Information recommendation method, device and electronic equipment
By receiving location information in store recommendation requests, obtaining store data and determining store levels based on multiple rating dimensions, the problems of inaccurate store information recommendation and waste of resources in the existing technology are solved, and accurate and comprehensive store information recommendations are achieved and user privacy protection.
Patent Information
- Application Number
- CN202110639366.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-06-08
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2041-06-08
AI Technical Summary
The prior art causes inaccuracy and waste of resources in store information recommendations when user information browsing records are insufficient or incorrect, and increases user search costs.
By receiving location information in store recommendation requests, obtaining store data within the specified range, determining store levels based on multiple rating dimensions, and returning store recommendation information that meets the preset level conditions, avoiding relying on user browsing history.
It improves the accuracy and comprehensiveness of store information recommendations, saves user search costs, and protects user privacy data.
Smart Images

Figure CN113360790B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of information processing technology, and in particular to an information recommendation method, device and electronic device. Background Art
[0002] With the development of Internet technology, the Internet can provide users with more and more network services. For example, users can browse videos, listen to music, read, shop, etc. on the Internet. On the Internet platform, users can search for the information they need through the search function. At the same time, in order to facilitate users to obtain information, the Internet platform can also actively recommend information to users.
[0003] Currently, we can obtain the user's information browsing history, analyze the user's interest, and then recommend store information to the user based on the interest.
[0004] However, if the user's information browsing record contains less data, no data, or is incorrect, the user's interest level obtained through analysis will be inaccurate or unable to be obtained, which will in turn affect the accuracy of store information recommendations, resulting in the possibility that the recommended information is incorrect. This not only wastes the resources used for information recommendations, but also prevents users from obtaining the store recommendation information they need on the web page in the first place, thereby increasing the cost of finding the required information. Summary of the invention
[0005] In view of this, the present application provides an information recommendation method, device and electronic device, the main purpose of which is to improve the technical problems of the current existing technology that affect the accuracy of store information recommendation, waste resources called for information recommendation, and increase the cost of users searching for the required information.
[0006] According to one aspect of the present application, there is provided an information recommendation method, which can be applied to a server side, and the method includes:
[0007] receiving a store recommendation request, wherein the store recommendation request carries location information;
[0008] Acquire platform data of each target store within a preset range of the location information, wherein the platform data includes: store data, historical order data and corresponding order user data of the target store;
[0009] According to the platform data, determining the store level corresponding to each target store based on multiple rating dimensions;
[0010] Returns the recommended information of target stores whose store levels meet the preset level conditions.
[0011] Optionally, determining store grades corresponding to the target stores based on the platform data and multiple rating dimensions specifically includes:
[0012] According to the platform data, the number of dimensions in which the target store's ratings meet the standards in multiple rating dimensions is obtained;
[0013] The store grade corresponding to the target store is determined based on the number of dimensions that meet the rating standards.
[0014] Optionally, obtaining the number of dimensions in which the target store's ratings meet the standards in multiple rating dimensions according to the platform data specifically includes:
[0015] Calculate the scores of the target store in multiple rating dimensions according to the platform data;
[0016] For each rating dimension, determine whether the score corresponding to the target store is greater than or equal to the threshold corresponding to the rating dimension. If so, determine that the target store has met the rating standard in the rating dimension;
[0017] Count the number of dimensions for which the target store ratings meet the standards.
[0018] Optionally, before determining, for each rating dimension, whether the score corresponding to the target store is greater than or equal to a threshold corresponding to the rating dimension, the method further includes:
[0019] According to the number of store recommendations within a preset range of the location information, the distribution of grade levels, and the priorities among the multiple rating dimensions, the thresholds corresponding to the multiple rating dimensions are determined as a whole.
[0020] Optionally, the step of determining the thresholds corresponding to the multiple rating dimensions as a whole based on the number of recommended stores within a preset range of the location information, the distribution of grade levels, and the priorities among the multiple rating dimensions specifically includes:
[0021] In descending order of priority among the multiple rating dimensions, a Z-shaped search is performed according to the store scores of each store within the preset range of the location information, and the search is stopped when the number of stores searched meets a stop condition, wherein the stop condition is determined according to the number of recommended stores and the distribution of grade levels;
[0022] The threshold values corresponding to each of the multiple rating dimensions are determined with reference to the store ratings that were last searched for each of the multiple rating dimensions after the search is stopped.
[0023] Optionally, calculating the scores of the target store in multiple rating dimensions respectively according to the platform data specifically includes:
[0024] If the rating dimension is the first dimension of local specific user behavior, then the score corresponding to the target store in the first dimension is determined according to the number of consumers of the local specific users of the target store within the preset time period;
[0025] If the rating dimension is the second dimension of non-local user behavior, then for non-local users whose maximum interval of days with order records is less than or equal to the preset day threshold, the score corresponding to the target store in the second dimension is determined based on the product of the non-local user's average consumption and the number of orders of the target store;
[0026] If the rating dimension is the third dimension of local user behavior, the score of the target store corresponding to the third dimension is determined based on the ratio of the number of local users who shop at stores outside the specific range more than a preset number threshold to the total number of local users who shop at the target store;
[0027] If the rating dimension is the fourth dimension of all user behaviors, the score of the target store corresponding to the fourth dimension is determined based on the product of all orders of the target store and the average consumption per person;
[0028] If the rating dimension is the fifth dimension of store reviews, the score of the target store corresponding to the fifth dimension is determined based on the user review score of the target store.
[0029] Optionally, the returning of recommendation information of target stores whose store grades meet preset grade conditions specifically includes:
[0030] Obtain target stores whose store levels are greater than the preset level threshold, and filter them according to the number of stores that need to be recommended at each level;
[0031] Returns the recommended information of the filtered target store.
[0032] According to another aspect of the present application, there is provided an information recommendation method, which can be applied to a client side, and the method includes:
[0033] Sending a store recommendation request, wherein the store recommendation request carries location information, so that according to the platform data of each target store within a preset range of the location information, the store level corresponding to each target store is determined based on multiple rating dimensions, wherein the platform data includes: store data of the target store, historical order data, and corresponding order user data;
[0034] Receive recommendation information of target stores whose store grades meet preset grade conditions.
[0035] Optionally, after receiving the recommendation information of the target store whose store grade meets the preset grade condition, the method further includes:
[0036] Output the received target store recommendation information and the store level tags corresponding to each target store.
[0037] According to another aspect of the present application, there is provided an information recommendation device, which can be applied to a server side, and the device includes:
[0038] A receiving module, configured to receive a store recommendation request, wherein the store recommendation request carries location information;
[0039] An acquisition module, used to acquire platform data of each target store within a preset range of the location information, wherein the platform data includes: store data, historical order data and corresponding order user data of the target store;
[0040] A determination module, configured to determine store grades corresponding to the target stores based on the platform data and multiple rating dimensions;
[0041] The sending module is used to return the recommendation information of the target stores whose store levels meet the preset level conditions.
[0042] According to another aspect of the present application, there is provided an information recommendation device, which can be applied to a client side, and the device includes:
[0043] A sending module, configured to send a store recommendation request, wherein the store recommendation request carries location information, so that store grades corresponding to the target stores are determined based on multiple rating dimensions according to platform data of each target store within a preset range of the location information, wherein the platform data includes: store data of the target store, historical order data, and corresponding order user data;
[0044] The receiving module is used to receive recommendation information of target stores whose store grades meet preset grade conditions.
[0045] According to another aspect of the present application, a storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned information recommendation method is implemented.
[0046] According to another aspect of the present application, an electronic device is provided, which may include: a server device or a client device, specifically including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor implements the above-mentioned information recommendation method when executing the computer program.
[0047] By means of the above technical solution, the present application provides an information recommendation method, device and electronic device. Compared with the current traditional method, the present application does not need to rely on the user's information browsing history to recommend store information. The reference data used in the present application is the platform data of each target store within the specified location range, specifically including the store data, historical order data and corresponding order user data of the target store. And according to the reference data, the store level corresponding to each target store is determined based on multiple rating dimensions, and then from different rating dimensions, the target store information whose store level meets the preset level conditions is recommended to the user. On the one hand, the accuracy and comprehensiveness of the store information recommendation can be achieved, saving the cost of users searching for the required information; on the other hand, it can reduce the infringement of the user's privacy data and protect the user's privacy.
[0048] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS
[0049] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:
[0050] Figure 1 A schematic diagram of a process of an information recommendation method provided in an embodiment of the present application is shown;
[0051] Figure 2 A schematic diagram of a store rating algorithm model provided in an embodiment of the present application is shown;
[0052] Figure 3 A schematic diagram showing a flow chart of another information recommendation method provided in an embodiment of the present application is shown;
[0053] Figure 4 A schematic diagram showing an example effect of information recommendation display provided by an embodiment of the present application is shown;
[0054] Figure 5 A schematic diagram of the structure of an information recommendation device provided in an embodiment of the present application is shown;
[0055] Figure 6 A schematic diagram of the structure of another information recommendation device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION
[0056] The present application will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.
[0057] In order to improve the technical problems that the existing technology affects the accuracy of store information recommendation, wastes the resources used for information recommendation, and increases the cost of users searching for required information. This embodiment provides an information recommendation method, such as Figure 1 As shown, it can be applied to the server side, and the method includes:
[0058] Step 101: The server receives a store recommendation request sent by the client.
[0059] The store recommendation request carries location information, which may be the location information of the specified store to be searched, which may be set by the system default, or manually selected by the user, or determined by the client according to the current location information of the terminal, etc. The client may be configured on the user's smart phone, tablet computer, smart watch, smart bracelet or other smart terminal side.
[0060] Step 102: The server obtains platform data of each target store within a preset range of location information in the store recommendation request.
[0061] The preset range may be set by system default or manually selected by the user, etc. For example, the platform data of each target store within the city, district / county, 2 kilometers, or 500 meters of the designated location may be searched and obtained.
[0062] The platform data of the target store may specifically include: store data of the target store (such as store name, location, store type, specifications, etc.), historical order data (such as historical order information of the target store, which may include order content and order time, etc.) and corresponding order user data (such as the user ID, permanent residence, other store orders of the user who consumes the order, etc., where the permanent residence can be inferred by calculating the time of each order and the location of the order store for the user over a period of time).
[0063] Step 103: The server determines the store level corresponding to each target store based on multiple rating dimensions according to the acquired platform data of each target store.
[0064] The rating dimension can be determined according to actual needs. In this embodiment, multiple rating dimensions can be considered, and the store data, historical order data, and order user data of these target stores can be used as references to comprehensively analyze the store grades of these target stores. Different store grades can represent different store quality standards.
[0065] Step 104: The server returns to the client the recommendation information of the target store whose store grade meets the preset grade condition.
[0066] The preset grade conditions can be set in advance according to actual needs, such as by system default settings or client user personalized settings (which can then achieve accurate store recommendations that meet the user's personalized needs), etc. The preset grade conditions can be used for target stores whose store quality meets the requirements for recommendation to users.
[0067] The store recommendation information returned by the server may include the name, location, store features, store rating standards, etc. of the recommended store. The client outputs according to the returned store recommendation information.
[0068] Compared with the current traditional methods, the information recommendation method provided in this embodiment does not need to rely on the user's information browsing history to recommend store information. The reference data used in this embodiment is the platform data of each target store within the specified location range, specifically including the store data, historical order data and corresponding order user data of the target store. And according to the reference data, the store level corresponding to each target store is determined based on multiple rating dimensions, and then from different rating dimensions, the target store information whose store level meets the preset level conditions is recommended to the user. On the one hand, the accuracy and comprehensiveness of store information recommendations can be achieved, saving the cost of users searching for the required information; on the other hand, it can reduce the infringement of users' privacy data and protect the privacy of users.
[0069] Further, as a refinement and extension of the specific implementation methods of the above-mentioned embodiment, optionally, step 103 may specifically include: the server first obtains the number of dimensions of the target store that meet the rating standards in multiple rating dimensions based on the platform data of each target store obtained; and then determines the store level corresponding to the target store based on the number of dimensions that meet the rating standards.
[0070] For example, each rating dimension has its own corresponding rating standard, where A can represent the "highest level", B can represent "medium", and C can represent "poor".
[0071] One option is that if a store is rated as A-level in a certain rating dimension, then the store can be considered to have met the rating standard in that rating dimension. If there are 6 rating dimensions, and store 1 is rated as A-level in all 6 rating dimensions, then store 1 can be considered as a 6A store, and the store grade of store 1 is determined to be 6A; if store 2 is rated as A-level in 4 of the 6 rating dimensions, then store 2 can be considered as a 4A store, and the store grade of store 2 is determined to be 4A.
[0072] Another option is that if a store is evaluated to have reached the B level or above (including B level) standard in a certain rating dimension, then the store can be considered to have met the rating standard in the rating dimension. Then, based on the number of dimensions that have met the rating standard and the specific rating information of each rating dimension, the store grade corresponding to the target store is comprehensively determined. If there are 6 rating dimensions, and store 3 has 3 A-levels, 2 B-levels, and 1 C-level in these 6 rating dimensions, then store 3 can be considered to be a store with an upper-middle store grade; store 4 has 1 A-level, 2 B-levels, and 2 C-levels in these 6 rating dimensions, then store 4 can be considered to be a store with a lower-middle store grade.
[0073] Further, different rating dimensions have different weights. If the rating dimension weight is larger, it means that the rating dimension is more important and has a greater impact on the store rating. In addition, when determining the store rating, this embodiment can comprehensively determine the store rating corresponding to the target store based on the number of rating dimensions that meet the rating standards, the specific rating information of each rating dimension, and the weight of each rating dimension, so as to obtain a more accurate store rating.
[0074] In order to accurately determine whether the target store meets the rating requirements for the rating dimensions, as another optional method, the above-mentioned server obtains the number of dimensions in which the target store meets the rating requirements in multiple rating dimensions based on the platform data of each target store obtained. Specifically, it may include: first, according to the obtained platform data of the target store, calculate the scores corresponding to the target store in multiple rating dimensions respectively; then, for each rating dimension, determine whether the score corresponding to the target store is greater than or equal to the threshold value corresponding to the rating dimension; if so, determine that the target store meets the rating requirements in the rating dimension; and count the number of dimensions in which the target store meets the rating requirements.
[0075] This embodiment adopts a method of scoring multiple rating dimensions separately to accurately assess the rating standards of each rating dimension, and then accurately find the rating dimensions that meet the rating standards, so that the store grade can be accurately obtained.
[0076] As for the specific scoring method, illustratively, as an optional scoring method, the above-mentioned score corresponding to the target store in multiple rating dimensions is calculated based on the platform data of the target store obtained, which may specifically include: if the rating dimension is the first dimension of local specific user behavior, then the score corresponding to the target store in the first dimension is determined according to the number of consumers of local specific users of the target store within a preset time period.
[0077] In this embodiment, the local user may be a resident user in the same area as the location information in the store recommendation request, and the local specific user may be a local user who has a number of order consumption times higher than the market inflection point value (the overall standard of such local users) in a specific time period (such as weekends and other holidays) at a place greater than a certain distance threshold from the local user's resident location. This type of user group is relatively store-oriented and tends to be higher-quality stores. Therefore, the score corresponding to the target store in this rating dimension can be accurately determined based on the number of consumers of the local specific users of the target store in the preset time period.
[0078] As another optional method of scoring, if the rating dimension is the second dimension of non-local user behavior, then for non-local users whose maximum interval of days with order records is less than or equal to a preset day threshold (pre-set based on actual conditions), the score corresponding to the target store in the second dimension is determined based on the product of the average consumption per non-local user of the target store and the number of orders.
[0079] Non-local users are judged relative to local users, that is, non-resident users. The store behavior of such users can reflect the popularity of the store. Therefore, the score of the target store in this rating dimension can be accurately determined based on the average consumption and number of orders of such users in the store.
[0080] As another optional way of scoring, if the rating dimension is the third dimension of local user behavior, the score corresponding to the target store in the third dimension is determined based on the ratio of the number of local users who have shopped at stores outside a specific range more than a preset threshold number of times to the total number of local users who have shopped at the target store.
[0081] The store behavior of local users can also reflect the quality of the store to a certain extent. Therefore, according to the analysis method of the local user store consumption behavior in this embodiment, the score corresponding to the target store in the rating dimension can be accurately determined.
[0082] As another optional way of scoring, if the rating dimension is the fourth dimension of all user behaviors, the score corresponding to the target store in the fourth dimension is determined based on the product of all orders of the target store and the average consumption per person.
[0083] In addition to analyzing local users, local specific users, and out-of-town users, this embodiment can also make a comprehensive evaluation based on the behaviors of all users. The number of all orders and per capita consumption of a store can accurately determine the advantage of the store in this rating dimension.
[0084] As another optional way of scoring, if the rating dimension is the fifth dimension of store reviews, the score corresponding to the target store in the fifth dimension is determined based on the user review score of the target store.
[0085] The user review score of a store can intuitively indicate the quality of the store. Therefore, this embodiment can accurately determine the score corresponding to the target store in this rating dimension based on the user review score of the target store.
[0086] Since the scoring method of each rating dimension is different, each rating dimension has its own corresponding threshold. The setting of the threshold determines the standard for rating compliance. Therefore, in order to accurately determine whether the store has met the rating standard in the rating dimension, it is further optional that before judging whether the score corresponding to the target store is greater than or equal to the threshold corresponding to the rating dimension for each rating dimension, the method of this embodiment may also include: according to the number of store recommendations within the preset range of the location information in the store recommendation request (such as the number of stores required to be recommended), the distribution of grade levels (such as the number of recommendations for each store grade on the list) and the priority between multiple rating dimensions (such as dividing the priorities between different rating dimensions according to the importance of different rating dimensions to the store grade determination, the higher the priority, the more important it is to the store grade determination), the threshold corresponding to each of the multiple rating dimensions is determined as a whole. Through this optional method, the most appropriate threshold can be obtained, which can meet the requirements of rating compliance determination and also meet the recommendation needs of the store.
[0087] Exemplarily, based on the number of store recommendations within a preset range of location information in a store recommendation request, the distribution of grade levels, and the priorities among multiple rating dimensions, the thresholds corresponding to each of the multiple rating dimensions are determined as a whole. Specifically, it may include: performing a Z-shaped search according to the store scores of each store within the preset range of the location information in the store recommendation request in order of priority from high to low, and stopping the search until the number of stores searched meets the stopping condition, wherein the stopping condition is determined based on the number of store recommendations and the distribution of grade levels; and determining the thresholds corresponding to each of the multiple rating dimensions with reference to the last store scores searched after the search is stopped.
[0088] For example, if you need to recommend stores within the city to users, you can determine the recommended high-end store data, store rank distribution, and priorities among multiple rating dimensions based on the size of the city. Figure 2 As shown, according to these rating dimensions, the algorithm model is searched in a "Z" shape. When the number of stores searched meets the number of listed stores and the distribution of listed stores, the thresholds corresponding to these rating dimensions can be found. In this way, the thresholds corresponding to each rating dimension can be accurately determined, which can then be used as a standard for judging compliance and accurately determining the store level of the store.
[0089] Optionally, step 104 may specifically include: obtaining target stores whose store levels are greater than a preset level threshold, and filtering them according to the number of stores that need to be recommended at each level; the server returns recommendation information of the filtered target stores to the client.
[0090] For example, there are five rating dimensions, and in each rating dimension, the A grade can be regarded as the highest grade. The preset grade threshold can be 3A, so 4A and 5A stores that are higher than 3A can be recommended as stores and then recommended to users. In practice, there are likely to be many 4A and 5A stores, and the size of the location area displayed to users is limited, so each grade level can be set in advance, such as recommending 2 5A stores and 1 4A store, and then filtering according to the number of stores that need to be recommended in each grade level, and filtering out 2 5A stores and 1 4A store to recommend to users.
[0091] Compared with the current traditional method, this embodiment considers multiple different rating dimensions and recommends target store information that meets the preset rating conditions to users. On the one hand, it can achieve accuracy and comprehensiveness in store information recommendation, saving users the cost of searching for required information; on the other hand, it can reduce the infringement of users' privacy data and protect users' privacy.
[0092] The above embodiment is an information recommendation process described on the server side. Further, in order to fully illustrate the implementation of this embodiment, this embodiment also provides another information recommendation method, which can be applied to the client side. Figure 3 As shown, the method includes:
[0093] Step 201: The client sends a store recommendation request to the server.
[0094] The store recommendation request carries location information, and further, the server determines the store level corresponding to each target store based on multiple rating dimensions according to the platform data of each target store within a preset range of the location information, wherein the platform data includes: store data of the target store, historical order data and corresponding order user data.
[0095] Step 202: The client receives recommendation information of target stores whose store grades meet preset grade conditions.
[0096] Optionally, after step 202, the method of this embodiment may further include: the client outputting the received recommendation information of the target stores, and the store level marks corresponding to the target stores.
[0097] For example, based on the received store recommendation information, the recommended store contents can be output in the form of a list, and the store grade of the store can be marked, such as 5A store, 4A store, etc. In addition, some recommendations can be output. Specifically, according to the priority of the rating dimension and the score corresponding to the rating dimension, the target rating dimension with a relatively high priority and a score exceeding the threshold can be selected, and then the content related to the target rating dimension can be referred to to generate the recommendation and display it in the list accordingly.
[0098] Compared with the current traditional method, the information recommendation method provided in this embodiment considers different rating dimensions and recommends target store information that meets the preset rating conditions to users. On the one hand, it can achieve accuracy and comprehensiveness in store information recommendation, saving users the cost of searching for required information; on the other hand, it can reduce the infringement of users' privacy data and protect users' privacy.
[0099] In order to facilitate understanding of the specific implementation process of the above-mentioned embodiments and methods, the following application scenarios are given, but not limited thereto:
[0100] In the recommendation demand for catering stores, based on the method of this embodiment, five dimensions are extracted by processing payment data: locals go there specially / tourist popularity / locals return rate / popularity / high rating. The standard of a good catering store is redefined from these five dimensions. That is, the catering stores are rated from these five dimensions, with A representing the highest level.
[0101] A special visit for local foodies: For example, users who spend more than the inflection point of the market at a location 3km away on weekends and other holidays are defined as local foodies. Any store where the number of local foodies visiting the store exceeds the threshold calculated by the algorithm within six months can be rated as A-level, a special visit for local foodies.
[0102] Tourist popularity: For users who are not permanent residents and have a maximum transaction interval of ≤7 days, the stores are ranked from high to low based on the number of orders per capita. Stores that reach a certain threshold calculated by the algorithm can be rated as A-level in terms of tourist popularity.
[0103] Local return rate: If the denominator is the total number of local people who shop at the store, and the numerator is the number of local people who shop at stores outside the 800m radius more than twice, stores that reach a certain threshold calculated by the algorithm can be rated as Grade A for local return rate.
[0104] Extremely popular: If all orders are ranked from high to low by average price per person, stores that reach a certain threshold calculated by the algorithm can be rated as extremely popular, Grade A.
[0105] High score: A store with a score of 4.0 or above (the threshold calculated by the algorithm, the full score can be 5.0) can be rated as a high-scoring A-level store.
[0106] Based on the above five dimensions, this embodiment rates the catering stores near the user or in the city where the user is located, and then recommends catering stores that meet the requirements to the user. The specific display effect can be as follows: Figure 4 Through this embodiment, accurate recommendations of high-quality restaurants can be made, saving users the cost of searching for required information.
[0107] Further, as Figure 1 The specific implementation of the method shown in the embodiment provides an information recommendation device that can be applied to the server side, such as Figure 5 As shown, the device includes: a receiving module 31, an acquiring module 32, a determining module 33, and a sending module 34.
[0108] The receiving module 31 is used to receive a store recommendation request, wherein the store recommendation request carries location information;
[0109] An acquisition module 32 is used to acquire platform data of each target store within a preset range of the location information, wherein the platform data includes: store data, historical order data and corresponding order user data of the target store;
[0110] A determination module 33, configured to determine store grades corresponding to the target stores based on the platform data and multiple rating dimensions;
[0111] The sending module 34 is used to return the recommendation information of the target store whose store grade meets the preset grade condition.
[0112] In a specific application scenario, the determination module 33 is specifically used to obtain the number of dimensions of the target store that meet the rating standards in multiple rating dimensions based on the platform data; and determine the store level corresponding to the target store based on the number of dimensions that meet the rating standards.
[0113] In a specific application scenario, the determination module 33 is further used to calculate the scores corresponding to the target store in multiple rating dimensions based on the platform data; for each rating dimension, determine whether the score corresponding to the target store is greater than or equal to the threshold corresponding to the rating dimension, and if so, determine that the target store's rating meets the standard in the rating dimension; and count the number of dimensions in which the target store's rating meets the standard.
[0114] In a specific application scenario, the determination module 33 is also used to determine the threshold values corresponding to each of the multiple rating dimensions as a whole based on the number of store recommendations within a preset range of the location information, the grade distribution, and the priority between the multiple rating dimensions before judging whether the score corresponding to the target store is greater than or equal to the threshold value corresponding to the rating dimension for each rating dimension.
[0115] In a specific application scenario, the determination module 33 is specifically used to perform a Z-shaped search according to the store scores of each store within a preset range of the location information in an order of priority from high to low among the multiple rating dimensions, and stop the search until the number of searched stores meets the stop condition, wherein the stop condition is determined based on the number of store recommendations and the grade distribution; and determine the thresholds corresponding to each of the multiple rating dimensions with reference to the store scores last searched after the search is stopped.
[0116] In a specific application scenario, the determination module 33 is also specifically used to determine the score of the target store in the first dimension according to the number of consumers of the local specific users of the target store within a preset time period if the rating dimension is the first dimension of local specific user behavior; if the rating dimension is the second dimension of non-local user behavior, then for non-local users whose maximum interval of days with order records is less than or equal to the preset day threshold, the score of the target store in the second dimension is determined according to the product of the average consumption of the non-local users of the target store and the number of orders; if the rating dimension is the third dimension of local user behavior, then the score of the target store in the third dimension is determined according to the ratio of the number of local users who have consumed in stores outside a specific range more than the preset number threshold to the total number of local users who have consumed in the target store; if the rating dimension is the fourth dimension of all user behavior, then the score of the target store in the fourth dimension is determined according to the product of all orders of the target store and the average consumption; if the rating dimension is the fifth dimension of store reviews, then the score of the target store in the fifth dimension is determined according to the user review score of the target store.
[0117] In a specific application scenario, the sending module 34 is specifically used to obtain target stores whose store levels are greater than a preset level threshold, and filter them according to the number of stores that need to be recommended at each level; and return recommendation information of the filtered target stores.
[0118] It should be noted that for other corresponding descriptions of various functional units involved in an information recommendation device applicable to a server side provided in this embodiment, reference can be made to Figure 1 The corresponding description of the method in will not be repeated here.
[0119] Further, as Figure 3 The specific implementation of the method shown in the embodiment of the present application provides an information recommendation device that can be applied to the client side, such as Figure 6 As shown, the device includes: a sending module 41 and a receiving module 42.
[0120] The sending module 41 is used to send a store recommendation request, wherein the store recommendation request carries location information, so that according to the platform data of each target store within a preset range of the location information, the store level corresponding to each target store is determined based on multiple rating dimensions, wherein the platform data includes: store data of the target store, historical order data and corresponding order user data;
[0121] The receiving module 42 is used to receive recommendation information of target stores whose store grades meet the preset grade conditions.
[0122] In a specific application scenario, the device further includes: an output module;
[0123] The output module is used to output the received target store recommendation information and the store level marks corresponding to the target stores after receiving the recommendation information of the target stores whose store levels meet the preset level conditions.
[0124] It should be noted that for other corresponding descriptions of the functional units involved in the information recommendation device applicable to the client side provided in this embodiment, please refer to Figure 3 The corresponding description of the method in will not be repeated here.
[0125] Based on the above Figure 1 The method shown in the embodiment of the present application is accordingly provided with a storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned Figure 1 Based on the above Figure 3 The present application also provides another storage medium on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned Figure 3 The method shown.
[0126] Based on this understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, USB flash drive, mobile hard disk, etc.), including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods of various implementation scenarios of the present application.
[0127] Based on the above Figure 1 The method shown, and Figure 5 In order to achieve the above-mentioned purpose, the embodiment of the present application also provides a server device, which can be a server, a computer device, or other network devices. The client device includes a storage medium and a processor; the storage medium is used to store a computer program; the processor is used to execute the computer program to achieve the above-mentioned Figure 1 The method shown.
[0128] Based on the above Figure 3 The method shown, and Figure 6 In order to achieve the above purpose, the embodiment of the present application also provides a client device, which can be a tablet computer, a smart phone, a smart watch, a smart bracelet, or other network devices. The device includes a storage medium and a processor; the storage medium is used to store a computer program; the processor is used to execute the computer program to achieve the above purpose. Figure 3 The method shown.
[0129] Optionally, both of the above-mentioned physical devices may further include a user interface, a network interface, a camera, a radio frequency (RF) circuit, a sensor, an audio circuit, a WI-FI module, etc. The user interface may include a display screen (Display), an input unit such as a keyboard (Keyboard), etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (such as a WI-FI interface), etc.
[0130] Those skilled in the art will appreciate that the physical device structure of a client device and a server device provided in this embodiment does not constitute a limitation on the two physical devices, and may include more or fewer components, or a combination of certain components, or different component arrangements.
[0131] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the two physical devices mentioned above, and supports the operation of information processing programs and other software and / or programs. The network communication module is used to realize communication between the components inside the storage medium, and communication with other hardware and software in the information processing physical device.
[0132] Based on the above content, further, an embodiment of the present application also provides an information recommendation system, which includes a server device and a client device.
[0133] The server device can be used to perform the following steps: Figure 1 The method shown in the client device can be used to perform the following Figure 3 The method shown.
[0134] The client device is used to send a store recommendation request to the server device, wherein the store recommendation request carries location information.
[0135] A server device is used to receive a store recommendation request sent by a client device; obtain platform data of each target store within a preset range of the location information carried in the store recommendation request, wherein the platform data includes: store data, historical order data and corresponding order user data of the target store; then determine the store level corresponding to each target store based on multiple rating dimensions according to the platform data; and finally return recommendation information of the target store whose store level meets the preset level conditions to the client device.
[0136] The client device is used to receive the recommendation information of the target store whose store grade meets the preset grade condition returned by the server device.
[0137] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform, or by hardware. By applying the technical solution of this embodiment, compared with the current traditional method, this embodiment does not need to rely on the user's information browsing history to recommend store information. The reference data used in this embodiment is the platform data of each target store within the specified location range, specifically including the store data, historical order data and corresponding order user data of the target store. And according to the reference data, the store level corresponding to each target store is determined based on multiple rating dimensions, and then from different rating dimensions, the target store information whose store level meets the preset level conditions is recommended to the user. On the one hand, the accuracy and comprehensiveness of the store information recommendation can be achieved, saving the cost of users searching for the required information; on the other hand, it can reduce the infringement of the user's privacy data and protect the user's privacy.
[0138] Those skilled in the art will appreciate that the accompanying drawings are only schematic diagrams of a preferred implementation scenario, and the modules or processes in the accompanying drawings are not necessarily necessary for implementing the present application. Those skilled in the art will appreciate that the modules in the devices in the implementation scenario can be distributed in the devices of the implementation scenario according to the description of the implementation scenario, or can be changed accordingly and located in one or more devices different from the present implementation scenario. The modules of the above-mentioned implementation scenario can be combined into one module, or can be further split into multiple submodules.
[0139] The above serial numbers of this application are only for description and do not represent the advantages and disadvantages of the implementation scenarios. The above disclosure is only a few specific implementation scenarios of this application, but this application is not limited to them, and any changes that can be thought of by technicians in this field should fall within the scope of protection of this application.
Claims
1. An information recommendation method, It is characterized in that include: receiving a store recommendation request, wherein the store recommendation request carries location information; Acquire platform data of each target store within a preset range of the location information, wherein the platform data includes: store data, historical order data and corresponding order user data of the target store; According to the platform data, the store grades corresponding to the target stores are determined based on multiple rating dimensions, wherein the store grades are determined based on the number of dimensions in which the target stores meet the rating standards in the multiple rating dimensions, and the number of dimensions in which the rating standards meet is determined based on the scores and thresholds corresponding to the target stores in the multiple rating dimensions, and the scores are calculated based on the platform data; The calculation methods of the scores of the target store corresponding to the multiple rating dimensions include: If the rating dimension is the first dimension of local specific user behavior, the score of the target store in the first dimension is determined according to the number of consumers of the local specific users of the target store within a preset time period, wherein the local specific users are local users who are at a place greater than a certain distance threshold from the local user's permanent residence on holidays and have order consumption times higher than the overall standard of local users; If the rating dimension is the second dimension of non-local user behavior, then for non-local users whose maximum interval of days with order records is less than or equal to the preset day threshold, the score corresponding to the target store in the second dimension is determined based on the product of the non-local user's average consumption and the number of orders of the target store; If the rating dimension is the third dimension of local user behavior, the score of the target store corresponding to the third dimension is determined based on the ratio of the number of local users who shop at stores outside the specific range more than a preset number threshold to the total number of local users who shop at the target store; If the rating dimension is the fourth dimension of all user behaviors, the score of the target store corresponding to the fourth dimension is determined based on the product of all orders of the target store and the average consumption per person; If the rating dimension is the fifth dimension of store reviews, then the score of the target store corresponding to the fifth dimension is determined according to the user review score of the target store; Returns the recommended information of target stores whose store levels meet the preset level conditions.
2. The method according to claim 1, It is characterized in that Determining store grades corresponding to the target stores based on the platform data and multiple rating dimensions specifically includes: According to the platform data, the number of dimensions in which the target store's ratings meet the standards in multiple rating dimensions is obtained; The store grade corresponding to the target store is determined based on the number of dimensions that meet the rating standards.
3. The method according to claim 2, It is characterized in that The step of obtaining the number of dimensions of the target store that meet the rating standards in multiple rating dimensions according to the platform data specifically includes: Calculate the scores of the target store in multiple rating dimensions according to the platform data; For each rating dimension, determine whether the score corresponding to the target store is greater than or equal to the threshold corresponding to the rating dimension. If so, determine that the target store has met the rating standard in the rating dimension; Count the number of dimensions for which the target store ratings meet the standards.
4. The method according to claim 3, It is characterized in that Before determining, for each rating dimension, whether the score corresponding to the target store is greater than or equal to a threshold corresponding to the rating dimension, the method further includes: According to the number of store recommendations within a preset range of the location information, the distribution of grade levels, and the priorities among the multiple rating dimensions, the thresholds corresponding to the multiple rating dimensions are determined as a whole.
5. The method according to claim 4, It is characterized in that The step of determining the thresholds corresponding to the multiple rating dimensions as a whole based on the number of recommended stores within the preset range of the location information, the distribution of grade levels, and the priorities among the multiple rating dimensions specifically includes: In descending order of priority among the multiple rating dimensions, a Z-shaped search is performed according to the store scores of each store within the preset range of the location information, and the search is stopped when the number of stores searched meets a stop condition, wherein the stop condition is determined according to the number of recommended stores and the distribution of grade levels; The threshold values corresponding to each of the multiple rating dimensions are determined with reference to the store ratings that were last searched for each of the multiple rating dimensions after the search is stopped.
6. The method according to claim 1, It is characterized in that The returned recommendation information of the target store whose store level meets the preset level condition specifically includes: Obtain target stores whose store levels are greater than the preset level threshold, and filter them according to the number of stores that need to be recommended at each level; Returns the recommended information of the filtered target store.
7. An information recommendation method, It is characterized in that include: Send a store recommendation request, which carries location information, so that according to the platform data of each target store within a preset range of the location information, the store level corresponding to each target store is determined based on multiple rating dimensions, wherein the platform data includes: store data, historical order data and corresponding order user data of the target store; the store level is determined according to the number of dimensions of the target store that meet the rating standards in the multiple rating dimensions, the number of dimensions of the target store that meet the rating standards is determined according to the scores and thresholds corresponding to the target store in the multiple rating dimensions, and the scores are calculated according to the platform data; The calculation methods of the scores of the target store corresponding to the multiple rating dimensions include: If the rating dimension is the first dimension of local specific user behavior, the score of the target store in the first dimension is determined according to the number of consumers of the local specific users of the target store within a preset time period, wherein the local specific users are local users who are at a place greater than a certain distance threshold from the local user's permanent residence on holidays and have order consumption times higher than the overall standard of local users; If the rating dimension is the second dimension of non-local user behavior, then for non-local users whose maximum interval of days with order records is less than or equal to the preset day threshold, the score corresponding to the target store in the second dimension is determined based on the product of the non-local user's average consumption and the number of orders of the target store; If the rating dimension is the third dimension of local user behavior, the score of the target store corresponding to the third dimension is determined based on the ratio of the number of local users who shop at stores outside the specific range more than a preset number threshold to the total number of local users who shop at the target store; If the rating dimension is the fourth dimension of all user behaviors, the score of the target store corresponding to the fourth dimension is determined based on the product of all orders of the target store and the average consumption per person; If the rating dimension is the fifth dimension of store reviews, then the score of the target store corresponding to the fifth dimension is determined according to the user review score of the target store; Receive recommendation information of target stores whose store grades meet preset grade conditions.
8. The method according to claim 7, It is characterized in that After receiving the recommendation information of the target store whose store grade meets the preset grade condition, the method further includes: Output the received target store recommendation information and the store level tags corresponding to each target store.
9. An information recommendation device, It is characterized in that include: A receiving module, configured to receive a store recommendation request, wherein the store recommendation request carries location information; An acquisition module, used to acquire platform data of each target store within a preset range of the location information, wherein the platform data includes: store data, historical order data and corresponding order user data of the target store; A determination module, configured to determine store grades corresponding to the target stores based on the platform data and multiple rating dimensions; the store grades are determined based on the number of dimensions for which the target stores meet the rating standards in the multiple rating dimensions, the number of dimensions for which the rating standards meet the rating standards is determined based on the scores and thresholds corresponding to the target stores in the multiple rating dimensions, and the scores are calculated based on the platform data; The calculation methods of the scores of the target store corresponding to the multiple rating dimensions include: If the rating dimension is the first dimension of local specific user behavior, the score of the target store in the first dimension is determined according to the number of consumers of the local specific users of the target store within a preset time period, wherein the local specific users are local users who are at a place greater than a certain distance threshold from the local user's permanent residence on holidays and have order consumption times higher than the overall standard of local users; If the rating dimension is the second dimension of non-local user behavior, then for non-local users whose maximum interval of days with order records is less than or equal to the preset day threshold, the score corresponding to the target store in the second dimension is determined based on the product of the non-local user's average consumption and the number of orders of the target store; If the rating dimension is the third dimension of local user behavior, the score of the target store corresponding to the third dimension is determined based on the ratio of the number of local users who shop at stores outside the specific range more than a preset number threshold to the total number of local users who shop at the target store; If the rating dimension is the fourth dimension of all user behaviors, the score of the target store corresponding to the fourth dimension is determined based on the product of all orders of the target store and the average consumption per person; If the rating dimension is the fifth dimension of store reviews, then the score of the target store corresponding to the fifth dimension is determined according to the user review score of the target store; The sending module is used to return the recommendation information of the target stores whose store levels meet the preset level conditions.
10. An information recommendation device, It is characterized in that include: A sending module, used for sending a store recommendation request, wherein the store recommendation request carries location information, so that according to the platform data of each target store within a preset range of the location information, the store level corresponding to each target store is determined based on multiple rating dimensions, wherein the platform data includes: store data, historical order data and corresponding order user data of the target store; the store level is determined according to the number of dimensions of the target store that meet the rating standards in the multiple rating dimensions, the number of dimensions of the target store that meet the rating standards is determined according to the scores and thresholds corresponding to the target store in the multiple rating dimensions, and the scores are calculated according to the platform data; The calculation methods of the scores of the target store corresponding to the multiple rating dimensions include: If the rating dimension is the first dimension of local specific user behavior, the score of the target store in the first dimension is determined according to the number of consumers of the local specific users of the target store within a preset time period, wherein the local specific users are local users who are at a place greater than a certain distance threshold from the local user's permanent residence on holidays and have order consumption times higher than the overall standard of local users; If the rating dimension is the second dimension of non-local user behavior, then for non-local users whose maximum interval of days with order records is less than or equal to the preset day threshold, the score corresponding to the target store in the second dimension is determined based on the product of the non-local user's average consumption and the number of orders of the target store; If the rating dimension is the third dimension of local user behavior, the score of the target store corresponding to the third dimension is determined based on the ratio of the number of local users who shop at stores outside the specific range more than a preset number threshold to the total number of local users who shop at the target store; If the rating dimension is the fourth dimension of all user behaviors, the score of the target store corresponding to the fourth dimension is determined based on the product of all orders of the target store and the average consumption per person; If the rating dimension is the fifth dimension of store reviews, then the score of the target store corresponding to the fifth dimension is determined according to the user review score of the target store; The receiving module is used to receive recommendation information of target stores whose store grades meet preset grade conditions.
11. A storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.
12. An electronic device comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, It is characterized in that When the processor executes the computer program, the method according to any one of claims 1 to 8 is implemented.
Citation Information
Patent Citations
Shop evaluation obtaining method and device, equipment and storage medium
CN110348909A
Shop recommendation method, device and equipment
CN110428298A
Delicious food recommendation list generation method and device, equipment and storage medium
CN110942344A
Information recommendation method and device, and server
CN111782941A
Merchant recommendation method and device and computer equipment
CN111861139A
