CN116402545B - Data analysis processing method and unmanned retail terminal - Google Patents
Data analysis processing method and unmanned retail terminal Download PDFInfo
- Publication number
- CN116402545B CN116402545B CN202310655693.7A CN202310655693A CN116402545B CN 116402545 B CN116402545 B CN 116402545B CN 202310655693 A CN202310655693 A CN 202310655693A CN 116402545 B CN116402545 B CN 116402545B
- Authority
- CN
- China
- Prior art keywords
- sales
- sales terminal
- radius
- data
- terminal
- 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
- 238000007405 data analysis Methods 0.000 title claims abstract description 35
- 238000003672 processing method Methods 0.000 title claims abstract description 26
- 238000004458 analytical method Methods 0.000 claims abstract description 54
- 238000000034 method Methods 0.000 claims abstract description 23
- 238000012549 training Methods 0.000 claims abstract description 17
- 238000013507 mapping Methods 0.000 claims description 11
- 230000002860 competitive effect Effects 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 abstract description 16
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 230000000875 corresponding effect Effects 0.000 description 31
- 230000000694 effects Effects 0.000 description 4
- 235000020188 drinking water Nutrition 0.000 description 3
- 239000003651 drinking water Substances 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 235000013361 beverage Nutrition 0.000 description 2
- 235000009508 confectionery Nutrition 0.000 description 2
- 235000013305 food Nutrition 0.000 description 2
- 235000013402 health food Nutrition 0.000 description 2
- 235000011888 snacks Nutrition 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000474 nursing effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000007306 turnover Effects 0.000 description 1
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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
- G06Q30/0281—Customer communication at a business location, e.g. providing product or service information, consulting
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07F—COIN-FREED OR LIKE APPARATUS
- G07F11/00—Coin-freed apparatus for dispensing, or the like, discrete articles
- G07F11/004—Restocking arrangements therefor
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Control Of Vending Devices And Auxiliary Devices For Vending Devices (AREA)
Abstract
The invention discloses a data analysis processing method and an unmanned retail terminal, wherein the method comprises the following steps: acquiring associated building types respectively corresponding to each sales terminal through a cloud server, and acquiring distance data of each associated building type and the sales terminal; acquiring commodity sales data of each sales terminal in a set period; taking the associated building type of each sales terminal as input data, taking a free selling commodity set of each sales terminal as output data, and inputting a prediction model to perform model training; according to the training result, a first analysis model for analyzing the recommended vending list is obtained; inputting the associated building type of each sales terminal into a first analysis model to output a recommended vending list of each sales terminal; and sending the recommended vending list to the user terminal bound by the sales terminal. The method and the system are beneficial to analyzing and processing the data of each sales terminal through the computing capacity of the cloud server.
Description
Technical Field
The invention relates to the technical field of data processing systems, in particular to a data analysis processing method and an unmanned retail terminal.
Background
The data analysis means that a large amount of collected data is analyzed by a proper statistical analysis method, and the collected data are summarized, understood and digested to maximally develop the function of the data and play a role of the data. Data analysis is the process of detailed research and summarization of data in order to extract useful information and form conclusions. The advent of computers has led to the promotion of data analysis. Data analysis is a product of a combination of mathematics and computer science.
Along with the development of various portable devices, the Internet of things, cloud computing, cloud storage and other technologies, the data content and the data format are diversified, the data granularity is also finer, large data technologies such as distributed storage, distributed computing and stream processing appear, various industries search more application scenes based on various data sources even crossing industries in a correlated manner, and meanwhile, the timeliness of individual decision-making and application is more focused. Therefore, the data form, the processing technology and the application form of the big data form big data application different from the traditional data application, the application field of the big data is wider and wider, and the industry threshold of the application is lower and lower.
While the application of data analysis is becoming more and more widespread, data analysis in the sales arts (e.g., supermarket sales, store sales, unmanned retail terminal sales) is also only applied to analyze the resulting data metrics of each sales, such as gross, plateau, cross, sales-to-entry, profitability, turnover, homonymy, and cyclic, etc. Therefore, the data analysis processing method is not deep in the direction of the sales process.
Meanwhile, in the existing sales process, the data of each sales terminal are stored independently, so that the data of each sales terminal are isolated, and the data of a single sales terminal cannot be shared and reused, so that the data management and control of the sales process by uploading the data of a plurality of sales terminals are inconvenient. Moreover, each sales terminal has weak computing power and is not suitable for large-scale data processing.
The cloud server has strong computing power, which means that a huge data computing processing program is decomposed into countless small programs through a network 'cloud', and then the small programs are processed and analyzed through a system formed by a plurality of servers to obtain results, and the results are returned to a user.
Therefore, if the computing power of the cloud server can be applied to processing the data of each sales terminal, the problem that the data rule of each sales terminal is inconvenient to obtain by using the data processing of the similar sales terminals in the prior art due to the weak data processing power of the sales terminals can be solved. Therefore, it is desirable to provide a method for analyzing and processing data of each sales terminal through the computing power of the cloud server.
Disclosure of Invention
The invention mainly aims to provide a data analysis processing method, and aims to provide a method capable of analyzing and processing data of each sales terminal through the computing capacity of a cloud server.
In order to achieve the above object, in the data analysis processing method provided by the present invention, a cloud server is communicatively connected with a plurality of sales terminals, and the method includes the following steps:
acquiring associated building types corresponding to the sales terminals respectively through a cloud server, and acquiring distance data of the associated building types and the sales terminals, wherein the associated building types are building types with the distances from the sales terminals not exceeding a preset radius;
acquiring commodity sales data of each sales terminal in a set period;
taking the associated building type of each sales terminal as input data, taking a free selling commodity set of each sales terminal as output data, and inputting a prediction model to perform model training;
according to the training result, a first analysis model for analyzing the recommended vending list is obtained;
inputting the associated building type of each sales terminal into a first analysis model to output a recommended vending list of each sales terminal;
and sending the recommended vending list to the user terminal bound by the sales terminal.
Preferably, the step of obtaining, by the cloud server, the associated building type corresponding to each sales terminal and obtaining distance data between each associated building type and the sales terminal includes:
acquiring a preset radius through a cloud server, and acquiring a positioning address of each sales terminal;
acquiring a set building type keyword;
identifying geographic areas within a preset radius range of each sales terminal from a map according to the preset radius and the positioning address of each sales terminal, and identifying associated building types corresponding to building type keywords from the geographic areas;
distance data between the identified associated building type and the point-of-sale terminal is obtained.
Preferably, the step of acquiring distance data between the identified associated building type and the sales terminal includes:
acquiring a set first radius, a second radius and a third radius, wherein the first radius, the second radius and the third radius are sequentially increased, and the third radius does not exceed a preset radius;
identifying a first geographic area from the geographic areas, wherein the distance between the first geographic area and each sales terminal does not exceed a first radius, and identifying a first associated building type corresponding to a building type keyword from the first geographic area;
identifying a second geographical area from the geographical areas, wherein the distance between the second geographical area and each sales terminal is larger than the first radius and does not exceed a second radius, and identifying a second associated building type corresponding to the building type keyword from the second geographical area;
a third geographic area is identified from the geographic areas that is greater than the second radius and does not exceed the third radius, and a third associated building type is identified from the third geographic area that corresponds to the building type keyword.
Preferably, the acquiring the set first radius, second radius, and third radius includes:
acquiring competing distances between each sales terminal and the nearest competing point of sale;
determining a first radius according to one half of the average value of each competition distance;
determining a second radius according to the minimum value of each competing distance;
the third radius is determined based on the maximum value of each competing distance.
Preferably, the step of inputting the prediction model to perform model training using the associated building type of each sales terminal as input data and the set of free-selling commodities of each sales terminal as output data includes:
taking the first associated building type of each sales terminal as input data;
taking the free selling commodity set of each sales terminal as output data;
and carrying the input data and the output data into a prediction model for model training.
Preferably, the step of inputting the associated building type of each sales terminal into the first analysis model to output a recommended vending list of each sales terminal includes:
inputting a first associated building type for each sales terminal into the first analysis model to output a first recommended vending list for each sales terminal;
inputting a second associated building type for each sales terminal into the first analysis model to output a second recommended vending list for each sales terminal;
inputting a third associated building type for each sales terminal into the first analysis model to output a third recommended vending list for each sales terminal;
and ordering the commodities according to the first recommended vending list, the second recommended vending list and the third recommended vending list to form recommended vending lists of all the sales terminals.
Preferably, the method further comprises:
sending settlement information to a cloud server through a sales terminal, wherein the settlement information comprises consumer roles and purchased goods;
the cloud server inputs settlement information of all the sales terminals into a second analysis model to output a mapping relation table of consumer roles and purchased goods;
the cloud server determines consumer groups of each sales terminal according to settlement information of each sales terminal;
and the cloud server corrects the recommended vending list of each vending terminal according to the consumer group and the mapping relation table.
Preferably, a plurality of data sequences are established in the second analysis model, each data sequence being associated with a different consumer role; the cloud server inputs settlement information of all sales terminals into a second analysis model to output a mapping relation table of consumer roles and purchased goods, and the method comprises the following steps:
the cloud server inputs the received settlement information into a second analysis model;
the second analysis model determines an associated data sequence according to the consumer role corresponding to the settlement information, and adds the purchased goods corresponding to the settlement information to the associated data sequence; wherein, in the data sequence, sorting is carried out according to the times of adding the purchased commodity to the data sequence;
and the second analysis model outputs a mapping relation table of the consumer roles and the purchased commodities according to the consumer roles corresponding to each data sequence and the commodities in the set order in each data sequence.
Preferably, outputting the recommended vending list through the first analysis model specifically comprises the following steps:
；
wherein ,recommended vending list for sales terminals, +.>Is the%>Recommended vending list corresponding to each associated building type, < +.>Is the%>Personal associationRecommending factors of recommending vending lists corresponding to building types; />，/>Total number of key building types for the point-of-sale;
；
wherein ,，/>is the%>A distance of each associated building type from the point of sale terminal; />For a first radius>For a second radius>Is a third radius;
；
wherein ,is->Competitive distance between the individual sales terminal and the nearest competing point of sale,/->；，/>The total number of the sales terminals;
；
to be the +.>Inputting the types of the related buildings into an analysis result obtained by the first analysis model; />Is the%>A plurality of associated building types; />Is the%>And a recommended vending list corresponding to each associated building type, wherein the recommended vending list is a set of various commodity names.
The invention further provides an unmanned retail terminal, the data analysis processing method is applied, the unmanned retail terminal is a sales terminal, and the unmanned retail terminal is in communication connection with the cloud server.
According to the technical scheme, the associated building types around each sales terminal are acquired through the cloud server, wherein the distance between the associated building types of the sales terminal and the sales terminal does not exceed a preset radius, and customer groups of the sales terminal mainly originate from people stream groups caused by the associated building types. And other building types beyond the preset radius have relatively little effect on sales of the sales terminal, so that the sales category of the sales terminal can be determined mainly according to the associated building types near the sales terminal. It is easy to understand that different people flow groups have different shopping tendencies, in the invention, the prediction model is trained, the associated building types of the sales terminals are used as input data, and the free selling commodity set of each sales terminal is used as output data, so that the prediction model can determine what free selling commodity set the sales terminals have under the condition of different associated building types. Further, when the number of the associated building types of the sales terminal is plural, each associated building type has corresponding distance data, and the sales list of the sales terminal is determined by all the associated building types within the preset radius range. Therefore, the method and the system acquire the data of the single sales terminal, share the data into the cloud server, analyze the association of the sales data of each sales terminal and the crowd brought by the associated building type through the first analysis model of the cloud server, solve the current situation that the data processing capacity of the single sales terminal is weak, and solve the problem through the strong computing capacity of the cloud server. Therefore, the method and the system are beneficial to analyzing and processing the data of each sales terminal through the computing capacity of the cloud server. And, the invention uses the predictive model to analyze the shopping tendency of the crowd related to the associated building type of the sales terminal, so as to provide different sales lists for each sales terminal through the predictive model, and guide the sales process through the result of data analysis processing.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to the structures shown in these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a data analysis processing method according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, in order to achieve the above objective, a first embodiment of the present invention provides a data analysis processing method, in which a cloud server is communicatively connected with a plurality of sales terminals, the method includes the following steps:
step S10, acquiring associated building types corresponding to the sales terminals respectively through a cloud server, and acquiring distance data of the associated building types and the sales terminals, wherein the associated building types are building types with the distances from the sales terminals not exceeding a preset radius;
step S20, acquiring commodity sales data of each sales terminal in a set period;
step S30, taking the associated building type of each sales terminal as input data, taking the free selling commodity set of each sales terminal as output data, and inputting a prediction model for model training;
step S40, obtaining a first analysis model for analyzing the recommended vending list according to the training result;
s50, inputting the associated building type of each sales terminal into a first analysis model to output a recommended vending list of each sales terminal;
step S60, the recommended vending list is sent to the user terminal bound by the sales terminal.
The point of sale terminal may be a supermarket, a sales store, or an unmanned retail terminal.
According to the technical scheme, the associated building types around each sales terminal are acquired through the cloud server, wherein the distance between the associated building types of the sales terminal and the sales terminal does not exceed a preset radius, and customer groups of the sales terminal mainly originate from people stream groups caused by the associated building types. And other building types beyond the preset radius have relatively little effect on sales of the sales terminal, so that the sales category of the sales terminal can be determined mainly according to the associated building types near the sales terminal. It is easy to understand that different people flow groups have different shopping tendencies, in the invention, the prediction model is trained, the associated building types of the sales terminals are used as input data, and the free selling commodity set of each sales terminal is used as output data, so that the prediction model can determine what free selling commodity set the sales terminals have under the condition of different associated building types. Further, when the number of the associated building types of the sales terminal is plural, each associated building type has corresponding distance data, and the sales list of the sales terminal is determined by all the associated building types within the preset radius range. Therefore, the method and the system acquire the data of the single sales terminal, share the data into the cloud server, analyze the association of the sales data of each sales terminal and the crowd brought by the associated building type through the first analysis model of the cloud server, solve the current situation that the data processing capacity of the single sales terminal is weak, and solve the problem through the strong computing capacity of the cloud server. Therefore, the method and the system are beneficial to analyzing and processing the data of each sales terminal through the computing capacity of the cloud server. And, the invention uses the predictive model to analyze the shopping tendency of the crowd related to the associated building type of the sales terminal, so as to provide different sales lists for each sales terminal through the predictive model, and guide the sales process through the result of data analysis processing.
In particular, the type of building in the present invention is related to the use of the building. For example, building types may include sports fields, parks, primary schools, universities, hospitals, nursing homes, residential areas, bus stops, parks, malls, movie theatres, and the like, without limitation.
The type of associated building that is not more than a predetermined radius from the point of sale determines the type of people stream and thus what people will pass through the point of sale in a small area (within a range that is not more than a predetermined radius from the point of sale). It is readily understood that each group has different shopping needs. Thus, when the distance of the associated building type from the point-of-sale terminal does not exceed the preset radius, it can be presumed that the probability of the group of people within the associated building type passing the associated building type is relatively large. Furthermore, each of the associated building types also has a certain guiding effect on the direction of people flow. For example, when the associated building type is a public transportation station, people can be drained and more people can be provided, so that the vending variety ratio of people related to the public transportation station can be improved. Therefore, all the associated building type sets corresponding to each sales terminal are taken as input data to be brought into the prediction model, and the crowd types passing through the sales terminals can be predicted.
For example, when the associated building type is a stadium, the resulting population is typically a fitness population, who may have a significant tendency to shop for beverages, drinking water, and health foods, which may significantly increase sales of beverages, drinking water, and health foods when passing through a point of sale terminal; as another example, when the associated building type is school, the population is typically students, and the shopping demands of the students for candies, drinks, snacks and high-calorie foods may be relatively large, so that sales of candies, drinks, snacks and high-calorie foods may be significantly increased when such population passes through the sales terminal; for another example, when the associated building type is a hospital, the resulting population is typically a patient, and such population may be in prominent demand for masks and drinking water. However, it is difficult to detect how much the different people are selling goods and whether the different people have other shopping tendencies in addition to the above shopping tendencies. Therefore, training by the predictive model becomes a first analysis model for analyzing recommended sales listings, and the sales listings of each sales terminal are facilitated to be obtained by the first analysis model.
In a second embodiment of the data analysis processing method according to the present invention, the step S10 further includes:
step S11, acquiring a preset radius through a cloud server, and acquiring a positioning address of each sales terminal;
step S12, acquiring a set building type keyword;
step S13, identifying geographic areas within a preset radius range of each sales terminal from a map according to the preset radius and the positioning address of each sales terminal, and identifying associated building types corresponding to building type keywords from the geographic areas;
and step S14, acquiring distance data between the identified associated building type and the sales terminal.
In the present invention, building type keywords help the sales terminal to screen out the associated building type from the map. Specifically, the position of the sales terminal is required to be positioned firstly, then the sales terminal is taken as a center, a geographic area positioned at the periphery of the sales terminal is circled according to a preset radius, and then building types conforming to building type keywords are screened out of the geographic area as associated building types in a keyword screening mode in the geographic area.
The determination of the preset radius is related to the size of the corresponding point of sale of the point of sale terminal. The larger the scale of the sales terminal, the more perfect the type of the sales commodity, the larger the preset radius.
In the present invention, a point-of-sale terminal refers to a computing terminal of a point-of-sale, which may be, for example, a supermarket, a store, or an unmanned retail machine. The sales terminal may be a cash terminal of a supermarket, a cash terminal of a store, or a cash module of an unmanned vending machine, and of course, the sales terminal may be other types of terminals.
It should be noted that, in the present invention, the first analysis model should select data corresponding to sales terminals of the same kind of sales points as input data (associated building type of sales terminals) and output data (mass-market data) at the time of training and at the time of formal application. The first analysis model is assumed to be trained by using a sales terminal corresponding to a supermarket to select the type of the associated building, and the first analysis model is applied by using a sales terminal corresponding to an unmanned vending machine to select the type of the associated building, so that the model analysis result is inaccurate due to different preset radiuses.
Specifically, when the point of sale corresponding to the sales terminal is an unmanned retail terminal, the preset radius may take a value below 400 meters, and preferably below 200 meters.
In a third embodiment of the data analysis processing method according to the present invention, the step S14 includes:
step S141, acquiring a set first radius, a second radius and a third radius, wherein the first radius, the second radius and the third radius are sequentially increased, and the third radius does not exceed a preset radius;
step S142, identifying a first geographical area with a distance not exceeding a first radius from each sales terminal from the geographical areas, and identifying a first associated building type corresponding to the building type keyword from the first geographical area;
step S143, identifying a second geographical area which is larger than the first radius and not exceeding a second radius from the geographical areas and identifying a second associated building type corresponding to the building type keyword from the second geographical area;
step S144, a third geographical area with a distance between the third geographical area and each sales terminal being larger than the second radius and not exceeding the third radius is identified, and a third associated building type corresponding to the building type keyword is identified from the third geographical area.
The first radius, the second radius and the third radius are used for dividing the area around the sales terminal into three areas from the near to the far. The first radius defines a first geographic area centered at the point-of-sale terminal, the second radius defines a second geographic area that surrounds the annulus between the first radius and the second radius of the point-of-sale terminal, and the third radius defines a third geographic area that surrounds the annulus between the second radius and the third radius of the point-of-sale terminal.
The first geographic area, the second geographic area, and the third geographic area are farther from the point of sale terminal. Therefore, the influence of the crowd brought by the first association building type on the sales data of the sales terminal is the largest, the influence of the crowd brought by the second association building type on the sales data of the sales terminal is the second, and the influence of the crowd brought by the third association building type on the sales data of the sales terminal is smaller. However, all three groups are brought by the associated building types within the preset radius range, so that all three groups can influence the sales data of the sales terminals.
In a fourth embodiment of the data analysis processing method according to the present invention, the step S141 includes:
step S141a, obtaining competition distances between each sales terminal and the nearest competition point of sale;
step S141b, determining a first radius according to one half of the average value of each competition distance;
step S141c, determining a second radius according to the minimum value of each competing distance;
step S141d, determining a third radius according to the maximum value of each competing distance.
Specifically, the first radius delineates the group of people closest to the point of sale terminal. If other similar sales shops exist in the first radius range, a competitive relationship of customer groups is formed between the sales terminal and the sales terminal. In the present invention, the distance between the sales terminal and the competing point of sale is the competing distance.
Thus, to remove the effects of the same sort of competition, in this embodiment, the first radius is determined as half the average of the competing distances between each sales terminal and the competing sales points. Therefore, the competitive behaviour of sales can be ignored in the first radius, and interference data generated when shopping trends of different groups are studied can be avoided.
The second radius delineates the category of people closer to the point of sale terminal. For a real sales environment, the sales store or unmanned retail terminal is very densely distributed. Thus, in a real sales environment, sales data for each sales terminal may actually be affected by other points of sale in the vicinity. Thus, the second radius is determined using the minimum value of each competing distance to facilitate reflecting the sales data impact of surrounding points of sale on the present sales terminal in the second geographic area.
The third radius demarcates the population category that is slightly farther from the point of sale terminal, but the population category is still close to the point of sale terminal, which can have some impact on the sales data of the point of sale terminal. And the third data can be delimited by the maximum value of the respective competing distances.
It is contemplated that the present invention contemplates that the market environment into which each sales terminal is placed is approximate in determining the competitive distance between each sales terminal and the competing point of sale. For example, individual sales terminals may be distributed across streets in the same city, even though individual sales terminals are distributed across different cities, considering that people in different cities have similar shopping tendencies and similar people stream densities.
For example, when a part of sales terminals are put in rural areas in north and another part of sales terminals are put in cities in south, the first radius determined according to a half of the average value of competing distances between each sales terminal and competing sales points, the second radius determined according to the minimum value of each competing distance, and the third radius determined according to the maximum value of each competing distance are not data formed on the same premise, so that accuracy of data analysis may be lowered.
According to a fifth embodiment of the data analysis processing method of the present invention, in the third embodiment or the fourth embodiment, the step S30 includes:
step S31, the first associated building type of each sales terminal is used as input data;
step S32, using the mass-market commodity set of each sales terminal as output data;
and step S33, the input data and the output data are brought into a prediction model to carry out model training.
In this embodiment, in order to avoid the influence of the same kind of competition, only the data in the first radius where no competition point of sale exists (the first associated building type of each sales terminal is used as the input data) is used as the input data, and the set of marketable commodities of each sales terminal is used as the output data and is brought into the prediction model for training. The first analysis model obtained through training can maximally eliminate the influence of similar competition points on sales data so as to reflect the real shopping tendency of the crowd of the target building type.
According to a fifth embodiment of the present invention, in a sixth embodiment of the data analysis processing method of the present invention, the step S50 includes:
step S51, inputting a first associated building type of each sales terminal into the first analysis model to output a first recommended vending list of each sales terminal;
step S52, inputting the second associated building type of each sales terminal into the first analysis model to output a second recommended sales list of each sales terminal;
step S53, inputting the third associated building type of each sales terminal into the first analysis model to output a third recommended sales list of each sales terminal;
in step S54, the goods are ordered according to the first, second and third recommended vending lists, so as to form recommended vending lists of the respective vending terminals.
In this embodiment, the products in the first, second, and third recommended vending lists are respectively set with different recommendation factors (the recommendation factors gradually decrease) so that different recommendation orders can be generated according to the generated recommended vending lists of the first, second, and third recommended vending lists.
In a seventh embodiment of the data analysis processing method according to the present invention, based on the first to fourth embodiments of the present invention, the method further includes:
step S70, sending settlement information to a cloud server through a sales terminal, wherein the settlement information comprises consumer roles and purchased goods;
step S80, the cloud server inputs settlement information of all sales terminals into a second analysis model to output a mapping relation table of consumer roles and purchased goods;
step S90, the cloud server determines consumer groups of each sales terminal according to settlement information of each sales terminal;
step S100, the cloud server corrects the recommended vending list of each vending terminal according to the consumer group and the mapping relation table.
Wherein the consumer role may be determined from the payment information of the consumer. The consumer role may be the type of crowd corresponding to the consumer purchasing the merchandise.
Counting purchased goods of the same consumer role has analytical significance in determining shopping preferences of the same consumer role.
In the first embodiment, a vending list of each sales terminal is determined according to the associated building type and the set of open-sell commodities of the sales terminal. Thus, the sales listings recommended by sales terminals of the same type of associated building are the same. The method corresponds to the formation of a recommended vending list from the commonality of each sales terminal.
The settlement information of each sales terminal is directly analyzed in the embodiment, the real consumer group of each sales terminal is counted from a plurality of settlement information, and the commodity really purchased by each consumer role of each sales terminal is counted from a plurality of settlement information, so that the correction of the recommended vending list for each sales terminal according to the real consumer group and the commodity really purchased by each consumer role is facilitated, which is equivalent to the adjustment of the recommended vending list of each sales terminal according to the real difference condition of each sales terminal.
Based on the seventh embodiment of the present invention, in an eighth embodiment of the data analysis processing method of the present invention, a plurality of data sequences are established in the second analysis model, each data sequence being associated with a different consumer role; the step S80 includes:
step S81, the cloud server inputs the received settlement information into a second analysis model;
step S82, the second analysis model determines an associated data sequence according to the consumer roles corresponding to the settlement information, and adds the purchased goods corresponding to the settlement information to the associated data sequence; wherein, in the data sequence, sorting is carried out according to the times of adding the purchased commodity to the data sequence;
in step S83, the second analysis model outputs a mapping relationship table of the consumer roles and the purchased commodities according to the consumer roles corresponding to each data sequence and the commodities in the set order ordered in each data sequence. Wherein the order of the setting may be such that the ordering order is in the first 30% in the data sequence.
In a ninth embodiment of the data analysis processing method according to the present invention, the outputting of the recommended vending list by the first analysis model specifically includes the steps of:
；
wherein ,recommended vending list for sales terminals, +.>Is the%>Recommended vending list corresponding to each associated building type, < +.>Is the%>Recommendation factors of the recommended vending lists corresponding to the associated building types; />，/>Total number of key building types for the point-of-sale;
；
wherein ,，/>is the%>A distance of each associated building type from the point of sale terminal; />For a first radius>For a second radius>Is a third radius;
；
wherein ,is->Competitive distance between the individual sales terminal and the nearest competing point of sale,/->；，/>The total number of the sales terminals;
；
to be the +.>Inputting the types of the related buildings into an analysis result obtained by the first analysis model; />Is the%>A plurality of associated building types; />Is the%>And a recommended vending list corresponding to each associated building type, wherein the recommended vending list is a set of various commodity names.
In addition, in order to achieve the above purpose, the invention also provides an unmanned retail terminal, which is a sales terminal and is in communication connection with a cloud server by applying the data analysis processing method.
The foregoing description of the preferred embodiments of the present invention should not be construed as limiting the scope of the invention, but rather utilizing equivalent structural changes made in the present invention description and drawings or directly/indirectly applied to other related technical fields are included in the scope of the present invention.
Claims (7)
1. The data analysis processing method is characterized in that a cloud server is in communication connection with a plurality of sales terminals, and the method comprises the following steps:
the cloud server is used for obtaining the associated building types respectively corresponding to the sales terminals and obtaining the distance data between each associated building type and the sales terminal, and the cloud server comprises the following steps: acquiring a preset radius through a cloud server, and acquiring a positioning address of each sales terminal; acquiring a set building type keyword; identifying geographic areas within a preset radius range of each sales terminal from a map according to the preset radius and the positioning address of each sales terminal, and identifying associated building types corresponding to building type keywords from the geographic areas; acquiring distance data between the identified associated building type and the sales terminal; wherein the associated building type is a building type with a distance from the sales terminal not exceeding a preset radius;
acquiring commodity sales data of each sales terminal in a set period;
taking the associated building type of each sales terminal as input data, taking a free selling commodity set of each sales terminal as output data, and inputting a prediction model to perform model training;
according to the training result, a first analysis model for analyzing the recommended vending list is obtained;
inputting the associated building type of each sales terminal into a first analysis model to output a recommended vending list of each sales terminal;
transmitting the recommended vending list to a user terminal bound by the sales terminal;
the step of acquiring distance data between the identified associated building type and the sales terminal includes: acquiring a set first radius, a second radius and a third radius, wherein the first radius, the second radius and the third radius are sequentially increased, and the third radius does not exceed a preset radius; identifying a first geographic area from the geographic areas, wherein the distance between the first geographic area and each sales terminal does not exceed a first radius, and identifying a first associated building type corresponding to a building type keyword from the first geographic area; identifying a second geographical area from the geographical areas, wherein the distance between the second geographical area and each sales terminal is larger than the first radius and does not exceed a second radius, and identifying a second associated building type corresponding to the building type keyword from the second geographical area; identifying a third geographic area from the geographic areas, wherein the distance between the third geographic area and each sales terminal is larger than the second radius and does not exceed a third radius, and identifying a third associated building type corresponding to the building type keyword from the third geographic area;
the step of inputting the prediction model to perform model training by taking the associated building type of each sales terminal as input data and the free selling commodity set of each sales terminal as output data, comprises the following steps: taking the first associated building type of each sales terminal as input data; taking the free selling commodity set of each sales terminal as output data; and carrying the input data and the output data into a prediction model for model training.
2. The data analysis processing method according to claim 1, wherein the acquiring the set first radius, second radius, and third radius includes:
acquiring competing distances between each sales terminal and the nearest competing point of sale;
determining a first radius according to one half of the average value of each competition distance;
determining a second radius according to the minimum value of each competing distance;
the third radius is determined based on the maximum value of each competing distance.
3. The data analysis processing method according to claim 1, wherein the step of inputting the associated building type of each sales terminal into the first analysis model to output the recommended sales list of each sales terminal includes:
inputting a first associated building type for each sales terminal into the first analysis model to output a first recommended vending list for each sales terminal;
inputting a second associated building type for each sales terminal into the first analysis model to output a second recommended vending list for each sales terminal;
inputting a third associated building type for each sales terminal into the first analysis model to output a third recommended vending list for each sales terminal;
and ordering the commodities according to the first recommended vending list, the second recommended vending list and the third recommended vending list to form recommended vending lists of all the sales terminals.
4. The data analysis processing method according to claim 1 or 2, characterized by further comprising:
sending settlement information to a cloud server through a sales terminal, wherein the settlement information comprises consumer roles and purchased goods;
the cloud server inputs settlement information of all the sales terminals into a second analysis model to output a mapping relation table of consumer roles and purchased goods;
the cloud server determines consumer groups of each sales terminal according to settlement information of each sales terminal;
and the cloud server corrects the recommended vending list of each vending terminal according to the consumer group and the mapping relation table.
5. The data analysis processing method according to claim 4, wherein a plurality of data sequences are built in the second analysis model, each data sequence being associated with a different consumer role; the cloud server inputs settlement information of all sales terminals into a second analysis model to output a mapping relation table of consumer roles and purchased goods, and the method comprises the following steps:
the cloud server inputs the received settlement information into a second analysis model;
the second analysis model determines an associated data sequence according to the consumer role corresponding to the settlement information, and adds the purchased goods corresponding to the settlement information to the associated data sequence; wherein, in the data sequence, sorting is carried out according to the times of adding the purchased commodity to the data sequence;
and the second analysis model outputs a mapping relation table of the consumer roles and the purchased commodities according to the consumer roles corresponding to each data sequence and the commodities in the set order in each data sequence.
6. The data analysis processing method according to claim 2, wherein the outputting of the recommended vending list by the first analysis model comprises the steps of:
；
wherein ,recommended vending list for sales terminals, +.>Is the%>Recommended vending list corresponding to each associated building type, < +.>Is the%>Recommendation factors of the recommended vending lists corresponding to the associated building types;，/>total number of key building types for the point-of-sale;
；
wherein ,，/>is the%>A distance of each associated building type from the point of sale terminal;for a first radius>For a second radius>Is a third radius;
；
wherein ,is->Competitive distance between the individual sales terminal and the nearest competing point of sale,/->；/>，The total number of the sales terminals;
；
to be the +.>Inputting the types of the related buildings into an analysis result obtained by the first analysis model; />Is the%>A plurality of associated building types; />Is the%>And a recommended vending list corresponding to each associated building type, wherein the recommended vending list is a set of various commodity names.
7. An unmanned retail terminal, characterized in that the data analysis processing method according to any one of claims 1 to 6 is applied, the unmanned retail terminal is a sales terminal, and the unmanned retail terminal is in communication connection with a cloud server.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310655693.7A CN116402545B (en) | 2023-06-05 | 2023-06-05 | Data analysis processing method and unmanned retail terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310655693.7A CN116402545B (en) | 2023-06-05 | 2023-06-05 | Data analysis processing method and unmanned retail terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116402545A CN116402545A (en) | 2023-07-07 |
| CN116402545B true CN116402545B (en) | 2023-08-15 |
Family
ID=87007955
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310655693.7A Active CN116402545B (en) | 2023-06-05 | 2023-06-05 | Data analysis processing method and unmanned retail terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116402545B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103064838A (en) * | 2011-10-19 | 2013-04-24 | 阿里巴巴集团控股有限公司 | Data searching method and device |
| CN107492027A (en) * | 2017-09-27 | 2017-12-19 | 应瑞 | New retail trade system based on cell Intelligent service terminal |
| CN110675189A (en) * | 2019-09-20 | 2020-01-10 | 东北大学 | Unmanned shelf location method based on Wide & Deep model and genetic algorithm |
| KR20200009542A (en) * | 2018-07-19 | 2020-01-30 | 한국기술교육대학교 산학협력단 | Intelligent Shopping Platform Management System and Its Methods Based on Consumer Big Data |
| WO2020047918A1 (en) * | 2018-09-06 | 2020-03-12 | 深圳码隆科技有限公司 | Self-service vending method, apparatus, and system, electronic device, and computer storage medium |
| CN111445296A (en) * | 2020-04-13 | 2020-07-24 | 智粤云(广州)数字信息科技有限公司 | Electronic commerce system based on big data cloud platform |
| CN112184399A (en) * | 2020-11-10 | 2021-01-05 | 广州鸿森资本管理有限公司 | Commodity sale recommendation system and method based on Internet |
| CN115019440A (en) * | 2022-05-31 | 2022-09-06 | 海南睿德感知物联科技有限公司 | Intelligent vending machine |
| CN115345530A (en) * | 2022-10-18 | 2022-11-15 | 广州数说故事信息科技有限公司 | Market address recommendation method, device and equipment and computer readable storage medium |
| CN115797020A (en) * | 2023-02-06 | 2023-03-14 | 网思科技股份有限公司 | Retail recommendation method, system and medium based on data processing of graph database |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8944314B2 (en) * | 2012-11-29 | 2015-02-03 | Ebay Inc. | Systems and methods for recommending a retail location |
| US20160140589A1 (en) * | 2014-11-14 | 2016-05-19 | International Business Machines Corporation | Retail customer engagement zones |
-
2023
- 2023-06-05 CN CN202310655693.7A patent/CN116402545B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103064838A (en) * | 2011-10-19 | 2013-04-24 | 阿里巴巴集团控股有限公司 | Data searching method and device |
| CN107492027A (en) * | 2017-09-27 | 2017-12-19 | 应瑞 | New retail trade system based on cell Intelligent service terminal |
| KR20200009542A (en) * | 2018-07-19 | 2020-01-30 | 한국기술교육대학교 산학협력단 | Intelligent Shopping Platform Management System and Its Methods Based on Consumer Big Data |
| WO2020047918A1 (en) * | 2018-09-06 | 2020-03-12 | 深圳码隆科技有限公司 | Self-service vending method, apparatus, and system, electronic device, and computer storage medium |
| CN110675189A (en) * | 2019-09-20 | 2020-01-10 | 东北大学 | Unmanned shelf location method based on Wide & Deep model and genetic algorithm |
| CN111445296A (en) * | 2020-04-13 | 2020-07-24 | 智粤云(广州)数字信息科技有限公司 | Electronic commerce system based on big data cloud platform |
| CN112184399A (en) * | 2020-11-10 | 2021-01-05 | 广州鸿森资本管理有限公司 | Commodity sale recommendation system and method based on Internet |
| CN115019440A (en) * | 2022-05-31 | 2022-09-06 | 海南睿德感知物联科技有限公司 | Intelligent vending machine |
| CN115345530A (en) * | 2022-10-18 | 2022-11-15 | 广州数说故事信息科技有限公司 | Market address recommendation method, device and equipment and computer readable storage medium |
| CN115797020A (en) * | 2023-02-06 | 2023-03-14 | 网思科技股份有限公司 | Retail recommendation method, system and medium based on data processing of graph database |
Non-Patent Citations (1)
| Title |
|---|
| 无人值守智能商业融合平台技术框架设计;袁路妍;李锋;;物流技术(第02期);第121-124页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116402545A (en) | 2023-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11748379B1 (en) | Systems and methods for generating and implementing knowledge graphs for knowledge representation and analysis | |
| Clark et al. | Understanding the impact of the modifiable areal unit problem on the relationship between active travel and the built environment | |
| Zhai et al. | Mapping the popularity of urban restaurants using social media data | |
| US11983203B1 (en) | Systems and methods of establishing correlative relationships between geospatial data features in feature vectors representing property locations | |
| CN108429776B (en) | Network object pushing method, device, client, interaction equipment and system | |
| CN111091409B (en) | Client tag determination method and device and server | |
| Wu et al. | Modeling shopping center location choice: shopper preference–based competitive location model | |
| CN106600360B (en) | Method and device for sorting recommended objects | |
| Feizizadeh et al. | Urban restaurants and online food delivery during the COVID-19 pandemic: A spatial and socio-demographic analysis | |
| CN110599281A (en) | Method and device for determining target shop | |
| Mao et al. | Utilizing multi-source data in popularity prediction for shop-type recommendation | |
| Palma | Improving the prediction of ranking data | |
| CN116402545B (en) | Data analysis processing method and unmanned retail terminal | |
| CN110659920B (en) | Method and device for recommending service object | |
| Lee et al. | Machine learning based prediction of the value of buildings | |
| TWI630574B (en) | Real-estate information system and its method | |
| CN111460300B (en) | Network content pushing method, device and storage medium | |
| JP6910515B1 (en) | Analytical instruments, analytical methods and analytical programs | |
| Agarwal et al. | Binarized spiking neural networks optimized with Nomadic People Optimization-based sentiment analysis for social product recommendation | |
| CN111369315A (en) | Resource object recommendation method and device, and data prediction model training method and device | |
| Kar et al. | New Approaches to Forecasting Growth and Inflation: Big Data and Machine Learning | |
| KR20200096023A (en) | System and method for generating prediction results using big data | |
| TWM542827U (en) | Real-estate information system | |
| Aljomai et al. | Integrating social network analysis and data mining techniques into effective e-market framework | |
| M Sri Rangan | Creating accurate valuation models for real estate properties |
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 |