CN112381616A - Item recommendation guiding method and device and computer equipment - Google Patents
Item recommendation guiding method and device and computer equipment Download PDFInfo
- Publication number
- CN112381616A CN112381616A CN202011363492.2A CN202011363492A CN112381616A CN 112381616 A CN112381616 A CN 112381616A CN 202011363492 A CN202011363492 A CN 202011363492A CN 112381616 A CN112381616 A CN 112381616A
- Authority
- CN
- China
- Prior art keywords
- user
- article
- item
- recommendation
- scoring matrix
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 67
- 239000011159 matrix material Substances 0.000 claims abstract description 95
- 239000013598 vector Substances 0.000 claims abstract description 18
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 14
- 230000006399 behavior Effects 0.000 claims description 99
- 238000004891 communication Methods 0.000 claims description 52
- 230000015654 memory Effects 0.000 claims description 23
- 230000005855 radiation Effects 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 12
- 239000000126 substance Substances 0.000 claims description 6
- 230000005484 gravity Effects 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 10
- 230000008569 process Effects 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an article recommendation guiding method, an article recommendation guiding device and computer equipment, wherein the method comprises the following steps: acquiring historical behavior data of a user, and constructing an article-user scoring matrix according to the historical behavior data; vectorizing the characteristic values in the item-user scoring matrix to obtain characteristic vectors; respectively calculating similarity parameters between different articles according to the feature vectors to generate an article similarity matrix; determining the recommendation degree of different articles corresponding to each user according to the similarity parameter in the article similarity matrix and the characteristic value in the article-user scoring matrix; identifying the login operation of the user, and issuing the recommended article information determined according to the recommendation degree to the user terminal; according to the method, the object recommendation is carried out through an improved collaborative filtering recommendation algorithm, and meanwhile, real-time navigation is carried out while more accurate target objects are pushed to each user by combining an indoor trilateral positioning method, so that the user is helped to quickly and accurately find the needed objects.
Description
Technical Field
The invention belongs to the technical field of internet, and particularly relates to an article recommendation guiding method, an article recommendation guiding device and computer equipment.
Background
Various large-scale business surpasses and libraries appear all over the country at present, and the large-scale business surpasses and the libraries have various internal articles, so that a user can hardly find the commodity of the user's mind quickly; with the rapid development of computer technology, commodity management systems and book management systems are continuously updated, and personalized recommendation is in the first place, for example, resource recommendation can be performed on various e-commerce platforms and media clients. Most of the conventional collaborative recommendation algorithms recommend commodities based on the existing purchasing behaviors of users, and recommended products do not fit with interesting products of the users; the accuracy of the recommended product needs to be improved; in addition, due to the complex indoor layout planning, much time is wasted when the user finds the target object.
Disclosure of Invention
In view of at least one of the drawbacks and needs of the prior art, the present invention provides an article recommendation guiding method, apparatus and computer device.
To achieve the above object, according to a first aspect of the present invention, there is provided an item recommendation guidance method including the steps of:
acquiring historical behavior data of users, and constructing an article-user scoring matrix according to the historical behavior data, wherein a characteristic value in the article-user scoring matrix is used for representing the interest degree of each user in different articles;
vectorizing the characteristic values in the item-user scoring matrix to obtain characteristic vectors; respectively calculating similarity parameters between different articles according to the feature vectors to generate an article similarity matrix;
determining the recommendation degree of different articles corresponding to each user according to the similarity parameter in the article similarity matrix and the characteristic value in the article-user scoring matrix;
and identifying the login operation of the user, and issuing the recommended article information determined according to the recommendation degree to the user terminal.
Preferably, the item recommendation guidance method further includes:
and acquiring a target object selected by a user, and planning a path according to the position information of the target object and the current position of the user so as to guide the user to search the target object according to the planned path.
Preferably, the item recommendation guidance method, wherein the building of the item-user scoring matrix according to the historical behavior data includes:
acquiring a pre-configured weight distribution table; the weight distribution table comprises weight parameters of different types of user behaviors corresponding to different articles, wherein the user behaviors comprise a search behavior, a navigation behavior, a collection behavior and a purchase behavior;
and respectively collecting historical behavior data of each user on different articles, determining the interest degree of the user on different commodities according to the historical behavior data and the weight distribution table, and generating an article-user scoring matrix.
Preferably, in the item recommendation guidance method, the weights of the same user behavior corresponding to different items in the weight distribution table may be the same or different.
Preferably, before determining the interest level of the user in different commodities according to the historical behavior data and the weight distribution table, the method for guiding recommendation of an item further includes:
historical behavior data executed by each user for different articles is collected, and invalid data in the historical behavior data are filtered out based on a custom strategy.
Preferably, the item recommendation guidance method further includes: and correcting the interestingness in the item-user scoring matrix according to a time factor, wherein the time factor is inversely proportional to the time difference between the current time and the historical behavior occurrence time of the user.
Preferably, the article recommendation guidance method calculates the similarity parameter by using Cosine similarity Cosine:
wherein the content of the first and second substances,
representing a similarity parameter between the two items;Nrepresenting the total number of users participating in the scoring;x i is shown asiThe user's interest level in the first item;y i is shown asiThe level of interest of the individual user in the second item.
Preferably, the item recommendation guidance method, where issuing the recommended item information determined according to the recommendation degree to the user terminal, includes:
generating a recommendation list according to the sequence of the similarity from high to low;
deleting the information of the articles of which the current user has executed any one or more historical behaviors from the recommendation list to obtain an updated recommendation list;
selecting an article with the recommendation degree not less than a preset recommendation degree threshold value from the updated recommendation list as a recommended article and issuing the recommended article to the user terminal; alternatively, the first and second electrodes may be,
and selecting a preset number of articles in the front sequence from the updated recommendation list as recommended articles and issuing the recommended articles to the user terminal.
Preferably, in the item recommendation guidance method, the current location of the user is determined by:
acquiring the receiving intensity of a communication signal transmitted by communication equipment by a mobile terminal held by a user;
and calculating the current position of the user according to the layout position of the communication equipment and the receiving intensity by adopting a triangulation algorithm.
Preferably, in the method for guiding recommendation of an article, when the current location of the user is calculated according to the layout location of the communication device and the reception intensity by using a triangulation algorithm,
if the signal radiation areas of the three communication devices are intersected together, determining a first intersection point and a second intersection point of the signal radiation areas of any two communication devices;
and taking a third intersection point of a straight line formed by connecting the first intersection point and the second intersection point and the boundary of the signal radiation area of the rest communication equipment, and taking the position coordinate corresponding to the third intersection point as the current position of the user.
Preferably, in the method for guiding recommendation of an article, when the current location of the user is calculated according to the layout location of the communication device and the reception intensity by using a triangulation algorithm,
and if the signal radiation areas of the three communication devices are not intersected, determining the middle points of three connecting lines formed by the layout positions of the three communication devices, and taking the position coordinates corresponding to the gravity center of a triangle formed by the three middle points as the current position of the user.
According to a second aspect of the present invention, there is also provided an item recommendation guiding device, the device including:
the acquisition module is used for acquiring historical behavior data of users and constructing an article-user scoring matrix according to the historical behavior data, and the characteristic values in the article-user scoring matrix are used for representing the interest degree of each user in different articles;
the first calculation module is used for vectorizing the characteristic values in the item-user scoring matrix to obtain characteristic vectors; respectively calculating similarity parameters between different articles according to the feature vectors to generate an article similarity matrix;
the second calculation module is used for determining the recommendation degree of different articles corresponding to each user according to the similarity parameter in the article similarity matrix and the characteristic value in the article-user scoring matrix;
the recommendation module is used for identifying login operation of a user and issuing recommended article information determined according to the recommendation degree to the user terminal;
and the guiding module is used for acquiring the target item selected by the user from the recommendation list, and planning a path according to the position information of the target item and the current position of the user so as to guide the user to search the target item according to the planned path.
According to a third aspect of the present invention, there is also provided a computer device, comprising at least one processing unit, and at least one storage unit, wherein the storage unit stores a computer program which, when executed by the processing unit, causes the processing unit to perform the steps of any of the above item recommendation guiding methods.
In general, compared with the prior art, the above technical solution contemplated by the present invention can achieve the following beneficial effects:
(1) according to the item recommendation guiding method, the item recommendation guiding device and the computer equipment, firstly, similarity parameters among different items are respectively calculated according to an item-user scoring matrix, and an item similarity matrix is generated; then determining the recommendation degree of different articles corresponding to each user according to the similarity parameter in the article similarity matrix and the characteristic value in the article-user scoring matrix; when the login operation of the user is identified, the recommended article information determined according to the recommendation degree is issued to the user terminal; the method comprises the steps of obtaining a target object selected by a user, planning a path according to position information of the target object and the current position of the user, reducing the time for searching the target object, pushing the accurate position of the target object to the user, and simultaneously performing real-time navigation to help the user to quickly and accurately find a required object; meanwhile, the display device can be used as a platform for displaying articles, so that the user viscosity can be improved, and convenient operation is provided for the user.
(2) According to the item recommendation guiding method, the item recommendation guiding device and the computer equipment, the item-user scoring matrix is established based on the historical behaviors of the user and the weight distribution tables of different items, the user behaviors comprise searching behaviors, navigation behaviors, collecting behaviors, purchasing behaviors and the like, and the interest degree of the user on the commodities can be comprehensively reflected; the interest degree in the item-user scoring matrix is corrected through the time factor, which is essentially equivalent to setting weight for historical behavior data generated at different times, so that the influence of earlier-generated historical behaviors on the interest degree in the item-user scoring matrix is ensured to be smaller, the item-user scoring matrix is ensured to be more accurate to construct, and the actual purchasing psychology of the user is better fitted.
(3) The item recommendation guiding method, the item recommendation guiding device and the computer equipment provided by the invention adopt the Bluetooth positioning technology, have the advantages of low cost, easiness in deployment and high precision, and are suitable for various scenes.
Drawings
Fig. 1 is a schematic flowchart of an article recommendation guidance method according to an embodiment of the present application;
fig. 2 is a schematic flowchart of another item recommendation guidance method according to an embodiment of the present application;
FIG. 3 is a schematic diagram illustrating an implementation principle of a triangulation algorithm provided in an embodiment of the present application;
FIG. 4 is a schematic diagram of a preferred three-point positioning method according to an embodiment of the present application;
FIG. 5 is a schematic diagram of a preferred three-point positioning method according to an embodiment of the present application;
fig. 6 is a logic block diagram of an item recommendation guiding device according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of a computer device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
In the following description, the terms "first" and "second" are used for descriptive purposes only and are not intended to indicate or imply relative importance. The following description provides embodiments of the present application, where different embodiments may be substituted or combined, and thus the present application is intended to include all possible combinations of the same and/or different embodiments described. Thus, if one embodiment includes feature A, B, C and another embodiment includes feature B, D, then this application should also be considered to include an embodiment that includes one or more of all other possible combinations of A, B, C, D, even though this embodiment may not be explicitly recited in text below.
The following description provides examples, and does not limit the scope, applicability, or examples set forth in the claims. Changes may be made in the function and arrangement of elements described without departing from the scope of the disclosure. Various examples may omit, substitute, or add various procedures or components as appropriate. For example, the described methods may be performed in an order different than the order described, and various steps may be added, omitted, or combined. Furthermore, features described with respect to some examples may be combined into other examples.
Fig. 1 is a schematic flowchart of an item recommendation guiding method according to this embodiment. Referring to fig. 1, in an embodiment of the present application, the method includes the steps of:
s101: acquiring historical behavior data of users, and constructing an article-user scoring matrix according to the historical behavior data, wherein characteristic values in the article-user scoring matrix are used for representing the interest degree of each user in different articles;
in the embodiment, through analyzing historical behaviors of a large number of users, the interest degree/purchasing tendency of the users to different articles is quantified to form an article-user scoring matrix, and the probability of the users purchasing other related articles is predicted on the basis of the article-user scoring matrix; at present, most of the creation of the item-user scoring matrix takes the purchasing behavior of the user as a reference, but the method cannot fully reflect the interest degree of the user in the commodity.
As a specific example, the creating process of the item-user scoring matrix in this embodiment includes:
firstly, acquiring a pre-configured weight distribution table; the weight distribution table comprises weight parameters of different types of user behaviors corresponding to different articles, wherein the user behaviors comprise a search behavior, a navigation behavior, a collection behavior and a purchase behavior;
table 1 weight distribution table
In this embodiment, a search behavior of a user when searching for an item in an item search bar, navigation data of the user in real-time navigation, a collection behavior of the user for an item, and a purchase behavior are all used as historical behavior data of the user to construct an item-user scoring matrix. Referring to table 1, in this embodiment, weighting coefficients are respectively allocated to different types of user behaviors, and the setting manner of the weighting coefficients is not particularly limited. Generally, purchasing behavior indicates that the user has the greatest interest in the item, and thus the weighting factor for purchasing behavior is generally set to the maximum. The weights of the same user behavior corresponding to different items in the weight distribution table may be the same or different, and this embodiment is not limited in particular. In Table 1, various articlesI 1 ~I N The weight coefficient assignment of (2) is different.
Secondly, historical behavior data of each user on different goods and a weight distribution table are collected respectively, the interestingness of the user on different goods is calculated, and a goods-user scoring matrix A is generated.
Before the item-user scoring matrix is constructed, historical behavior data, including historical behaviors and corresponding execution times, of each user executed on different items needs to be collected from one or more electronic commerce systems; the larger the data volume of the historical behavior data is, the more accurate the constructed object-user scoring matrix is, but the larger the calculation amount is, the system performance is influenced; therefore, the present embodiment configures a size threshold of the collected historical behavior data in advance, and controls the size of the collected historical behavior data according to time factors, such as: when the historical behavior data amount of the last 30 days exceeds the set threshold range, the time interval is shortened, namely the data of the last 20 days can be obtained, and the scale of the historical behavior data is ensured to be within the threshold range; and similarly, when the data volume of the last 30 days is smaller than the set threshold range, the time interval is expanded, namely the data of the last 40 days can be obtained, and the data volume of the historical behaviors is ensured to be in a reasonable range.
Calculating the interest degree of the user to different commodities according to the historical behaviors, the execution times and the weight distribution table of each user to different commodities, and generating an item-user scoring matrixA ij Wherein, in the step (A),i=1-M，Mrepresenting an item dimension, i.e., a total number of items;j=1-N，Nrepresenting a user dimension, i.e. a total number of users; as shown in table 2, each element in the item-user scoring matrix reflects the interest level of the corresponding user in the corresponding item;
TABLE 2 item-user Scoring matrix
As a preferred example, after collecting the historical behavior data executed by each user for different articles, the present embodiment filters out invalid data in the historical behavior data based on the custom policy; since the historical behavior data is generated in the user operation process and has a large amount of noise and misoperation, the historical behavior data needs to be cleaned to obtain clean user operation data; the specific content of the custom policy can be set according to actual requirements, for example: and filtering navigation data with navigation time of less than 5 seconds of the user, search data repeatedly executed within 5 seconds by the user, and the like.
As a preferable example, the item recommendation guidance method further includes: correcting the interest degree in the item-user scoring matrix according to a time factor, wherein the time factor is inversely proportional to the time difference between the current time and the historical behavior occurrence time of the user; in one specific example, the expression for the time factor is:
wherein the content of the first and second substances,trepresents a time factor;T 0 represents the current time;T i representing the time when the user's historical behavior occurred;αthe user-defined adjustment threshold is represented, and the specific value can be adjusted according to the quantity of the articles.
It can be seen that the longer the time for generating the historical behavior data of the user is, the smaller the value of the time factor is, and the smaller the influence of the corresponding historical behavior on the interestingness in the item-user scoring matrix after the interestingness in the item-user scoring matrix is corrected by the time factor is.
According to the embodiment, the interestingness in the item-user scoring matrix is corrected through the time factor, which is essentially equivalent to setting weights for historical behavior data generated at different times, so that the influence of earlier-generated historical behaviors on the interestingness in the item-user scoring matrix is smaller, the item-user scoring matrix is more accurate to construct, and the actual purchasing psychology of the user is better fitted.
S102: vectorizing the characteristic values in the item-user scoring matrix to obtain characteristic vectors; respectively calculating similarity parameters between different articles according to the feature vectors to generate an article similarity matrix;
generating an item-user scoring matrixA ij Then, the item-user scoring matrix is usedA ij Calculating the similarity between different articles to generate a similarity matrix between the articlesB jj (ii) a Before calculating similarity, scoring matrix for item-userA ij Vectorizing the characteristic value to obtain a characteristic vector; then respectively calculating similarity parameters among different articles according to the feature vectors;
the similarity calculation method can adopt any one of cosine similarity, Euclidean distance, Pearson correlation, Jacard similarity and other methods; in this embodiment, preferably, cosine similarity is used to calculate similarity parameters between different articles, and a specific calculation formula is as follows:
wherein the content of the first and second substances,
representing a similarity parameter between the two items;Nrepresenting the total number of users participating in the scoring;x i is shown asiThe user's interest level in the first item;y i is shown asiThe level of interest of the individual user in the second item.
Corresponding generated similarity matrix between articlesB jj The elements in (A) are as follows:
TABLE 3 similarity matrix between items
For example: calculating a first item I based on the item-user scoring matrix in Table 21A second article I2The similarity between them is:
s103: determining the recommendation degree of different articles corresponding to each user according to the similarity parameter in the article similarity matrix and the characteristic value in the article-user scoring matrix;
in the embodiment, when recommending articles for different users, the recommendation degree is calculated according to an article similarity matrix and an article-user scoring matrix; in particular, an item-user scoring matrixA ij Similarity matrix with objectB jj Multiplying to obtain an item recommendation matrixC ij ，C ij =A ij ×B jj (ii) a Table 4 showsItem recommendation matrixC ij The elements of (1);
TABLE 4 item recommendation matrix
As can be seen from Table 4, for each userU i In other words, the item recommendation matrix gives the recommendation degrees of different items.
S104: and identifying the login operation of the user, and issuing the recommended article information determined according to the recommendation degree to the user terminal.
As a preferred example, before issuing the recommended item information determined according to the recommendation degree to the user terminal, the method further includes:
generating a recommendation list according to the sequence of the similarity from high to low;
deleting the information of the articles of which the current user has executed any one or more historical behaviors from the recommendation list to obtain an updated recommendation list;
selecting an article with the recommendation degree not less than a preset recommendation degree threshold value from the updated recommendation list as a recommended article and issuing the recommended article to the user terminal; alternatively, the first and second electrodes may be,
and selecting a preset number of articles in the front sequence from the updated recommendation list as recommended articles and issuing the recommended articles to the user terminal.
Wherein, for the items which the user has collected, navigated, searched or purchased, the items are deleted from the recommendation list; the method and the device remove the influence of the existing item factors in the recommendation list, and only recommend new items to the user, so that the freshness and the viscosity of the user are improved.
As shown in fig. 2, as an alternative embodiment, after step S104, the method further includes:
s105: acquiring a target article selected by a user, and planning a path according to the position information of the target article and the current position of the user so as to guide the user to search the target article according to the planned path;
in a specific example, the recommended item information generated in step S104 is sent to a terminal device held by the user, and the user selects a target item in which the user is interested; acquiring a target object selected by a user and searching position information of the target object, then performing path planning according to the position of the target object and the current position of the user, and issuing an indoor map formed according to indoor floors and room distribution and a planned route displayed in the indoor map to an equipment terminal of the user; preferably, all indoor routes are preset according to indoor map distribution, and the shortest route between the position of the target object and the current position of the user is selected as the planned optimal route. The GIS map equipped on the equipment terminal can display the indoor map and the planned path, so that the user is guided to quickly find the position of the target object according to the indoor map and the planned path.
In one specific example, the current location of the user is determined by:
acquiring the receiving intensity of a communication signal transmitted by communication equipment by a mobile terminal held by a user;
and calculating the current position of the user according to the layout position of the communication equipment and the receiving intensity by adopting a triangulation algorithm.
Fig. 3 is a schematic diagram of an implementation principle of a triangulation location algorithm provided in this embodiment, and referring to fig. 3, in the three-point location method, according to an indoor layout position of the communication device and a reception intensity of a mobile terminal held by a user for a communication signal transmitted by the communication device, the three devices intersect at one point, and a unique intersection point position can be determined according to a layout position of the communication device; in this example, the communication device is bluetooth, and the signal coverage area of each bluetooth is represented by a circle with a bluetooth position as a center of a circle and a signal intensity as a radius; calculating the distance between the mobile terminal and the Bluetooth according to the receiving intensity of the mobile terminal held by the user to the communication signal transmitted by the communication equipment, namely, according to the coordinates and the radius of three points, the point a coordinate ((x 1 ,y 1 ) Radius, radiusr 1 Point b coordinates: (x 2 ,y 2 ) Radius, radiusr 2 Point c coordinates: (x 3 ,y 3 ) Radius, radiusr 3 The point of intersection P (can be determined by Pythagorean theoremx 0 ,y 0 ) And then the current position of the user can be obtained.
