Geographic position recommendation method and system based on positioning technology

Abstract

The invention belongs to the technical field of positioning, and particularly discloses a geographic position recommendation method and system based on a positioning technology, and the method comprises the steps: detecting a stop point of a shopper in a supermarket shelf based on an LED positioning principle; finding the interest point of the shopper according to the staying time at the staying point; obtaining the preference degree of the shopper to the interest point; a shelf is used as a positioning unit, after interests and preferences of shoppers are obtained based on activity tracks of the shoppers in a supermarket, a collaborative filtering algorithm is adopted for preference information, shoppers with similar interests are found, and recommendation is carried out on the supermarket.

Description

Technical Field

[0001] This invention belongs to the field of positioning technology, and in particular relates to a method and system for recommending geographical locations based on positioning technology. Background Technology

[0002] Existing research on supermarket item recommendation algorithms largely focuses on combining supermarket / shopper tags, shopper activity, and visualization techniques with collaborative filtering algorithms. While these studies have yielded some results, they struggle to produce accurate recommendations when data is sparse. Therefore, there is an urgent need to propose a location-based recommendation method to address these technical challenges. Summary of the Invention

[0003] This invention provides a location-based recommendation method and system based on positioning technology, which solves the problem that existing supermarket item recommendation methods struggle to make correct recommendations when using collaborative filtering algorithms in the case of sparse data.

[0004] Firstly, a location recommendation method based on positioning technology is provided, the method comprising:

[0005] Detecting the shopper's stopping point on supermarket shelves based on LED positioning principle;

[0006] Discover shoppers' interests by analyzing the time they spend at each point of interest;

[0007] To determine how much shoppers like or dislike a particular point of interest;

[0008] Using shelves as the location unit, and based on the shopper's activity trajectory in the supermarket to obtain the shopper's interests and preferences, the preference information is used to apply a collaborative filtering algorithm to discover shoppers with similar interests and make recommendations to the supermarket.

[0009] Secondly, a location recommendation system based on positioning technology is provided, the system comprising:

[0010] The dwell point detection module is used to detect the dwell points of shoppers on supermarket shelves based on the LED positioning principle;

[0011] The point of interest discovery module is used to discover shoppers' points of interest based on the time spent at each stop point;

[0012] The preference level acquisition module is used to obtain the shopper's preference level for points of interest;

[0013] The supermarket recommendation module uses shelves as the location unit. Based on the shopper's activity trajectory in the supermarket, it obtains the shopper's interests and preferences. Then, it uses a collaborative filtering algorithm to find shoppers with similar interests and makes recommendations to the supermarket.

[0014] This invention provides a location-based recommendation method and system based on positioning technology. The supermarket recommendation algorithm based on indoor positioning uses shelves as positioning units. It obtains shoppers' interests and preferences based on their activity trajectories in the supermarket, and introduces the preference information into a user-based collaborative filtering algorithm to discover shoppers with similar interests and make recommendations accordingly. This can effectively solve the data sparsity problem in supermarket recommendation systems and provide shoppers with location-related personalized supermarket recommendations.

[0015] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this invention, illustrate exemplary embodiments of the invention and are used to explain the invention, but do not constitute an undue limitation of the invention. In the drawings:

[0017] Figure 1 This is a schematic diagram illustrating the implementation process of a location recommendation method based on positioning technology according to an embodiment of the present invention;

[0018] Figure 2 This is a schematic diagram illustrating the visible light communication and positioning principle according to an embodiment of the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this specification clearer, the technical solutions of this specification will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, and not all of them. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort are within the protection scope of this specification.

[0020] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, apparatus, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0021] The technical solutions provided in the various embodiments of this specification are described in detail below with reference to the accompanying drawings.

[0022] To improve the ability to recommend supermarkets to shoppers in a personalized way, embodiments of the present invention provide a location-based recommendation method and system based on location technology.

[0023] Figure 1 This is a schematic diagram illustrating the implementation process of a location-based recommendation method according to an embodiment of the present invention. (See also...) Figure 1 The method includes:

[0024] S100: Detects the shopper's stopping point on supermarket shelves based on LED positioning principle;

[0025] S102: Discover shoppers' interests based on the time spent at their stops;

[0026] S104: Obtain the shopper's level of preference for points of interest;

[0027] S106: Using the shelf as the positioning unit, after obtaining the shopper's interests and preferences based on the shopper's activity trajectory in the supermarket, the preference information is used to discover shoppers with similar interests and make recommendations to the supermarket.

[0028] In one specific implementation, at the signal transmitting end, the information to be transmitted is compiled into a modulated signal and applied to the driving current of the LED lamp using pulse width modulation. The LED light source flashes at a high frequency according to the signal, propagating the signal. At the signal receiving end, the signal receiving module receives the optical signal carrying the information, and recovers the original signal after signal processing such as decoding and demodulation. After obtaining the original signal, the position of the moving target is analyzed by a positioning algorithm. The positioning principle is as follows: Figure 2 As shown.

[0029] In one specific implementation, the step of detecting the shopper's stopping point on the supermarket shelf based on the LED positioning principle specifically includes:

[0030] As shoppers stand in front of the supermarket shelves, browsing and selecting items, their mobile phones equipped with positioning systems can automatically turn on their cameras, communicate with the surrounding LED lights, and complete the shopper's location function, placing the shopper at their current point on the supermarket map.

[0031] The positioning system records shoppers' movement trajectories and the time spent in each area in real time, ultimately forming the shopper's activity trajectory within the supermarket. This trajectory consists of a series of stop points, and a shopper's historical activity trajectory within the supermarket can be expressed as a sequence of stop points using the following formula:

[0032]

[0033] Where: p i Indicates the point where the shopper stops; Δt i This indicates the time spent at each point in time. These points capture key aspects of shopper behavior and prepare the data for subsequent processing.

[0034] In one specific implementation, the step of identifying the shopper's points of interest based on the time spent at the stop point specifically includes:

[0035] To determine whether a given point is a point of interest, a constraint value must be set. If a shopper spends more than or equal to this constraint value at that point, then the shopper is interested in the items on the shelf corresponding to that point; otherwise, they are not. The constraint value is defined considering the shopper's past shopping habits, as shown in the following formulas:

[0036]

[0037] T u =min(T) u,j (1≤j≤m);

[0038]

[0039] Wherein: T u,j Δt represents the shortest time shopper u spends in front of the shelf when purchasing a single item during their j-th visit to the supermarket; S is the set of shelves corresponding to the set of items purchased by shopper u during their j-th visit to the supermarket; Δt j,p∈S This indicates the time shopper u spends in front of shelf p during their jth visit to the supermarket; n j,p T represents the number of items purchased by shopper u on the supermarket shelf p during shopper u's j-th visit; u This represents the shortest time reader u spent at the supermarket during their m previous visits to purchase a single item; F u This represents the number of times shopper u has visited the supermarket and made purchases; m is an empirical value, and if shopper u's number of visits to the supermarket is greater than or equal to m, then the constraint value T is...const It's T u If shopper u visits the supermarket less than m times, then the constraint value T is... const It equals 'a'; 'a' is a constant, referring to all previous shoppers T. const The minimum value;

[0040] Determine the constraint value T const Then, determine the current stopping point p. i The formula for determining whether something is a point of interest is:

[0041]

[0042] Where: IP is the set of shopper's points of interest. When the shopper stays for a period of time greater than or equal to the constraint value, the current point is the shopper's point of interest.

[0043] In one specific implementation, obtaining the shopper's preference for points of interest specifically includes:

[0044] The score is obtained by calculating the shopper's preference for the current point of interest using the following formula. i :

[0045]

[0046] Among them, score i The higher the value, the greater the shopper's liking for the current point of interest i.

[0047] In one specific implementation, after obtaining the shopper's interests and preferences based on the shopper's activity trajectory in the supermarket, using the shelf as the positioning unit, the preference information is applied to a collaborative filtering algorithm to discover shoppers with similar interests and to make recommendations to the supermarket. This specifically includes:

[0048] The similarity between shoppers can be obtained using the Pearson correlation coefficient method according to the following formula:

[0049]

[0050] Where sim(x,y) represents the similarity between shopper x and shopper y; r x,s S represents the rating of shopper x for point of interest s; xy This represents the set of interest points that shoppers x and y jointly rate; and This represents the average ratings of shopper x and shopper y for all points of interest;

[0051] Based on the similarity between shoppers, the Top-N recommendation method is used to select the K shoppers who are most similar to the current shopper;

[0052] The weighted average method is used to calculate the shopper's predicted future rating for item k:

[0053]

[0054] Among them, P u,k NB is the predicted rating of shopper u for item k; NB is the set of neighboring shoppers of shopper u.

