CN115660733A - Sales prediction system and method based on artificial intelligence - Google Patents
Sales prediction system and method based on artificial intelligence Download PDFInfo
- Publication number
- CN115660733A CN115660733A CN202211378457.7A CN202211378457A CN115660733A CN 115660733 A CN115660733 A CN 115660733A CN 202211378457 A CN202211378457 A CN 202211378457A CN 115660733 A CN115660733 A CN 115660733A
- Authority
- CN
- China
- Prior art keywords
- sales data
- data
- model
- expected
- expected sales
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Abstract
The invention provides a sales prediction system and method based on artificial intelligence, and the method comprises the following steps: obtaining historical sales data in a preset period, and generating a first prediction model by using a trained first neural network according to the historical sales data; obtaining first expected sales data in a first preset period from D0 according to the first prediction model, wherein the first expected sales data at least comprise a first single-out probability of each single product, a first profit of each single product and a first contribution rate of each single product to the total profit; then, processing the first expected sales data by using a preset second prediction model to obtain second expected sales data; and processing the second expected sales data to obtain a product classification model. By the scheme of the embodiment of the invention, the single products which can be stably predicted can be accurately predicted from massive single product information, and data such as single quantity, profit and the like can be further predicted, so that effective support is provided for business decision making of merchants.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a sales prediction system and a sales prediction method based on artificial intelligence.
Background
The sales prediction refers to the estimation of the accumulated sales quantity of the commodities in a period of time in the future, and with the popularization of the internet and the development of the internet technology, the electric commerce accounts for more and more larger market share of the current commodity transaction, so that the accurate prediction of the sales quantity of the commodities has important significance on the marketing planning, the market analysis, the logistics planning and the like of an electric commerce platform. However, the existing sales prediction method is not adaptive in some scenes, so that the prediction accuracy is low.
Disclosure of Invention
The invention provides a sales prediction system and method based on artificial intelligence based on the problems, and by the scheme of the embodiment of the invention, which single products can be accurately predicted from massive single product information, the single product can be stably predicted, and the data such as the single product, the profit and the like can be further predicted, so that the business decision of a merchant can be effectively supported.
In view of the above, an aspect of the present invention provides an artificial intelligence-based sales volume prediction system, including: the system comprises an acquisition module, a model generation module and a processing module; wherein the content of the first and second substances,
the acquisition module is configured to: obtaining historical sales data in a preset period, wherein the historical sales data comprises order data, order number, number of purchasing users, sales profit rate and latest date of order output of a product;
the model generation module is configured to: generating a first prediction model by utilizing a trained first neural network according to the historical sales data;
the processing module is configured to:
obtaining first expected sales data in a first preset period from D0 according to the first prediction model, wherein the first expected sales data at least comprise a first single-out probability of each single product, a first profit of each single product and a first contribution rate of each single product to the total profit;
processing the first expected sales data by using a preset second prediction model to obtain second expected sales data;
and processing the second expected sales data to obtain a product classification model.
Optionally, in the processing the first expected sales data by using a preset second prediction model to obtain second expected sales data, the processing module is specifically configured to:
inputting the first expected sales data into the second predictive model;
ranking the first expected sales data from large to small with the first probability of making a single, the first profit, and the first contribution rate, respectively;
and selecting expected sales data within a first preset range from the first single-out probability and/or within a first profit range from the first profit and/or within a first contribution rate range from the first contribution rate to obtain the second expected sales data.
Optionally, in the step of processing the second expected sales data to obtain a product classification model, the processing module is specifically configured to:
carrying out interval division on the second expected sales data according to a preset interval division rule;
and classifying the products by using the credit rating card model and combining the interval discrimination to form a product classification model.
Optionally, the processing module is further configured to:
acquiring actual sales data in a second preset period from the DO day;
judging whether the actual sales data are in accordance with expected sales data corresponding to the second preset period in the second expected sales data within a preset sales deviation range or not;
if not, starting an abnormal detection process;
and correcting and optimizing the first prediction model and the second prediction model according to an abnormal detection result.
Optionally, in the generating a first prediction model by using a trained first neural network according to the historical sales data, the model generating module is specifically configured to:
identifying and processing null values and abnormal values in the historical sales data, and performing data conversion and data standardization on the processed data to form a sample data set;
dividing the sample data set into a training set and a test set;
inputting the training set into the first neural network, and further training the first neural network to obtain a first training model;
inputting the test set into the first training model for performance test to obtain a test result;
and correcting and optimizing the first training model according to the test result to obtain the first prediction model.
Another aspect of the present invention provides a method for predicting sales based on artificial intelligence, the method comprising:
obtaining historical sales data in a preset period, wherein the historical sales data comprises order data, order number, number of purchasing users, sales profit rate and latest date of order output of a product;
generating a first prediction model by utilizing a trained first neural network according to the historical sales data;
obtaining first expected sales data in a first preset period from D0 according to the first prediction model, wherein the first expected sales data at least comprise a first single-out probability of each single product, a first profit of each single product and a first contribution rate of each single product to the total profit;
processing the first expected sales data by using a preset second prediction model to obtain second expected sales data;
and processing the second expected sales data to obtain a product classification model.
Optionally, the step of processing the first expected sales data by using a preset second prediction model to obtain second expected sales data includes:
inputting the first expected sales data into the second predictive model;
ranking the first expected sales data from big to small with the first singleout probability, the first profit, and the first contribution rate, respectively;
and selecting expected sales data within a first preset range from the first single-out probability and/or within a first profit range from the first profit and/or within a first contribution rate range from the first contribution rate to obtain the second expected sales data.
Optionally, the step of processing the second expected sales data to obtain a product classification model includes:
carrying out interval division on the second expected sales data according to a preset interval division rule;
and classifying the products by using the credit rating card model and combining the interval discrimination to form a product classification model.
Optionally, the method further comprises:
acquiring actual sales data in a second preset period from the DO day;
judging whether the actual sales data are in accordance with expected sales data corresponding to the second preset period in the second expected sales data within a preset sales deviation range;
if not, starting an abnormal detection process;
and correcting and optimizing the first prediction model and the second prediction model according to an abnormal detection result.
Optionally, the step of generating a first prediction model by using a trained first neural network according to the historical sales data includes:
identifying and processing null values and abnormal values in the historical sales data, and performing data conversion and data standardization on the processed data to form a sample data set;
dividing the sample data set into a training set and a test set;
inputting the training set into the first neural network, and further training the first neural network to obtain a first training model;
inputting the test set into the first training model for performance test to obtain a test result;
and correcting and optimizing the first training model according to the test result to obtain the first prediction model.
By adopting the technical scheme, historical sales data in a preset period are obtained, wherein the historical sales data comprise order data, order number, number of purchased users, sales profit rate and latest date of order output of a product; generating a first prediction model by utilizing a trained first neural network according to the historical sales data; obtaining first expected sales data in a first preset period from the D0 day according to the first prediction model, wherein the first expected sales data at least comprise a first order-out probability of each single item, a first profit of each single item and a first contribution rate of each single item to the total profit; then, processing the first expected sales data by using a preset second prediction model to obtain second expected sales data; and processing the second expected sales data to obtain a product classification model. By the scheme of the embodiment of the invention, the single products which can be stably predicted can be accurately predicted from massive single product information, and the data of single quantity, profit and the like can be further predicted, so that effective support is provided for business decisions of merchants.
Drawings
FIG. 1 is a schematic block diagram of an artificial intelligence based sales prediction system provided by one embodiment of the present invention;
FIG. 2 is a flowchart of a method for artificial intelligence based sales prediction according to an embodiment of the present invention.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced otherwise than as specifically described herein and, therefore, the scope of the present invention is not limited by the specific embodiments disclosed below.
The terms "first," "second," and the like in the description and claims of the present application and in the above-described drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein may be combined with other embodiments.
An artificial intelligence based sales prediction system and method provided according to some embodiments of the present invention will be described below with reference to fig. 1 to 2.
As shown in fig. 1, an embodiment of the present invention provides an artificial intelligence-based sales volume prediction system, including: the system comprises an acquisition module, a model generation module and a processing module; wherein the content of the first and second substances,
the acquisition module is configured to: obtaining historical sales data in a preset period, wherein the historical sales data comprises order data, order number, number of purchasing users, sales profit rate and latest date of order output of a product;
the model generation module is configured to: generating a first prediction model by utilizing a trained first neural network according to the historical sales data;
the processing module is configured to:
obtaining first expected sales data in a first preset period from D0 according to the first prediction model, wherein the first expected sales data at least comprise a first single-out probability of each single product, a first profit of each single product and a first contribution rate of each single product to the total profit;
processing the first expected sales data by using a preset second prediction model to obtain second expected sales data;
and processing the second expected sales data to obtain a product classification model.
It is understood that, in the embodiment of the present invention, by using the historical sales data in combination with the trained first neural network, a first prediction model mainly for predicting whether or not an order is stabilized within a first preset time period is generated, and first expected sales data is output. The preset second prediction model is mainly used for obtaining second expected sales data including but not limited to the invoicing amount (sales), profit data and the like for the first expected sales data, and processing the second expected sales data to obtain a product classification model, such as defining S, A, B and C products.
By adopting the technical scheme of the embodiment, historical sales data in a preset period are obtained, wherein the historical sales data comprise order data, order number, number of purchased users, sales profit rate and latest date of order output of a product; generating a first prediction model by using a trained first neural network according to the historical sales data; obtaining first expected sales data in a first preset period from the D0 day according to the first prediction model, wherein the first expected sales data at least comprise a first order-out probability of each single item, a first profit of each single item and a first contribution rate of each single item to the total profit; then, processing the first expected sales data by using a preset second prediction model to obtain second expected sales data; and processing the second expected sales data to obtain a product classification model. By the scheme of the embodiment of the invention, the single products which can be stably predicted can be accurately predicted from massive single product information, and data such as single quantity, profit and the like can be further predicted, so that effective support is provided for business decision making of merchants.
It should be understood that the block diagram of the artificial intelligence based sales prediction system shown in fig. 1 is merely illustrative, and the number of the illustrated modules does not limit the scope of the present invention.
In some possible embodiments of the present invention, in the processing the first expected sales data by using a preset second prediction model to obtain second expected sales data, the processing module is specifically configured to:
inputting the first expected sales data into the second predictive model;
ranking the first expected sales data from large to small with the first probability of making a single, the first profit, and the first contribution rate, respectively;
and selecting expected sales data within a first preset range from the first single-out probability and/or within a first profit range from the first profit and/or within a first contribution rate range from the first contribution rate to obtain the second expected sales data.
It is to be understood that, in the present embodiment, the first expected sales data is input to the second predictive model; ranking the first expected sales data from large to small with the first probability of making a single, the first profit, and the first contribution rate, respectively; and selecting expected sales data within a first preset range from the first single-out probability and/or within a first profit range from the first profit and/or within a first contribution rate range from the first contribution rate to obtain the second expected sales data. According to the scheme, through analyzing key features/indexes in the first expected sales data, a sensitive data statistical model can be provided, and multiple dimensions are provided for commodity selection.
In some possible embodiments of the invention, in the processing the second expected sales data to obtain the product classification model, the processing module is specifically configured to:
carrying out interval division on the second expected sales data according to a preset interval division rule;
and classifying the products by using the credit rating card model and combining the interval discrimination to form a product classification model.
It can be understood that, in order to make the product classification degree obvious, in this embodiment, according to a data statistical analysis method, the second expected sales data is subjected to interval division according to a preset interval division rule; and classifying the products by using the credit rating card model and combining the interval discrimination to form a product classification model.
In some possible embodiments of the invention, the processing module is further configured to:
acquiring actual sales data in a second preset period from the DO day;
judging whether the actual sales data are in accordance with expected sales data corresponding to the second preset period in the second expected sales data within a preset sales deviation range;
if not, starting an abnormal detection process;
and correcting and optimizing the first prediction model and the second prediction model according to an abnormal detection result.
It can be understood that, in practice, the prediction result of the prediction model may be different from the actual sales data, and in order to make the prediction model more accurate, in the embodiment of the present invention, the actual sales data in the second preset period from the DO day is acquired; judging whether the actual sales data are in accordance with expected sales data corresponding to the second preset period in the second expected sales data within a preset sales deviation range or not; if not, starting an abnormal detection process; and correcting and optimizing the first prediction model and the second prediction model according to an abnormal detection result.
In some possible embodiments of the present invention, in the generating a first prediction model by using a trained first neural network according to the historical sales data, the model generating module is specifically configured to:
identifying and processing null values and abnormal values in the historical sales data, and performing data conversion and data standardization on the processed data to form a sample data set;
dividing the sample data set into a training set and a test set;
inputting the training set into the first neural network, and further training the first neural network to obtain a first training model;
inputting the test set into the first training model for performance test to obtain a test result;
and correcting and optimizing the first training model according to the test result to obtain the first prediction model.
It will be appreciated that in order to make the predictive model more accurate, in embodiments of the invention, the predictive model is generated using a neural network, in particular: identifying and processing null values and abnormal values in the historical sales data, and performing data conversion and data standardization on the processed data to form a sample data set; dividing the sample data set into a training set and a test set; inputting the training set into the first neural network, and further training the first neural network to obtain a first training model; inputting the test set into the first training model for performance test to obtain a test result; and correcting and optimizing the first training model according to the test result to obtain the first prediction model.
Referring to fig. 2, another embodiment of the present invention provides a method for predicting sales based on artificial intelligence, the method comprising:
obtaining historical sales data in a preset period, wherein the historical sales data comprises order data, order number, number of purchasing users, sales profit rate and latest date of order output of a product;
generating a first prediction model by utilizing a trained first neural network according to the historical sales data;
obtaining first expected sales data in a first preset period from D0 according to the first prediction model, wherein the first expected sales data at least comprise a first single-out probability of each single product, a first profit of each single product and a first contribution rate of each single product to the total profit;
processing the first expected sales data by using a preset second prediction model to obtain second expected sales data;
and processing the second expected sales data to obtain a product classification model.
It is understood that, in the embodiment of the present invention, by using the historical sales data in combination with the trained first neural network, a first prediction model mainly for predicting whether or not an order is stabilized within a first preset time period is generated, and first expected sales data is output. The preset second prediction model is mainly used for obtaining second expected sales data including but not limited to invoicing amount (sales), profit data and the like for the first expected sales data, and processing the second expected sales data to obtain a product classification model, for example, defining S, A, B and C types of products.
By adopting the technical scheme of the embodiment, historical sales data in a preset period are obtained, wherein the historical sales data comprise order data, order number, number of purchased users, sales profit rate and latest date of order output of a product; generating a first prediction model by utilizing a trained first neural network according to the historical sales data; obtaining first expected sales data in a first preset period from D0 according to the first prediction model, wherein the first expected sales data at least comprise a first single-out probability of each single product, a first profit of each single product and a first contribution rate of each single product to the total profit; then, processing the first expected sales data by using a preset second prediction model to obtain second expected sales data; and processing the second expected sales data to obtain a product classification model. By the scheme of the embodiment of the invention, the single products which can be stably predicted can be accurately predicted from massive single product information, and data such as single quantity, profit and the like can be further predicted, so that effective support is provided for business decision making of merchants.
In some possible embodiments of the present invention, the step of processing the first expected sales data by using a preset second prediction model to obtain second expected sales data includes:
inputting the first expected sales data into the second predictive model;
ranking the first expected sales data from large to small with the first probability of making a single, the first profit, and the first contribution rate, respectively;
and selecting expected sales data within a first preset range from the first single-out probability and/or within a first profit range from the first profit and/or within a first contribution rate range from the first contribution rate to obtain the second expected sales data.
It is to be understood that, in the present embodiment, the first expected sales data is input to the second predictive model; ranking the first expected sales data from big to small with the first singleout probability, the first profit, and the first contribution rate, respectively; and selecting expected sales data within a first preset range from the first single-out probability and/or within a first profit range from the first profit and/or within a first contribution rate range from the first contribution rate to obtain the second expected sales data. According to the scheme, through analyzing key features/indexes in the first expected sales data, a sensitive data statistical model can be provided, and multiple dimensions are provided for commodity selection.
In some possible embodiments of the present invention, the step of processing the second expected sales data to obtain a product classification model includes:
carrying out interval division on the second expected sales data according to a preset interval division rule;
and classifying the products by using a credit rating card model and combining the interval discrimination to form a product classification model.
It can be understood that, in order to make the degree of classification of the products obvious, in this embodiment, according to a data statistical analysis method, the second expected sales data is subjected to interval division according to a preset interval division rule; and classifying the products by using the credit rating card model and combining the interval discrimination to form a product classification model.
In some possible embodiments of the invention, the method further comprises:
acquiring actual sales data in a second preset period from the DO day;
judging whether the actual sales data are in accordance with expected sales data corresponding to the second preset period in the second expected sales data within a preset sales deviation range or not;
if not, starting an abnormal detection process;
and correcting and optimizing the first prediction model and the second prediction model according to an abnormal detection result.
It can be understood that, in practice, there may be a large difference between the prediction result of the prediction model and the actual sales data, and in order to make the prediction model more accurate, in the embodiment of the present invention, the actual sales data in the second preset period from the DO day is obtained; judging whether the actual sales data are in accordance with expected sales data corresponding to the second preset period in the second expected sales data within a preset sales deviation range or not; if not, starting an abnormal detection process; and correcting and optimizing the first prediction model and the second prediction model according to an abnormal detection result.
In some possible embodiments of the present invention, the step of generating a first prediction model using a trained first neural network according to the historical sales data includes:
identifying and processing null values and abnormal values in the historical sales data, and performing data conversion and data standardization on the processed data to form a sample data set;
dividing the sample data set into a training set and a test set;
inputting the training set into the first neural network, and further training the first neural network to obtain a first training model;
inputting the test set into the first training model for performance test to obtain a test result;
and correcting and optimizing the first training model according to the test result to obtain the first prediction model.
It will be appreciated that in order to make the predictive model more accurate, in embodiments of the invention, the predictive model is generated using a neural network, in particular: identifying and processing null values and abnormal values in the historical sales data, and performing data conversion and data standardization on the processed data to form a sample data set; dividing the sample data set into a training set and a test set; inputting the training set into the first neural network, and further training the first neural network to obtain a first training model; inputting the test set into the first training model for performance test to obtain a test result; and correcting and optimizing the first training model according to the test result to obtain the first prediction model.
It should be noted that for simplicity of description, the above-mentioned embodiments of the method are described as a series of acts, but those skilled in the art should understand that the present application is not limited by the described order of acts, as some steps may be performed in other orders or simultaneously according to the present application. Further, those skilled in the art will recognize that the embodiments described in this specification are preferred embodiments and that acts or modules referred to are not necessarily required for this application.
In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the above-described units is only one type of logical functional division, and other divisions may be realized in practice, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of some interfaces, devices or units, and may be an electric or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit may be stored in a computer readable memory if it is implemented in the form of a software functional unit and sold or used as a separate product. Based on such understanding, the technical solutions of the present application, which are essential or part of the technical solutions contributing to the prior art, or all or part of the technical solutions, may be embodied in the form of a software product, which is stored in a memory and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the above methods of the embodiments of the present application. And the aforementioned memory comprises: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk, and various media capable of storing program codes.
Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by associated hardware instructed by a program, which may be stored in a computer-readable memory, which may include: flash Memory disks, read-Only memories (ROMs), random Access Memories (RAMs), magnetic or optical disks, and the like.
The foregoing detailed description of the embodiments of the present application has been presented to illustrate the principles and implementations of the present application, and the above description of the embodiments is only provided to help understand the method and the core concept of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, the specific implementation manner and the application scope may be changed, and in summary, the content of the present specification should not be construed as a limitation to the present application.
Although the present invention is disclosed above, the present invention is not limited thereto. Various changes and modifications can be easily made by those skilled in the art without departing from the spirit and scope of the present invention, and it is within the scope of the present invention to include different functions, combination of implementation steps, software and hardware implementations.
Claims (10)
1. An artificial intelligence-based sales prediction system, comprising: the system comprises an acquisition module, a model generation module and a processing module; wherein, the first and the second end of the pipe are connected with each other,
the acquisition module is configured to: obtaining historical sales data in a preset period, wherein the historical sales data comprises order data, order number, number of purchasing users, sales profit rate and latest date of order output of a product;
the model generation module is configured to: generating a first prediction model by utilizing a trained first neural network according to the historical sales data;
the processing module is configured to:
obtaining first expected sales data in a first preset period from D0 according to the first prediction model, wherein the first expected sales data at least comprise a first single-out probability of each single product, a first profit of each single product and a first contribution rate of each single product to the total profit;
processing the first expected sales data by using a preset second prediction model to obtain second expected sales data;
and processing the second expected sales data to obtain a product classification model.
2. The artificial intelligence based sales prediction system of claim 1, wherein in the processing the first expected sales data using a preset second prediction model to obtain second expected sales data, the processing module is specifically configured to:
inputting the first expected sales data into the second predictive model;
ranking the first expected sales data from big to small with the first singleout probability, the first profit, and the first contribution rate, respectively;
and selecting expected sales data within a first preset range from the first single-out probability and/or within a first profit range from the first profit and/or within a first contribution rate range from the first contribution rate to obtain the second expected sales data.
3. The artificial intelligence based sales prediction system of claim 2, wherein in said processing the second expected sales data into a product classification model, the processing module is specifically configured to:
carrying out interval division on the second expected sales data according to a preset interval division rule;
and classifying the products by using the credit rating card model and combining the interval discrimination to form a product classification model.
4. The artificial intelligence based sales prediction system of claim 3, wherein the processing module is further configured to:
acquiring actual sales data in a second preset period from the DO day;
judging whether the actual sales data are in accordance with expected sales data corresponding to the second preset period in the second expected sales data within a preset sales deviation range;
if not, starting an abnormal detection process;
and correcting and optimizing the first prediction model and the second prediction model according to an abnormal detection result.
5. The artificial intelligence based sales prediction system of claims 1-4, wherein in the generating a first prediction model using a trained first neural network from the historical sales data, the model generation module is specifically configured to:
identifying and processing null values and abnormal values in the historical sales data, and performing data conversion and data standardization on the processed data to form a sample data set;
dividing the sample data set into a training set and a test set;
inputting the training set into the first neural network, and further training the first neural network to obtain a first training model;
inputting the test set into the first training model for performance test to obtain a test result;
and correcting and optimizing the first training model according to the test result to obtain the first prediction model.
6. A method for predicting sales based on artificial intelligence, the method comprising:
obtaining historical sales data in a preset period, wherein the historical sales data comprises order data, order number, number of purchasing users, sales profit rate and latest date of order output of a product;
generating a first prediction model by using a trained first neural network according to the historical sales data;
obtaining first expected sales data in a first preset period from D0 according to the first prediction model, wherein the first expected sales data at least comprise a first single-out probability of each single product, a first profit of each single product and a first contribution rate of each single product to the total profit;
processing the first expected sales data by using a preset second prediction model to obtain second expected sales data;
and processing the second expected sales data to obtain a product classification model.
7. The method of claim 6, wherein the step of processing the first expected sales data with a preset second prediction model to obtain second expected sales data comprises:
inputting the first expected sales data into the second predictive model;
ranking the first expected sales data from big to small with the first singleout probability, the first profit, and the first contribution rate, respectively;
and selecting expected sales data within a first preset range from the first single-out probability and/or within a first profit range from the first profit and/or within a first contribution rate range from the first contribution rate to obtain the second expected sales data.
8. The method of claim 7, wherein the step of processing the second expected sales data to obtain a product classification model comprises:
carrying out interval division on the second expected sales data according to a preset interval division rule;
and classifying the products by using the credit rating card model and combining the interval discrimination to form a product classification model.
9. The artificial intelligence based sales prediction method of claim 8, further comprising:
acquiring actual sales data in a second preset period from the DO day;
judging whether the actual sales data are in accordance with expected sales data corresponding to the second preset period in the second expected sales data within a preset sales deviation range;
if not, starting an abnormal detection process;
and correcting and optimizing the first prediction model and the second prediction model according to an abnormal detection result.
10. The artificial intelligence based sales prediction method of claims 6-9, wherein the step of generating a first prediction model using a trained first neural network based on the historical sales data comprises:
identifying and processing null values and abnormal values in the historical sales data, and performing data conversion and data standardization on the processed data to form a sample data set;
dividing the sample data set into a training set and a test set;
inputting the training set into the first neural network, and further training the first neural network to obtain a first training model;
inputting the test set into the first training model for performance test to obtain a test result;
and correcting and optimizing the first training model according to the test result to obtain the first prediction model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211378457.7A CN115660733A (en) | 2022-11-04 | 2022-11-04 | Sales prediction system and method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211378457.7A CN115660733A (en) | 2022-11-04 | 2022-11-04 | Sales prediction system and method based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115660733A true CN115660733A (en) | 2023-01-31 |
Family
ID=85016926
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211378457.7A Pending CN115660733A (en) | 2022-11-04 | 2022-11-04 | Sales prediction system and method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115660733A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107274231A (en) * | 2017-06-29 | 2017-10-20 | 北京京东尚科信息技术有限公司 | Data predication method and device |
| CN107403345A (en) * | 2017-09-22 | 2017-11-28 | 北京京东尚科信息技术有限公司 | Best-selling product Forecasting Methodology and system, storage medium and electric terminal |
| CN110443533A (en) * | 2018-05-02 | 2019-11-12 | 北京京东尚科信息技术有限公司 | Commodity divide storehouse storage method, device, electronic equipment and computer-readable medium |
| CN112132343A (en) * | 2020-09-23 | 2020-12-25 | 创优数字科技(广东)有限公司 | Commodity purchasing prediction method and system and readable storage medium |
| CN112330415A (en) * | 2020-11-19 | 2021-02-05 | 北京沃东天骏信息技术有限公司 | Live scene item sales data prediction method, training method of model and medium |
| CN112396365A (en) * | 2019-08-14 | 2021-02-23 | 顺丰科技有限公司 | Inventory item prediction method and device, computer equipment and storage medium |
| CN112734494A (en) * | 2021-01-18 | 2021-04-30 | 深圳市轱辘车联数据技术有限公司 | Sales prediction method and device, terminal equipment and readable storage medium |
| CA3177585A1 (en) * | 2021-04-16 | 2022-10-16 | Strong Force Vcn Portfolio 2019, Llc | Systems, methods, kits, and apparatuses for digital product network systems and biology-based value chain networks |
-
2022
- 2022-11-04 CN CN202211378457.7A patent/CN115660733A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107274231A (en) * | 2017-06-29 | 2017-10-20 | 北京京东尚科信息技术有限公司 | Data predication method and device |
| CN107403345A (en) * | 2017-09-22 | 2017-11-28 | 北京京东尚科信息技术有限公司 | Best-selling product Forecasting Methodology and system, storage medium and electric terminal |
| CN110443533A (en) * | 2018-05-02 | 2019-11-12 | 北京京东尚科信息技术有限公司 | Commodity divide storehouse storage method, device, electronic equipment and computer-readable medium |
| CN112396365A (en) * | 2019-08-14 | 2021-02-23 | 顺丰科技有限公司 | Inventory item prediction method and device, computer equipment and storage medium |
| CN112132343A (en) * | 2020-09-23 | 2020-12-25 | 创优数字科技(广东)有限公司 | Commodity purchasing prediction method and system and readable storage medium |
| CN112330415A (en) * | 2020-11-19 | 2021-02-05 | 北京沃东天骏信息技术有限公司 | Live scene item sales data prediction method, training method of model and medium |
| CN112734494A (en) * | 2021-01-18 | 2021-04-30 | 深圳市轱辘车联数据技术有限公司 | Sales prediction method and device, terminal equipment and readable storage medium |
| CA3177585A1 (en) * | 2021-04-16 | 2022-10-16 | Strong Force Vcn Portfolio 2019, Llc | Systems, methods, kits, and apparatuses for digital product network systems and biology-based value chain networks |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106485562B (en) | Commodity information recommendation method and system based on user historical behaviors | |
| US20210027357A1 (en) | Systems and methods for credit card selection based on a consumer's personal spending | |
| CN110008973B (en) | Model training method, method and device for determining target user based on model | |
| KR101783476B1 (en) | A system and method for distributing profit by providing source data in data transaction service | |
| CN111681051B (en) | Purchase intention prediction method and device, storage medium and terminal | |
| WO2020023647A1 (en) | Privacy preserving ai derived simulated world | |
| CN109360089A (en) | Credit risk prediction technique and device | |
| CN109685537B (en) | User behavior analysis method, device, medium and electronic equipment | |
| CN112001754A (en) | User portrait generation method, device, equipment and computer readable medium | |
| US20190080352A1 (en) | Segment Extension Based on Lookalike Selection | |
| CN111340606A (en) | Full-process income auditing method and device | |
| CN111179051A (en) | Financial target customer determination method and device and electronic equipment | |
| CN111582932A (en) | Inter-scene information pushing method and device, computer equipment and storage medium | |
| CN114116802A (en) | Data processing method, device, equipment and storage medium of Flink computing framework | |
| CN110555749B (en) | Credit behavior prediction method and device based on neural network | |
| CN115545886A (en) | Overdue risk identification method, overdue risk identification device, overdue risk identification equipment and storage medium | |
| EP3543943A1 (en) | Purchase information utilization system, purchase information utilization method, and program | |
| CN114896506A (en) | Product recommendation method, device, equipment and storage medium | |
| TW202145105A (en) | Customized marketing method and system for customer grouping service being performed by a processing module to create a marketing list | |
| CN107944589A (en) | The Forecasting Methodology and prediction meanss of ad click rate | |
| CN111177581A (en) | Multi-platform-based social e-commerce website commodity recommendation method and device | |
| CN110889716A (en) | Method and device for identifying potential registered user | |
| CN112686448B (en) | Loss early warning method and system based on attribute data | |
| CN115660733A (en) | Sales prediction system and method based on artificial intelligence | |
| CN113052604A (en) | Object detection method, device, 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 |