Business district discount information and vehicle scene recommendation system

Abstract

The invention, which relates to the technical field of information recommendation, discloses a commercial district discount information and in-vehicle scene recommendation system comprising a discount information module, a discount acquisition module, a discount recommendation module, a commercial district judgment module, a distance calculation module and a discount preference module. The discount collection module obtains discount information of each business district based on the big data and uploads the obtained discount information to the discount information module, and the discount information module stores the obtained information; and the discount preference module obtains discount information data frequently watched by the user, performs preference setting on preferences of the user, and intelligently recommends discount information of favorite commodities for the user. According to the invention, the user is prevented from self-screening in mass information, the time and energy are greatly saved, the user can timely obtain the surrounding consumable discount information in the travel process, the discount information is comprehensively collected and highly utilized, the information is timely released, and the consumption behavior of the user is facilitated.

Description

Technical Field

[0001] The present invention relates to the technical field of information recommendation, and in particular to a system for recommending business district discount information and vehicle scenarios. Background Art

[0002] In today's society, people's pace of life is accelerating, and the demand for travel is growing. With the continuous increase in the number of cars, the car system plays an increasingly important role in people's travel. On the one hand, modern consumers pay more and more attention to cost-effectiveness when shopping and consuming, and have a strong demand for discount information in the business district. In order to attract customers, merchants in the business district will launch various forms of discount activities, but consumers often find it difficult to obtain this information in a comprehensive and timely manner. The disadvantage of the existing technology is that it only displays discount information on its own platform, and consumers who happen to pass by it during driving cannot know the discount information in a timely manner. Only when I actively open the mini program or official account of the corresponding shopping mall can I passively search for discount information, and the information is across multiple platforms and not concentrated. In this regard, we propose a business district discount information and car-machine scenario recommendation system. Summary of the invention

[0003] In order to solve the above technical problems, a shopping district discount information and vehicle scenario recommendation system is provided. This technical solution solves the above-mentioned problems of incomplete highway information collection, low utilization of effective information, and untimely information release.

[0004] To achieve the above objectives, the technical solution adopted by the present invention is: a shopping district discount information and vehicle scenario recommendation system, including: a discount information module, a discount collection module, a discount recommendation module, a shopping district judgment module, a distance calculation module and a discount preference module;

[0005] The discount collection module obtains discount information of each business district based on big data, uploads the obtained discount information to the discount information module, and the discount information module stores the obtained information;

[0006] The discount preference module obtains the discount information data that users often view, sets preferences based on users’ preferences, and intelligently recommends discount information for favorite products to users;

[0007] The business district judgment module obtains the navigation route of the vehicle computer and determines whether there is business district information in the navigation route;

[0008] When there is a business district in the navigation route of the vehicle computer, the discount information in the discount information module is intelligently recommended based on the discount preference module;

[0009] After the user selects the recommended discount information, the distance calculation module calculates the distance between the current vehicle location and the business district, and selects the nearest route option for the user, allowing the user to shop within the business district.

[0010] Preferably, the discount collection module is based on network big data technology and obtains discount information of various business districts from multiple channels, including the Internet, offline advertising and television promotion. After the discount collection module successfully obtains the discount information of various business districts, the information is preliminarily sorted and screened to remove duplicate, invalid and expired discount information, and the screened information is uploaded to the discount information module for storage.

[0011] Preferably, the discount preference module obtains discount information data that users often view based on vehicle computer data and records the user's browsing history. When the user views discount information on specific products in a business district, or repeatedly browses promotional activities for a certain type of product, the discount preference module captures and records this information, analyzes the collected user data, and extracts the user's consumption preference characteristics based on data mining and machine learning algorithms.

[0012] Preferably, the calculation formula for user consumption preference characteristics is:

[0013] y=w 1 *a+w 2 *b

[0014] y is the current commodity consumption preference characteristic value, a is the browsing time of the commodity category, b is the number of browsing times of the commodity category, w 1 With w 2 is the corresponding weight value. The user's preference characteristics for different types of commodity consumption are determined by calculation. Based on the analysis, the threshold of the preference characteristics of commodity consumption is obtained. After comparing the threshold with the calculated y value, the type of commodity preferred by the user is determined, and the user's preferred commodities are extracted.

