CN106600360B - Method and device for sorting recommended objects - Google Patents
Method and device for sorting recommended objects Download PDFInfo
- Publication number
- CN106600360B CN106600360B CN201611039688.XA CN201611039688A CN106600360B CN 106600360 B CN106600360 B CN 106600360B CN 201611039688 A CN201611039688 A CN 201611039688A CN 106600360 B CN106600360 B CN 106600360B
- Authority
- CN
- China
- Prior art keywords
- user
- vector
- recommended
- establishing
- commodities
- 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.)
- Active
Links
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
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method and a device for sorting recommended objects, wherein the method comprises the following steps: identifying location information of a user; acquiring a recommended object corresponding to the position information; determining the ranking order of the recommended object based on the correlation between the recommended object and the user. By implementing the method and the device, the acquired recommendation objects can be arranged at different positions aiming at different users on the basis of recommending according to the spatial positions of the users, so that the recommendation effect of 'thousands of people and thousands of faces' is realized, and the user experience and the purchase conversion rate of websites can be improved.
Description
Technical Field
The present invention relates to the field of communications, and in particular, to a method and an apparatus for ranking recommended objects.
Background
With the development of mobile communication networks, electronic commerce has come to be developed unprecedentedly. The ranking order of merchants recommended by e-commerce websites to website users directly results in the user experience and purchase conversion rate of the websites. However, in the current phase, e-commerce websites generally recommend merchants to users by: first, identifying position information (navigation map information) of a user; then, acquiring a merchant corresponding to the position information; secondly, the commercial tenant is scored based on the operation data of the commercial tenant (including the sales volume of the commercial tenant, the user goodness, the commodity price, the commercial tenant state, the preferential event and the like); and finally, determining the ranking order of the commercial tenant according to the scoring result. Although the merchant recommendation can be performed by combining the spatial characteristics (navigation map position) of the user in the above manner, the arrangement order of the recommended merchants is based on the attributes of the merchants. Therefore, the recommended merchants are shown to a plurality of users at the same navigation map position in the same arrangement sequence, and the users have no distinction, so that the indexes such as user experience and the purchasing conversion rate of websites are reduced.
Disclosure of Invention
In order to solve the technical problem, the invention provides a method and a device for sorting recommended objects.
In one aspect, an embodiment of the present invention provides a method for ranking recommended objects, where the method includes:
identifying location information of a user;
acquiring a recommended object corresponding to the position information;
determining the ranking order of the recommended object based on the correlation between the recommended object and the user.
Because the corresponding recommended objects are obtained according to the position information of the user, and the ranking order of the recommended objects is determined based on the correlation between the recommended objects and the user, the recommended objects can be arranged at different positions aiming at different users on the basis of recommending according to the spatial position of the user, the defect that the recommended objects are shown to a plurality of users at the same navigation map position in the same arrangement sequence is overcome, and the recommending effect of thousands of people is achieved. Therefore, the user experience and the purchasing conversion rate of the website can be improved.
In some embodiments of the present invention, the determining the ranking of the recommended object based on the correlation between the recommended object and the user comprises:
calculating a recommendation score for the recommended object based on a correlation between the recommended object and the user;
and determining the ranking order of the recommended objects according to the recommendation scores.
In some embodiments of the present invention, the calculating the recommendation score of the recommended object based on the correlation between the recommended object and the user includes:
acquiring an object vector of the recommended object and a user vector of the user;
calculating a similarity between the object vector and the user vector;
assigning the similarity to the recommendation score.
By means of the similarity between the user vector abstracted for the user and the object vector abstracted for the recommended object, the correlation between the user and the recommended object can be quantized intuitively and accurately.
In some embodiments of the invention, the method further comprises:
and establishing the object vector based on the historical orders of the recommended objects.
Because the object vector of the recommended object is established based on the historical order, the established object vector can truly and effectively reflect the transaction condition of the recommended object.
In some embodiments of the invention, the creating the object vector based on the historical order of the recommended object comprises:
grouping the commodities in the historical order according to a set dimension;
calculating the ratio of the quantity of the commodities in the group to the total quantity of the commodities in the historical order;
and establishing the object vector through the ratio.
In the case that the recommendation object is a merchant in an e-commerce website, since the commodity is a core for facilitating the transaction between the user and the recommendation merchant, the object vector is established from the dimension of the commodity, so that the similarity calculated subsequently based on the object vector is more real and effective.
In some embodiments of the invention, the method further comprises:
establishing the user vector based on the historical orders of the user.
Because the user vector of the user is established based on the historical order, the established user vector can truly and effectively reflect the transaction condition of the user.
In some embodiments of the invention, the establishing the user vector based on the historical orders of the user comprises:
grouping the commodities in the historical order according to a set dimension;
calculating the ratio of the quantity of the commodities in the group to the total quantity of the commodities in the historical order;
and establishing the user vector through the ratio.
In the case that the recommendation object is a merchant in an e-commerce website, since the commodity is a core for facilitating the transaction between the user and the recommended merchant, the user vector is established from the dimension of the commodity, so that the similarity calculated subsequently based on the user vector can be more real and effective.
In some embodiments of the present invention, the similarity is a cosine value of an angle between the object vector and the user vector.
In the space geometry, the more the cosine value of the included angle of the two vectors is close to 1, the more the included angle of the two vectors is close to 0 degrees, namely the more the two vectors are similar, so the more the objects represented by the two vectors are related, therefore, in the invention, the similarity between the object vector and the user vector can be accurately and effectively obtained based on the cosine value of the included angle of the object vector and the user vector. In another aspect, an embodiment of the present invention provides an apparatus for ranking recommended objects, including:
the identification module is used for identifying the position information of the user;
the acquisition module is used for acquiring a recommendation object corresponding to the position information;
and the ranking order determining module is used for determining the ranking order of the recommended object based on the correlation between the recommended object and the user.
Because the corresponding recommended objects are obtained according to the position information of the user, and the ranking order of the recommended objects is determined based on the correlation between the recommended objects and the user, the recommended objects can be arranged at different positions aiming at different users on the basis of recommending according to the spatial position of the user, the defect that the recommended objects are shown to a plurality of users at the same navigation map position in the same arrangement sequence is overcome, and the recommending effect of thousands of people is achieved. Therefore, the user experience and the purchasing conversion rate of the website can be improved.
In some embodiments of the invention, the rank determination module comprises:
a calculation unit configured to calculate a recommendation score for the recommended object based on a correlation between the recommended object and the user;
and the ranking order determining unit is used for determining the ranking order of the recommended objects according to the recommendation scores.
In some embodiments of the invention, the computing unit comprises:
the acquisition component is used for acquiring an object vector of the recommended object and a user vector of the user;
a similarity calculation component for calculating a similarity between the object vector and the user vector;
a valuation component for valuing the similarity to the recommendation score.
By means of the similarity between the user vector abstracted for the user and the object vector abstracted for the recommended object, the correlation between the user and the recommended object can be quantized intuitively and accurately.
In some embodiments of the invention, the apparatus further comprises:
and the object vector establishing module is used for establishing the object vector based on the historical order of the recommended object.
Because the object vector of the recommended object is established based on the historical order, the established object vector can truly and effectively reflect the transaction condition of the recommended object.
In some embodiments of the invention, the object vector creation module comprises:
the grouping unit is used for grouping the commodities in the historical order according to a set dimension;
the ratio calculation unit is used for calculating the ratio of the quantity of the commodities in the group to the total quantity of the commodities in the historical order;
and the establishing unit is used for establishing the object vector through the ratio.
In the case that the recommendation object is a merchant in an e-commerce website, since the commodity is a core for facilitating the transaction between the user and the recommendation merchant, the object vector is established from the dimension of the commodity, so that the similarity calculated subsequently based on the object vector is more real and effective.
In some embodiments of the invention, the apparatus further comprises:
and the user vector establishing module is used for establishing the user vector based on the historical orders of the user.
Because the user vector of the user is established based on the historical order, the established user vector can truly and effectively reflect the transaction condition of the user.
In some embodiments of the invention, the user vector establishing module comprises:
the grouping unit is used for grouping the commodities in the historical order according to a set dimension;
the ratio calculation unit is used for calculating the ratio of the quantity of the commodities in the group to the total quantity of the commodities in the historical order;
and the establishing unit is used for establishing the user vector through the ratio.
In the case that the recommendation object is a merchant in an e-commerce website, since the commodity is a core for facilitating the transaction between the user and the recommended merchant, the user vector is established from the dimension of the commodity, so that the similarity calculated subsequently based on the user vector can be more real and effective.
In some embodiments of the present invention, the similarity is a cosine value of an angle between the object vector and the user vector.
In the space geometry, the more the cosine value of the included angle of the two vectors is close to 1, the more the included angle of the two vectors is close to 0 degrees, namely the more the two vectors are similar, so the more the objects represented by the two vectors are related, therefore, in the invention, the similarity between the object vector and the user vector can be accurately and effectively obtained based on the cosine value of the included angle of the object vector and the user vector.
Drawings
Fig. 1 is a flowchart of a method of ranking recommended objects according to embodiment 1 of the method of the present invention;
FIG. 2 is a flow chart of a method of ranking recommended objects according to method embodiment 2 of the present invention;
FIG. 3 is a flowchart of a method of ranking recommended objects according to method embodiment 3 of the present invention;
FIG. 4 is a flowchart of a method of ranking recommended objects according to method embodiment 8 of the present invention;
FIG. 5 is a flowchart of a method for ranking recommended objects according to method embodiment 9 of the present invention;
FIG. 6 is a schematic structural diagram of an apparatus for sorting recommended objects according to embodiment 1 of the apparatus of the present invention;
FIG. 7 illustrates one embodiment of the rank determination module 13 shown in FIG. 6;
fig. 8 shows an embodiment of the calculation unit 131 shown in fig. 7.
Detailed Description
Various aspects of the invention are described in detail below with reference to the figures and the specific embodiments. Well-known modules, units and their interconnections, links, communications or operations with each other are not shown or described in detail. Also, the described features, architectures, or functions may be combined in any manner in one or more embodiments. It will be understood by those skilled in the art that the various embodiments described below are illustrative only and are not intended to limit the scope of the present invention. It will also be readily understood that the modules or elements or steps of the various embodiments described herein and illustrated in the figures can be combined and designed in a wide variety of different configurations.
[ METHOD EXAMPLE 1 ]
Fig. 1 is a flowchart of a method of ranking recommended objects according to embodiment 1 of the method of the present invention. Referring to fig. 1, in the present embodiment, the method includes:
s11: location information of the user is identified.
In the present embodiment, the position Information may be, for example, a Point of Information (navigation map Information). Each piece of navigation map information includes: longitude and latitude, and information of nearby businesses.
S12: and acquiring a recommended object corresponding to the position information.
S13: determining the ranking order of the recommended object based on the correlation between the recommended object and the user.
Because the corresponding recommended objects are obtained according to the position information of the user, and the ranking order of the recommended objects is determined based on the correlation between the recommended objects and the user, the recommended objects can be arranged at different positions aiming at different users on the basis of recommending according to the spatial position of the user, the defect that the recommended objects are shown to a plurality of users at the same navigation map position in the same arrangement sequence is overcome, and the recommending effect of thousands of people is achieved. Therefore, the user experience and the purchasing conversion rate of the website can be improved.
[ METHOD EXAMPLE 2 ]
Fig. 2 is a flowchart of a method for ranking recommended objects according to embodiment 2 of the method of the present invention. Referring to fig. 2, in the present embodiment, the method includes:
s21: location information of the user is identified.
S22: and acquiring a recommended object corresponding to the position information.
S23: calculating a recommendation score for the recommended object based on a correlation between the recommended object and the user.
S24: and determining the ranking order of the recommended objects according to the recommendation scores.
[ METHOD EXAMPLE 3 ]
Fig. 3 is a flowchart of a method for ranking recommended objects according to embodiment 3 of the method of the present invention. Referring to fig. 3, in the present embodiment, the method includes:
s31: location information of the user is identified.
S32: and acquiring a recommended object corresponding to the position information.
S33: and acquiring an object vector of the recommended object and a user vector of the user.
S34: calculating a similarity between the object vector and the user vector.
S35: and assigning the similarity to a recommendation score of the recommended object.
S36: and determining the ranking order of the recommended objects according to the recommendation scores.
The object vector and the user vector are vector space models for describing the recommended object and the user respectively. The recommendation object and the user are abstracted into a vector space model, and the correlation between the two objects is reflected by the similarity of the two vectors on the space.
By means of the similarity between the user vector abstracted for the user and the object vector abstracted for the recommended object, the correlation between the user and the recommended object can be quantized intuitively and accurately.
[ METHOD EXAMPLE 4 ]
The method provided in this embodiment includes all the processing in method embodiment 3, and is not described herein again. On the basis of method embodiment 3, the method provided by this embodiment further includes the following processing:
and establishing the object vector based on the historical orders of the recommended objects.
Because the object vector of the recommended object is established based on the historical order, the established object vector can truly and effectively reflect the transaction condition of the recommended object.
[ METHOD EXAMPLE 5 ]
The method provided in this embodiment includes all the processing in method embodiment 4, and is not described herein again. In this embodiment, the creating the object vector based on the historical order of the recommended object includes the following processing:
(1) and grouping the commodities in the historical order of the recommendation object according to a set dimension.
