Information recommendation method and device based on artificial intelligence, computer equipment and medium

Abstract

The invention belongs to the field of artificial intelligence and the field of financial science and technology, and relates to an artificial intelligence-based information recommendation method, which comprises the following steps of: obtaining position information and user information of a user; judging whether the position information is in the target geo-fencing area or not; if yes, acquiring initial merchant information corresponding to the target geo-fence area from a database; acquiring a user portrait of the user based on the user information; screening the initial merchant information based on the user portrait and a first preset recommendation algorithm to obtain first merchant information; screening the first merchant information based on the user portrait and a second preset recommendation algorithm to obtain second merchant information; and pushing the second merchant information to the user. The invention further provides an artificial intelligence-based information recommendation device, computer equipment and a storage medium. In addition, the second merchant information may be stored in the blockchain. According to the method, the position information, the user portrait and the recommendation algorithm are combined for information recommendation, so that the pertinence and accuracy of information recommendation are improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence development technology and financial technology, and in particular to artificial intelligence-based information recommendation methods, devices, computer equipment and storage media. Background Art

[0002] With the rapid development of science and technology, the popularization of mobile communication technology and intelligent terminal devices, especially the widespread use of smartphones, has profoundly changed people's daily lifestyles. With its high portability, powerful computing power and rich application ecology, smartphones have become an indispensable platform for information acquisition and interaction in modern society. This trend has not only promoted the rise of emerging entertainment and business models such as short videos and live streaming, but also greatly expanded the marketing boundaries in multiple fields such as finance and life services.

[0003] However, in the current mobile application market, although product recommendation systems have been widely used in various apps to improve user experience and promote user consumption, most recommendation algorithms still rely mainly on factors such as content popularity and merchant profit considerations for matching, ignoring the unique geographical location perception capabilities of mobile terminals. This practice of ignoring the location advantages of mobile terminals not only limits the relevance and timeliness of recommended content, but also leads to low accuracy of information recommendations. Summary of the invention

[0004] The purpose of the embodiments of the present application is to propose an information recommendation method, device, computer equipment and storage medium based on artificial intelligence, so as to solve the technical problem that the existing recommendation algorithm still mainly relies on factors such as content popularity and merchant profit considerations for matching, ignoring the unique geographical location perception capabilities of mobile terminals, which not only limits the relevance and timeliness of recommended content, but also leads to low accuracy of information recommendations.

[0005] In order to solve the above technical problems, the present application embodiment provides an information recommendation method based on artificial intelligence, which adopts the following technical solutions:

[0006] Get the user's location information and user information;

[0007] Determining whether the location information is within a preset target geo-fenced area;

[0008] If so, obtaining initial merchant information corresponding to the target geo-fenced area from a pre-created database;

[0009] Acquire a user portrait of the user based on the user information;

[0010] Filtering the initial merchant information based on the user portrait and a first preset recommendation algorithm to obtain corresponding first merchant information;

[0011] Filtering the first merchant information based on the user portrait and a second preset recommendation algorithm to obtain corresponding second merchant information;

[0012] The second merchant information is pushed to the user.

[0013] Furthermore, the step of determining whether the location information is within a preset target geo-fenced area specifically includes:

[0014] Get multiple preset geospatial algorithms;

[0015] determining a target geospatial algorithm from among all of the geospatial algorithms;

[0016] The location information and the target geofence area are processed based on the target geospatial algorithm to generate a location matching result between the location information and the target geofence area; wherein the location matching result includes that the location information is within the target geofence area, or that the location information is not within the target geofence area.

[0017] Furthermore, the step of acquiring the initial merchant information corresponding to the target geo-fenced area from a pre-created database specifically includes:

[0018] Obtain a target identifier of the target geo-fenced area;

[0019] Constructing a corresponding database query statement based on the target identifier;

[0020] calling the database;

[0021] Executing the database query statement to retrieve corresponding third merchant information from the database;

[0022] Filtering fourth merchant information that meets the time validity condition from the third merchant information;

[0023] The fourth merchant information is used as the initial merchant information.

[0024] Furthermore, the step of screening the first merchant information based on the user portrait and the second preset recommendation algorithm to obtain the corresponding second merchant information specifically includes:

[0025] Obtaining product description information corresponding to the first merchant information;

[0026] Extracting features from the user portrait and the product description information respectively to obtain a first feature corresponding to the user portrait and a second feature corresponding to the product description information;

[0027] Calculating the similarity between the first feature and the second feature based on a preset similarity algorithm to obtain a recommendation score for the first merchant information;

[0028] Filtering out a designated recommendation score greater than a preset score threshold from all the recommendation scores;

[0029] Filtering out designated merchant information corresponding to the designated recommendation score from all the first merchant information;

[0030] The designated merchant information is used as the second merchant information.

[0031] Furthermore, the step of pushing the second merchant information to the user specifically includes:

[0032] Deduplication processing is performed on the second merchant information to obtain corresponding fifth merchant information;

[0033] Obtaining a ranking factor corresponding to the fifth merchant information;

[0034] Determining preset weights corresponding to the ranking factors;

[0035] generating a comprehensive score for the fifth merchant information based on the ranking factor and the preset weight;

[0036] Sorting all the fifth merchant information in descending order based on the comprehensive scores to obtain a corresponding recommended merchant information list;

[0037] The recommended merchant information list is pushed to the user.

[0038] Furthermore, the step of pushing the recommended merchant information list to the user specifically includes:

[0039] Call the preset display component;

[0040] Determining a screen display position corresponding to the recommended merchant information list;

[0041] Based on the display component, the recommended merchant information list is displayed in the screen display position.

[0042] Furthermore, before the step of acquiring the initial merchant information corresponding to the target geo-fenced area from the pre-created database, the method further includes:

[0043] Delineate geo-fenced areas on a map based on a preset map service tool;

[0044] Obtaining geo-fence information of the geo-fence area;

[0045] Collecting merchant information and establishing association information between the merchant information and the geo-fenced area;

[0046] Creating a matching rule corresponding to the merchant information;

[0047] Get the target data format;

[0048] Based on the target data format, the geo-fence information, the merchant information, the association information and the matching rule are stored in a preset initial database to obtain the database.

[0049] In order to solve the above technical problems, the embodiment of the present application further provides an information recommendation device based on artificial intelligence, which adopts the following technical solution:

[0050] A first acquisition module is used to acquire the user's location information and user information;

[0051] A determination module, used to determine whether the location information is within a preset target geographic fence area;

[0052] A second acquisition module is used to acquire initial merchant information corresponding to the target geo-fenced area from a pre-created database;

[0053] A third acquisition module, used to acquire a user portrait of the user based on the user information;

[0054] A first screening module, configured to screen the initial merchant information based on the user portrait and a first preset recommendation algorithm to obtain corresponding first merchant information;

[0055] A second screening module, configured to screen the first merchant information based on the user portrait and a second preset recommendation algorithm to obtain corresponding second merchant information;

[0056] A push module is used to push the second merchant information to the user.

[0057] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0058] Get the user's location information and user information;

[0059] Determining whether the location information is within a preset target geo-fenced area;

[0060] If so, obtaining initial merchant information corresponding to the target geo-fenced area from a pre-created database;

[0061] Acquire a user portrait of the user based on the user information;

[0062] Filtering the initial merchant information based on the user portrait and a first preset recommendation algorithm to obtain corresponding first merchant information;

[0063] Filtering the first merchant information based on the user portrait and a second preset recommendation algorithm to obtain corresponding second merchant information;

[0064] The second merchant information is pushed to the user.

[0065] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0066] Get the user's location information and user information;

[0067] Determining whether the location information is within a preset target geo-fenced area;

[0068] If so, obtaining initial merchant information corresponding to the target geo-fenced area from a pre-created database;

[0069] Acquire a user portrait of the user based on the user information;

[0070] Filtering the initial merchant information based on the user portrait and a first preset recommendation algorithm to obtain corresponding first merchant information;

[0071] Filtering the first merchant information based on the user portrait and a second preset recommendation algorithm to obtain corresponding second merchant information;

[0072] The second merchant information is pushed to the user.

[0073] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0074] The present application first obtains the user's location information and user information; then determines whether the location information is within a preset target geo-fence area; if so, obtains initial merchant information corresponding to the target geo-fence area from a pre-created database; then obtains a user portrait of the user based on the user information; subsequently, filters and processes the initial merchant information based on the user portrait and a first preset recommendation algorithm to obtain corresponding first merchant information; further filters and processes the first merchant information based on the user portrait and a second preset recommendation algorithm to obtain corresponding second merchant information; and finally pushes the second merchant information to the user. This application obtains the user's location information and user information, and obtains the user portrait based on the user information. After detecting that the location information is within a preset target geographic fence area, the application will first obtain the initial merchant information corresponding to the target geographic fence area from the database, and then preliminarily screen the initial merchant information based on the user portrait and a first preset recommendation algorithm to obtain the first merchant information. Subsequently, based on the first merchant information, the application will further combine the user portrait with the use of a second preset recommendation algorithm to perform refined screening of the first merchant information for personalized recommendation, ensuring that the obtained second merchant information is merchant information that is highly relevant to the user's interests and is timely. Finally, the second merchant information is pushed to the user, which effectively improves the recommendation accuracy of the merchant information and is conducive to improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0076] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0077] Figure 2 A flowchart of an embodiment of an information recommendation method based on artificial intelligence according to the present application;

[0078] Figure 3 is a structural schematic diagram of an embodiment of an information recommendation device based on artificial intelligence according to the present application;

[0079] Figure 4 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0080] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0081] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0082] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0083] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0084] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0085] The terminal devices 101, 102, and 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, desktop computers, and the like.

[0086] The server 105 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal devices 101 , 102 , and 103 .

[0087] It should be noted that the artificial intelligence-based information recommendation method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the artificial intelligence-based information recommendation device is generally set in the server / terminal device.

[0088] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0089] Continue to refer Figure 2 , showing a flowchart of an embodiment of an information recommendation method based on artificial intelligence according to the present application. According to different requirements, the order of the steps in the flowchart can be changed, and some steps can be omitted. The information recommendation method based on artificial intelligence provided in the embodiment of the present application can be applied to any scenario where information recommendation is required, and the information recommendation method based on artificial intelligence can be applied to products in these scenarios, for example, information recommendation in the field of finance and insurance. The information recommendation method based on artificial intelligence includes the following steps:

[0090] Step S201, obtaining the user's location information and user information.

[0091] In this embodiment, the information recommendation method based on artificial intelligence is executed on the electronic device (for example Figure 1The server / terminal device shown in the figure) can obtain the user's location information and user information through a wired connection or a wireless connection. It should be noted that the above-mentioned wireless connection method may include but is not limited to 3G / 4G / 5G connection, Wi-Fi connection, Bluetooth connection, Wi MAX connection, Zigbee connection, UWB (Ultra Wi DeBand) connection, and other wireless connection methods currently known or to be developed in the future. The execution subject of the present application may be an information recommendation device, and the present application may be applied to the information recommendation scenario of financial insurance. The merchant information corresponding to the information recommendation may include merchant activities, discounts, notifications and other information of the merchant. The above-mentioned merchants may include insurance companies, banks, etc., and the merchant products may include insurance products, deposit products, loan products, etc. Among them, when the user starts the electronic device, the user's location authorization will be requested. Preferably, the "always allow" permission will be requested so that the user's location information can be continuously obtained in the background. The above-mentioned user information may include the user's name or user ID. In addition, an efficient data collection channel is established to collect the user's location information and user information according to a preset frequency (such as 5 minutes, 10 minutes, 30 minutes). Furthermore, to ensure that data traffic consumption is minimized, the reported data is compressed and the user's sensitive information needs to be encrypted to ensure data security.

[0092] Step S202, determining whether the location information is within a preset target geographic fence area.

[0093] In this embodiment, the specific implementation process of the above-mentioned determination of whether the location information is within the preset target geographic fence area will be further described in detail in the subsequent specific embodiments of this application and will not be elaborated here.

[0094] Step S203: If yes, obtain the initial merchant information corresponding to the target geo-fenced area from a pre-created database.

[0095] In this embodiment, the specific implementation process of obtaining the initial merchant information corresponding to the target geographic fence area from the pre-created database will be further described in detail in subsequent specific embodiments of the present application and will not be elaborated on here.

[0096] Step S204: obtaining a user portrait of the user based on the user information.

[0097] In this embodiment, a target portrait matching the user information can be queried from a pre-built portrait database to obtain a user portrait of the user. The portrait database is a pre-built database storing multiple customers and portrait data corresponding to various customers. The user portrait may include historical behavior, preference settings and other data.

[0098] Step S205: Screening the initial merchant information based on the user portrait and a first preset recommendation algorithm to obtain corresponding first merchant information.

[0099] In this embodiment, the first preset recommendation algorithm may specifically adopt a collaborative filtering algorithm. By using the historical behavior data of the user contained in the user portrait, other users similar to the user (based on user collaborative filtering) or similar items liked by the user (based on item collaborative filtering) can be found, and then the initial merchant information is preliminarily filtered according to the preferences of these similar users or items to obtain corresponding candidate recommendation information, i.e., the first merchant information.

[0100] Step S206: filter the first merchant information based on the user portrait and a second preset recommendation algorithm to obtain corresponding second merchant information.

[0101] In this embodiment, the specific implementation process of filtering and processing the first merchant information based on the user portrait and the second preset recommendation algorithm to obtain the corresponding second merchant information will be further described in detail in subsequent specific embodiments of the present application and will not be elaborated on here.

[0102] Step S207: Push the second merchant information to the user.

[0103] In this embodiment, the specific implementation process of pushing the second merchant information to the user will be further described in detail in subsequent specific embodiments of the present application, and will not be elaborated on here.

[0104] The present application first obtains the user's location information and user information; then determines whether the location information is within a preset target geo-fence area; if so, obtains initial merchant information corresponding to the target geo-fence area from a pre-created database; then obtains a user portrait of the user based on the user information; subsequently, filters and processes the initial merchant information based on the user portrait and a first preset recommendation algorithm to obtain corresponding first merchant information; further filters and processes the first merchant information based on the user portrait and a second preset recommendation algorithm to obtain corresponding second merchant information; and finally pushes the second merchant information to the user. This application obtains the user's location information and user information, and obtains the user portrait based on the user information. After detecting that the location information is within a preset target geographic fence area, the application will first obtain the initial merchant information corresponding to the target geographic fence area from the database, and then preliminarily screen the initial merchant information based on the user portrait and a first preset recommendation algorithm to obtain the first merchant information. Subsequently, based on the first merchant information, the application will further combine the user portrait with the use of a second preset recommendation algorithm to perform refined screening of the first merchant information for personalized recommendation, ensuring that the obtained second merchant information is merchant information that is highly relevant to the user's interests and is timely. Finally, the second merchant information is pushed to the user, which effectively improves the recommendation accuracy of the merchant information and is conducive to improving the user experience.

[0105] In some optional implementations, step S202 includes the following steps:

[0106] Get multiple preset geospatial algorithms.