[0015] Preferably, the business district judgment module obtains the navigation route information of the current vehicle from the vehicle navigation line. The navigation route information includes the starting point, the end point, and detailed geographical location data of each section and intersection passed through. After obtaining the navigation route, the business district judgment module conducts an in-depth scan and analysis of the area covered by this route. Based on the algorithm and database information, it carefully searches and determines whether there is any business district-related information within the entire navigation route. After discovering a business district, it will try to obtain more detailed content such as the number of stores in the business district, the names of the main stores, and the parking lot information, so as to provide more comprehensive and valuable data support for subsequent related applications.

[0016] Preferably, based on the algorithm and database information calculation and analysis, let the current vehicle location be P(x, z), for n known business district centers C i (x i , z i ) where i is 1, 2, ... n, and the distance from point P to the center of the business district C is calculated. iThe distance is:

[0017]

[0018] Where d is the distance between two points;

[0019] Each business district center C i The corresponding business scale weight is w i The weight is determined based on the area of ​​the business district, the number of stores and the turnover. The influence of the business district is calculated using the following formula:

[0020]

[0021] Among them I i d i is the calculated influence result value, k is the distance attenuation coefficient, and when the distance d is 0, its influence is the largest, and as the distance increases, the influence decreases.

[0022] Preferably, the formula for determining the comprehensive information of the business district is:

[0023]

[0024] Among them, IP is the comprehensive influence value. The influence threshold of the business district is obtained based on big data, and the threshold is compared with the calculated IP result. If it is greater than the threshold, it is judged that the current location of the vehicle exists in the business district.

[0025] Preferably, after determining that there is a business district at the current location of the vehicle, the discount information stored in the discount information module is filtered based on the user's commodity consumption preference value analyzed by the discount preference module, and the commodity discounts that meet the current user's preferences are filtered out, and intelligent recommendations are made based on the vehicle computer for the user to browse and filter.

[0026] Preferably, after the user selects the recommended discount information, the distance calculation module obtains the real-time location information of the current vehicle, including detailed longitude and latitude geographic coordinate data, obtains the location information of the currently selected business district from a pre-stored business district database, obtains its geographic location coordinates, and navigates the vehicle to the selected business district.

[0027] Preferably, based on the Euclidean distance formula, the distance between the current vehicle position and each business district is calculated, and based on the navigation taking into account the actual traffic conditions, road types and existing traffic restrictions, the shortest path is estimated to navigate the user to the business district.

[0028] Compared with the prior art, the present invention has the following beneficial effects:

[0029] The present invention sets preferences by analyzing discount information data that users often view through a discount preference module, and can deeply understand the commodity categories and brands that users are really interested in. This enables the recommendation system to intelligently recommend discount information of their favorite commodities to users, avoiding users from filtering through massive amounts of information by themselves, greatly saving time and energy. The business district judgment module is combined with the navigation route to determine the business district information around the user's driving route. After determining that there is a business district, the discount information is recommended in combination with the discount preference module. Users can obtain the surrounding consumable discount information in time during the travel process. The discount information is collected comprehensively, the utilization is high, and the information is released in time, which facilitates the user's consumption behavior. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 The following is a system framework diagram recommended by the present invention. DETAILED DESCRIPTION

[0031] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0032] Reference Figure 1 As shown, a shopping district discount information and vehicle scenario recommendation system includes: a discount information module, a discount collection module, a discount recommendation module, a shopping district judgment module, a distance calculation module and a discount preference module;

[0033] The discount collection module obtains discount information of each business district based on big data, uploads the obtained discount information to the discount information module, and the discount information module stores the obtained information;

[0034] The discount preference module obtains the discount information data that users often view, sets preferences based on users’ preferences, and intelligently recommends discount information for favorite products to users;

[0035] The business district judgment module obtains the navigation route of the vehicle computer and determines whether there is business district information in the navigation route;

[0036] When there is a business district in the navigation route of the vehicle computer, the discount information in the discount information module is intelligently recommended based on the discount preference module;

[0037] After the user selects the recommended discount information, the distance calculation module calculates the distance between the current vehicle location and the business district, and selects the nearest route option for the user, allowing the user to shop within the business district.

