CN113327152A - Commodity recommendation method and device, computer equipment and storage medium - Google Patents
Commodity recommendation method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN113327152A CN113327152A CN202110643084.0A CN202110643084A CN113327152A CN 113327152 A CN113327152 A CN 113327152A CN 202110643084 A CN202110643084 A CN 202110643084A CN 113327152 A CN113327152 A CN 113327152A
- Authority
- CN
- China
- Prior art keywords
- commodity
- index
- objects
- time
- sales
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 63
- 238000004364 calculation method Methods 0.000 claims abstract description 45
- 238000011156 evaluation Methods 0.000 claims abstract description 19
- 230000008859 change Effects 0.000 claims description 30
- 238000001816 cooling Methods 0.000 claims description 15
- 230000006399 behavior Effects 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 10
- 238000004891 communication Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 8
- 238000012545 processing Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000001413 cellular effect Effects 0.000 description 2
- 238000005034 decoration Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013179 statistical model Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Landscapes
- Business, Economics & Management (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a commodity recommendation method, a commodity recommendation device, commodity recommendation equipment and a commodity recommendation medium, wherein the method comprises the following steps: determining a freshness index, a sales index and a competition index corresponding to each commodity object in a commodity database, and performing weighted summation on the freshness index, the sales index and the competition index according to a preset heat calculation formula to obtain a heat index corresponding to the commodity object; and selecting a commodity recommendation list according to the popularity index, wherein the commodity recommendation list comprises a plurality of selected commodity objects, and the popularity index of the selected commodity objects is higher than that of the unselected commodity objects. The method is comprehensive and scientific, is very suitable for calculating the heat indexes of commodities of different e-commerce platforms, and can efficiently and quickly perform unified heat index evaluation on different e-commerce independent stations; the obtained commodity recommendation list can be used for more effectively recommending hot-market commodities for the seller users, so that the time for selecting commodities is saved, the seller users are prevented from selecting by mistake and missing, and the efficiency of selecting commodities by merchants is greatly improved.
Description
Technical Field
The embodiment of the application relates to the technical field of internet, in particular to a commodity recommendation method and device, computer equipment and a storage medium.
Background
With the development of the cross-border e-commerce field in recent years, more and more new merchants join the e-commerce industry, and the merchants often need to spend a long time on selecting products to determine the goods to be sold, so a method for recommending hot sales products to the merchants is urgently needed.
Meanwhile, cross-border e-commerce is different from the traditional e-commerce, the information of the commodities of the cross-border e-commerce is sourced from each independent station and each e-commerce platform, the unification is difficult, and the difficulty exists in how to select a relatively comprehensive standard to evaluate the popularity of the commodities. In the existing goods selection method, goods are recommended to merchants based on the ranking of a goods list, so that the dimensionality reflecting the popularity of the goods is single.
Disclosure of Invention
The embodiment of the invention provides a commodity recommendation method, a commodity recommendation device, computer equipment and a storage medium.
In order to solve the above technical problem, the embodiment of the present invention adopts a technical solution that: provided is a commodity recommendation method including:
determining a freshness index corresponding to each commodity object in a commodity database, wherein the freshness index is obtained by counting inflection point time of long tail distribution of the commodity database according to commodity shelf time and performing time attenuation calculation on the commodity shelf time of the commodity object by combining Newton's cooling law and the inflection point time;
determining a sales index of each commodity object in a commodity database, wherein the sales index is obtained by weighted calculation according to a plurality of evaluation scores reflecting the history or potential sales capacity of the commodity object;
determining a competition index corresponding to each commodity object in a commodity database, wherein the competition index is obtained by calculation according to ranking change data of the commodity object in a ranking list corresponding to the class of the E-commerce platform to which the commodity object belongs;
for each commodity object, carrying out weighted summation on the corresponding freshness index, sales index and competition index according to a preset heat calculation formula to obtain a heat index corresponding to the commodity object;
and selecting a commodity recommendation list according to the popularity index of each commodity object, wherein the commodity recommendation list comprises a plurality of selected commodity objects, and the popularity index of the selected commodity objects is higher than that of the unselected commodity objects.
Optionally, the step of determining the freshness index corresponding to each commodity object in the commodity database includes:
acquiring commodity shelving time recorded by first shelving of each commodity object in a commodity database, classifying and summarizing the commodity objects according to the commodity shelving time, and determining the quantity of the commodity objects shelving in each time period;
determining inflection point time of long tail distribution according to the statistical characteristics of long tail distribution presented by the number of commodity objects on shelves in each time period;
and (4) applying Newton's cooling law and inflection point time to perform time attenuation calculation on the commodity shelf-loading time of each commodity object in the commodity database, and taking the calculation result as a freshness index corresponding to each commodity object.
Optionally, the step of determining the sales index of each commodity object in the commodity database includes:
determining any two or more indexes of each commodity object in the commodity database as follows: the method comprises the following steps of advertising data scoring, ranking scoring, total distribution website scoring, evaluation data scoring and sales data scoring, wherein the scoring of all indexes is unified into the same total scoring standard;
and weighting and summarizing the plurality of determined indexes for each commodity object to obtain the sales index of the commodity object.
Optionally, the step of determining a competition index corresponding to each commodity object in the commodity database includes:
acquiring specific ranking list data of a plurality of time nodes within a certain historical time corresponding to each commodity object;
for each commodity object, calculating a comprehensive change rate of the commodity object according to the plurality of time nodes, wherein the comprehensive change rate is a ratio between a difference value of a score of a specific ranking list of the commodity object obtained at the last time node and a score of the specific ranking list of the commodity object obtained at the earliest time node and a sum of scores of the specific ranking lists of the commodity object obtained at all time nodes;
and regarding each commodity object, taking the ratio of the difference value between the comprehensive change rate and the minimum comprehensive change rate obtained from all the commodity objects and the difference value between the maximum comprehensive change rate and the minimum comprehensive change rate in all the commodity objects as the competition index.
Optionally, for each commodity object, performing weighted summation on the corresponding freshness index, sales index and competition index which are unified to the same total score standard according to a preset heat calculation formula, and in the step of obtaining the corresponding heat index of the commodity object, the freshness index, sales index and competition index are all unified to the same total score standard for metering.
Optionally, the commodity recommendation method includes the following post-steps:
and recommending the commodity recommendation list to seller users registered in each independent transaction site maintained by the e-commerce platform.
Optionally, the commodity recommendation method includes the following pre-steps:
the commodity database is preferably selected to include only the commodity objects of which the historical trading behavior information only includes the specific physical positions.
In order to solve the above technical problem, an embodiment of the present invention further provides a commodity recommendation device, including:
the freshness index module is used for determining the freshness index corresponding to each commodity object in the commodity database, counting the inflection point time of long tail distribution of the commodity database according to the commodity shelf time, and performing time attenuation calculation on the commodity shelf time of the commodity object by combining Newton's cooling law and the inflection point time;
the sales index module is used for determining the sales index of each commodity object in the commodity database, and the sales index is obtained by weighted calculation according to a plurality of evaluation scores reflecting the history or potential sales capacity of the commodity object;
the competition index module is used for determining competition indexes corresponding to the commodity objects in the commodity database, and the competition indexes are obtained by calculation according to ranking change data of the commodity objects in ranking list corresponding to the categories of the electronic commerce platform to which the commodity objects belong;
the weighting calculation module is used for weighting and summing the corresponding freshness index, sales index and competition index of each commodity object according to a preset popularity calculation formula to obtain the popularity index corresponding to the commodity object;
and the commodity recommendation module is used for selecting a commodity recommendation list according to the popularity indexes of the commodity objects, wherein the commodity recommendation list comprises a plurality of selected commodity objects, and the popularity indexes of the selected commodity objects are higher than those of the unselected commodity objects.
In order to solve the above technical problem, an embodiment of the present invention further provides a computer device, including a memory and a processor, where the memory stores computer-readable instructions, and the computer-readable instructions, when executed by the processor, cause the processor to execute the steps of the product recommendation method.
In order to solve the above technical problem, an embodiment of the present invention further provides a storage medium storing computer-readable instructions, which, when executed by one or more processors, cause the one or more processors to perform the steps of the article recommendation method.
Compared with the prior art, the embodiment of the invention has the beneficial effects that:
1. according to the method, a data source and a statistical mode are optimized, a new index, a sales index and a competition index corresponding to each commodity object in a commodity database are determined, then the new index, the sales index and the competition index are subjected to weighted summation according to a preset popularity calculation formula, and finally an index reflecting the popularity of the commodity is obtained. Compared with the existing method for obtaining the commodity popularity based on the single-dimension list ranking, the method for obtaining the commodity popularity index is more comprehensive and scientific, and popularity ranking data of the transaction commodities can be screened out.
2. The numerical value obtained by the method conforms to the unified heat evaluation standard, so that the method is not influenced by evaluation standards of different independent transaction sites in different e-commerce platforms and cross-border e-commerce platforms, is very suitable for carrying out unified heat index calculation on commodities of different e-commerce platforms and different independent transaction sites, and particularly can carry out unified heat index evaluation on different e-commerce independent sites efficiently and quickly.
3. Due to the beneficial effects, the obtained commodity recommendation list can be used for more effectively recommending hot-market commodities to the seller users registered in each independent transaction site maintained by the e-commerce platform, so that the time for selecting the commodities is saved, the seller users are prevented from selecting by mistake and missing, and the efficiency of selecting the commodities by the merchants is greatly improved.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a schematic diagram of a typical network deployment architecture related to implementing the technical solution of the present application;
FIG. 2 is a schematic diagram of a basic flow chart of a method for recommending a commodity object according to an embodiment of the present application;
FIG. 3 is a schematic flow chart of the specific steps of step S100 in FIG. 2;
FIG. 4 is a schematic flow chart of the specific steps of step S200 in FIG. 2;
FIG. 5 is a schematic flow chart illustrating the specific steps of step S300 in FIG. 2;
FIG. 6 is a schematic diagram of a basic flow chart of a merchandise object recommendation method according to another embodiment of the present application;
FIG. 7 is a schematic diagram illustrating a basic flow chart of a merchandise object recommendation method according to another embodiment of the present application;
FIG. 8 is a graphical user interface diagram of a method for merchandise recommendation in accordance with an embodiment of the present application;
FIG. 9 is a schematic diagram of a basic structure of a merchandise recommendation device according to an embodiment of the present application;
fig. 10 is a block diagram of a basic structure of a computer device according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary only for the purpose of explaining the present application and are not to be construed as limiting the present application.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It will be understood by those within the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
As used herein, a "terminal" includes both devices that are wireless signal receivers, devices that have only wireless signal receivers without transmit capability, and devices that have receive and transmit hardware, devices that have receive and transmit hardware capable of performing two-way communication over a two-way communication link, as will be understood by those skilled in the art. Such a device may include: a cellular or other communication device having a single line display or a multi-line display or a cellular or other communication device without a multi-line display; PCS (Personal Communications Service), which may combine voice, data processing, facsimile and/or data communication capabilities; a PDA (Personal Digital Assistant), which may include a radio frequency receiver, a pager, internet/intranet access, a web browser, a notepad, a calendar and/or a GPS (Global Positioning System) receiver; a conventional laptop and/or palmtop computer or other device having and/or including a radio frequency receiver. As used herein, a "terminal" may be portable, transportable, installed in a vehicle (aeronautical, maritime, and/or land-based), or situated and/or configured to operate locally and/or in a distributed fashion at any other location(s) on earth and/or in space. The "terminal" used herein may also be a communication terminal, a web-enabled terminal, a music/video playing terminal, such as a PDA, an MID (Mobile Internet Device) and/or a Mobile phone with music/video playing function, and may also be a smart tv, a set-top box, etc.
The hardware referred to by the names "server", "client", "service node", etc. is essentially an electronic device with the performance of a personal computer, and is a hardware device having necessary components disclosed by the von neumann principle such as a central processing unit (including an arithmetic unit and a controller), a memory, an input device, an output device, etc., a computer program is stored in the memory, and the central processing unit calls a program stored in an external memory into the internal memory to run, executes instructions in the program, and interacts with the input and output devices, thereby completing a specific function.
It should be noted that the concept of "server" as referred to in this application can be extended to the case of a server cluster. According to the network deployment principle understood by those skilled in the art, the servers should be logically divided, and in physical space, the servers may be independent from each other but can be called through an interface, or may be integrated into one physical computer or a set of computer clusters. Those skilled in the art will appreciate this variation and should not be so limited as to restrict the implementation of the network deployment of the present application. Referring to fig. 1, the hardware basis required for implementing the related art embodiments of the present application may be deployed according to the architecture shown in the figure. The server 80 is deployed at the cloud end, and serves as a business server, and is responsible for further connecting to a related data server and other servers providing related support, so as to form a logically associated server cluster to provide services for related terminal devices, such as a smart phone 81 and a personal computer 82 shown in the figure, or a third-party server (not shown in the figure). Both the smart phone and the personal computer can access the internet through a known network access mode, and establish a data communication link with the cloud server 80 so as to run a terminal application program related to the service provided by the server.
For the server, the application program is usually constructed as a service process, and a corresponding program interface is opened for remote call of the application program running on various terminal devices.
The application program refers to an application program running on a server or a terminal device, the application program implements the related technical scheme of the application in a programming mode, a program code of the application program can be saved in a nonvolatile storage medium which can be identified by a computer in a form of a computer executable instruction, and is called into a memory by a central processing unit to run, and the related device of the application is constructed by running the application program on the computer.
For the server, the application program is usually constructed as a service process, and a corresponding program interface is opened for remote call of the application program running on various terminal devices.
Referring to fig. 2, fig. 2 is a basic flow chart of the method for recommending a commodity object according to the embodiment.
As shown in fig. 2, the method for recommending a commodity object disclosed in the present application includes steps S100 to S500, which are specifically as follows:
step S100, determining a freshness index corresponding to each commodity object in a commodity database, wherein the freshness index is obtained by counting inflection point time of long tail distribution of the commodity database according to commodity shelf time and performing time attenuation calculation on the commodity shelf time of the commodity object by combining Newton' S cooling law and the inflection point time;
in this embodiment, the commodity database is preferably a relational database, and may be any one of Oracle, Sybase, informax, and INGRES, and the operation of the method is performed, and the corresponding information of each commodity object included in the commodity database is obtained by sorting and capturing according to a corresponding sorting system, such as a home appliance class, a garment class, and the like, pre-established on an e-commerce platform. The corresponding information of each commodity object comprises commodity names, commodity shelf time, commodity sales quantity and the like. The commodity shelf-loading time is the first shelf-loading time of any commodity.
The commodity objects exist in a plurality of independent commodity transaction stations, hereinafter referred to as independent stations. The independent stations are independent transaction stations supported by a cross-border e-commerce platform known by those skilled in the art, and since the corresponding sales volume information of the commodity objects on each independent station is different, for example, the sales volume of the commodity named as a is ranked as 1 st on the X independent station, and the sales volume of the commodity named as a is ranked as 4 th on the Y independent station, it becomes a problem to be solved urgently to judge the hot commodity object and recommend the commodity, which is an improvement point of the present application compared with the prior art.
The newton's law of cooling and the method of obtaining and calculating inflection point times are disclosed below:
referring to fig. 3, fig. 3 is a step of obtaining a freshness index corresponding to each commodity object in the commodity database in an embodiment, which specifically includes:
step S110: and acquiring commodity shelving time recorded by the first shelving of each commodity object in the commodity database, classifying and summarizing the commodity objects according to the commodity shelving time, and determining the quantity of the commodity objects shelving in each time period.
The time-to-live can be set by a person skilled in the art with the accuracy required in practice, for example to date or hour, minute and second. Similarly, the time periods may be set to several days or several hours of a day, respectively.
Step S120: determining inflection point time of long tail distribution according to the statistical characteristics of long tail distribution presented by the number of commodity objects on shelves in each time period;
the long tail distribution statistics are preferred statistical models known to those skilled in the art, and those skilled in the art can also calculate from other statistical models: by applying statistical knowledge, the commodity first-time shelving time of commodity objects is used as an index item, and the total quantity of the commodity objects to be shelved in each year or each month is counted year by year or month by month, so that a change curve or a column diagram is formed, and the inflection point time in the whole curve can be calculated according to the long-tail distribution principle.
Step S130: and (4) applying Newton's cooling law and inflection point time to perform time attenuation calculation on the commodity shelf-loading time of each commodity object in the commodity database, and taking the calculation result as a freshness index corresponding to each commodity object.
The newton's law of cooling is:
T^′＝-α(T-H)
in this embodiment, T (T) is a time (T) function of the heat (T) of any merchandise object. The rate of heat change (cooling), i.e., the decay rate, is the derivative of the heat function, T' (T). H represents the average heat of the commodity object, and T (t) -H is the difference value between the current heat and the average heat. This is a positive value since the current heat is higher than the average heat. The constant α (α >0) represents a proportional relationship between the average heat and the cooling rate. The negative sign in the front indicates a cooling down. Those skilled in the art can adjust the parameter α according to the specific data distribution to make the attenuation rate meet the service requirement. An exemplary formula that incorporates the integral form of newton's law of cooling is as follows:
wherein:
sale _ index represents freshness index;
g represents an attenuation coefficient, and a person skilled in the art can adjust parameters according to specific data distribution to enable the attenuation rate to meet the service requirement;
diff _ days represents the difference between the commodity shelf time and the current day of the day;
wherein 7 is a self-defined period, and can be set by a person skilled in the art according to actual requirements.
That is, the freshness index is decayed by a preset decay coefficient in a period of 7 days.
Through the method, the freshness index corresponding to each commodity object in the commodity database can be quickly obtained and used for calculation in the subsequent steps of the application.
Step S200, determining the sales index of each commodity object in the commodity database, wherein the sales index is obtained by weighted calculation according to a plurality of evaluation scores reflecting the history or potential sales capability of the commodity object.
In an embodiment, the step of specifically obtaining the sales index corresponding to each commodity object in the commodity database is shown in fig. 3, and includes:
step S210, determining any two or more indexes of each commodity object in the commodity database as follows: the method comprises the following steps of advertising data scoring, ranking scoring, total distribution website scoring, evaluation data scoring and sales data scoring, wherein the scoring of all indexes is unified into the same total scoring standard;
in some embodiments, the advertisement data score is obtained according to the variation of the commodity object in the latest certain time period of the advertisement amount and the position information, such as the last 3 days, the last 7 days and the last 14 days, to obtain the variation of the commodity advertisement in different time periods, and then the variation is multiplied by different weight values to be added, and the weight values can be adjusted according to actual demands, so as to obtain the commodity object advertisement data score. An exemplary formula is as follows:
wherein: ad _ score represents advertisement data score;
min (ad _ hot) represents the minimum advertisement weight;
max (ad _ hot) represents the maximum advertisement weight;
ad _ hot represents the advertisement weight, which is calculated as follows:
ad_hot＝sum(index_weight×time_weight)
wherein:
index _ weight represents the ad position weight, e.g., 4 for the first three ad positions in the ad list and 3 for the second;
time _ weight represents the advertisement time weight, e.g., when the advertisement is on shelf for 2 days 3, 3 days 7, 4 days 14;
that is, the above formula shows that the advertisement data score of the commodity object is obtained by dividing the difference between the advertisement weight of the commodity object minus the minimum advertisement weight in all the commodity objects by the difference between the maximum advertisement weight in all the commodity objects and the minimum advertisement weight in all the commodity objects, and multiplying the ratio by 100.
In order to prevent the denominator from being meaningless, 1 is added, and the ratio is multiplied by 100, so that the scoring result is set within 100, the value is conveniently and visually obtained, and the subsequent calculation is convenient, the functions of adding 1 to the denominator and multiplying 100 by the ratio in the formula disclosed below are the same, and details are omitted below.
The advertisement data score comprehensively reflects the browsed condition of the commodity object in some recent time periods, and also reflects the potential sale capability of the commodity object to some extent.
In some embodiments, the ranking score of the list is based on the ranking value and the score of the list of the classification system pre-established on the e-commerce platform where the commodity object is located, for example, a certain type of television of a certain brand is ranked the third in the month household appliance hot-selling ranking list of the e-commerce platform, is ranked the second in the month popularity digital ranking list of the e-commerce platform, and the like, each spu may be specifically refined, and the ranking score of the commodity is obtained through comprehensive calculation. An exemplary formula is as follows:
wherein: rank score represents a ranking score;
rank represents the ranking of the list where the commodity is located;
min (rank) represents the minimum list ranking score;
max (rank) represents the maximum ranking score of the leaderboard.
That is, the ranking score is obtained by dividing the difference between the highest ranking in all the commodity objects and the lowest ranking in all the commodity objects by the difference between the highest ranking in all the commodity objects and the lowest ranking in all the commodity objects, and multiplying the ratio by 100.
The list ranking score comprehensively reflects the relative popularity of the commodity object in the commodity objects of the same category, and reflects the historical sales capability of the commodity object.
In some embodiments, the total distribution point score is obtained by performing a comprehensive calculation according to the number of stores in the category of the classification system pre-established on the e-commerce platform where the commodity object is located, and an exemplary formula of the total distribution point score of the commodity object is as follows:
wherein: the shop _ sore represents the total score of the distribution network points;
shop _ num represents the number of selling shops;
min (shop _ num) represents the minimum number of selling shops;
max (shop _ num) represents the maximum number of selling shops.
That is, the distribution point total score is obtained by dividing the difference between the number of the selling stores of the commodity object minus the minimum number of the selling stores of all the commodity objects by the difference between the maximum number of the selling stores of all the commodity objects and the minimum number of the selling stores of all the commodity objects, and multiplying the ratio by 100.
It will be appreciated that the total score of the distribution points collectively reflects the potential sales potential of the commodity object.
In some embodiments, the evaluation data score is calculated according to the evaluation and scoring information of the e-commerce platform where the commodity object is located, and an exemplary formula is as follows:
wherein: comment _ sore represents the rating data score;
score represents total score of the commodity;
min (score) represents the minimum total commodity score;
max (score) represents the maximum total score for the good.
That is, the evaluation data score is obtained by dividing the difference between the total commodity score of the commodity object minus the minimum total commodity score of all the commodity objects by the difference between the maximum total commodity score of all the commodity objects and the minimum total commodity score of all the commodity objects, and multiplying the ratio by 100.
The evaluation data score comprehensively reflects the popularity of the commodity object and reflects the historical sales capability of the commodity object.
In some embodiments, the sales data score is calculated by integrating the sales score of the merchant platform on which the commodity object is located, and an exemplary formula is as follows:
wherein: sample _ sore represents sales data score;
the calculation formula of the sample _ info is as follows:
sale _ info ═ c × historical sales + d ═ recent monthly sales increase
Where c and d represent the weight values for historical sales and recent monthly sales increments, respectively. That is, the sales data score is obtained by subtracting the difference between the minimum value of the historical sales and the increase number of sales in the last month calculated by a certain parameter in all the commodity objects from the sum of the historical sales and the increase number of sales in the last month calculated by a certain parameter in the commodity object, and dividing the difference between the maximum value of the historical sales and the increase number of sales in the last month calculated by a certain parameter in all the commodity objects, and multiplying the ratio by 100. The sales data scoring comprehensively reflects the comprehensive condition of the historical sales of the commodity object, and can intuitively reflect the historical sales capacity of the commodity object.
And S220, weighting and summarizing the plurality of determined indexes for each commodity object to obtain the sales index of the commodity object. The calculation formula is exemplified as follows:
sales index α ad _ score + β rank _ source + γ shop _ source + δ comment _ source + ε sample _ source
Where α, β, γ, δ, and ε all represent weights for different scores, and those skilled in the art can adjust the parameters according to actual traffic.
By the method, the sales index corresponding to each commodity object in the commodity database can be scientifically and intuitively obtained according to a unified evaluation standard.
And step S300, determining a competition index corresponding to each commodity object in the commodity database, wherein the competition index is calculated according to ranking change data of the commodity object in a ranking list corresponding to the commodity class of the E-commerce platform to which the commodity object belongs.
In an embodiment, the step of specifically obtaining the competition index corresponding to each commodity object in the commodity database is shown in fig. 4, and includes:
step S310, specific ranking list data of a plurality of time nodes within a certain historical time corresponding to each commodity object are obtained;
in this embodiment, a plurality of time nodes in a certain historical time can be obtained according to actual conditions, such as 12 pm to 2 pm in three days before a certain holiday, and 7 pm to 10 pm in the afternoon.
Step S320, calculating the comprehensive change rate of each commodity object according to the plurality of time nodes, wherein the comprehensive change rate is the ratio of the difference value of the score of the specific ranking list of the commodity object at the last time node and the score of the specific ranking list of the commodity object at the earliest time node to the sum of the scores of the specific ranking lists of the commodity object at all time nodes;
in this embodiment, the specific ranking list is derived from an internal self-building list of the e-commerce platform, and is specifically formed by mapping external website information such as amazon bsr or google trend to the e-commerce internal goods. The time node can be set to be accurate to the hour, minute or a certain date according to actual requirements.
The calculation formula of the integrated change rate of the commodity object is exemplified as follows:
rank _ list represents the last three day list change scores, with an exemplary formula as follows:
wherein:
rank _1t _ spec represents a day list score before the current date;
rank _2t _ spec represents the score of the list before the current date of two days;
rank _3t _ spec represents the three-day-ahead list score for the current date.
Step S330, regarding each commodity object, using the ratio of the difference value between the comprehensive change rate and the minimum comprehensive change rate obtained from all the commodity objects and the difference value between the maximum comprehensive change rate and the minimum comprehensive change rate in all the commodity objects as the competition index. An exemplary formula is as follows:
wherein: comp _ score represents the overall rate of change;
min (rank _ list) represents the score of the minimum specific ranking list;
max (rank _ list) represents the score of the maximum particular leaderboard.
That is, the total change rate is obtained by dividing the difference between the total product score of the product object and the score of the minimum specific ranking list among all the product objects by the difference between the score of the maximum specific ranking list among all the product objects and the score of the minimum specific ranking list among all the product objects, and multiplying the ratio by 100.
And S400, carrying out weighted summation on the freshness index, the sales index and the competition index corresponding to each commodity object according to a preset heat calculation formula to obtain the heat index corresponding to the commodity object.
The calculation formula is exemplified as follows:
heat index ═ α · sales index + β · competition index + γ · freshness index
Wherein α, β, γ represent weights of different scores, and those skilled in the art can adjust parameters according to actual services, and even can give the relevant user self-adjustment of these weights, and accordingly increase the weights of the relevant user according to the concerned different aspects.
The heat index calculated by the formula can form a relatively uniform and comprehensive standard for commodity objects of a plurality of commodity information sources of different independent stations.
And S500, selecting a commodity recommendation list according to the popularity indexes of the commodity objects, wherein the commodity recommendation list comprises a plurality of selected commodity objects, and the popularity indexes of the selected commodity objects are higher than those of the unselected commodity objects.
In this embodiment, the information of the related commodity objects included in the commodity push list selected according to the popularity index of each commodity object may be set by a person skilled in the art according to actual needs, for example, the ID names of the commodity objects, the pictures of the commodity objects, the prices of the commodity objects, and the like, and the display effect of the display page on the user equipment is as shown in fig. 8.
In this embodiment, a person skilled in the art may also sort the commodity objects according to the heat levels according to actual needs, and set the categories of the commodity recommendation list and the corresponding number of each category, for example, the commodity recommendation list includes the top 50 household electrical appliances with the highest heat levels.
The sales index, the competition index and the freshness index of each commodity object are weighted and summed according to a certain formula, the popularity index is obtained according to a unified evaluation standard, and the method is more scientific and comprehensive compared with a method for counting by only taking the list ranking as a single dimension; in addition, due to the fact that the commodity objects of a plurality of commodity information sources of different independent stations can be evaluated according to a relatively uniform and comprehensive standard, even if different E-commerce platforms with different commodity sales conditions, commodity popularity conditions and the like exist, effective commodity popularity ranking can be achieved, and the method and the system have wide applicability; due to the beneficial effects, the obtained commodity recommendation list can be used for more effectively recommending hot-market commodities to the seller users registered in each independent transaction site maintained by the e-commerce platform, so that the time for selecting the commodities is saved, the seller users are prevented from selecting by mistake and missing, and the efficiency of selecting the commodities by the merchants is greatly improved.
Referring to fig. 6, in some embodiments, in addition to the steps S100 to S500, the method for recommending a commodity further includes a step S600 of recommending the commodity recommendation list to a seller user registered at each independent trading site maintained by the e-commerce platform.
Referring to fig. 7, in some embodiments, in step S010, the merchandise database is filtered, so that the historical transaction behavior information of the merchandise objects in the database includes location information pointing to a specific physical location.
By carrying out the optimization that historical transaction behavior information only contains a specific physical position on the commodity database in advance, the commodity recommendation list obtained by the commodity recommendation method can better aim at the commodity popularity of a specific physical position, and the commodity recommendation method is favorable for a seller user to carry out commodity sales in a certain area in a targeted manner.
Further, a commodity recommending apparatus according to the present application may be constructed by functionalizing each embodiment of the above commodity object recommending method, and according to this idea, please refer to fig. 9, in which in an exemplary embodiment, the apparatus includes:
the freshness index module 11 is configured to determine a freshness index corresponding to each commodity object in the commodity database, where the freshness index is obtained by counting inflection time of long tail distribution in the commodity database according to commodity shelf time, and performing time decay calculation on the commodity shelf time of the commodity object by combining newton's cooling law and the inflection time;
a sales index module 12 for determining a sales index of each commodity object in the commodity database, the sales index being calculated by weighting a plurality of evaluation scores reflecting historical or potential sales capabilities of the commodity object;
the competition index module 13 is configured to determine a competition index corresponding to each commodity object in the commodity database, where the competition index is calculated according to ranking change data of the commodity object in a ranking list corresponding to the category of the electronic commerce platform to which the commodity object belongs;
the weighting calculation module 14 is configured to perform weighted summation on the freshness index, the sales index, and the competition index corresponding to each commodity object according to a preset popularity calculation formula to obtain a popularity index corresponding to the commodity object;
and the commodity recommending module 15 is configured to select a commodity recommending list according to the popularity index of each commodity object, where the commodity recommending list includes a plurality of selected commodity objects, and the popularity index of the selected commodity objects is higher than that of the non-selected commodity objects.
In order to solve the above technical problem, an embodiment of the present invention further provides a computer device. The commodity recommendation method comprises a central processing unit and a memory, wherein the central processing unit is used for calling and operating a computer program stored in the memory to execute the steps of the commodity recommendation method. Referring to fig. 10, fig. 10 is a block diagram of a basic structure of a computer device according to the present embodiment.
As shown in fig. 10, the internal structure of the computer device is schematically illustrated. The computer device includes a processor, a non-volatile storage medium, a memory, and a network interface connected by a system bus. The non-volatile storage medium of the computer device stores an operating system, a database and computer readable instructions, the database can store control information sequences, and the computer readable instructions can enable a processor to realize a commodity object recommendation method when being executed by the processor. The processor of the computer device is used for providing calculation and control capability and supporting the operation of the whole computer device. The memory of the computer device may have stored therein computer readable instructions that, when executed by the processor, may cause the processor to perform a method of merchandise object recommendation. The network interface of the computer device is used for connecting and communicating with the terminal. Those skilled in the art will appreciate that the architecture shown in fig. 9 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In this embodiment, the processor is configured to execute specific functions of the freshness index module 11, the sales index module 12, the competition index module 13, the weighting calculation module 14, and the commodity recommendation module 15 in the drawing, and the memory stores program codes and various types of data required for executing the modules. The network interface is used for data transmission to and from a user terminal or a server. The memory in this embodiment stores program codes and data necessary for executing all the submodules in the commodity object recommending apparatus, and the server can call the program codes and data of the server to execute the functions of all the submodules.
The present invention also provides a storage medium storing computer-readable instructions, which when executed by one or more processors, cause the one or more processors to perform the steps of the method for recommending an object of merchandise according to any of the above embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and can include the processes of the embodiments of the methods described above when the computer program is executed. The storage medium may be a non-volatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a Random Access Memory (RAM).
Those of skill in the art will appreciate that the various operations, methods, steps in the processes, acts, or solutions discussed in this application can be interchanged, modified, combined, or eliminated. Further, other steps, measures, or schemes in various operations, methods, or flows that have been discussed in this application can be alternated, altered, rearranged, broken down, combined, or deleted. Further, steps, measures, schemes in the prior art having various operations, methods, procedures disclosed in the present application may also be alternated, modified, rearranged, decomposed, combined, or deleted.
The foregoing is only a partial embodiment of the present application, and it should be noted that, for those skilled in the art, several modifications and decorations can be made without departing from the principle of the present application, and these modifications and decorations should also be regarded as the protection scope of the present application.
Claims (10)
1. A commodity recommendation method is characterized by comprising the following steps:
determining a freshness index corresponding to each commodity object in a commodity database, wherein the freshness index is obtained by counting inflection point time of long tail distribution of the commodity database according to commodity shelf time and performing time attenuation calculation on the commodity shelf time of the commodity object by combining Newton's cooling law and the inflection point time;
determining a sales index of each commodity object in a commodity database, wherein the sales index is obtained by weighted calculation according to a plurality of evaluation scores reflecting the history or potential sales capacity of the commodity object;
determining a competition index corresponding to each commodity object in a commodity database, wherein the competition index is obtained by calculation according to ranking change data of the commodity object in a ranking list corresponding to the class of the E-commerce platform to which the commodity object belongs;
for each commodity object, carrying out weighted summation on the corresponding freshness index, sales index and competition index according to a preset heat calculation formula to obtain a heat index corresponding to the commodity object;
and selecting a commodity recommendation list according to the popularity index of each commodity object, wherein the commodity recommendation list comprises a plurality of selected commodity objects, and the popularity index of the selected commodity objects is higher than that of the unselected commodity objects.
2. The article recommendation method according to claim 1, wherein: the step of determining the freshness index corresponding to each commodity object in the commodity database comprises the following steps:
acquiring commodity shelving time recorded by first shelving of each commodity object in a commodity database, classifying and summarizing the commodity objects according to the commodity shelving time, and determining the quantity of the commodity objects shelving in each time period;
determining inflection point time of long tail distribution according to the statistical characteristics of long tail distribution presented by the number of commodity objects on shelves in each time period;
and (4) applying Newton's cooling law and inflection point time to perform time attenuation calculation on the commodity shelf-loading time of each commodity object in the commodity database, and taking the calculation result as a freshness index corresponding to each commodity object.
3. The article recommendation method according to claim 1, wherein: the step of determining the sales index of each commodity object in the commodity database comprises the following steps:
determining any two or more indexes of each commodity object in the commodity database as follows: the method comprises the following steps of advertising data scoring, ranking scoring, total distribution website scoring, evaluation data scoring and sales data scoring, wherein the scoring of all indexes is unified into the same total scoring standard;
and weighting and summarizing the plurality of determined indexes for each commodity object to obtain the sales index of the commodity object.
4. The article recommendation method according to claim 1, wherein: the step of determining the competition index corresponding to each commodity object in the commodity database comprises the following steps:
acquiring specific ranking list data of a plurality of time nodes within a certain historical time corresponding to each commodity object;
for each commodity object, calculating a comprehensive change rate of the commodity object according to the plurality of time nodes, wherein the comprehensive change rate is a ratio between a difference value of a score of a specific ranking list of the commodity object obtained at the last time node and a score of the specific ranking list of the commodity object obtained at the earliest time node and a sum of scores of the specific ranking lists of the commodity object obtained at all time nodes;
and regarding each commodity object, taking the ratio of the difference value between the comprehensive change rate and the minimum comprehensive change rate obtained from all the commodity objects and the difference value between the maximum comprehensive change rate and the minimum comprehensive change rate in all the commodity objects as the competition index.
5. The article recommendation method according to claim 1, wherein: and aiming at each commodity object, carrying out weighted summation on the corresponding freshness index, sales index and competition index which are unified to the same total score standard according to a preset heat calculation formula, and obtaining the corresponding heat index of the commodity object, wherein the freshness index, the sales index and the competition index are all unified to the same total score standard for metering.
6. The commodity recommendation method according to any one of claims 1 to 5, comprising a post-step of: and recommending the commodity recommendation list to seller users registered in each independent transaction site maintained by the e-commerce platform.
7. The commodity recommendation method according to any one of claims 1 to 5, comprising a preceding step of: the commodity database is preferably selected to include only the commodity objects of which the historical trading behavior information only includes the specific physical positions.
8. An article recommendation device, comprising:
the freshness index module is used for determining the freshness index corresponding to each commodity object in the commodity database, counting the inflection point time of long tail distribution of the commodity database according to the commodity shelf time, and performing time attenuation calculation on the commodity shelf time of the commodity object by combining Newton's cooling law and the inflection point time;
the sales index module is used for determining the sales index of each commodity object in the commodity database, and the sales index is obtained by weighted calculation according to a plurality of evaluation scores reflecting the history or potential sales capacity of the commodity object;
the competition index module is used for determining competition indexes corresponding to the commodity objects in the commodity database, and the competition indexes are obtained by calculation according to ranking change data of the commodity objects in ranking list corresponding to the categories of the electronic commerce platform to which the commodity objects belong;
the weighting calculation module is used for weighting and summing the corresponding freshness index, sales index and competition index of each commodity object according to a preset popularity calculation formula to obtain the popularity index corresponding to the commodity object;
and the commodity recommendation module is used for selecting a commodity recommendation list according to the popularity indexes of the commodity objects, wherein the commodity recommendation list comprises a plurality of selected commodity objects, and the popularity indexes of the selected commodity objects are higher than those of the unselected commodity objects.
9. A computer device comprising a memory and a processor, the memory having stored therein computer-readable instructions that, when executed by the processor, cause the processor to perform the steps of the merchandise object recommendation method of any of claims 1-7.
10. A storage medium having computer-readable instructions stored thereon, which, when executed by one or more processors, cause the one or more processors to perform the steps of the method for merchandise object recommendation according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110643084.0A CN113327152B (en) | 2021-06-09 | 2021-06-09 | Commodity recommendation method, commodity recommendation device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110643084.0A CN113327152B (en) | 2021-06-09 | 2021-06-09 | Commodity recommendation method, commodity recommendation device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113327152A true CN113327152A (en) | 2021-08-31 |
| CN113327152B CN113327152B (en) | 2024-04-16 |
Family
ID=77420216
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110643084.0A Active CN113327152B (en) | 2021-06-09 | 2021-06-09 | Commodity recommendation method, commodity recommendation device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113327152B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114663155A (en) * | 2022-04-01 | 2022-06-24 | 广州华多网络科技有限公司 | Advertisement putting and selecting method and device, equipment, medium and product thereof |
| CN116109336A (en) * | 2023-04-13 | 2023-05-12 | 厦门蝉羽网络科技有限公司 | Method, system and storage medium for analysis and management of popularization data of electronic shop |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110852846A (en) * | 2019-11-11 | 2020-02-28 | 京东数字科技控股有限公司 | Processing method and device for recommended object, electronic equipment and storage medium |
| WO2020085786A1 (en) * | 2018-10-23 | 2020-04-30 | 오드컨셉 주식회사 | Style recommendation method, device and computer program |
| CN112149003A (en) * | 2020-10-28 | 2020-12-29 | 浙江集享电子商务有限公司 | Commodity community recommendation method and device and computer equipment |
| CN112288464A (en) * | 2020-10-16 | 2021-01-29 | 杭州贝嘟科技有限公司 | Commodity recommendation method and device, computer equipment and storage medium |
-
2021
- 2021-06-09 CN CN202110643084.0A patent/CN113327152B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020085786A1 (en) * | 2018-10-23 | 2020-04-30 | 오드컨셉 주식회사 | Style recommendation method, device and computer program |
| KR20200045668A (en) * | 2018-10-23 | 2020-05-06 | 오드컨셉 주식회사 | Method, apparatus and computer program for style recommendation |
| CN110852846A (en) * | 2019-11-11 | 2020-02-28 | 京东数字科技控股有限公司 | Processing method and device for recommended object, electronic equipment and storage medium |
| CN112288464A (en) * | 2020-10-16 | 2021-01-29 | 杭州贝嘟科技有限公司 | Commodity recommendation method and device, computer equipment and storage medium |
| CN112149003A (en) * | 2020-10-28 | 2020-12-29 | 浙江集享电子商务有限公司 | Commodity community recommendation method and device and computer equipment |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114663155A (en) * | 2022-04-01 | 2022-06-24 | 广州华多网络科技有限公司 | Advertisement putting and selecting method and device, equipment, medium and product thereof |
| CN116109336A (en) * | 2023-04-13 | 2023-05-12 | 厦门蝉羽网络科技有限公司 | Method, system and storage medium for analysis and management of popularization data of electronic shop |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113327152B (en) | 2024-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220036429A1 (en) | Systems and methods for generating recommendations using a corpus of data | |
| JP4886749B2 (en) | Recommended product selection device, recommended product selection program, and product search device | |
| TW202004618A (en) | Product recommendation method and device | |
| US20170243288A1 (en) | Delivery apparatus, delivery method, non-transitory computer readable storage medium, and delivery system | |
| CN108280749B (en) | Method and device for displaying service function entry | |
| US20130030950A1 (en) | Providing social product recommendations | |
| CN102282551A (en) | Automated decision support for pricing entertainment tickets | |
| US8135713B2 (en) | Sourcing controller | |
| CN113327152B (en) | Commodity recommendation method, commodity recommendation device, computer equipment and storage medium | |
| US20090024489A1 (en) | Reputation based display | |
| CN113095893A (en) | Method and device for determining sales of articles | |
| JP2016212926A (en) | Determination device, determination method, and determination program | |
| US20210109906A1 (en) | Clustering model analysis for big data environments | |
| US20230351428A1 (en) | Systems and methods for providing user offers based on efficient iterative recommendation structures | |
| US20150120761A1 (en) | Systems and methods for selecting components for inclusion in portions of a displayable file | |
| US20140236675A1 (en) | Information processing apparatus, information processing method, information processing program, and recording medium | |
| CN110570271A (en) | information recommendation method and device, electronic equipment and readable storage medium | |
| US20150254651A1 (en) | Optimizing financial transactions network flow | |
| CN111597237A (en) | Data query result generation method and device, electronic equipment and storage medium | |
| CN110490682B (en) | Method and device for analyzing commodity attributes | |
| US20220292552A1 (en) | Systems and Methods for Generating Efficient Iterative Recommendation Structures | |
| CN113327151A (en) | Commodity object recommendation method and device, computer equipment and storage medium | |
| CN114461918A (en) | Article recommendation method and device, electronic equipment and storage medium | |
| CN114169965A (en) | Commodity similarity matching method and device, equipment, medium and product thereof | |
| CN113421148A (en) | Commodity data processing 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |