CN111199414A - Data analysis method and device - Google Patents
Data analysis method and device Download PDFInfo
- Publication number
- CN111199414A CN111199414A CN201811382301.XA CN201811382301A CN111199414A CN 111199414 A CN111199414 A CN 111199414A CN 201811382301 A CN201811382301 A CN 201811382301A CN 111199414 A CN111199414 A CN 111199414A
- Authority
- CN
- China
- Prior art keywords
- product
- transaction
- transaction product
- raw material
- sales information
- 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
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000007405 data analysis Methods 0.000 title claims abstract description 30
- 239000002994 raw material Substances 0.000 claims abstract description 117
- 238000012549 training Methods 0.000 claims description 30
- 230000008569 process Effects 0.000 claims description 23
- 238000012706 support-vector machine Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 13
- 238000004590 computer program Methods 0.000 description 10
- 238000012545 processing Methods 0.000 description 7
- 238000004519 manufacturing process Methods 0.000 description 6
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 230000001360 synchronised effect Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 235000008429 bread Nutrition 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004549 pulsed laser deposition Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0203—Market surveys; Market polls
Abstract
The invention discloses a data analysis method and a data analysis device, which are used for providing a new data analysis method. The method comprises the following steps: identifying each raw material product corresponding to a predetermined first transaction product to be predicted; for each raw material product, according to the transaction product, the invoicing date and the sales information recorded in each invoice, according to each first statistical period, counting first target sales information of the raw material product in each first statistical period; according to the order of each first statistical cycle, the first target sales information of each raw material product in each first statistical cycle is predicted based on the sales prediction model. When the sales information of the first transaction product is predicted, the raw material product of the first transaction product is considered, and the sales information of the first transaction product is predicted according to the sales information of the raw material recorded in the invoice, so that the analysis of the sales condition of the first transaction product is realized.
Description
Technical Field
The present invention relates to the field of data analysis technologies, and in particular, to a data analysis method and apparatus.
Background
With the development of society, the product manufacturing industry is continuously increased, and the manufactured products are full of precious. Sales and price of products have been a concern. Many methods for predicting and analyzing sales and prices of products have been proposed, and generally, prices of products in the next period of time are analyzed from prices of products in the past, and sales of products in the next period of time are analyzed from sales of products in the past.
The traditional analysis method generally adopts simple mathematical statistics, such as a ring ratio increase value, a same ratio increase value and other statistical methods to carry out statistical analysis.
With the development of internet technology, companies, enterprises, government units and the like all generate invoices when purchasing or selling products, the invoices accompany the whole process of enterprise production and operation and are also the embodiment of enterprise production and operation conditions, and how to analyze the product sales conditions and the like by using data recorded in the invoices is a technical problem to be solved.
Disclosure of Invention
The embodiment of the invention discloses a data analysis method and a data analysis device, which are used for providing a new data analysis method.
In order to achieve the above object, an embodiment of the present invention discloses a data analysis method, including:
identifying each raw material product corresponding to a predetermined first transaction product to be predicted;
for each raw material product, according to the transaction product, the invoicing date and the sales information recorded in each invoice stored in the bill bank, and according to each preset first statistical period, counting first target sales information of the raw material product in each first statistical period;
predicting sales information for the first transaction product based on the order of each first statistical cycle and the first target sales information for each raw material product in each first statistical cycle and based on a pre-trained sales prediction model.
Further, the process of training the sales prediction model in advance includes:
according to the transaction product, the invoicing date and the sales information recorded in each invoice stored in the bill bank, and according to each preset second statistical period, counting second target sales information of the first transaction product in each second statistical period;
identifying each raw material product corresponding to the predetermined first transaction product;
for each raw material product, according to the transaction product, the invoicing date and the sales information recorded in each invoice stored in the bill bank, and according to each preset second statistical period, counting third target sales information of the raw material product in each second statistical period;
and training the sales forecasting model according to the sequence of each second statistical period, the second target sales information of the first transaction product and the third target sales information of each raw material product in each second statistical period and based on a preset training model.
Further, the process of predetermining each raw material product corresponding to the first transaction product includes:
determining each target invoice corresponding to the first transaction product according to the transaction product recorded in each invoice stored in the bill bank;
determining a manufacturer of the first transaction product according to the seller and the buyer recorded in each target invoice;
determining each raw material product of the first transaction product among second transaction products purchased by a manufacturer according to the purchaser and the transaction products recorded in each invoice held in the bill store.
Further, the determining the manufacturer of the first transaction product according to the seller and buyer recorded in each target invoice comprises:
identifying each seller selling the first transaction product according to the seller recorded in each target invoice;
identifying an intermediary that both sells and purchases the first transaction product based on the seller and purchaser recorded in each target invoice;
merchants in the vendor other than the intermediary are determined to be manufacturers of the first transaction product.
Further, the determining, from the purchaser and the transaction product recorded in each invoice stored in the bill bank, the raw material product of the first transaction product among the second transaction products purchased by the manufacturer, includes;
determining each second transaction product purchased by the manufacturer according to the buyer and the transaction product recorded in each invoice stored in the bill bank, and counting the first quantity of each second transaction product purchased by the manufacturer to determine each raw material product of the first transaction product according to the first quantity of each second transaction product.
Further, the preset training model is a vector autoregressive model or a support vector machine model.
Further, the sales information includes any one of:
sales quantity, sales unit price, total sales price.
The embodiment of the invention discloses a data analysis device, which comprises:
the identification module is used for identifying each raw material product corresponding to a predetermined first transaction product to be predicted;
the counting module is used for counting first target sales information of the raw material product in each first statistical period according to the transaction product, the invoicing date and the sales information recorded in each invoice stored in the bill bank and the preset first statistical period aiming at each raw material product;
and the prediction module is used for predicting the sales information of the first transaction product according to the sequence of each first statistical cycle and the first target sales information of each raw material product in each first statistical cycle and based on a sales prediction model which is trained in advance.
Further, the apparatus further comprises:
the training module is used for counting second target sales information of the first transaction product in each second counting period according to the transaction product, the invoicing date and the sales information recorded in each invoice stored in the bill bank and according to each preset second counting period;
identifying each raw material product corresponding to the predetermined first transaction product;
for each raw material product, according to the transaction product, the invoicing date and the sales information recorded in each invoice stored in the bill bank, and according to each preset second statistical period, counting third target sales information of the raw material product in each second statistical period;
and training the sales forecasting model according to the sequence of each second statistical period, the second target sales information of the first transaction product and the third target sales information of each raw material product in each second statistical period and based on a preset training model.
Further, the apparatus further comprises: the determining module is used for determining each target invoice corresponding to the first transaction product according to the transaction product recorded in each invoice stored in the bill bank;
determining a manufacturer of the first transaction product according to the seller and the buyer recorded in each target invoice;
determining each raw material product of the first transaction product among second transaction products purchased by a manufacturer according to the purchaser and the transaction products recorded in each invoice held in the bill store.
Further, the determining module is specifically configured to identify each seller selling the first transaction product according to a seller recorded in each target invoice;
identifying an intermediary that both sells and purchases the first transaction product based on the seller and purchaser recorded in each target invoice;
merchants in the vendor other than the intermediary are determined to be manufacturers of the first transaction product.
Further, the determining module is specifically configured to determine each second transaction product purchased by the manufacturer according to the buyer and the transaction product recorded in each invoice stored in the bill repository, and count the first quantity of each second transaction product purchased by the manufacturer to determine each raw material product of the first transaction product according to the first quantity of each second transaction product.
In the embodiment of the invention, when the sales information of the first transaction product is predicted, the raw material product of the first transaction product is considered, and the sales information of the first transaction product is predicted according to the sales information of the raw material recorded in the invoice, so that the analysis of the sales condition of the first transaction product is realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic diagram of a data analysis process according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a data analysis process according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a data analysis process according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1:
fig. 1 is a schematic diagram of a data analysis process provided in embodiment 1 of the present invention, where the process includes the following steps:
s101: each raw material product corresponding to a predetermined first transaction product to be predicted is identified.
The data analysis method provided by the embodiment of the invention is applied to electronic equipment.
The electronic device may receive a forecast request for a first transaction product and forecast sales information for the first transaction product upon receiving the forecast request for the first transaction product. When the electronic device receives the first transaction product prediction request, the other device may send the prediction request of the first transaction product to the electronic device, and the electronic device receives the prediction request of the first transaction product sent by the other device, or the electronic device receives the prediction request of the first transaction product triggered by the user when the user operates on the electronic device.
The product to be predicted for sale is simply referred to herein as the first transaction product, which may be any product manufactured from raw material processing.