(2) And calculating the ratio of the quantity of the commodities in the group to the total quantity of the commodities in the historical orders.
(3) And establishing the object vector through the ratio.
In the case that the recommendation object is a merchant in an e-commerce website, since the commodity is a core for facilitating the transaction between the user and the recommendation merchant, the object vector is established from the dimension of the commodity, so that the similarity calculated subsequently based on the object vector is more real and effective.
[ METHOD EXAMPLE 6 ]
The method provided in this embodiment includes all the processing in method embodiment 3, and is not described herein again. On the basis of method embodiment 3, the method provided by this embodiment further includes the following processing:
establishing the user vector based on the historical orders of the user.
Because the user vector of the user is established based on the historical order, the established user vector can truly and effectively reflect the transaction condition of the user.
[ METHOD EXAMPLE 7 ]
The method provided in this embodiment includes all the processing in method embodiment 6, and is not described herein again. In this embodiment, the establishing the user vector based on the historical orders of the user includes the following processing:
(1) and grouping the commodities in the historical orders of the user according to a set dimension.
(2) And calculating the ratio of the quantity of the commodities in the group to the total quantity of the commodities in the historical orders.
(3) And establishing the user vector through the ratio.
In the case that the recommendation object is a merchant in an e-commerce website, since the commodity is a core for facilitating the transaction between the user and the recommended merchant, the user vector is established from the dimension of the commodity, so that the similarity calculated subsequently based on the user vector can be more real and effective.
[ METHOD EXAMPLE 8 ]
The method provided by the present embodiment includes all the processes in method embodiment 3. In this embodiment, the similarity is a cosine value of an included angle between the object vector and the user vector, and specifically, the method provided in this embodiment includes:
s41: location information of the user is identified.
S42: and acquiring a recommended object corresponding to the position information.
S43: and acquiring an object vector of the recommended object and a user vector of the user.
S44: and calculating the cosine value of the included angle between the object vector and the user vector.
S45: and assigning the cosine value to the similarity between the object vector and the user vector.
S46: and assigning the similarity to a recommendation score of the recommended object.
S47: and determining the ranking order of the recommended objects according to the recommendation scores.
In the space geometry, the more the cosine value of the included angle of the two vectors is close to 1, the more the included angle of the two vectors is close to 0 degrees, namely the more the two vectors are similar, so the more the objects represented by the two vectors are related, therefore, in the invention, the similarity between the object vector and the user vector can be accurately and effectively obtained based on the cosine value of the included angle of the object vector and the user vector.
[ METHOD EXAMPLE 9 ]
In this embodiment, a recommendation object is taken as an example of a merchant in an e-commerce website, and a description is given of a method for sorting recommendation objects provided in this embodiment. Referring to fig. 5, the method includes:
s51: and establishing a merchant vector of an existing merchant and a user vector of an existing user in the e-commerce website.
S52: location information of a current user is identified.
S53: and acquiring a merchant corresponding to the position information of the current user.
S54: and extracting the obtained merchant vector of the merchant and the user vector of the current user.
S55: and calculating the cosine value of the included angle between the extracted merchant vector and the user vector.
S56: and assigning the calculated cosine value to the similarity between the extracted merchant vector and the user vector.
S57: and assigning the calculated similarity to the obtained recommendation score of the merchant.
S58: and determining the obtained ranking order of the merchants according to the recommendation score.
In the present embodiment, for the process S51, a vector space model is established for each merchant and user living in the e-commerce website through big data analysis technology. So as to represent the similarity between two objects through the similarity of the two vectors in space. And in the present invention, the established model can be updated periodically or in real time.
Aiming at establishing the merchant vector, the method is realized by the following processes:
the commodities in the historical order of the merchant are grouped according to the commodity display classification (common commodity display classifications C1-Cn in the commodity library are set), the ratio of the quantity of the commodities in each group to the total quantity of the commodities in the historical order is assumed to be A, and for all the classifications, A1+ A2+ A3+ … … An is 1. And taking the vectors (A1, A2, A3, … …, An) as the merchant vectors of the merchants.
For establishing the user vector, the following processes are used:
the commodities in the user's historical order are also grouped according to the commodity display classification, and assuming that the ratio of the quantity of the commodities in each group to the total quantity of the commodities in the user's historical order is B, for all the classifications, B1+ B2+ B3+ … … Bn is 1. And taking the vectors (B1, B2, B3, … … and Bn) as the merchant vectors of the merchants.
In the present embodiment, the position Information may be, for example, a Point of Information (navigation map Information). Each piece of navigation map information includes: longitude and latitude, and information of nearby businesses.
In addition, in other embodiments of the present invention, if the determined ranking order belongs to the first three digits, the corresponding recommended merchant is subjected to a special type display process to highlight the recommended merchant. Of course, the embodiment of the present invention is not limited to this, and those skilled in the art can reasonably determine the range of the recommended merchants for performing the special-type exhibition process according to actual needs.
In addition, besides the commodity dimension, in other embodiments of the present invention, other dimensions for establishing a vector space model of the commodity and the user may be added.
[ DEVICE EXAMPLE 1 ]
Fig. 6 is a schematic structural diagram of an apparatus for sorting recommended objects according to embodiment 1 of the present invention. Referring to fig. 6, the apparatus 1 comprises: the identification module 11, the obtaining module 12, and the rank determining module 13 specifically:
the identification module 11 is used for identifying the position information of the user.
In the present embodiment, the position Information may be, for example, a Point of Information (navigation map Information). Each piece of navigation map information includes: longitude and latitude, and information of nearby businesses.
The obtaining module 12 is configured to obtain a recommendation object corresponding to the location information identified by the identifying module 11.
The rank determining module 13 is configured to determine a rank of the recommended object based on the correlation between the recommended object and the user acquired by the acquiring module 12.
Because the corresponding recommended objects are obtained according to the position information of the user, and the ranking order of the recommended objects is determined based on the correlation between the recommended objects and the user, the recommended objects can be arranged at different positions aiming at different users on the basis of recommending according to the spatial position of the user, the defect that the recommended objects are shown to a plurality of users at the same navigation map position in the same arrangement sequence is overcome, and the recommending effect of thousands of people is achieved. Therefore, the user experience and the purchasing conversion rate of the website can be improved.
[ DEVICE EXAMPLE 2 ]
The apparatus provided in this embodiment includes all the modules in apparatus embodiment 1, and is not described herein again. Referring to fig. 7, in the present embodiment, the rank determination module 13 includes: the calculating unit 131 and the rank determining unit 132 specifically:
the calculating unit 131 is configured to calculate a recommendation score of the recommended object based on a correlation between the recommended object and the user.
The ranking order determining unit 132 is configured to determine a ranking order of the recommended objects according to the recommendation score calculated by the calculating unit 131.
[ DEVICE EXAMPLE 3 ]
The apparatus provided in this embodiment includes all the modules and units in apparatus embodiment 2, which are not described herein again. Referring to fig. 8, in the present embodiment, the calculation unit 131 includes: an acquisition component 1311, a similarity calculation component 1312, and a valuation component 1313, specifically:
the obtaining component 1311 is configured to obtain an object vector of the recommended object and a user vector of the user.
The similarity calculation component 1312 is configured to calculate the similarity between the object vector and the user vector acquired by the acquisition component 1311.
The assigning component 1313 is configured to assign the similarity calculated by the similarity calculation component 1312 to the recommendation score of the recommended subject.
The object vector and the user vector are vector space models for describing the recommended object and the user respectively. The recommendation object and the user are abstracted into a vector space model, and the similarity between the two objects is reflected by the similarity of the two vectors on the space.
By means of the similarity between the user vector abstracted for the user and the object vector abstracted for the recommended object, the correlation between the user and the recommended object can be quantized intuitively and accurately.
[ DEVICE EXAMPLE 4 ]
The apparatus provided in this embodiment includes all modules, units, and components in apparatus embodiment 3, which are not described herein again. On the basis of the device embodiment 3, the device provided by the present embodiment further includes: an object vector establishing module, specifically:
the object vector establishing module is used for establishing the object vector based on the historical orders of the recommended objects.
Because the object vector of the recommended object is established based on the historical order, the established object vector can truly and effectively reflect the transaction condition of the recommended object.
[ DEVICE EXAMPLE 5 ]
The method provided by this embodiment includes all the modules, units, and components in apparatus embodiment 4, which are not described herein again. In this embodiment, the object vector establishing module includes: grouping unit, ratio calculating unit, and establishing unit, specifically:
the grouping unit is used for grouping the commodities in the historical order of the recommendation object according to a set dimension.
The ratio calculation unit is used for calculating the ratio of the quantity of the commodities in the group divided by the grouping unit to the total quantity of the commodities in the historical order of the recommendation object.
The establishing unit is used for establishing the object vector through the ratio.
In the case that the recommendation object is a merchant in an e-commerce website, since the commodity is a core for facilitating the transaction between the user and the recommendation merchant, the object vector is established from the dimension of the commodity, so that the similarity calculated subsequently based on the object vector is more real and effective.
[ DEVICE EXAMPLE 6 ]
The apparatus provided in this embodiment includes all modules, units, and components in apparatus embodiment 3, which are not described herein again. On the basis of the device embodiment 3, the device provided by the present embodiment further includes: a user vector establishing module, specifically:
the user vector establishing module is used for establishing the user vector based on the historical orders of the user.
Because the user vector of the user is established based on the historical order, the established user vector can truly and effectively reflect the transaction condition of the user.
[ DEVICE EXAMPLE 7 ]
The apparatus provided in this embodiment includes all the modules, units, and components in apparatus embodiment 6, which are not described herein again. In this embodiment, the user vector establishing module includes: grouping unit, ratio calculating unit, and establishing unit, specifically:
the grouping unit is used for grouping the commodities in the historical orders of the user according to a set dimension.
The ratio calculation unit is used for calculating the ratio of the quantity of the commodities in the groups divided by the grouping unit to the total quantity of the commodities in the historical orders of the user.
The establishing unit is used for establishing the user vector through the ratio.
In the case that the recommendation object is a merchant in an e-commerce website, since the commodity is a core for facilitating the transaction between the user and the recommended merchant, the user vector is established from the dimension of the commodity, so that the similarity calculated subsequently based on the user vector can be more real and effective.
[ DEVICE EXAMPLE 8 ]
The apparatus provided in this embodiment includes all modules, units, and components in apparatus embodiment 3, which are not described herein again. In this embodiment, the similarity is a cosine value of an included angle between the object vector and the user vector. Specifically, in the present embodiment, the similarity calculation component 1312 includes a calculation subcomponent and an assignment subcomponent, specifically:
the calculating subassembly is used for calculating a cosine value of an included angle between the object vector and the user vector.
And the assignment sub-component is used for assigning the cosine value calculated by the calculation sub-component to the similarity between the object vector and the user vector.
In the space geometry, the more the cosine value of the included angle of the two vectors is close to 1, the more the included angle of the two vectors is close to 0 degrees, namely the more the two vectors are similar, so the more the objects represented by the two vectors are related, therefore, in the invention, the similarity between the object vector and the user vector can be accurately and effectively obtained based on the cosine value of the included angle of the object vector and the user vector.
Those skilled in the art will clearly understand that the present invention may be implemented entirely in software, or by a combination of software and a hardware platform. Based on such understanding, all or part of the technical solutions of the present invention contributing to the background may be embodied in the form of a software product, which may be stored in a storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, a smart phone, a network device, etc.) to execute the method according to each embodiment or some parts of the embodiments of the present invention.
As used herein, the term "software" or the like refers to any type of computer code or set of computer-executable instructions in a general sense that is executed to program a computer or other processor to perform various aspects of the present inventive concepts as discussed above. Furthermore, it should be noted that according to one aspect of the embodiment, one or more computer programs implementing the method of the present invention when executed do not need to be on one computer or processor, but may be distributed in modules in multiple computers or processors to execute various aspects of the present invention.
Computer-executable instructions may take many forms, such as program modules, executed by one or more computers or other devices. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. In particular, the functionality of the program modules may be combined or split between various embodiments as desired.
Also, technical solutions of the present invention may be embodied as a method, and at least one example of the method has been provided. The actions may be performed in any suitable order and may be presented as part of the method. Thus, embodiments may be configured such that acts may be performed in an order different than illustrated, which may include performing some acts simultaneously (although in the illustrated embodiments, the acts are sequential).
The definitions given and used herein should be understood with reference to dictionaries, definitions in documents incorporated by reference, and/or their ordinary meanings.
In the claims, as well as in the specification above, all transitional phrases such as "comprising," "having," "containing," "carrying," "having," "involving," "consisting essentially of …," and the like are to be understood to be open-ended, i.e., to include but not limited to. Only "consisting of … …" should be an overphrase of being closed or semi-closed.
The terms and expressions used in the specification of the present invention have been set forth for illustrative purposes only and are not meant to be limiting. It will be appreciated by those skilled in the art that changes could be made to the details of the above-described embodiments without departing from the underlying principles thereof. The scope of the invention is, therefore, indicated by the appended claims, in which all terms are intended to be interpreted in their broadest reasonable sense unless otherwise indicated.
Claims (10)
1. A method for ranking recommended objects, the method comprising:
identifying location information of a user;
acquiring a recommended object corresponding to the position information;
determining a ranking order of the recommended object based on a correlation between the recommended object and the user;
wherein the determining the ranking of the recommended object based on the correlation between the recommended object and the user comprises: calculating a recommendation score of the recommended object based on the correlation between the recommended object and the user, and determining the ranking order of the recommended object according to the recommendation score;
wherein the method further comprises: establishing an object vector based on the historical order of the recommended object, and establishing a user vector based on the historical order of the user;
wherein the calculating of the recommendation score for the recommended object based on the correlation between the recommended object and the user comprises: and acquiring an object vector of the recommended object and a user vector of the user, calculating the similarity between the object vector and the user vector, and assigning the similarity to the recommendation score.
2. The method of claim 1, wherein the building an object vector based on the historical order of the recommended object comprises:
grouping the commodities in the historical order according to a set dimension;
calculating the ratio of the quantity of the commodities in the group to the total quantity of the commodities in the historical order;
and establishing the object vector through the ratio.
3. The method of claim 1, wherein the establishing a user vector based on the user's historical orders comprises:
grouping the commodities in the historical order according to a set dimension;
calculating the ratio of the quantity of the commodities in the group to the total quantity of the commodities in the historical order;
and establishing the user vector through the ratio.
4. The method of any one of claims 1 to 3, wherein the similarity is a cosine value of an angle of the object vector with respect to the user vector.
5. An apparatus for ranking recommended objects, the apparatus comprising:
the identification module is used for identifying the position information of the user;
the acquisition module is used for acquiring a recommendation object corresponding to the position information;
a ranking order determination module for determining a ranking order of the recommended object based on a correlation between the recommended object and the user;
wherein the rank order determination module comprises:
a calculation unit configured to calculate a recommendation score for the recommended object based on a correlation between the recommended object and the user;
the ranking order determining unit is used for determining the ranking order of the recommended objects according to the recommendation scores;
wherein the apparatus further comprises:
the object vector establishing module is used for establishing an object vector based on the historical order of the recommended object;
the user vector establishing module is used for establishing a user vector based on the historical order of the user; wherein the calculation unit includes:
the acquisition component is used for acquiring an object vector of the recommended object and a user vector of the user;
a similarity calculation component for calculating a similarity between the object vector and the user vector;
a valuation component for valuing the similarity to the recommendation score.
6. The apparatus of claim 5, wherein the object vector establishment module comprises:
the grouping unit is used for grouping the commodities in the historical order according to a set dimension;
the ratio calculation unit is used for calculating the ratio of the quantity of the commodities in the group to the total quantity of the commodities in the historical order;
and the establishing unit is used for establishing the object vector through the ratio.
7. The apparatus of claim 5, wherein the user vector establishment module comprises:
the grouping unit is used for grouping the commodities in the historical order according to a set dimension;
the ratio calculation unit is used for calculating the ratio of the quantity of the commodities in the group to the total quantity of the commodities in the historical order;
and the establishing unit is used for establishing the user vector through the ratio.
8. The apparatus of any of claims 5 to 7, wherein the similarity is a cosine value of an angle of the object vector with the user vector.
9. A terminal device comprising a memory and a processor; wherein the content of the first and second substances,
the memory is to store one or more computer instructions, wherein the one or more computer instructions, when executed by the processor, are capable of implementing the method of any of claims 1 to 4.
10. A computer storage medium storing one or more computer instructions which, when executed, are capable of implementing the method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611039688.XA CN106600360B (en) | 2016-11-11 | 2016-11-11 | Method and device for sorting recommended objects |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611039688.XA CN106600360B (en) | 2016-11-11 | 2016-11-11 | Method and device for sorting recommended objects |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106600360A CN106600360A (en) | 2017-04-26 |
| CN106600360B true CN106600360B (en) | 2020-05-12 |
Family
ID=58592829
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611039688.XA Active CN106600360B (en) | 2016-11-11 | 2016-11-11 | Method and device for sorting recommended objects |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106600360B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107705185A (en) * | 2017-10-13 | 2018-02-16 | 山东浪潮通软信息科技有限公司 | A kind of Method of Commodity Recommendation and device |
| CN108090807B (en) * | 2017-12-13 | 2021-06-22 | 北京星选科技有限公司 | Information recommendation method and device |
| CN108628833B (en) * | 2018-05-11 | 2021-01-22 | 北京三快在线科技有限公司 | Method and device for determining summary of original content and method and device for recommending original content |
| CN111402013B (en) * | 2020-06-04 | 2020-09-01 | 成都晓多科技有限公司 | Commodity collocation recommendation method, system, device and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012098950A (en) * | 2010-11-02 | 2012-05-24 | Nippon Telegr & Teleph Corp <Ntt> | Similar user extraction method, similar user extraction device and similar user extraction program |
| JP2013029872A (en) * | 2009-10-19 | 2013-02-07 | Nec Corp | Information recommendation system, method, and program |
| JP2014215685A (en) * | 2013-04-23 | 2014-11-17 | 株式会社Ｎｔｔドコモ | Recommendation server and recommendation content determination method |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101206751A (en) * | 2007-12-25 | 2008-06-25 | 北京科文书业信息技术有限公司 | Customer recommendation system based on data digging and method thereof |
| CN105205689A (en) * | 2015-08-26 | 2015-12-30 | 深圳市万音达科技有限公司 | Method and system for recommending commercial tenant |
| CN105868237A (en) * | 2015-12-09 | 2016-08-17 | 乐视网信息技术（北京）股份有限公司 | Multimedia data recommendation method and server |
| CN106021456B (en) * | 2016-05-17 | 2020-02-21 | 中山大学 | Interest point recommendation method fusing text and geographic information in local collaborative arrangement |
-
2016
- 2016-11-11 CN CN201611039688.XA patent/CN106600360B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013029872A (en) * | 2009-10-19 | 2013-02-07 | Nec Corp | Information recommendation system, method, and program |
| JP2012098950A (en) * | 2010-11-02 | 2012-05-24 | Nippon Telegr & Teleph Corp <Ntt> | Similar user extraction method, similar user extraction device and similar user extraction program |
| JP2014215685A (en) * | 2013-04-23 | 2014-11-17 | 株式会社Ｎｔｔドコモ | Recommendation server and recommendation content determination method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106600360A (en) | 2017-04-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107465741B (en) | Information pushing method and device | |
| KR20200123015A (en) | Information recommendation method, apparatus, device and medium | |
| CN106600360B (en) | Method and device for sorting recommended objects | |
| CN110008973B (en) | Model training method, method and device for determining target user based on model | |
| US20200234218A1 (en) | Systems and methods for entity performance and risk scoring | |
| CN110322300B (en) | Data processing method and device, electronic equipment and storage medium | |
| CN110084658B (en) | Method and device for matching articles | |
| CN110348921B (en) | Method and device for selecting store articles | |
| CN116308684B (en) | Online shopping platform store information pushing method and system | |
| KR102320097B1 (en) | Order system using identification code assigned by every each seat and order method using the same | |
| CN111967924A (en) | Commodity recommendation method, commodity recommendation device, computer device, and medium | |
| KR20210032691A (en) | Method and apparatus of recommending goods based on network | |
| CN113781149A (en) | Information recommendation method and device, computer-readable storage medium and electronic equipment | |
| CN115423555A (en) | Commodity recommendation method and device, electronic equipment and storage medium | |
| CN112199451A (en) | Commodity identification method and device, computer equipment and storage medium | |
| US20170249684A1 (en) | Systems and methods for search term prioritization | |
| CN111626767A (en) | Resource data distribution method, device and equipment | |
| KR102250131B1 (en) | Method and apparatus for recommending supply companies to demand companies for inter-company transactions | |
| CN116911953A (en) | Article recommendation method, apparatus, electronic device and computer readable storage medium | |
| WO2020150597A1 (en) | Systems and methods for entity performance and risk scoring | |
| CN113297462A (en) | Data processing method, device, equipment and storage medium | |
| CN110490682A (en) | The method and apparatus for analyzing item property | |
| CN110879863B (en) | Cross-domain search method and cross-domain search device | |
| CN114429384A (en) | Intelligent product recommendation method and system based on e-commerce platform | |
| CN111339434B (en) | Information recommendation method and device, electronic equipment and computer storage medium |
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 | ||
| CB02 | Change of applicant information |
Address after: Building N3, building 12, No. 27, Jiancai Chengzhong Road, Haidian District, Beijing 100096 Applicant after: Beijing Xingxuan Technology Co.,Ltd. Address before: 100085 Beijing, Haidian District on the road to the information on the ground floor of the 1 to the 3 floor of the 2 floor, room 11, 202 Applicant before: Beijing Xiaodu Information Technology Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |