CN117557318A - Management intelligent analysis method and system based on virtual shopping - Google Patents
Management intelligent analysis method and system based on virtual shopping Download PDFInfo
- Publication number
- CN117557318A CN117557318A CN202311853329.8A CN202311853329A CN117557318A CN 117557318 A CN117557318 A CN 117557318A CN 202311853329 A CN202311853329 A CN 202311853329A CN 117557318 A CN117557318 A CN 117557318A
- Authority
- CN
- China
- Prior art keywords
- shopping
- client
- platform
- similar
- period
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 32
- 238000013135 deep learning Methods 0.000 claims description 56
- 238000003062 neural network model Methods 0.000 claims description 55
- 238000012216 screening Methods 0.000 claims description 45
- 238000007726 management method Methods 0.000 claims description 30
- 210000002569 neuron Anatomy 0.000 claims description 21
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 14
- 230000015654 memory Effects 0.000 claims description 14
- 238000012360 testing method Methods 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 10
- 239000013598 vector Substances 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 9
- 230000000694 effects Effects 0.000 claims description 6
- 230000009471 action Effects 0.000 claims description 5
- 230000004913 activation Effects 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 5
- 238000000034 method Methods 0.000 description 17
- 230000008569 process Effects 0.000 description 6
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000000638 solvent extraction Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000005034 decoration Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000013068 supply chain management Methods 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
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
- G06N3/061—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using biological neurons, e.g. biological neurons connected to an integrated circuit
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Software Systems (AREA)
- Accounting & Taxation (AREA)
- Mathematical Physics (AREA)
- Finance (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Neurology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an intelligent management analysis method and system based on virtual shopping, which belongs to the field of data processing systems specially applied to management.
Description
Technical Field
The invention belongs to the field of data processing systems specially suitable for management, and particularly relates to an intelligent management analysis method and system based on virtual shopping.
Background
The model is evaluated using the test dataset and the superparameters are adjusted to optimize the model performance, in addition, the confusion matrix, accuracy, recall, and F1 score metrics can be used to evaluate the model performance, predict and manage decisions: the method can be applied to various fields such as supply chain management, human resource management, marketing, financial analysis and the like, for example, the type of the demands of customers on commodities can be accurately predicted by deep learning, and similar customer purchase data and historical purchase data of the customers cannot be considered during prediction in the prior art, so that more useless data are acquired in the acquired data, further the prediction accuracy is poor, and the problems in the prior art exist;
for example, in chinese patent application publication No. CN116739653a, a sales data collection and analysis system and method are disclosed, which firstly obtain historical sales data, and then use deep neural network model based on deep learning as feature extractor to perform multi-scale extraction analysis and decoding processing on the historical sales data, so as to determine whether to increase product inventory, thereby improving accuracy and efficiency of product inventory management.
The problems proposed in the background art exist in the above patents: in the prior art, similar customer purchase data and historical customer purchase data cannot be considered when prediction is carried out, so that more useless data in collected data is caused, and further prediction accuracy is poor.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a management intelligent analysis method and a system based on virtual shopping, the invention sets a shopping period, acquires shopping category data of a client to be selected in a historical shopping period of a platform, acquires shopping category data of a first screening client in the historical shopping period of the platform, substitutes the acquired shopping category data of the client to be selected in the historical shopping period of the platform and the shopping category data of the first screening client in the historical shopping period of the platform into a similar client searching strategy to search for the similar client, calculates similar client similarity values, constructs a deep learning neural network model for predicting the shopping category probability of the client to be selected in the historical shopping period of the platform based on the shopping category data of the client to be selected, the historical similar client similarity values and the historical shopping category data of the client to be selected in the historical shopping period of the platform, acquires the shopping category data of the similar client to be selected in the platform, the calculated similar client similarity values and the shopping category data of the client to be selected in the historical shopping period of the platform, outputs commodity category probability of the client to be selected in the similar client shopping period of the deep learning neural network model, and displays commodity category probability of the client to be selected in real time according to the commodity category probability of the client to be selected in the client to be selected, and the commodity category of the client to be selected needs to be displayed in real time, and the commodity category of the commodity of the client to be selected needs to be displayed and the commodity is displayed accurately is displayed.
In order to achieve the above purpose, the present invention provides the following technical solutions:
a management intelligent analysis method based on virtual shopping comprises the following specific steps:
s1, setting a shopping period, acquiring shopping category data of a to-be-selected client in a historical shopping period of a platform, and simultaneously acquiring shopping category data of a first screening client in the historical shopping period of the platform;
s2, substituting the obtained shopping category data of the client to be selected in the historical shopping period of the platform and the shopping category data of the first screening client in the historical shopping period of the platform into a similar client searching strategy to search for the similar client, and calculating a similar value of the similar client;
s3, based on the shopping category data of the historical similar clients in the shopping period of the platform, the historical similar client similarity values and the shopping category data of the historical to-be-selected clients in the historical shopping period of the platform, constructing a deep learning neural network model for predicting the shopping commodity category probability of the to-be-selected clients in the shopping period;
s4, acquiring shopping category data of similar clients of the clients to be selected on the platform, obtaining similar client similarity values through calculation, and importing the shopping category data of the clients to be selected on the historical shopping periods of the platform into a deep learning neural network model, and outputting shopping commodity category probability of the clients to be selected in the shopping periods;
And S5, displaying the corresponding commodity types in a descending order on a display interface according to the output shopping cycle shopping commodity type probability of the customer to be selected for the customer to be selected to select.
Specifically, the step S1 includes the following specific steps:
s11, setting a shopping period according to the shopping time interval of the client to be selected, wherein the shopping period is set according to the shopping time interval of the client to be selected, for example, the client to be selected performs platform shopping once on average for three days, the shopping period is set to be three days, shopping type data of the historical shopping period of the client to be selected on the platform is obtained, the shopping type data comprise the price of shopping commodities, the effect of the shopping commodities and the type data of the shopping commodities, the obtained shopping type data of the client to be selected on the historical shopping period of the platform are transmitted and stored in the form of a first dimension vector, for example, the first dimension vector is in the form of 1 piece of clothes is purchased in the first period, and then the first dimension vector is: clothing, 59 yuan, cold-proof decoration, ornament;
s12, acquiring other clients of the shopping period except the client to be selected, which have purchased goods on the platform, setting the clients as first screening clients, acquiring prices of the shopping goods, roles of the shopping goods and category data of the shopping goods of the first screening clients in the historical shopping period of the platform, and transmitting and storing the data in a second dimension vector form;
It should be noted that, the price of the shopping commodity, the action of the shopping commodity and the category data of the shopping commodity in the historical shopping period of the client are obtained only in the system calculation process, the leakage mode such as hacking is not performed, and the leakage mode is not leaked to the outside, so that the price of the shopping commodity, the action of the shopping commodity and the category data of the shopping commodity in the historical shopping period of the client cannot be obtained on the premise that the external personnel do not perform network attack, and the specific confidentiality problem is not considered;
specifically, the similar client search policy in S2 includes the following specific contents:
s21, extracting shopping category data of the historical shopping period of the client to be selected on the platform and shopping category data of the historical shopping period of the first screening client on the platform;
s22, substituting the extracted shopping category data of the client to be selected in the historical shopping period of the platform and the shopping category data of the first screening client in the historical shopping period of the platform into a similar client similar value calculation formula to calculate a similar client similar value, wherein the similar client similar value calculation formula is as follows:wherein n is the number of history periods, m is the number of shopping categories of i periods, a 1 Is a kind of duty ratio coefficient, a 2 For the price-to-duty factor, z () is the number of elements in brackets, exp () is the power of e, t i For the effect of the shopping commodity of the customer to be selected in the ith shopping period of the platform and the set formed by the category data of the shopping commodity, t' i S for the first screening client to act on the shopping commodity of the platform corresponding to the ith shopping period and the set formed by the category data of the shopping commodity ij Price, s 'of the jth shopping commodity of the ith shopping period of the platform for the customer to be selected' ij Price of the jth shopping commodity corresponding to the first screening client in the ith shopping period of the platform, wherein a 1 +a 2 ＝1；
S23, extracting a calculated similar client similarity value of the first screening client, wherein the first screening client with the similar client similarity value smaller than or equal to a set similarity threshold value is set as the similar client, and the first screening client with the similar client similarity value larger than the set similarity threshold value is not set as the similar client;
here, a is as follows 1 、a 2 The similarity threshold value is obtained by the following steps: selecting shopping data of at least 5000 groups of historical clients, dividing the historical clients into similar clients, importing the shopping data divided into the similar clients into a similar client similarity value calculation formula, substituting the calculated similar client similarity values into fitting software, and outputting optimal a meeting the judgment accuracy of the similar clients 1 、a 2 And the value of the similarity threshold.
Specifically, the content of S3 includes the following specific steps:
s31, extracting shopping category data of a historical similar client on a platform, a historical similar client similarity value and shopping category data of a historical shopping period of a historical client to be selected on the platform, constructing shopping category data which are input as the similar client on the platform, the similar client similarity value and the shopping category data of the historical shopping period of the client to be selected on the platform, and outputting a deep learning neural network model which is used as the shopping period shopping commodity category probability of the client to be selected;
s32, setting parameter training sets and parameter test sets according to the ratio of 9:1 according to the extracted shopping category data of the similar clients on the platform, the similar client similarity values and the shopping category data of the historical shopping periods of the clients to be selected on the platform; inputting 90% of parameter training sets into a deep learning neural network model for training to obtain an initial deep learning neural network model; testing the initial deep learning neural network model by using a 10% parameter test set, and outputting an optimal initial deep learning neural network model meeting the shopping commodity type probability of a client to be selected in the shopping period as the deep learning neural network model, wherein an output strategy formula of an M-layer s-th neuron in the deep learning neural network model is as follows: Wherein->For the output of the M-layer s-th neuron, < ->For the connection weight of the M-1 th layer c-th neuron and the M layer s-th neuron,/o>Input representing the c-th neuron of the M-1 th layer,/and>representing the bias of the linear relationship of the M-1 th and M-layer s-th neurons, σ () represents the Sigmoid activation function, w is the number of M-1 th neurons.
Specifically, the specific content of S4 includes the following specific steps:
s41, acquiring shopping category data of similar clients of the clients to be selected on a platform, a calculated similar value of the similar clients and shopping category data of historical shopping periods of the clients to be selected on the platform;
s42, importing the obtained shopping category data of the similar clients of the clients to be selected in the platform, the calculated similar client similarity values and the shopping category data of the clients to be selected in the historical shopping periods of the platform into the constructed deep learning neural network model, and outputting the shopping commodity category probability of the clients to be selected in the shopping periods in a descending order.
The intelligent management analysis system based on virtual shopping is realized based on the intelligent management analysis method based on virtual shopping, and comprises a data acquisition module, a similar client searching module, a deep learning neural network model building module, a commodity type probability output module, a commodity type display module and a control module, wherein the data acquisition module is used for setting a shopping period, acquiring shopping type data of a client to be selected in a historical shopping period of a platform, simultaneously acquiring shopping type data of a first screening client in the historical shopping period of the platform, and the similar client searching module is used for substituting the acquired shopping type data of the client to be selected in the historical shopping period of the platform and the shopping type data of the first screening client in the historical shopping period of the platform into a similar client searching strategy to search similar clients and calculate similar values of the similar clients.
Specifically, the deep learning neural network model construction module is used for constructing a deep learning neural network model for predicting the commodity type probability of the client to be selected in the current shopping period based on the shopping type data of the client to be selected in the current shopping period of the platform, the historical similar client similar value and the shopping type data of the client to be selected in the historical shopping period of the platform, the commodity type probability output module is used for acquiring the shopping type data of the client to be selected in the platform, the calculated similar client similar value and the shopping type data of the client to be selected in the historical shopping period of the platform, and importing the data into the constructed deep learning neural network model to output the commodity type probability of the client to be selected in the current shopping period, and the commodity type display module is used for displaying the corresponding commodity types for the client to be selected in descending order on the display interface according to the outputted commodity type probability of the client to be selected in the current shopping period.
Specifically, the control module is used for controlling the operation of the data acquisition module, the similar client searching module, the deep learning neural network model building module, the commodity type probability output module and the commodity type display module.
An electronic device, comprising: a processor and a memory, wherein the memory stores a computer program for the processor to call;
the processor executes the intelligent analysis method based on virtual shopping management by calling the computer program stored in the memory.
A computer readable storage medium storing instructions that when executed on a computer cause the computer to perform a virtual shopping based management intelligent analysis method as described above.
Compared with the prior art, the invention has the beneficial effects that:
the method comprises the steps of setting a shopping period, acquiring shopping category data of a client to be selected in a historical shopping period of a platform, acquiring shopping category data of a first screening client in the historical shopping period of the platform, substituting the acquired shopping category data of the client to be selected in the historical shopping period of the platform and the first screening client in a similar client searching strategy to search for similar clients, calculating similar values of the similar clients, displaying corresponding commodity categories in a descending order on a display interface according to the output shopping category data of the client to be selected in the current shopping period of the platform, the similar values of the historical similar clients and the shopping category data of the historical client to be selected in the historical shopping period of the platform, constructing a deep learning neural network model for predicting the commodity category probability of the client to be selected in the current shopping period of the client to be selected, acquiring the similar client category data of the client to be selected, the calculated similar client category value and the shopping category data of the client to be selected in the historical shopping period of the platform, importing the constructed deep learning neural network model, outputting the commodity category probability of the client to be selected in the current shopping period of the client to be selected, and displaying the commodity category probability of the client to be selected in a descending order on the display interface for the corresponding commodity category of the current shopping period to be selected, and the commodity category of the client to be selected, so that the commodity category of the client to be selected can be required to be displayed with real-time and commodity category needs to be accurately and the commodity category needs to be displayed for the client to be searched in real time.
Drawings
FIG. 1 is a schematic flow chart of a management intelligent analysis method based on virtual shopping;
FIG. 2 is a schematic diagram of an overall framework of a virtual shopping-based management intelligent analysis system;
FIG. 3 is a schematic diagram of a deep learning neural network model constructed in the intelligent analysis method for virtual shopping management of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments.
Example 1
Referring to fig. 1 and 3, an embodiment of the present invention is provided: a management intelligent analysis method based on virtual shopping comprises the following specific steps:
s1, setting a shopping period, acquiring shopping category data of a to-be-selected client in a historical shopping period of a platform, and simultaneously acquiring shopping category data of a first screening client in the historical shopping period of the platform;
the following is a simple example of a C language code for obtaining historical shopping period and shopping category data of the user on the platform, which is just one example, and needs to be adjusted according to actual requirements and data structures,
This exemplary code defines a function named 'getUserSshopData' that obtains shopping periods and shopping categories based on user IDs, note that this function needs to be adjusted based on actual conditions and data structures to obtain real historical shopping period and shopping category data from a database or other data source;
it should be noted that, S1 includes the following specific steps:
s11, setting a shopping period according to the shopping time interval of the client to be selected, wherein the shopping period is set according to the shopping time interval of the client to be selected, for example, the client to be selected performs platform shopping once on average for three days, the shopping period is set to be three days, shopping type data of the historical shopping period of the client to be selected on the platform is obtained, the shopping type data comprise the price of shopping commodity, the effect of the shopping commodity and the type data of the shopping commodity, the obtained shopping type data of the historical shopping period of the client to be selected on the platform is transmitted and stored in the form of a first dimension vector, for example, the first dimension vector is in the form of 1 piece of clothes is purchased in the first period, and then the first dimension vector is: clothing, 59 yuan, cold-proof decoration, ornament;
S12, acquiring other clients of the shopping period except the client to be selected, which have purchased goods on the platform, setting the clients as first screening clients, acquiring prices of the shopping goods, roles of the shopping goods and category data of the shopping goods of the first screening clients in the historical shopping period of the platform, and transmitting and storing the data in a second dimension vector form;
it should be noted that, the price of the shopping commodity, the action of the shopping commodity and the category data of the shopping commodity in the historical shopping period of the client are obtained only in the system calculation process, the leakage mode such as hacking is not performed, and the leakage mode is not leaked to the outside, so that the price of the shopping commodity, the action of the shopping commodity and the category data of the shopping commodity in the historical shopping period of the client cannot be obtained on the premise that the external personnel do not perform network attack, and the specific confidentiality problem is not considered;
s2, substituting the obtained shopping category data of the client to be selected in the historical shopping period of the platform and the shopping category data of the first screening client in the historical shopping period of the platform into a similar client searching strategy to search for the similar client, and calculating a similar value of the similar client;
It should be noted that, the similar client lookup policy in S2 includes the following specific contents:
s21, extracting shopping category data of the historical shopping period of the client to be selected on the platform and shopping category data of the historical shopping period of the first screening client on the platform;
s22, substituting the extracted shopping category data of the client to be selected in the historical shopping period of the platform and the shopping category data of the first screening client in the historical shopping period of the platform into a similar client similar value calculation formula to calculate a similar client similar value, wherein the similar client similar value calculation formula is as follows:wherein n is the number of history periods, m is the number of shopping categories of i periods, a 1 Is a kind of duty ratio coefficient, a 2 For the price-to-duty factor, z () is the number of elements in brackets, exp () is the power of e, t i For the effect of the shopping commodity of the customer to be selected in the ith shopping period of the platform and the set formed by the category data of the shopping commodity, t' i S for the first screening client to act on the shopping commodity of the platform corresponding to the ith shopping period and the set formed by the category data of the shopping commodity ij Price, s 'of the jth shopping commodity of the ith shopping period of the platform for the customer to be selected' ij Price of the jth shopping commodity corresponding to the first screening client in the ith shopping period of the platform, wherein a 1 +a 2 ＝1；
S23, extracting a calculated similar client similarity value of the first screening client, wherein the first screening client with the similar client similarity value smaller than or equal to a set similarity threshold value is set as the similar client, and the first screening client with the similar client similarity value larger than the set similarity threshold value is not set as the similar client;
here, a is as follows 1 、a 2 The similarity threshold value is obtained by the following steps: selecting shopping data of at least 5000 groups of historical clients, employing an expert to divide the historical clients into similar clients, importing the shopping data divided into the similar clients into a similar client similarity value calculation formula, substituting the calculated similar client similarity values into fitting software, and outputting optimal a meeting the judgment accuracy of the similar clients 1 、a 2 And the value of the similarity threshold;
the division of similar clients refers to dividing a client group into sub-groups with similar characteristics or behavior patterns according to certain characteristics or attributes; the division can help enterprises to better understand client demands, formulate personalized marketing strategies and provide customized services;
S3, based on the shopping category data of the historical similar clients in the shopping period of the platform, the historical similar client similarity values and the shopping category data of the historical to-be-selected clients in the historical shopping period of the platform, constructing a deep learning neural network model for predicting the shopping commodity category probability of the to-be-selected clients in the shopping period;
the content of S3 includes the following specific steps:
s31, extracting shopping category data of a historical similar client on a platform, a historical similar client similarity value and shopping category data of a historical shopping period of a historical client to be selected on the platform, constructing shopping category data which are input as the similar client on the platform, the similar client similarity value and the shopping category data of the historical shopping period of the client to be selected on the platform, and outputting a deep learning neural network model which is used as the shopping period shopping commodity category probability of the client to be selected;
the following is a simple Python code example, which is used for constructing a deep learning neural network model, the model inputs the shopping category data of the similar clients on the platform, the similar client similarity value and the shopping category data of the historical shopping period of the clients to be selected on the platform, and outputs the shopping commodity category probability of the shopping period of the clients to be selected, which is only an example, and the model needs to be adjusted according to the actual requirement and the data structure;
/>
In this example code we define a class named 'NeuralNetwork' for building a deep learning neural network model, we use the 'tf.keras.sequential' model as input and output, and the 'tf.nn.sigmoid' as activation function, we can calculate gradients using the 'backward' method and optimize using the optimizer when training the neural network, we can compute output probabilities using the 'forward' method when predicting similar customer shopping data, similar customer similarity values and candidate customer shopping data as input;
s32, setting parameter training sets and parameter test sets according to the ratio of 9:1 according to the extracted shopping category data of the similar clients on the platform, the similar client similarity values and the shopping category data of the historical shopping periods of the clients to be selected on the platform; inputting 90% of parameter training sets into a deep learning neural network model for training to obtain an initial deep learning neural network model; testing the initial deep learning neural network model by using a 10% parameter test set, and outputting an optimal initial deep learning neural network model meeting the shopping commodity type probability of a client to be selected in the shopping period as the deep learning neural network model, wherein an output strategy formula of an M-layer s-th neuron in the deep learning neural network model is as follows: Wherein->For the output of the M-layer s-th neuron, < ->For the connection weight of the M-1 th layer c-th neuron and the M layer s-th neuron,/o>Representing the input of the M-1 layer c neuron,a bias representing the linear relationship of the M-1 th and M-layer s-th neurons, σ () representing a Sigmoid activation function, w being the number of M-1 th neurons;
s4, acquiring shopping category data of similar clients of the clients to be selected on the platform, obtaining similar client similarity values through calculation, and importing the shopping category data of the clients to be selected on the historical shopping periods of the platform into a deep learning neural network model, and outputting shopping commodity category probability of the clients to be selected in the shopping periods;
the specific content of S4 includes the following specific steps:
s41, acquiring shopping category data of similar clients of the clients to be selected on a platform, a calculated similar value of the similar clients and shopping category data of historical shopping periods of the clients to be selected on the platform;
s42, importing the obtained shopping category data of the similar clients of the clients to be selected in the platform, the calculated similar client similarity values and the shopping category data of the clients to be selected in the historical shopping periods of the platform into a constructed deep learning neural network model, and outputting the shopping commodity category probability of the clients to be selected in the shopping periods in a descending order;
S5, displaying corresponding commodity types in a descending order on a display interface according to the output shopping cycle shopping commodity type probability of the customer to be selected for the customer to be selected to select;
the method comprises the steps of setting a shopping period, acquiring shopping category data of a client to be selected in a historical shopping period of a platform, acquiring shopping category data of a first screening client in the historical shopping period of the platform, substituting the acquired shopping category data of the client to be selected in the historical shopping period of the platform and the first screening client in a similar client searching strategy to search for similar clients, calculating similar values of the similar clients, displaying corresponding commodity categories in a descending order on a display interface according to the output shopping category data of the client to be selected in the current shopping period of the platform, the similar values of the historical similar clients and the shopping category data of the historical client to be selected in the historical shopping period of the platform, constructing a deep learning neural network model for predicting the commodity category probability of the client to be selected in the current shopping period of the client to be selected, acquiring the similar client category data of the client to be selected, the calculated similar client category value and the shopping category data of the client to be selected in the historical shopping period of the platform, importing the constructed deep learning neural network model, outputting the commodity category probability of the client to be selected in the current shopping period of the client to be selected, and displaying the commodity category probability of the client to be selected in a descending order on the display interface for the corresponding commodity category of the current shopping period to be selected, and the commodity category of the client to be selected, so that the commodity category of the client to be selected can be required to be displayed with real-time and commodity category needs to be accurately and the commodity category needs to be displayed for the client to be searched in real time.
Example 2
As shown in fig. 2, a virtual shopping-based management intelligent analysis system is implemented based on the above-mentioned management intelligent analysis method based on virtual shopping, and includes a data acquisition module, a similar client search module, a deep learning neural network model building module, a commodity type probability output module, a commodity type display module and a control module, where the data acquisition module is used for setting a shopping period, acquiring shopping type data of a to-be-selected client in a historical shopping period of a platform, and simultaneously acquiring shopping type data of a first screening client in the historical shopping period of the platform, and the similar client search module is used for substituting the acquired shopping type data of the to-be-selected client in the historical shopping period of the platform and the shopping type data of the first screening client in the historical shopping period of the platform into a similar client search policy to perform similar client search, and simultaneously performing calculation of a similar value of the similar client;
in this embodiment, the deep learning neural network model building module is configured to build a deep learning neural network model for predicting the commodity type probability of the to-be-selected client in the present shopping period based on the shopping type data of the to-be-selected client in the present shopping period of the platform, the historical similar client similarity value and the shopping type data of the to-be-selected client in the historical shopping period of the platform, the commodity type probability output module is configured to obtain the shopping type data of the to-be-selected client in the platform, the calculated similar client similarity value and the shopping type data of the to-be-selected client in the historical shopping period of the platform, and to input the constructed deep learning neural network model to output the commodity type probability of the to-be-selected client in the present shopping period, and the commodity type display module is configured to display the corresponding commodity types in descending order on the display interface according to the outputted shopping type probability of the to-be-selected client in the present shopping period;
In this embodiment, the control module is configured to control operations of the data acquisition module, the similar client search module, the deep learning neural network model building module, the commodity type probability output module, and the commodity type display module.
Example 3
The present embodiment provides an electronic device including: a processor and a memory, wherein the memory stores a computer program for the processor to call;
the processor executes a virtual shopping based management intelligent analysis method as described above by calling a computer program stored in the memory.
The electronic device may be configured or configured differently to generate a larger difference, and may include one or more processors (Central Processing Units, CPU) and one or more memories, where at least one computer program is stored in the memories, and the computer program is loaded and executed by the processors to implement a virtual shopping based management intelligent analysis method provided by the above method embodiment. The electronic device can also include other components for implementing the functions of the device, for example, the electronic device can also have wired or wireless network interfaces, input-output interfaces, and the like, for inputting and outputting data. The present embodiment is not described herein.
Example 4
The present embodiment proposes a computer-readable storage medium having stored thereon an erasable computer program;
the computer program, when executed on the computer device, causes the computer device to perform a virtual shopping based management intelligent analysis method as described above.
For example, the computer readable storage medium can be Read-Only Memory (ROM), random access Memory (Random Access Memory, RAM), compact disk Read-Only Memory (Compact Disc Read-Only Memory, CD-ROM), magnetic tape, floppy disk, optical data storage device, etc.
It should be understood that, in various embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present application.
It should be understood that determining B from a does not mean determining B from a alone, but can also determine B from a and/or other information.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions in accordance with embodiments of the present invention are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, by way of wired or/and wireless networks from one website site, computer, server, or data center to another. Computer readable storage media can be any available media that can be accessed by a computer or data storage devices, such as servers, data centers, etc. that contain one or more collections of available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a solid state disk.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the partitioning of units is merely one way of partitioning, and there may be additional ways of partitioning in actual implementation, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
In the description of the present specification, the descriptions of the terms "one embodiment," "example," "specific example," and the like, mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The preferred embodiments of the invention disclosed above are intended only to assist in the explanation of the invention. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise form disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best understand and utilize the invention. The invention is limited only by the claims and the full scope and equivalents thereof.
Claims (10)
1. The intelligent management analysis method based on virtual shopping is characterized by comprising the following specific steps of:
s1, setting a shopping period, acquiring shopping category data of a to-be-selected client in a historical shopping period of a platform, and simultaneously acquiring shopping category data of a first screening client in the historical shopping period of the platform;
s2, substituting the obtained shopping category data of the client to be selected in the historical shopping period of the platform and the shopping category data of the first screening client in the historical shopping period of the platform into a similar client searching strategy to search for the similar client, and calculating a similar value of the similar client;
S3, based on the shopping category data of the historical similar clients in the shopping period of the platform, the historical similar client similarity values and the shopping category data of the historical to-be-selected clients in the historical shopping period of the platform, constructing a deep learning neural network model for predicting the shopping commodity category probability of the to-be-selected clients in the shopping period;
s4, acquiring shopping category data of similar clients of the clients to be selected on the platform, obtaining similar client similarity values through calculation, and importing the shopping category data of the clients to be selected on the historical shopping periods of the platform into a deep learning neural network model, and outputting shopping commodity category probability of the clients to be selected in the shopping periods;
and S5, displaying the corresponding commodity types in a descending order on a display interface according to the output shopping cycle shopping commodity type probability of the customer to be selected for the customer to be selected to select.
2. The intelligent analysis method for virtual shopping based management of claim 1, wherein S1 comprises the following specific steps:
s11, setting a shopping period according to the shopping time interval of the client to be selected, wherein the shopping period is set according to the shopping time interval of the client to be selected, acquiring shopping category data of the historical shopping period of the client to be selected on the platform, wherein the shopping category data comprises the price of shopping commodities, the effect of the shopping commodities and the category data of the shopping commodities, and transmitting and storing the acquired shopping category data of the client to be selected on the historical shopping period of the platform in a first dimension vector form;
S12, acquiring other clients of the shopping period except the client to be selected, which have purchased goods on the platform, setting the clients as first screening clients, acquiring prices of the shopping goods, roles of the shopping goods and category data of the shopping goods of the first screening clients in the historical shopping period of the platform, and transmitting and storing the data in the form of second dimension vectors.
3. The intelligent analysis method for virtual shopping management as claimed in claim 2, wherein the similar client searching policy in S2 includes the following specific contents:
s21, extracting shopping category data of the historical shopping period of the client to be selected on the platform and shopping category data of the historical shopping period of the first screening client on the platform;
s22, substituting the extracted shopping category data of the client to be selected in the historical shopping period of the platform and the shopping category data of the first screening client in the historical shopping period of the platform into a similar client similar value calculation formula to calculate a similar client similar value, wherein the similar client similar value calculation formula is as follows:wherein n is the number of history periods, m is the number of shopping categories of i periods, a 1 Is a kind of duty ratio coefficient, a 2 For the price-to-duty factor, z () is the number of elements in brackets, exp () is the power of e, t i For the effect of the shopping commodity of the customer to be selected in the ith shopping period of the platform and the set formed by the category data of the shopping commodity, t i ' s is a set composed of the action of shopping commodity of the first screening client on the platform corresponding to the ith shopping period and the category data of the shopping commodity ij Price s of jth shopping commodity of customer to be selected in ith shopping period of platform ij 'price of the jth shopping commodity corresponding to the first screening client in the ith shopping period of the platform', wherein a) 1 +a 2 ＝1；
S23, extracting the calculated similarity value of the first screening clients, wherein the first screening clients with the similarity value smaller than or equal to the set similarity threshold value are set as the similar clients, and the first screening clients with the similarity value larger than the set similarity threshold value are not set as the similar clients.
4. The intelligent analysis method for virtual shopping management as claimed in claim 3, wherein the content of S3 includes the following steps:
s31, extracting shopping category data of a historical similar client on a platform, a historical similar client similarity value and shopping category data of a historical shopping period of a historical client to be selected on the platform, constructing shopping category data which are input as the similar client on the platform, the similar client similarity value and the shopping category data of the historical shopping period of the client to be selected on the platform, and outputting a deep learning neural network model which is used as the shopping period shopping commodity category probability of the client to be selected;
S32, setting parameter training sets and parameter test sets according to the ratio of 9:1 according to the extracted shopping category data of the similar clients on the platform, the similar client similarity values and the shopping category data of the historical shopping periods of the clients to be selected on the platform; inputting 90% of parameter training sets into a deep learning neural network model for training to obtain an initial deep learning neural network model; testing the initial deep learning neural network model by using a 10% parameter test set, and outputting an optimal initial deep learning neural network model meeting the shopping commodity type probability of a client to be selected in the shopping period as the deep learning neural network model, wherein an output strategy formula of an M-layer s-th neuron in the deep learning neural network model is as follows:wherein->For the output of the M-layer s-th neuron, < ->For the connection weight of the M-1 th layer c-th neuron and the M layer s-th neuron,/o>Input representing the c-th neuron of the M-1 th layer,/and>representing the bias of the linear relationship of the M-1 th and M-layer s-th neurons, σ () represents the Sigmoid activation function, w is the number of M-1 th neurons.
5. The intelligent analysis method for virtual shopping management as claimed in claim 4, wherein the specific content of S4 includes the following steps:
S41, acquiring shopping category data of similar clients of the clients to be selected on a platform, a calculated similar value of the similar clients and shopping category data of historical shopping periods of the clients to be selected on the platform;
s42, importing the obtained shopping category data of the similar clients of the clients to be selected on the platform, the calculated similar client similarity values and the shopping category data of the historical shopping periods of the clients to be selected on the platform into the constructed deep learning neural network model, and outputting the shopping commodity category probability of the clients to be selected in the shopping periods in a descending order.
6. The intelligent management analysis system based on virtual shopping is realized based on the intelligent management analysis method based on virtual shopping according to any one of claims 1-5, and is characterized by comprising a data acquisition module, a similar client searching module, a deep learning neural network model building module, a commodity type probability output module, a commodity type display module and a control module, wherein the data acquisition module is used for setting a shopping period, acquiring shopping type data of a client to be selected in a historical shopping period of a platform, simultaneously acquiring shopping type data of a first screening client in the historical shopping period of the platform, and the similar client searching module is used for substituting the acquired shopping type data of the client to be selected in the historical shopping period of the platform and the shopping type data of the first screening client in the historical shopping period of the platform into a similar client searching strategy to search similar clients and calculate similar values of the similar clients.
7. The intelligent analysis system for managing virtual shopping according to claim 6, wherein the deep learning neural network model construction module is configured to construct a deep learning neural network model for predicting the probability of the shopping category of the client to be selected in the present shopping period based on the shopping category data of the client to be selected in the present shopping period of the platform, the historical similar client similarity value and the historical shopping category data of the client to be selected in the present shopping period of the platform, the commodity category probability output module is configured to obtain the shopping category data of the client to be selected in the platform, the calculated similar client similarity value and the shopping category data of the client to be selected in the historical shopping period of the platform, to input the constructed deep learning neural network model, to output the probability of the shopping category of the client to be selected in the present shopping period, and the commodity category display module is configured to display the corresponding commodity categories in descending order on the display interface according to the outputted probability of the shopping category of the client to be selected in the present shopping period.
8. The intelligent analysis system for virtual shopping based management of claim 7, wherein the control module is configured to control operation of the data acquisition module, the similar client lookup module, the deep learning neural network model building module, the commodity category probability output module, and the commodity category display module.
9. An electronic device, comprising: a processor and a memory, wherein the memory stores a computer program for the processor to call;
-the processor executing a virtual shopping based management intelligent analysis method as claimed in any one of claims 1-6 by invoking a computer program stored in the memory.
10. A computer readable storage medium storing instructions which, when executed on a computer, cause the computer to perform a virtual shopping based management intelligent analysis method as claimed in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311853329.8A CN117557318B (en) | 2023-12-29 | 2023-12-29 | Management intelligent analysis method and system based on virtual shopping |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311853329.8A CN117557318B (en) | 2023-12-29 | 2023-12-29 | Management intelligent analysis method and system based on virtual shopping |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117557318A true CN117557318A (en) | 2024-02-13 |
| CN117557318B CN117557318B (en) | 2024-06-11 |
Family
ID=89813010
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311853329.8A Active CN117557318B (en) | 2023-12-29 | 2023-12-29 | Management intelligent analysis method and system based on virtual shopping |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117557318B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108665333A (en) * | 2017-03-31 | 2018-10-16 | 北京京东尚科信息技术有限公司 | Method of Commodity Recommendation, device, electronic equipment and storage medium |
| US20190279273A1 (en) * | 2018-03-09 | 2019-09-12 | Boe Technology Group Co., Ltd. | Shopping recommendation method, client, and server |
| CN112884547A (en) * | 2021-02-03 | 2021-06-01 | 绿瘦健康产业集团有限公司 | Intelligent commodity recommendation method, device, medium and terminal equipment |
| CN113191838A (en) * | 2021-04-09 | 2021-07-30 | 山东师范大学 | Shopping recommendation method and system based on heterogeneous graph neural network |
| CN114429384A (en) * | 2021-12-30 | 2022-05-03 | 杭州盟码科技有限公司 | Intelligent product recommendation method and system based on e-commerce platform |
| CN116402569A (en) * | 2023-03-09 | 2023-07-07 | 浙江创邻科技有限公司 | Commodity recommendation method, device and system based on knowledge graph and storage medium |
| CN116629973A (en) * | 2023-06-02 | 2023-08-22 | 安徽三联学院 | Commodity recommendation method and system based on neural network |
-
2023
- 2023-12-29 CN CN202311853329.8A patent/CN117557318B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108665333A (en) * | 2017-03-31 | 2018-10-16 | 北京京东尚科信息技术有限公司 | Method of Commodity Recommendation, device, electronic equipment and storage medium |
| US20190279273A1 (en) * | 2018-03-09 | 2019-09-12 | Boe Technology Group Co., Ltd. | Shopping recommendation method, client, and server |
| CN112884547A (en) * | 2021-02-03 | 2021-06-01 | 绿瘦健康产业集团有限公司 | Intelligent commodity recommendation method, device, medium and terminal equipment |
| CN113191838A (en) * | 2021-04-09 | 2021-07-30 | 山东师范大学 | Shopping recommendation method and system based on heterogeneous graph neural network |
| CN114429384A (en) * | 2021-12-30 | 2022-05-03 | 杭州盟码科技有限公司 | Intelligent product recommendation method and system based on e-commerce platform |
| CN116402569A (en) * | 2023-03-09 | 2023-07-07 | 浙江创邻科技有限公司 | Commodity recommendation method, device and system based on knowledge graph and storage medium |
| CN116629973A (en) * | 2023-06-02 | 2023-08-22 | 安徽三联学院 | Commodity recommendation method and system based on neural network |
Non-Patent Citations (3)
| Title |
|---|
| 冀俊忠, 沙志强, 刘椿年: "一种基于贝叶斯网客户购物模型的商品推荐方法", 计算机应用研究, no. 04, 28 April 2005 (2005-04-28) * |
| 王屯屯;: "基于LSTM的在线商城商品推荐研究", 现代计算机(专业版), no. 08, 15 March 2018 (2018-03-15) * |
| 陈田;: "网上智能虚拟购物中心及其关键实施策略", 上海电机学院学报, no. 05, 25 October 2010 (2010-10-25) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117557318B (en) | 2024-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Miao et al. | Context‐based dynamic pricing with online clustering | |
| CN111373415A (en) | Analyzing sequence data using neural networks | |
| US20070233586A1 (en) | Method and apparatus for identifying cross-selling opportunities based on profitability analysis | |
| CN109034960B (en) | Multi-attribute inference method based on user node embedding | |
| CN110363213A (en) | The cognitive analysis of image of clothing and classification | |
| JP2019079302A (en) | Sales activity support system, sales activity support method and sales activity support program | |
| WO2022100518A1 (en) | User profile-based object recommendation method and device | |
| CA3114298C (en) | Recommendation method and system and method and system for improving a machine learning system | |
| CN111008335B (en) | Information processing method, device, equipment and storage medium | |
| CN114663198A (en) | Product recommendation method, device and equipment based on user portrait and storage medium | |
| CN112085615A (en) | Method and device for training graph neural network | |
| US20200250623A1 (en) | Systems and techniques to quantify strength of a relationship with an enterprise | |
| WO2023284516A1 (en) | Information recommendation method and apparatus based on knowledge graph, and device, medium, and product | |
| Abbasimehr et al. | A novel time series clustering method with fine-tuned support vector regression for customer behavior analysis | |
| CN114997916A (en) | Prediction method, system, electronic device and storage medium of potential user | |
| CN113569162A (en) | Data processing method, device, equipment and storage medium | |
| CN114240555A (en) | Click rate prediction model training method and device and click rate prediction method and device | |
| CN115630221A (en) | Terminal application interface display data processing method and device and computer equipment | |
| CN115545886A (en) | Overdue risk identification method, overdue risk identification device, overdue risk identification equipment and storage medium | |
| CN116764236A (en) | Game prop recommending method, game prop recommending device, computer equipment and storage medium | |
| Radmehr et al. | A Survey of Business Intelligence Solutions in Banking Industry and Big Data Applications | |
| CN117557318B (en) | Management intelligent analysis method and system based on virtual shopping | |
| CN116523598A (en) | Medical instrument recommendation method, system and storage medium | |
| Kuo et al. | Integration of artificial immune system and K-means algorithm for customer clustering | |
| CN115456708A (en) | Recommendation model training method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |