target object. Optionally, when there are multiple feature dimensions in the object features, the terminal respectively displays the expansion components corresponding to each feature dimension. See Figure 5 shown in

[0151] It should be noted that by displaying the expansion component instead of directly displaying the recombined information, the terminal makes the current page more concise and avoids interference to the user caused by a large amount of information. At the same time, since the area occupied by the expansion component is smaller than the area occupied by the recombined information, this also enables more information items of the first target object to be displayed on the page at the same time, thus facilitating the user to compare and select multiple first target objects and improving the information display efficiency.

[0152] Mode B: The recombined information in the third feature dimension is displayed in the slidable component in the information item of the first target object. In response to a sliding operation in the slidable component, the terminal displays the recombined information in the fourth feature dimension in the slidable component, where the fourth feature dimension is another feature dimension among at least one feature dimension other than the third feature dimension. Optionally, the slidable component supports at least one of left-right sliding operations and front-back sliding operations, which are not limited here. See Figure 5 As shown, 503 is the slidable component corresponding to the first target object.

[0153] It should be noted that by displaying the slidable component, the terminal supports switching to view the recombined information in different feature dimensions through a sliding operation without changing the existing layout in the page. This enables the user to quickly obtain different key information, and then determine whether the first target object meets their own needs for multiple feature dimensions. This not only improves the information display efficiency but also improves the human-computer interaction efficiency.

[0154] It should be noted that the above steps S304 to S305 do not distinguish the order, that is, the recombined name and recombined information of the first target object are displayed in the information item at the same time. In addition, the terminal supports further filtering the currently displayed first target object. See the following steps S306 and S307 for details.

[0155] In step S306, the terminal, in response to a trigger operation on any filtering label further displayed on the page of the information item displaying the first target object, displays the second target object in the first target object, where the second target object matches both the object features and the features indicated by the filtering label.

[0156] In the embodiments of the present disclosure, the filtering label can be one or multiple. See Figure 5 As shown, 504 is a filtering label. Optionally, the filtering labels displayed on the page include at least one of the following categories: filtering labels determined based on object features, that is, the first category of filtering labels; preset filtering labels corresponding to the object category of the first target object, that is, the second category of filtering labels. If the filtering label is a variable filtering label generated and determined according to natural language description information, such as generated by AI based on natural description information, then when the natural language description information input by the user changes, the filtering label also changes accordingly. This is more in line with the user's search preferences or search needs, while the preset filtering labels corresponding to the object category can supplement the content already input by the user.

[0157] For example, when the natural language description information is "a mobile phone that is blue, takes good photos, and costs around a thousand yuan", the object category is a mobile phone. On the page, there is a first type of filtering label "Takes good photos", and there are also second type of filtering labels such as "Long battery life", "Large screen", "Many positive reviews", and "Dual SIM dual standby". When the natural language description information is "I want a lightweight camera suitable for traveling", the object category is a camera. On the page, there are second type of filtering labels such as "High definition", "Large storage capacity", "Anti-shake function", and "Small and portable".

[0158] In some embodiments, when the terminal displays multiple filtering labels, the terminal supports the user to control the display of different filtering labels on the page. Correspondingly, in response to a sliding operation in the display area of the multiple filtering labels, the terminal displays other filtering labels in the display area.

[0159] It should be noted that by displaying at least one type of filtering label, the terminal provides a function of further quick filtering. Compared with the traditional method of presetting fixed filtering options in advance, through the above method, the terminal provides filtering labels that are more in line with the user's preferences and needs according to the natural language description information input by the user, which not only improves the personalization level, but also improves the flexibility and search efficiency of information search.

[0160] In step S307, the terminal displays the recombined name of the second target object on the information item of the second target object, and the recombined name includes the information corresponding to the object characteristics in the object information of the second target object.

[0161] In the embodiments of the present disclosure, optionally, the recombined name further includes the information corresponding to the characteristics indicated by the filtering label in the object information of the second target object. That is, when the filtering label is triggered to further filter the first target object, the second target object is obtained. The recombined name of the second target object can be the same as before the filtering, that is, it only includes the information corresponding to the object characteristics, or it can be reorganized based on the filtering label, that is, it includes both the information corresponding to the object characteristics and the information corresponding to the characteristics indicated by the filtering label. For example, when the recombined name of the second target object before filtering is "A brand mobile phone with 50 million pixels and sky blue color", and the filtering label is "Long battery life", the recombined name after filtering by the filtering label can remain unchanged, or it can be "A brand mobile phone with 50 million pixels and sky blue color, 36-hour battery life".

[0162] It should be noted that after further rapid screening, the organization names are reorganized according to the screening tags selected by the user to obtain reorganized names including information corresponding to the features indicated by the screening tags. This realizes the timely follow-up of the user's needs, reduces the time for obtaining key information, facilitates the user to quickly obtain information, and improves the flexibility and efficiency of information search.

[0163] In some embodiments, reorganized information under the feature dimension corresponding to the screening tag is also displayed on the information item of the second target object, and the reorganized information is used to describe the second target object under the feature dimension corresponding to the screening tag.

[0164] For example, when the triggered screening tag is "long battery life", the reorganized information under the feature dimension corresponding to the screening tag includes battery life information, such as one or more parameters among battery type, battery capacity, full charge battery life, charging power, and the duration required to fully charge, etc. For example, the reorganized information of the second target object A at this time is something like "The battery type is graphene, the full charge battery life is 48 hours, and the duration required to fully charge is 10 minutes"; the reorganized information of the second target object B at this time is something like "The battery type is potassium manganate, the full charge battery life is 42 hours, and the duration required to fully charge is 25 minutes"; the reorganized information of the second target object C at this time is something like "The battery type is potassium manganate, the full charge battery life is 48 hours, and the duration required to fully charge is 30 minutes".

[0165] It should be noted that by displaying the reorganized information under the corresponding feature dimension on the information item of the second target object obtained by screening after the screening tag is triggered, this enables the user to quickly obtain the key information corresponding to the screening tag, and then determine whether the second target object meets their own needs. This not only improves the intuitiveness and readability of the information, but also reduces the time for obtaining key information and improves the information display and acquisition efficiency.

[0166] Optionally, if any screening tag displayed on the page has been described by natural language description information, then in response to the trigger operation on this screening tag, since the first target object at this time meets the description of this screening tag, there is no need to perform screening again, and it is only necessary to keep the first target object still displayed on the page. However, the reorganized information of the third feature dimension displayed on the information item of each first target object is replaced with the reorganized information under the feature dimension corresponding to this screening tag.

[0167] For ease of description, refer to Figure 6 as shown in Figure 6 FIG. 6 is a schematic diagram of another page displaying information items according to an exemplary embodiment. 601 is the triggered screening tag, and 602 is the reorganized information of the second target object corresponding to the feature dimension corresponding to this screening tag.

[0168] In some embodiments, the terminal displays adjustment prompt information to prompt for adjustment of the existing natural language description text. Accordingly, based on the object features parsed from the natural language description information, the terminal displays adjustment prompt information, which is used to prompt for adjustment operations on the natural language description information for at least one feature dimension. The adjustment operations include at least one of addition, deletion, and replacement operations on the natural language description information under any feature dimension.

[0169] For example, when the natural language description information is "a mobile phone that is blue, takes good photos, and costs around a thousand yuan", the adjustment prompt information includes feature dimensions such as color, price, brand, and weight. The adjustment prompt information is used to prompt for further limitation of the brand and weight in the natural language description, or deletion or replacement of the existing descriptions for color and price. It should be noted that by displaying the adjustment prompt information, the terminal provides the user with modification suggestions for the input natural language description information, which is beneficial to improving the flexibility of information search and the overall search efficiency.

[0170] In some embodiments, in response to a trigger operation on an information item of any first target object, the terminal displays a detail page associated with the first target object. The detail page associated with the first target object is used to display the detail information of the first target object and obtain the first target object. For ease of description, refer to Figure 7 shown Figure 7 is a schematic diagram of a detail page shown according to an exemplary embodiment. Among them, 701 is a control for obtaining the first target object. It should be noted that through the above method, the terminal supports quick jump to the detail page associated with the first target object, facilitating the user to understand and obtain the first target object in more detail, with simple operation and improved human-computer interaction efficiency.

[0171] For ease of describing the overall process, refer to Figure 8 shown Figure 8 is a schematic diagram of an overall process shown according to an exemplary embodiment. First, input object features. Accordingly, obtain natural language description information containing the object features; then, perform information recognition. Accordingly, use natural language processing technology to identify keywords and intentions in the natural language description information, such as obtaining the parsed object features; perform information extraction. Accordingly, according to the identified information, match relevant objects in the database and extract relevant content in the object information, such as extracting information matching the object features; perform information arrangement. Accordingly, sort and filter the search results to ensure that the displayed objects best meet the user's needs; finally, perform information display. Accordingly, display the recombined name and recombined information in an intuitive manner in the user interface.

[0172] The embodiments of the present disclosure provide a search method. Through natural language processing technology, it can quickly understand and respond to complex search requirements of users, reduce the multiple screenings and comparisons that users need to perform in traditional search methods, and greatly improve the search efficiency. Secondly, users can describe their shopping needs in natural language, and the terminal automatically provides accurate search results, enabling users to find the required objects more intuitively and conveniently, thus significantly enhancing the user experience. Finally, not only are the objects that meet the user's description screened out, but also through specific formats and display methods, such as the standardization of object names and the prominent display of key features, users can quickly obtain the key information of the objects, improving the information display and acquisition efficiency.

[0173] The technical effects of this method are introduced below.

[0174] First of all, in this method, the terminal supports users to input inaccurate or relatively colloquial natural language description information, rather than requiring users to input accurate keywords. Since the parsing result of the natural language description information includes the object features described by the natural language description information, and the object features can reflect the user's needs and be used as the basis for searching, thus realizing the accurate search for the first target object. Therefore, through the above method, when the natural language description information input by the user does not include accurate keywords, the terminal can still provide accurate search results based on the object features, thereby improving the search accuracy and reducing the requirements for the information input by the user, enabling users to input natural language description information according to their own language habits, enhancing the flexibility. Therefore, the embodiments of the present disclosure can handle complex and diverse search requirements of users and have a wider scope of application.

[0175] Secondly, the natural language description information in this method can reflect the user's needs, the object features can reflect the focus of the user's attention, and the restructured name of the first target object includes information corresponding to the object features. This method supports displaying the above information in a prominent display manner and also supports displaying the above information in a specific display order. Therefore, the restructured name can intuitively display the key information that the user focuses on, which improves the information display efficiency, is conducive to users quickly obtaining the information they focus on by browsing the restructured name of the first target object, thereby comparing different objects and assisting in decision-making, improving the efficiency of users obtaining information, and enhancing the user experience.

[0176] In addition, the information items of the target object also support displaying the target image and the reorganized information. Among them, the target image can more intuitively reflect the information that the user is concerned about, and the reorganized information is the information describing the first target object under the feature dimension that the user is concerned about. This enables the user to quickly determine whether the object meets their own needs by browsing the target image and the reorganized information, without the user having to search for the corresponding information in the details page of the first target object by themselves. This not only improves the intuitiveness and readability of the information, but also reduces the time to obtain key information and improves the information display and acquisition efficiency.

[0177] Any combination of the above optional technical solutions can form an optional embodiment of the present disclosure, which will not be elaborated here one by one.

[0178] Figure 9 It is a block diagram of a search device shown according to an exemplary embodiment. As Figure 9 shown, the device includes: a first display unit 901, an acquisition unit 902, and a second display unit 903.

[0179] The first display unit 901 is configured to display a search page;

[0180] The acquisition unit 902 is configured to acquire the natural language description information input in the search page;

[0181] The second display unit 903 is configured to display the information items of the first target object based on the object features parsed from the natural language description information, and the first target object matches the object features;

[0182] The second display unit 903 is further configured to display the reorganized name of the first target object on the information items of the first target object, and the reorganized name includes the information corresponding to the object features in the object information of the first target object.

[0183] In some embodiments, the object features include at least one feature dimension;

[0184] The second display unit 903 is configured to display, in the reorganized name of the first target object, the information corresponding to each feature dimension in the object information of the first target object in the order from front to back according to the word order corresponding to at least one feature dimension in the natural language description information.

[0185] In some embodiments, the object features include at least one feature dimension;

[0186] The second display unit 903 is configured to display, in the reorganized name of the first target object, the information corresponding to each feature dimension in the object information of the first target object in the order from front to back according to the preset word order of each feature dimension under the object category of the first target object.

[0187] In some embodiments, the second display unit 903 is configured to display an updated recombined name of the first target object in response to dragging the information corresponding to the first feature dimension to a position before or after the information corresponding to the second feature dimension in the word order. In the updated recombined name, the information corresponding to the first feature dimension is displayed before or after the information corresponding to the second feature dimension, and the first feature dimension and the second feature dimension are different feature dimensions among at least one feature dimension.

[0188] In some embodiments, the second display unit 903 is configured to highlight the information corresponding to the object features in the object information of the first target object in the recombined name of the first target object.

[0189] In some embodiments, the object features include at least one feature dimension;

[0190] The second display unit 903 is further configured to display a detail page of the first target object in response to a trigger operation on the information corresponding to any feature dimension in the recombined name of the first target object. The detail page displays information describing the first target object under the feature dimension.

[0191] In some embodiments, a target image corresponding to the first target object is further displayed on the information item of the first target object, and the degree of association between the target image and the object features meets a preset condition.

[0192] In some embodiments, the object features include at least one feature dimension, and recombined information under a third feature dimension is further displayed on the information item of the first target object. The third feature dimension is any one of the at least one feature dimension, and the recombined information under the third feature dimension is used to describe the first target object under the third feature dimension; the recombined information includes at least one of text, table, image, and video.

[0193] In some embodiments, the recombined information under the third feature dimension is displayed in a slidable component in the information item of the first target object;

[0194] The second display unit 903 is further configured to display recombined information under a fourth feature dimension in the slidable component in response to a sliding operation in the slidable component. The fourth feature dimension is another feature dimension other than the third feature dimension among the at least one feature dimension.

[0195] In some embodiments, Figure 10 is a block diagram of another search device shown according to an exemplary embodiment, as Figure 10 shown, at least one of a filtering label determined based on object features and a preset filtering label corresponding to the object category of the first target object is further displayed on the page displaying the information item of the first target object:

[0196] The apparatus further includes:

[0197] A third display unit 904, configured to display a second target object in the first target object in response to a triggering operation on any filtering label, where the second target object matches both the object feature and the feature indicated by the filtering label; and display a recombined name of the second target object on an information item of the second target object, where the recombined name includes information corresponding to the object feature in the object information of the second target object.

[0198] In some embodiments, the recombined name further includes information corresponding to the feature indicated by the filtering label in the object information of the second target object.

[0199] In some embodiments, recombined information in a feature dimension corresponding to the filtering label is further displayed on the information item of the second target object, and the recombined information is used to describe the second target object in the feature dimension corresponding to the filtering label.

[0200] In some embodiments, the apparatus further includes:

[0201] A fourth display unit 905, configured to display adjustment prompt information based on the object feature parsed from the natural language description information, where the adjustment prompt information is used to prompt an adjustment operation on the natural language description information for at least one feature dimension, and the adjustment operation includes at least one of an addition operation, a deletion operation, and a replacement operation on the natural language description information in any feature dimension.

[0202] An embodiment of the present disclosure provides a search apparatus. The apparatus obtains natural language description information input by a user on a search page, uses the object feature parsed from the natural language description information as a search basis to obtain a first target object that matches the object feature, and displays a recombined name of the first target object on an information item of the first target object. Among them, the natural language description information can reflect the user's needs, and the object feature can reflect the user's focus. Since the recombined name of the first target object includes information corresponding to the object feature, the recombined name can intuitively display the content corresponding to the user's focus to the user, which improves the information display efficiency, helps the user quickly obtain the content they focus on by browsing the recombined name of the first target object, thereby comparing different objects and assisting in decision-making, improving the user's information acquisition efficiency, and enhancing the user experience.

[0203] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure.

[0204] It should be noted that the search device provided in the above embodiments is only illustrated by the division of the above functional units. In practical applications, the above functions can be allocated to different functional units according to needs, that is, the internal structure of the electronic device is divided into different functional units to complete all or part of the functions described above. In addition, the search device provided in the above embodiments and the embodiments of the search method belong to the same concept. For the specific implementation process, please refer to the method embodiments and will not be elaborated here.

[0205] Regarding the search device in the above embodiments, the specific manners in which each module performs operations have been described in detail in the embodiments related to the method and will not be elaborated here.

[0206] Figure 11 It is a block diagram of an electronic device shown according to an exemplary embodiment. Generally, the electronic device 1100 includes: a processor 1101 and a memory 1102.

[0207] The processor 1101 may include one or more processing cores, such as a 4-core processor, an 11-core processor, etc. The processor 1101 may be implemented in at least one of the following hardware forms: DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 1101 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the wake state, also known as the CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 1101 may be integrated with a GPU (Graphics Processing Unit), and the GPU is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 1101 may further include an AI (Artificial Intelligence) processor, which is used to process computational operations related to machine learning.

[0208] The memory 1102 may include one or more computer-readable storage media, which may be non-transitory. The memory 1102 may also include high-speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices and flash storage devices. In some embodiments, the non-transitory computer-readable storage media in the memory 1102 is used to store at least one program code, and the at least one program code is used to be executed by the processor 1101 to implement the search method provided in the method embodiments of the present disclosure.

[0209] In some embodiments, the electronic device 1100 may further optionally include: a peripheral device interface 1103 and at least one peripheral device. The processor 1101, the memory 1102, and the peripheral device interface 1103 may be connected through a bus or signal lines. Each peripheral device may be connected to the peripheral device interface 1103 through a bus, signal lines, or a circuit board. Specifically, the peripheral devices include at least one of a radio frequency circuit 1104, a display screen 1105, a camera assembly 1106, an audio circuit 1107, and a power supply 1108.

[0210] The peripheral device interface 1103 may be used to connect at least one peripheral device related to I / O (Input / Output) to the processor 1101 and the memory 1102. In some embodiments, the processor 1101, the memory 1102, and the peripheral device interface 1103 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 1101, the memory 1102, and the peripheral device interface 1103 may be implemented on a separate chip or circuit board, and this embodiment does not limit this.

[0211] The radio frequency circuit 1104 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit 1104 communicates with a communication network and other communication devices through electromagnetic signals. The radio frequency circuit 1104 converts an electrical signal into an electromagnetic signal for transmission, or converts the received electromagnetic signal into an electrical signal. Optionally, the radio frequency circuit 1104 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a subscriber identity module card, and so on. The radio frequency circuit 1104 can communicate with other electronic devices through at least one wireless communication protocol. The wireless communication protocol includes but is not limited to: a metropolitan area network, various generations of mobile communication networks (2G, 3G, 4G, and 5G), a wireless local area network, and / or a WiFi (Wireless Fidelity) network. In some embodiments, the radio frequency circuit 1104 may further include a circuit related to NFC (Near Field Communication), which is not limited in this disclosure.

[0212] The display screen 1105 is used to display a UI (User Interface). The UI may include graphics, text, icons, videos, and any combination thereof. When the display screen 1105 is a touch display screen, the display screen 1105 also has the ability to collect touch signals on or above the surface of the display screen 1105. The touch signal can be input to the processor 1101 as a control signal for processing. At this time, the display screen 1105 can also be used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or a soft keyboard. In some embodiments, the display screen 1105 can be one, disposed on the front panel of the electronic device 1100; in other embodiments, the display screen 1105 can be at least two, respectively disposed on different surfaces of the electronic device 1100 or in a folded design; in still other embodiments, the display screen 1105 can be a flexible display screen, disposed on a curved surface or a folded surface of the electronic device 1100. Even, the display screen 1105 can be set to an irregular non-rectangular shape, that is, a special-shaped screen. The display screen 1105 can be prepared using materials such as LCD (Liquid Crystal Display) and OLED (Organic Light-Emitting Diode).

[0213] The camera assembly 1106 is used to capture images or videos. Optionally, the camera assembly 1106 includes a front camera and a rear camera. Generally, the front camera is disposed on the front panel of the electronic device, and the rear camera is disposed on the back of the electronic device. In some embodiments, there are at least two rear cameras, which are any one of a main camera, a depth camera, a wide-angle camera, and a telephoto camera, so as to implement the function of background blurring by fusing the main camera and the depth camera, panoramic shooting and VR (Virtual Reality) shooting functions or other fusion shooting functions by fusing the main camera and the wide-angle camera. In some embodiments, the camera assembly 1106 may further include a flash. The flash can be a single-color temperature flash or a dual-color temperature flash. The dual-color temperature flash refers to the combination of a warm light flash and a cold light flash, which can be used for light compensation under different color temperatures.

[0214] The audio circuit 1107 may include a microphone and a speaker. The microphone is used to collect sound waves of the user and the environment, and convert the sound waves into electrical signals and input them to the processor 1101 for processing, or input them to the radio frequency circuit 1104 to achieve voice communication. For the purpose of stereo collection or noise reduction, there may be multiple microphones, which are respectively disposed at different parts of the electronic device 1100. The microphone can also be an array microphone or an omnidirectional collection type microphone. The speaker is used to convert the electrical signal from the processor 1101 or the radio frequency circuit 1104 into sound waves. The speaker can be a traditional thin film speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can not only convert the electrical signal into sound waves audible to humans, but also convert the electrical signal into sound waves inaudible to humans for uses such as ranging. In some embodiments, the audio circuit 1107 may further include a headphone jack.

[0215] The power supply 1108 is used to supply power to each component in the electronic device 1100. The power supply 1108 can be alternating current, direct current, a primary battery or a rechargeable battery. When the power supply 1108 includes a rechargeable battery, the rechargeable battery can support wired charging or wireless charging. The rechargeable battery can also be used to support fast charging technology.

[0216] Those skilled in the art can understand that Figure 11 the structure shown in

[0217] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 1102 including instructions, and the above instructions can be executed by a processor 1101 of a terminal 1100 to complete the above search method. Optionally, the computer-readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0218] A computer program product includes a computer program which, when executed by a processor, implements the above search method.

[0219] After considering the specification and practicing the invention disclosed herein, those skilled in the art will readily conceive of other embodiments of the present disclosure. The present disclosure is intended to cover any variations, uses, or adaptations of the present disclosure, which follow the general principles of the present disclosure and include known common knowledge or conventional technical means in the technical field not disclosed by the present disclosure. The specification and embodiments are only regarded as exemplary, and the true scope and spirit of the present disclosure are pointed out by the following claims.

[0220] It should be understood that the present disclosure is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present disclosure is only limited by the appended claims.

Claims

1. A search method, characterized in that: The method comprises: Display the search page; Obtaining natural language description information entered in the search page; Based on the object features obtained by parsing the natural language description information, displaying information items of a first target object, the first target object matching the object features; On the information item of the first target object, a reorganized name of the first target object is displayed, where the reorganized name includes information corresponding to the object feature in the object information of the first target object.

2. The search method according to claim 1, characterized in that: The object feature comprises at least one feature dimension; The displaying, on the information item of the first target object, the reorganized name of the first target object comprises: In the reorganized name of the first target object, information corresponding to each characteristic dimension in the object information of the first target object is displayed from front to back according to the word order corresponding to the at least one characteristic dimension in the natural language description information.

3. The search method according to claim 1, characterized in that: The object feature comprises at least one feature dimension; The displaying, on the information item of the first target object, the reorganized name of the first target object comprises: In the reorganized name of the first target object, information corresponding to each characteristic dimension in the object information of the first target object is displayed from front to back according to the preset word order for each characteristic dimension under the object category of the first target object.

4. The search method according to any one of claims 2 or 3, characterized in that: The method further comprises: In response to dragging the information corresponding to the first characteristic dimension to the previous word order position or the next word order position of the information corresponding to the second characteristic dimension, the updated reorganized name of the first target object is displayed, and the information corresponding to the first characteristic dimension in the updated reorganized name is displayed before or after the information corresponding to the second characteristic dimension, and the first characteristic dimension and the second characteristic dimension are different characteristic dimensions among the at least one characteristic dimension.

5. The search method according to claim 1, characterized in that: The displaying, on the information item of the first target object, the reorganized name of the first target object comprises: In the reorganized name of the first target object, information corresponding to the object feature in the object information of the first target object is highlighted.

6. The search method according to claim 1, characterized in that: The object feature comprises at least one feature dimension; The method further comprises: In response to a triggering operation on information corresponding to any characteristic dimension in the reorganized name of the first target object, a detail page of the first target object is displayed, wherein the detail page displays information describing the first target object under the characteristic dimension.

7. The search method according to claim 1, characterized in that: A target image corresponding to the first target object is also displayed on the information item of the first target object, and the correlation between the target image and the object feature meets a preset condition.

8. The search method according to claim 1, characterized in that: The object feature includes at least one feature dimension, and reorganized information under a third feature dimension is further displayed on the information item of the first target object, where the third feature dimension is any feature dimension of the at least one feature dimension, and the reorganized information under the third feature dimension is used to describe the first target object under the third feature dimension; The reorganized information includes at least one of text, table, image and video.

9. The search method according to claim 8, characterized in that: The reorganized information under the third characteristic dimension is displayed in a slidable component in the information item of the first target object; The method further comprises: In response to a sliding operation in the slidable component, reorganized information in a fourth characteristic dimension is displayed in the slidable component, where the fourth characteristic dimension is another characteristic dimension in the at least one characteristic dimension except the third characteristic dimension.

10. The search method according to claim 1, characterized in that: The page displaying the information item of the first target object also displays at least one of the filter tags determined based on the object feature and the preset filter tags corresponding to the object category of the first target object: The method further comprises: In response to a triggering operation on any filtering tag, displaying a second target object among the first target objects, the second target object matching both the object feature and the feature indicated by the filtering tag; On the information item of the second target object, a reorganized name of the second target object is displayed, where the reorganized name includes information corresponding to the object feature in the object information of the second target object.

11. The search method according to claim 10, characterized in that: The recombinant name also includes information in the object information of the second target object corresponding to the feature indicated by the screening tag.

12. The search method according to claim 10, characterized in that: The information item of the second target object also displays reorganization information under the feature dimension corresponding to the filtering tag, and the reorganization information is used to describe the second target object under the feature dimension corresponding to the filtering tag.

13. The search method according to claim 1, characterized in that: The method further comprises: Based on the object features obtained by parsing the natural language description information, adjustment prompt information is displayed, and the adjustment prompt information is used to prompt an adjustment operation to be performed on the natural language description information for at least one feature dimension, and the adjustment operation includes at least one of an addition operation, a deletion operation, and a replacement operation on the natural language description information under any feature dimension.

14. A search device, characterized in that: The device comprises: A first display unit, configured to display a search page; an acquisition unit, configured to acquire natural language description information input in the search page; a second display unit configured to display information items of a first target object based on the object features obtained by parsing the natural language description information, the first target object matching the object features; The second display unit is further configured to display a reorganized name of the first target object on the information item of the first target object, wherein the reorganized name includes information corresponding to the object feature in the object information of the first target object.

15. An electronic device, characterized in that: The electronic device comprises: one or more processors; a memory for storing program code executable by the processor; The processor is configured to execute the program code to implement the search method according to any one of claims 1 to 13.

16. A computer-readable storage medium, characterized in that: When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the search method as described in any one of claims 1 to 13.

17. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the search method according to any one of claims 1 to 13 is implemented.

Images