Information recommendation method and device, electronic equipment, storage medium and product

Abstract

The application provides an information recommendation method and device, electronic equipment, storage medium and product, and belongs to the technical field of Internet. The method comprises the following steps: receiving a query request sent by a user account, wherein the query request comprises page information of a target page to be displayed; determining a recall batch of each recall mode based on the page information of the target page, information stored in a cache, and a recall quantity corresponding to each recall mode; performing an information recall operation based on the recall batch of each recall mode to obtain candidate information recalled by each recall mode; determining target information corresponding to the target page based on the candidate information recalled by multiple recall modes; and sending the target information to the user account. By recalling candidate information in multiple batches, the application avoids recalling a large amount of information at one time, and improves system performance.

Description

Technical Field

[0001] This application relates to the field of Internet technology, and in particular to an information recommendation method, apparatus, electronic device, storage medium, and product. Background Technology

[0002] With the development of internet technology, information on the internet has exploded. Faced with this massive amount of information, recommending information that meets user needs has become crucial.

[0003] In related technologies, a large amount of information, such as 10,000 items, is retrieved at once based on a search request sent by a user account. The retrieved information is then stored in a cache. When a query request for a specific page is received from a user account, the information corresponding to that page is retrieved from the cache and then recommended to the user account.

[0004] The above information recommendation method can meet the user's need for any page turning, but the system performance is poor because it recalls a large amount of information at once. Summary of the Invention

[0005] This application provides an information recommendation method, apparatus, electronic device, storage medium, and product. By employing multiple recall methods, candidate information is recalled in multiple recall batches, avoiding the need to recall a large amount of information at once, thus improving system performance. The technical solution is as follows:

[0006] Firstly, an information recommendation method is provided, the method comprising:

[0007] Receive a query request sent by a user account, the query request including page information of the target page to be displayed;

[0008] Based on the page information of the target page, the information stored in the cache, and the recall quantity corresponding to each recall method, the recall batch for each recall method is determined;

[0009] Based on the recall batches of each recall method, perform information recall operations to obtain candidate information recalled using each recall method;

[0010] Based on the candidate information recalled using multiple recall methods, the target information corresponding to the target page is determined;

[0011] The target information is sent to the user account.

[0012] Secondly, an information recommendation device is provided, the device comprising:

[0013] The receiving module is used to receive query requests sent by user accounts, wherein the query request includes page information of the target page to be displayed;

[0014] The first determining module is used to determine the recall batch for each recall method based on the page information of the target page, the information stored in the cache, and the recall quantity corresponding to each recall method.

[0015] The recall module is used to perform information recall operations based on the recall batches of each recall method, and obtain candidate information recalled using each recall method.

[0016] The second determining module is used to determine the target information corresponding to the target page based on the candidate information recalled using multiple recall methods;

[0017] The sending module is used to send the target information to the user account.

[0018] Thirdly, an electronic device is provided, including a processor and a memory; the memory stores at least one piece of program code; the at least one piece of program code is called and executed by the processor to implement the information recommendation method as described in the first aspect.

[0019] Fourthly, a computer-readable storage medium is provided, wherein at least one computer program is stored therein, and when executed by a processor, the at least one computer program is capable of implementing the information recommendation method as described in the first aspect.

[0020] Fifthly, a computer program product is provided, the computer program product comprising a computer program that, when executed by a processor, can implement the information recommendation method as described in the first aspect.

[0021] The beneficial effects of the technical solutions provided in this application are:

[0022] This application supports multiple recall methods. After receiving a query request from a user account, based on the recall quantity of each recall method, the information stored in the cache, and the page information of the target page to be displayed, the recall batch corresponding to each recall method is determined. Then, based on the recall batch corresponding to each recall method, the corresponding recall method is used to perform information recall operations, obtaining candidate information recalled using each recall method. Then, based on the candidate information recalled by multiple recall methods, the target information on the target page is determined, and the target information is recommended to the user account. Since a one-time recall method is no longer used, but multiple recall methods are used to recall in multiple batches, the amount of information recalled in a single recall is reduced, the system pressure is reduced, and the system performance is improved. Moreover, the information of each recall is stored in the cache. By querying the cache, duplicate information can be recalled, further reducing the number of candidate information and helping to improve system performance. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a schematic diagram of the implementation environment involved in an information recommendation method provided in an embodiment of this application;

[0025] Figure 2 This is a flowchart of an information recommendation method provided in an embodiment of this application;

[0026] Figure 3 This is a flowchart of another information recommendation method provided in the embodiments of this application;

[0027] Figure 4 This is a schematic diagram of the structure of an information recommendation device provided in an embodiment of this application;

[0028] Figure 5 This illustration shows a structural block diagram of an electronic device 500 provided in an exemplary embodiment of this application. Detailed Implementation

[0029] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0030] It is understood that the terms "each," "multiple," and "any" used in the embodiments of this application, etc., mean that "multiple" includes two or more, "each" refers to each of the corresponding multiples, and "any" refers to any one of the corresponding multiples. For example, multiple words include 10 words, and "each word" refers to each of the 10 words, while "any word" refers to any one of the 10 words.

[0031] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation portals are provided for users to choose to authorize or refuse.

[0032] Before implementing the embodiments of this application, the terms involved in this application will be explained first.

[0033] Search recommendation is short for search engine recommendation. It refers to the process by which search engines recommend relevant search results to users based on their search history, search behavior, browsing history, and other information. This can help users find the information they want more quickly and improve information search efficiency.

[0034] Caching refers to temporarily storing data in memory to improve the efficiency of data access. In search and recommendation systems, caching can be used to store candidate sets to improve recall efficiency.

[0035] Multi-path recall refers to employing multiple recall strategies to recall candidate sets separately, and then merging the recall results from different strategies to obtain a final candidate set. Using multi-path recall can improve the accuracy and diversity of the recalled information.

[0036] Recall batches refer to dividing the candidate set into multiple batches and then recalling them separately. Recall batches can improve the efficiency of recall, especially when the candidate set is large.

[0037] Mainstream recall refers to the primary recall strategy employed. Mainstream recall typically uses simple strategies, such as text-based recall strategies, to improve recall efficiency.

[0038] Bypass recall refers to recall strategies used to supplement main path recall. Bypass recall typically employs complex strategies, such as vector recall strategies, to improve the accuracy and diversity of the recall.

[0039] Multi-path fusion refers to combining multiple recall results to obtain a final candidate set. Multi-path fusion can improve the accuracy and diversity of recall results.

[0040] In search and recommendation scenarios, there are currently two main recall fusion solutions:

[0041] The first option is a one-time recall and integration solution.

[0042] This solution employs a large-scale retrieval and fusion approach to retrieve the information needed for a user's current search or recommendation in one go. The amount of information retrieved at once is typically very large, for example, 10,000 entries. This retrieved information is usually stored in a cache for users to access later via page navigation. While this solution can satisfy users' need for arbitrary page navigation, the large volume of information retrieved at once places high demands on system processing performance and is time-consuming.

[0043] The second method is the waterfall-style recall plan.

[0044] This solution employs a batch recall and fusion approach, recalling the information needed for the user's current search or recommendation in multiple batches. It then uses a waterfall-style browsing method to continuously generate subsequent information related to the user's search or recommendation, thereby reducing the amount of information in each recall batch. Generally, the amount of information recalled in each batch can exceed the amount of information displayed in a single waterfall display, thus avoiding blank areas during browsing and improving the user experience. Alternatively, a certain amount of information can be recalled at once and then stored in a cache to meet the user's need for continuous waterfall browsing. This solution addresses the performance and time consumption issues of one-time recall and fusion solutions; however, because it uses a waterfall-style browsing method, the total amount of information cannot be accurately determined, and users cannot manually turn pages, thus failing to meet user needs.

[0045] To address the issues of large information volume, long processing time, and high system performance requirements in single-batch recall and fusion scenarios, and to resolve the inability to perform pagination in multi-batch recall, this application provides an information recommendation method. This method employs a multi-batch recall approach, recalling information sequentially in batches as needed, reducing the amount of information recalled per batch, improving system performance, and shortening the time spent on the recall and fusion process. Furthermore, caching technology is used to write the recalled and fused information into a cache for subsequent pagination queries, reducing the number of query requests sent, improving system performance, and reducing the time spent on the recall and fusion process. Additionally, by setting recall and fusion strategies, it is ensured that the recalled candidate information can be paginated correctly.

[0046] Please refer to Figure 1 It illustrates the implementation environment involved in the information recommendation method provided in the embodiments of this application, see [link to relevant documentation]. Figure 1 The implementation environment includes: terminal 101 and server 102. Terminal 101 and server 102 can communicate directly or indirectly through network 103, which can be a wired network or a wireless network.

[0047] The terminal 101 can be a smartphone, tablet, laptop, desktop computer, smart speaker, wearable device, etc. The terminal 101 has at least one search and recommendation application installed, such as a shopping application. Based on this application, the terminal 101 can send search or query requests to the server 102 through a logged-in user account to obtain the required information.

[0048] Server 102 serves as the backend server for any search and recommendation application in terminal 101. Server 102 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, CDN (Content Delivery Network), and big data and artificial intelligence platforms. Server 102 can receive search or query requests sent by terminal 101. In response to these requests, it can use various recall methods to recall candidate information in multiple batches, merge the candidate information recalled by these methods, and recommend the merged information to terminal 101.

[0049] This application provides an information recommendation method, see [link to relevant documentation]. Figure 2 The method flow provided by the embodiments of this application, executed by server 102, includes:

[0050] 201. Receive query requests sent by user accounts.

[0051] The query request can include page information of the target page to be displayed, such as the page number. Generally, the user account requests a page number greater than or equal to 1. In the search push scenario, to obtain the required information, the user account can enter search criteria on the search push application. These search criteria can be search terms, etc., and then send a query request to the server based on these search criteria. This query request includes not only the page information of the target page but also the search criteria. In this case, the target page can be the first page.

[0052] Of course, the search application interface can display information and page numbers retrieved based on search criteria. While browsing the information on the search application interface, users can perform page turning operations to generate a query request for the target page. At this time, the target page can be the page selected by the user in the search application interface, or the page corresponding to the page number entered by the user in the search application interface.

[0053] 202. Based on the page information of the target page, the information stored in the cache, and the recall quantity corresponding to each recall method, determine the recall batch for each recall method.

[0054] This application supports multiple recall methods, including main path recall and side path recall. Main path recall can be text recall, which directly recalls results based on the search terms entered by the user account. Side path recall can be vector recall, which generates a corresponding feature vector based on the search terms entered by the user account and then recalls results based on the generated feature vector. In this application embodiment, the main path recall can be one path, and the side path recall can be one path or multiple paths. For multi-path recall fusion, the total number of search results is based on the main path recall, with side path recall as a supplement. Therefore, it is necessary to ensure that the minimum number of information recalled using the main path recall method is greater than or equal to the amount of information carried by the target page. For ease of analysis and calculation, this application embodiment sets the amount of information carried on each page to be the same. Furthermore, considering that the bypass recall method is based on the similarity of feature vectors, the accuracy of the recalled information is worse than that of the main road recall method. Therefore, to ensure the accuracy of the recalled information, the recall batches for the main road recall method can be unlimited, while the recall batches for the bypass recall method can be limited, such as once. Additionally, embodiments of this application can also set corresponding recall quantities for different recall batches of the main road recall method. Specifically, the recall quantities for different recall batches of the main road recall method can be set to be the same, or they can be set to be different. For example, the recall quantity for the first recall batch of the main road recall method can be set to x, and the recall quantity for the second recall batch can be set to y, where x and y are positive integers, and x and y can be the same or different. Similarly, embodiments of this application can also set corresponding recall quantities for different recall batches of the bypass recall method. Specifically, the recall quantities for different recall batches of the bypass recall method can be set to be the same, or they can be set to be different. For example, the number of items recalled in the first recall batch of the bypass recall method can be set to z.

[0055] Let the recall batch of the main road recall method be i (where i is greater than or equal to 2), the recall quantity of the first recall batch of the main road recall method be x, and the recall quantity of the second recall batch and subsequent recall batches be y. Then, when using the main road recall method for recall, the range of the number of information recalled in different recall batches are as follows: the range of the number of information recalled in the first recall batch is [0, x); the range of the number of information recalled in the second recall batch is [x, x+y); and the range of the number of information recalled in the i-th recall batch is [y*(i-2)+x, y*(i-1)+x).

[0056] If the number of recall batches in the bypass recall method is set to 1, and the number of recalls in the first recall batch of the bypass recall method is z, then when the bypass recall method is used for recall, the range of the number of information recalled in the first recall batch is [0, z).

[0057] In this embodiment of the application, the recall batch for each recall method is determined based on the page information of the target page, the information stored in the cache, and the recall quantity corresponding to each recall method. The following method can be used:

[0058] 2011. Based on the number of pages and the amount of information displayed on each page, determine the information carried by the target page.

[0059] In the application embodiment, the number of pages of the target page is set to m, and the number of information displayed on each page is n. Then the range of the number of information carried by the target page is [n*(m-1), nm).

[0060] For example, if the target page has 10 pages and each page displays 10 pieces of information, then the range of the number of pieces of information on the target page is [90, 100].

[0061] 2012. Based on the information carried by the target page, the information stored in the cache, and the recall quantity corresponding to each recall method, determine the recall batch for each recall method.

[0062] In one possible implementation, the recall batch for each recall method is determined based on the information carried by the target page, the information stored in the cache, and the recall quantity corresponding to each recall method. This can be achieved using the following method:

[0063] 201211. Check if the information carried by the target page is stored in the cache.

[0064] In this embodiment of the application, the cache can store information retrieved based on user accounts for search terms. To avoid repeated retrieval of information, it is possible to query whether the information carried by the target page is stored in the cache.

[0065] 201212. When the information carried by the target page is stored in the cache, the number of information to be recalled is obtained by subtracting the number of information carried by the target page stored in the cache from the number of information displayed on each page.

[0066] When the cache stores the information carried by the target page, the amount of information carried by the target page stored in the cache can be obtained, as well as the amount of information displayed on each page. Then, the amount of information carried by the target page stored in the cache is subtracted from the amount of information displayed on each page to obtain the amount of information to be recalled.

[0067] The information carried by the target page stored in the cache can include two cases:

[0068] The first scenario is that all the information contained in the target page is stored in the cache.

[0069] In the first scenario, since all the information on the target page is stored in the cache, there is no need for retrieval; the information can be directly retrieved from the cache. In this case, the number of information items to be retrieved is 0. The specific analysis is as follows: Since the number of information items on the target page is the number of information items displayed per page, and all the information on the target page is stored in the cache, that is, the number of information items stored in the cache is the number of information items displayed per page. Subtracting the number of information items stored in the cache from the number of information items displayed per page yields a result showing that the number of information items to be retrieved is 0.

[0070] The second scenario is that the information contained in the target page is stored in the cache.

[0071] For the second scenario, information stored in the cache can be retrieved directly from the cache, while information not stored in the cache needs to be retrieved again.

[0072] 201213. Based on the recall quantity and the amount of information to be recalled corresponding to each recall method, determine the recall batch for each recall method.

[0073] In this embodiment, the number of items recalled for each recall method is fixed, while the number of recall batches for the bypass recall method is limited. Therefore, the recall batches for the bypass recall method can be pre-set, and the recall batches for the main recall method can be determined based on the number of items recalled for each recall method, the number of items to be recalled, and the recall batches for the bypass recall method. For example, if the number of items to be recalled is 100, the number of recall batches for the bypass recall method is 1, the number of items recalled for the bypass recall method is 10, the number of items recalled for the first recall batch of the main recall method is 50, and the number of items recalled for the second and subsequent recall batches of the main recall method is 30, then subtracting the 10 items recalled by the bypass recall method from the 100 items to be recalled, the remaining 90 items need to be recalled using the main recall method. Since the 90 items need to be recalled 3 times using the main recall method, the number of recall batches for the main recall method can be determined to be 3.