In the embodiment of the present invention, the electronic device may store the raw material product to be used for processing and manufacturing the first transaction product, and then the electronic device identifies the raw material product of the first transaction product that is stored in advance, or may store the raw material product corresponding to the first transaction product in another device and send the raw material product to the electronic device by the other device. The raw material product of the first transaction product stored in the electronic device may be pre-configured on the electronic device by the user.
S102: and for each raw material product, according to the transaction product, the invoicing date and the sales information recorded in each invoice stored in the bill bank, and according to each preset first statistical period, counting the first target sales information of the raw material product in each first statistical period.
Invoices issued by companies, enterprises and the like are stored in the bill bank, so that a plurality of invoices are stored in the bill bank, and invoicing dates, transaction products, selling unit prices, selling quantity, selling total price, buyers, sellers, invoice codes, invoice numbers, taxpayers and the like are recorded in common invoices, and are not described in detail herein. Wherein, the selling unit price, the selling quantity and the selling total price can be called as the selling information of the transaction product. The date of the invoice, the product of the transaction, the sales information, the purchaser and the seller described in this application refer to what these terms are specific in the invoice, and the following brief description is given:
billing time, e.g., 11 months and 5 days 2018; transaction products, such as bread, automobiles, etc.; selling unit price, e.g., 5 yuan; number of sales, e.g., 2, total sales, e.g., 8 dollars; a seller, such as x company; purchasers, for example: # # # # # limited.
For convenience of prediction, each first statistical period may be previously stored in the electronic device, the sales information of the raw material product in each first statistical period may be counted according to the transaction product, the invoicing date and the sales information recorded in the invoice, and the sales information of the raw material product in each first statistical period may be referred to as first target sales information.
The statistical process of each raw material product is the same, and any raw material product is taken as an example for explanation, firstly, the electronic device acquires each invoice in the bill bank, determines each invoice corresponding to the raw material product according to the transaction product recorded in each invoice, and for convenience of description, the invoice corresponding to the raw material product can be called a first invoice, that is, the transaction product in the first invoice is the raw material product; then, the electronic equipment counts the first invoices in each first statistical period according to the invoicing date recorded in each first invoice, namely, the invoicing dates of the first invoices are all located in the first statistical period; finally, for each first statistical period, first target sales information for the raw material product in the first statistical period is determined based on the sales information in each first invoice in the first statistical period.
S103: predicting sales information for the first transaction product based on the order of each first statistical cycle and the first target sales information for each raw material product in each first statistical cycle and based on a pre-trained sales prediction model.
In the embodiment of the present invention, the sales prediction model may be trained in advance, and at the time of training, the training may be performed according to each training sample, and the training sample may be the sales information of the first transaction product and the sales information of each raw material product in the second statistical period.
After determining the first target sales information of each raw material product in each first statistical cycle, the electronic device can predict the sales information of the first transaction product according to the sequence of each first statistical cycle, the first target sales information of each raw material product in each first statistical cycle, and a pre-trained sales prediction model. Generally, the electronic device will sequentially input the sales information of the raw material products into the sales prediction model according to a set format and a time sequence, and the predicting personnel can also input some relevant parameter information of the model, and the sales prediction model can output a result, that is, the sales information of the first transaction product is predicted.
The time intervals between the first statistical period and the second statistical period are the same, for example, 1 day, 12 hours, 1 week, etc.
In the embodiment of the invention, when the sales information of the first transaction product is predicted, the raw material product of the first transaction product is considered, and the sales information of the first transaction product is predicted according to the sales information of the raw material recorded in the invoice, so that the analysis of the sales condition of the first transaction product is realized.
Example 2:
the process of training the sales prediction model in advance comprises the following steps:
according to the transaction product, the invoicing date and the sales information recorded in each invoice stored in the bill bank, and according to each preset second statistical period, counting second target sales information of the first transaction product in each second statistical period;
identifying each raw material product corresponding to the predetermined first transaction product;
for each raw material product, according to the transaction product, the invoicing date and the sales information recorded in each invoice stored in the bill bank, and according to each preset second statistical period, counting third target sales information of the raw material product in each second statistical period;
and training the sales forecasting model according to the sequence of each second statistical period, the second target sales information of the first transaction product and the third target sales information of each raw material product in each second statistical period and based on a preset training model.
In the embodiment of the present invention, in general, in order to implement the training of the sales prediction model, training samples need to be arranged in advance, and one training sample may be understood as the sales information of the first transaction product and the sales information of each raw material product corresponding to the first transaction product in a second statistical period. The sales information of the first transaction product in the second statistical period is referred to as second target sales information, and the sales information of the raw material product in the second statistical period is referred to as third target sales information.
In order to ensure the accuracy of the prediction, when the sales prediction model is trained, the raw material products of the first transaction product are determined in advance, and the second target sales information of the first transaction product and the third target sales information of each raw material product in each second statistical period are determined.
The process of determining the raw material product of the first transaction product by the electronic device can be referred to the description of the above embodiment.
In determining the second target sales information of the first transaction product in each second statistical period, the second target sales information of the first transaction product in each second statistical period may be counted according to the transaction product, the invoicing date and the sales information recorded in each invoice stored in the bill repository and according to each preset second statistical period. Specifically, firstly, the electronic device obtains each invoice in the bill bank, determines each invoice corresponding to the first transaction product according to the transaction product recorded in each invoice, and for convenience of description, the invoice corresponding to the first transaction product may be referred to as a target invoice, that is, the transaction product in the target invoice is the first transaction product; then, the electronic equipment counts the target invoices in each second counting period according to the invoicing date recorded in each target invoice, namely, the invoicing dates of the target invoices are all located in the second counting period; finally, for each second statistical period, second target sales information of the first transaction product in the second statistical period is determined according to the sales information in each target invoice in the second statistical period.
The electronic device may count the third target sales information of the raw material product in each second statistical period according to each preset second statistical period based on the transaction product, the invoicing date and the sales information recorded in each invoice stored in the bill bank when determining the third target sales information of the raw material product in each second statistical period for each raw material product. The specific determination process is similar to the above-mentioned process for determining the second target sales information of the first transaction product in the second statistical period and determining the first target sales information of the raw material product in the first statistical period, and is not described in detail herein.
The electronic device stores a training model for training the sales prediction model in advance, which may be a support vector machine model or a vector autoregressive model. After determining the sequence of each second statistical period, the second target sales information of the first transaction product and the third target sales information of each raw material product in each second statistical period, the electronic device may train the sales prediction model based on a preset training model according to the sequence of each second statistical period, the second target sales information of the first transaction product and the third target sales information of each raw material product in each second statistical period.
Example 3:
the sales information may be generally sales amount or sales unit price or sales total.
If the sales information is the sales unit price, the process of counting the target sales information of the products in each counting period comprises the following steps: and determining the average value of the selling unit prices of the products in the statistical period as the target selling information of the products in the statistical period for each statistical period.
If the sales information is the sales quantity, the process of counting the target sales information of the product in each counting period comprises the following steps: and determining the total value of the sales quantity of the products in the statistical period as the target sales information of the products in the statistical period for each statistical period.
If the sales information is the sales unit price, the process of counting the target sales information of the products in each counting period comprises the following steps: and determining the total value of the total sales price of the product in the statistical period as the target sales information of the product in the statistical period for each statistical period.
Example 4:
in order to more accurately and conveniently determine the raw material products corresponding to the transaction products, the raw material products corresponding to each transaction product can be determined according to the data in the invoice and stored. In an embodiment of the present invention, the process of predetermining each raw material product corresponding to the first transaction product includes:
firstly, determining each target invoice corresponding to a first transaction product according to the transaction product recorded in each invoice stored in a bill bank, namely determining the transaction product in the target invoice as the first transaction product;
then, the manufacturer of the first transaction product is determined according to the seller and buyer recorded in each target invoice.
Specifically, each seller selling the first transaction product may be identified according to the seller recorded in each target invoice; identifying an intermediary that both sells and purchases the first transaction product based on the seller and purchaser recorded in each target invoice; merchants in the vendor other than the intermediary are determined to be manufacturers of the first transaction product.
The seller here may be understood as a merchant recorded in the invoice as a seller of the first transaction product, and the electronic device first determines a set of merchants recorded in the invoice that sell the first transaction product, where the merchants in the set may be self-produced selling merchants or reverse selling merchants. A merchant is then identified that is both a seller of the first transaction product and a purchaser of the first transaction product, such merchant may be referred to as an intermediary, i.e., a reselling merchant. After the seller removes the middleman, the rest can be considered as self-produced and self-sold type merchants, namely manufacturers, self-produced and self-sold.
Finally, each raw material product of the first transaction product is determined in the second transaction product purchased by the manufacturer according to the purchaser and the transaction product recorded in each invoice stored in the bill bank.
Specifically, each second transaction product purchased by the manufacturer is determined according to the purchaser and the transaction products recorded in each invoice stored in the bill bank, the first quantity of each second transaction product purchased by the manufacturer is counted, and each raw material product of the first transaction product is determined according to the first quantity of each second transaction product.
Generally, a manufacturer produces a first transaction product by itself, and the manufacturer needs to purchase a raw material product of the first transaction product, so that the raw material product of the first transaction product can be determined from the transaction products purchased by the manufacturer, and the raw material product purchased by the manufacturer is referred to as a second transaction product. The number of the raw material products may be one or plural, and the second number of the raw material products may be predetermined.
The number of manufacturers determined according to the above process may be one or more.
If the number of the manufacturers is one, the first number of each second transaction product purchased by the manufacturer can be counted, each raw material product of the first transaction product is determined according to the first number of each second transaction product, specifically, each second transaction product is sorted according to the descending order of the first number, and the second transaction product with the second number which is sorted in the top is determined as the raw material product of the first transaction product.
If the number of the manufacturers is multiple, the number of each yielding transaction product purchased by the multiple manufacturers can be counted, and at least two transaction products purchased by the manufacturers may be the same, and the number of the same second transaction products purchased by the manufacturers can be added. Determining the quantity of each second transaction product purchased by all manufacturers as a first quantity, and subsequently determining each raw material product of the first transaction product according to the first quantity of each second transaction product.
Example 5:
in order to make the process of data analysis faster and more accurate, on the basis of the above embodiments, in an embodiment of the present invention, before counting, for each product, target sales information of the product in each counting period, the method further includes:
invalid invoices in the bill bank are filtered.
Some invoices in the bill bank may be invalid, for example, the invoices which are invalidated, for example, the invoice is red, and for the invalid invoice, an invalid mark may be added to the invoice, that is, the electronic device may filter out the invoices in the bill bank which are marked with the invalid mark first.
The bill bank can be stored on the electronic equipment, and also can be stored on other equipment as long as the electronic equipment can read the invoices in the bill bank.
After knowing what the transaction product is, sparkSQL may be used to determine the first invoice corresponding to the first transaction product. The statistical timing can also be determined by sparkSQL. It can be understood that the determination, statistics and other processes of the present application can be implemented by combining sparkSQL algorithm.
Fig. 2 is a schematic diagram of a data analysis process provided in an embodiment of the present invention:
firstly, filtering invalid invoices in invoice data of a bill bank, remaining valid invoices, extracting invoices of a transaction product A from the valid invoices, counting a seller selling the transaction product A according to the invoices of the transaction product A, filtering out an intermediate seller selling the transaction product A and purchasing the transaction product A from a sales merchant, and remaining a manufacturer B producing and manufacturing the transaction product A.
Then, the transaction products purchased by the manufacturer B are counted in the valid invoice, and the three C, D, E with the largest transaction amount are taken as the raw materials of the transaction product a.
Finally, the sales relation and the price relation of the transaction product A and the raw material product C, D, E are counted according to time, the change relation between the transaction product A and the raw material product C, D, E is analyzed according to the counted data, and a sales prediction model of the transaction product A is determined for subsequent use.
Example 6:
fig. 3 is a data analysis apparatus according to an embodiment of the present invention, where the apparatus includes:
an identification module 31 for identifying each raw material product corresponding to a predetermined first transaction product to be predicted;
the counting module 32 is used for counting first target sales information of the raw material product in each first statistical period according to the transaction product, the invoicing date and the sales information recorded in each invoice stored in the bill bank and according to each preset first statistical period aiming at each raw material product;
and the predicting module 33 is used for predicting the sales information of the first transaction product according to the sequence of each first statistical cycle and the first target sales information of each raw material product in each first statistical cycle and based on a sales predicting model trained in advance.
Further, the apparatus further comprises:
the training module 34 is configured to count second target sales information of the first transaction product in each second statistical period according to the transaction product, the invoicing date and the sales information recorded in each invoice stored in the bill bank and according to each preset second statistical period;
identifying each raw material product corresponding to the predetermined first transaction product;
for each raw material product, according to the transaction product, the invoicing date and the sales information recorded in each invoice stored in the bill bank, and according to each preset second statistical period, counting third target sales information of the raw material product in each second statistical period;
and training the sales forecasting model according to the sequence of each second statistical period, the second target sales information of the first transaction product and the third target sales information of each raw material product in each second statistical period and based on a preset training model.
Further, the apparatus further comprises:
the determining module 35 is configured to determine each target invoice corresponding to the first transaction product according to the transaction product recorded in each invoice stored in the bill store;
determining a manufacturer of the first transaction product according to the seller and the buyer recorded in each target invoice;
determining each raw material product of the first transaction product among second transaction products purchased by a manufacturer according to the purchaser and the transaction products recorded in each invoice held in the bill store.
Further, the determining module 35 is specifically configured to identify each seller selling the first transaction product according to the seller recorded in each target invoice;
identifying an intermediary that both sells and purchases the first transaction product based on the seller and purchaser recorded in each target invoice;
merchants in the vendor other than the intermediary are determined to be manufacturers of the first transaction product.
Further, the determining module 35 is specifically configured to determine each second transaction product purchased by the manufacturer according to the buyer and the transaction product recorded in each invoice stored in the bill repository, and count the first quantity of each second transaction product purchased by the manufacturer to determine each raw material product of the first transaction product according to the first quantity of each second transaction product.
Example 7:
based on the same inventive concept as the data analysis method, an embodiment of the present application further provides a data analysis apparatus, configured to perform an operation performed by an electronic device in the data analysis method, where the data analysis apparatus includes: the processor and transceiver, optionally, also include memory. The processor is configured to invoke a set of programs, and when the programs are executed, the processors are enabled to execute the operations executed by the electronic device in the data analysis method. The memory is used for storing programs executed by the processor.
The processor may be a Central Processing Unit (CPU), a Network Processor (NP), or a combination of a CPU and an NP.
The processor may further include a hardware chip or other general purpose processor. The hardware chip may be an application-specific integrated circuit (ASIC), a Programmable Logic Device (PLD), or a combination thereof. The aforementioned PLDs may be Complex Programmable Logic Devices (CPLDs), field-programmable gate arrays (FPGAs), General Array Logic (GAL) and other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., or any combination thereof. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
It will also be appreciated that the memory referred to in the embodiments of the application may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The non-volatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash Memory. Volatile Memory can be Random Access Memory (RAM), which acts as external cache Memory. By way of example, but not limitation, many forms of RAM are available, such as Static random access memory (Static RAM, SRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic random access memory (Synchronous DRAM, SDRAM), Double data rate Synchronous Dynamic random access memory (DDR SDRAM), Enhanced Synchronous SDRAM (ESDRAM), Synchronous link SDRAM (SLDRAM), and Direct Rambus RAM (DR RAM). It should be noted that the memory described herein is intended to comprise, without being limited to, these and any other suitable types of memory.
The embodiment of the application provides a computer storage medium, which stores a computer program, wherein the computer program comprises a program for executing the data analysis method.
Embodiments of the present application provide a computer program product containing instructions which, when run on a computer, cause the computer to perform the above-described data analysis method.
Any kind of data analysis device that this application embodiment provided can also be a chip.
For the system/apparatus embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference may be made to some descriptions of the method embodiments for relevant points.
It is to be noted that, in this document, relational terms such as first and second, and the like are used solely to distinguish one entity or operation from another entity or operation without necessarily requiring or implying any actual such relationship or order between such entities or operations.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely application embodiment, or an embodiment combining application and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While the preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all alterations and modifications as fall within the scope of the application.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.
Claims (12)
1. A method of data analysis, the method comprising:
identifying each raw material product corresponding to a predetermined first transaction product to be predicted;
for each raw material product, according to the transaction product, the invoicing date and the sales information recorded in each invoice stored in the bill bank, and according to each preset first statistical period, counting first target sales information of the raw material product in each first statistical period;
predicting sales information for the first transaction product based on the order of each first statistical cycle and the first target sales information for each raw material product in each first statistical cycle and based on a pre-trained sales prediction model.
2. The method of claim 1, wherein the process of training the sales prediction model in advance comprises:
according to the transaction product, the invoicing date and the sales information recorded in each invoice stored in the bill bank, and according to each preset second statistical period, counting second target sales information of the first transaction product in each second statistical period;
identifying each raw material product corresponding to the predetermined first transaction product;
for each raw material product, according to the transaction product, the invoicing date and the sales information recorded in each invoice stored in the bill bank, and according to each preset second statistical period, counting third target sales information of the raw material product in each second statistical period;
and training the sales forecasting model according to the sequence of each second statistical period, the second target sales information of the first transaction product and the third target sales information of each raw material product in each second statistical period and based on a preset training model.
3. The method of claim 1 or 2, wherein predetermining each raw material product corresponding to the first trading product comprises:
determining each target invoice corresponding to the first transaction product according to the transaction product recorded in each invoice stored in the bill bank;
determining a manufacturer of the first transaction product according to the seller and the buyer recorded in each target invoice;
determining each raw material product of the first transaction product among second transaction products purchased by a manufacturer according to the purchaser and the transaction products recorded in each invoice held in the bill store.
4. The method of claim 3, wherein said determining the manufacturer of the first transaction product based on the seller and buyer recorded in each target invoice comprises:
identifying each seller selling the first transaction product according to the seller recorded in each target invoice;
identifying an intermediary that both sells and purchases the first transaction product based on the seller and purchaser recorded in each target invoice;
merchants in the vendor other than the intermediary are determined to be manufacturers of the first transaction product.
5. The method of claim 3, wherein said determining a raw material product of said first transaction product among second transaction products purchased by a manufacturer based on the purchaser and transaction products recorded in each invoice held in the voucher repository comprises;
determining each second transaction product purchased by the manufacturer according to the buyer and the transaction product recorded in each invoice stored in the bill bank, and counting the first quantity of each second transaction product purchased by the manufacturer to determine each raw material product of the first transaction product according to the first quantity of each second transaction product.
6. The method of claim 2, wherein the predetermined training model is a vector autoregressive model or a support vector machine model.
7. The method of any of claims 1-6, wherein the sales information comprises any of:
sales quantity, sales unit price, total sales price.
8. A data analysis apparatus, characterized in that the apparatus comprises:
the identification module is used for identifying each raw material product corresponding to a predetermined first transaction product to be predicted;
the counting module is used for counting first target sales information of the raw material product in each first statistical period according to the transaction product, the invoicing date and the sales information recorded in each invoice stored in the bill bank and the preset first statistical period aiming at each raw material product;
and the prediction module is used for predicting the sales information of the first transaction product according to the sequence of each first statistical cycle and the first target sales information of each raw material product in each first statistical cycle and based on a sales prediction model which is trained in advance.
9. The apparatus of claim 8, wherein the apparatus further comprises:
the training module is used for counting second target sales information of the first transaction product in each second counting period according to the transaction product, the invoicing date and the sales information recorded in each invoice stored in the bill bank and according to each preset second counting period;
identifying each raw material product corresponding to the predetermined first transaction product;
for each raw material product, according to the transaction product, the invoicing date and the sales information recorded in each invoice stored in the bill bank, and according to each preset second statistical period, counting third target sales information of the raw material product in each second statistical period;
and training the sales forecasting model according to the sequence of each second statistical period, the second target sales information of the first transaction product and the third target sales information of each raw material product in each second statistical period and based on a preset training model.
10. The apparatus of claim 8 or 9, wherein the apparatus further comprises: the determining module is used for determining each target invoice corresponding to the first transaction product according to the transaction product recorded in each invoice stored in the bill bank;
determining a manufacturer of the first transaction product according to the seller and the buyer recorded in each target invoice;
determining each raw material product of the first transaction product among second transaction products purchased by a manufacturer according to the purchaser and the transaction products recorded in each invoice held in the bill store.
11. The apparatus according to claim 10, wherein the determining module is specifically configured to identify each seller selling the first transaction product based on the seller recorded in each target invoice;
identifying an intermediary that both sells and purchases the first transaction product based on the seller and purchaser recorded in each target invoice;
merchants in the vendor other than the intermediary are determined to be manufacturers of the first transaction product.
12. The apparatus of claim 10, wherein the determining module is specifically configured to determine each second transaction product purchased by the manufacturer according to the buyer and the transaction product recorded in each invoice stored in the voucher repository, and count the first quantity of each second transaction product purchased by the manufacturer to determine each raw material product of the first transaction product according to the first quantity of each second transaction product.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811382301.XA CN111199414A (en) | 2018-11-20 | 2018-11-20 | Data analysis method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811382301.XA CN111199414A (en) | 2018-11-20 | 2018-11-20 | Data analysis method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111199414A true CN111199414A (en) | 2020-05-26 |
Family
ID=70744556
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811382301.XA Pending CN111199414A (en) | 2018-11-20 | 2018-11-20 | Data analysis method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111199414A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112488637A (en) * | 2020-12-18 | 2021-03-12 | 航天信息股份有限公司 | Method and device for collecting inventory information of finished oil, storage medium and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104268758A (en) * | 2014-09-15 | 2015-01-07 | 周刚 | Merchandise anti-counterfeiting system based on invoice and third-party e-commerce platform |
| CN104838402A (en) * | 2014-09-12 | 2015-08-12 | 深圳市银信网银科技有限公司 | Article circulation system based on electronic certificates |
| CN104838407A (en) * | 2014-09-12 | 2015-08-12 | 深圳市银信网银科技有限公司 | Electronic certificate generating device and system |
| CN107085770A (en) * | 2017-05-02 | 2017-08-22 | 北京华融启明风险管理技术股份有限公司 | Staple commodities Risk Identification Method and system, business datum method for pushing and system |
| CN108288147A (en) * | 2018-01-08 | 2018-07-17 | 东莞嘉泰钟表有限公司 | A kind of quick-searching and input control method for production management |
-
2018
- 2018-11-20 CN CN201811382301.XA patent/CN111199414A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104838402A (en) * | 2014-09-12 | 2015-08-12 | 深圳市银信网银科技有限公司 | Article circulation system based on electronic certificates |
| CN104838407A (en) * | 2014-09-12 | 2015-08-12 | 深圳市银信网银科技有限公司 | Electronic certificate generating device and system |
| CN104268758A (en) * | 2014-09-15 | 2015-01-07 | 周刚 | Merchandise anti-counterfeiting system based on invoice and third-party e-commerce platform |
| CN107085770A (en) * | 2017-05-02 | 2017-08-22 | 北京华融启明风险管理技术股份有限公司 | Staple commodities Risk Identification Method and system, business datum method for pushing and system |
| CN108288147A (en) * | 2018-01-08 | 2018-07-17 | 东莞嘉泰钟表有限公司 | A kind of quick-searching and input control method for production management |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112488637A (en) * | 2020-12-18 | 2021-03-12 | 航天信息股份有限公司 | Method and device for collecting inventory information of finished oil, storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110415119B (en) | Model training method, bill transaction prediction method, model training device, bill transaction prediction device, storage medium and equipment | |
| KR101783476B1 (en) | A system and method for distributing profit by providing source data in data transaction service | |
| US20140012643A1 (en) | Methods and systems for encouraging recycling | |
| CN108154275A (en) | Automobile residual value prediction model and Forecasting Methodology based on big data | |
| US11100409B2 (en) | Machine learning assisted transaction component settlement | |
| Salutina et al. | Transformation of business technologies into digital platforms and evaluation of the effectiveness of their application | |
| CN106920119A (en) | The evaluation method and device of a kind of user's value | |
| CN110019798B (en) | Method and system for measuring commodity type difference of sale and sale items | |
| US20130275292A1 (en) | Systems and methods for competitive apr pricing | |
| CN113781106B (en) | Commodity operation data analysis method, device, equipment and computer readable medium | |
| CN115147144A (en) | Data processing method and electronic equipment | |
| CN111199414A (en) | Data analysis method and device | |
| CN108492112B (en) | Method and device for judging false resource transfer and false transaction and electronic equipment | |
| CN112801456A (en) | Fund liquidity risk early warning method, device and electronic equipment | |
| US20150161583A1 (en) | Method and system for negotiating, generating, documenting, and fulfilling vendor financing opportunities | |
| JP2000250888A (en) | Model selection type demand predicting system by predictive purposes | |
| US20170178164A1 (en) | Systems and Methods for Use in Processing Transaction Data | |
| CN107194190B (en) | Method and device for identifying influence of service object on cost in medical cost database | |
| KR101409273B1 (en) | Method and apparatus for calculating to measure influential power of users | |
| US11935075B2 (en) | Card inactivity modeling | |
| CN110969400A (en) | Supply chain upstream and downstream data association method and device | |
| Highfill et al. | Bidding and prices for online art auctions: sofa art or investment | |
| CN114169928A (en) | Novel store sales management method, system, equipment and readable storage medium | |
| TW201516925A (en) | Assembly and charge system of processing composite discount and the method thereof | |
| CN113781120A (en) | Construction method of sales amount prediction model and sales amount prediction method |
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 |