Search

CN-121996731-A - Geographic position recommending method and system based on positioning technology

CN121996731ACN 121996731 ACN121996731 ACN 121996731ACN-121996731-A

Abstract

The invention belongs to the technical field of positioning, and particularly discloses a geographic position recommending method and a geographic position recommending system based on a positioning technology, wherein the method comprises the steps of detecting stay points of shoppers in a supermarket shelf based on an LED positioning principle; the method comprises the steps of finding interest points of a shopper according to stay time of the stay points, obtaining preference degree of the shopper for the interest points, taking a goods shelf as a positioning unit, after interest preference of the shopper is obtained based on the moving track of the shopper in the supermarket, finding interest similar shoppers by adopting a collaborative filtering algorithm to preference information, and recommending the supermarket.

Inventors

  • LIU ZEREN

Assignees

  • 北京航天情报与信息研究所

Dates

Publication Date
20260508
Application Date
20251225

Claims (10)

  1. 1. A geographic location recommendation method based on a positioning technology, the method comprising: Detecting stay points of shoppers in supermarket shelves based on an LED positioning principle; Finding the interest point of the shopper according to the stay time at the stay point; obtaining the preference degree of the shopper for the interest points; and (3) taking the goods shelf as a positioning unit, acquiring interest preference of the shopper based on the moving track of the shopper in the supermarket, and then adopting a collaborative filtering algorithm to find out similar interest shoppers to recommend the supermarket.
  2. 2. The method according to claim 1, wherein the detecting the stay point of the shopper in the supermarket shelf based on the LED positioning principle specifically comprises: the method comprises the steps that a shopper browses and selects articles before sitting on a shelf in a supermarket, a portable mobile phone provided with a positioning system can automatically start a camera to communicate with surrounding LED lamps, the positioning function of the shopper is completed, and the shopper is positioned at the current point of a map of the supermarket; The positioning system records the moving track of the shopper and the stay time of the shopper in each area in real time, and finally forms the moving track of the shopper in the supermarket, wherein the track is a series of stay points, and the historical track of the movement of the shopper in the supermarket is expressed as a stay point sequence as follows: Where p i represents the point where the shopper stays and Δt i represents the time to stay at this point, where these stay points grasp the shopper's behavioral emphasis while being ready for subsequent data processing.
  3. 3. The method according to claim 2, wherein the finding the point of interest of the shopper based on the time of stay at the point of stay comprises: For a given point, judging whether the point is an interest point or not, and setting a constraint value, if the residence time of the shopper at the point is greater than or equal to the constraint value, the shopper is interested in the goods on the shelf corresponding to the point, otherwise, the definition of the constraint value considers the past shopping habits of the shopper, as shown in the following formulas: T u ＝min(T u,j )(1≤j≤m); Wherein T u,j represents the shortest time for a shopper u to check out a single item to stay before a shelf, S is a shelf set corresponding to the item set purchased by the shopper u to check out the j, deltat j,p∈S represents the time for the shopper u to check out the supermarket j before a shelf p, n j,p represents the number of items purchased by the shopper u to stay on the shelf p, T u represents the shortest time for a reader u to check out the single item to stay m before the shopper u checks out, F u represents the number of times the shopper u has checked out the supermarket and purchased, m is an empirical value, if the number of times the shopper u checks out is greater than or equal to m, the constraint value T const is T u , if the number of times the shopper u checks out is less than m, the constraint value T const is equal to a, a is a constant, and the minimum value of all shoppers T const in the past is referred to; After determining the constraint value T const , the formula for determining whether the current stay point p i is the point of interest is as follows: IP is a point of interest set of a shopper, and the current point of interest is the point of interest of the shopper when the stay time of the shopper is greater than or equal to a constraint value.
  4. 4. The method of claim 3, wherein the obtaining the preference of the shopper for the point of interest specifically comprises: The shopper's preference score i for the current point of interest is obtained as follows: Wherein, the higher score i value indicates the higher preference of the shopper to the current point of interest i.
  5. 5. The method of claim 4, wherein the method takes the shelf as a positioning unit, and after obtaining interest preferences of the shopper based on the activity track of the shopper in the supermarket, the preference information is used for finding interest similar shoppers by a collaborative filtering algorithm, and the method specifically comprises the following steps: the similarity between shoppers is obtained using the pearson correlation coefficient method as follows: where sim (x, y) represents the similarity between shopper x and shopper y; r x,s represents the score of shopper x to points of interest S, S xy represents a set of points of interest that shoppers x, y commonly score; And Representing the average of shopper x and shopper y scores for all points of interest; According to the similarity among shoppers, selecting K shoppers closest to the current shopper by using a Top-N recommendation method; calculating a predicted score of the shopper for the item k in the future by adopting a weighted average method: wherein P u,k is the predictive score of shopper u for item k, NB is the set of nearby shoppers for shopper u; And selecting M articles with highest predictive scores of the current shopper for recommendation, and based on the M articles, attracting the shopper to purchase the M articles in the supermarket.
  6. 6. A geographic position recommending system based on a positioning technology, characterized in that the geographic position recommending method based on the positioning technology as defined in any one of claims 1 to 5 is adopted, and the system comprises: The stay point detection module is used for detecting stay points of shoppers in the supermarket shelves based on the LED positioning principle; The interest point finding module is used for finding the interest point of the shopper according to the stay time of the stay point; The preference degree acquisition module is used for acquiring preference degree of the shopper on the interest points; and the supermarket recommending module is used for recommending the supermarket by using the shelf as a positioning unit, acquiring interest preferences of the shopper based on the moving track of the shopper in the supermarket and then adopting a collaborative filtering algorithm to the preference information to find out similar interest shoppers.
  7. 7. The system according to claim 6, wherein the stay point detection module is specifically configured to: the method comprises the steps that a shopper browses and selects articles before sitting on a shelf in a supermarket, a portable mobile phone provided with a positioning system can automatically start a camera to communicate with surrounding LED lamps, the positioning function of the shopper is completed, and the shopper is positioned at the current point of a map of the supermarket; The positioning system records the moving track of the shopper and the stay time of the shopper in each area in real time, and finally forms the moving track of the shopper in the supermarket, wherein the track is a series of stay points, and the historical track of the movement of the shopper in the supermarket is expressed as a stay point sequence as follows: Where p i represents the point where the shopper stays and Δt i represents the time to stay at this point, where these stay points grasp the shopper's behavioral emphasis while being ready for subsequent data processing.
  8. 8. The system of claim 7, wherein the point of interest discovery module is specifically configured to: For a given point, judging whether the point is an interest point or not, and setting a constraint value, if the residence time of the shopper at the point is greater than or equal to the constraint value, the shopper is interested in the goods on the shelf corresponding to the point, otherwise, the definition of the constraint value considers the past shopping habits of the shopper, as shown in the following formulas: T u ＝min(T u,j )(1≤j≤m); Wherein T u,j represents the shortest time for a shopper u to check out a single item to stay before a shelf, S is a shelf set corresponding to the item set purchased by the shopper u to check out the j, deltat j,p∈S represents the time for the shopper u to check out the supermarket j before a shelf p, n j,p represents the number of items purchased by the shopper u to stay on the shelf p, T u represents the shortest time for a reader u to check out the single item to stay m before the shopper u checks out, F u represents the number of times the shopper u has checked out the supermarket and purchased, m is an empirical value, if the number of times the shopper u checks out is greater than or equal to m, the constraint value T const is T u , if the number of times the shopper u checks out is less than m, the constraint value T const is equal to a, a is a constant, and the minimum value of all shoppers T const in the past is referred to; After determining the constraint value T const , the formula for determining whether the current stay point p i is the point of interest is as follows: IP is a point of interest set of a shopper, and the current point of interest is the point of interest of the shopper when the stay time of the shopper is greater than or equal to a constraint value.
  9. 9. The system according to claim 8, wherein the preference obtaining module is specifically configured to: The shopper's preference score i for the current point of interest is obtained as follows: Wherein, the higher score i value indicates the higher preference of the shopper to the current point of interest i.
  10. 10. The system according to claim 9, wherein the supermarket recommendation module is specifically configured to: the similarity between shoppers is obtained using the pearson correlation coefficient method as follows: where sim (x, y) represents the similarity between shopper x and shopper y; r x,s represents the score of shopper x to points of interest S, S xy represents a set of points of interest that shoppers x, y commonly score; And Representing the average of shopper x and shopper y scores for all points of interest; According to the similarity among shoppers, selecting K shoppers closest to the current shopper by using a Top-N recommendation method; calculating a predicted score of the shopper for the item k in the future by adopting a weighted average method: wherein P u,k is the predictive score of shopper u for item k, NB is the set of nearby shoppers for shopper u; And selecting M articles with highest predictive scores of the current shopper for recommendation, and based on the M articles, attracting the shopper to purchase the M articles in the supermarket.

Description

Geographic position recommending method and system based on positioning technology Technical Field The invention belongs to the technical field of positioning, and particularly relates to a geographic position recommending method and system based on a positioning technology. Background The research of the conventional supermarket article recommendation algorithm is focused on the research of combining supermarket/shopper labels, shopper activities, visualization technologies and the like with collaborative filtering algorithms, and the research has some achievements, but the correct recommendation is difficult to make by using the collaborative filtering algorithm under the condition of sparse data. Therefore, there is a need to propose a geographic location recommendation method based on positioning technology to solve the above-mentioned technical problems. Disclosure of Invention The invention provides a geographic position recommending method and a geographic position recommending system based on a positioning technology, which are used for solving the problem that correct recommendation is difficult to be made by using a collaborative filtering algorithm under the condition of sparse data in the conventional supermarket article recommendation. In a first aspect, a geographic location recommendation method based on a positioning technology is provided, the method comprising: Detecting stay points of shoppers in supermarket shelves based on an LED positioning principle; Finding the interest point of the shopper according to the stay time at the stay point; obtaining the preference degree of the shopper for the interest points; and (3) taking the goods shelf as a positioning unit, acquiring interest preference of the shopper based on the moving track of the shopper in the supermarket, and then adopting a collaborative filtering algorithm to find out similar interest shoppers to recommend the supermarket. In a second aspect, there is provided a geographic location recommendation system based on location technology, the system comprising: The stay point detection module is used for detecting stay points of shoppers in the supermarket shelves based on the LED positioning principle; The interest point finding module is used for finding the interest point of the shopper according to the stay time of the stay point; The preference degree acquisition module is used for acquiring preference degree of the shopper on the interest points; and the supermarket recommending module is used for recommending the supermarket by using the shelf as a positioning unit, acquiring interest preferences of the shopper based on the moving track of the shopper in the supermarket and then adopting a collaborative filtering algorithm to the preference information to find out similar interest shoppers. According to the geographic position recommending method and system based on the positioning technology, based on the supermarket recommending algorithm of indoor positioning, the goods shelves are used as positioning units, interest preference of the shopper is obtained according to the moving track of the shopper in the supermarket, preference information is introduced into the collaborative filtering algorithm based on the user, the shopper with similar interest is found, and the recommending is performed, so that the problem of data sparseness in the supermarket recommending system can be effectively solved, and personalized supermarket recommending with relevant positions can be provided for the shopper. Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings. Drawings The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention and do not constitute a limitation on the invention. In the drawings: FIG. 1 is a schematic flow chart of an implementation of a geographic position recommending method based on a positioning technology according to an embodiment of the present invention; fig. 2 is a schematic diagram of a visible light communication and positioning principle according to an embodiment of the present invention. Detailed Description For the purposes of making the objects, technical solutions and advantages of the present specification more apparent, the technical solutions of the present specification will be clearly and completely described below with reference to specific embodiments of the present specification and corresponding drawings. It will be apparent that the desc