Query item generation method and apparatus, device and storage medium

Abstract

The embodiments of the present disclosure relate to a query item generation method and apparatus, a device and a storage medium. The method disclosed herein comprises: on the basis of user interaction information associated with a point of interest, generating a first group of candidate query items associated with the point of interest; determining the number of points of interest matching the first group of candidate query items; on the basis of the number of points of interest, determining a second group of candidate query items satisfying a preset condition from the first group of candidate query items; and, on the basis of evaluation information of the second group of candidate query items, determining at least one query item associated with the point of interest from the second group of candidate query items. In this way, the embodiments of the present disclosure can enable a user to more efficiently acquire information associated with a point of interest, thereby improving information delivery efficiency.

Description

Methods, apparatus, devices and storage media for generating query items Technical Field

[0001] The exemplary embodiments disclosed herein relate generally to the field of computers, and in particular to methods, apparatus, devices, and computer-readable storage media for generating query items. Background Technology

[0002] With the development of computer technology, various forms of electronic devices have greatly enriched people's daily lives. For example, people can use electronic devices to perform various search tasks, such as shopping searches, ordering food, and so on. How to improve the efficiency of information retrieval and acquisition is a key concern. Summary of the Invention

[0003] In a first aspect of this disclosure, a method for generating query items is provided. The method includes: generating a first set of candidate query items associated with points of interest (POIs) based on user interaction information associated with POIs; determining the number of POIs matching the first set of candidate query items; determining a second set of candidate query items that meet preset conditions from the first set of candidate query items based on the number of POIs; and determining at least one query item associated with a POI from the second set of candidate query items based on evaluation information of the second set of candidate query items.

[0004] In a second aspect of this disclosure, an apparatus for generating query items is provided. The apparatus includes: a content generation module configured to generate a first set of candidate query items associated with points of interest (POIs) based on user interaction information associated with POIs; a first determining module configured to determine the number of POIs matching the first set of candidate query items; a second determining module configured to determine a second set of candidate query items from the first set of candidate query items that meet preset conditions based on the number of POIs; and a third determining module configured to determine at least one query item associated with a POI from the second set of candidate query items based on evaluation information of the second set of candidate query items.

[0005] In a third aspect of this disclosure, an electronic device is provided. The device includes at least one processor; and at least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor. When executed by the at least one processor, the instructions cause the device to perform the method of the first aspect.

[0006] In a fourth aspect of this disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores computer-executable instructions that can be executed by a processor to implement the method of the first aspect.

[0007] In a fifth aspect of this disclosure, a computer program product is provided, which is tangibly stored in a computer storage medium and includes computer-executable instructions that, when executed by a device, cause the device to perform the method of the first aspect.

[0008] It should be understood that the content described in this content section is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0009] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0010] Figure 1 shows a schematic diagram of an example environment in which embodiments of the present disclosure may be implemented;

[0011] Figure 2 illustrates a flowchart of an example process for generating query items according to some embodiments of the present disclosure;

[0012] Figure 3 shows an example flowchart of generating query items according to some embodiments of the present disclosure;

[0013] Figures 4A to 4C show the display interface of example query items according to some embodiments of the present disclosure;

[0014] Figure 5 shows a schematic structural block diagram of an example apparatus for generating query items according to some embodiments of the present disclosure; and

[0015] Figure 6 shows a block diagram of an electronic device capable of implementing several embodiments of the present disclosure. Detailed Implementation

[0016] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0017] It should be noted that the headings of any section / subsection provided herein are not limiting. Various embodiments are described throughout this document, and embodiments of any type may be included under any section / subsection. Furthermore, embodiments described in any section / subsection may be combined in any way with any other embodiments described in the same section / subsection and / or different sections / subsections.

[0018] In the description of embodiments of this disclosure, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may also be included below. The terms "first", "second", etc., may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0019] The embodiments of this disclosure may involve user data, data acquisition, and / or use. All of these aspects comply with applicable laws, regulations, and relevant provisions. In the embodiments of this disclosure, all data collection, acquisition, processing, manipulation, forwarding, and use are conducted with the user's knowledge and confirmation. Accordingly, in implementing the embodiments of this disclosure, the type, scope of use, and usage scenarios of any data or information that may be involved should be communicated to the user and their authorization obtained in accordance with relevant laws and regulations through appropriate means. The specific methods of notification and / or authorization may vary depending on the actual situation and application scenario, and the scope of this disclosure is not limited in this respect.

[0020] In this specification and the embodiments, any processing of personal information will be carried out only under the premise of legality (such as obtaining the consent of the personal information subject, or being necessary for the performance of a contract), and will only be carried out within the scope stipulated or agreed upon. A user's refusal to process personal information other than that necessary for basic functions will not affect the user's use of basic functions.

[0021] Traditional solutions make it difficult for users to find or search for queries with a limited number of points of interest, thus impacting the user experience.

[0022] Embodiments of this disclosure propose a scheme for generating query items. According to this scheme, a first set of candidate query items associated with points of interest (POIs) can be generated based on user interaction information associated with POIs; the number of POIs matching the first set of candidate query items can be determined; based on the number of POIs, a second set of candidate query items that meet preset conditions can be determined from the first set of candidate query items; and based on the evaluation information of the second set of candidate query items, at least one query item associated with a POI can be determined from the second set of candidate query items.

[0023] In this way, embodiments of the present disclosure enable users to obtain information associated with points of interest more efficiently, thereby improving the efficiency of information transmission.

[0024] The following section provides a detailed description of various example implementations of this scheme, with reference to the accompanying drawings.

[0025] Example Environment

[0026] Figure 1 illustrates a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. As shown in Figure 1, the example environment 100 may include an electronic device 110.

[0027] In this example environment 100, electronic device 110 generates corresponding query items based on the acquired user interaction information. That is, electronic device 110 is at least configured to output the received user interaction information as corresponding query items.

[0028] In some embodiments, electronic device 110 may be any type of mobile terminal, fixed terminal, or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, personal communication system (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio receivers, e-book devices, gaming devices, or any combination thereof, including accessories and peripherals of these devices or any combination thereof. In some embodiments, electronic device 110 may also support any type of user-facing interface (such as "wearable" circuitry).

[0029] In some embodiments, electronic device 110 may establish a communication connection with server 120 to provide services to electronic device 110.

[0030] Server 120 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks, and big data and artificial intelligence platforms. Server 120 may include, for example, computing systems / servers such as mainframes, edge computing nodes, computing devices in a cloud environment, etc. Server 120 can provide backend services for electronic device 110.

[0031] A communication connection can be established between server 120 and electronic device 110. This communication connection can be established via wired or wireless means. The communication connection may include, but is not limited to, Bluetooth, mobile network, Universal Serial Bus (USB), and Wireless Fidelity (WiFi) connections; the embodiments of this disclosure are not limited in this respect. In the embodiments of this disclosure, server 120 and electronic device 110 can achieve signaling interaction through the communication connection between them.

[0032] It should be understood that the structure and function of the various elements in environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of this disclosure.

[0033] The following description will continue with reference to the accompanying drawings, which will provide some exemplary embodiments of this disclosure.

[0034] Example process

[0035] Figure 2 shows a flowchart of an example query item generation process 200 according to some embodiments of the present disclosure. Process 200 can be implemented at electronic device 110. Process 200 is described below with reference to Figure 1.

[0036] As shown in Figure 2, in box 210, electronic device 110 generates a first set of candidate query items associated with points of interest based on user interaction information associated with points of interest.

[0037] In some embodiments, the electronic device 110 can determine a point of interest from a set of candidate points of interest based on classification information. For example, such a point of interest could be a restaurant, a shop, a tourist attraction, or other similar location. For ease of description, a restaurant will be used as an example below.

[0038] Taking Figure 3 as an example, in box 301, the electronic device 110 can filter a set of candidate restaurants based on their classification information to determine the target restaurant. In some embodiments, such classification information may indicate the category information of a set of candidate restaurants, such as Chinese food, Western food, fast food, snacks, etc. Further, the electronic device 110 can filter out restaurants without distinctive features (e.g., fast food, snacks, etc.) from the candidate restaurants to determine the target restaurant. Additionally or alternatively, the target restaurant can also be a restaurant with high popularity or high ratings.

[0039] In some embodiments, user interaction information may indicate media content associated with a point of interest and commentary content associated with that point of interest. As an example, electronic device 110 may acquire video content associated with a target restaurant and use a model to convert the audio in the video content into text content. Further, electronic device 110 may determine user interaction information based on the text content and commentary content corresponding to the restaurant. Additionally or alternatively, such user interaction information may also include the target restaurant's location information, menu information, average customer ratings, etc.

[0040] Furthermore, in box 302, the electronic device 110 can provide user interaction information to the first model to generate multiple candidate query items. Such a first model could be, for example, a language model. Such multiple candidate query items could be, for example, a preset number of candidate query items (e.g., 3 to 6), and these candidate query items could include text content and / or emoticons. Such candidate query items could be, for example, offering free dishes, having theme A, having decoration B, etc. As an example, such multiple candidate query items could be candidate query item 1, candidate query item 2, candidate query item 3, candidate query item 4, candidate query item 5, and candidate query item 6.

[0041] Further, in box 303, the electronic device 110 can determine the first group of candidate query items by merging a group of candidate query items whose similarity is greater than a threshold from multiple candidate query items. As an example, the electronic device 110 can use a vector library to calculate the similarity of multiple candidate query items, thereby replacing or merging candidate query items whose similarity is greater than the threshold. Specifically, the electronic device 110 can recall the target query item from a group of candidate query items in the vector library. If the electronic device 110 determines that the similarity between the recalled query item and the target query item is greater than the threshold, it can merge or delete the target query item; otherwise, the electronic device 110 can save the target query item to the vector library.

[0042] In some embodiments, in response to an initial empty vector library, the electronic device 110 can determine that the first candidate query item (e.g., candidate query item 1) among the plurality of candidate query items can be directly added to the library. Further, the electronic device 110 can compare the similarity of the second candidate query item (e.g., candidate query item 2) among the group of candidate query items with the first candidate query item in the vector library to determine whether the second candidate query item can be added to the library. Assuming the electronic device 110 determines that the similarity between the first and second candidate query items does not reach a threshold, it can determine that the second candidate query item can be added to the library. Further, the electronic device 110 can compare the third candidate query item among the plurality of candidate query items with the first and second candidate query items in the vector library respectively to determine whether the third candidate query item should be added to the library, and so on, thus determining the first group of candidate query items.

[0043] As an example, if electronic device 110 determines that the similarity between query item 6 and query item 5 is greater than a threshold, and the similarity between other candidate query items is less than the threshold, then the first group of candidate query items can be determined. As an example, the first group of candidate query items could be candidate query item 1, candidate query item 2, candidate query item 3, candidate query item 4, and candidate query item 5', where candidate query item 5' can represent the result of merging candidate query item 5 and candidate query item 6.

[0044] Furthermore, in box 304, electronic device 110 can use a target model to perform a first merging of the first group of candidate query terms. This first merging aims to merge candidate query terms with complex semantics. The target model can be, for example, a language model. As an example, in response to using the target model to determine that candidate query term 5' and candidate query term 4 are semantically similar, electronic device 110 can obtain the merged first group of candidate query terms. As an example, the merged first group of candidate query terms can be candidate query term 1, candidate query term 2, candidate query term 3, and candidate query term 4', where candidate query term 4' can represent the result of merging candidate query term 4 and candidate query term 5'.

[0045] In some embodiments, the electronic device 110 may be configured with a preset thesaurus to indicate words that are not expected to appear in candidate query terms. Furthermore, such a preset thesaurus may also correspond to the expected expressions for the words that are not expected to appear. For example, offering a beverage can be expressed as a free gift, and offering side dishes can also be expressed as a free gift.

[0046] Furthermore, the electronic device 110 can perform a second merging of the merged first group of candidate query items based on the preset thesaurus. Specifically, in box 305, the electronic device 110 can use the target model to match the merged first group of candidate query items with words in the preset thesaurus. Assuming that candidate query item 3 and candidate query item 4' involve words contained in the preset thesaurus, for example, candidate query item 3 is "free drink" and candidate query item 4' is "free side dish". Further, the electronic device 110 can convert candidate query item 3 and candidate query item 4' into the same candidate query item and merge them, for example, merging them into candidate query item 3': "free gift". In this way, the electronic device 110 can obtain the first group of candidate query items after the second merging (e.g., query item 1, query item 2, and query item 3').

[0047] The following describes the process by which electronic device 110 processes the first group of candidate query items (hereinafter referred to as the first group of candidate query items) after two merging processes.

[0048] Returning to Figure 2, in box 220, electronic device 110 determines the number of points of interest that match the first group of candidate query items.

[0049] As an example, suppose electronic device 110 determines that two restaurants have candidate query items that both include complimentary side dishes. Then, the number of restaurants matching the candidate query item "complimentary side dishes" is 2. Furthermore, electronic device 110 can group the first group of candidate query items based on the number of points of interest and determine the second group of candidate query items.

[0050] Returning to Figure 2, in box 230, electronic device 110 determines a second set of candidate query items that meet preset conditions from the first set of candidate query items based on the number of points of interest.

[0051] In some embodiments, such a preset condition may indicate that the number of points of interest corresponding to the candidate query item is greater than a first threshold; and / or the number of points of interest corresponding to the candidate query item is less than a second threshold, wherein the second threshold is less than or equal to the first threshold.

[0052] Referring again to Figure 3, in box 306, electronic device 110 can group candidate queries based on the number of restaurants associated with each candidate query in the first group. Further, in response to a target candidate query having fewer than a second threshold (e.g., 4), electronic device 110 can determine that the target candidate query is a relatively "niche" candidate query and add it to the first set. Conversely, in response to a target candidate query having more than a first threshold (e.g., 5), electronic device 110 can determine that the target candidate query is a relatively "popular" candidate query and add it to the second set.

[0053] Furthermore, the electronic device 110 can use the target model to filter or screen such a first set and a second set. In box 307, the electronic device 110 can use the target model to filter candidate query items in the first set that do not meet the "niche" criterion. Specifically, the electronic device 110 can use the target model to determine whether the first set includes relatively common (i.e., "mainstream") candidate query items. Further, if the electronic device 110 determines that the first set includes relatively common candidate query items, it can delete these relatively common query items from the first set. In box 308, the electronic device 110 can use the target model to filter candidate query items in the second set that do not meet the "mainstream" criterion. Specifically, the electronic device 110 can use the target model to determine whether the second set includes relatively uncommon (i.e., "niche") candidate query items. Further, if the electronic device 110 determines that the second set includes relatively uncommon candidate query items, it can delete these relatively uncommon candidate query items from the second set. As an example, electronic device 110 can use a target model to determine whether a candidate query is "niche" or "mass-market" based on the frequency with which the candidate query appears in other restaurants, thereby further filtering the first and second sets.

[0054] Furthermore, the electronic device 110 can determine a second set of candidate query items that meet preset conditions and have completed filtering, based on the first and second sets that have completed filtering. The second set of candidate query items that meet preset conditions and have completed filtering will be processed below.

[0055] Referring again to Figure 3, in box 309, electronic device 110 can also determine additional query items associated with the point of interest based on the set of tags associated with the point of interest. As an example, electronic device 110 can also obtain highlight tags for the restaurant, such as tags like "XXX is very unique," "XXX has been to this restaurant," "This restaurant has a bad environment," etc., as additional query items.

[0056] Additionally or alternatively, electronic device 110 can also use a supervised model to filter out some relatively empty and time-sensitive candidate query items and / or additional query items, such as candidate query items such as "waiter's enthusiasm" and "opening ceremony discount".

[0057] Furthermore, in box 310, the electronic device 110 can use a model to score the second set of candidate query items and additional query items. As an example, the electronic device 110 can use a scoring model to score candidate query items based on factors such as scarcity or accuracy. Specifically, the electronic device 110 can use a scoring model to give high scores (e.g., 3-4 points) to candidate query items that are scarce or easily improve the efficiency of user information retrieval, and low scores (e.g., 0-2 points) to candidate query items that are time-sensitive or do not easily improve the efficiency of user information retrieval. In some embodiments, the electronic device 110 can also give low scores to candidate query items in the second set, which will be used as supplementary data for display or searching on interfaces associated with points of interest.

[0058] In some embodiments, the electronic device 110 can filter candidate queries with a score of 0 to obtain a set of high-quality candidate queries. Such candidate queries with a score of 0 may be time-sensitive queries (e.g., opening ceremony) and / or queries with problems.

[0059] Through the scoring process described above, the electronic device 110 can display query items with higher scores at the forefront of the Points of Interest (POI) interface and / or highlight query items with higher scores, while displaying query items with lower scores at the end. Taking Figures 4A and 4B as examples, the electronic device 110 can prioritize displaying query items with higher scores on the interface based on the score ranking of the candidate query items in the second candidate query category. For example, the electronic device 110 can prioritize displaying query items 401 and 402 with higher scores on interfaces 400A and 400B. It is understood that the score of query item 401 must be greater than or equal to the score of query item 403.

[0060] Furthermore, taking Figure 4C as an example, the electronic device 110 can highlight query items with higher scores on the map so that users can view and access them.

[0061] Returning to Figure 2, in box 240, electronic device 110 determines at least one query item associated with the point of interest from the second set of candidate query items based on the evaluation information of the second set of candidate query items.

[0062] In some embodiments, the electronic device 110 may provide a second set of candidate query items and descriptive information of points of interest to a second model to obtain answers to preset questions. Such a second model may be, for example, a supervised model and / or a model for generating recommendation intentions. Such descriptive information may, for example, indicate location information, review information, rating information, environmental atmosphere information, and food sales information corresponding to the points of interest.

[0063] Referring again to Figure 3, in box 311, electronic device 110 can use a supervised model to identify the second set of candidate query items and the corresponding restaurant description information, thereby obtaining the answer content about the preset question.

[0064] In some embodiments, the description information may indicate a set of services associated with the point of interest, and the preset question may indicate the target service in the output set of services that matches the candidate query. As an example, such a set of services may be food sales services, environmental atmosphere services, etc.

[0065] As an example, in response to the supervised model identifying the target candidate query as a food sales service, electronic device 110 can extract recommended dishes from the corresponding restaurant. Specifically, electronic device 110 can obtain all recommended dishes from the corresponding restaurant and the recommended dish that best matches the target candidate query. Furthermore, electronic device 110 can highlight the recommended dishes module based on the restaurant's details page, and prominently display the recommended dish corresponding to the target candidate query within that module. For example, electronic device 110 can pin the recommended dish to the top of the recommended dishes module.

[0066] As another example, in response to the supervised model identifying the target candidate query item as an environmental atmosphere service, the electronic device 110 can highlight the environmental information on the details page of the corresponding restaurant. Such environmental information can be highlighted in the form of pictures or text descriptions. For example, the electronic device 110 can pin the environmental information of the restaurant to the top for users to view.

[0067] In another embodiment, the descriptive information may also indicate comment data associated with points of interest, and a preset question may indicate the reasons for recommending candidate queries based on the comment data.

[0068] As an example, if electronic device 110 determines that the target candidate query is not a set of services associated with a point of interest, it can use a recommendation intention generation model to generate a recommendation reason corresponding to the target candidate query. For example, if the target candidate query is "XXX recommends", electronic device 110 can generate a corresponding recommendation reason based on the comment data associated with the point of interest, such as "XXX has been to this restaurant" or "XXX recommended this restaurant on a certain program". Furthermore, electronic device 110 can highlight the recommendation reason on the corresponding restaurant's details page; for example, electronic device 110 can pin the recommendation reason "XXX has been to this restaurant" to the top.

[0069] In some other embodiments, in response to the target candidate query being a set of services associated with a point of interest, the electronic device 110 may also use a recommendation intention generation model to generate a recommendation reason corresponding to the point of interest, which is associated with this set of services. For example, if the target candidate query is "want to eat hot pot", then the recommendation reason could be "Restaurant A's hot pot tastes very good".

[0070] Based on the above, the electronic device 110 can obtain the answer content of the preset question from the second set of candidate query items.

[0071] Furthermore, the electronic device 110 can determine the evaluation information of the second group of candidate query items based on the answer content. Such evaluation information can indicate the uniqueness of the expression of the second group of candidate query items, that is, support users to obtain information related to their points of interest more efficiently.

[0072] Referring again to Figure 3, in box 312, personnel can score the candidate query items in this second group of candidate query items, thereby filtering out candidate query items with low scores.

[0073] As an example, personnel can score the candidate queries in the second group of candidate queries based on the extracted recommended dishes and the generated recommendation reasons to obtain the corresponding human evaluation information. Of course, personnel can also score the candidate queries in the second group of candidate queries based on other scoring criteria to obtain the corresponding human evaluation information, which will not be elaborated here.

[0074] In some embodiments, the electronic device 110 may also score the second group of candidate query items based on the answer content to further determine the evaluation information of the second group of candidate query items. As an example, the electronic device may score the second group of candidate query items based on whether the answer content meets preset conditions. The preset conditions may include whether the answer content is reasonable, whether the answer content reflects the characteristics of the point of interest, whether the quality of the answer content is higher than a threshold, whether the answer content matches the point of interest, whether the answer content matches a preset question, etc.

[0075] In other embodiments, the electronic device 110 may also determine the evaluation information corresponding to the second set of candidate query items based on the candidate evaluation information of the second set of candidate query items determined by the answer content and the manual evaluation information of personnel for the second set of candidate query items.

[0076] In some embodiments, the electronic device 110 may also feed back the candidate query items whose evaluation information does not meet the scoring threshold and the reasons why the evaluation information does not meet the scoring threshold to the scoring model in step 310 (for example, using the candidate query items whose evaluation information does not meet the scoring threshold and the reasons why the evaluation information does not meet the scoring threshold as prompts for the scoring model), so that the scoring model can further learn and summarize the scoring criteria, thereby improving the accuracy of the scoring model.

[0077] Furthermore, the electronic device 110 can, based on the evaluation information, determine at least one query item associated with the point of interest from the second set of candidate query items. For example, it can determine query items with scores higher than a score threshold or a predetermined number of top-ranked query items from the second set of candidate query items. In some embodiments, such query items may include text content and / or emoticons.

[0078] In some embodiments, in response to determining that a user-input query matches a query obtained through the above process, the electronic device 110 can provide a corresponding point of interest as a search result. In other embodiments, the electronic device 110 can display the corresponding query on an interface associated with the point of interest as a description of the point of interest.

[0079] In this way, embodiments of the present disclosure enable users to obtain information associated with points of interest more efficiently, thereby improving the efficiency of information transmission.

[0080] Example devices and equipment

[0081] Embodiments of this disclosure also provide corresponding apparatus for implementing the methods or processes described above. Figure 5 shows a schematic structural block diagram of an example apparatus 500 for generating query items according to certain embodiments of this disclosure. Apparatus 500 may be implemented as or included in electronic device 110. The various modules / components in apparatus 500 may be implemented by hardware, software, firmware, or any combination thereof.

[0082] As shown in Figure 5, the device 500 includes a content generation module 510 configured to generate a first set of candidate query items associated with points of interest based on user interaction information associated with points of interest; a first determination module 520 configured to determine the number of points of interest matching the first set of candidate query items; a second determination module 530 configured to determine a second set of candidate query items that meet preset conditions from the first set of candidate query items based on the number of points of interest; and a third determination module 540 configured to determine at least one query item associated with a point of interest from the second set of candidate query items based on evaluation information of the second set of candidate query items.

[0083] In some embodiments, the apparatus 500 further includes a fourth determining module configured to determine an interest point from a set of candidate interest points based on classification information of a set of candidate interest points.

[0084] In some embodiments, user interaction information includes at least one of the following: media content associated with a point of interest; and comment content associated with a point of interest.

[0085] In some embodiments, the content generation module 510 is further configured to provide user interaction information to the first model to generate multiple candidate query items; and to determine a first set of candidate query items by merging a group of candidate query items whose similarity is greater than a threshold among the multiple candidate query items.

[0086] In some embodiments, the preset condition indicates that the number of points of interest corresponding to the candidate query item is greater than a first threshold; and / or the number of points of interest corresponding to the candidate query item is less than a second threshold, wherein the second threshold is less than or equal to the first threshold.

[0087] In some embodiments, the evaluation information of the second set of candidate query terms indicates the uniqueness of the expression of the second set of candidate query terms.

[0088] In some embodiments, the apparatus 500 further includes a processing module configured to provide a second set of candidate query items and points of interest with a second model to obtain answer content about a preset question; and to determine evaluation information of the second set of candidate query items based on the answer content.

[0089] In some embodiments, the description information indicates a set of services associated with a point of interest, and the preset question indicates the target service among the set of services that matches the candidate query.

[0090] In some embodiments, the descriptive information indicates comment data associated with points of interest, and the preset question indicates the reasons for recommending candidate queries based on the comment data.

[0091] In some embodiments, the apparatus 500 further includes a fifth determining module configured to determine additional query items associated with the point of interest based on a set of tags associated with the point of interest.

[0092] In some embodiments, at least one query item includes text content and / or emojis.

[0093] The modules included in device 500 can be implemented in various ways, including software, hardware, firmware, or any combination thereof. In some embodiments, one or more units can be implemented using software and / or firmware, such as machine-executable instructions stored on a storage medium. In addition to or as an alternative to machine-executable instructions, some or all of the modules in device 500 can be implemented at least partially by one or more hardware logic components. By way of example, and not limitation, exemplary types of hardware logic components that can be used include field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-chips (SoCs), complex programmable logic devices (CPLDs), and so on.

[0094] As shown in Figure 6, electronic device 600 is in the form of a general-purpose electronic device. Components of electronic device 600 may include, but are not limited to, one or more processors or processor 610, memory 620, storage device 630, one or more communication units 640, one or more input devices 650, and one or more output devices 660. Processor 610 may be a physical or virtual processor and is capable of performing various processes according to programs stored in memory 620. In a multiprocessor system, multiple processors execute computer-executable instructions in parallel to improve the parallel processing capability of electronic device 600. Electronic device 600 shown in Figure 6 can be used to implement electronic device 110 of Figure 1.

[0095] Electronic device 600 typically includes multiple computer storage media. Such media can be any accessible media that is accessible to electronic device 600, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 620 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. Storage device 630 can be removable or non-removable media and can include machine-readable media, such as flash drives, disks, or any other media that can be used to store information and / or data and can be accessed within electronic device 600.

[0096] Electronic device 600 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not shown in FIG. 6, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks may be provided. In these cases, each drive may be connected to a bus (not shown) via one or more data media interfaces. Memory 620 may include computer program product 625 having one or more program modules configured to perform various methods or actions of various embodiments of the present disclosure.

[0097] The communication unit 640 enables communication with other electronic devices via a communication medium. Additionally, the functionality of the components of the electronic device 600 can be implemented using a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, the electronic device 600 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network node.

[0098] Input device 650 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 660 can be one or more output devices, such as a monitor, speaker, printer, etc. Electronic device 600 can also communicate with one or more external devices (not shown) via communication unit 640 as needed. These external devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with electronic device 600, or with any device that enables electronic device 600 to communicate with one or more other electronic devices (e.g., network card, modem, etc.). Such communication can be performed via input / output (I / O) interface (not shown).

[0099] According to an exemplary implementation of this disclosure, a computer-readable storage medium is provided that stores computer-executable instructions thereon, wherein the computer-executable instructions are executed by a processor to implement the methods described above. According to an exemplary implementation of this disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, which are executed by a processor to implement the methods described above.

[0100] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0101] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processing unit of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0102] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0103] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0104] Various implementations of this disclosure have been described above. The foregoing description is exemplary and not exhaustive, nor is it limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is chosen to best explain the principles, practical applications, or improvements to technology in the market, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. A method for generating query terms, comprising: Based on user interaction information associated with points of interest, a first set of candidate query items associated with the points of interest is generated; Determine the number of points of interest that match the first group of candidate query items; Based on the number of points of interest, a second group of candidate query items that meet preset conditions is determined from the first group of candidate query items; as well as Based on the evaluation information of the second group of candidate query items, at least one query item associated with the point of interest is determined from the second group of candidate query items.

2. The method according to claim 1, further comprising: The interest point is determined from the set of candidate interest points based on the classification information of a set of candidate interest points.

3. The method according to claim 1, wherein the user interaction information includes at least one of the following: Media content associated with the points of interest; Comments related to the stated points of interest.

4. The method according to claim 1, wherein generating a first set of candidate query items associated with the points of interest based on user interaction information associated with the points of interest comprises: The user interaction information is provided to the first model to generate multiple candidate query items; as well as The first group of candidate query items is determined by merging a group of candidate query items whose similarity is greater than a threshold among the multiple candidate query items.

5. The method according to claim 1, wherein the preset condition indicates: The number of interest points corresponding to the candidate query item is greater than a first threshold; and / or The number of points of interest corresponding to the candidate query item is less than a second threshold, and the second threshold is less than or equal to the first threshold.

6. The method of claim 1, wherein the evaluation information of the second set of candidate query items indicates the uniqueness of the expression of the second set of candidate query items.

7. The method according to claim 1, further comprising: The second model is provided with descriptive information of the second set of candidate query items and the points of interest to obtain answers to preset questions. as well as Based on the answer content, the evaluation information of the second group of candidate query items is determined.

8. The method of claim 7, wherein the description information indicates a set of services associated with the point of interest, and the preset question indicates the output of a target service among the set of services that matches the candidate query.

9. The method of claim 7, wherein the descriptive information indicates comment data associated with the point of interest, and the preset question indicates a reason for recommending candidate queries based on the comment data.

10. The method according to claim 1, further comprising: Based on the set of tags associated with the point of interest, additional query items associated with the point of interest are determined.

11. The method of claim 1, wherein the at least one query item includes text content and / or emojis.

12. An apparatus for generating query terms, comprising: The content generation module is configured to generate a first set of candidate query items associated with the points of interest based on user interaction information associated with the points of interest. The first determining module is configured to determine the number of points of interest that match the first group of candidate query items; The second determining module is configured to determine a second group of candidate query items that meet preset conditions from the first group of candidate query items based on the number of points of interest. as well as The third determining module is configured to determine at least one query item associated with the point of interest from the second group of candidate query items based on the evaluation information of the second group of candidate query items.

13. An electronic device, comprising: At least one processor; as well as At least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor, the instructions causing the electronic device to perform the method according to any one of claims 1 to 11 when executed by the at least one processor.

14. A computer-readable storage medium having stored thereon computer-executable instructions that can be executed by a processor to implement the method according to any one of claims 1 to 11.

15. A computer program product tangibly stored in a computer storage medium and comprising computer-executable instructions that, when executed by a device, cause the device to perform the method according to any one of claims 1 to 11.

Images