[0038] The discount collection module of this application collects discount information of various business districts through big data and stores it in the discount information module. Consumers do not need to search for discounts in different business districts through multiple channels. All information is concentrated on one platform. At the same time, the discount preference module determines the preferences of users based on the discount information they often see, and intelligently recommends discounts for their favorite products, which avoids consumers from screening in massive amounts of information, saving a lot of time and energy. Consumers can choose the nearest route to go to the business district for consumption, reducing travel time and cost, and indirectly increasing consumers' satisfaction with the entire consumption process;

[0039] The business district judgment module combines the car navigation route to judge the business district information. When there is a business district in the navigation route, intelligent recommendations based on discount preferences enable consumers to obtain discounts in the surrounding area in a timely manner during their travels. This personalized discount recommendation and convenient navigation route planning function provide users with a high-quality service experience, increase users' dependence on the platform and frequency of use, and improve user stickiness.

[0040] The discount collection module is based on network big data technology and obtains discount information of various business districts from multiple channels, including the Internet, offline advertising and television promotion. After the discount collection module successfully obtains the discount information of various business districts, it preliminarily organizes and screens the information, removes duplicate, invalid and expired discount information, and uploads the screened information to the discount information module for storage.

[0041] This application collects discount information through multiple channels, including the Internet, offline advertising and television promotions. Consumers can obtain more comprehensive discount information in business districts, whether it is discounts on online shopping platforms, promotional advertisements posted by offline stores, or commercial activity discounts mentioned in TV commercials. All can be integrated. The initial sorting and screening process removes duplicate, invalid and expired information to ensure that consumers receive accurate and useful discount content, so that consumers can find truly valuable discounts more efficiently and avoid being disturbed by a large amount of useless information. This eliminates the need for consumers to run around between various channels to search, and they can get all discount information in one stop.

[0042] The discount preference module obtains the discount information data that users often view based on the vehicle computer data and records the user's browsing history. When the user views the discount information of specific products in the business district, or repeatedly browses the promotional activities of a certain type of product, the discount preference module captures and records it, analyzes the collected user data, and extracts the user's consumption preference characteristics based on data mining and machine learning algorithms.

[0043] This application can provide users with highly personalized discount information recommendations by recording users' browsing history and analyzing consumption preference characteristics. If users frequently browse discount information of sports brands, the system will focus on pushing discounts on sports-related products. Users do not need to sift through a large amount of irrelevant promotional information, but can directly see discounts on products that they are interested in, which greatly improves the user experience. In the process of shopping decisions, users no longer need to spend a lot of time looking for discounts on products that suit their preferences.

[0044] The calculation formula for user consumption preference characteristics is:

[0045] y=w 1 *a+w 2 *b

[0046] y is the current commodity consumption preference characteristic value, a is the browsing time of the commodity category, b is the number of browsing times of the commodity category, w 1 With w 2 is the corresponding weight value. The user's preference characteristics for different types of commodity consumption are determined by calculation. Based on the analysis, the threshold of the preference characteristics of commodity consumption is obtained. After comparing the threshold with the calculated y value, the type of commodity preferred by the user is determined, and the user's preferred commodities are extracted.

[0047] The business district judgment module obtains the navigation route information of the current vehicle from the vehicle navigation line. The navigation route information includes the starting point, the end point, and the detailed geographic location data of each section and intersection along the way. After obtaining the navigation route, the business district judgment module conducts an in-depth scan and analysis of the area covered by this route. Based on the algorithm and database information, it carefully searches and determines whether there is any business district-related information within the entire navigation route. After discovering a business district, it will try to obtain more detailed information about the number of stores in the business district, the names of the main stores, and the parking lot information, so as to provide more comprehensive and valuable data support for subsequent related applications.

[0048] The users of this application may have various needs during their travels, such as dining, shopping, and leisure. By understanding the business district information in the navigation route, users can quickly find places that meet these needs and receive discount recommendations for consumption, making their travel more convenient.

[0049] Based on the algorithm and database information calculation and analysis, let the current vehicle location be P(x, z), for n known business district centers C i (x i , z i ) where i is 1, 2, ... n, and the distance from point P to the center of the business district C is calculated. i The distance is:

[0050]

[0051] Where d is the distance between two points;

[0052] Each business district center C i The corresponding business scale weight is w i The weight is determined based on the area of ​​the business district, the number of stores and the turnover. The influence of the business district is calculated using the following formula:

[0053]

[0054] Among them I i d i is the calculated influence result value, k is the distance attenuation coefficient, and when the distance d is 0, its influence is the largest, and as the distance increases, the influence decreases.

[0055] The formula for judging the comprehensive information of the business district is:

[0056]

[0057] Among them, IP is the comprehensive influence value. The influence threshold of the business district is obtained based on big data, and the threshold is compared with the calculated IP result. If it is greater than the threshold, it is judged that the current location of the vehicle exists in the business district.

[0058] After determining that there is a business district at the current location of the vehicle, the discount information stored in the discount information module is filtered based on the user's product consumption preference value analyzed by the discount preference module, and the product discounts that meet the current user's preferences are screened out, and intelligent recommendations are made based on the vehicle computer for users to browse and filter.

[0059] Users of this application do not need to search for content of interest among a large amount of disorganized discount information. The system filters according to the user's product consumption preference value and only presents product discounts that meet the user's preferences, making the information received by the user highly personalized. Accurately recommended discount information increases the possibility of users finding their favorite products and enjoying discounts. When users can buy their favorite products at a lower price, consumer satisfaction will be significantly improved, thereby enhancing the user's trust and reliance on the entire recommendation system.

[0060] After the user selects the recommended discount information, the distance calculation module obtains the real-time location information of the current vehicle, including detailed longitude and latitude geographic coordinate data, obtains the location information of the currently selected business district from the pre-stored business district database, obtains its geographic location coordinates, and navigates the vehicle to the selected business district.

[0061] Users of this application do not need to manually enter destination information. The system automatically navigates according to the business district location corresponding to the selected discount information, which greatly simplifies the operation process and enables users to reach their destination more conveniently. Accurate distance calculation and navigation help to select the optimal route, reduce mileage and time, and thus reduce fuel consumption or vehicle energy consumption costs. For users, this means that while enjoying shopping discounts, they can also achieve a certain degree of savings in travel costs.

[0062] Based on the Euclidean distance formula, the distance between the current vehicle position and each business district is calculated. Based on the navigation, the actual traffic conditions, road types and existing traffic restrictions are taken into account, and the shortest path is estimated to navigate the user to the business district.

[0063] The Euclidean distance formula in this application is a prior art and will not be elaborated on here. Considering actual traffic conditions, such as congestion, road types, such as highways, urban main roads, branch roads, and traffic restrictions, such as one-way streets and restricted areas, calculating distances and planning the shortest path can effectively reduce the time users spend on the road. Users can reach the business district faster and have more time to spend shopping or enjoying the services in the business district.

[0064] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments, and the above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention, and these changes and improvements fall within the scope of the present invention claimed.

Claims

1. A shopping district discount information and vehicle scenario recommendation system, characterized in that: include: Discount information module, discount collection module, discount recommendation module, business district judgment module, distance calculation module and discount preference module; The discount collection module obtains discount information of each business district based on big data, uploads the obtained discount information to the discount information module, and the discount information module stores the obtained information; The discount preference module obtains the discount information data that users often view, sets preferences based on users’ preferences, and intelligently recommends discount information for favorite products to users; The business district judgment module obtains the navigation route of the vehicle computer and determines whether there is business district information in the navigation route; When there is a business district in the navigation route of the vehicle computer, the discount information in the discount information module is intelligently recommended based on the discount preference module; After the user selects the recommended discount information, the distance calculation module calculates the distance between the current vehicle location and the business district, and selects the nearest route option for the user, allowing the user to shop within the business district.

2. A shopping district discount information and vehicle scenario recommendation system according to claim 1, characterized in that: The discount collection module is based on network big data technology and obtains discount information of various business districts from multiple channels, including the Internet, offline advertising and television promotion; After the discount collection module successfully obtains the discount information of each business district, it preliminarily organizes and screens the information, removes duplicate, invalid and expired discount information, and uploads the screened information to the discount information module for storage.

3. The shopping district discount information and vehicle scenario recommendation system according to claim 1, characterized in that: The discount preference module obtains the discount information data that users often view based on the vehicle computer data and records the user's browsing history. When the user views the discount information of specific products in the business district, or repeatedly browses the promotional activities of a certain type of product, the discount preference module captures and records it, analyzes the collected user data, and extracts the user's consumption preference characteristics based on data mining and machine learning algorithms.

4. The shopping district discount information and vehicle scenario recommendation system according to claim 3, characterized in that: The calculation formula for user consumption preference characteristics is: y=w1*a+w2*b y is the current commodity consumption preference characteristic value, a is the browsing time of the commodity category, b is the browsing times of the commodity category, w1 and w2 are the corresponding weight values. The user's consumption preference characteristics for different types of commodities are determined by calculation. Based on the analysis, the commodity consumption preference characteristic threshold is obtained. After comparing the threshold with the calculated y value, the user's preferred commodity category is determined, and the user's preferred commodities are extracted.

5. The shopping district discount information and vehicle scenario recommendation system according to claim 1, characterized in that: The business district judgment module obtains the navigation route information of the current vehicle from the vehicle navigation line. The navigation route information includes the starting point, the end point, and the detailed geographic location data of each section and intersection along the way. After obtaining the navigation route, the business district judgment module conducts an in-depth scan and analysis of the area covered by this route. Based on the algorithm and database information, it carefully searches and determines whether there is any business district-related information within the entire navigation route. After discovering a business district, it will try to obtain more detailed information about the number of stores in the business district, the names of the main stores, and the parking lot information, so as to provide more comprehensive and valuable data support for subsequent related applications.

6. A shopping district discount information and vehicle scenario recommendation system according to claim 5, characterized in that: Based on the algorithm and database information calculation and analysis, let the current vehicle location be P(x, z), for n known business district centers C i (x i , z i ) where i is 1, 2, ... n, and the distance from point P to the center of the business district C is calculated. i The distance is: Where d is the distance between two points; Each business district center C i The corresponding business scale weight is w i The weight is determined based on the area of ​​the business district, the number of stores and the turnover. The influence of the business district is calculated using the following formula: Among them I i d i is the calculated influence result value, k is the distance attenuation coefficient, and when the distance d is 0, its influence is the largest, and as the distance increases, the influence decreases.

7. The shopping district discount information and vehicle scenario recommendation system according to claim 6, characterized in that: The formula for judging the comprehensive information of the business district is: Among them, IP is the comprehensive influence value. The influence threshold of the business district is obtained based on big data, and the threshold is compared with the calculated IP result. If it is greater than the threshold, it is judged that the current location of the vehicle exists in the business district.

8. The shopping district discount information and vehicle scenario recommendation system according to claim 1, characterized in that: After determining that there is a business district at the current location of the vehicle, the discount information stored in the discount information module is filtered based on the user's product consumption preference value analyzed by the discount preference module, and the product discounts that meet the current user's preferences are screened out, and intelligent recommendations are made based on the vehicle computer for users to browse and filter.

9. The shopping district discount information and vehicle scenario recommendation system according to claim 1, characterized in that: After the user selects the recommended discount information, the distance calculation module obtains the real-time location information of the current vehicle, including detailed longitude and latitude geographic coordinate data, obtains the location information of the currently selected business district from the pre-stored business district database, obtains its geographic location coordinates, and navigates the vehicle to the selected business district.

10. A shopping district discount information and vehicle scenario recommendation system according to claim 9, characterized in that: Based on the Euclidean distance formula, the distance between the current vehicle position and each business district is calculated. Based on the navigation, the actual traffic conditions, road types and existing traffic restrictions are taken into account, and the shortest path is estimated to navigate the user to the business district.

Images