As a preferred example, when the current position of the user is calculated according to the layout position of the communication devices and the receiving intensity by using the triangulation algorithm, if signal radiation areas of three communication devices are intersected together, a first intersection point and a second intersection point of the signal radiation areas of any two communication devices are determined;
and taking a third intersection point of a straight line formed by connecting the first intersection point and the second intersection point and the boundary of the signal radiation area of the rest communication equipment, and taking the position coordinate corresponding to the third intersection point as the current position of the user.
Fig. 4 is a schematic diagram of a preferred three-point positioning method provided in this embodiment, referring to fig. 4, in an actual implementation process, signal coverage areas of three bluetooth devices are likely to have a common intersection area, and at this time, a current location of a user cannot be determined by finding an intersection point of the signal coverage areas of the three bluetooth devices in fig. 3; at this time, an optimal solution needs to be obtained, specifically, two intersection points of any two bluetooth signal radiation areas are determined first, a straight line is determined according to the two intersection points, and an intersection point P2 between the straight line and the boundary of the third bluetooth signal radiation area is determined as the current position of the user.
The three-point positioning method provided by the example is completely suitable for a field where the Bluetooth equipment is reasonably arranged, can meet the actual use effect, and is small in calculation error.
As a preferable example, in the article recommendation guidance method, when the current location of the user is calculated according to the layout positions of the communication devices and the reception intensities by using a triangulation algorithm, if signal radiation areas of the three communication devices do not intersect with each other, midpoints of three connecting lines formed by the layout positions of the three communication devices are determined, and location coordinates corresponding to a center of gravity of a triangle formed by the three midpoints are used as the current location of the user.
Fig. 5 is a schematic diagram of a preferred three-point positioning method provided in this embodiment, referring to fig. 5, if the layout positions of multiple bluetooth devices in a room are unreasonable, or a bluetooth beacon is damaged, a situation that signal radiation areas of three bluetooth devices are not intersected may occur in an actual execution process, at this time, the signal reception intensity of a mobile terminal held by a user is weak, and the positioning effect is worse than the former two situations. Therefore, in order to improve the accuracy of the position calculation, the present embodiment determines the position where the user is currently located in the following manner: firstly, the midpoints of the connecting lines of the positions of the two Bluetooth devices are respectively determined, the midpoints of the three connecting lines form a triangle, and the gravity center P3 of the triangle is used as the current position of the user.
The three-point positioning method provided by the example can make up for extreme conditions in actual use and avoid the problem of positioning failure.
The following describes in detail the item recommendation guiding device provided in this embodiment with reference to fig. 6. It should be noted that the article recommendation guiding device shown in fig. 6 is used for executing the method of the embodiment shown in fig. 1 of the present application, and for convenience of description, only the portion related to the embodiment of the present application is shown, and specific technical details are not disclosed, please refer to the embodiment shown in fig. 1 of the present application.
Fig. 6 is a logic block diagram of an item recommendation guiding device provided in this embodiment, and as shown in fig. 6, the device includes:
the acquisition module 601 is configured to acquire historical behavior data of users, and construct an item-user score matrix according to the historical behavior data, where a feature value in the item-user score matrix is used to represent the interest degree of each user in different items;
a first calculation module 602, configured to perform vectorization processing on the feature values in the item-user scoring matrix to obtain feature vectors; respectively calculating similarity parameters between different articles according to the feature vectors to generate an article similarity matrix;
a second calculating module 603, configured to determine recommendation degrees of different items corresponding to each user according to the similarity parameter in the item similarity matrix and the eigenvalue in the item-user scoring matrix;
and the recommending module 604 is configured to identify login operation of the user and issue recommended item information determined according to the recommendation degree to the user terminal.
As an optional embodiment, the article recommendation guiding apparatus further includes a guiding module 605:
and the guiding module 605 is configured to obtain a target item selected by a user, and perform path planning according to the position information of the target item and the current position of the user, so as to guide the user to search for the target item according to a planned path.
As a preferred example, the acquisition module 601 is specifically configured to;
acquiring a pre-configured weight distribution table; the weight distribution table comprises weight parameters of different types of user behaviors corresponding to different articles, wherein the user behaviors comprise a search behavior, a navigation behavior, a collection behavior and a purchase behavior; the weights of the same user behavior corresponding to different articles in the weight distribution table can be the same or different;
and respectively collecting historical behavior data of each user on different articles, determining the interest degree of the user on different commodities according to the historical behavior data and the weight distribution table, and generating an article-user scoring matrix.
After the historical behavior data executed by each user on different articles is collected, the collection module 601 filters invalid data in the historical behavior data based on a custom policy.
As a preferred example, the article recommendation guiding device further includes a modification module 606;
the correcting module 606 is configured to correct the interestingness in the item-user scoring matrix according to a time factor, where the time factor is inversely proportional to a time difference between a current time and a historical behavior occurrence time of the user; the time factor is specifically expressed as:
wherein the content of the first and second substances,trepresents a time factor;T 0 represents the current time;T i representing the time when the user's historical behavior occurred;αindicating a custom adjustment threshold.
As a preferred example, the first calculating module 602 performs similarity calculation using cosine similarity:
wherein the content of the first and second substances,
representing a similarity parameter between the two items;Nrepresenting the total number of users participating in the scoring;x i is shown asiThe user's interest level in the first item;y i is shown asiThe level of interest of the individual user in the second item.
As a preferred example, the recommendation module 604 includes:
the sorting unit is used for generating a recommendation list according to the sequence of the similarity from high to low;
the updating unit is used for deleting the item information of any one or more historical behaviors executed by the current user from the recommendation list to obtain an updated recommendation list;
the selecting unit is used for selecting the articles with the recommendation degree not less than a preset recommendation degree threshold from the updated recommendation list as recommended articles and issuing the recommended articles to the user terminal; or selecting a preset number of articles in the front order from the updated recommendation list as recommended articles and issuing the recommended articles to the user terminal.
As a preferred example, the guidance module 606 determines where the user is currently located by:
acquiring the receiving intensity of a communication signal transmitted by communication equipment by a mobile terminal held by a user;
and calculating the current position of the user according to the layout position of the communication equipment and the receiving intensity by adopting a triangulation algorithm.
As a preferred example, the guidance module 606 determines where the user is currently located by:
if the signal radiation areas of the three communication devices are intersected together, determining a first intersection point and a second intersection point of the signal radiation areas of any two communication devices;
and taking a third intersection point of a straight line formed by connecting the first intersection point and the second intersection point and the boundary of the signal radiation area of the rest communication equipment, and taking the position coordinate corresponding to the third intersection point as the current position of the user.
As a preferred example, the guidance module 606 determines where the user is currently located by:
and if the signal radiation areas of the three communication devices are not intersected, determining the middle points of three connecting lines formed by the layout positions of the three communication devices, and taking the position coordinates corresponding to the gravity center of a triangle formed by the three middle points as the current position of the user.
It is clear to a person skilled in the art that the solution according to the embodiments of the present application can be implemented by means of software and/or hardware. The "unit" and "module" in this specification refer to software and/or hardware that can perform a specific function independently or in cooperation with other components, where the hardware may be, for example, a Field-Programmable Gate Array (FPGA), an Integrated Circuit (IC), or the like.
Each processing unit and/or module in the embodiments of the present application may be implemented by an analog circuit that implements the functions described in the embodiments of the present application, or may be implemented by software that executes the functions described in the embodiments of the present application.
Referring to fig. 7, a schematic structural diagram of a computer device according to an embodiment of the present application is shown, where the computer device may be used to implement the method in the embodiment shown in fig. 1. As shown in fig. 7, the computer device 700 may include: at least one central processor 701, at least one network interface 704, a user interface 703, a memory 705, at least one communication bus 702.
Wherein a communication bus 702 is used to enable connective communication between these components.
The user interface 703 may include a Display screen (Display) and a Camera (Camera), and the optional user interface 703 may also include a standard wired interface and a standard wireless interface.
The network interface 704 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), among others.
The central processor 701 may include one or more processing cores. The central processor 601 connects various parts within the entire terminal 700 using various interfaces and lines, and performs various functions of the terminal 700 and processes data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 705, and calling data stored in the memory 705. Optionally, the central Processing unit 701 may be implemented in at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA). The Central Processing Unit 601 may integrate one or a combination of a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), a modem, and the like. Wherein, the CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for rendering and drawing the content required to be displayed by the display screen; the modem is used to handle wireless communications. It is understood that the modem may not be integrated into the cpu 701, and may be implemented by a single chip.
The Memory 705 may include a Random Access Memory (RAM) or a Read-Only Memory (Read-Only Memory). Optionally, the memory 705 includes a non-transitory computer-readable medium. The memory 705 may be used to store instructions, programs, code sets, or instruction sets. The memory 705 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the various method embodiments described above, and the like; the storage data area may store data and the like referred to in the above respective method embodiments. The memory 705 may optionally be at least one memory device located remotely from the central processor 701. As shown in fig. 7, the memory 705, which is a type of computer storage medium, may include therein an operating system, a network communication module, a user interface module, and program instructions.
In the computer device 700 shown in fig. 7, the user interface 703 is mainly used as an interface for providing input for a user, and acquiring data input by the user; and the processor 701 may be configured to invoke the item recommendation guidance application stored in the memory 705, and specifically perform the following operations:
acquiring historical behavior data of users, and constructing an article-user scoring matrix according to the historical behavior data, wherein a characteristic value in the article-user scoring matrix is used for representing the interest degree of each user in different articles;
vectorizing the characteristic values in the item-user scoring matrix to obtain characteristic vectors; respectively calculating similarity parameters between different articles according to the feature vectors to generate an article similarity matrix;
determining the recommendation degree of different articles corresponding to each user according to the similarity parameter in the article similarity matrix and the characteristic value in the article-user scoring matrix;
and identifying the login operation of the user, and issuing the recommended article information determined according to the recommendation degree to the user terminal.
The present application also provides a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the above-mentioned item recommendation guiding method. The computer-readable storage medium may include, but is not limited to, any type of disk including floppy disks, optical disks, DVD, CD-ROMs, microdrive, and magneto-optical disks, ROMs, RAMs, EPROMs, EEPROMs, DRAMs, VRAMs, flash memory devices, magnetic or optical cards, nanosystems (including molecular memory ICs), or any type of media or device suitable for storing instructions and/or data.
It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present application is not limited by the order of acts described, as some steps may occur in other orders or concurrently depending on the application. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required in this application.
