Information pushing method and device, equipment, medium and product

Abstract

The invention provides an information pushing method and device, equipment, a medium and a product, which can be applied to the fields of computer technology, information recommendation technology and e-commerce technology. The information pushing method comprises the steps that in response to a received pushing request from an object, a candidate item set is acquired from target mapping according to a target position indicated by the pushing request, the target mapping comprises a corresponding relation between candidate area identification and candidate item information, and the candidate item set is selected from the candidate area identification and the candidate item information; the corresponding relation is determined based on the main body position and the coverage range of the main body used for providing the candidate article; and screening the candidate item set according to the type information indicated by the push request to push the obtained target list to the object.

Description

Technical Field

[0001] This disclosure relates to the fields of computer technology, information recommendation technology, and e-commerce technology, and more specifically, to an information push method, apparatus, device, medium, or product. Background Technology

[0002] Currently, food delivery platforms widely use various ranking lists (such as best-selling lists and positive review lists) to assist users in making decisions and improve ordering efficiency.

[0003] In related technologies, the ranking list is usually divided based on the fourth-level address of the administrative region and the product category. The production process mainly includes: the operators pre-configure the product selection rules (such as sales volume, number of positive reviews, number of repeat purchases, etc.) and scoring models for the ranking list on the platform. The big data system performs offline screening, scoring and sorting of all products according to these rules, and truncates a fixed number of products in the sorted product list to generate a static ranking list.

[0004] In realizing the concept disclosed herein, the inventors discovered at least the following problems in the related technologies: under the same fourth-level address and product category, all users see the same list content, which cannot be differentiated according to the user's real-time location, making it difficult to effectively guarantee the flexibility and accuracy of list push. Summary of the Invention

[0005] In view of this, the present disclosure provides an information push method, apparatus, device, medium, and product.

[0006] According to one aspect of this disclosure, an information push method is provided, comprising: in response to receiving a push request from an object, obtaining a set of candidate items from a target mapping according to a target location indicated by the push request, wherein the target mapping includes a correspondence between candidate region identifiers and candidate item information, the correspondence being determined based on the subject location and coverage area of ​​the subject providing the candidate items; and filtering the set of candidate items according to type information indicated by the push request, so as to push the obtained target list to the object.

[0007] According to another aspect of this disclosure, an information push device is provided, comprising: an acquisition module, configured to, in response to receiving a push request from an object, acquire a set of candidate items from a target mapping according to a target location indicated by the push request, wherein the target mapping includes a correspondence between candidate region identifiers and candidate item information, the correspondence being determined based on the location and coverage of the subject providing the candidate items; and a push module, configured to filter the set of candidate items according to type information indicated by the push request, so as to push the obtained target list to the object.

[0008] According to another aspect of this disclosure, an electronic device is provided, comprising: one or more processors; and a memory for storing one or more instructions, wherein, when executed by the one or more processors, the one or more processors cause the one or more processors to perform the method as described in this disclosure.

[0009] According to another aspect of this disclosure, a computer-readable storage medium is provided having executable instructions stored thereon, which, when executed by a processor, cause the processor to perform the methods described in this disclosure.

[0010] According to another aspect of this disclosure, a computer program product is provided, which includes computer-executable instructions that, when executed, are used to perform the methods described in this disclosure. Attached Figure Description

[0011] The above and other objects, features and advantages of this disclosure will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0012] Figure 1 This illustration schematically shows a system architecture to which the information push method can be applied according to embodiments of the present disclosure;

[0013] Figure 2 A flowchart illustrating an information push method according to an embodiment of the present disclosure is shown schematically;

[0014] Figure 3 This schematic diagram illustrates an example of a process for constructing a target map according to an embodiment of the present disclosure;

[0015] Figure 4A This schematically illustrates an example diagram of the construction process of a first sub-mapping according to an embodiment of the present disclosure;

[0016] Figure 4B This schematically illustrates an example diagram of the construction process of a second sub-mapping according to an embodiment of the present disclosure;

[0017] Figure 4C This schematic diagram illustrates an example of a process for constructing a target map according to another embodiment of the present disclosure;

[0018] Figure 5A The illustration shows an example schematic diagram of an update process for a target mapping according to an embodiment of the present disclosure;

[0019] Figure 5B The illustration shows an example schematic diagram of an update process for a target mapping according to another embodiment of the present disclosure;

[0020] Figure 6The illustration shows an example diagram of the process for obtaining a target list according to an embodiment of the present disclosure;

[0021] Figure 7 A block diagram of an information push device according to an embodiment of the present disclosure is schematically shown; and

[0022] Figure 8 A block diagram of an electronic device suitable for implementing an information push method according to an embodiment of the present disclosure is shown schematically. Detailed Implementation

[0023] The embodiments of the present disclosure will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the disclosure. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts of the present disclosure.

[0024] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0025] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0026] When using expressions such as "at least one of A, B and C", they should generally be interpreted in accordance with the meaning that is commonly understood by those skilled in the art (e.g., "a system having at least one of A, B and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B and C, etc.).

[0027] In the technical solution of this invention, the user information (including but not limited to user personal information, user image information, user device information, such as location information) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of related data all comply with relevant laws, regulations, and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entry points for users to choose to authorize or refuse.

[0028] The ranking process, which uses fourth-level addresses and product categories based on administrative regions as the categorization dimensions, is essentially a "one-size-fits-all" approach. This means that all users with the same fourth-level address and product category see identical ranking content, making it difficult to meet the needs of refined operations. Furthermore, because the rankings are generated offline based on administrative regions, and the actual availability of takeout products is limited by the dynamic delivery range of each store, users may see items on the rankings that cannot be delivered to their specific delivery address. This can interfere with decision-making, reducing the usability of the rankings and the efficiency of guiding orders.

[0029] In summary, the current rankings cannot differentiate based on users' real-time locations, making it difficult to effectively guarantee the flexibility and accuracy of ranking pushes.

[0030] To this end, this disclosure provides an information push method, apparatus, device, medium, and product that can be applied to the fields of computer technology, information recommendation technology, and e-commerce technology. The information push method includes: responding to receiving a push request from an object; obtaining a set of candidate items from a target mapping based on the target location indicated by the push request, wherein the target mapping includes a correspondence between candidate region identifiers and candidate item information, the correspondence being determined based on the location and coverage area of ​​the entity providing the candidate items; and filtering the set of candidate items according to the type information indicated by the push request, so as to push the obtained target list to the object.

[0031] In the embodiments of this disclosure, in response to receiving a push request, a set of candidate items is obtained from a target map based on the target location in the push request. Since the correspondence in the target map is determined based on the location and coverage of the entity providing the items, it ensures that all obtained candidate items are deliverable relative to the target location. This solves the problem that items in the list may not be deliverable in related technologies, improving the practicality and effectiveness of the list and shopping guide. Furthermore, by filtering the set of candidate items according to the type information in the push request, deliverable items can be filtered based on different type information, and the filtered target list is pushed to the recipient. Since the target location changes dynamically with the push request, and the filtering process depends on the set of deliverable items at that specific target location, for the same type information, recipients at different target locations will receive a target list consisting of different items, all matching their target location. This achieves personalized recommendations and improves the flexibility and accuracy of the list push.

[0032] Figure 1 The illustration schematically depicts a system architecture to which the information push method can be applied according to embodiments of this disclosure. It should be noted that... Figure 1 The examples shown are merely examples of system architectures that can be applied to the embodiments of this disclosure, in order to help those skilled in the art understand the technical content of this disclosure, but do not mean that the embodiments of this disclosure cannot be used in other devices, systems, environments or scenarios.

[0033] like Figure 1 As shown, the system architecture 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between different devices.

[0034] It should be noted that the information push method provided in this embodiment can generally be executed by the server 105. Accordingly, the information push device provided in this embodiment can generally be set in the server 105.

[0035] Alternatively, the information push method provided in this embodiment of the present disclosure can also be executed by the first terminal device 101, the second terminal device 102, or the third terminal device 103. Correspondingly, the information push device provided in this embodiment of the present disclosure can also be disposed in the first terminal device 101, the second terminal device 102, or the third terminal device 103.

[0036] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0037] It should be noted that the sequence numbers of the operations in the following methods are for descriptive purposes only and should not be considered as indicating the execution order of the operations. Unless explicitly stated otherwise, the method does not need to be executed in the exact order shown.

[0038] The above describes the system architecture for applying the information push method provided in this disclosure. The following will use... Figure 2 As an example, the information dissemination process of this disclosure will be further explained.

[0039] Figure 2 A flowchart illustrating an information push method according to an embodiment of the present disclosure is shown schematically.

[0040] like Figure 2 As shown, the information push method 200 may include operations S210~S220.

[0041] In operation S210, in response to receiving a push request from an object, a set of candidate items is obtained from the target map according to the target location indicated by the push request. The target map includes the correspondence between candidate area identifiers and candidate item information, and the correspondence is determined based on the subject location and coverage area of ​​the subject that provides the candidate items.

[0042] In operation S220, the candidate item set is filtered according to the type information indicated by the push request in order to push the obtained target list to the target.

[0043] An object refers to the entity that requests the ranking list; for example, an object could be an end user using a food delivery application. A push request is an instruction or message initiated by the object to request the ranking list. The target location refers to the geographic location information included in the push request, used to determine the reachability of the item delivery; for example, the target location could be the latitude and longitude of the user's delivery address, or the latitude and longitude of the user's real-time location.

[0044] The triggering method for push requests can be configured according to actual business needs and is not limited here. For example, a push request can be triggered when a user opens the "Nearby Hot Selling List" page in the food delivery app; alternatively, a push request can also be automatically triggered after detecting that a user has reached a preset time threshold in a certain area on the map page; alternatively, a push request can also be proactively pushed to users who have recently placed orders during peak hours such as lunch or dinner, and is not limited here.

[0045] Upon receiving a push request, the target location indicated in the request can be used as an index to query the set of candidate items from the target map. The target map is a pre-built data structure used to associate a geographic region with deliverable items located within that region. For example, the target map can be presented as a key-value database (such as Redis), where the key is a candidate region identifier, and the value is a list of all deliverable candidate items within the corresponding candidate sub-region. After receiving a push request, the target location can be converted into a region identifier, and this encoding can be used as the key to query the target map.

[0046] Candidate region identifiers can be unique codes for each candidate sub-region after geospatial division. For example, a candidate region identifier can be a string code generated based on the GeoHash algorithm; alternatively, it can be an index code based on a hexagonal grid. For instance, if the candidate sub-regions are polygonal grids, the candidate region identifier can be a string used to uniquely identify a particular candidate sub-region.

[0047] Candidate item information can be relevant attribute data of the item. For example, in a food delivery scenario, candidate item information may include the item's identifier, item category, candidate list type, and evaluation value. The candidate item set refers to the set of item information retrieved from the target mapping based on the target location, indicating that the item is available for delivery at that location.

[0048] The correspondence between candidate region identifiers and candidate item information in the target mapping can be determined based on the entity's location and coverage area. The entity is the person providing the item; for example, it could be a food delivery merchant or a food delivery store. The entity's location is its physical location; for example, it could be the latitude and longitude coordinates of a food delivery store. The coverage area refers to the geographical region where the entity can provide delivery services. For example, the coverage area could be a circular delivery range with a radius of 3 kilometers centered on the food delivery store.

[0049] After retrieving the candidate item set, you can directly filter it based on the type information indicated in the push request. Alternatively, you can obtain a set of recommended items from the food delivery platform's push system based on the target location and type information. The final set of items used to generate the target list can be determined by combining the candidate item set and the recommended item set; this is not limited here.

[0050] Type information can include the item category and the candidate list type. Item category refers to the type of item; for example, item categories can include beverages, desserts, etc. Candidate list type refers to the classification or sorting criteria of the list; for example, candidate list types can be "best-selling list," "highly rated list," "discount list," etc.

[0051] After obtaining the filtered set of items, a target list can be generated from the item set and pushed to the object. For example, the complete target list can be returned directly; alternatively, the top few items of the target list can be pushed first, and the subsequent items in the target list can be loaded and pushed asynchronously based on the object's scrolling behavior, etc., which is not limited here.

[0052] In the embodiments of this disclosure, in response to receiving a push request, a set of candidate items is obtained from a target map based on the target location in the push request. Since the correspondence in the target map is determined based on the location and coverage of the entity providing the items, it ensures that all obtained candidate items are deliverable relative to the target location. This solves the problem that items in the list may not be deliverable in related technologies, improving the practicality and effectiveness of the list and shopping guide. Furthermore, by filtering the set of candidate items according to the type information in the push request, deliverable items can be filtered based on different type information, and the filtered target list is pushed to the recipient. Since the target location changes dynamically with the push request, and the filtering process depends on the set of deliverable items at that specific target location, for the same type information, recipients at different target locations will receive a target list consisting of different items, all matching their target location. This achieves personalized recommendations and improves the flexibility and accuracy of the list push.

[0053] The information push method provided in this disclosure has been explained above. The following will use... Figure 3 As an example, the construction process of a target mapping provided in this disclosure will be further explained.

[0054] Figure 3 The illustration shows an example schematic diagram of the process for constructing a target map according to an embodiment of the present disclosure.

[0055] like Figure 3 As shown, in embodiment 300 of constructing the target mapping, a first sub-mapping 330 can be constructed based on the main body location 311 and coverage area 312 of the main body 310, and the candidate items 320 provided by the main body 310. The first sub-mapping 330 may include the correspondence between candidate area identifiers and candidate item identifiers. Based on the evaluation value 321 obtained by evaluating the candidate items 320, a second sub-mapping 340 can be constructed. The second sub-mapping 340 may include the correspondence between candidate item identifiers and evaluation values. On this basis, the first sub-mapping 330 and the second sub-mapping 340 can be aggregated based on the candidate item identifiers to obtain the target mapping 350.

[0056] Candidate item 320 refers to a product provided by entity 310 that is available for user selection. For example, candidate item 320 could be "bubble tea" or "beef burger" sold in a store. Candidate item identifier refers to a code used to uniquely identify a candidate item 320. For example, candidate item identifier could be the product's SKU.

[0057] For each subject 310, the candidate region identifier corresponding to the coverage area 312 of subject 310 can be calculated, and the candidate item identifiers of all candidate items 320 provided by subject 310 can be associated with these candidate region identifiers to form a first sub-mapping 330. The first sub-mapping 330 is a data structure that represents the association between the geographical area where subject 310 is located and the candidate items 320 provided by subject 310. For example, the first sub-mapping 330 can be a set of key-value pairs, where the key is the candidate region identifier and the value is a list of IDs of all goods provided by the subject within the sub-region corresponding to the candidate region identifier.

[0058] For example, taking the milk tea shop located at the origin of the coordinate system as subject 310, its delivery range within 3 kilometers covers grids A, B, and C. The milk tea shop provides items "milk tea 1" and "milk tea 2". The first sub-mapping can be constructed as: {grid A:[milk tea 1 ID, milk tea 2 ID], grid B:[milk tea 1 ID, milk tea 2 ID], grid C:[milk tea 1 ID, milk tea 2 ID]}.

[0059] The evaluation score 321 refers to the quantitative score obtained after calculating the candidate item 320 using a preset evaluation model. It can be used to characterize a certain aspect or overall performance of the candidate item 320. For example, the evaluation score 321 can be a product popularity score calculated based on the weighted average of sales volume, number of positive reviews, and number of repeat purchases over the past 30 days.

[0060] For each candidate item 320, it can be evaluated according to a set evaluation system (such as sales volume, reputation, profit, etc.), and the obtained evaluation value 321 can be associated with the candidate item identifier of the candidate item 320 to form a second sub-mapping 340. The second sub-mapping 340 is a data structure that represents the relationship between the candidate item 320 and its evaluation value 321. For example, the second sub-mapping 340 can be a set of key-value pairs, where the key is the product ID and the value is the overall rating of the product.

[0061] After obtaining the first sub-mapping 330 and the second sub-mapping 340, the item list under each region in the first sub-mapping 330 can be associated with the evaluation value 321 of these candidate items 320 in the second sub-mapping 340, using the candidate item identifier as the connection key, to form the target mapping 350. The target mapping 350 is a comprehensive data structure formed by aggregating the first sub-mapping 330 and the second sub-mapping 340. For example, the target mapping 350 can be a mapping table with the candidate region identifier as the key and all deliverable items under the sub-region corresponding to the candidate region identifier and their respective evaluation values ​​as values.

[0062] For example, if the product list under candidate sub-region A is [ID1,ID2], and ID1 = 90 points and ID2 = 85 points in the second sub-mapping 340, then the value of grid A in the target mapping 350 after aggregation is [(ID1,90),(ID2,85)].

[0063] In the embodiments of this disclosure, a first sub-mapping is constructed to precisely associate candidate items with deliverable geographic areas, solving the problem that traditional ranking lists may recommend unreachable items because they cannot match the user's specific location. A second sub-mapping is constructed to evaluate candidate items, providing an objective and consistent quality measurement standard for the ranking list. Based on this, a unified target mapping is generated by aggregating these two sub-mappings based on candidate item identifiers. This target mapping integrates item accessibility information and evaluation values ​​in a spatial dimension, enabling a quick query of the target mapping when responding to user requests to simultaneously obtain a set of candidate items matching the user's location and their pre-calculated evaluation values. This provides a data foundation for subsequent real-time filtering, improving the efficiency and personalization of target ranking list generation.

[0064] The foregoing has described the construction process of a target mapping provided in this disclosure. The following will describe the process using... Figure 4A , Figure 4B and Figure 4C For example, the construction process of the first sub-mapping, the construction process of the second sub-mapping, and the construction process of another target mapping provided in this disclosure are further explained.

[0065] Figure 4A The illustration shows an example schematic diagram of the construction process of a first sub-mapping according to an embodiment of the present disclosure.

[0066] like Figure 4AAs shown, in embodiment 400A of constructing the first sub-mapping, the area corresponding to the subject position of the subject 410 can be divided into multiple candidate sub-regions 401. Based on the subject position and coverage area 402 of the subject 410, at least one target sub-region corresponding to the subject 410 is determined from the multiple candidate sub-regions 401. The candidate item identifier 421 of the candidate item 420 provided by the subject 410 is associated with the candidate region identifier 411 of the target sub-region to obtain the first sub-mapping 430.

[0067] A region refers to a specific geographical area surrounding the location of the subject that needs to be analyzed. For example, a region could be the city, district, county, or fourth-level address where subject 410 is located, or a region defined based on a preset analysis boundary. A candidate sub-region 401 refers to a smaller, standardized geographical unit obtained by dividing the above regions. For example, a candidate sub-region 401 could be a regular hexagonal grid obtained by dividing the fourth-level address according to preset side lengths, with each regular hexagonal grid being a candidate sub-region 401.

[0068] The partitioning method for candidate sub-region 401 can be configured according to actual business needs and is not limited here. For example, a geographic grid model with equal area or shape (such as a square, regular hexagon, etc.) can be used to globally partition the region. The geographic grid model is used to continuously divide the region according to certain latitude and longitude or ground distance based on unified rules, and to control spatial uncertainty within a certain range, forming regular polygons, and each polygon is called a grid unit, thereby forming a hierarchical and multi-level grid system, realizing ground spatial discretization, and assigning a unified code.

[0069] Alternatively, different resolution grids can be used to divide the area based on regional characteristics. For example, a high-resolution grid with a side length of 100 meters can be used in densely populated commercial areas, while a low-resolution grid with a side length of 500 meters can be used in suburban areas to accommodate different densities of commercial distribution and query accuracy requirements.

[0070] For each subject 410, at least one target sub-region corresponding to the subject 410 can be determined from multiple candidate sub-regions 401 based on the subject's location and coverage area 402. For example, if a milk tea shop is located at point P and its delivery range is a circle with P as the center and radius R, the intersection relationship between this circle and all candidate sub-regions 401 can be determined. All candidate sub-regions 401 that intersect with this circle are then selected, and these candidate sub-regions 401 are the target sub-regions of the shop.

[0071] The target sub-region refers to those sub-regions that are contained within or intersect with the coverage area 402 of the subject 410 among all candidate sub-regions 401. That is, when an object is located within these candidate sub-regions 401, it can order the candidate item 420 provided by the subject. For example, if the subject 410 is a pizza shop and the coverage area 402 is 3 kilometers, and it covers candidate sub-regions 401A, 401B, 401C, and 401D, then these four candidate sub-regions 401 are the target sub-regions.

[0072] The method for determining the target sub-region can be configured according to actual business needs and is not limited here. For example, the coverage area 402 of the main body 410 can be geometrically intersected with each candidate sub-region 401 to determine whether there is an overlapping area, thereby determining the target sub-region. Alternatively, the distance from the main body location to the geometric center point of each candidate sub-region 401 can be calculated. If this distance is less than the coverage area 402 of the main body 410, then the candidate sub-region 401 is considered the target sub-region.

[0073] After obtaining at least one target sub-region corresponding to the subject 410, the target sub-region can be associated with all candidate items 420 provided by the subject 410. For example, the milk tea shop mentioned above has products "milk tea A" and "milk tea B", the candidate item identifier 421 of milk tea A is 001, the candidate item identifier 421 of milk tea B is 002, and its target sub-regions are M1, M2, and M3. Then, for the target sub-region M1, its corresponding candidate item identifier 421 is [001, 002].

[0074] In the embodiments of this disclosure, by dividing the area corresponding to the subject's location into multiple candidate sub-regions, continuous geographic space is standardized into discrete, coded query units. Based on this, by determining the target sub-region among these candidate sub-regions according to the subject's location and coverage area, the projection of the effective service space boundary of each subject onto the standardized grid is accurately characterized. A first sub-mapping is constructed by associating candidate item identifiers with candidate region identifiers of the target sub-region. This first sub-mapping is essentially a catalog of deliverable goods indexed by spatial regions, thereby transforming the delivery capacity assessment problem into a data query problem based on the first sub-mapping, improving the efficiency and accuracy of list generation.

[0075] Figure 4B The illustration shows an example schematic diagram of the construction process of a second sub-mapping according to an embodiment of the present disclosure.

[0076] like Figure 4BAs shown, in embodiment 400B of constructing the second sub-mapping, candidate item 420 can be evaluated according to evaluation strategy 404 for each candidate list type 403 to obtain evaluation value 422 of candidate item 420 relative to candidate list type 403. Based on this, the candidate item identifier of candidate item 420, candidate list type 403, and evaluation value 422 of candidate item 420 relative to candidate list type 403 can be associated to obtain the second sub-mapping 440.

[0077] Candidate list type 403 refers to a pre-defined list category with different ranking objectives and business focuses. For example, candidate list type 403 may include a best-selling list focusing on sales volume, a positive review list focusing on user evaluation, a repeat purchase list focusing on user loyalty, and a discount list focusing on promotional efforts.

[0078] Evaluation strategy 404 refers to the pre-configured filtering and calculation rules for generating a list of a specific candidate list type 403. Evaluation strategy 404 can define the basic evaluation items for candidate list type 403, the filtering thresholds for each basic evaluation item, and the weights. It should be noted that for different candidate list types 403, the basic evaluation items, the filtering thresholds for each basic evaluation item, and the weights can be the same or different, and this is not limited here.

[0079] Basic evaluation items refer to specific quantitative indicators used to measure the performance of candidate items 420, representing the content that needs to be evaluated for this candidate list type 403. For example, basic evaluation items may include sales volume in the past 30 days, number of positive reviews in the past 30 days, number of repeat purchases in the past 30 days, historical average product rating, store rating, etc.

[0080] The screening threshold refers to the minimum threshold value set for each basic evaluation item. It represents the screening method for each basic evaluation item in this candidate list type 403. That is, only candidate items 420 that meet or exceed all threshold requirements will enter the subsequent evaluation and scoring stage. For example, the screening threshold may include setting sales control thresholds, positive review control thresholds, repeat purchase control thresholds, etc. For example, the screening thresholds may be "sales ≥ 50 orders in the past 7 days" or "positive review rate ≥ 90%".

[0081] Weighting refers to the coefficients assigned to each basic evaluation item when calculating the overall evaluation value 422, used to reflect the degree of importance that different list types place on each evaluation item. For example, for the "best-selling list," the sales volume weight is set to 0.7, and the number of positive reviews weight is set to 0.3; for the "positive review list," the sales volume weight might be 0.3, and the number of positive reviews weight might be 0.7, etc.

[0082] In addition to defining the basic evaluation items, screening thresholds, and weights for each basic evaluation item, evaluation strategy 404 can also configure the scope of the ranking for this candidate ranking type 403. For example, the ranking scope can include city range, category range, city blacklist, and category blacklist. Cities belonging to the city blacklist and categories belonging to the category blacklist can be filtered.

[0083] For each candidate item 420, based on the evaluation strategy 404 corresponding to the candidate list type 403, the unqualified candidate items 420 can be filtered out first using the screening threshold. Then, the basic evaluation items of the qualified candidate items 420 are calculated according to their weights to obtain the evaluation value 422 of each candidate item 420 for the candidate list type 403.

[0084] After obtaining the evaluation value 422 of candidate item 420 relative to candidate list type 403, the evaluation value 422 can be structured. For example, if the candidate item identifier of candidate item 420 is G001, and its evaluation value 422 in the "best-selling list" is 85 points and its evaluation value 422 in the "positive review list" is 92 points, then the second sub-mapping 440 can be obtained with G001 as the key and (best-selling list, 85) and (positive review list, 92) as the values.

[0085] In the embodiments of this disclosure, candidate items are evaluated according to the evaluation strategy used for each candidate list type. Since specific basic evaluation items, screening thresholds, and weights are defined for each candidate list type, professional and differentiated evaluation is achieved. Based on this, a second sub-mapping is obtained by associating candidate item identifiers, candidate list types, and evaluation values. This efficiently organizes the professional evaluation results, so that when personalized lists need to be generated in real time, there is no need for complex indicator statistics and weighted calculations again. Instead, the pre-calculated evaluation values ​​of relevant items can be retrieved from this second sub-mapping based on the list type requested by the user. This reduces the computational overhead and latency of real-time sorting and improves the efficiency of list push.

[0086] Figure 4C The illustration shows an example schematic diagram of the process for constructing a target map according to another embodiment of the present disclosure.

[0087] like Figure 4CAs shown, in embodiment 400C of constructing the target mapping, the candidate item identifiers in the first sub-mapping 430 and the second sub-mapping 440 can be used as guides to associate the candidate item identifiers, candidate region identifiers, item categories, candidate list types, and evaluation values ​​to obtain association information 450. Based on this, for each piece of association information 450, a target mapping 460 is constructed using the candidate region identifier as the key and the candidate item information 461 obtained based on the candidate item identifier, item category, candidate list type, and evaluation value as the value.

[0088] The correspondence in the first sub-mapping 430 can also include item categories. Item categories refer to the classification of candidate items according to their attributes, functions, or business logic. For example, in the food delivery scenario, item categories could be milk tea and juice, hamburgers and pizzas, Sichuan and Hunan cuisine, convenience stores, etc.

[0089] Linked information 450 refers to a complete data record that logically links various information about the candidate item obtained from different first sub-mappings 430 and 440 through the candidate item identifier as a bridge. The specific linking method can be configured according to actual business needs and is not limited here. For example, records containing the candidate item identifier can be retrieved from the first sub-mapping 430 to obtain a list of candidate area identifiers for which the candidate item can be delivered and its item category; at the same time, the evaluation value of the candidate item identifier under different candidate list types can be retrieved from the first sub-mapping 440; and then this information is summarized and linked according to the candidate item identifier.

[0090] In a key-value pair data model, the key is a unique identifier used for quick retrieval and location, and the value is the data content associated with the key. Candidate item information 461 refers to the set of information needed to describe a candidate item within a specific candidate list type and candidate sub-region. For example, candidate item information 461 may include the candidate item identifier, item category, candidate list type, and its evaluation value.

[0091] For example, taking the associated information 450 as {Product ID: "P_888", Grid ID: "G_1001", Item Category: "Chinese Fast Food", Candidate List Type: "Hot Selling List", Evaluation Value: "92.5"}, we can use Grid ID: "G_1001" as the key and integrate Product ID: "P_888", Item Category: "Chinese Fast Food", Candidate List Type: "Hot Selling List", and Evaluation Value: "92.5" into candidate item information 461 as the value, thereby obtaining target mapping 460.

[0092] In the embodiments of this disclosure, multi-dimensional information is associated with candidate item identifiers as a guide, and scattered information is accurately aligned and integrated through candidate item identifiers. Based on this, the target mapping is reconstructed using candidate region identifiers from the obtained associated information as keys, transforming the item-centric associated information into a geographic region-centric target mapping. Thus, during the real-time query phase of list generation, when a request arrives, only the user's location needs to be converted into a region identifier. By querying the key-value pairs of the target mapping, a structured candidate item information containing categories and multi-dimensional scores can be obtained in one go, improving response speed and list generation efficiency.

[0093] The construction process of the target mapping provided in this disclosure has been described above. The following will use... Figure 5A As an example, the update process of a target mapping provided in this disclosure is further illustrated.

[0094] Figure 5A The illustration shows an example schematic diagram of an update process for a target mapping according to an embodiment of the present disclosure.

[0095] like Figure 5A As shown, in embodiment 500A of updating the target mapping, in response to detecting a change in at least one of the candidate item 520, the subject location 511, and the coverage area 512 provided by the subject 510, at least one changed sub-region corresponding to the subject is re-determined among multiple candidate sub-regions based on the changed information. On this basis, the target mapping can be updated according to the candidate region identifier of the changed sub-region, resulting in an updated target mapping 550.

[0096] Specifically, the first sub-mapping can be updated based on the candidate region identifier of the changed sub-region to obtain the updated first sub-mapping 530, and the target mapping can be updated based on the updated first sub-mapping 530 to obtain the updated target mapping 550.

[0097] A modified sub-region refers to a sub-region that is recalculated based on new information and matches the new service capabilities of the subject 510 after changes have been made to the candidate item 520, subject location 511, or coverage area 512 provided by the subject 510. Modified sub-regions can include newly added, reduced, and unchanged sub-regions.

[0098] Changes to candidate items 520 provided by entity 510 refer to the listing or removal of candidate items 520. For example, if a store lists a new candidate item 5201, and the store originally covered sub-area A and sub-area B, then candidate item 5201 can correspond to sub-area A and sub-area B.

[0099] A change in the main location 511 refers to a relocation of the main entity 510 or a reduction or expansion of the store size. For example, after a store moves from location A to location B, it adds coverage to sub-regions C and D, but no longer covers the original sub-regions A and B.

[0100] Changes to coverage area 512 refer to reductions or enhancements in the delivery capacity of entity 510. For example, after expanding its delivery range, a store may newly cover sub-area A and sub-area B; after shrinking its delivery range, it may no longer cover sub-area C.

[0101] An update process can be triggered when at least one of the candidate item 520, the subject location 511, and the coverage area 512 provided by the subject 510 is detected to have changed. That is, using the new candidate item 520 provided, the new subject location 511, and / or the new coverage area 512, the spatial relationship with all candidate sub-regions is recalculated to obtain new changed sub-regions affected by the subject.

[0102] The method for determining the changed sub-region can be configured according to actual business needs and is not limited here. For example, one can listen for merchant information change events. Once triggered, the new item offering information of the subject 510, the subject location 511, or the coverage area 512 is read, and a full spatial intersection calculation is performed with each candidate sub-region to obtain the new changed sub-region. Alternatively, the type of change can be analyzed. If it is a location move, two circular buffers can be generated with the old and new locations as centers and the coverage radius as the radius. The symmetrical difference between these two buffers is calculated. The sub-region covered by this difference is the area that needs to be recalculated in detail. Precise spatial judgment can be performed only within this area to determine the changed sub-region.

[0103] After obtaining the changed sub-region, the corresponding entries in the target mapping can be modified to obtain the updated target mapping 550. The updated target mapping 550 is a data mapping that reflects the latest service capability status, obtained by adding, deleting, or modifying the affected key-value pairs in the target mapping based on the subject's change information.

[0104] For example, for a newly added candidate region identifier, all product information provided by the subject 510 can be added to the information corresponding to the candidate region identifier in the target mapping; for a removed candidate region identifier, all product information belonging to the subject 510 can be deleted from the information corresponding to the candidate region identifier in the target mapping.

[0105] In the embodiments of this disclosure, by responding to the detection of changes in candidate items, subject location, or coverage area provided by the subject and redetermining the changed sub-region, the synchronization and consistency between the correspondence between candidate items, subjects, and sub-regions and the actual state are ensured, thereby guaranteeing real-time performance. Furthermore, by adaptively updating the target mapping based on the candidate sub-region identifier of the changed sub-region, the timeliness and accuracy of product accessibility information are ensured, thereby improving the accuracy of ranking pushes.

[0106] The following will be based on Figure 5B As an example, another target mapping update process provided in this disclosure is further illustrated.

[0107] Figure 5B The illustration shows an example schematic diagram of an update process for a target mapping according to another embodiment of the present disclosure.

[0108] like Figure 5B As shown, in embodiment 500B of updating the target mapping, a real-time distance for the distance evaluation item can be determined based on the target location, the subject location 511, and the coverage area 512. The evaluation value is updated based on the real-time distance and the weights used for the distance evaluation item, resulting in an updated evaluation value 521. Based on this, the target mapping is updated according to the updated evaluation value 521, resulting in an updated target mapping 550.

[0109] The evaluation strategy also defines distance evaluation items for candidate leaderboard types and the weights used for these items. The evaluation value of the distance evaluation item can be calculated based on the real-time spatial distance between the object and the subject, and this distance evaluation item can be used to reflect the consideration that closer proximity may result in a better experience.

[0110] It should be noted that the weight of the distance evaluation item can be the same or different for different candidate list types, and this is not limited here. For example, in the "Nearby Preferred List", the weight of the distance evaluation item can be 0.4; while in the "National Best-Selling List", the weight of the distance evaluation item can be 0.1.

[0111] Real-time distance refers to the spatial distance calculated in real time based on the target location, the subject location 511, and the coverage area 512 at the moment the user request occurs. For example, the real-time distance can be determined by calculating the straight-line distance or the actual road distance between two points. Alternatively, since both the object and subject locations 511 can be mapped to candidate region identifiers, the distance between the center points of the respective candidate regions of the two candidate region identifiers, or the number of hops between the respective candidate regions of the two candidate region identifiers, can be used as an approximation of the real-time distance.

[0112] After obtaining the real-time distance, the evaluation value can be updated based on the real-time distance and the weights used for distance evaluation, resulting in an updated evaluation value of 521. This updated evaluation value of 521 refers to the comprehensive score recalculated after incorporating the real-time distance factor. After obtaining the updated evaluation value of 521, the target mapping can be updated based on the updated evaluation value of 521, resulting in an updated target mapping of 550.

[0113] It should be noted that since the real-time distance varies for different objects, the updated target mapping 550 can be stored only in the context of this user session or in a temporary small-capacity cache, so as to be used exclusively for the generation of this leaderboard, while keeping the global target mapping unchanged.

[0114] In the embodiments of this disclosure, by determining the real-time distance based on the target location and the subject location, the real-time, dynamic spatial relationship between the object and the subject is captured. By updating the original evaluation value based on the real-time distance and weight, the final evaluation value of the same candidate differs for objects at different locations. Furthermore, by updating the target mapping based on the updated evaluation value, the ranking list generation, in addition to considering overall quality and delivery accessibility, further leans towards the real-time geographical location of the object, thereby more accurately guiding the object to make a quick order decision and improving the targeting and accuracy of the ranking list generation.

[0115] The following will be based on Figure 6 As an example, the process of obtaining the target list provided in this disclosure will be further explained.

[0116] Figure 6 The illustration shows an example schematic diagram of the process for obtaining a target list according to an embodiment of the present disclosure.

[0117] like Figure 6 As shown, in embodiment 600 for obtaining the target list, the object sub-region corresponding to the object 610 can be determined from multiple candidate sub-regions 601 based on the target location 611 of the object 610. Based on the region identifier 612 of the object sub-region, the candidate region identifiers 612 in the target mapping 620 are matched, and the obtained candidate item information 621 is used as the candidate item set 630.

[0118] In response to receiving a push request, the object sub-region to which the target location 611 of object 610 belongs can be calculated using the same spatial partitioning method as when constructing candidate sub-region 601. The object sub-region is the candidate sub-region 601 to which the user's target location 611 falls. The region identifier 612 is a string used to uniquely identify the object sub-region.

[0119] After obtaining the region identifier 612 of the object sub-region, the region identifier 612 can be used as the query key to perform an exact match in 620, resulting in a candidate item set 630. The candidate item set 630 refers to the list of all deliverable item information located within the object sub-region, obtained through matching and querying 620. For example, the candidate item set 630 can be [{candidate item information A}, {candidate item information B}, ...].

[0120] In the embodiments of this disclosure, by determining the object sub-region based on the target location, the specific geographic coordinates of the object are mapped to a standard query unit. By matching the target mapping based on the regional identifier of the object sub-region and obtaining a set of candidate items, the advantages of the pre-built data structure indexed by the candidate regional identifier are fully utilized. The deliverability query process, which originally required complex spatial calculations in real time, is optimized into a fast key-value pair retrieval, thereby solving the problem that items in the list may not be deliverable in related technologies and improving the efficiency and relevance of list generation.

[0121] After obtaining the candidate item set 640, the recommended item set 640 can be obtained based on the type information 613 indicated by the push request. The recommended item set 630 is matched with the candidate item set 640 to obtain the target list 650.

[0122] Type information 613 may include item category and target list type. Recommended item set 640 refers to a list of item identifiers initially selected by a recommendation algorithm based on the target location 611 of object 610, the selected item category, and the target list type, which are considered likely to match the interests of object 610. The method of obtaining recommended item set 640 can be configured according to actual business needs and is not limited here.

[0123] For example, based on the long-term historical order, browsing, and favorites behavior of object 610, a user profile can be constructed, or similar user groups can be found through collaborative filtering algorithms. Then, a set of recommended items 640 that similar user groups might like and that match the item category and target list type can be recommended to object 610. Alternatively, the current time period and weather of object 610 can be analyzed, and combined with the selected item category and target list type, a ranking model can be invoked in real time to predict the set of recommended items 640 that object 610 is most likely to click or place an order at that moment.

[0124] The candidate item set 630 refers to a list of product information obtained from 620 based on the target location 611 of object 610, which guarantees delivery at that location and has had its evaluation value calculated for each list type. After obtaining the recommended item set 640, the candidate item identifiers in the recommended item set 640 can be matched with the candidate item identifiers in the candidate item set 630 to form the candidate item set 650 for push notification.

[0125] The specific method for generating the candidate item set 650 can be configured according to actual business needs and is not limited here. For example, the candidate item identifiers of the candidate item set 630 and the recommended item set 640 can be compared, common candidate item identifiers can be retained, and then the candidate item set 650 can be generated by sorting the evaluation values ​​corresponding to the target list type in the candidate item set 630 according to these candidate item identifiers in descending order. Alternatively, the recommended item set 640 can also include the recommendation confidence score of each recommended item. In this case, weights can be assigned to the distribution of recommended items in the recommended item set 640 and candidate items in the candidate item set 630, and the recommendation confidence score and evaluation value can be weighted based on different weights, and the candidate item set 650 can be generated based on the weighted score.

[0126] In the embodiments of this disclosure, by obtaining a set of recommended items based on the target location, item category, and target list type, and matching the set of recommended items with the set of candidate items, it is ensured that the products that are finally listed are both those that users may like and those that can actually be delivered to users, thereby improving the targeting and accuracy of the target list.

[0127] In one embodiment, matching the recommended item set 640 with the candidate item set 630 to obtain the candidate item set 650 includes: taking the intersection of the recommended item set 640 and the candidate item set 630 to obtain a first intermediate item set, wherein the first intermediate item set includes multiple candidate item information 621, and the candidate item information 621 includes item category, candidate list type and evaluation value; filtering the intermediate item set according to the item category and target list type to obtain a second intermediate item set; and sorting the candidate items according to the evaluation value of each candidate item in the second intermediate item set to obtain the candidate item set 650.

[0128] After obtaining the recommended item set 640 and the candidate item set 630, the two sets can be compared to find items that exist in both sets simultaneously. Their candidate item information 621 in the candidate item set 630 is then extracted to form a first intermediate item set. This first intermediate item set is the set of item information obtained by taking the intersection of the recommended item set 640 and the candidate item set 630. In other words, the items in this first intermediate item set are both considered by the recommendation system to be potentially suitable for the user's interests and can be delivered to the user's current location.

[0129] The method for obtaining the first intermediate item set can be configured according to actual business needs and is not limited here. For example, each candidate item identifier in the recommended item set 640 can be traversed, and a search can be performed in the candidate item set 630. If found, the information corresponding to the candidate item identifier can be added to the first intermediate item set. Alternatively, all candidate item identifiers in the recommended item set 640 can be loaded into a hash set, and then the candidate item set 630 can be traversed to check whether each candidate item identifier exists in the hash set. If it exists, it can be added to the first intermediate item set.

[0130] For example, the recommended item set 640 contains product IDs: [A, B, C], and the candidate item set 630 contains product information: [A, C, D]. The intersection is A and C, and the first intermediate item set can be [A, C].

[0131] After obtaining the first intermediate item set, each candidate item information 621 in the first intermediate item set can be iterated through to check whether its item category field matches the item category selected by the user, and whether its candidate list type field matches the target list type selected by the user. Candidate item information 621 that meets both conditions can be retained. The second intermediate item set is the set of item information obtained by further filtering from the first intermediate item set to find items whose item category matches the selection of object 610 and whose candidate list type matches the target list type selected by the user.

[0132] After obtaining the second intermediate item set, all candidate items in the second intermediate item set can be sorted according to the evaluation value corresponding to the target list type in their candidate item information 621, and the top N ranked items can be selected as needed to form the final "candidate item set 650". For example, if the second intermediate item set has 3 candidate items with evaluation values ​​of 95, 88 and 90 respectively, and they are sorted in descending order as [95, 90, 88], then the top 2 can be selected to generate the candidate item set 650 containing candidate items with evaluation values ​​of 95 and 90.

[0133] In the embodiments of this disclosure, a first intermediate item set is obtained by taking the intersection of the recommended item set and the candidate item set, and a second intermediate item set is obtained by filtering according to the item category and the target list type. Finally, the target list is obtained by sorting according to the evaluation value. This solves the pain point that the list generation method in related technologies may lead users to select products that cannot be delivered, improves the targeting and accuracy of the list, and effectively improves the user's selection efficiency, order conversion rate and overall consumption experience.

[0134] The above are merely exemplary embodiments, but are not limited to them. Other information push methods known in the art may also be included, as long as they can improve the flexibility and accuracy of the ranking push.

[0135] Figure 7 A block diagram of an information push device according to an embodiment of the present disclosure is shown schematically.

[0136] like Figure 7 As shown, the information push device 700 may include an acquisition module 710 and a push module 720.

[0137] The acquisition module 710 is used to respond to receiving a push request from an object and, according to the target location indicated by the push request, acquire a set of candidate items from the target map. The target map includes the correspondence between candidate area identifiers and candidate item information, and the correspondence is determined based on the location and coverage of the subject that provides the candidate items.

[0138] The push module 720 is used to filter the candidate item set according to the type information indicated by the push request, so as to push the obtained target list to the target.

[0139] Any one or more of the modules according to embodiments of this disclosure, or at least part of the functionality of any one or more of them, can be implemented in one module. Any one or more of the modules according to embodiments of this disclosure can be implemented by dividing them into multiple modules. Any one or more of the modules according to embodiments of this disclosure can be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or implemented in hardware or firmware by any other reasonable means of integrating or packaging circuitry, or implemented in software, hardware, or firmware, or in any suitable combination of any of these three implementation methods. Alternatively, one or more of the modules according to embodiments of this disclosure can be at least partially implemented as computer program modules, which, when run, can perform corresponding functions.

[0140] It should be noted that the information push device part in the embodiments of this disclosure corresponds to the information push method part in the embodiments of this disclosure. The description of the information push device part is specifically referred to in the information push method part, and will not be repeated here.

[0141] Figure 8 A block diagram of an electronic device suitable for implementing an information push method according to an embodiment of the present disclosure is shown schematically. Figure 8 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0142] like Figure 8 As shown, a computer electronic device 800 according to an embodiment of the present disclosure includes a processor 801, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 802 or a program loaded from a storage portion 809 into a random access memory (RAM) 803. The processor 801 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 801 may also include onboard memory for caching purposes. The processor 801 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0143] RAM 803 stores various programs and data required for the operation of electronic device 800. Processor 801, ROM 802, and RAM 803 are interconnected via bus 804.

[0144] According to embodiments of this disclosure, the electronic device 800 may further include an input / output (I / O) interface 805, which is also connected to a bus 804. The electronic device 800 may also include one or more of the following components connected to the input / output (I / O) interface 805: an input section 806 including a keyboard, mouse, etc.; an output section 807 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 808 including a hard disk, etc.; and a communication section 809 including a network interface card such as a LAN card, modem, etc. The communication section 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to the input / output (I / O) interface 805 as needed. A removable medium 811, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 810 as needed so that computer programs read from it can be installed into the storage section 808 as needed.

[0145] This disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs, which, when executed, implement the information push method according to the embodiments of this disclosure.

[0146] In this disclosure, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0147] Embodiments of this disclosure also include a computer program product comprising a computer program containing program code for performing the methods provided in the embodiments of this disclosure. When the computer program product is run on an electronic device, the program code is used to enable the electronic device to implement the information push method provided in the embodiments of this disclosure.

[0148] When the computer program is executed by the processor 801, it performs the functions defined in the system / apparatus of this disclosure embodiments. According to embodiments of this disclosure, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0149] According to embodiments of this disclosure, program code for executing computer programs provided in embodiments of this disclosure can be written in any combination of one or more programming languages.

[0150] 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. It should also be noted that in some alternative implementations, the functions indicated in the boxes may occur in a different order than those shown in the drawings.

[0151] The embodiments of this disclosure have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of this disclosure. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. The scope of this disclosure is defined by the appended claims and their equivalents. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of this disclosure, and all such substitutions and modifications should fall within the scope of this disclosure.

Claims

1. An information push method, comprising: In response to receiving a push request from an object, a set of candidate items is obtained from a target map based on the target location indicated by the push request. The target map includes a correspondence between candidate region identifiers and candidate item information, determined based on the location and coverage area of ​​the entity providing the candidate items. Based on the type information indicated by the push request, the candidate item set is filtered to push the resulting target list to the target.

2. The method according to claim 1, wherein, The target mapping is obtained in the following way: Based on the main body's location and coverage area, and the candidate items provided by the main body, a first sub-mapping is constructed, wherein the first sub-mapping includes the correspondence between candidate area identifiers and candidate item identifiers; Based on the evaluation values ​​obtained by evaluating the candidate items, a second sub-mapping is constructed, wherein the second sub-mapping includes the correspondence between candidate item identifiers and the evaluation values; and Based on the candidate item identifier, the first sub-mapping and the second sub-mapping are aggregated to obtain the target mapping.

3. The method according to claim 2, wherein, The step of constructing a first sub-mapping based on the subject's location and coverage area, and the candidate items provided by the subject, includes: The region corresponding to the main body location is divided into multiple candidate sub-regions; Based on the subject's location and coverage area, at least one target sub-region corresponding to the subject is determined from among the multiple candidate sub-regions; and The candidate item identifier of the candidate item is associated with the candidate region identifier of the target sub-region to obtain the first sub-mapping.

4. The method according to claim 2, wherein, The step of constructing a second sub-mapping based on the evaluation values ​​obtained by evaluating the candidate items includes: The candidate items are evaluated according to the evaluation strategy used for each candidate list type to obtain an evaluation value for each candidate item relative to the candidate list type. The evaluation strategy defines basic evaluation items for each candidate list type, screening thresholds for each basic evaluation item, and weights. The candidate item identifier, the candidate list type, and the evaluation value of the candidate item relative to the candidate list type are associated to obtain the second sub-mapping.

5. The method according to claim 2, wherein, The mapping in the first sub-mapping also includes item categories; The step of aggregating the first sub-mapping and the second sub-mapping based on the candidate item identifier to obtain the target mapping includes: Using the candidate item identifier as a guide, the candidate item identifier, the candidate region identifier, the item category, the candidate list type, and the evaluation value are associated to obtain association information; and For each piece of associated information, the target mapping is constructed using the candidate region identifier as the key and the candidate item information obtained based on the candidate item identifier, the item category, the candidate list type, and the evaluation value as the value.

6. The method according to claim 3, further comprising: In response to detecting a change in at least one of the candidate items provided by the subject, the subject's location, and the coverage area, based on the changed information, at least one changed sub-region corresponding to the subject is re-determined among the plurality of candidate sub-regions; as well as The target mapping is updated based on the candidate region identifier of the changed sub-region to obtain the updated target mapping.

7. The method according to claim 4, wherein, The evaluation strategy also defines a distance evaluation item for the candidate list type and a weight for the distance evaluation item; The method further includes, after the response to receiving a push request from the object: Based on the target location, the subject location, and the coverage area, determine the real-time distance used for the distance evaluation item; The evaluation value is updated based on the real-time distance and the weights used for the distance evaluation item to obtain the updated evaluation value; as well as The target mapping is updated based on the updated evaluation value to obtain the updated target mapping.

8. The method according to any one of claims 1 to 7, wherein, The step of obtaining a set of candidate items from the target map based on the target location indicated by the push request includes: Based on the target location, determine the object sub-region corresponding to the object from multiple candidate sub-regions; and Based on the region identifier of the object sub-region, the candidate region identifiers in the target mapping are matched, and the resulting candidate item information is used as the candidate item set.

9. The method according to any one of claims 1 to 7, wherein, The type information includes item category and target list type; The step of filtering the candidate item set based on the type information indicated by the push request includes: Based on the target location, the item category, and the target ranking list type, obtain a set of recommended items; as well as The recommended item set is matched with the candidate item set to obtain the target list.

10. The method according to claim 9, wherein, The step of matching the recommended item set with the candidate item set to obtain the target list includes: The intersection of the recommended item set and the candidate item set is used to obtain a first intermediate item set, wherein the first intermediate item set includes multiple candidate item information, and the candidate item information includes the item category, the candidate list type and the evaluation value; The intermediate item set is filtered according to the item category and the target list type to obtain a second intermediate item set; and The candidate items are sorted according to their evaluation values ​​in the second intermediate item set to obtain the target list.

11. An information push device, comprising: The acquisition module is configured to, in response to receiving a push request from an object, acquire a set of candidate items from a target map based on the target location indicated by the push request, wherein the target map includes a correspondence between candidate region identifiers and candidate item information, the correspondence being determined based on the location and coverage area of ​​the entity providing the candidate items; and The push module is used to filter the candidate item set according to the type information indicated by the push request, so as to push the obtained target list to the object.

12. An electronic device, comprising: One or more processors; Memory, used to store one or more computer programs. The characteristic feature is that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 10.

13. A computer-readable storage medium having a computer program or instructions stored thereon, characterized in that, When the computer program or instructions are executed by a processor, they implement the steps of the method according to any one of claims 1 to 10.

14. A computer program product comprising a computer program or instructions, characterized in that, When the computer program or instructions are executed by a processor, they implement the steps of the method according to any one of claims 1 to 10.

Images