[0074] Two points need to be clarified below. First, considering that this application's embodiments employ a multi-path recall method, the information recalled by this method may have some overlap. If recall is based on the number of pieces of information to be recalled, after merging the information from multiple recall methods, the total number of merged information plus the number of information stored in the cache may be less than the number of pieces of information required by the target page, resulting in blank areas on the target page and a poor user experience. To improve the user's browsing experience and ensure that the target page can be displayed correctly, the total number of pieces of information recalled using each recall method should be greater than the number of pieces of information to be recalled.

[0075] Secondly, the more recall batches there are, the more information is recalled, which better meets the pagination requirements. However, as the number of recall batches increases, the amount of information stored in the cache also increases, and the system performance deteriorates. Therefore, the number of recall batches for each recall method should not be too large.

[0076] In another possible implementation, the recall batch for each recall method is determined based on the information quantity range, the information stored in the cache, and the recall quantity corresponding to each recall method. This can be achieved using the following method:

[0077] 201221. Based on the number of information displayed on each page and the recall quantity corresponding to each recall method, determine the reference recall batch for each recall method.

[0078] 201222. Check if the information carried by the target page is stored in the cache.

[0079] 201221. When the information carried by the target page is stored in the cache, the number of information displayed on each page is subtracted from the number of information carried by the target page stored in the cache to obtain the number of information to be recalled.

[0080] 201222. Based on the amount of information to be recalled, the reference recall batch for each recall method is corrected to obtain the recall batch for each recall method.

[0081] Regarding this step, since the reference recall batch for each recall method is determined based on the amount of information displayed on the target page, and the cache stores some information from the target page, recalling according to the reference recall batch for each recall method would recall duplicate information, wasting network resources, prolonging the recall time, and reducing system performance. Therefore, once the actual amount of information to be recalled is determined, the reference recall batch for each recall method can be modified based on this actual amount of information to be recalled. When modifying the reference recall batch for each recall method, the recall batch for the bypass recall method can be reduced while ensuring that the main recall method and the bypass recall method can be recalled in parallel.

[0082] In another embodiment of this application, before determining the recall batch for each recall method based on the page information of the target page, the information stored in the cache, and the recall quantity corresponding to each recall method, the server can query whether the shared information context of the user account is stored in the cache. This shared information context is information shared when the user account performs multiple query operations on candidate information found for the same search term. This shared information can be the total number of candidate information found based on the same search term for the user account, etc. If the shared information context is stored in the cache, it is obtained, and then the system is configured based on the shared information context and the number of information displayed per page. The system determines the maximum number of pages in the system and then checks if the target page's page count exceeds this maximum. If the target page's page information includes fewer pages than the maximum, it is determined that the target page's page count does not exceed the page limit. The system then performs operations based on the target page's page information, cached information, and the recall quantity corresponding to each recall method to determine the recall batch for each recall method. If the target page's page information includes more pages than the maximum, it is determined that the target page's page count exceeds the page limit. A notification is then sent to the user account, prompting the user to modify the page information of the target page to be displayed.

[0083] Furthermore, if the shared information context is not stored in the cache, a shared information context can be generated for the user account after the current information retrieval operation is completed, and then stored in the cache so that the shared information context can be retrieved from the cache when the next query request for the user account is received.

[0084] 203. Based on the recall batches of each recall method, perform information recall operations to obtain candidate information recalled using each recall method.

[0085] In this embodiment, once the recall batch for each recall method is determined, the corresponding recall method for each recall method can be used to perform an information recall operation, thereby obtaining the candidate information recalled by each recall method in each recall batch. For example, if the recall batch for the main road recall method is 2 and the recall batch for the bypass recall method is 1, then two main road recalls and one bypass recall can be performed. When performing each main road recall, candidate information can be recalled according to the recall quantity corresponding to each recall batch, thereby obtaining the candidate information for the two recall batches corresponding to the main road recall method and the candidate information for the one recall batch of the bypass recall method.

[0086] 204. Based on the candidate information recalled using multiple recall methods, determine the target information corresponding to the target page.

[0087] Specifically, based on the candidate information retrieved using multiple recall methods, the target information corresponding to the target page can be determined using the following methods:

[0088] 2041. Merge candidate information recalled by multiple recall methods within the same recall batch to obtain the fusion result of multiple recall batches.

[0089] For candidate information recalled using different recall methods, the candidate information recalled within the same recall batch can be merged to obtain the fusion result for each recall batch. When merging candidate information recalled within the same recall batch, the information recalled by the main recall method and the information recalled by the bypass recall method within the same recall batch can be deduplicated. The deduplicated information is then sorted and stored in a cache for retrieval after the current recall is completed.

[0090] Two points need to be clarified here. First, the fusion operation in this step can be performed during the information recall process. That is, for each batch of candidate information recalled by the main recall method and the bypass recall method, the information recalled in the same batch is fused, and the fusion result is stored in the cache so that it can be retrieved from the cache after the information recall fusion is completed.

[0091] Secondly, the recall batches corresponding to the main road recall method and the recall batches corresponding to the bypass recall method may not be the same. When merging the candidate information recalled by the main road recall method and the candidate information recalled by the bypass recall method, only the candidate information recalled within the same recall batch is merged. For recall batches with only one path, they can be directly stored in the cache.

[0092] 2042. Based on the number of information displayed on each page, obtain a number of information items from the fusion results of multiple recall batches as the target information corresponding to the target page.

[0093] The target information refers to the information displayed on the target page. Since the information stored in the cache is sorted according to the search terms entered by the user account and the user account's attribute information, the earlier the sorted information appears, the better it meets the user's needs. Therefore, when retrieving the target information corresponding to the target page from the cache, the information stored in the cache can be retrieved first, followed by the information retrieved and fused in this recall. Once the number of retrieved information reaches the number of information displayed on the target page, no further retrieval will be performed.

[0094] 205. Send the target information to the user account.

[0095] Once the target information is obtained, it can be sent to the user account so that it can be displayed on the terminal where the user account is logged in, thereby satisfying the user account's browsing needs for the target page.

[0096] This application embodiment is based on caching technology and employs a multi-batch recall method for information retrieval. This solves the problems of poor system performance and long processing times associated with large-scale information retrieval in multi-path recall. By predicting the batches of this recall, it ensures that after the data is written to the cache, the cached data can satisfy pagination requests, thus providing users with the ability to freely flip through pages, conforming to user habits. Furthermore, the method provided in this application embodiment retrieves all information in the database, while a one-time recall fusion scheme can only retrieve a portion of the data in the database, resulting in insufficient information retrieval.

[0097] Figure 3 This document shows an overall flowchart of the information recommendation method provided in an embodiment of this application. See also: Figure 3 The entire process includes the following steps:

[0098] 1. When a query request is received from a user account, the server queries the shared context information of that user account;

[0099] 2. The server obtains the shared context information of the user account.

[0100] 3. The server determines the recall batches for the main recall method and the recall batches for the bypass recall method based on the recall quantity of the main recall method, the recall quantity of the bypass recall method, and the page information of the target page to be displayed.

[0101] 4. Check if the information that needs to be recalled is stored in the cache.

[0102] 5. If the cache stores the information that needs to be recalled this time, then filter out the information that is not in the cache but needs to be recalled this time.

[0103] 6. The recall will be carried out using both main road recall and bypass recall methods.

[0104] 7. Merge the information of the same recall batch for the main road recall method and the bypass recall method, and store the fusion result in the cache.

[0105] 8. If this recall operation is the first recall operation for a user account, then the shared context information of the user account will be generated and stored in the cache.

[0106] 9-10. Based on the requested pagination information, retrieve the corresponding information from the cache to obtain the pagination result.

[0107] All of the above-mentioned optional technical solutions can be combined in any way to form the optional embodiments of this application, and will not be described in detail here.

[0108] Please refer to Figure 4The diagram illustrates a structural schematic of an information recommendation device provided in an embodiment of this application. This device can be implemented through software, hardware, or a combination of both, and can be all or part of an electronic device. The device includes:

[0109] The receiving module 401 is used to receive a query request sent by a user account. The query request includes page information of the target page to be displayed.

[0110] The first determining module 402 is used to determine the recall batch for each recall method based on the page information of the target page, the information stored in the cache, and the recall quantity corresponding to each recall method.

[0111] The recall module 403 is used to perform information recall operations based on the recall batches of each recall method to obtain candidate information recalled using each recall method.

[0112] The second determining module 404 is used to determine the target information corresponding to the target page based on the candidate information recalled using multiple recall methods;

[0113] The sending module 405 is used to send the target information to the user account.

[0114] In another embodiment of this application, the page information includes the page number. A first determining module is used to determine the information carried by the target page based on the page number and the amount of information displayed on each page; and to determine the recall batch of each recall method based on the information carried by the target page, the information stored in the cache, and the recall quantity corresponding to each recall method.

[0115] In another embodiment of this application, the first determining module is used to query whether the information carried by the target page is stored in the cache; if the information carried by the target page is stored in the cache, the number of information displayed on each page is subtracted from the number of information carried by the target page stored in the cache to obtain the number of information to be recalled; based on the recall quantity corresponding to each recall method and the number of information to be recalled, the recall batch of each recall method is determined.

[0116] In another embodiment of this application, the first determining module is configured to determine a reference recall batch for each recall method based on the number of information displayed on each page and the recall quantity corresponding to each recall method; query whether the information carried by the target page is stored in the cache; if the information carried by the target page is stored in the cache, subtract the number of information carried by the target page stored in the cache from the number of information displayed on each page to obtain the number of information to be recalled; and modify the reference recall batch for each recall method based on the number of information to be recalled to obtain the recall batch for each recall method.

[0117] In another embodiment of this application, the device further includes:

[0118] The query module is used to check whether the shared information context of a user account is stored in the cache. The shared information context is the information shared when a user account performs multiple query operations on the candidate information found for the same search term.

[0119] The retrieval module is used to retrieve the shared information context when it is stored in the cache.

[0120] The first determining module is used to determine the recall batch for each recall method when the number of pages of the target page is determined based on the shared information context and does not exceed the page limit, based on the page information of the target page, the information stored in the cache, and the recall quantity corresponding to each recall method.

[0121] In another embodiment of this application, the device further includes:

[0122] The generation module is used to generate a shared information context when the shared information context is not stored in the cache.

[0123] The storage module is used to store the shared information context in the cache so that the shared information context can be retrieved from the cache the next time a query request for a user account is received.

[0124] In another embodiment of this application, the second determining module is used to fuse candidate information recalled by multiple recall methods in the same recall batch to obtain the fusion result of multiple recall batches; based on the number of information displayed on each page, a number of information items are obtained from the fusion result of multiple recall batches as the target information corresponding to the target page.

[0125] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0126] Figure 5 This diagram illustrates a structural block diagram of an electronic device 500 provided in an exemplary embodiment of this application. Typically, the electronic device 500 includes a processor 501 and a memory 502.

[0127] The processor 501 can be implemented using at least one of the following hardware forms: DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 501 may also include a main processor and a coprocessor; the main processor is a processor for processing data in the wake-up state, and the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 501 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, the processor 501 may also include an artificial intelligence processor for handling computational operations related to machine learning.

[0128] The memory 502 may include one or more computer-readable storage media, which may be non-transitory computer-readable storage media, such as CD-ROM (Compact Disc Read-Only Memory), ROM, RAM (Random Access Memory), magnetic tape, floppy disk, and optical data storage devices. The computer-readable storage medium stores at least one computer program, which, when executed, enables an information recommendation method.

[0129] Of course, the aforementioned electronic device may also include other components, such as input / output interfaces and communication components. Input / output interfaces provide an interface between the processor and peripheral interface modules, which can be output devices, input devices, etc. Communication components are configured to facilitate wired or wireless communication between the electronic device and other devices.

[0130] Those skilled in the art will understand that Figure 5 The structure shown does not constitute a limitation on the electronic device 500, and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0131] This application provides a computer-readable storage medium storing at least one computer program, which, when executed by a processor, can implement the above-described information recommendation method.

[0132] This application provides a computer program product, which includes a computer program that, when executed by a processor, can implement the above-described information recommendation method.

[0133] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. An information recommendation method, characterized in that, The method includes: Receive a query request sent by a user account, the query request including page information of the target page to be displayed; Based on the page information of the target page, the information stored in the cache, and the recall quantity corresponding to each recall method, the recall batch for each recall method is determined; Based on the recall batches of each recall method, perform information recall operations to obtain candidate information recalled using each recall method; Based on the candidate information recalled using multiple recall methods, the target information corresponding to the target page is determined; The target information is sent to the user account.

2. The method according to claim 1, characterized in that, The page information includes the page number. The determination of the recall batch for each recall method based on the page information of the target page, the information stored in the cache, and the recall quantity corresponding to each recall method includes: Based on the number of pages and the amount of information displayed on each page, the information carried by the target page is determined; Based on the information carried by the target page, the information stored in the cache, and the recall quantity corresponding to each recall method, the recall batch for each recall method is determined.

3. The method according to claim 2, characterized in that, The determination of the recall batch for each recall method, based on the information carried by the target page, the information stored in the cache, and the recall quantity corresponding to each recall method, includes: Check whether the information carried by the target page is stored in the cache; When the cache stores information carried by the target page, the number of information to be recalled is obtained by subtracting the number of information carried by the target page stored in the cache from the number of information displayed on each page. Based on the recall quantity corresponding to each recall method and the amount of information to be recalled, the recall batch for each recall method is determined.

4. The method according to claim 2, characterized in that, The determination of the recall batch for each recall method, based on the information carried by the target page, the information stored in the cache, and the recall quantity corresponding to each recall method, includes: Based on the amount of information displayed on each page and the recall quantity corresponding to each recall method, determine the reference recall batch for each recall method; Check whether the information carried by the target page is stored in the cache; When the cache stores the information carried by the target page, the number of information to be recalled is obtained by subtracting the number of information carried by the target page stored in the cache from the number of information displayed on each page. Based on the amount of information to be recalled, the reference recall batch for each recall method is adjusted to obtain the recall batch for each recall method.

5. The method according to claim 1, characterized in that, Before determining the recall batch for each recall method based on the page information of the target page, the information stored in the cache, and the recall quantity corresponding to each recall method, the method further includes: Query whether the cache stores the shared information context of the user account, wherein the shared information context is the information shared when the user account performs multiple query operations on the candidate information found for the same search term; When the shared information context is stored in the cache, retrieve the shared information context; When it is determined based on the shared information context that the number of pages of the target page does not exceed the page limit, the operation of determining the recall batch for each recall method is performed based on the page information of the target page, the information stored in the cache, and the recall quantity corresponding to each recall method.

6. The method according to claim 5, characterized in that, The method further includes: When the shared information context is not stored in the cache, the shared information context is generated and stored in the cache so that the shared information context can be retrieved from the cache the next time a query request for the user account is received.

7. The method according to claim 1, characterized in that, The process of determining the target information corresponding to the target page based on candidate information retrieved using multiple recall methods includes: The candidate information recalled by multiple recall methods in the same recall batch is merged to obtain the fusion result of multiple recall batches; Based on the number of information items displayed on each page, the number of information items are obtained from the fusion results of multiple recall batches as the target information corresponding to the target page.

8. An information recommendation device, characterized in that, The device includes: The receiving module is used to receive query requests sent by user accounts, wherein the query request includes page information of the target page to be displayed; The first determining module is used to determine the recall batch for each recall method based on the page information of the target page, the information stored in the cache, and the recall quantity corresponding to each recall method. The recall module is used to perform information recall operations based on the recall batches of each recall method, and obtain candidate information recalled using each recall method. The second determining module is used to determine the target information corresponding to the target page based on the candidate information recalled using multiple recall methods; The sending module is used to send the target information to the user account.

9. An electronic device, characterized in that, It includes a processor and a memory; the memory stores at least one piece of program code; the at least one piece of program code is called and executed by the processor to implement the information recommendation method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one computer program, which, when executed by a processor, is capable of implementing the information recommendation method as described in any one of claims 1 to 7.

11. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, can implement the information recommendation method as described in any one of claims 1 to 7.

Images