[0107] In this embodiment, the above-mentioned geospatial algorithm may refer to a point within a polygon judgment algorithm, which may specifically include a Ray-Casting algorithm, an angle sum method, a winding number method, a half-plane method, a barycentric coordinate method, and the like.

[0108] A target geospatial algorithm is determined from among all the geospatial algorithms.

[0109] In this embodiment, there is no specific limitation on the method for determining the target geospatial algorithm, and one algorithm can be randomly selected from all the geospatial algorithms and used as the target geospatial algorithm. Preferably, the Ray-Casting algorithm is used as the target geospatial algorithm.

[0110] The location information and the target geo-fenced area are processed based on the target geo-spatial algorithm to generate a location matching result between the location information and the target geo-fenced area.

[0111] In this embodiment, the location information and the target geofence area are processed by using the above-mentioned target geospatial algorithm to determine the user's current location, that is, whether the above-mentioned location information is within the above-mentioned target geofence area, and generate a location matching result between the location information and the target geofence area. Specifically, by traversing the coordinate points of all geofences, each geofence is regarded as a polygon. For each polygon, a ray is emitted in any direction (such as horizontally to the right) starting from the user's current position (point). The number of intersections between the ray and the polygon boundary is counted. If the number of intersections is an odd number, the point is inside the polygon; if it is an even number, the point is outside the polygon. Among them, the location matching result includes that the location information is within the target geofence area, or that the location information is not within the target geofence area.

[0112] The present application obtains a plurality of preset geospatial algorithms; then determines a target geospatial algorithm from all the geospatial algorithms; and subsequently processes the location information and the target geofence area based on the target geospatial algorithm to generate a location matching result between the location information and the target geofence area. The present application determines a target geospatial algorithm from a plurality of geospatial algorithms, and then processes the location information and the target geofence area based on the target geospatial algorithm, so that a location matching result between the location information and the target geofence area can be generated quickly and accurately, thereby improving the efficiency of generating the location matching result and ensuring the accuracy of the obtained location matching result.

[0113] In some optional implementations of this embodiment, step S203 includes the following steps:

[0114] Get a target identifier for the target geo-fenced area.

[0115] In this embodiment, after determining that the location information is within the target geo-fenced area, an identifier query process may be performed within the target geo-fenced area to obtain a target identifier of the target geo-fenced area.

[0116] A corresponding database query statement is constructed based on the target identifier.

[0117] In this embodiment, a corresponding SQL query statement may be constructed according to the target identifier to obtain the database query statement.

[0118] The database is called.

[0119] In this embodiment, the database is a pre-constructed database storing geo-fence information of geo-fence areas, merchant information, association information between the merchant information and the geo-fence areas, matching rules corresponding to the merchant information, etc. The construction process of the database will be described in further detail in subsequent specific embodiments, and will not be elaborated on here.

[0120] The database query statement is executed to retrieve corresponding third merchant information from the database.

[0121] In this embodiment, the above-mentioned database query statement is executed to retrieve all the merchant information associated with the above-mentioned target geographic fence area from the database to obtain the above-mentioned third merchant information.

[0122] The fourth merchant information that meets the time validity condition is screened out from the third merchant information.

[0123] In this embodiment, by checking the start time and end time of the activity or discount for all third merchant information, valid merchant information whose current time is within the valid range is obtained and used as the fourth merchant information.

[0124] The fourth merchant information is used as the initial merchant information.

[0125] The present application obtains the target identifier of the target geo-fenced area; then constructs a corresponding database query statement based on the target identifier; then calls the database; subsequently executes the database query statement to retrieve the corresponding third merchant information from the database; finally, filters out the fourth merchant information that meets the time validity condition from the third merchant information, and uses the fourth merchant information as the initial merchant information. The present application constructs a database query statement based on the target identifier of the target geo-fenced area, and then executes the database query statement to retrieve the corresponding third merchant information from the database, and intelligently filters out the merchant information that meets the time validity condition from the third merchant information to obtain the final initial merchant information, thereby improving the intelligence of the screening of the initial merchant information and ensuring the validity and accuracy of the obtained initial merchant information.

[0126] In some optional implementations, step S206 includes the following steps:

[0127] Obtain product description information corresponding to the first merchant information.

[0128] In this embodiment, the second preset recommendation algorithm may specifically adopt a content-based recommendation algorithm. The first merchant information includes description information about the merchant's products / activities, such as titles, tags, keywords, categories, and other information.

[0129] Feature extraction is performed on the user portrait and the product description information respectively to obtain a first feature corresponding to the user portrait and a second feature corresponding to the product description information.

[0130] In this embodiment, by extracting key features from the user portrait, a first feature corresponding to the user portrait is obtained, and by extracting key features from the product description information, a second feature corresponding to the product description information is obtained. The key features may refer to features such as user interest tags or product categories.

[0131] The similarity between the first feature and the second feature is calculated based on a preset similarity algorithm to obtain a recommendation score for the first merchant information.

[0132] In this embodiment, the similarity algorithm may be any one of text similarity, TF-IDF weight, word embedding, etc. The similarity between the first feature and each of the second features is calculated by using the similarity algorithm, and the obtained similarity is used as the recommendation score of each of the first merchant information.

[0133] A designated recommendation score greater than a preset score threshold is screened out from all the recommendation scores.

[0134] In this embodiment, there is no specific limitation on the numerical setting of the above-mentioned score threshold, which can be set according to actual screening requirements.

[0135] Filter out designated merchant information corresponding to the designated recommendation score from all the first merchant information.

[0136] In this embodiment, the designated merchant information refers to merchant information that has a corresponding relationship with the designated recommendation score among all the first merchant information.

[0137] The designated merchant information is used as the second merchant information.

[0138] This application obtains the product description information corresponding to the first merchant information; then extracts features from the user portrait and the product description information respectively to obtain a first feature corresponding to the user portrait, and a second feature corresponding to the product description information; then calculates the similarity between the first feature and the second feature based on a preset similarity algorithm to obtain a recommendation score for the first merchant information; subsequently, a designated recommendation score greater than a preset score threshold is screened out from all the recommendation scores; further, a designated merchant information corresponding to the designated recommendation score is screened out from all the first merchant information; and finally, the designated merchant information is used as the second merchant information. After the first merchant information is obtained after a preliminary screening of the initial merchant information, this application will further combine the user portrait on the basis of the first merchant information, and use a content-based recommendation algorithm to perform a refined screening of the first merchant information for personalized recommendations, thereby ensuring that the second merchant information obtained is merchant information that is highly relevant to the user's interests, and effectively improving the accuracy of merchant information recommendations.

[0139] In some optional implementations, step S207 includes the following steps:

[0140] The second merchant information is deduplicated to obtain corresponding fifth merchant information.

[0141] In this embodiment, duplicate content, such as product or activity information, is checked and removed from the second merchant information to ensure that the recommended content viewed by the user is unique and valuable.

[0142] A ranking factor corresponding to the fifth merchant information is obtained.

[0143] In this embodiment, the above-mentioned sorting factors may at least include the above-mentioned recommendation score, the popularity of the product / activity, the user's historical behavior, and the time factor. Among them, the above-mentioned recommendation score reflects the user's potential interest in the product / activity of the second merchant information. The popularity of the above-mentioned product / activity can be measured based on indicators such as sales volume, click volume, and number of ratings. Popular products / activities tend to attract more users. The above-mentioned user's historical behavior refers to the user's past interaction history with similar products / activities, such as purchases, browsing, ratings, etc., which can be used as a reference for recommendation weights. The above-mentioned time factor refers to the timeliness of the product / activity (such as promotions, limited-time offers). The greater the timeliness, the higher the importance of the time factor.

[0144] Determine a preset weight corresponding to the ranking factor.

[0145] In this embodiment, the importance of each ranking factor in the final ranking result may be different, and a weight may be assigned to each ranking factor in advance based on business experience or expert judgment.

[0146] A comprehensive score of the fifth merchant information is generated based on the ranking factors and the preset weights.

[0147] In this embodiment, by obtaining the quantitative values ​​corresponding to the ranking factors, such as the similarity score, the popularity score, etc., the quantitative values ​​corresponding to the ranking factors and the preset weights are weighted summed using a weighted summation method, and the calculated result is used as the comprehensive score of the fifth merchant information.

[0148] All the fifth merchant information are sorted in descending order based on the comprehensive scores to obtain a corresponding recommended merchant information list.

[0149] In this embodiment, diversity factors can also be considered during the sorting process to avoid the recommendation results being too single. This can be achieved in the following ways: Group sorting: first group the recommended items according to certain dimensions (such as category, brand, price, etc.), then sort them within each group, and finally merge the results of each group to obtain a recommended merchant information list. Diversity algorithm: Use a special diversity algorithm (such as a greedy algorithm, simulated annealing algorithm, etc.) to optimize the diversity of the recommended merchant information list.

[0150] The recommended merchant information list is pushed to the user.

[0151] In this embodiment, the specific implementation process of pushing the recommended merchant information list to the user will be described in further detail in subsequent specific embodiments of the present application, and will not be elaborated on here.

[0152] This application obtains the corresponding fifth merchant information by performing deduplication processing on the second merchant information; then obtains the sorting factor corresponding to the fifth merchant information; then determines the preset weight corresponding to the sorting factor; subsequently generates the comprehensive score of the fifth merchant information based on the sorting factor and the preset weight; further sorts all the fifth merchant information in descending order based on the comprehensive score to obtain the corresponding recommended merchant information list; and finally pushes the recommended merchant information list to the user. After obtaining the second merchant information, this application obtains the fifth merchant information by intelligently performing deduplication processing on the second merchant information, then obtains the sorting factor corresponding to the fifth merchant information, and generates the comprehensive score of the fifth merchant information according to the preset weight corresponding to the sorting factor, and then sorts all the fifth merchant information in descending order based on the comprehensive score, and pushes the recommended merchant information list generated after sorting to the user for reference and selection, intelligently realizing the optimization processing of the display sorting of the second merchant information, and realizing personalized recommendation for users based on the use of the recommended merchant information list, improving the intelligence of information recommendation, and being conducive to improving the user experience.

[0153] In some optional implementations of this embodiment, pushing the recommended merchant information list to the user includes the following steps:

[0154] Call the preset display component.

[0155] In this embodiment, the display component may specifically be a widget component.

[0156] Determine a screen display position corresponding to the recommended merchant information list.

[0157] In this embodiment, there is no specific limitation on the method for determining the above screen display position, which can be set according to actual display requirements, for example, it can be set to the upper left corner, upper right corner, lower left corner, lower right corner, middle position of the screen, etc. In addition, the user's preferred viewing position can also be obtained and used as the above screen display position to improve the user's viewing experience.

[0158] Based on the display component, the recommended merchant information list is displayed in the screen display position.

[0159] In this embodiment, by using the above-mentioned display component, the recommended business information list can be quickly displayed in real time at the screen display position in the user's screen.

[0160] This application calls a preset display component; then determines the screen display position corresponding to the recommended merchant information list; and then based on the display component, displays the recommended merchant information list in the screen display position. This application determines the screen display position corresponding to the recommended merchant information list, and then based on the use of the display component, displays the recommended merchant information list in the screen display position, so that the user can view the pushed recommended merchant information list on the screen without opening the App, which improves the convenience of user viewing, effectively improves the intelligence of information push, and improves the user experience.

[0161] In some optional implementations of this embodiment, before step S203, the electronic device may further perform the following steps:

[0162] Draw geo-fenced areas on the map based on preset map service tools.

[0163] In this embodiment, the selection of the above-mentioned map service tool is not specifically limited, and the map service function of the map service provider can be used. The map service provider can be Google Maps, Mapbox, Baidu Maps, etc. The map service provider usually provides an API to create and manage geo-fences. Specifically, by using the map service tool provided by the map service provider, a specific area is manually drawn on the map or automatically demarcated by coordinate points to complete the division of the geo-fence area. The geo-fence area can be a circle, a polygon, or other custom shapes, depending on the support of the service provider.

[0164] Get geo-fence information of the geo-fence area.

[0165] In this embodiment, the geo-fence information may include coordinates, shape, identifier, etc. of the geo-fence area. A unique identifier (such as ID or name) is assigned to each geo-fence area for reference and query in the database.

[0166] Collect merchant information and establish association information between the merchant information and the geo-fenced area.

[0167] In this embodiment, the above-mentioned merchant information may refer to the information of the merchant included in the map, and the merchant information may include the merchant's basic information (such as name, address, contact information) and detailed content such as activities, discounts, and notifications. The merchant information may be associated with a specific geo-fenced area to obtain the association information between the merchant information and the geo-fenced area. The merchant's geographical location (latitude and longitude) may be used to determine which geo-fenced area it belongs to.

[0168] A matching rule corresponding to the merchant information is created.

[0169] In this embodiment, matching rules are set for merchant information (including merchant activities, discounts, etc.) within the geo-fenced area. These matching rules can be set based on multiple factors such as time (such as valid within a specific time period), user attributes (such as a specific user group), and activity type.

[0170] Get the target data format.

[0171] In this embodiment, the target data format may specifically adopt a Map data format, for example, may include JSON, XML and other formats.

[0172] Based on the target data format, the geo-fence information, the merchant information, the association information and the matching rule are stored in a preset initial database to obtain the database.

[0173] In this embodiment, by storing the geo-fence information, the merchant information, the association information and the matching rules in the target data format, i.e., the Map data format, in the initial database to obtain the corresponding database, it can be ensured that it can be quickly retrieved and updated. The initial database can be a newly developed blank database without data.

[0174] This application delineates a geo-fenced area on a map based on a preset map service tool; then obtains the geo-fenced information of the geo-fenced area; then collects business information, and establishes association information between the business information and the geo-fenced area; subsequently creates matching rules corresponding to the business information; further obtains the target data format; and finally based on the target data format, stores the geo-fence information, the business information, the association information, and the matching rules in a preset initial database to obtain the database. This application delineates a geo-fenced area on a map based on the use of a map service tool, then obtains the geo-fence information of the geo-fenced area, collects business information, and establishes association information between the business information and the geo-fenced area, and creates matching rules corresponding to the business information, and then based on the target data format, stores the geo-fence information, the business information, the association information, and the matching rules in a preset initial database to obtain the database, thereby achieving rapid and intelligent completion of database construction, and improving database construction efficiency and construction intelligence. This is conducive to the subsequent use of the database to query the required business information, thereby improving the efficiency of obtaining business information.

[0175] This application cleverly combines geo-fencing to push the company's products to users in a timely manner, establish efficient user stickiness, maintain timely interaction with users, and recommend the most favorable promotional products and financial products to customers. This model completely subverts the existing model in the industry, and the component display method can greatly improve practicality. In addition, the established database can be gradually improved and supplemented to become the company's data assets, providing accumulation for the company, and at the same time improving the authenticity and accuracy of the data in the process of gradual correction. The geo-fence mode allows users to more conveniently understand the company's latest activities and products, maintaining stable customer retention.

[0176] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0177] It should be emphasized that in order to further ensure the privacy and security of the above-mentioned second merchant information, the above-mentioned second merchant information can also be stored in a node of a blockchain.

[0178] The blockchain referred to in this application is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0179] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0180] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0181] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0182] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0183] Further references Figure 3 , as a response to the above Figure 2 The present application provides an embodiment of an information recommendation device based on artificial intelligence. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0184] like Figure 3 As shown, the information recommendation device 300 based on artificial intelligence described in this embodiment includes: a first acquisition module 301, a judgment module 302, a second acquisition module 303, a third acquisition module 304, a first screening module 305, a second screening module 306 and a push module 307. Among them:

[0185] The first acquisition module 301 is used to acquire the user's location information and user information;

[0186] A determination module 302 is used to determine whether the location information is within a preset target geo-fenced area;

[0187] A second acquisition module 303 is used to acquire initial merchant information corresponding to the target geo-fenced area from a pre-created database;

[0188] A third acquisition module 304 is used to acquire a user portrait of the user based on the user information;

[0189] A first screening module 305 is used to screen the initial merchant information based on the user portrait and a first preset recommendation algorithm to obtain corresponding first merchant information;

[0190] A second screening module 306, configured to screen the first merchant information based on the user portrait and a second preset recommendation algorithm to obtain corresponding second merchant information;

[0191] The push module 307 is used to push the second merchant information to the user.

[0192] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based information recommendation method in the aforementioned implementation mode, and will not be repeated here.

[0193] In some optional implementations of this embodiment, the determination module 302 includes:

[0194] The first acquisition submodule is used to acquire a plurality of preset geospatial algorithms;

[0195] A first determination module, configured to determine a target geospatial algorithm from among all the geospatial algorithms;

[0196] The first generating submodule is used to process the location information and the target geo-fence area based on the target geospatial algorithm to generate a location matching result between the location information and the target geo-fence area; wherein the location matching result includes that the location information is within the target geo-fence area, or that the location information is not within the target geo-fence area.

[0197] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based information recommendation method in the aforementioned implementation mode, and will not be repeated here.

[0198] In some optional implementations of this embodiment, the second acquisition module 303 includes:

[0199] A second acquisition submodule is used to acquire a target identifier of the target geo-fenced area;

[0200] A construction submodule, used to construct a corresponding database query statement based on the target marker;

[0201] A calling submodule, used for calling the database;

[0202] A retrieval submodule, used to execute the database query statement to retrieve corresponding third merchant information from the database;

[0203] A first screening submodule, used for screening fourth merchant information that meets the time validity condition from the third merchant information;

[0204] The second determining submodule is configured to use the fourth merchant information as the initial merchant information.

[0205] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based information recommendation method in the aforementioned implementation mode, and will not be repeated here.

[0206] In some optional implementations of this embodiment, the second screening module 306 includes:

[0207] A third acquisition submodule is used to acquire product description information corresponding to the first merchant information;

[0208] An extraction submodule, configured to perform feature extraction on the user portrait and the product description information respectively, to obtain a first feature corresponding to the user portrait and a second feature corresponding to the product description information;

[0209] A calculation submodule, configured to calculate the similarity between the first feature and the second feature based on a preset similarity algorithm to obtain a recommendation score for the first merchant information;

[0210] A second screening submodule, used to screen out a designated recommendation score greater than a preset score threshold from all the recommendation scores;

[0211] A third screening submodule, configured to screen out designated merchant information corresponding to the designated recommendation score from all the first merchant information;

[0212] The third determining submodule is configured to use the designated merchant information as the second merchant information.

[0213] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based information recommendation method in the aforementioned implementation mode, and will not be repeated here.

[0214] In some optional implementations of this embodiment, the push module 307 includes:

[0215] a deduplication submodule, configured to perform deduplication processing on the second merchant information to obtain corresponding fifth merchant information;

[0216] A fourth acquisition submodule, used to acquire a ranking factor corresponding to the fifth merchant information;

[0217] A fourth determination submodule, used to determine a preset weight corresponding to the ranking factor;

[0218] A second generating submodule, configured to generate a comprehensive score of the fifth merchant information based on the ranking factor and the preset weight;

[0219] A sorting submodule, used for sorting all the fifth merchant information in descending order based on the comprehensive scores to obtain a corresponding recommended merchant information list;

[0220] The push submodule is used to push the recommended merchant information list to the user.

[0221] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based information recommendation method in the aforementioned implementation mode, and will not be repeated here.

[0222] In some optional implementations of this embodiment, the push submodule includes:

[0223] A calling unit, used to call a preset display component;

[0224] A determination unit, used to determine a screen display position corresponding to the recommended merchant information list;

[0225] A display unit is used to display the recommended merchant information list in the screen display position based on the display component.

[0226] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based information recommendation method in the aforementioned implementation mode, and will not be repeated here.

[0227] In some optional implementations of this embodiment, the information recommendation device based on artificial intelligence further includes:

[0228] A demarcation module, used for demarcating a geographic fence area on a map based on a preset map service tool;

[0229] A fourth acquisition module, used to acquire geo-fence information of the geo-fence area;

[0230] Establishing a module for collecting merchant information and establishing association information between the merchant information and the geo-fenced area;

[0231] A creation module, used to create a matching rule corresponding to the merchant information;

[0232] A fifth acquisition module, used to acquire a target data format;

[0233] A storage module is used to store the geo-fence information, the merchant information, the association information and the matching rule in a preset initial database based on the target data format to obtain the database.

[0234] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based information recommendation method in the aforementioned implementation mode, and will not be repeated here.

[0235] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0236] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 4 with components 41-43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital processors (DSPs), embedded devices, etc.

[0237] The computer device may be a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with the user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0238] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk equipped on the computer device 4, a smart memory card (Smart Med ia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions of the information recommendation method based on artificial intelligence, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0239] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run computer-readable instructions stored in the memory 41 or process data, such as computer-readable instructions for running the information recommendation method based on artificial intelligence.

[0240] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0241] The present application also provides another embodiment, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the above-mentioned artificial intelligence-based information recommendation method.

[0242] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0243] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. An information recommendation method based on artificial intelligence, characterized in that: The steps include: Get the user's location information and user information; Determining whether the location information is within a preset target geo-fenced area; If so, obtaining initial merchant information corresponding to the target geo-fenced area from a pre-created database; Acquire a user portrait of the user based on the user information; Filtering the initial merchant information based on the user portrait and a first preset recommendation algorithm to obtain corresponding first merchant information; Filtering the first merchant information based on the user portrait and a second preset recommendation algorithm to obtain corresponding second merchant information; The second merchant information is pushed to the user.

2. The information recommendation method based on artificial intelligence according to claim 1, characterized in that: The step of determining whether the location information is within a preset target geo-fenced area specifically includes: Get multiple preset geospatial algorithms; determining a target geospatial algorithm from among all of the geospatial algorithms; The location information and the target geofence area are processed based on the target geospatial algorithm to generate a location matching result between the location information and the target geofence area; wherein the location matching result includes that the location information is within the target geofence area, or that the location information is not within the target geofence area.

3. The information recommendation method based on artificial intelligence according to claim 1, characterized in that: The step of acquiring the initial merchant information corresponding to the target geo-fenced area from a pre-created database specifically includes: Obtain a target identifier of the target geo-fenced area; Constructing a corresponding database query statement based on the target identifier; calling the database; Executing the database query statement to retrieve corresponding third merchant information from the database; Filtering fourth merchant information that meets the time validity condition from the third merchant information; The fourth merchant information is used as the initial merchant information.

4. The information recommendation method based on artificial intelligence according to claim 1, characterized in that: The step of screening the first merchant information based on the user portrait and the second preset recommendation algorithm to obtain the corresponding second merchant information specifically includes: Obtaining product description information corresponding to the first merchant information; Extracting features from the user portrait and the product description information respectively to obtain a first feature corresponding to the user portrait and a second feature corresponding to the product description information; Calculating the similarity between the first feature and the second feature based on a preset similarity algorithm to obtain a recommendation score for the first merchant information; Filtering out a designated recommendation score greater than a preset score threshold from all the recommendation scores; Filtering out designated merchant information corresponding to the designated recommendation score from all the first merchant information; The designated merchant information is used as the second merchant information.

5. The information recommendation method based on artificial intelligence according to claim 1, characterized in that: The step of pushing the second merchant information to the user specifically includes: Deduplication processing is performed on the second merchant information to obtain corresponding fifth merchant information; Obtaining a ranking factor corresponding to the fifth merchant information; Determining preset weights corresponding to the ranking factors; generating a comprehensive score for the fifth merchant information based on the ranking factor and the preset weight; Sorting all the fifth merchant information in descending order based on the comprehensive scores to obtain a corresponding recommended merchant information list; The recommended merchant information list is pushed to the user.

6. The information recommendation method based on artificial intelligence according to claim 5, characterized in that: The step of pushing the recommended merchant information list to the user specifically includes: Call the preset display component; Determining a screen display position corresponding to the recommended merchant information list; Based on the display component, the recommended merchant information list is displayed in the screen display position.

7. The information recommendation method based on artificial intelligence according to claim 1, characterized in that: Before the step of acquiring the initial merchant information corresponding to the target geo-fenced area from the pre-created database, the method further includes: Delineate geo-fenced areas on a map based on a preset map service tool; Obtaining geo-fence information of the geo-fence area; Collecting merchant information and establishing association information between the merchant information and the geo-fenced area; Creating a matching rule corresponding to the merchant information; Get the target data format; Based on the target data format, the geo-fence information, the merchant information, the association information and the matching rule are stored in a preset initial database to obtain the database.

8. An information recommendation device based on artificial intelligence, characterized in that: include: A first acquisition module, used to acquire the user's location information and user information; A determination module, used to determine whether the location information is within a preset target geographic fence area; A second acquisition module is used to acquire initial merchant information corresponding to the target geo-fenced area from a pre-created database; A third acquisition module, used to acquire a user portrait of the user based on the user information; A first screening module, configured to screen the initial merchant information based on the user portrait and a first preset recommendation algorithm to obtain corresponding first merchant information; A second screening module, configured to screen the first merchant information based on the user portrait and a second preset recommendation algorithm to obtain corresponding second merchant information; A push module is used to push the second merchant information to the user.

9. A computer device, characterized in that: It comprises a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the information recommendation method based on artificial intelligence as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the artificial intelligence-based information recommendation method according to any one of claims 1 to 7.

Images