[0055] The goal is to select the M items with the highest predicted ratings from current shoppers and recommend them to them, thereby attracting shoppers to this supermarket to purchase these M items.

[0056] Based on the same inventive concept, the present invention also provides a geolocation recommendation system based on positioning technology, the system comprising:

[0057] The dwell point detection module is used to detect the dwell points of shoppers on supermarket shelves based on the LED positioning principle;

[0058] The point of interest discovery module is used to discover shoppers' points of interest based on the time spent at each stop point;

[0059] The preference level acquisition module is used to obtain the shopper's preference level for points of interest;

[0060] The supermarket recommendation module uses shelves as the location unit. Based on the shopper's activity trajectory in the supermarket, it obtains the shopper's interests and preferences. Then, it uses a collaborative filtering algorithm to find shoppers with similar interests and makes recommendations to the supermarket.

[0061] In one specific embodiment, the dwell point detection module is specifically used for:

[0062] As shoppers stand in front of the supermarket shelves, browsing and selecting items, their mobile phones equipped with positioning systems can automatically turn on their cameras, communicate with the surrounding LED lights, and complete the shopper's location function, placing the shopper at their current point on the supermarket map.

[0063] The positioning system records shoppers' movement trajectories and the time spent in each area in real time, ultimately forming the shopper's activity trajectory within the supermarket. This trajectory consists of a series of stop points, and a shopper's historical activity trajectory within the supermarket can be expressed as a sequence of stop points using the following formula:

[0064]

[0065] Where: p i Indicates the point where the shopper stops; Δt i This indicates the time spent at each point in time. These points capture key aspects of shopper behavior and prepare the data for subsequent processing.

[0066] In one specific implementation, the point of interest discovery module is specifically used for:

[0067] To determine whether a given point is a point of interest, a constraint value must be set. If a shopper spends more than or equal to this constraint value at that point, then the shopper is interested in the items on the shelf corresponding to that point; otherwise, they are not. The constraint value is defined considering the shopper's past shopping habits, as shown in the following formulas:

[0068]

[0069] T u =min(T) u,j (1≤j≤m);

[0070]

[0071] Wherein: T u,j Δt represents the shortest time shopper u spends in front of the shelf when purchasing a single item during their j-th visit to the supermarket; S is the set of shelves corresponding to the set of items purchased by shopper u during their j-th visit to the supermarket; Δt j,p∈S This indicates the time shopper u spends in front of shelf p during their jth visit to the supermarket; n j,p T represents the number of items purchased by shopper u on the supermarket shelf p during shopper u's j-th visit; u This represents the shortest time reader u spent at the supermarket during their m previous visits to purchase a single item; F u This represents the number of times shopper u has visited the supermarket and made purchases; m is an empirical value, and if shopper u's number of visits to the supermarket is greater than or equal to m, then the constraint value T is... const It's T u If shopper u visits the supermarket less than m times, then the constraint value T is... const It equals 'a'; 'a' is a constant, referring to all previous shoppers T. const The minimum value;

[0072] Determine the constraint value T const Then, determine the current stopping point p. i The formula for determining whether something is a point of interest is:

[0073]

[0074] Where: IP is the set of shopper's points of interest. When the shopper stays for a period of time greater than or equal to the constraint value, the current point is the shopper's point of interest.

[0075] In one specific implementation, the preference level acquisition module is specifically used for:

[0076] The score is obtained by calculating the shopper's preference for the current point of interest using the following formula. i :

[0077]

[0078] Among them, score i The higher the value, the greater the shopper's liking for the current point of interest i.

[0079] In one specific implementation, the supermarket recommendation module is specifically used for:

[0080] The similarity between shoppers can be obtained using the Pearson correlation coefficient method according to the following formula:

[0081]

[0082] Where sim(x,y) represents the similarity between shopper x and shopper y; r x,s S represents the rating of shopper x for point of interest s; xy This represents the set of interest points that shoppers x and y jointly rate; and This represents the average ratings of shopper x and shopper y for all points of interest;

[0083] Based on the similarity between shoppers, the Top-N recommendation method is used to select the K shoppers who are most similar to the current shopper;

[0084] The weighted average method is used to calculate the shopper's predicted future rating for item k:

[0085]

[0086] Among them, P u,k NB is the predicted rating of shopper u for item k; NB is the set of neighboring shoppers of shopper u.