In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus may be implemented in other manners. For example, the above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one type of division of logical functions, and there may be other divisions when actually implementing, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of some service interfaces, devices or units, and may be an electrical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable memory. Based on such understanding, the technical solution of the present application may be substantially implemented or a part of or all or part of the technical solution contributing to the prior art may be embodied in the form of a software product stored in a memory, and including several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method described in the embodiments of the present application. And the aforementioned memory comprises: various media capable of storing program codes, such as a usb disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk.
Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by a program, which is stored in a computer-readable memory, and the memory may include: flash disks, Read-Only memories (ROMs), Random Access Memories (RAMs), magnetic or optical disks, and the like.
The above description is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure should not be limited thereby. That is, all equivalent changes and modifications made in accordance with the teachings of the present disclosure are intended to be included within the scope of the present disclosure. Embodiments of the present disclosure will be readily apparent to those skilled in the art from consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
Claims (10)
1. An item recommendation guidance method, comprising:
acquiring historical behavior data of users, and constructing an article-user scoring matrix according to the historical behavior data, wherein a characteristic value in the article-user scoring matrix is used for representing the interest degree of each user in different articles;
vectorizing the characteristic values in the item-user scoring matrix to obtain characteristic vectors; respectively calculating similarity parameters between different articles according to the feature vectors to generate an article similarity matrix;
determining the recommendation degree of different articles corresponding to each user according to the similarity parameter in the article similarity matrix and the characteristic value in the article-user scoring matrix;
and identifying the login operation of the user, and issuing the recommended article information determined according to the recommendation degree to the user terminal.
2. The item recommendation guidance method of claim 1, further comprising:
and acquiring a target object selected by a user, and planning a path according to the position information of the target object and the current position of the user so as to guide the user to search the target object according to the planned path.
3. The item recommendation guidance method of claim 1, wherein said constructing an item-user scoring matrix from said historical behavior data comprises:
acquiring a pre-configured weight distribution table; the weight distribution table comprises weight parameters of different types of user behaviors corresponding to different articles, wherein the user behaviors comprise a search behavior, a navigation behavior, a collection behavior and a purchase behavior;
and respectively collecting historical behavior data of each user on different articles, determining the interest degree of the user on different commodities according to the historical behavior data and the weight distribution table, and generating an article-user scoring matrix.
4. The item recommendation guidance method of claim 1, further comprising:
and correcting the interestingness in the item-user scoring matrix according to a time factor, wherein the time factor is inversely proportional to the time difference between the current time and the historical behavior occurrence time of the user.
5. The item recommendation guidance method of claim 1, wherein the similarity parameter calculation is performed using cosine similarity:
wherein the content of the first and second substances,
representing a similarity parameter between the two items;Nrepresenting the total number of users participating in the scoring;x i is shown asiThe user's interest level in the first item;y i is shown asiThe level of interest of the individual user in the second item.
6. The item recommendation guidance method of claim 2, wherein the current location of the user is determined by:
acquiring the receiving intensity of a communication signal transmitted by communication equipment by a mobile terminal held by a user;
and calculating the current position of the user according to the layout position of the communication equipment and the receiving intensity by adopting a triangulation algorithm.
7. The item recommendation guidance method according to claim 6, wherein when calculating the current position of the user according to the layout position of the communication equipment and the reception intensity by using a triangulation algorithm,
if the signal radiation areas of the three communication devices are intersected together, determining a first intersection point and a second intersection point of the signal radiation areas of any two communication devices;
and taking a third intersection point of a straight line formed by connecting the first intersection point and the second intersection point and the boundary of the signal radiation area of the rest communication equipment, and taking the position coordinate corresponding to the third intersection point as the current position of the user.
8. The item recommendation guidance method according to claim 6, wherein when calculating the current position of the user according to the layout position of the communication equipment and the reception intensity by using a triangulation algorithm,
and if the signal radiation areas of the three communication devices are not intersected, determining the middle points of three connecting lines formed by the layout positions of the three communication devices, and taking the position coordinates corresponding to the gravity center of a triangle formed by the three middle points as the current position of the user.
9. An item recommendation guide device, comprising:
the acquisition module is used for acquiring historical behavior data of users and constructing an article-user scoring matrix according to the historical behavior data, and the characteristic values in the article-user scoring matrix are used for representing the interest degree of each user in different articles;
the first calculation module is used for vectorizing the characteristic values in the item-user scoring matrix to obtain characteristic vectors; respectively calculating similarity parameters between different articles according to the feature vectors to generate an article similarity matrix;
the second calculation module is used for determining the recommendation degree of different articles corresponding to each user according to the similarity parameter in the article similarity matrix and the characteristic value in the article-user scoring matrix;
and the recommending module is used for identifying the login operation of the user and issuing the recommended article information determined according to the recommendation degree to the user terminal.
10. A computer arrangement comprising at least one processing unit and at least one memory unit, wherein the memory unit stores a computer program which, when executed by the processing unit, causes the processing unit to carry out the steps of the method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011363492.2A CN112381616A (en) | 2020-11-28 | 2020-11-28 | Item recommendation guiding method and device and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011363492.2A CN112381616A (en) | 2020-11-28 | 2020-11-28 | Item recommendation guiding method and device and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112381616A true CN112381616A (en) | 2021-02-19 |
Family
ID=74588962
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011363492.2A Pending CN112381616A (en) | 2020-11-28 | 2020-11-28 | Item recommendation guiding method and device and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112381616A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113657971A (en) * | 2021-08-31 | 2021-11-16 | 卓尔智联(武汉)研究院有限公司 | Article recommendation method and device and electronic equipment |
| CN115422438A (en) * | 2022-07-21 | 2022-12-02 | 中国铁道科学研究院集团有限公司电子计算技术研究所 | Railway material supply resource recommendation method, system and storage medium |
| CN116170497A (en) * | 2022-12-09 | 2023-05-26 | 北京国电通网络技术有限公司 | User behavior information pushing method, device, electronic equipment and computer medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105242241A (en) * | 2015-10-28 | 2016-01-13 | 国家电网公司 | Indoor positioning method based on Wi-Fi |
| CN108647996A (en) * | 2018-04-11 | 2018-10-12 | 中山大学 | A kind of personalized recommendation method and system based on Spark |
| CN109829792A (en) * | 2019-02-20 | 2019-05-31 | 杭州师范大学 | A kind of personalized item recommendation method and system based on user location distribution |
| CN111220943A (en) * | 2019-12-04 | 2020-06-02 | 湖南三一智能控制设备有限公司 | Positioning method, positioning system, computer-readable storage medium and vehicle |
| CN111310046A (en) * | 2020-02-18 | 2020-06-19 | 苏州大学 | Object recommendation method and device |
| CN111915409A (en) * | 2020-08-11 | 2020-11-10 | 深圳墨世科技有限公司 | Article recommendation method, device and equipment based on article and storage medium |
-
2020
- 2020-11-28 CN CN202011363492.2A patent/CN112381616A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105242241A (en) * | 2015-10-28 | 2016-01-13 | 国家电网公司 | Indoor positioning method based on Wi-Fi |
| CN108647996A (en) * | 2018-04-11 | 2018-10-12 | 中山大学 | A kind of personalized recommendation method and system based on Spark |
| CN109829792A (en) * | 2019-02-20 | 2019-05-31 | 杭州师范大学 | A kind of personalized item recommendation method and system based on user location distribution |
| CN111220943A (en) * | 2019-12-04 | 2020-06-02 | 湖南三一智能控制设备有限公司 | Positioning method, positioning system, computer-readable storage medium and vehicle |
| CN111310046A (en) * | 2020-02-18 | 2020-06-19 | 苏州大学 | Object recommendation method and device |
| CN111915409A (en) * | 2020-08-11 | 2020-11-10 | 深圳墨世科技有限公司 | Article recommendation method, device and equipment based on article and storage medium |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113657971A (en) * | 2021-08-31 | 2021-11-16 | 卓尔智联(武汉)研究院有限公司 | Article recommendation method and device and electronic equipment |
| CN113657971B (en) * | 2021-08-31 | 2023-12-01 | 卓尔智联(武汉)研究院有限公司 | Article recommendation method and device and electronic equipment |
| CN115422438A (en) * | 2022-07-21 | 2022-12-02 | 中国铁道科学研究院集团有限公司电子计算技术研究所 | Railway material supply resource recommendation method, system and storage medium |
| CN116170497A (en) * | 2022-12-09 | 2023-05-26 | 北京国电通网络技术有限公司 | User behavior information pushing method, device, electronic equipment and computer medium |
| CN116170497B (en) * | 2022-12-09 | 2023-10-20 | 北京国电通网络技术有限公司 | User behavior information pushing method, device, electronic equipment and computer medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112381616A (en) | Item recommendation guiding method and device and computer equipment | |
| CN107481114B (en) | Commodity recommendation method and device, electronic commerce system and storage medium | |
| CN109101989B (en) | Merchant classification model construction and merchant classification method, device and equipment | |
| CN107808122B (en) | Target tracking method and device | |
| CN109409612B (en) | Path planning method, server and computer storage medium | |
| JP4911536B2 (en) | Regional information retrieval device, regional information retrieval device control method, regional information retrieval system, and regional information retrieval system control method | |
| CN106844376A (en) | Recommend the method and device of point of interest | |
| US20160034968A1 (en) | Method and device for determining target user, and network server | |
| US20210125131A1 (en) | Electronic device, method for constructing scoring model of retail outlets, system, and computer readable medium | |
| CN106165463A (en) | Select the user related to geography fence | |
| CN110675177A (en) | Store site selection method and device | |
| CN111027895A (en) | Stock prediction and behavior data collection method, apparatus, device and medium for commodity | |
| CN110009379A (en) | A kind of building of site selection model and site selecting method, device and equipment | |
| CN108182253A (en) | For generating the method and apparatus of information | |
| JP2019512806A5 (en) | ||
| WO2019169050A1 (en) | Inventory placement recommendation system | |
| CN108960912A (en) | Method and apparatus for determining target position | |
| CN107430631A (en) | From position, report determines semantic place name | |
| CN110298508A (en) | Behavior prediction method, device and equipment | |
| CN106886934A (en) | Method, system and apparatus for determining merchant categories | |
| US20140122238A1 (en) | Coupon offer personalization | |
| CN108182589A (en) | Commercial circle radiation scope determines method and device | |
| CN116757715A (en) | Ranking list generation method and device, storage medium and computer equipment | |
| CN103678292B (en) | A kind of method and apparatus for being ranked up based on location information | |
| JP2013206070A (en) | Information processor and information processing method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |