CN107220881B - Method and device for ranking e-commerce popularity based on time and space - Google Patents
Method and device for ranking e-commerce popularity based on time and space Download PDFInfo
- Publication number
- CN107220881B CN107220881B CN201710389131.7A CN201710389131A CN107220881B CN 107220881 B CN107220881 B CN 107220881B CN 201710389131 A CN201710389131 A CN 201710389131A CN 107220881 B CN107220881 B CN 107220881B
- Authority
- CN
- China
- Prior art keywords
- user
- commodity
- value
- heat value
- influence factor
- 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]
- G06Q30/0623—Item investigation
-
- 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
Abstract
The invention provides a method and a device for ranking the popularity of an e-commerce based on time and space, wherein the method comprises the following steps: receiving an operation instruction of a user on the commodity, and updating the influence factor of each user on the commodity in the user relation table according to the user relation table corresponding to the user; according to the updated influence factors, recalculating the corresponding heat value of the current commodity; and reordering the coordinate positions of the commodities according to the corresponding heat value of the current commodity. Compared with a ranking algorithm only considering a time dimension, the method and the device have the advantages that various parameters contained in the user relation table corresponding to the user are also considered as the commodity ranking algorithm, and the influence relation between the user and the user is considered from the space dimension, so that commodities provided for the user are more accurate, the user experience is enhanced, and meanwhile the commodity volume can be effectively increased.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a method and a device for ranking e-commerce popularity based on time and space.
Background
The information that the internet explosion grows makes it increasingly difficult for users to find valuable information, making recommendation systems one of the most active research areas of today's academia. Recommendation systems attempt to assist users in finding potentially favorite music, movies, merchandise, apps, etc.
For commodities, the commodities with the highest popularity are pushed to the user, so that the purchase rate of the commodities can be effectively improved, and the user can select the commodities satisfying as much as possible. Most of the traditional rank-ranking algorithms only consider the time dimension, namely, the earlier popular commodities have smaller influence on the user and the popularity gradually declines as time goes on. But neglecting the influence of the spatial dimension, i.e. the physical relationship on the popularity, the user cannot predict the goods that the surrounding close people or other people in the same area want to buy or are buying. For example, taking the efficient environment as an example, for a certain popular commodity, whether the user uses the commodity or not is often greatly influenced by whether the user chooses to purchase the commodity or not, and the user may make a break when the user uses the commodity; on the contrary, if the surrounding people do not use the product, the user's will of purchase is relatively small even if the product is popular.
Therefore, the traditional popularity reduction ranking algorithm only considers time as a ranking element, and cannot completely meet the requirement of the user on the accuracy of commodity selection, namely, commodities which the user needs to buy are selected out, and the sensory experience of the user is influenced.
Disclosure of Invention
Therefore, a method and a device for ranking the e-commerce popularity based on time and space are needed to be provided, so that the problems that the traditional popularity decay ranking algorithm cannot completely and accurately predict commodities which a user wants to purchase and influence the sensory experience of the user due to the fact that only time is considered as a ranking element are solved.
To achieve the above object, the inventor provides a method for ranking electric power provider heat based on time and space, the method comprising the following steps:
receiving an operation instruction of a user on the commodity, and updating the influence factor of each user on the commodity in the user relation table according to the user relation table corresponding to the user;
according to the updated influence factors, recalculating the corresponding heat value of the current commodity; the heat value comprises a time heat value and a space heat value, the time heat value is determined according to a timestamp of an operation instruction of the commodity, and the space heat value is determined according to the updated influence factor;
and reordering the coordinate positions of the commodities according to the corresponding heat value of the current commodity.
Further, the user relationship table comprises an area position relationship table, and the area position relationship table is used for recording the coordinate position relationship between the user and the user; the step of updating the influence factors of each user in the user relation table according to the user relation table corresponding to the user comprises the following steps: when an operation instruction of a certain user on the commodity is received, adjusting the influence factors of other users belonging to the same area range with the user coordinate position on the commodity in the area position relation table.
Further, the user relationship table includes a cluster user relationship table, and the step of determining the spatial heat value according to the updated influence factor includes: obtaining the influence factors of all users belonging to the same cluster in the cluster user relation table aiming at a certain commodity, sequencing according to the size of the influence factors, recalculating the influence factors corresponding to the commodity according to a preset percentage, and determining a spatial heat value according to the recalculated influence factors.
Further, the user relationship table includes a cluster user relationship table, and the step of determining the spatial heat value according to the updated influence factor includes: when an operation instruction of a certain user on the commodity is received, adjusting the influence factors of other users belonging to the same cluster with the user on the commodity in the cluster user relation table.
Further, the step of "recalculating the heat value corresponding to the current commodity according to the updated influence factor" includes:
setting a first weight value and a second weight value;
calculating the product of the first weight value and the time heat value to obtain a first product value, and calculating the product of the second weight value and the space heat value to obtain a second product value;
and accumulating the first product value and the second product value to obtain a final heat value corresponding to the current commodity.
Further, the device comprises an instruction receiving unit, an influence factor updating unit, a heat value calculating unit and a sorting unit;
the instruction receiving unit is used for receiving an operation instruction of a user on the commodity, and the influence factor updating unit is used for updating the influence factor of each user on the commodity in the user relation table according to the user relation table corresponding to the user;
the heat value calculating unit is used for recalculating the heat value corresponding to the current commodity according to the updated influence factor; the heat value comprises a time heat value and a space heat value, the time heat value is determined according to a timestamp of an operation instruction of the commodity, and the space heat value is determined according to the updated influence factor;
the sorting unit is used for re-sorting the coordinate positions of the commodities according to the heat value corresponding to the current commodity.
Further, the user relationship table comprises an area position relationship table, and the area position relationship table is used for recording the coordinate position relationship between the user and the user; the "influence factor updating unit is configured to update the influence factor of each user in the user relationship table according to the user relationship table corresponding to the user" includes: when the instruction receiving unit receives an operation instruction of a certain user on the commodity, the influence factor updating unit is used for adjusting the influence factors of other users belonging to the same area range with the user coordinate position in the area position relation table on the commodity.
Further, the user relationship table includes a cluster user relationship table, and the determining the spatial heat value according to the updated influence factor includes: the influence factor updating unit is used for acquiring influence factors of all users belonging to the same cluster in the cluster user relation table aiming at a certain commodity, sorting according to the size of the influence factors, recalculating the influence factors corresponding to the commodity according to a preset percentage, and the heat value calculating unit is used for determining a space heat value according to the recalculated influence factors.
Further, the user relationship table includes a cluster user relationship table, and the step of determining the spatial heat value according to the updated influence factor includes: when an operation instruction of a certain user on the commodity is received, adjusting the influence factors of other users belonging to the same cluster with the user on the commodity in the cluster user relation table.
Further, the heat value calculation unit comprises a weight value setting unit, a product value calculation unit and a final value calculation unit; the "the heat value calculating unit is configured to recalculate the heat value corresponding to the current commodity according to the updated influence factor" includes:
the weight value setting unit is used for setting a first weight value and a second weight value;
the product value calculation unit is used for calculating the product of the first weight value and the time heat value to obtain a first product value, and calculating the product of the second weight value and the space heat value to obtain a second product value;
and the final value calculating unit is used for accumulating the first product value and the second product value to obtain a final heat value corresponding to the current commodity.
The invention provides a method and a device for ranking the popularity of an e-commerce based on time and space, wherein the method comprises the following steps: receiving an operation instruction of a user on the commodity, and updating the influence factor of each user on the commodity in the user relation table according to the user relation table corresponding to the user; according to the updated influence factors, recalculating the corresponding heat value of the current commodity; and reordering the coordinate positions of the commodities according to the corresponding heat value of the current commodity. Compared with a ranking algorithm only considering a time dimension, the method and the device have the advantages that various parameters contained in the user relation table corresponding to the user are also considered as the commodity ranking algorithm, and the influence relation between the user and the user is considered from the space dimension, so that commodities provided for the user are more accurate, the user experience is enhanced, and meanwhile the commodity volume can be effectively increased.
Drawings
FIG. 1 is a flow chart of a method for temporal and spatial based e-commerce popularity ranking according to an embodiment of the present invention;
FIG. 2 is a flow chart of an apparatus for temporal and spatial based e-commerce popularity ranking according to an embodiment of the present invention;
description of reference numerals:
101. an instruction receiving unit;
102. an influence factor updating unit;
103. a heat value calculation unit; 113. a weight value setting unit; 123. a product value calculation unit; 133. a final value calculation unit;
104. and a sorting unit.
Detailed Description
To explain technical contents, structural features, and objects and effects of the technical solutions in detail, the following detailed description is given with reference to the accompanying drawings in conjunction with the embodiments.
Referring to fig. 1, a flowchart of a method for ranking e-commerce popularity based on time and space according to an embodiment of the present invention is shown. According to the method, the time dimension and the space dimension are combined to serve as a reference factor for ranking the commodities on the line, and due to the fact that offline factors (such as purchasing behaviors of other users associated with the user) are introduced to serve as the reference factor for commodity ranking, the commodities provided for the user are more accurate, user experience is enhanced, and meanwhile the commodity volume can be effectively improved. The method comprises the following steps:
firstly, the method goes to step S101 to receive an operation instruction of a user on a commodity, and according to a user relationship table corresponding to the user, the influence factor of each user on the commodity in the user relationship table is updated. In the present embodiment, the operation instruction for the product includes, but is not limited to, collection, browsing, sharing, purchasing, commenting, and the like for the product. The user relationship table records the incidence relationship information between the users and the influence degree of the incidence relationship on the influence factors of the commodities. The association relationship information may be association relationship information of geographic locations, or may be association relationship between user identities. The influence factor is a physical quantity that represents the degree of influence of a certain user on a certain commodity, and may be a numerical value. For example, the influence factor of the first user on a certain product relative to the second user is 0.1 (in other embodiments, the change range of the influence factor may be other values, which are set according to actual needs), which indicates that if the first user has an operation behavior on the product, the influence factor of the second user on the product is increased by 0.1, and when the value of the influence factor is increased, the product is more likely to be recommended to the browsing page of the second user.
In some embodiments, the user relationship table records associations between user identities. For example, in an application scenario of a school, a user is a student of a college, and the user relationship table records information about other users such as a class, a grade, a college, and a community where the student is located. Next, step S101 will be further described by taking operations of browsing and purchasing a certain product as an example. For the first student who purchases the commodity, the initial value of the influence factor of the student on the commodity is set to 0. From a certain point in time, if other students (who belong to a class, grade, college or community with the first student) browse or purchase the commodity again, the influence factor of the first student on the commodity is adjusted. The method specifically comprises the following steps: if the student who operates the commodity browses the commodity once (in some embodiments, the student may also be a commodity of the same type), the influence factor of other students on the commodity, which occurs before the browsing at the point of time of purchase, is + 0.1; if the student who operates the commodity purchases the commodity once, the influence factor +1 of other students on the commodity occurs before the current purchase at the purchase time point (in other embodiments, the change range of the purchase behavior on the influence factor may be other numerical values, and is specifically set according to actual needs). Therefore, through big data calculation statistics, when a user executes an operation instruction on a commodity, the influence factor of each user on the commodity in the user relation table can be updated according to the user relation table corresponding to the user, and the influence factor distribution diagram of each user on a certain commodity which is related to each other is obtained.
When a user selects to buy a certain commodity, the mind of the user often exists, namely when the user goes out to find that people around use a certain commodity, the possibility of buying the commodity is greatly increased, namely the commodity buying is also influenced by regional factors. In some embodiments, the user relationship table comprises an area position relationship table, and the area position relationship table is used for recording coordinate position relationships between users; the step of updating the influence factors of each user in the user relation table according to the user relation table corresponding to the user comprises the following steps: when an operation instruction of a certain user on the commodity is received, adjusting the influence factors of other users belonging to the same area range with the user coordinate position on the commodity in the area position relation table.
Taking a certain community application scenario as an example, the user relationship table records the address information of the user, that is, all the user information living in a certain community. For the first user who purchases a certain commodity, the initial value of the influence factor of the user on the commodity is set to be 0. From a certain time point, if other users (the coordinate position of the user who first purchases the commodity and the user who first purchases the commodity belong to a community) browse or purchase the commodity again, the influence factor of the first user on the commodity is adjusted. The method specifically comprises the following steps: if the user who operates the product browses the product once (in some embodiments, the product may also be a similar product), the influence factor of other users who purchase the product before the browsing at the time point (including the first user and all users who purchase the product before the browsing until the browsing occurs) on the product is + 0.1; if the user who operates the product later purchases the product once, the influence factor +1 of other users on the product before the current purchase occurs on the purchase time point. Therefore, through big data calculation statistics, when a user executes an operation instruction on a commodity, the influence factor of each user on the commodity in the user relation table can be updated according to the user relation table corresponding to the user, and the influence factor distribution diagram of each user on a certain commodity in the region coordinate position range is obtained.
And then, the step S102 is carried out to recalculate the heat value corresponding to the current commodity according to the updated influence factor. The heat value comprises a time heat value and a space heat value, the time heat value is determined according to a timestamp of an operation instruction of the commodity, and the space heat value is determined according to the updated influence factor. Preferably, the temporal heat value may be finally determined according to the following manner: and calculating the interval time between the time stamp of the current operation of the user on the commodity and the time stamp of the last operation of the user on the commodity, and finally determining the time heat value, wherein the longer the interval time is, the smaller the time heat value is.
In some embodiments, the user relationship table comprises a cluster user relationship table, and the step of determining the spatial heat value according to the updated influence factor comprises: obtaining the influence factors of all users belonging to the same cluster in the cluster user relation table aiming at a certain commodity, sequencing according to the size of the influence factors, recalculating the influence factors corresponding to the commodity according to a preset percentage, and determining a spatial heat value according to the recalculated influence factors. Similarly, taking the efficient application scenario as an example, after obtaining the impact factor distribution map of users belonging to the same class on a certain commodity according to the previous steps, the impact factors of the commodity can be sorted according to the size of each user, and the impact factors of the first 10% or 20% (the preset percentage can be adjusted according to actual needs) are taken as the impact factors of the class where the user is located on the commodity, and are recorded as the class impact factors. After the class influence factors are determined, when the commodity popularity ranking of a certain user is finally calculated, the class influence factor corresponding to the class where the user is located is taken as an important consideration factor of the space popularity value, and the important consideration factor is added into the calculation of the space popularity value which influences the commodity on the user browsing interface, and the two factors present a positive correlation relationship. The same calculation of the influence factors of the grades, the colleges and the communities can be obtained, and the details are not repeated herein. For example, if the impact factor of a user on a certain product is w1, and the impact factors of the user on the product at the class, college and community are w2, w3 and w4, respectively, the spatial heat value of the product on the user's browsing interface may be w1+ w2+ w3+ w 4. The method has the advantages that due to the consideration of multiple factors, the popularity of the commodities is sorted according to the associated users corresponding to the user relationship under the user line, so that the sorted commodities can better meet the requirements of the users, the user experience can be improved, the commodity volume can be increased, and the turnover of sellers can be increased.
In some embodiments, the user relationship table comprises a cluster user relationship table, and the step of determining the spatial heat value according to the updated influence factor comprises: when an operation instruction of a certain user on the commodity is received, adjusting the influence factors of other users belonging to the same cluster with the user on the commodity in the cluster user relation table. The cluster may be a family, a school, a class, a company, or the like, for example, also taking a class as an example, when a certain user purchases a certain commodity, the influence factor on the commodity of other users belonging to the same class as the user in the user relationship table may be factored. Further, if the influence factor of the user who purchases the commodity is larger, the increase of the influence factor of other users on the commodity in the same class is larger, the popularity value of the commodity on other users is more likely to be ranked ahead, and the commodity is more likely to be recommended to interfaces of other users in the same class.
In some embodiments, the step of "recalculating the heat value corresponding to the current commodity according to the updated influence factor" includes: setting a first weight value and a second weight value; calculating the product of the first weight value and the time heat value to obtain a first product value, and calculating the product of the second weight value and the space heat value to obtain a second product value; and accumulating the first product value and the second product value to obtain a final heat value corresponding to the current commodity. The first weight value and the second weight value can be determined according to actual needs, the influence proportion of the time heat value and the space heat value to the final heat value can be correspondingly adjusted by adjusting the first weight value and the second weight value, and then the commodity heat value which best meets the requirements of users is calculated.
Then, the process may proceed to step S103 to reorder the coordinate positions of the commodities according to the heat value corresponding to the current commodity. In this embodiment, the commodity ranking corresponding to the current user is performed by determining the final commodity heat value according to the influence factor after the last user operation. That is, the data of the current operation is sent to the server after the user closes the page, the server stores the data of the current operation on the commodity (such as browsing and purchasing the commodity) and the previous operation data of the commodity by the user correspondingly, recalculates the influence factor of the user on the commodity, and reorders the commodity according to the updated influence factor. Therefore, when the user opens the commodity browsing page again, the next time, the commodity ordered list which meets the requirements of the user can be seen, the commodity ordered list can be selected by the user, and the sensory experience of the user is improved.
Referring to fig. 2, a flowchart of an apparatus for ranking e-commerce popularity based on time and space according to an embodiment of the present invention; the device is an electronic device with a specific commodity display function and a browsing operation function, such as a mobile phone, a tablet computer, a personal computer and the like. The device comprises an instruction receiving unit 101, an influence factor updating unit 102, a heat value calculating unit 103 and a sorting unit 104;
the instruction receiving unit 101 is configured to receive an operation instruction of a user on a commodity, and the influence factor updating unit 102 is configured to update an influence factor of each user on the commodity in the user relationship table according to the user relationship table corresponding to the user. In the present embodiment, the operation instruction for the product includes, but is not limited to, collection, browsing, sharing, purchasing, commenting, and the like for the product. The user relationship table records the incidence relationship information between the users and the influence degree of the incidence relationship on the influence factors of the commodities. The association relationship information may be association relationship information of geographic locations, or may be association relationship between user identities. The influence factor is a physical quantity that represents the degree of influence of a certain user on a certain commodity, and may be a numerical value. For example, if the influence factor of the first user on a certain product is 0.1 relative to that of the second user, it indicates that if the first user has an operation behavior on the product, the influence factor of the second user on the product is increased by 0.1, and when the value of the influence factor is increased, it indicates that the product is more likely to be recommended to the browsing page of the second user.
In some embodiments, the user relationship table comprises an area position relationship table, and the area position relationship table is used for recording coordinate position relationships between users; the "influence factor updating unit is configured to update the influence factor of each user in the user relationship table according to the user relationship table corresponding to the user" includes: when the instruction receiving unit receives an operation instruction of a certain user on the commodity, the influence factor updating unit is used for adjusting the influence factors of other users belonging to the same area range with the user coordinate position in the area position relation table on the commodity. . Therefore, through big data calculation statistics, when a user executes an operation instruction on a commodity, the influence factor of each user on the commodity in the user relation table can be updated according to the user relation table corresponding to the user, and the influence factor distribution diagram of each user on a certain commodity in the region coordinate position range is obtained.
The heat value calculating unit 103 is configured to recalculate the heat value corresponding to the current commodity according to the updated influence factor; the heat value comprises a time heat value and a space heat value, the time heat value is determined according to a timestamp of an operation instruction of the commodity, and the space heat value is determined according to the updated influence factor. Preferably, the temporal heat value may be finally determined according to the following manner: and calculating the interval time between the time stamp of the current operation of the user on the commodity and the time stamp of the last operation of the user on the commodity, and finally determining the time heat value, wherein the longer the interval time is, the smaller the time heat value is.
In some embodiments, the user relationship table comprises a cluster user relationship table, and the determining the spatial heat value according to the updated influence factor comprises: the influence factor updating unit is used for acquiring influence factors of all users belonging to the same cluster in the cluster user relation table aiming at a certain commodity, sorting according to the size of the influence factors, recalculating the influence factors corresponding to the commodity according to a preset percentage, and the heat value calculating unit is used for determining a space heat value according to the recalculated influence factors. The method has the advantages that due to the consideration of multiple factors, the popularity of the commodities is sorted according to the associated users corresponding to the user relationship under the user line, so that the sorted commodities can better meet the requirements of the users, the user experience can be improved, the commodity volume can be increased, and the turnover of sellers can be increased.
In some embodiments, the user relationship table comprises a cluster user relationship table, and the determining the spatial heat value according to the updated influence factor comprises: the influence factor updating unit is used for acquiring influence factors of all users belonging to the same cluster in the cluster user relation table aiming at a certain commodity, sorting according to the size of the influence factors, recalculating the influence factors corresponding to the commodity according to a preset percentage, and the heat value calculating unit is used for determining a space heat value according to the recalculated influence factors. The cluster may be a family, a school, a class, a company, or the like, for example, also taking a class as an example, when a certain user purchases a certain commodity, the influence factor on the commodity of other users belonging to the same class as the user in the user relationship table may be factored. Further, if the influence factor of the user who purchases the commodity is larger, the increase of the influence factor of other users on the commodity in the same class is larger, the popularity value of the commodity on other users is more likely to be ranked ahead, and the commodity is more likely to be recommended to interfaces of other users in the same class.
In some embodiments, the heat value calculation unit 103 includes a weight value setting unit 113, a product value calculation unit 123, and a final value calculation unit 133; the "the heat value calculating unit is configured to recalculate the heat value corresponding to the current commodity according to the updated influence factor" includes: the weight value setting unit 113 is configured to set a first weight value and a second weight value; the product value calculating unit 123 is configured to calculate a product of the first weight value and the temporal heat value to obtain a first product value, and calculate a product of the second weight value and the spatial heat value to obtain a second product value; the final value calculating unit 133 is configured to accumulate the first product value and the second product value to obtain a final heat value corresponding to the current product. The first weight value and the second weight value can be determined according to actual needs, the influence proportion of the time heat value and the space heat value to the final heat value can be correspondingly adjusted by adjusting the first weight value and the second weight value, and then the commodity heat value which best meets the requirements of users is calculated.
The sorting unit 104 is configured to reorder the coordinate positions of the commodities according to the heat value corresponding to the current commodity. In this embodiment, the commodity ranking corresponding to the current user is performed by determining the final commodity heat value according to the influence factor after the last user operation. That is, the data of the current operation is sent to the server after the user closes the page, the server stores the data of the current operation on the commodity (such as browsing and purchasing the commodity) and the previous operation data of the commodity by the user correspondingly, recalculates the influence factor of the user on the commodity, and reorders the commodity according to the updated influence factor. Therefore, when the user opens the commodity browsing page again, the next time, the commodity ordered list which meets the requirements of the user can be seen, the commodity ordered list can be selected by the user, and the sensory experience of the user is improved.
The invention provides a method and a device for ranking the popularity of an e-commerce based on time and space, wherein the method comprises the following steps: receiving an operation instruction of a user on the commodity, and updating the influence factor of each user on the commodity in the user relation table according to the user relation table corresponding to the user; according to the updated influence factors, recalculating the corresponding heat value of the current commodity; and reordering the coordinate positions of the commodities according to the corresponding heat value of the current commodity. Compared with a ranking algorithm only considering a time dimension, the method and the device have the advantages that various parameters contained in the user relation table corresponding to the user are also considered as the commodity ranking algorithm, and the influence relation between the user and the user is considered from the space dimension, so that commodities provided for the user are more accurate, the user experience is enhanced, and meanwhile the commodity volume can be effectively increased.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrases "comprising … …" or "comprising … …" does not exclude the presence of additional elements in a process, method, article, or terminal that comprises the element. Further, herein, "greater than," "less than," "more than," and the like are understood to exclude the present numbers; the terms "above", "below", "within" and the like are to be understood as including the number.
As will be appreciated by one skilled in the art, the above-described embodiments may be provided as a method, apparatus, or computer program product. These embodiments may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. All or part of the steps in the methods according to the embodiments may be implemented by a program instructing associated hardware, where the program may be stored in a storage medium readable by a computer device and used to execute all or part of the steps in the methods according to the embodiments. The computer devices, including but not limited to: personal computers, servers, general-purpose computers, special-purpose computers, network devices, embedded devices, programmable devices, intelligent mobile terminals, intelligent home devices, wearable intelligent devices, vehicle-mounted intelligent devices, and the like; the storage medium includes but is not limited to: RAM, ROM, magnetic disk, magnetic tape, optical disk, flash memory, U disk, removable hard disk, memory card, memory stick, network server storage, network cloud storage, etc.
The various embodiments described above are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a computer apparatus to produce a machine, such that the instructions, which execute via the processor of the computer apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer device to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer apparatus to cause a series of operational steps to be performed on the computer apparatus to produce a computer implemented process such that the instructions which execute on the computer apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Although the embodiments have been described, once the basic inventive concept is obtained, other variations and modifications of these embodiments can be made by those skilled in the art, so that the above embodiments are only examples of the present invention, and not intended to limit the scope of the present invention, and all equivalent structures or equivalent processes using the contents of the present specification and drawings, or any other related technical fields, which are directly or indirectly applied thereto, are included in the scope of the present invention.
Claims (8)
1. A method for temporal and spatial based e-commerce popularity ranking, the method comprising the steps of:
receiving an operation instruction of a user on the commodity, and updating the influence factor of each user on the commodity in the user relation table according to the user relation table corresponding to the user;
according to the updated influence factors, recalculating the corresponding heat value of the current commodity; the heat value comprises a time heat value and a space heat value, the time heat value is determined according to a timestamp of an operation instruction of the commodity, and the space heat value is determined according to the updated influence factor;
reordering the coordinate positions of the commodities according to the corresponding heat value of the current commodity;
the user relation table comprises an area position relation table, and the area position relation table is used for recording the coordinate position relation between the user and the user; the step of updating the influence factors of each user in the user relation table according to the user relation table corresponding to the user comprises the following steps: when an operation instruction of a certain user on the commodity is received, adjusting the influence factors of other users belonging to the same area range with the user coordinate position on the commodity in the area position relation table.
2. The method for temporal and spatial based e-commerce popularity ranking of claim 1, wherein the user relationship table comprises a clustered user relationship table, and wherein the step of determining the spatial popularity value based on the updated influence factor comprises: obtaining the influence factors of all users belonging to the same cluster in the cluster user relation table aiming at a certain commodity, sequencing according to the size of the influence factors, recalculating the influence factors corresponding to the commodity according to a preset percentage, and determining a spatial heat value according to the recalculated influence factors.
3. The method for temporal and spatial based e-commerce popularity ranking of claim 1, wherein the user relationship table comprises a clustered user relationship table, and wherein the step of determining the spatial popularity value based on the updated influence factor comprises: when an operation instruction of a certain user on the commodity is received, adjusting the influence factors of other users belonging to the same cluster with the user on the commodity in the cluster user relation table.
4. The method for time and space based e-commerce heat ranking of claim 1, wherein the step of "recalculating the heat value corresponding to the current commodity according to the updated influence factor" comprises:
setting a first weight value and a second weight value;
calculating the product of the first weight value and the time heat value to obtain a first product value, and calculating the product of the second weight value and the space heat value to obtain a second product value;
and accumulating the first product value and the second product value to obtain a final heat value corresponding to the current commodity.
5. The device for ranking the e-commerce popularity based on time and space is characterized by comprising an instruction receiving unit, an influence factor updating unit, a popularity value calculating unit and a sorting unit;
the instruction receiving unit is used for receiving an operation instruction of a user on the commodity, and the influence factor updating unit is used for updating the influence factor of each user on the commodity in the user relation table according to the user relation table corresponding to the user;
the heat value calculating unit is used for recalculating the heat value corresponding to the current commodity according to the updated influence factor; the heat value comprises a time heat value and a space heat value, the time heat value is determined according to a timestamp of an operation instruction of the commodity, and the space heat value is determined according to the updated influence factor;
the sorting unit is used for re-sorting the coordinate positions of the commodities according to the heat value corresponding to the current commodity;
the user relation table comprises an area position relation table, and the area position relation table is used for recording the coordinate position relation between the user and the user; the "influence factor updating unit is configured to update the influence factor of each user in the user relationship table according to the user relationship table corresponding to the user" includes: when the instruction receiving unit receives an operation instruction of a certain user on the commodity, the influence factor updating unit is used for adjusting the influence factors of other users belonging to the same area range with the user coordinate position in the area position relation table on the commodity.
6. The apparatus of claim 5, wherein the user relationship table comprises a cluster user relationship table, and wherein the determining the spatial heat value according to the updated influence factor comprises: the influence factor updating unit is used for acquiring influence factors of all users belonging to the same cluster in the cluster user relation table aiming at a certain commodity, sorting according to the size of the influence factors, recalculating the influence factors corresponding to the commodity according to a preset percentage, and the heat value calculating unit is used for determining a space heat value according to the recalculated influence factors.
7. The apparatus for temporal and spatial based e-commerce popularity ranking of claim 5, wherein the user relationship table comprises a clustered user relationship table, and wherein the step of determining the spatial popularity value based on the updated influence factor comprises: when an operation instruction of a certain user on the commodity is received, adjusting the influence factors of other users belonging to the same cluster with the user on the commodity in the cluster user relation table.
8. The apparatus for temporal and spatial based e-commerce popularity ranking of claim 5, wherein the popularity value calculation unit comprises a weight value setting unit, a product value calculation unit and a final value calculation unit; the "the heat value calculating unit is configured to recalculate the heat value corresponding to the current commodity according to the updated influence factor" includes:
the weight value setting unit is used for setting a first weight value and a second weight value;
the product value calculation unit is used for calculating the product of the first weight value and the time heat value to obtain a first product value, and calculating the product of the second weight value and the space heat value to obtain a second product value;
and the final value calculating unit is used for accumulating the first product value and the second product value to obtain a final heat value corresponding to the current commodity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710389131.7A CN107220881B (en) | 2017-05-27 | 2017-05-27 | Method and device for ranking e-commerce popularity based on time and space |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710389131.7A CN107220881B (en) | 2017-05-27 | 2017-05-27 | Method and device for ranking e-commerce popularity based on time and space |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107220881A CN107220881A (en) | 2017-09-29 |
| CN107220881B true CN107220881B (en) | 2020-12-18 |
Family
ID=59948094
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710389131.7A Active CN107220881B (en) | 2017-05-27 | 2017-05-27 | Method and device for ranking e-commerce popularity based on time and space |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107220881B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109561311A (en) * | 2018-12-07 | 2019-04-02 | 莆田学院 | A kind of 3 d video encoding bit rate control method and storage equipment based on the domain ρ |
| CN112269938A (en) * | 2020-11-16 | 2021-01-26 | 北京百度网讯科技有限公司 | Information display method and device, electronic equipment and storage medium |
| CN112330427B (en) * | 2021-01-05 | 2021-03-26 | 中智关爱通(南京)信息科技有限公司 | Method, electronic device and storage medium for commodity sorting |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2933770A1 (en) * | 2012-12-14 | 2015-10-21 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and system for pushing mobile application |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103425703B (en) * | 2012-05-25 | 2018-07-27 | 深圳市腾讯计算机系统有限公司 | A kind for the treatment of method and apparatus of the network information |
| CN105335365A (en) * | 2014-05-30 | 2016-02-17 | 小米科技有限责任公司 | Method and apparatus for placing order, server and terminal |
-
2017
- 2017-05-27 CN CN201710389131.7A patent/CN107220881B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2933770A1 (en) * | 2012-12-14 | 2015-10-21 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and system for pushing mobile application |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107220881A (en) | 2017-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106651542B (en) | Article recommendation method and device | |
| CN110413877A (en) | A kind of resource recommendation method, device and electronic equipment | |
| CN108108821A (en) | Model training method and device | |
| CN106850750B (en) | Method and device for pushing information in real time | |
| TW201923675A (en) | Information recommendation method, device and apparatus | |
| CN110413870A (en) | Method of Commodity Recommendation, device and server | |
| CN110008397B (en) | Recommendation model training method and device | |
| CN108021708B (en) | Content recommendation method and device and computer readable storage medium | |
| CN107220881B (en) | Method and device for ranking e-commerce popularity based on time and space | |
| CN111782947B (en) | Search content display method and device, electronic equipment and storage medium | |
| CN110851699A (en) | Deep reinforcement learning-based information flow recommendation method, device, equipment and medium | |
| CN109168047B (en) | Video recommendation method and device, server and storage medium | |
| WO2013155440A2 (en) | Method, web server and web browser of providing information | |
| CN112445970B (en) | Information recommendation method and device, electronic equipment and storage medium | |
| CN111414532B (en) | Information recommendation method, equipment and machine-readable storage medium | |
| CN111695960A (en) | Object recommendation system, method, electronic device and storage medium | |
| CN108595493A (en) | Method for pushing and device, storage medium, the electronic device of media content | |
| US20150073932A1 (en) | Strength Based Modeling For Recommendation System | |
| CN114168843A (en) | Search word recommendation method, device and storage medium | |
| CN110225407A (en) | The acquisition methods and device and computer readable storage medium of a kind of played data | |
| CN112132660A (en) | Commodity recommendation method, system, device and storage medium | |
| CN111680213B (en) | Information recommendation method, data processing method and device | |
| CN106156351B (en) | Multimedia resource recommendation information generation method and device | |
| CN109255645B (en) | Consumption prediction method and device and electronic equipment | |
| CN110570271A (en) | information recommendation method and device, electronic equipment and readable 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |