CN117952673A - Genetic algorithm-based method for displaying spare parts of hydrogen station and storage medium - Google Patents
Genetic algorithm-based method for displaying spare parts of hydrogen station and storage medium Download PDFInfo
- Publication number
- CN117952673A CN117952673A CN202410354053.7A CN202410354053A CN117952673A CN 117952673 A CN117952673 A CN 117952673A CN 202410354053 A CN202410354053 A CN 202410354053A CN 117952673 A CN117952673 A CN 117952673A
- Authority
- CN
- China
- Prior art keywords
- chromosome
- sales
- spare part
- fitness
- retail
- 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
- 238000003860 storage Methods 0.000 title claims abstract description 27
- UFHFLCQGNIYNRP-UHFFFAOYSA-N Hydrogen Chemical compound [H][H] UFHFLCQGNIYNRP-UHFFFAOYSA-N 0.000 title claims description 39
- 229910052739 hydrogen Inorganic materials 0.000 title claims description 39
- 239000001257 hydrogen Substances 0.000 title claims description 39
- 238000002986 genetic algorithm method Methods 0.000 title claims description 11
- 238000000034 method Methods 0.000 claims abstract description 42
- 238000005984 hydrogenation reaction Methods 0.000 claims abstract description 41
- 230000002068 genetic effect Effects 0.000 claims abstract description 24
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 22
- 210000000349 chromosome Anatomy 0.000 claims description 176
- 238000012360 testing method Methods 0.000 claims description 45
- 230000003442 weekly effect Effects 0.000 claims description 24
- 230000006870 function Effects 0.000 claims description 22
- 230000035772 mutation Effects 0.000 claims description 19
- 108090000623 proteins and genes Proteins 0.000 claims description 19
- 230000015654 memory Effects 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000009395 breeding Methods 0.000 claims description 3
- 230000001488 breeding effect Effects 0.000 claims description 3
- 239000000047 product Substances 0.000 description 19
- 238000012549 training Methods 0.000 description 19
- 238000012795 verification Methods 0.000 description 11
- 238000003032 molecular docking Methods 0.000 description 10
- 238000004891 communication Methods 0.000 description 7
- 238000004590 computer program Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000004138 cluster model Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000002028 premature Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000007723 transport mechanism Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a method for displaying spare parts of a hydrogenation station and a storage medium based on a genetic algorithm, which not only consider the predicted sales influence of spare parts of the hydrogenation station, but also integrate constraint conditions such as the volume of spare parts, the container capacity of the hydrogenation station and the profit of the spare parts so as to maximize the profit of the spare parts under a display model and ensure the effective utilization of the container.
Description
Technical Field
The embodiment of the application relates to the technical field of artificial intelligence, in particular to a method for displaying a spare part commodity of a hydrogen station based on a genetic algorithm, electronic equipment and a computer readable storage medium.
Background
According to research, the placement position of the commodity has obvious influence on sales volume of the commodity, and the display placement of related spare part commodities in the conventional hydrogenation station is mainly based on manual mode to place and supplement according to experience and subjective judgment, so that the intelligent degree is not high, the purchasing demands of users on different spare part commodities can not be matched well, and the sales volume and profit of the whole spare part commodity of the hydrogenation station can not be expected. Therefore, how to display and place the spare parts of the hydrogenation station more intelligently so as to improve sales and profits of the spare parts of the hydrogenation station is a technical problem to be solved at present.
Disclosure of Invention
The embodiment of the application provides a method for displaying a commodity of a spare part of a hydrogenation station based on a genetic algorithm, electronic equipment and a computer readable storage medium, which aim to intelligently display and place the commodity of the spare part of the hydrogenation station, thereby improving sales and profits of the commodity of the spare part of the hydrogenation station.
In a first aspect, an embodiment of the present application provides a method for displaying a commodity of a spare part of a hydrogen station based on a genetic algorithm, including: acquiring spare part commodity photos on commodity shelves of all the hydrogenation stations, classifying and identifying all the spare part commodity photos to obtain classification and identification results, and classifying the spare part commodity on the commodity shelves of all the hydrogenation stations according to the classification and identification results to obtain a plurality of first-class categories;
According to the obtained sales records of the spare part commodities corresponding to the primary categories, calculating the historical daily average sales of the spare part commodities corresponding to the primary categories, and predicting the future daily average sales of the spare part commodities corresponding to the primary categories according to the historical daily average sales of the spare part commodities corresponding to the primary categories;
Pre-grouping the various hydrogenation stations according to the obtained geographic position information and sales spare part commodity information of all the hydrogenation stations to obtain a plurality of retail groups, and respectively establishing a corresponding display model for each retail group, wherein each retail group comprises at least one hydrogenation station;
For each of the display models, taking the display model as a chromosome, and encoding the chromosome into an integer array, wherein the size of each element in the integer array is limited by the container capacity of the corresponding retail group and the volume of spare part commodity corresponding to each of the primary categories;
For each chromosome, calculating the fitness of the chromosome by taking the total container volume of the retail group corresponding to the obtained chromosome, the volume and profit of spare part commodities corresponding to each primary category and the average sales volume in the future as constraint conditions, and calculating the expected total profit of the chromosome under the constraint conditions through a preset fitness function, wherein the fitness function is used for calculating the expected total profit of the chromosome under the constraint conditions;
Chromosome propagation is carried out based on fitness of each chromosome to obtain an initial chromosome population, and a plurality of target chromosomes are selected from the initial chromosome population to serve as first generation populations, wherein the target chromosomes are chromosomes with the fitness being greater than or equal to a preset fitness threshold;
Performing crossover and mutation operations on the chromosomes in the first generation population to obtain a second generation population, and repeating iteration operations of chromosome propagation, selection, crossover and mutation by taking the second generation population as an iteration starting point until the preset iteration times are reached or the fitness of the chromosomes reaches a stable level to obtain a final chromosome population;
And selecting the chromosome with the highest fitness from the final chromosome population as the optimal display model, and displaying and placing spare part commodities of all the hydrogen stations in the corresponding retail groups according to the optimal display model.
In some embodiments, when at least one of the docking stations introduces a target spare part commodity for which no sales records exist, the method further comprises: selecting one of the retail groups having a total sales closest to the average of sales of all of the retail groups as a test group from a plurality of the retail groups;
identifying and marking the primary category of the target spare part commodity as a test category;
Acquiring historical sales data and market trend data of spare part commodities corresponding to the test categories in the test group;
And calculating the historical daily average sales volume of spare part commodities corresponding to the test categories in the test group according to the historical sales data and the market trend data, and predicting the future daily initial sales volume of the target spare part commodities according to the historical daily average sales volume of the spare part commodities corresponding to the test categories in the test group.
In some embodiments, after predicting the future daily initial sales of the target spare part commodity according to the historical daily average sales of the spare part commodity corresponding to the test category in the test group, the method further includes: continuously collecting trial sales data of the target spare part commodity in the test group in a target time period;
and dynamically adjusting the display model corresponding to the test group according to the trial sales data, and adding the target spare part commodity to the rest retail groups when the trial sales data is greater than or equal to preset trial sales reference data.
In some embodiments, the calculating the fitness of the chromosome by a preset fitness function includes: obtaining the gene composition of the chromosome, wherein the primary category comprises a plurality of secondary categories, and each gene of the chromosome characterizes the replenishment quantity of spare part commodities corresponding to one secondary category under the primary category;
calculating the total volume of the chromosome according to the gene composition of the chromosome;
And when the total volume is larger than the total volume of containers of the retail group corresponding to the chromosome, setting the chromosome as invalid, recording the fitness of the chromosome as 0, or when the total volume is smaller than or equal to the total volume of containers of the retail group corresponding to the chromosome, calculating the expected total profit of the chromosome under the constraint condition so as to realize the calculation of the fitness of the chromosome.
In some embodiments, the crossing and mutation of the chromosomes in the first generation population to obtain a second generation population comprises: randomly selecting one or more genes on a plurality of chromosomes from the first generation population for mutation, and randomly selecting at least two chromosomes from the first generation population for pairwise pairing;
Determining, for each set of paired two said chromosomes, the same number of at least one crossover point from each of the two said chromosomes;
the genes at all the crossing points at the corresponding positions of the two chromosomes are swapped.
In some embodiments, said chromosome propagation based on fitness of each of said chromosomes comprises: chromosome breeding is performed based on fitness of each of the chromosomes using a roulette selection strategy or a tournament selection strategy.
In some embodiments, after the displaying and placing the spare parts commodities of all the hydrogen stations in the corresponding retail groups according to the optimal display model, the method further comprises: statistically optimizing actual sales of all spare part commodities in the retail group corresponding to the display model per week;
Predicting and obtaining the optimal future daily average sales volume of the spare part commodities in the first class corresponding to the display model according to the optimal future daily average sales volume of the spare part commodities in the first class corresponding to the display model;
Comparing and calculating the actual weekly sales with the future weekly sales to obtain differentiated weekly sales;
And adjusting the optimal display model according to the differentiated sales volume so as to enable the optimal display model to be in a continuously updated state.
In some embodiments, said adjusting the optimal display model according to the differentiated weekly sales comprises: when the differentiated weekly sales are within a preset difference threshold, repeating iterative operations of chromosome reproduction, selection, crossover and mutation to determine an updated final chromosome population, and selecting the chromosome with the highest fitness from the updated final chromosome population as the optimal display model;
or when the differentiated weekly sales volume is not in a preset difference threshold value range, adjusting the constraint condition according to the differentiated weekly sales volume, and recalculating the fitness of the chromosome through a preset fitness function based on the adjusted constraint condition.
In a second aspect, an embodiment of the present application provides an electronic device, including: at least one processor;
At least one memory for storing at least one program;
The genetic algorithm-based method of merchandise display of a hydrogen station spare part as described above is implemented when at least one of the programs is executed by at least one of the processors.
In a third aspect, embodiments of the present application provide a computer readable storage medium having stored therein a processor executable program for implementing a genetic algorithm-based method of merchandise display of a hydrogen station spare part as described above when executed by a processor.
According to the genetic algorithm-based method, electronic equipment and computer-readable storage medium for displaying the spare parts of the hydrogenation station, provided by the embodiment of the application, not only is the predicted sales influence of the spare parts of the hydrogenation station considered, but also constraint conditions such as the volume of the spare parts, the container capacity of the hydrogenation station and the profit of the spare parts are synthesized, so that the profit of the spare parts under a display model is maximized and the effective utilization of the container is ensured, and in the subsequent process, the display model is continuously optimized by defining the steps such as fitness function, selection strategy, cross mechanism and variation mechanism, so that the optimal display model can be determined, and the optimal display model can be matched with the purchasing demands of users on different spare parts of the hydrogenation station, so that the intelligent display placement of the spare parts of the hydrogenation station can be realized on the whole, and the sales and profit of the spare parts of the hydrogenation station are improved.
Drawings
FIG. 1 is a flow chart of a method for displaying a product of a hydrogen plant spare part based on a genetic algorithm according to an embodiment of the present application;
FIG. 2 is a flow chart of a method for displaying a product of a hydrogen plant spare part based on a genetic algorithm according to another embodiment of the present application;
Fig. 3 is a flowchart of step S12000 in fig. 2;
fig. 4 is a flowchart of step S5000 in fig. 1;
fig. 5 is a flowchart of step S7000 in fig. 1;
fig. 6 is a flowchart after step S8000 in fig. 1;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
It should be noted that although functional block division is performed in a device diagram and a logic sequence is shown in a flowchart, in some cases, the steps shown or described may be performed in a different order than the block division in the device, or in the flowchart.
The application provides a method, electronic equipment and a computer readable storage medium for displaying spare parts of a hydrogenation station based on a genetic algorithm, which not only consider the predicted sales influence of spare parts of the hydrogenation station, but also integrate constraint conditions such as the volume of spare parts, the container capacity of the hydrogenation station and the profit of the spare parts so as to maximize the profit of the spare parts under a display model and ensure the effective utilization of the container.
The genetic algorithm-based commodity display method for the hydrogen adding station spare parts and the storage medium provided by the embodiment of the application are specifically described through the following embodiments, and the genetic algorithm-based commodity display method for the hydrogen adding station spare parts in the embodiment of the application is described first.
The embodiment of the application provides a genetic algorithm-based method for displaying the spare parts of a hydrogen station, and relates to the technical field of artificial intelligence. The method for displaying the spare parts of the hydrogen station based on the genetic algorithm can be applied to a communication node, can be applied to a server side, and can also be software running in the communication node or the server side. In some embodiments, the communication node may be a smart phone, tablet computer, notebook computer, desktop computer, or the like; the server side can be configured as an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, and a cloud server for providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDNs, basic cloud computing services such as big data and artificial intelligent platforms and the like; the software may be an application or the like that implements a genetic algorithm-based inventory display method for the hydrogen plant spare parts, but is not limited to the above.
The application is operational with numerous general purpose or special purpose computer system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like. The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
FIG. 1 is a flow chart of a method for displaying a product of a hydrogen station spare part based on a genetic algorithm according to an embodiment of the present application. As shown in fig. 1, the method may include, but is not limited to, steps S1000 to S8000.
Step S1000: acquiring spare part commodity photos on commodity shelves of all the hydrogenation stations, classifying and identifying all the spare part commodity photos to obtain classification and identification results, and classifying the spare part commodity on the commodity shelves of all the hydrogenation stations according to the classification and identification results to obtain a plurality of first-class categories;
The method for acquiring the spare part commodity photos can be various, for example, but not limited to, tracking shooting can be performed by adopting a camera or a high-speed camera, the time of the selected spare part commodity photos can be a historical time period with a duration, and the selected spare part commodity photos can be set correspondingly by a person skilled in the art according to actual application situations; the classification and identification may be performed by using a specific classification and identification network, for example, a corresponding pre-trained deep identification network, so as to obtain a plurality of first-class classes, where the first-class classes mainly represent main differences between spare part commodities of the hydrogen station, that is, main features of the spare part commodities of different first-class classes are used to distinguish between the spare part commodities, in other words, there is a significant difference between the spare part commodities of different first-class classes, for example, different first-class classes may include a sensor class, a hydrogen energy battery product class, a hydrogen storage product class, and the like, each class may include a plurality of similar or similar commodities, for example, a vehicle sensor class may include hydrogen energy vehicle sensors of different models and batches, and the hydrogen energy battery product class may include battery products of various types and specifications, which are not described herein.
Step S2000: according to the obtained sales records of the spare part commodities corresponding to the first class, calculating the historical daily average sales of the spare part commodities corresponding to the first class, and predicting the future daily average sales of the spare part commodities corresponding to the first class according to the historical daily average sales of the spare part commodities corresponding to the first class;
The sales records and the shooting period of the spare part commodity photos can be kept consistent, namely the sales records of the spare part commodities in the shooting period are required to be acquired, further, the historical daily average sales volume of the spare part commodities corresponding to each class is calculated according to the sales records, and then the future daily average sales volume of the spare part commodities corresponding to each class is predicted according to the historical daily average sales volume, so that the method is more accurate and reliable.
Step S3000: pre-grouping the various hydrogenation stations according to the obtained geographic position information of all the hydrogenation stations and commodity information of the sales spare parts to obtain a plurality of retail groups, and respectively establishing a corresponding display model for each retail group, wherein each retail group comprises at least one hydrogenation station;
It should be noted that, in this embodiment, the type, location, etc. of the docking station are not limited, and the spare parts may be related articles of the docking vehicle, auxiliary products required for the docking process, and docking products, etc., which are not limited herein.
It will be appreciated that the geographic location information of the docking station and the sales of the spare parts merchandise information may have a significant impact, for example, sales of spare parts merchandise of the docking station in a luxury business area or service area may be better, sales of spare parts merchandise related to the class of cars of the docking station may be better, so by considering these geographic location information and sales of spare parts merchandise information to group each docking station better, so as to establish a corresponding display model for each retail group respectively; the mode of constructing the display model can be various, for example, after a plurality of retail groups are determined, sales data of each retail group are respectively obtained, then the sales data are used as a training set for training, and related condition data are used for post-verification, and finally a pre-trained training model which is the display model can be obtained; for example, but not limited to, the sales data of each retail group may be input into a machine learning model after training, the corresponding training model may be output via the machine learning model after training, where the machine learning model may be a convolutional neural network, correspondingly, the sales data of each retail group obtained at this time may be converted into a format of a corresponding container picture for presentation, the container picture is input into the convolutional neural network, the primarily obtained training model may be output, a linear regression model, a cluster model, a random forest model, and the like may be used as a training model for pre-training, and then post-verification may be performed based on the primarily obtained training model, where the relevant condition data may be preset verification data, such as sales data of a part of or all retail groups in a previous history period, or verification data separated from sales data of the retail group obtained at this time, that is, for sales data of each retail group obtained at this time, before training, the container picture may be divided into training data and verification data in advance, a basis manner of a leave-out method, a cross verification method, a self-service method, a self-training method, and the like may be adopted, and a specific item may be set as the post-verification data, and a specific item may be selected as the post-verification data, and the post-verification data may be selected, and the item may be a specific item, and the item may be selected, and the item, and the post-verification data may be selected, and the item according to the method, and the item may be selected, and the item data may be selected and the item. And (3) inputting the verification data as new training data into the preliminary training model, repeating the steps for a plurality of times, and updating the obtained training model in real time according to the training result each time to finally obtain a pre-trained training model, wherein the pre-trained training model is a display model.
Step S4000: for each display model, taking the display model as a chromosome, and encoding the chromosome into an integer array, wherein the size of each element in the integer array is limited by the container capacity of the corresponding retail group and the volume of spare part commodity corresponding to each primary class;
that is, each chromosome represents a model of display that is specifically composed of several genes, and given the total volume of the container at the hydrogen station, the chromosome may be, but is not limited to, encoded as an integer array, such that the size of each element is limited by the container capacity and the volume of the spare part commodity, and the volume of the integer array as a whole is also computable.
Step S5000: for each chromosome, taking the total container volume of the retail group corresponding to the obtained chromosome, the volume and profit of spare part commodities corresponding to each primary category and the average sales quantity in the future as constraint conditions, calculating the fitness of the chromosome through a preset fitness function, wherein the fitness function is used for calculating the expected total profit of the chromosome under the constraint conditions, specifically, the fitness function can be correspondingly set according to specific scenes, the constraint conditions are not limited here, and the constraint conditions are represented in the fitness function as associated data of the fitness function, for example, the fitness function can be set as follows:；
Wherein, Is the sum of the volumes of spare part commodities corresponding to each primary category under the chromosome,For the total container volume of the retail group to which the chromosome corresponds,Profit for the spare part commodity corresponding to the ith class,The future daily average sales of spare part commodities corresponding to the ith class are calculated, and k is the number of the first class; as can be seen from the fitness function, for a chromosome, when the sum of the volumes of spare part commodities corresponding to each primary class is larger than the total container volume of the retail group, the fitness of the chromosome is set to be 0, otherwise, the sum of the profits of the spare part commodities corresponding to each primary class under the constraint condition, namely the total profit, of the spare part commodities corresponding to the chromosome under all primary classes is calculated by combining the constraint conditions of the profits of the spare part commodities corresponding to each primary class and the average sales quantity in the future, and the total profit is the fitness of the chromosome.
It should be noted that, the constraint condition is not particularly limited, and in the subsequent calculation iteration process, new constraint conditions may be added or some constraint conditions may be removed according to circumstances; the constraint conditions can be matched with the predicted sales influence of spare part commodities in the hydrogenation station (namely, the predicted daily sales C1 of the spare part commodities in each class), the volume of the spare part commodities (comprising the volumes V1, V2 … … and vn of the spare part commodities in each class), the container capacity of the hydrogenation station (namely, the total container volume V_total after the container modeling in the hydrogenation station), the profit of the spare part commodities (namely, m 1-mn corresponding to the volume of the spare part commodities) and the like are integrated, so that the calculation of the profit of the spare part commodities under the display model can be maximized on the whole, the effective utilization of the container is ensured, and the calculated chromosome fitness is more accurate and reliable.
Step S6000: chromosome propagation is carried out based on fitness of each chromosome to obtain an initial chromosome population, and a plurality of target chromosomes are selected from the initial chromosome population to serve as a first generation population, wherein the target chromosomes are chromosomes with fitness greater than or equal to a preset fitness threshold;
In particular, chromosome breeding may be performed based on fitness of individual chromosomes using, but not limited to, roulette selection strategies or tournament selection strategies, such that a stable and reliable initial chromosome population may be obtained;
The principle of the roulette selection strategy is that the probability of occurrence in offspring is calculated according to the fitness value of the chromosome, the chromosome is selected randomly to form offspring population according to the probability, the higher the fitness value of the chromosome is, the larger the selected probability is, but it is noted that when the roulette selection strategy is applied, the fitness value of all the chromosomes must be ensured to be nonnegative, otherwise, errors can be possibly encountered, in order to solve the problem, a minimum fitness value fmin can be set, and if the fitness value of a certain chromosome is smaller than or equal to fmin, the selected probability is 0; if the fitness value of a chromosome is equal to fmin, then the probability of being selected is 1/n, where n is the size of the population.
The basic idea of the tournament selection strategy is to select the first-ranked chromosome in each round of match and add it to the next generation population, the key of the tournament selection method is to select how many chromosomes participate in each round of match (marked as k), if k is too small, premature convergence may be caused, so that the population lacks diversity, but if k is too large, the advantages of the tournament selection strategy cannot be fully exerted, and therefore proper k needs to be selected according to practical situations; in addition, tournament selection strategies may be selected for individuals with low fitness, and thus may be used in conjunction with other genetic algorithm operations (e.g., crossover, mutation, etc., operations described in subsequent embodiments) to enhance optimization when in actual use.
Both strategies are used when finding a solution to the optimization problem, but when solving the minimization problem, the fitness function needs to be converted into the inverse or the opposite number to be converted into the maximization problem, but in this embodiment, the maximization profit needs to be obtained, so that the solution can be directly used without considering the situation.
Step S7000: performing crossover and mutation operations on chromosomes in the first generation population to obtain a second generation population, and repeatedly performing iteration operations of chromosome propagation, selection, crossover and mutation by taking the second generation population as an iteration starting point until the preset iteration times are reached or the adaptability of the chromosomes reaches a stable level to obtain a final chromosome population;
After one-time crossing and mutation operation, the required population can not be directly obtained, so that the iteration operation of chromosome propagation, selection, crossing and mutation can be repeatedly performed until the preset iteration times are reached or the adaptability of the chromosomes reaches a stable level, so that the required final chromosome population can be obtained; the number of iterations may be specifically set according to the situation, and it may be determined whether the fitness of the chromosome reaches a stable level, or may be in various manners, for example, by calculating a difference value between the overall fitness average value of all chromosomes in the population under the iteration and the overall fitness average value of all chromosomes in the population under the previous iteration, and if so, it may be considered that the fitness of the chromosome has reached a stable level, or vice versa, and the difference value may also be a variance difference value, or the like, where the difference value is not limited.
Step S8000: from the final chromosome population, the chromosome with the highest fitness is selected as the optimal display model, and the spare part commodities of all the hydrogen stations in the corresponding retail group are displayed and placed according to the optimal display model.
In the step, not only the predicted sales volume influence of spare part commodities of the hydrogenation station is considered, but also constraint conditions such as the volume of the spare part commodities, the container capacity of the hydrogenation station and the profit of the spare part commodities are synthesized, so that the profit of the spare part commodities under the display model is maximized and the effective utilization of the container is ensured.
As shown in FIG. 2, in one embodiment of the present application, when at least one of the docking stations introduces a target spare part commodity for which no sales records exist, the method may further include, but is not limited to, steps S9000 through S12000.
Step S9000: selecting one retail group from the plurality of retail groups, the total sales of which is closest to the average of sales of all the retail groups, as a test group to ensure that the test group can represent the general characteristics and customer requirements of the corresponding retail group;
Step S10000: identifying and marking a first class to which the target spare part commodity belongs as a test class;
Step S11000: acquiring historical sales data and market trend data of spare part commodities corresponding to test categories in a test group;
Step S12000: and calculating the historical daily average sales of spare part commodities corresponding to the test categories in the test group according to the historical sales data and the market trend data, and predicting the future daily initial sales of the target spare part commodities according to the historical daily average sales of the spare part commodities corresponding to the test categories in the test group.
In the step, for new products added to the hydrogenation station without any sales records of the hydrogenation station, the sales data is combined by cold start processing as shown above, namely by trial sales in a representative retail group, so as to quickly formulate and adjust a replenishment strategy for the new products; the historical sales data and market trend data of spare parts corresponding to the test category in the test group can be obtained through related data in a historical time period, the historical sales data represents the sales actual quantity of the spare parts, the market trend data represents the sales distribution composition of the spare parts, specific calculation modes are well known to those skilled in the art, details are not repeated herein, specifically, the market trend data represent the sales trend of the spare parts corresponding to the test category in the market, in short, whether the spare parts are favored by customers or not are usually represented by percentage ratios according to the sales distribution composition condition, the spare parts can be multiple, for example, if the spare parts corresponding to the test category are the sensor category goods, the monthly goods intake quantity of the spare parts is counted respectively in 1 month to 6 months, so as to determine the general market trend of the sensor category goods in 1 month to 6 months through the daily relative proportion, or the daily selling time of the spare parts corresponding to the sensor category can be counted, namely, whether the spare parts are purchased by customers in each day is favored by the customer daily, the whole market trend data can be determined through the daily trend data, and the sales trend data can be further determined through the daily market trend data.
As shown in fig. 3, in step S12000, "predicting the future daily initial sales of the target spare part items according to the historical daily average sales of the spare part items corresponding to the test categories in the test group" may include, but is not limited to, steps S12100 to S12200, according to one embodiment of the present application.
Step S12100: continuously collecting trial sales data of target spare part commodities in a test group in a target time period;
Step S12200: and dynamically adjusting a display model corresponding to the test group according to the trial sales data, and adding the target spare part commodity to each of the rest retail groups when the trial sales data is greater than or equal to preset trial sales reference data.
In the step, a new product is introduced into a test set, sales performance of the new product is monitored, and a display model of the new product is dynamically adjusted according to the sales data at a specific time (for example, after a week or a month) by collecting the sales data of the new product in the test set so as to evaluate the market acceptance of the new product based on the sales data of the test set, if the new product performs well in the test set, the new product can be gradually promoted to other hydrogen stations in the same group, and can also be further added to other retail sets.
It should be noted that the trial reference data may be set accordingly according to a specific application scenario, which is not limited herein.
As shown in fig. 4, step S5000 may include, but is not limited to, steps S5010 to S5030, according to one embodiment of the application.
Step S5010: obtaining the gene composition of a chromosome, wherein the primary category comprises a plurality of secondary categories, and each gene of the chromosome represents the replenishment quantity of spare part commodities corresponding to one secondary category under the primary category;
step S5020: calculating the total volume of the chromosome according to the gene composition of the chromosome;
Step S5030: and when the total volume is larger than the total volume of containers of the retail group corresponding to the chromosome, the chromosome is set to be invalid, the fitness of the chromosome is recorded to be 0, or when the total volume is smaller than or equal to the total volume of containers of the retail group corresponding to the chromosome, the expected total profit of the chromosome under the constraint condition is calculated, so that the fitness of the chromosome is calculated.
In this step, on the basis of knowing the genetic composition of the chromosome, since each gene of the chromosome characterizes the replenishment quantity of spare parts corresponding to one secondary category under the primary category, the total volume of the chromosome can be calculated according to the genetic composition of the chromosome, and then the total volume of the chromosome is compared with the total volume of containers of the corresponding retail group, that is, the total volume of the chromosome is greater than the total volume of containers of the retail group corresponding to the chromosome, which means that the capacity of the containers is exceeded at this time, the chromosome does not meet the requirement and needs to be placed as invalid, otherwise, the chromosome meets the requirement, and the expected total profit of the chromosome under the constraint condition under this condition can be calculated as the fitness of the chromosome.
As shown in FIG. 5, in one embodiment of the present application, the "crossover and mutation operations on chromosomes in the first generation population to obtain the second generation population" in step S7000 may include, but is not limited to, steps S7100 to S7300.
Step S7100: randomly selecting one or more genes on a plurality of chromosomes from the first generation population for mutation, and randomly selecting at least two chromosomes from the first generation population for pairwise pairing;
Step S7200: for each set of paired two chromosomes, determining the same number of at least one crossover point from each of the two chromosomes;
Step S7300: genes at all crossing points at corresponding positions of the two chromosomes are swapped.
In this step, the size of the first generation population, that is, the size of the subsequently generated population is not particularly limited, and can be set correspondingly according to a specific application scenario; the random selection of one or more genes on several chromosomes for mutation and the random selection of at least two chromosomes for pairwise pairing can be performed according to a preset mutation rate and crossover rate, and the positions of at least one crossover point of the same number respectively determined from the two chromosomes during crossover can be unlimited, but generally, the crossover points can be selected as different positions in different times of crossover to reflect a certain diversity, so that the genes on each crossover point can be basically crossed through multiple crossover, and a better crossover effect can be obtained.
As shown in fig. 6, one embodiment of the present application may further include, but is not limited to, steps S8100 to S8400 after step S8000.
Step S8100: counting the weekly actual sales of all spare part commodities in the retail group corresponding to the optimal display model;
step S8200: predicting and obtaining the future daily average sales of the spare part commodities of the first class corresponding to the optimal display model according to the future daily average sales of the spare part commodities of the first class corresponding to the optimal display model;
Step S8300: comparing and calculating the actual sales per week with the future sales per week to obtain differentiated sales per week;
step S8400: and adjusting the optimal display model according to the differentiated sales quantity so as to enable the optimal display model to be in a continuously updated state.
In this step, the weekly actual sales volume of all spare part commodities in the retail group corresponding to the optimal display model is counted to predict the future sales volume of the spare part commodities in the first class corresponding to the optimal display model, so that the weekly actual sales volume and the future sales volume can be compared and calculated, the optimal display model is adjusted according to the calculation result, so that the optimal display model is in a continuously updated state, and as can be seen, the importance of periodic updating and adjustment is emphasized, so that the sales trend is adapted, namely, the sales volume comparison and evaluation is carried out, so that the display model is adjusted in time, and the optimal state is maintained.
Note that, in addition to calculating the difference according to the weekly sales, the difference may be calculated according to the monthly sales, the quaternary sales, and the like, and the manner is similar to the above embodiment, and the description thereof is omitted here.
Step S8400 may include, but is not limited to, step S8410, in one embodiment of the application.
Step S8410: when the differential weekly sales are within the preset differential threshold, repeating the iterative operations of chromosome reproduction, selection, crossover and mutation to determine an updated final chromosome population, and selecting a chromosome with highest fitness from the updated final chromosome population as an optimal display model;
Or when the differential weekly sales are not in the preset differential threshold range, adjusting constraint conditions according to the differential weekly sales, and recalculating fitness of the chromosome through a preset fitness function based on the adjusted constraint conditions.
In this step, the magnitude between the differential weekly sales and the preset differential threshold range is compared, and under different comparison conditions, the differential weekly sales are respectively processed, that is, when the differential weekly sales are within the preset differential threshold range, the display model only needs to be finely tuned at the moment, so that the chromosome can be iteratively updated, the subsequent steps are the same as the embodiments, and when the differential weekly sales are not within the preset differential threshold range, the display model is relatively inaccurate, the fitness of the chromosome is recalculated by adjusting the constraint conditions, and the subsequent steps are the same as the embodiments, so that the optimal display model is determined again.
It will be appreciated that the constraints may be, but are not limited to, adjusted separately from the total container volume of the retail group to which the chromosome corresponds, the volume and profit of the spare part commodity to which each primary category corresponds, and the directions of the average sales volume in the future, without limitation.
Fig. 7 is a schematic structural diagram of an electronic device 1000 according to an embodiment of the present application. As shown in fig. 7, the electronic device 1000 includes a memory 1100, a processor 1200. The number of the memories 1100 and the processors 1200 may be one or more, and one memory 1100 and one processor 1200 are exemplified in fig. 7; the memory 1100 and the processor 1200 in the device may be connected by a bus or otherwise, for example in fig. 7.
The memory 1100 is used as a computer readable storage medium for storing software programs, computer executable programs and modules, such as program instructions/modules corresponding to the method for displaying articles of merchandise in a hydrogen station based on genetic algorithm according to any one of the embodiments of the present application. The processor 1200 implements the above-described genetic algorithm-based method of merchandise display for a hydrogen station spare part by running software programs, instructions, and modules stored in the memory 1100.
The memory 1100 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, at least one application program required for functions. In addition, memory 1100 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device. In some examples, memory 1100 may further include memory located remotely from processor 1200, which may be connected to the device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
An embodiment of the present application also provides a computer-readable storage medium storing computer-executable instructions for performing the method for displaying a commodity of a hydrogen station spare part based on the genetic algorithm as provided in any embodiment of the present application.
An embodiment of the present application also provides a computer program product, including a computer program or computer instructions, where the computer program or computer instructions are stored in a computer readable storage medium, and where a processor of a computer device reads the computer program or computer instructions from the computer readable storage medium, and where the processor executes the computer program or computer instructions, so that the computer device performs the method for displaying a product of a spare part in a hydrogen station based on a genetic algorithm as provided in any embodiment of the present application.
The electronic device and the application scenario described in the embodiments of the present application are for more clearly describing the technical solution of the embodiments of the present application, and do not constitute a limitation on the technical solution provided by the embodiments of the present application, and those skilled in the art can know that, with the evolution of the electronic device and the appearance of a new application scenario, the technical solution provided by the embodiments of the present application is applicable to similar technical problems.
Those of ordinary skill in the art will appreciate that all or some of the steps of the methods, systems, functional modules/units in the devices disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof.
In a hardware implementation, the division between the functional modules/units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be performed cooperatively by several physical components. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as known to those skilled in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer. Furthermore, as is well known to those of ordinary skill in the art, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media.
As used in this specification, the terms "component," "module," "system," and the like are intended to refer to a computer-related entity, either hardware, firmware, a combination of hardware and software, or software in execution. For example, a component may be, but is not limited to being, a process running on a processor, an object, an executable, a thread of execution, a program, or a computer. By way of illustration, both an application running on a computing device and the computing device can be a component. One or more components may reside within a process or thread of execution and a component may be localized on one computer or distributed between 2 or more computers. Furthermore, these components can execute from various computer readable media having various data structures stored thereon. The components may communicate by way of local or remote processes such as in accordance with a signal having one or more data packets (e.g., data from a local system, a distributed system, or two components interacting with one another across a network, such as the internet with other systems by way of the signal).
Claims (10)
1. A genetic algorithm-based method for displaying a commodity of a hydrogen station spare part, comprising:
acquiring spare part commodity photos on commodity shelves of all the hydrogenation stations, classifying and identifying all the spare part commodity photos to obtain classification and identification results, and classifying the spare part commodity on the commodity shelves of all the hydrogenation stations according to the classification and identification results to obtain a plurality of first-class categories;
According to the obtained sales records of the spare part commodities corresponding to the primary categories, calculating the historical daily average sales of the spare part commodities corresponding to the primary categories, and predicting the future daily average sales of the spare part commodities corresponding to the primary categories according to the historical daily average sales of the spare part commodities corresponding to the primary categories;
Pre-grouping the various hydrogenation stations according to the obtained geographic position information and sales spare part commodity information of all the hydrogenation stations to obtain a plurality of retail groups, and respectively establishing a corresponding display model for each retail group, wherein each retail group comprises at least one hydrogenation station;
For each of the display models, taking the display model as a chromosome, and encoding the chromosome into an integer array, wherein the size of each element in the integer array is limited by the container capacity of the corresponding retail group and the volume of spare part commodity corresponding to each of the primary categories;
For each chromosome, calculating the fitness of the chromosome by taking the total container volume of the retail group corresponding to the obtained chromosome, the volume and profit of spare part commodities corresponding to each primary category and the average sales volume in the future as constraint conditions, and calculating the expected total profit of the chromosome under the constraint conditions through a preset fitness function, wherein the fitness function is used for calculating the expected total profit of the chromosome under the constraint conditions;
Chromosome propagation is carried out based on fitness of each chromosome to obtain an initial chromosome population, and a plurality of target chromosomes are selected from the initial chromosome population to serve as first generation populations, wherein the target chromosomes are chromosomes with the fitness being greater than or equal to a preset fitness threshold;
Performing crossover and mutation operations on the chromosomes in the first generation population to obtain a second generation population, and repeating iteration operations of chromosome propagation, selection, crossover and mutation by taking the second generation population as an iteration starting point until the preset iteration times are reached or the fitness of the chromosomes reaches a stable level to obtain a final chromosome population;
And selecting the chromosome with the highest fitness from the final chromosome population as the optimal display model, and displaying and placing spare part commodities of all the hydrogen stations in the corresponding retail groups according to the optimal display model.
2. The genetic algorithm-based method for displaying inventory of parts in a hydrogen addition station of claim 1, wherein when at least one of the hydrogen addition stations introduces a target inventory item for which no sales record exists, the method further comprises:
Selecting one of the retail groups having a total sales closest to the average of sales of all of the retail groups as a test group from a plurality of the retail groups;
identifying and marking the primary category of the target spare part commodity as a test category;
Acquiring historical sales data and market trend data of spare part commodities corresponding to the test categories in the test group;
And calculating the historical daily average sales volume of spare part commodities corresponding to the test categories in the test group according to the historical sales data and the market trend data, and predicting the future daily initial sales volume of the target spare part commodities according to the historical daily average sales volume of the spare part commodities corresponding to the test categories in the test group.
3. The genetic algorithm-based method for displaying the inventory of the hydrogen plant spare parts according to claim 2, wherein the predicting the future daily initial sales of the target inventory according to the historical daily average sales of the inventory corresponding to the test category in the test group further comprises:
continuously collecting trial sales data of the target spare part commodity in the test group in a target time period;
and dynamically adjusting the display model corresponding to the test group according to the trial sales data, and adding the target spare part commodity to the rest retail groups when the trial sales data is greater than or equal to preset trial sales reference data.
4. The genetic algorithm-based commodity display method for a hydrogen plant according to claim 1, wherein said calculating the fitness of said chromosome by a preset fitness function comprises:
obtaining the gene composition of the chromosome, wherein the primary category comprises a plurality of secondary categories, and each gene of the chromosome characterizes the replenishment quantity of spare part commodities corresponding to one secondary category under the primary category;
calculating the total volume of the chromosome according to the gene composition of the chromosome;
And when the total volume is larger than the total volume of containers of the retail group corresponding to the chromosome, setting the chromosome as invalid, recording the fitness of the chromosome as 0, or when the total volume is smaller than or equal to the total volume of containers of the retail group corresponding to the chromosome, calculating the expected total profit of the chromosome under the constraint condition so as to realize the calculation of the fitness of the chromosome.
5. The genetic algorithm-based merchandise display method of claim 4, wherein said crossing and mutating said chromosomes in said first generation population to obtain a second generation population, comprising:
Randomly selecting one or more genes on a plurality of chromosomes from the first generation population for mutation, and randomly selecting at least two chromosomes from the first generation population for pairwise pairing;
Determining, for each set of paired two said chromosomes, the same number of at least one crossover point from each of the two said chromosomes;
the genes at all the crossing points at the corresponding positions of the two chromosomes are swapped.
6. The genetic algorithm-based commodity display method for a hydrogen plant according to claim 1, wherein said chromosome reproduction based on fitness of each of said chromosomes comprises:
chromosome breeding is performed based on fitness of each of the chromosomes using a roulette selection strategy or a tournament selection strategy.
7. The genetic algorithm-based method of displaying inventory of hydrogen stations according to any one of claims 1 to 6, wherein after the displaying all inventory of hydrogen stations in the respective retail group according to the optimal display model, further comprising:
Statistically optimizing actual sales of all spare part commodities in the retail group corresponding to the display model per week;
Predicting and obtaining the optimal future daily average sales volume of the spare part commodities in the first class corresponding to the display model according to the optimal future daily average sales volume of the spare part commodities in the first class corresponding to the display model;
Comparing and calculating the actual weekly sales with the future weekly sales to obtain differentiated weekly sales;
And adjusting the optimal display model according to the differentiated sales volume so as to enable the optimal display model to be in a continuously updated state.
8. The genetic algorithm-based merchandise display method of claim 7, wherein said adjusting the optimal display model based on the differentiated sales volume comprises:
when the differentiated weekly sales are within a preset difference threshold, repeating iterative operations of chromosome reproduction, selection, crossover and mutation to determine an updated final chromosome population, and selecting the chromosome with the highest fitness from the updated final chromosome population as the optimal display model;
Or alternatively
And when the differentiated weekly sales are not in the preset difference threshold range, adjusting the constraint conditions according to the differentiated weekly sales, and recalculating fitness of the chromosome through a preset fitness function based on the adjusted constraint conditions.
9. An electronic device, comprising:
At least one processor;
At least one memory for storing at least one program;
A method of genetic algorithm-based merchandise display of a hydrogen station according to any one of claims 1 to 8 when at least one of said programs is executed by at least one of said processors.
10. A computer-readable storage medium, in which a processor-executable program is stored, which when executed by a processor is configured to implement the genetic algorithm-based commodity display method for a hydrogen station spare part according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410354053.7A CN117952673B (en) | 2024-03-27 | 2024-03-27 | Genetic algorithm-based method for displaying spare parts of hydrogen station and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410354053.7A CN117952673B (en) | 2024-03-27 | 2024-03-27 | Genetic algorithm-based method for displaying spare parts of hydrogen station and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117952673A true CN117952673A (en) | 2024-04-30 |
| CN117952673B CN117952673B (en) | 2024-06-25 |
Family
ID=90793029
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410354053.7A Active CN117952673B (en) | 2024-03-27 | 2024-03-27 | Genetic algorithm-based method for displaying spare parts of hydrogen station and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117952673B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030200129A1 (en) * | 2002-04-23 | 2003-10-23 | Kimberly-Clark Worldwide, Inc. | Method and system for allocating shelf space |
| JP2010152504A (en) * | 2008-12-24 | 2010-07-08 | Osaka Prefecture Univ | Commodity shelf arrangement device |
| CN109308630A (en) * | 2018-08-09 | 2019-02-05 | 虫极科技（北京）有限公司 | A kind of Intelligent cargo cabinet and its commodity display method |
| CN110070231A (en) * | 2019-04-26 | 2019-07-30 | 广州大学 | A kind of intelligent repository restocking method and device based on genetic algorithm |
| CN111311293A (en) * | 2018-12-12 | 2020-06-19 | 北京京东尚科信息技术有限公司 | Method and apparatus for determining merchandise display position |
| CN111724188A (en) * | 2019-03-22 | 2020-09-29 | 北京沃东天骏信息技术有限公司 | Method, apparatus, device and storage medium for optimizing commodity display position |
| CN113837694A (en) * | 2021-09-24 | 2021-12-24 | 多点生活(成都)科技有限公司 | Article display method, apparatus, electronic device and readable medium |
| CN117745323A (en) * | 2023-12-22 | 2024-03-22 | 广州市禾赢文化传播有限公司 | Retail content management method and system based on big data |
-
2024
- 2024-03-27 CN CN202410354053.7A patent/CN117952673B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030200129A1 (en) * | 2002-04-23 | 2003-10-23 | Kimberly-Clark Worldwide, Inc. | Method and system for allocating shelf space |
| JP2010152504A (en) * | 2008-12-24 | 2010-07-08 | Osaka Prefecture Univ | Commodity shelf arrangement device |
| CN109308630A (en) * | 2018-08-09 | 2019-02-05 | 虫极科技（北京）有限公司 | A kind of Intelligent cargo cabinet and its commodity display method |
| CN111311293A (en) * | 2018-12-12 | 2020-06-19 | 北京京东尚科信息技术有限公司 | Method and apparatus for determining merchandise display position |
| CN111724188A (en) * | 2019-03-22 | 2020-09-29 | 北京沃东天骏信息技术有限公司 | Method, apparatus, device and storage medium for optimizing commodity display position |
| CN110070231A (en) * | 2019-04-26 | 2019-07-30 | 广州大学 | A kind of intelligent repository restocking method and device based on genetic algorithm |
| CN113837694A (en) * | 2021-09-24 | 2021-12-24 | 多点生活(成都)科技有限公司 | Article display method, apparatus, electronic device and readable medium |
| CN117745323A (en) * | 2023-12-22 | 2024-03-22 | 广州市禾赢文化传播有限公司 | Retail content management method and system based on big data |
Non-Patent Citations (2)
| Title |
|---|
| 易艳红 等: "货架摆放量影响需求的库存管理", 上海师范大学学报(自然科学版), vol. 40, no. 6, 31 December 2011 (2011-12-31), pages 629 - 636 * |
| 李焕森 等: "基于深度学习技术的卷烟陈列智能化督导的研究与应用", 中国烟草学报, 26 January 2024 (2024-01-26), pages 1 - 13 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117952673B (en) | 2024-06-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210264448A1 (en) | Privacy preserving ai derived simulated world | |
| CN111861759B (en) | Matching method and system for product and customer group | |
| US20220284386A1 (en) | Computerized inventory redistribution control system | |
| CN113469597A (en) | Intelligent supply chain system and server platform | |
| US20210166179A1 (en) | Item substitution techniques for assortment optimization and product fulfillment | |
| US20230385857A1 (en) | Predictive systems and processes for product attribute research and development | |
| CN111080206A (en) | Method, device and equipment for generating replenishment list and storage medium | |
| US20210224351A1 (en) | Method and system for optimizing an objective having discrete constraints | |
| CN115423538A (en) | Method and device for predicting new product sales data, storage medium and electronic equipment | |
| CN110232150B (en) | User data analysis method and device, readable storage medium and terminal equipment | |
| CN113674040A (en) | Vehicle quotation method, computer device and computer-readable storage medium | |
| CN110348947A (en) | Object recommendation method and device | |
| CN113780913B (en) | Method and device for generating safety stock information | |
| CN117952673B (en) | Genetic algorithm-based method for displaying spare parts of hydrogen station and storage medium | |
| CN116881242A (en) | Intelligent storage system for purchasing data of fresh agricultural product electronic commerce | |
| CN114219547B (en) | Method, device, equipment and storage medium for determining store ordering amount | |
| CN115439180A (en) | Target object determination method and device, electronic equipment and storage medium | |
| CN114549174A (en) | User behavior prediction method and device, computer equipment and storage medium | |
| CN114444990A (en) | Product selection method for supply chain network front-end bin | |
| Cevallos-Torres et al. | Decision making in inventory control by using artificial neural networks | |
| CN117952656B (en) | Data mining method and related device | |
| Walek et al. | Proposal of an expert system for predicting warehouse stock | |
| KR102492907B1 (en) | Method and apparatus for providing fishery product distribution and management service based on artificial intelligence | |
| CN117974270B (en) | AI model-based footwear data management method and system | |
| US20230342793A1 (en) | Machine-learning (ml)-based system and method for generating dso impact score for financial transaction |
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 |