Search processing method, device, equipment and storage medium

Abstract

The embodiments of the present application provide a search processing method, apparatus, device and storage medium. When a user terminal obtains a user search request through the human-computer interaction interface of a target application, the user search request is reported to a background business server. The business server determines a scene set corresponding to the search keyword based on the user search request, and scores and sorts each scene in the scene set based on multiple preset filtering dimensions, determines a preset number of scenes ranked first, and sends the labels of the preset number of scenes to the target application on the user terminal, so that the target application can display the labels of the preset number of scenes through the human-computer interaction interface. In this technical solution, since the preset number of scenes to be displayed can be adjusted based on the preset filtering dimensions, the consistency between the displayed scenes and user needs can be improved, and the consistency between the recommended products and user needs can be improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of Internet technology, and in particular to a search processing method, apparatus, device and storage medium. Background Art

[0002] With the rapid development of Internet technology and social economy, online shopping, which allows users to purchase the goods they need without leaving home, has become more and more popular. Since there are many products to be displayed on e-commerce websites, but the terminal page space is limited, tabs can be used to control the display of the page, thereby saving page space and reducing the density of information display while ensuring the display of information.

[0003] At present, fixed scene tags are set on the human-computer interaction interface of the e-commerce website. The e-commerce client can send the user's search request to the e-commerce server and receive the recommended products sent by the e-commerce server, and then display the received recommended products under at least one fixed scene tag. Finally, based on the scene tag selected by the user, the products under the scene tag are displayed on the human-computer interaction interface.

[0004] In the process of implementing the present invention, the inventors found that there are at least the following problems in the prior art: the scene labels displayed on the human-computer interaction interface of the e-commerce website are fixed, the products under each scene label have a low correlation with the user, and there is a problem of poor consistency between the recommended products and user needs. Summary of the invention

[0005] The embodiments of the present application provide a search processing method, apparatus, device and storage medium to solve the problem in the prior art that the recommended products are poorly consistent with user needs due to the low correlation between the products under each scene tag and the user.

[0006] In a first aspect, an embodiment of the present application provides a search processing method, including:

[0007] Receiving a user search request sent by a user terminal through a target application, the user search request including: a search keyword and a user identifier;

[0008] Determining, according to the user search request, a scene set corresponding to the search keyword;

[0009] Based on the preset multiple screening dimensions, the scenes in the scene set are scored and sorted to determine a preset number of scenes ranked first;

[0010] The tags of the preset number of scenes are sent to the target application on the user terminal.

[0011] In a possible design of the first aspect, determining, according to the user search request, a scene set corresponding to the search keyword includes:

[0012] Determine, according to the search keyword, a first object set corresponding to the search keyword;

[0013] A scene set corresponding to the search keyword is determined according to feature information of each object in the first object set and location information of a store to which each object belongs.

[0014] In another possible design of the first aspect, the scoring and ranking of the scenes in the scene set based on the preset multiple screening dimensions to determine a preset number of scenes ranked first includes:

[0015] According to the user identifier, obtaining historical operation information of the user corresponding to the user identifier;

[0016] Determine, according to the historical operation information and a plurality of preset screening dimensions, a scene score of each scene in the scene set on each screening dimension;

[0017] Determine the score of each scene in the scene set according to the scene score of each scene in the scene set in each screening dimension and the preset weight coefficient of each screening dimension;

[0018] All scenes in the scene set are sorted in descending order of scores, and a preset number of scenes ranked first are determined.

[0019] In another possible design of the first aspect, after sending the tags of the preset number of scenes to the target application on the user terminal, the method further includes:

[0020] Receiving a scene parameter of a target search scene sent by the user terminal through the target application;

[0021] According to the scene parameter and the search keyword, a first-level search object set under the target search scene and at least two sub-tags included in the target search scene are determined.

[0022] Optionally, the method further includes:

[0023] Determining, according to the flow control rule, a resource code of each first-level object in the first-level search object set;

[0024] Determining an arrangement order of the at least two subtags according to data content and quality of each subtag of the at least two subtags;

[0025] Generate a first search result according to the resource code of each first-level object, the tag parameters of the at least two sub-tags, and the arrangement order of the at least two sub-tags;

[0026] The first search result is sent to the target application on the user terminal.

[0027] Optionally, after sending the first search result to the target application on the user terminal, the method further includes:

[0028] receiving a tag parameter of at least one target subtag sent by the user terminal through the target application;

[0029] Determining a second-level search object set corresponding to the at least one target subtag according to the search keyword and the tag parameter of the at least one target subtag;

[0030] Determining, according to the flow control rule, a resource code of each second-level object in the second-level search object set;

[0031] The resource code of each second-level object in the second-level search object set is sent to the target application of the user terminal, and the target application is used to display the object picture corresponding to the resource code of each second-level object through a human-computer interaction interface.

[0032] In a second aspect, an embodiment of the present application provides a search processing method, including:

[0033] Acquire a user search request issued by a user through a human-computer interaction interface of a target application, wherein the user search request includes: a search keyword and a user identifier;

[0034] receiving tags of a preset number of scenarios sent by a business server, where the tags of the preset number of scenarios are determined by the business server according to the user search request and a plurality of preset screening dimensions;

[0035] The labels of the preset number of scenes are displayed through the human-computer interaction interface of the target application.

[0036] In a possible design of the second aspect, after displaying the labels of the preset number of scenes through the human-computer interaction interface of the target application, the method further includes:

[0037] Acquire a scene selection indication of the user, where the scene selection indication is used to indicate a target search scene selected by the user;

[0038] Sending the scene parameters of the target search scene to the service server;

[0039] receiving a first search result sent by the business server, the first search result comprising: a resource code and at least two subtags of each first-level object in the first-level search object set, and an arrangement order of the at least two subtags, wherein the first-level search object set, the at least two subtags, and the arrangement order of the at least two subtags are determined by the business server according to the scenario parameter;

[0040] Obtaining, according to the resource code of each first-level object, an object image of each first-level object in the first-level search object set;

[0041] The object images of all first-level objects in the first-level object set are displayed under the directory of the target search scene through the target application, and the at least two sub-tags are displayed according to the arrangement order of the at least two sub-tags.

[0042] Optionally, after displaying the object images of all first-level objects in the first-level object set under the directory of the target search scene by the target application, and displaying the at least two sub-tags in the arrangement order of the at least two sub-tags, the method further includes:

[0043] Acquiring a sub-tag selection indication of the user through the human-computer interaction interface of the target application, wherein the sub-tag selection indication is used to indicate at least one target sub-tag selected by the user;

[0044] Sending the tag parameters of the at least one target subtag to the service server through the target application;

[0045] receiving a second-level search object set corresponding to the at least one target subtag sent by the business server, wherein the second-level search object set includes resource codes of a plurality of second-level objects;

[0046] According to the resource code of each second-level object, obtaining the object image of each second-level object in the second-level search object set;

[0047] The object images of all second-level objects in the second-level object set are displayed under the directory of the at least one target sub-tag through the target application.

[0048] In a third aspect, an embodiment of the present application provides a search processing device, including:

[0049] A receiving module, configured to receive a user search request sent by a user terminal through a target application, wherein the user search request includes: a search keyword and a user identifier;

[0050] A processing module, configured to determine a scene set corresponding to the search keyword according to the user search request;

[0051] A sorting module, used to score and sort the scenes in the scene set based on a plurality of preset screening dimensions, and determine a preset number of scenes ranked first;

[0052] A sending module is used to send the labels of the preset number of scenes to the target application on the user terminal.

[0053] In a possible design of the third aspect, the processing module is specifically configured to:

[0054] Determine, according to the search keyword, a first object set corresponding to the search keyword;

[0055] A scene set corresponding to the search keyword is determined according to feature information of each object in the first object set and location information of a store to which each object belongs.

[0056] In another possible design of the third aspect, the sorting module is specifically used to:

[0057] According to the user identifier, obtaining historical operation information of the user corresponding to the user identifier;

[0058] Determine, according to the historical operation information and a plurality of preset screening dimensions, a scene score of each scene in the scene set on each screening dimension;

[0059] Determine the score of each scene in the scene set according to the scene score of each scene in the scene set in each screening dimension and the preset weight coefficient of each screening dimension;

[0060] All scenes in the scene set are sorted in descending order of scores, and a preset number of scenes ranked first are determined.

[0061] In another possible design of the third aspect, the receiving module is further used to receive the scene parameters of the target search scene sent by the user terminal through the target application after the sending module sends the tags of the preset number of scenes to the target application on the user terminal;

[0062] The processing module is further used to determine the first-level search object set in the target search scene and at least two sub-tags included in the target search scene according to the scene parameter and the search keyword.

[0063] Optionally, the processing module is further used to:

[0064] Determining, according to the flow control rule, a resource code of each first-level object in the first-level search object set;

[0065] Determining an arrangement order of the at least two subtags according to data content and quality of each subtag of the at least two subtags;

[0066] Generate a first search result according to the resource code of each first-level object, the tag parameters of the at least two sub-tags, and the arrangement order of the at least two sub-tags;

[0067] The sending module is further configured to send the first search result to the target application on the user terminal.

[0068] Optionally, the receiving module is further configured to receive a tag parameter of at least one target subtag sent by the user terminal through the target application after the sending module sends the first search result to the target application on the user terminal;

[0069] The processing module is further used to determine a second-level search object set corresponding to the at least one target subtag according to the search keyword and the tag parameter of the at least one target subtag, and determine a resource code of each second-level object in the second-level search object set according to the flow control rule;

[0070] The sending module is also used to send the resource code of each second-level object in the second-level search object set to the target application of the user terminal, and the target application is used to display the object picture corresponding to the resource code of each second-level object through a human-computer interaction interface.

[0071] In a fourth aspect, an embodiment of the present application provides a search processing device, including:

[0072] An acquisition module, used to acquire a user search request issued by a user through a human-computer interaction interface of a target application, wherein the user search request includes: a search keyword and a user identifier;

[0073] A sending module, used for sending the user search request to a service server;

[0074] A receiving module, used to receive tags of a preset number of scenes sent by the business server, where the tags of the preset number of scenes are determined by the business server according to the user search request and a plurality of preset screening dimensions;

[0075] A display module is used to display the labels of the preset number of scenes through the human-computer interaction interface of the target application.

[0076] In a possible design of the fourth aspect, the acquisition module is further used to obtain the scene selection indication of the user after the display module displays the labels of the preset number of scenes through the human-computer interaction interface of the target application, and the scene selection indication is used to indicate the target search scene selected by the user;

[0077] The sending module is further used to send the scene parameters of the target search scene to the business server;

[0078] The receiving module is further configured to receive a first search result sent by the business server, the first search result comprising: a resource code and at least two sub-tags of each first-level object in the first-level search object set, and an arrangement order of the at least two sub-tags, wherein the first-level search object set, the at least two sub-tags, and the arrangement order of the at least two sub-tags are determined by the business server according to the scenario parameter;

[0079] The acquisition module is further used to acquire an object image of each first-level object in the first-level search object set according to the resource code of each first-level object;

[0080] The display module is also used to display object images of all first-level objects in the first-level object set under the directory of the target search scene through the target application, and display the at least two sub-tags according to the arrangement order of the at least two sub-tags.

[0081] Optionally, the acquisition module is further configured to, after the display module displays object images of all first-level objects in the first-level object set under the directory of the target search scene through the target application, and displays the at least two sub-tags in the arrangement order of the at least two sub-tags, acquire a sub-tag selection indication of the user through the human-computer interaction interface of the target application, wherein the sub-tag selection indication is used to indicate at least one target sub-tag selected by the user;

[0082] The sending module is further used to send the tag parameters of the at least one target sub-tag to the service server through the target application;

[0083] The receiving module is further configured to receive a second-level search object set corresponding to the at least one target sub-tag sent by the business server, wherein the second-level search object set includes resource codes of multiple second-level objects;

[0084] The acquisition module is further used to acquire an object image of each second-level object in the second-level search object set according to the resource code of each second-level object;

[0085] The display module is further configured to display object images of all second-level objects in the second-level object set under the directory of the at least one target sub-tag through the target application.

[0086] In a fifth aspect, an embodiment of the present application provides a business server, comprising a processor, a memory, a transceiver, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method described in the first aspect and various possible designs is implemented.

[0087] In a sixth aspect, an embodiment of the present application provides a user terminal, comprising a processor, a memory, a transceiver, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method described in the second aspect above is implemented.

[0088] In the seventh aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer execution instructions are stored. When the computer execution instructions are executed by a processor, they are used to implement the method described in the first aspect and various possible designs; or, when the computer execution instructions are executed by a processor, they are used to implement the method described in the second aspect.

[0089] In an eighth aspect, an embodiment of the present application provides a computer program product, which includes: computer instructions, which, when executed by a processor, are used to implement the method described in the first aspect and various possible designs; or, the computer execution instructions, when executed by a processor, are used to implement the method described in the second aspect.

[0090] The search processing method, device, equipment and storage medium provided in the embodiments of the present application can report the user search request to the background business server when the user terminal obtains the user search request through the human-computer interaction interface of the target application. The business server can determine the scene set corresponding to the search keyword based on the user search request, and then score and sort each scene in the scene set based on multiple preset filtering dimensions, determine a preset number of scenes ranked first, and finally send the labels of the preset number of scenes to the target application on the user terminal, so that the target application can display the labels of the preset number of scenes through the human-computer interaction interface. In this technical solution, since the preset number of scenes to be displayed can be adjusted based on the preset filtering dimensions, the consistency between the displayed scenes and user needs can be improved, and the consistency between the recommended products and user needs can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0091] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0092] Figure 1 A schematic diagram of a network architecture provided by the present invention;

[0093] Figure 2 An interactive schematic diagram of Embodiment 1 of the search processing method provided by the embodiment of the present invention;

[0094] Figure 3 A flowchart of a second embodiment of the search processing method provided in the embodiment of the present application;

[0095] Figure 4 A flowchart of a second embodiment of the search processing method provided in the embodiment of the present application;

[0096] Figure 5 An interactive diagram of Embodiment 3 of the search processing method provided in the embodiment of the present application;

[0097] Figure 6 A schematic diagram showing the first-level objects and sub-labels for the human-computer interaction interface of the target application;

[0098] Figure 7 An interactive schematic diagram of a fourth embodiment of the search processing method provided in an embodiment of the present application;

[0099] Figure 8 A schematic diagram showing the second level objects for the human-computer interaction interface of the target application;

[0100] Fig. 9 A schematic diagram of the structure of a search processing device embodiment 1 provided in the present application;

[0101] Fig.10 A schematic diagram of the structure of a second embodiment of a search processing device provided by the present application;

[0102] Fig.11 A schematic diagram of the structure of a service server provided in an embodiment of the present application;

[0103] Fig.12 A schematic diagram of the structure of a user terminal embodiment provided in an embodiment of the present application.

[0104] The above drawings show clear embodiments of the present disclosure, which will be described in more detail below. These drawings and text descriptions are not intended to limit the scope of the present disclosure in any way, but to illustrate the concepts of the present disclosure to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0105] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0106] First, the terms involved in the embodiments of the present application are explained:

[0107] Object

[0108] In the embodiments of the present application, the object can be a commodity in an e-commerce website or a food in a catering platform, which is not limited here. For commodities, commodity attributes can be generally divided into special attributes, extended attributes, specification parameters, sales attributes, etc., so the commodity attribute characteristics can specifically include commodity sku number, main sku number, commodity number, sku name, commodity name, commodity description, brand code, commodity origin, shelf life, sku valid mark, commodity valid mark, commodity serial number, commodity universal barcode, price information, gift mark, virtual commodity mark, import mark, etc.

[0109] Label

[0110] Tags can be represented by tab, which is mainly used to abstractly classify and summarize a certain feature of certain objects. For example, user tags are abstract classifications and summaries of a certain feature of a specific group, such as "college students", "white-collar workers", "student parents", "high-end people", etc. Scenario tags can be summaries of certain classification scenarios, such as time-limited tags such as "hourly delivery" and "nearby", or feature tags such as "xx logistics", "reputation", "new products", and "super value goods". Tags are not specifically limited here.

[0111] Dimensions

[0112] Dimensions can be multiple aspects of describing an object. For example, user dimensions can include gender, age, occupation, and region, etc. The characteristics of a user's gender dimension can be male or female, the characteristics of a user's age dimension can include young, middle-aged, and elderly, etc., and the purchasing power of a user can include low purchasing power, medium purchasing power, and high purchasing power, etc.

[0113] In the embodiments of the present application, new fields may include: Internet medical care, content field (pictures, text, live broadcast), shopping guide field, and great value products.

[0114] With the rapid development of Internet technology, more and more applications are deployed on terminals. In order to improve the usability of each application, the human-computer interaction interface of each application is generally provided with a navigation menu, through which users are guided to interact effectively with the product to achieve their goals.

[0115] The navigation menu is the most important bridge and platform for human-computer interaction, and its main function is to prevent users from getting lost. For example, fixed scene labels are deployed on the human-computer interaction interface of e-commerce websites. Reasonable scene labels can guide users to quickly find the appropriate scene, so as to perform product search in the target scene, laying the foundation for improving the conversion rate of products in the future.

[0116] The following uses the scenario of scene labels deployed on the human-computer interaction interface of an e-commerce website to introduce the technical problem to be solved by this application.

[0117] At present, the scene labels displayed on the human-computer interaction interface of e-commerce websites are fixed and divided according to product categories. When different users perform keyword searches, the scene labels displayed for all users are the same. Different scene labels cannot be given according to user needs, so the scenes of different users cannot be differentiated, and the scene labels cannot be updated in real time. Therefore, in the prior art, the relevance between the products under each scene label and the user is low, and there is a problem of poor consistency between the recommended products and user needs.

[0118] Specifically, in the scene tag deployment scheme in the prior art, cold-start products have fewer opportunities to be displayed, and weak categories and long-tail products are ranked low among similar products. Various businesses coexist in a single scene, for example, businesses that focus on timeliness and businesses that focus on quality. Among them, cold-start products are newly listed items that have no historical behavior data. Such items cannot be recommended through collaborative filtering. Weak categories refer to a category of products with low intrinsic value or strong substitutability or very low extrinsic value, which makes it difficult for the brand of this category to demonstrate its actual value. Long-tail products are products with low demand or poor sales.

[0119] Furthermore, due to the lack of scene segmentation in the head navigation area of ​​the human-computer interaction interface on current e-commerce websites, weak categories and mid- and low-end products lack competitive advantages, cold-start products have little exposure, and weak categories have limited operating space. Especially when various businesses coexist in a single scenario, the value of unique visitors (UV) of e-commerce websites has not been fully reflected.

[0120] Since the scene labels displayed on the human-computer interaction interface of existing e-commerce websites are fixed, the backend business server can only send them to e-commerce applications according to the set scene label rules, which is not conducive to the expansion of scene labels. For example, for the label of the scene of hourly delivery, the label of a store will only be issued if the number of objects recalled in a certain store within the target time reaches the threshold; for the label of new product tab, the new product tab of clothing, shoes and hats in the recent period is fixed, and different products cannot be pushed according to different users, and the personalized needs of users cannot be reflected.

[0121] In response to the above technical problems, the technical conception process of the present application is as follows: the inventor discovered through testing that, in the process of determining the goods to be sent, the background business server can locate a product set based on the keywords entered by the user, and then determine the multiple scenarios covered by the product set, and finally determine the value of each scenario based on different screening dimensions, and then combine the weight coefficients of each screening dimension to determine the multiple scenes to be displayed, and finally send them to the terminal where the e-commerce website is located, and then display them on the human-computer interaction interface of the e-commerce website.

[0122] Based on the above technical concept, the embodiment of the present application provides a search processing method. When the user terminal obtains a user search request through the human-computer interaction interface of the target application, the user search request can be reported to the background business server. The business server can determine the scene set corresponding to the search keyword based on the user search request, and then score and sort each scene in the scene set based on multiple preset filtering dimensions, determine a preset number of scenes ranked first, and finally send the labels of the preset number of scenes to the target application on the user terminal, so that the target application can display the labels of the preset number of scenes through the human-computer interaction interface. In this technical solution, since the preset number of scenes to be displayed can be adjusted based on the preset filtering dimensions, the consistency between the displayed scenes and user needs can be improved, and the consistency between the recommended products and user needs can be improved.

[0123] The search processing method provided in the embodiment of the present invention can be applied to the interaction process between a user terminal with a target application installed and a background business server. The background business server mainly implements scene screening processing, and the terminal with the target application installed displays labels of a preset number of scenes.

[0124] Optional, Figure 1 A schematic diagram of a network architecture provided by the present invention. Figure 1 As shown, the network architecture may include: a service server 11 and at least one user terminal ( Figure 1 Three user terminals are shown, namely user terminal 121, user terminal 122 and user terminal 123).

[0125] exist Figure 1 In the network architecture shown, each user terminal is installed with a target application 120, and the human-computer interaction interface of the target application 120 is displayed through the display interface of the user terminal. In actual applications, the user can input search keywords through the human-computer interaction interface of the target application 120, and the target application 120 will generate a search request based on the user identifier and the search keyword, and report it to the business server 11. The business server 11 will determine the scene set corresponding to the search keyword based on the user search request, and score and sort each scene in the scene set based on multiple preset screening dimensions, determine a preset number of scenes ranked first, and finally send the tags of the preset number of scenes to the target application.

[0126] In the e-commerce scenario, the scenario collection may include: xx logistics, great value products, word of mouth, delivery within one hour, nearby, store and many other scenarios, which are not limited here.

[0127] In actual applications, the business server 11 can receive user search requests sent by multiple user terminals. It is understandable that the user search requests sent by different user terminals may be different. The business server will perform corresponding operations for each user search request and feedback the determined processing results to the target application on the corresponding user terminal.

[0128] Optional, Figure 1 The user terminal shown may be a personal computer (PC) or a mobile terminal device such as a mobile phone or a tablet computer. The embodiment of the present application does not limit the type of the user terminal.

[0129] Furthermore, Figure 1 The network architecture shown may also include other devices, such as storage devices. This embodiment does not Figure 1 The network architecture shown includes specific devices and the number of devices, which can be determined based on actual scenarios.

[0130] In this embodiment, data can be transmitted between the above-mentioned devices through wired communication or wireless communication, which is not limited in this solution.

[0131] Below Figure 1 The architecture shown is applied in the scenario of the e-commerce industry as an example, and the technical solution of the present application and how the technical solution of the present application solves the above technical problems are described in detail through specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.

[0132] Figure 2The interactive diagram of the search processing method embodiment 1 provided by the embodiment of the present invention. In this embodiment, the search processing method is used to Figure 1 The information interaction between the service server and the user terminal installed with the target application is explained. Figure 2 As shown, the search processing method may include the following steps:

[0133] S201. A user terminal obtains a user search request sent by a user through a human-computer interaction interface of a target application. The user search request includes: a search keyword and a user identifier.

[0134] In actual applications, when the target application of the user terminal is in an open state, the user can enter a search keyword in the search box of the human-computer interaction interface and click a search option, and the target application can then obtain the search keyword entered by the user.

[0135] In addition, in order for the service server receiving the user search request to distinguish the device that issued the user search request, the user terminal also needs to carry a user identifier in the user search request.

[0136] It is understandable that the present embodiment does not limit the number of search keywords in the user search request, which may be one search keyword or multiple search keywords, which may be determined according to the actual scenario and will not be elaborated here.

[0137] S202: The user terminal sends the user search request to the service server through the target application.

[0138] The target application deployed on the user terminal is a computer program that is used to complete one or more specific tasks. It runs in user mode, can interact with users, and has a visual user interface. However, the normal and stable operation of the target application requires the support of the background business server. The business server can provide various services based on the user needs received by the target application, thereby triggering and executing various network services. Therefore, the target application of the user terminal needs to report the obtained user search request to the business server, and the business server will perform the corresponding operation.

[0139] In actual applications, a business server may be composed of a variety of business subsystems, each of which may implement different functions. In this embodiment, business subsystems with various functions are collectively referred to as business servers.

[0140] S203: The business server determines a scene set corresponding to the search keyword according to the received user search request.

[0141] In this embodiment, the service server may receive user search requests from different user terminals and perform corresponding operations respectively. Here, the service server executes a user search request sent by a user terminal for illustration.

[0142] Specifically, when the business server receives a user search request from a user terminal, it can parse the user search request, determine the search keyword included in the user search request, and then perform search processing based on the search keyword to obtain an object set corresponding to the search keyword. The object set can cover a variety of different scenarios, and by extracting a variety of different scenarios, a scene set corresponding to the search keyword can be formed.

[0143] For example, in the e-commerce industry, the scene set may be a combination of scenes with different attributes, for example, the scene set may include: xx logistics, import, value-for-money goods, word of mouth, delivery within one hour, nearby, store, member, etc. This embodiment does not limit the specific implementation of the scene, which can be determined according to the actual scene, and will not be elaborated here.

[0144] S204: The business server scores and sorts the scenes in the scene set based on a plurality of preset screening dimensions, and determines a preset number of scenes that are ranked first.

[0145] In this embodiment, in order to achieve different purposes, the R&D personnel of the e-commerce enterprise can preset different screening dimensions in the business server and configure different weight coefficients for different screening dimensions, so as to adjust the sorting of different scenarios.

[0146] Specifically, the business server can first calculate the scene score of each scene in each filtering dimension based on the preset multiple filtering dimensions for each scene in the above-mentioned scene set, and then calculate the score of each scene according to the preset weight coefficient of each filtering dimension, so as to determine the preset number of scenes in the top order based on the score.

[0147] S205: The service server sends tags of a preset number of scenes to a target application on the user terminal.

[0148] Exemplarily, after determining a preset number of scenes ranked first, the business server can feed back the labels of the preset number of scenes to the user terminal, that is, transmit them to the target application on the user terminal, so as to be displayed on the human-computer interaction interface of the target application, thereby presenting the labels of the above preset number of scenes to the user.

[0149] S206: The user terminal displays labels of the preset number of scenes on a human-computer interaction interface of the target application.

[0150] After receiving the labels of a preset number of scenes sent by the business server, the user terminal can push them to the human-computer interaction interface of the target application, and then use the target application to fill the labels of the preset number of scenes into the target navigation area of ​​the human-computer interaction interface, so that the labels of the preset number of scenes can be presented on the human-computer interaction interface.

[0151] The search processing method provided in the embodiment of the present application is that when the user terminal obtains a user search request through the human-computer interaction interface of the target application, the user search request is reported to the business server. The business server can determine the scene set corresponding to the search keyword based on the user search request, and then score and sort each scene in the scene set based on multiple preset filtering dimensions, determine a preset number of scenes ranked first, and finally send the tags of the preset number of scenes to the target application on the user terminal, so that the target application can display the tags of the preset number of scenes through the human-computer interaction interface. In this technical solution, since the preset number of scenes to be displayed can be adjusted based on the preset filtering dimensions, the consistency between the displayed scenes and user needs can be improved, and the consistency between the recommended products and user needs can be improved.

[0152] Based on the above embodiments, Figure 3 The flowchart of the second embodiment of the search processing method provided in the embodiment of the present application is as follows. Figure 3 As shown, the above S203 can be implemented by the following steps:

[0153] S301. Determine, based on the search keyword, a first object set corresponding to the search keyword.

[0154] In this embodiment, after receiving the user search request, the business server can query the object storage system or object storage list based on the search keyword in the user search request based on the search engine to determine all objects that meet the search keyword and form a first object set.

[0155] For example, in an e-commerce website, the business server can first determine the product set corresponding to the search keyword. For example, the search keyword is "milk". When the business server performs a search based on "milk", it will also determine "milk" in many scenarios, such as milk sold in the store downstairs, milk sold in the fresh supermarket, branded milk imported from abroad, and milk distributed by xx logistics, etc. The set of these milks constitutes the first object set.

[0156] S302: Determine a scene set corresponding to the search keyword according to feature information of each object in the first object set and location information of the store to which each object belongs.

[0157] In this embodiment, each object in the first object set covers a certain scene. Specifically, the business server can first determine the feature information of each object and the location information of the store to which each object belongs, and then determine the scene where each object is located based on the feature information of each object and the location information of the store to which each object belongs, and then the set of scenes where all objects are located is the scene set corresponding to the search keyword.

[0158] Exemplarily, for the first object set corresponding to the search keyword "milk", the characteristic information of milk sold in the store downstairs can be fresh milk, pure milk, etc., the location information of the store to which it belongs is nearby, and the corresponding scene can be represented by "nearby"; for milk sold in the fresh supermarket, its characteristic information can be fresh milk, pure milk, etc., and the location information of the store to which it belongs can also be summarized as nearby, and therefore, the corresponding scene can also be represented by "nearby"; similarly, the scene corresponding to foreign imported brand milk can be "imported" or "brand", and the scene corresponding to milk distributed by xx logistics can be "xx logistics", and therefore, the set of scenes such as "nearby", "imported", "brand", and "xx logistics" belongs to the scene set corresponding to the search keyword "milk".

[0159] It is understandable that, in actual applications, each scene in the scene set corresponding to the search keyword can also be divided according to different dimensions, and then a scene matrix can be formed.

[0160] In the search processing method provided in the embodiment of the present application, the business server determines the first object set corresponding to the search keyword based on the above search keyword, and determines the scene set corresponding to the search keyword based on the feature information of each object in the first object set and the location information of the store to which each object belongs. In this technical solution, scene division can effectively improve the effective distribution and conversion efficiency of traffic, which is the starting point and cornerstone of marketing. Therefore, the business server determines the scene set corresponding to the screening object based on the search keyword, which lays the foundation for the subsequent adjustment of the screening scene on the basis of ensuring the accuracy of the screening range.

[0161] Based on the above embodiments, Figure 4 The flowchart of the second embodiment of the search processing method provided in the embodiment of the present application is as follows. Figure 4 As shown, the above S204 can be implemented by the following steps:

[0162] S401. According to the user identifier, obtain historical operation information of the user corresponding to the user identifier.

[0163] In this embodiment, after receiving a user search request, the business server first queries and determines the historical operation information of the user corresponding to the user ID in the historical operation record based on the user ID in the user search request, and determines a more accurate scene set based on information such as the objects that the user is paying attention to, the objects or stores that have been browsed recently, thereby improving the match between the scene and the user.

[0164] Optionally, the business server can also determine the user profile based on the user ID, and perfectly abstract the overall information of a user based on the user profile, providing sufficient data basis for further accurate and rapid analysis of important information such as user behavior habits and consumption habits, thereby determining scenarios with higher consistency.

[0165] S402: Determine a scene score of each scene in the scene set in each screening dimension according to the historical operation information and a plurality of preset screening dimensions.

[0166] Exemplarily, in this step, multiple preset screening dimensions are illustrated as follows: stereotyped differences, user needs, scene object recall, object quality, filter item click volume, strategic support, etc. It is understandable that the preset multiple screening dimensions can be determined according to actual scenarios, and this embodiment does not limit them.

[0167] Among them, stereotyped differences refer to comments from the perspective of the category to which the object belongs. For example, dresses belong to the fashion category. Since new products have no advantages over old products, different weights can be assigned to new and old products. Therefore, based on the category to which the object in each scene belongs, the scene score of each scene on the screening dimension of stereotyped differences can be determined.

[0168] User needs are evaluated from the perspective of the user's screen. The user's historical purchase needs are determined based on the user's historical operation information. Then, based on the degree of correlation between the objects of each scene and the user's historical purchase needs, the scene score of each scene on the screening dimension of user needs is determined.

[0169] Scene object recall is an evaluation from the perspective of object recall and scene object recall magnitude. The scene score of each scene in the screening dimension of scene object recall is determined based on the proportion of new product feature objects covered by each object in the first object set corresponding to the search keyword.

[0170] Object quality, that is, the quality of the objects sold, determines the scene score of each scene on the object quality screening dimension based on whether the object pool orders and sales rate meet certain requirements.

[0171] For the filter item click volume, calculate whether each scenario belongs to the TOP N of the filter item scenarios in the overall filter click items, and determine the scenario score of each scenario in the filter item click volume filtering dimension.

[0172] Strategic support is determined by whether certain objects determined by search keywords belong to the objects in the company's key project layout, so as to determine the scenario scores of each scenario in the screening dimension of strategic support.

[0173] This solution can calculate the score of each scenario based on search terms, user needs, product recall level, product quality level, screening click rate, strategic support and other dimensions, laying the foundation for subsequent screening of scenarios with a high degree of consistency with users.

[0174] S403: Determine the score of each scene in the scene set according to the scene score of each scene in the scene set in each screening dimension and the preset weight coefficient of each screening dimension.

[0175] Optionally, due to different historical operation information of different users, each scene in the above-mentioned scene set has different scene scores on each filtering dimension. Then, according to the weight coefficient of each filtering dimension preset in the business server, the scene score on each filtering dimension is weighted and summed with the weight coefficient on the corresponding filtering dimension to obtain the score of each scene in the scene set, which is the main reference for subsequent sorting.

[0176] S404: Sort all scenes in the scene set in descending order of scores, and determine a preset number of scenes ranked first.

[0177] In an embodiment, the score of each scene can be used to characterize the degree of fit between the scene and the user. Therefore, all scenes in the scene set can be sorted in descending order according to the scene scores, and then the N scenes with the highest scores are extracted, thereby obtaining the top N scenes.

[0178] Wherein, N is a preset number, which is an integer greater than or equal to 2. This embodiment does not limit the specific value of N, which can be adjusted according to system settings or actual scenarios, and will not be repeated here.

[0179] In the search processing method provided in the embodiment of the present application, the business server obtains the historical operation information of the user corresponding to the user ID according to the user ID, and then determines the scene score of each scene in the above scene set on each filtering dimension according to the historical operation information and the preset multiple filtering dimensions, and then determines the score of each scene in the scene set in combination with the preset weight coefficient of each filtering dimension, and finally sorts all the scenes in the scene set in order from high to low according to the score, and determines the preset number of scenes ranked first. In this technical solution, based on the user's historical operation information, the search ranking of the scenes is differentiated by introducing multiple preset filtering dimensions, and the scenes ranked first can be dynamically adjusted by adjusting the weights later, which not only increases the display probability of disadvantaged categories or cold start categories, but also improves the consistency between the recommended scenes and user needs.

[0180] Based on the above embodiments, Figure 5 This is an interactive diagram of the third embodiment of the search processing method provided in the embodiment of the present application. Figure 5 As shown, after the above S206, the method may further include the following steps:

[0181] S501. A user terminal obtains a scene selection indication from a user, where the scene selection indication is used to indicate a target search scene selected by the user.

[0182] In this embodiment, after the user terminal displays the above-mentioned preset number of scenes through the human-computer interaction interface of the target application, the user can click on the label of a target search scene based on his / her needs, that is, a scene selection indication is issued to indicate the target search scene selected by the user. Therefore, the user terminal can obtain the user's scene selection indication through the target application.

[0183] S502: The user terminal sends the scene parameters of the target search scene to the service server.

[0184] In this embodiment, each scenario has corresponding scenario parameters, so that the target application and the service server can distinguish different scenarios according to the scenario parameters.

[0185] Specifically, after the user selects the target search scene, ie clicks the tab of the target search scene, the user terminal can obtain the scene parameters of the target search scene and send them to the business server so that the business server can determine the objects belonging to the target search scene.

[0186] S503: The business server determines a first-level search object set in a target search scenario and at least two sub-tags included in the target search scenario according to the received scenario parameters and search keywords.

[0187] Exemplarily, the business server can receive scene parameters of the target search scene sent by the target application from the user terminal. Thus, the business server can determine all object sets located in the target search scene from the first object set corresponding to the search keywords based on the received scene parameters and the search keywords in the above-mentioned user search request, thereby obtaining a first-level search object set.

[0188] It is understandable that in actual applications, in order to further improve the consistency between displayed objects and user needs, each scene label can also include at least two sub-labels. Therefore, the business server can determine at least two sub-labels included in the target search scene based on the first-level search object set under the target search scene.

[0189] Furthermore, in a specific implementation, the business server may also control the process of screening the object set based on the issued rule, that is, the business server may also perform the following steps:

[0190] S504: The business server determines the resource code of each first-level object in the first-level search object set according to the flow control rule.

[0191] In actual applications, traffic control rules can be pre-configured in the business server, so that the business server can determine the resource code of each first-level object in the first-level search object set in the resource pool according to the traffic control rules to reduce the traffic consumption of object delivery.

[0192] S505: The service server determines an arrangement order of at least two sub-tags according to the data content and quality of each of the at least two sub-tags.

[0193] As we all know, the core of refined marketing lies in finding the appropriate target user group. Therefore, the corresponding target user group can be directly determined by setting tags or sub-tags. Therefore, the data content and quality of tags or sub-tags are crucial.

[0194] In this step, when the business server determines that the target search scenario includes at least two sub-tags, in order to determine the adapted target user group, the business server can also sort the at least two sub-tags according to the data content and quality of each sub-tag, so that when the sub-tags are displayed in the human-computer interaction interface of the target application, the sub-tags with high user adaptability can be placed in an important position in the tag bar.

[0195] S506: The business server generates a first search result according to the resource code of each first-level object, the tag parameters of at least two sub-tags, and the arrangement order of the at least two sub-tags.

[0196] In this embodiment, in order to simplify the sending process, the business server can integrate or package the resource code of each first-level object, the tag parameters of at least two sub-tags, and the arrangement order of at least two sub-tags to obtain the first search result so that it can be sent down through one message, which can reduce resource consumption.

[0197] It can be understood that in this embodiment, the first search result includes: the resource code and at least two sub-tags of each first-level object in the first-level search object set, and the arrangement order of at least two sub-tags.

[0198] S507: The service server sends the first search result to the target application on the user terminal.

[0199] S508: The user terminal obtains an object image of each first-level object in the first-level search object set according to the resource code of each first-level object.

[0200] Exemplarily, the user terminal may receive the first search result sent by the service server, and parse the first search result to determine the resource code of each first-level object, at least two subtags included in the target search scenario, and the arrangement order of the at least two subtags.

[0201] The user terminal can query the preset object image library according to the resource code of each first-level object and obtain the object image corresponding to each resource code. That is, the user terminal can download the object image of each first-level object in the first-level search object set from the preset object image library based on the resource code of each first-level object.

[0202] S509: The user terminal displays object images of all first-level objects in the first-level object set in the target search scenario through the target application, and displays at least two sub-tags according to the arrangement order of the at least two sub-tags.

[0203] In actual applications, the human-computer interaction interface of the target application will be arranged with a scene display area, a sub-label display area and an object display area. Therefore, on the human-computer interaction interface of the target application, the user terminal displays object images of all first-level objects in the first-level object set in the object display area under the target search scene, and displays at least two sub-labels in the sub-label display area according to the arrangement order of at least two sub-labels.

[0204] For example, Figure 6 A diagram showing the first-level objects and sub-labels for the target application's human-computer interaction interface. Figure 6 In this article, we take the search keyword "shoes" as an example to explain. Figure 6As shown, the scene set corresponding to the shoe may include comprehensive ranking, sales volume, price, new product, store, reputation, etc. The target search scene selected by the user is new product. The sub-labels of the new product include trendy colors, popular new models, cutting-edge brands, etc. Correspondingly, the relevant information of multiple shoes included in the target search scene of new product is displayed in the object display area.

[0205] In actual applications, comprehensive ranking is the result of a comprehensive assessment of the goods, which usually includes store product descriptions, product main picture quality, single product comprehensive data, store transaction behavior, store positioning and other aspects. That is, if the comprehensive ranking is relatively high, it means that the comprehensive cost performance of the product is high. Sales volume refers to the sales volume of a product within a preset time period. Sales volume can characterize the hot sales of a product and can indirectly indicate the quality of the product. The price is based on the price of the product, that is, when the product keywords and categories are the same, the price will affect the ranking result. Since comprehensive ranking, sales volume, price and other factors are usually of concern to users, these three scene labels are first accumulated in the search navigation bar, and then the scene labels determined by the key search terms and preset filtering dimensions are displayed in turn. However, in actual applications, the above three labels are not limited. They can be determined according to the actual scenario, which will not be elaborated here.

[0206] It is understandable that the embodiments of the present application are not intended to Figure 6 The specific contents of the scenes, sub-tags, display objects, etc. in the illustrated embodiments are limited, which can be determined according to the actual scenes and will not be elaborated here.

[0207] The search processing method provided by the embodiment of the present application is that the user terminal obtains the user's scene selection indication, and the scene selection indication is used to indicate the target search scene selected by the user, and the scene parameters of the target search scene are sent to the business server, so that the business server determines the first-level search object set under the target search scene and the at least two sub-tags included in the target search scene according to the received scene parameters and search keywords, and further determines the resource code of each first-level object in the first-level search object set and the arrangement order of at least two sub-tags and sends them to the user terminal, so that the user terminal obtains the object image of each first-level object in the first-level search object set according to the resource code of each first-level object, and displays the object images of all first-level objects in the first-level object set in the target search scene through the target application, and displays at least two sub-tags according to the arrangement order of at least two sub-tags. In this technical solution, after the user selects the target search scene, the business server can determine the objects and sub-tags to be displayed, so that the corresponding marketing interest points can be displayed under the tag system of the target search scene, and the scene-based traffic difference control can be realized.

[0208] In the above Figure 5 Based on the embodiment shown, Figure 7 This is an interactive diagram of the fourth embodiment of the search processing method provided in the embodiment of the present application. Figure 7 As shown, after the above S509, the method may further include the following steps:

[0209] S701. A user terminal obtains a sub-tag selection indication of a user through a human-computer interaction interface of a target application, where the sub-tag selection indication is used to indicate at least one target sub-tag selected by the user.

[0210] In this embodiment, after the user terminal displays at least two sub-tags included in the target search scenario through the human-computer interaction interface of the target application, the user can further select at least one target sub-tag based on his / her needs, that is, issue a sub-tag selection indication to indicate the target sub-tag selected by the user. Therefore, the user terminal can obtain at least one target sub-tag selected by the user through the target application.

[0211] S702: The user terminal sends a tag parameter of at least one target subtag to a service server through the target application.

[0212] In this embodiment, each sub-tag also carries a corresponding tag parameter, so that the target application and the service server can distinguish different sub-tags according to the received tag parameters.

[0213] Specifically, after the user selects at least one target subtag, that is, clicks at least one target subtag under the target search scenario, the user terminal can obtain the tag parameters of these target subtags and send them to the business server so that the business server can determine the objects belonging to these target subtags.

[0214] S703: The business server determines a second-level search object set corresponding to at least one target sub-tag according to the search keyword and the tag parameter of at least one target sub-tag.

[0215] Optionally, after the business server receives the tag parameters of at least one target sub-tag sent by the user terminal, it can determine all object sets belonging to these target sub-tags in the first-level search object set corresponding to the target search scenario based on the tag parameters of the at least one target sub-tag and the search keywords in the above-mentioned user search request, thereby obtaining a second-level search object set.

[0216] S704: The business server determines the resource code of each second-level object in the second-level search object set according to the flow control rule.

[0217] In actual applications, similar to the display method of the first-level objects, the business server can also determine the resource code of each second-level object in the second-level search object set in the resource pool according to the pre-configured traffic control rules to reduce the traffic consumption of the object delivery.

[0218] S705: The service server sends the resource code of each second-level object in the second-level search object set to the target application of the user terminal.

[0219] S706: The user terminal obtains an object image of each second-level object in the second-level search object set according to the resource code of each second-level object.

[0220] In this embodiment, the user terminal receives the resource code of each second-level object sent by the business server to the target application, so that the user terminal can query the object image corresponding to each resource code in the preset object image library according to the resource code of each second-level object, thereby obtaining the object image of each second-level object in the second-level search object set, so that the target application can use the human-computer interaction interface to display the object image corresponding to the resource code of each second-level object.

[0221] S707: The user terminal displays object images of all second-level objects in the second-level object set under a directory of at least one target sub-tag through a target application.

[0222] In actual applications, when the user selects a target subtag in a target search scenario, the target subtag is selected, and on the human-computer interaction interface of the target application, the object display area under the directory of at least one target subtag displays object images of all second-level objects in the second-level object set.

[0223] For example, Figure 8 A schematic diagram showing the second level objects for the human-computer interaction interface of the target application. Figure 8 In the above Figure 6 Based on the search results, the shoes are explained. Figure 8 As shown, the user has selected target sub-tags such as trendy colors, popular new models, and cutting-edge brands under the directory of the target search scenario of new products. Therefore, the object display area of ​​the human-computer interaction interface displays relevant information of multiple shoes included in the target sub-tags of trendy colors, popular new models, and cutting-edge brands.

[0224] It is understandable that the embodiments of the present application are not Figure 8 The sub-tags and specific contents of the display objects in the illustrated embodiment are limited, which can be determined according to the actual scenario and will not be elaborated here.

[0225] In the search processing method provided by the embodiment of the present application, the user terminal obtains the user's sub-tag selection indication through the human-computer interaction interface of the target application, and the sub-tag selection indication is used to indicate at least one target sub-tag selected by the user, and sends the tag parameters of at least one target sub-tag to the business server, so that the business server determines the second-level search object set corresponding to at least one target sub-tag according to the search keyword and the tag parameters of at least one target sub-tag, and determines the resource code of each second-level object in the second-level search object set and sends it to the user terminal, so that the user terminal can obtain the object image of each second-level object in the second-level search object set according to the resource code of each second-level object and display the object images of all second-level objects in the second-level object set under the directory of at least one target sub-tag through the target application. In this technical solution, by setting multi-dimensional sub-tags, the needs of different groups can be accurately grasped, so that "supply and demand consistency" advertising push, personalized marketing and other services can be provided to different target user groups, which not only meets the user's demands, but also reduces the disgust and rejection caused by "irrelevant" and improves the user experience.

[0226] To sum up, the technical solution of the present application can support the rapid implementation of platform-level strategies, create platform-level services, improve user experience, support the multi-platform development of business scenarios, and meet differentiated shopping scenarios by adjusting the weights of multiple preset screening dimensions, thereby effectively conveying user intentions and needs, helping users quickly navigate search result types, brands, etc., increasing sales of mid- and tail-end objects, meeting the demands of different user groups, and improving the conversion rate and UV value of different user portrait groups. It also increases the repurchase rate of small categories and the usage rate of head products, and improves order conversion rate and user retention rate.

[0227] The following is an embodiment of the device of the present application, which can be used to execute the embodiment of the method of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method of the present application.

[0228] Fig. 9 This is a schematic diagram of the structure of the search processing device embodiment 1 provided by the present application. Fig. 9 As shown, the search processing device may include:

[0229] The receiving module 901 is used to receive a user search request sent by a user terminal through a target application, wherein the user search request includes: a search keyword and a user identifier;

[0230] Processing module 902, used to determine a scene set corresponding to the search keyword according to the user search request;

[0231] A sorting module 903 is used to sort the scenes in the scene set by scores based on a plurality of preset screening dimensions, and determine a preset number of scenes ranked first;

[0232] The sending module 904 is used to send the tags of the preset number of scenes to the target application on the user terminal.

[0233] In a possible design of the embodiment of the present application, the processing module 902 is specifically configured to:

[0234] Determine, according to the search keyword, a first object set corresponding to the search keyword;

[0235] A scene set corresponding to the search keyword is determined according to feature information of each object in the first object set and location information of a store to which each object belongs.

[0236] In another possible design of the embodiment of the present application, the sorting module 903 is specifically configured to:

[0237] According to the user identifier, obtaining historical operation information of the user corresponding to the user identifier;

[0238] Determine, according to the historical operation information and a plurality of preset screening dimensions, a scene score of each scene in the scene set on each screening dimension;

[0239] Determine the score of each scene in the scene set according to the scene score of each scene in the scene set in each screening dimension and the preset weight coefficient of each screening dimension;

[0240] All scenes in the scene set are sorted in descending order of scores, and a preset number of scenes ranked first are determined.

[0241] In another possible design of the embodiment of the present application, the receiving module 901 is further configured to receive a scene parameter of a target search scene sent by the user terminal through the target application after the sending module 904 sends the tags of the preset number of scenes to the target application on the user terminal;

[0242] The processing module 902 is further configured to determine, according to the scene parameter and the search keyword, a first-level search object set in the target search scene and at least two sub-tags included in the target search scene.

[0243] Optionally, the processing module 902 is further configured to:

[0244] Determining, according to the flow control rule, a resource code of each first-level object in the first-level search object set;

[0245] Determining an arrangement order of the at least two subtags according to data content and quality of each subtag of the at least two subtags;

[0246] Generate a first search result according to the resource code of each first-level object, the tag parameters of the at least two sub-tags, and the arrangement order of the at least two sub-tags;

[0247] The sending module 904 is further configured to send the first search result to the target application on the user terminal.

[0248] Optionally, the receiving module 901 is further configured to receive a tag parameter of at least one target subtag sent by the user terminal through the target application after the sending module sends the first search result to the target application on the user terminal;

[0249] The processing module 902 is further configured to determine a second-level search object set corresponding to the at least one target subtag according to the search keyword and the tag parameter of the at least one target subtag, and determine a resource code of each second-level object in the second-level search object set according to the flow control rule;

[0250] The sending module 904 is further used to send the resource code of each second-level object in the second-level search object set to the target application of the user terminal, and the target application is used to display the object picture corresponding to the resource code of each second-level object through a human-computer interaction interface.

[0251] The device provided in the embodiment of the present application can be used to perform the above Figures 2 to 7 The technical solution of the business server in the method embodiment has similar implementation principles and technical effects, which will not be repeated here.

[0252] Fig.10 This is a schematic diagram of the structure of the second embodiment of the search processing device provided by the present application. Fig.10 As shown, the search processing device may include:

[0253] The acquisition module 1001 is used to acquire a user search request sent by a user through the human-computer interaction interface of the target application, wherein the user search request includes: a search keyword and a user identifier;

[0254] A sending module 1002, configured to send the user search request to a service server;

[0255] The receiving module 1003 is used to receive tags of a preset number of scenes sent by the business server, where the tags of the preset number of scenes are determined by the business server according to the user search request and a plurality of preset screening dimensions;

[0256] The display module 1004 is used to display the labels of the preset number of scenes through the human-computer interaction interface of the target application.

[0257] In a possible design of an embodiment of the present application, the acquisition module 1001 is further used to obtain a scene selection indication of the user after the display module 1004 displays the labels of the preset number of scenes through the human-computer interaction interface of the target application, and the scene selection indication is used to indicate the target search scene selected by the user;

[0258] The sending module 1002 is further configured to send the scene parameters of the target search scene to the service server;

[0259] The receiving module 1003 is further configured to receive a first search result sent by the business server, wherein the first search result includes: a resource code of each first-level object in the first-level search object set and at least two sub-tags and an arrangement order of the at least two sub-tags, wherein the first-level search object set and the at least two sub-tags and the arrangement order of the at least two sub-tags are determined by the business server according to the scenario parameter;

[0260] The acquisition module 1001 is further used to acquire an object image of each first-level object in the first-level search object set according to the resource code of each first-level object;

[0261] The display module 1004 is further used to display object images of all first-level objects in the first-level object set under the directory of the target search scene through the target application, and to display the at least two sub-tags in the arrangement order of the at least two sub-tags.

[0262] Optionally, the acquisition module 1001 is further used to display the object pictures of all first-level objects in the first-level object set under the directory of the target search scene through the target application in the display module 1004, and after displaying the at least two sub-tags in the arrangement order of the at least two sub-tags, obtain the sub-tag selection indication of the user through the human-computer interaction interface of the target application, wherein the sub-tag selection indication is used to indicate at least one target sub-tag selected by the user;

[0263] The sending module 1002 is further configured to send the tag parameters of the at least one target subtag to the service server through the target application;

[0264] The receiving module 1003 is further configured to receive a second-level search object set corresponding to the at least one target sub-tag sent by the business server, where the second-level search object set includes resource codes of multiple second-level objects;

[0265] The acquisition module 1001 is further used to acquire an object image of each second-level object in the second-level search object set according to the resource code of each second-level object;

[0266] The display module 1004 is further configured to display object images of all second-level objects in the second-level object set under the directory of the at least one target sub-tag through the target application.

[0267] The device provided in the embodiment of the present application can be used to perform the above Figures 2 to 7 The technical solution of the user terminal in the method embodiment has similar implementation principles and technical effects, which will not be repeated here.

[0268] It should be noted that it should be understood that the division of the various modules of the above device is only a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. And these modules can all be implemented in the form of software called by processing elements; they can also be all implemented in the form of hardware; some modules can also be implemented in the form of software called by processing elements, and some modules can be implemented in the form of hardware. For example, the processing module can be a separately established processing element, or it can be integrated in a chip of the above device. In addition, it can also be stored in the memory of the above device in the form of program code, and called and executed by a processing element of the above device. The function of the above-mentioned module is determined. The implementation of other modules is similar. In addition, these modules can be fully or partially integrated together, or they can be implemented independently. The processing element described here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each module above can be completed by an integrated logic circuit of hardware in the processor element or instructions in the form of software.

[0269] Fig.11 This is a schematic diagram of the structure of the service server provided in the embodiment of the present application. Fig.11 As shown, the business server may include: a processor 1101, a memory 1102, a transceiver 1103 and a system bus 1104. The memory 1102 and the transceiver 1103 are connected to the processor 1101 through the system bus 1104 and communicate with each other. The memory 1102 is used to store computer execution instructions, and the transceiver 1103 is used to communicate with other devices. When the processor 1101 executes the computer execution instruction, the above-mentioned Figures 2 to 7 The technical solution of the business server in the illustrated embodiment.

[0270] Fig.12 This is a schematic diagram of the structure of a user terminal embodiment provided in the present application. Fig.12As shown, the user terminal may include: a processor 1201, a memory 1202, a transceiver 1203 and a system bus 1204. The memory 1202 and the transceiver 1203 are connected to the processor 1201 through the system bus 1204 and communicate with each other. The memory 1202 is used to store computer-executable instructions, and the transceiver 1203 is used to communicate with other devices. When the processor 1201 executes the computer-executable instructions, the above-mentioned Figures 2 to 7 The technical solution of the user terminal in the illustrated embodiment.

[0271] In the above Fig.11 and Fig.12 The above-mentioned processor can be a general-purpose processor, including a central processing unit CPU, a network processor (NP), etc.; it can also be a digital signal processor DSP, an application-specific integrated circuit ASIC, a field programmable gate array FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0272] The memory may include random access memory (RAM), may include read-only memory (RAM), and may also include non-volatile memory (non-volatile memory), such as at least one disk storage.

[0273] The transceiver, ie, the communication interface, is used to realize the communication between the database access device and other devices (such as the client, the read-write library and the read-only library).

[0274] The system bus can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The system bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0275] Optionally, the embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and when the computer instructions are executed on a computer, the computer executes the above Figures 2 to 7 The solution of the business server in the method embodiment is shown.

[0276] The embodiment of the present application also provides a computer-readable storage medium in which computer instructions are stored. When the computer instructions are executed on a computer, the computer executes the above Figures 2 to 7 The scheme of the user terminal in the method embodiment is shown.

[0277] Optionally, the present application embodiment further provides a chip for executing instructions, the chip being used to execute the above Figures 2 to 7 The solution of the business server in the method embodiment is shown.

[0278] The present application also provides a chip for executing instructions. Figures 2 to 7 The scheme of the user terminal in the method embodiment is shown.

[0279] The embodiment of the present application also provides a computer program product, the computer program product includes a computer program, the computer program is stored in a computer-readable storage medium, at least one processor can read the computer program from the computer-readable storage medium, and when the at least one processor executes the computer program, the above-mentioned Figures 2 to 7 The solution of the business server in the method embodiment is shown.

[0280] The embodiment of the present application also provides a computer program product, the computer program product includes a computer program, the computer program is stored in a computer-readable storage medium, at least one processor can read the computer program from the computer-readable storage medium, and when the at least one processor executes the computer program, the above-mentioned Figures 2 to 7 The scheme of the user terminal in the method embodiment is shown.

[0281] In the present application, "at least one" means one or more, and "plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: the existence of A alone, the existence of A and B at the same time, and the existence of B alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship; in a formula, the character " / " indicates that the previous and next associated objects are in a "division" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items.

[0282] It is to be understood that the various numerical numbers involved in the embodiments of the present application are only for the convenience of description and are not intended to limit the scope of the embodiments of the present application. In the embodiments of the present application, the size of the sequence number of each process does not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0283] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the application disclosed herein. This application is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0284] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A search processing method, characterized in that: include: Receiving a user search request sent by a user terminal through a target application, the user search request including: a search keyword and a user identifier; According to the search keyword, determine all objects that satisfy the search keyword to form a first object set; Determine, according to feature information of each object in the first object set and location information of a store to which each object belongs, a scene set corresponding to the search keyword, wherein the scene set includes scenes covered by the first object set; Based on the preset multiple screening dimensions, the scenes in the scene set are scored and sorted to determine a preset number of scenes ranked first; The tags of the preset number of scenes are sent to the target application on the user terminal to display the tags of the preset number of scenes.

2. The method according to claim 1, characterized in that The step of ranking the scenes in the scene set based on the preset multiple screening dimensions and determining a preset number of scenes ranked first includes: According to the user identifier, obtaining historical operation information of the user corresponding to the user identifier; Determine, according to the historical operation information and a plurality of preset screening dimensions, a scene score of each scene in the scene set on each screening dimension; Determine the score of each scene in the scene set according to the scene score of each scene in the scene set in each screening dimension and the preset weight coefficient of each screening dimension; All scenes in the scene set are sorted in descending order of scores, and a preset number of scenes ranked first are determined.

3. The method according to any one of claims 1 to 2, characterized in that: After sending the tags of the preset number of scenes to the target application on the user terminal, the method further includes: Receiving a scene parameter of a target search scene sent by the user terminal through the target application; According to the scene parameter and the search keyword, a first-level search object set under the target search scene and at least two sub-tags included in the target search scene are determined.

4. The method according to claim 3, characterized in that The method further comprises: Determining, according to the flow control rule, a resource code of each first-level object in the first-level search object set; Determining an arrangement order of the at least two subtags according to data content and quality of each subtag of the at least two subtags; Generate a first search result according to the resource code of each first-level object, the tag parameters of the at least two sub-tags, and the arrangement order of the at least two sub-tags; The first search result is sent to the target application on the user terminal.

5. The method according to claim 4, characterized in that After sending the first search result to the target application on the user terminal, the method further includes: receiving a tag parameter of at least one target subtag sent by the user terminal through the target application; Determining a second-level search object set corresponding to the at least one target subtag according to the search keyword and the tag parameter of the at least one target subtag; Determining, according to the flow control rule, a resource code of each second-level object in the second-level search object set; The resource code of each second-level object in the second-level search object set is sent to the target application of the user terminal, and the target application is used to display the object picture corresponding to the resource code of each second-level object through a human-computer interaction interface.

6. A search processing method, characterized in that: include: Acquire a user search request issued by a user through a human-computer interaction interface of a target application, wherein the user search request includes: a search keyword and a user identifier; Receiving labels of a preset number of scenes sent by a business server, where the labels of the preset number of scenes are determined by the business server according to the user search request and a preset plurality of screening dimensions, including: determining, according to the search keyword, all objects satisfying the search keyword to form a first object set; determining, according to feature information of each object in the first object set and location information of a store to which each object belongs, a scene set corresponding to the search keyword, where the scene set includes scenes covered by the first object set; and ranking each scene in the scene set by scoring based on the preset plurality of screening dimensions, determining a preset number of scenes ranked first, and obtaining labels for the preset number of scenes; The labels of the preset number of scenes are displayed through the human-computer interaction interface of the target application.

7. The method according to claim 6, characterized in that After displaying the labels of the preset number of scenes through the human-computer interaction interface of the target application, the method further includes: Acquire a scene selection indication of the user, where the scene selection indication is used to indicate a target search scene selected by the user; Sending the scene parameters of the target search scene to the service server; receiving a first search result sent by the business server, the first search result comprising: a resource code and at least two subtags of each first-level object in the first-level search object set, and an arrangement order of the at least two subtags, wherein the first-level search object set, the at least two subtags, and the arrangement order of the at least two subtags are determined by the business server according to the scenario parameter; Obtaining, according to the resource code of each first-level object, an object image of each first-level object in the first-level search object set; The object images of all first-level objects in the first-level object set are displayed under the directory of the target search scene through the target application, and the at least two sub-tags are displayed according to the arrangement order of the at least two sub-tags.

8. The method according to claim 7, characterized in that After displaying the object images of all first-level objects in the first-level object set under the directory of the target search scene by the target application, and displaying the at least two sub-tags in the arrangement order of the at least two sub-tags, the method further includes: Acquiring a sub-tag selection indication of the user through the human-computer interaction interface of the target application, wherein the sub-tag selection indication is used to indicate at least one target sub-tag selected by the user; Sending the tag parameters of the at least one target subtag to the service server through the target application; receiving a second-level search object set corresponding to the at least one target subtag sent by the business server, wherein the second-level search object set includes resource codes of a plurality of second-level objects; According to the resource code of each second-level object, obtaining the object image of each second-level object in the second-level search object set; The object images of all second-level objects in the second-level object set are displayed under the directory of the at least one target sub-tag through the target application.

9. A search processing device, characterized in that: include: A receiving module, configured to receive a user search request sent by a user terminal through a target application, wherein the user search request includes: a search keyword and a user identifier; a processing module, configured to determine, based on the search keyword, all objects satisfying the search keyword to form a first object set; and determine, based on feature information of each object in the first object set and location information of a store to which each object belongs, a scene set corresponding to the search keyword, wherein the scene set includes scenes covered by the first object set; A sorting module, used to score and sort the scenes in the scene set based on a plurality of preset screening dimensions, and determine a preset number of scenes ranked first; The sending module is used to send the labels of the preset number of scenes to the target application on the user terminal so as to display the labels of the preset number of scenes.

10. A search processing device, characterized in that: include: An acquisition module, used to acquire a user search request issued by a user through a human-computer interaction interface of a target application, wherein the user search request includes: a search keyword and a user identifier; A sending module, used for sending the user search request to a service server; A receiving module is used to receive labels of a preset number of scenes sent by the business server, where the labels of the preset number of scenes are determined by the business server according to the user search request and a preset plurality of screening dimensions, including: determining all objects satisfying the search keywords according to the search keywords to form a first object set; determining a scene set corresponding to the search keywords according to feature information of each object in the first object set and location information of a store to which each object belongs, where the scene set includes scenes covered by the first object set; and ranking each scene in the scene set by scoring based on the preset plurality of screening dimensions, determining a preset number of scenes ranked first, and obtaining labels for the preset number of scenes; A display module is used to display the labels of the preset number of scenes through the human-computer interaction interface of the target application.

11. A service server, comprising a processor, a memory, a transceiver, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 5 is implemented.

12. A user terminal, comprising a processor, a memory, a transceiver, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 6 to 8 is implemented.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 5 when executed by a processor; or, the computer-executable instructions are used to implement the method according to any one of claims 6 to 8 when executed by a processor.

14. A computer program product comprising: A computer-executable instruction, characterized in that when the computer-executable instruction is executed by a processor, it is used to implement the method as described in any one of claims 1-5; or, when the computer-executable instruction is executed by a processor, it is used to implement the method as described in any one of claims 6-8.

Images