[0087] The goal is to select the M items with the highest predicted ratings from current shoppers and recommend them to them, thereby attracting shoppers to this supermarket to purchase these M items.

[0088] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the invention.

[0089] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A geolocation recommendation method based on positioning technology, characterized in that, The method includes: Detecting the shopper's stopping point on supermarket shelves based on LED positioning principle; Discover shoppers' interests by analyzing the time they spend at each point of interest; To determine how much shoppers like or dislike a particular point of interest; Using shelves as the location unit, and based on the shopper's activity trajectory in the supermarket to obtain the shopper's interests and preferences, the preference information is used to apply a collaborative filtering algorithm to discover shoppers with similar interests and make recommendations to the supermarket.

2. The method according to claim 1, characterized in that, The method of detecting the shopper's stopping point on supermarket shelves based on the LED positioning principle specifically includes: As shoppers stand in front of the supermarket shelves, browsing and selecting items, their mobile phones equipped with positioning systems can automatically turn on their cameras, communicate with the surrounding LED lights, and complete the shopper's location function, placing the shopper at their current point on the supermarket map. The positioning system records shoppers' movement trajectories and the time spent in each area in real time, ultimately forming the shopper's activity trajectory within the supermarket. This trajectory consists of a series of stop points, and a shopper's historical activity trajectory within the supermarket can be expressed as a sequence of stop points using the following formula: Where: p i Indicates the point where the shopper stops; Δt i This indicates the time spent at each point in time. These points capture key aspects of shopper behavior and prepare the data for subsequent processing.

3. The method according to claim 2, characterized in that, The method of identifying shoppers' interests based on the time spent at each stop point specifically includes: To determine whether a given point is a point of interest, a constraint value must be set. If a shopper spends more than or equal to this constraint value at that point, then the shopper is interested in the items on the shelf corresponding to that point; otherwise, they are not. The constraint value is defined considering the shopper's past shopping habits, as shown in the following formulas: T u =min(T u,j )(1≤j≤m); Wherein: T u,j Δt represents the shortest time shopper u spends in front of the shelf when purchasing a single item during their j-th visit to the supermarket; S is the set of shelves corresponding to the set of items purchased by shopper u during their j-th visit to the supermarket; Δt j,p∈S This indicates the time shopper u spends in front of shelf p during their jth visit to the supermarket; n j,p T represents the number of items purchased by shopper u on the supermarket shelf p during shopper u's j-th visit; u This represents the shortest time reader u spent at the supermarket during their m previous visits to purchase a single item; F u This represents the number of times shopper u has visited the supermarket and made purchases; m is an empirical value, and if shopper u's number of visits to the supermarket is greater than or equal to m, then the constraint value T is... const It's T u If shopper u visits the supermarket less than m times, then the constraint value T is... const It equals 'a'; 'a' is a constant, referring to all previous shoppers T. const The minimum value; Determine the constraint value T const Then, determine the current stopping point p. i The formula for determining whether something is a point of interest is: Where: IP is the set of shopper's points of interest. When the shopper stays for a period of time greater than or equal to the constraint value, the current point is the shopper's point of interest.

4. The method according to claim 3, characterized in that, The acquisition of shoppers' preferences for points of interest specifically includes: The score is obtained by calculating the shopper's preference for the current point of interest using the following formula. i : Among them, score i The higher the value, the greater the shopper's liking for the current point of interest i.

5. The method according to claim 4, characterized in that, The process of using shelves as positioning units, obtaining shoppers' interests and preferences based on their activity trajectories within the supermarket, and then applying collaborative filtering algorithms to identify shoppers with similar interests and recommending products to the supermarket includes: The similarity between shoppers can be obtained using the Pearson correlation coefficient method according to the following formula: Where sim(x,y) represents the similarity between shopper x and shopper y; r x,s S represents the rating of shopper x for point of interest s; xy This represents the set of interest points that shoppers x and y jointly rate; and This represents the average ratings of shopper x and shopper y for all points of interest; Based on the similarity between shoppers, the Top-N recommendation method is used to select the K shoppers who are most similar to the current shopper; The weighted average method is used to calculate the shopper's predicted future rating for item k: Among them, P u,k NB is the predicted rating of shopper u for item k; NB is the set of neighboring shoppers of shopper u. The goal is to select the M items with the highest predicted ratings from current shoppers and recommend them to them, thereby attracting shoppers to this supermarket to purchase these M items.

6. A geolocation recommendation system based on positioning technology, characterized in that, The system employs the location-based recommendation method according to any one of claims 1 to 5, wherein the system comprises: The dwell point detection module is used to detect the dwell points of shoppers on supermarket shelves based on the LED positioning principle; The point of interest discovery module is used to discover shoppers' points of interest based on the time spent at each stop point; The preference level acquisition module is used to obtain the shopper's preference level for points of interest; The supermarket recommendation module uses shelves as the location unit. Based on the shopper's activity trajectory in the supermarket, it obtains the shopper's interests and preferences. Then, it uses a collaborative filtering algorithm to find shoppers with similar interests and makes recommendations to the supermarket.

7. The system according to claim 6, characterized in that, The dwell point detection module is specifically used for: As shoppers stand in front of the supermarket shelves, browsing and selecting items, their mobile phones equipped with positioning systems can automatically turn on their cameras, communicate with the surrounding LED lights, and complete the shopper's location function, placing the shopper at their current point on the supermarket map. The positioning system records shoppers' movement trajectories and the time spent in each area in real time, ultimately forming the shopper's activity trajectory within the supermarket. This trajectory consists of a series of stop points, and a shopper's historical activity trajectory within the supermarket can be expressed as a sequence of stop points using the following formula: Where: p i Indicates the point where the shopper stops; Δt i This indicates the time spent at each point in time. These points capture key aspects of shopper behavior and prepare the data for subsequent processing.

8. The system according to claim 7, characterized in that, The point of interest discovery module is specifically used for: To determine whether a given point is a point of interest, a constraint value must be set. If a shopper spends more than or equal to this constraint value at that point, then the shopper is interested in the items on the shelf corresponding to that point; otherwise, they are not. The constraint value is defined considering the shopper's past shopping habits, as shown in the following formulas: T u =min(T u,j )(1≤j≤m); Wherein: T u,j Δt represents the shortest time shopper u spends in front of the shelf when purchasing a single item during their j-th visit to the supermarket; S is the set of shelves corresponding to the set of items purchased by shopper u during their j-th visit to the supermarket; Δt j,p∈S This indicates the time shopper u spends in front of shelf p during their jth visit to the supermarket; n j,p T represents the number of items purchased by shopper u on the supermarket shelf p during shopper u's j-th visit; u This represents the shortest time reader u spent at the supermarket during their m previous visits to purchase a single item; F u This represents the number of times shopper u has visited the supermarket and made purchases; m is an empirical value, and if shopper u's number of visits to the supermarket is greater than or equal to m, then the constraint value T is... const It's T u If shopper u visits the supermarket less than m times, then the constraint value T is... const It equals 'a'; 'a' is a constant, referring to all previous shoppers T. const The minimum value; Determine the constraint value T const Then, determine the current stopping point p. i The formula for determining whether something is a point of interest is: Where: IP is the set of shopper's points of interest. When the shopper stays for a period of time greater than or equal to the constraint value, the current point is the shopper's point of interest.

9. The system according to claim 8, characterized in that, The preference level acquisition module is specifically used for: The score is obtained by calculating the shopper's preference for the current point of interest using the following formula. i : Among them, score i The higher the value, the greater the shopper's liking for the current point of interest i.

10. The system according to claim 9, characterized in that, The supermarket recommendation module is specifically used for: The similarity between shoppers can be obtained using the Pearson correlation coefficient method according to the following formula: Where sim(x,y) represents the similarity between shopper x and shopper y; r x,s S represents the rating of shopper x for point of interest s; xy This represents the set of interest points that shoppers x and y jointly rate; and This represents the average ratings of shopper x and shopper y for all points of interest; Based on the similarity between shoppers, the Top-N recommendation method is used to select the K shoppers who are most similar to the current shopper; The weighted average method is used to calculate the shopper's predicted future rating for item k: Among them, P u,k NB is the predicted rating of shopper u for item k; NB is the set of neighboring shoppers of shopper u. The goal is to select the M items with the highest predicted ratings from current shoppers and recommend them to them, thereby attracting shoppers to this supermarket to purchase these M items.

Images