Method and equipment for screening potential goods

Abstract

The invention provides a method and equipment for screening potential goods, and the method comprises the steps: determining index items for goods screening, and carrying out the standardization of the index items of a target goods and goods in a potential goods pool; calculating the total similarity between each commodity in the potential commodity pool and the target commodity based on each index item, and selecting a preset number of commodities with the highest total similarity to form a primary commodity set; carrying out trend, periodicity, product relevance and / or product silkworm feeding evaluation on the commodities in the preliminary screening commodity set, and selecting the commodities meeting preset conditions to form a selected commodity set; and quantifying the target commodity and the commodities in the selected commodity set into a coordinate system, and selecting the commodities meeting a preset condition to form a final selected commodity set according to the Euclidean distance and the vector included angle between each commodity in the selected commodity set and the target commodity.

Description

Technical Field

[0001] The present invention relates to the field of e-commerce, and in particular to a method and device for screening potential products. Background Art

[0002] With the development of Internet e-commerce, many brands have their main hot-selling products, but these hot-selling products have their life cycle. Often after a period of time, as the market becomes saturated, their product life cycle will enter a period of decline, and their sales will gradually decline. At this time, in e-commerce marketing, the response strategy often used is to select suitable products from the existing product pool to replace the existing hot products. This is a common and important application scenario in the e-commerce field - potential explosion screening.

[0003] In previous operational scenarios, the screening of potential explosive products often depends on the operator's understanding of the product pool and the grasp of the market prospects. At this time, the experience of the operation strategy personnel often becomes a double-edged sword. When the operation personnel are experienced, they can often quickly grasp the opportunity and quickly gain market recognition for the potential explosive products. However, if the operation personnel have limited experience and insufficient knowledge of their own products, the market can easily be eroded by competing products. Summary of the invention

[0004] In view of the problems in the prior art, the present invention provides a method for screening potential products, the method comprising:

[0005] Determine the indicators for product screening and standardize the indicators of the target products (existing popular products to be replaced) and products in the potential product pool;

[0006] Calculating the total similarity between each product in the potential product pool and the target product based on each indicator item, and selecting a preset number of products with the highest total similarity to form a preliminary product set;

[0007] Evaluate the trends, periodicity, product relevance and / or product cannibalization of the commodities in the initially screened commodity set, and select commodities meeting the preset conditions to form a selected commodity set;

[0008] The target product and the products in the selected product set are quantized into a coordinate system, and a preset number of products are selected to form a final selected product set according to the Euclidean distance and vector angle between each product in the selected product set and the target product.

[0009] Furthermore, the calculating of the total similarity between each product in the potential product pool and the target product based on each indicator item includes:

[0010] Based on the data of all index items of the target product, PCA principal component analysis is used to calculate the weight of each index item;

[0011] Calculate the similarity between each product in the potential product pool and each indicator item of the target product by using the DTW algorithm;

[0012] For each product in the potential product pool, the similarity of each index item is multiplied by the weight of the corresponding index item and the sum is calculated, so as to obtain the total similarity between the product and the target product.

[0013] Furthermore, a trend assessment is conducted on the commodities in the initially screened commodity set, including:

[0014] Use STL decomposition for each index item of the commodities in the initial screening commodity set, extract the trend component from the decomposition result, and then calculate the slope of the trend component. If the slope is positive, it means that the corresponding index item of the commodity tends to increase, and if the slope is negative, it means that the corresponding index item of the commodity tends to decrease.

[0015] Furthermore, the commodities in the initially screened commodity set are periodically evaluated, including:

[0016] Calculating the periodicity evaluation index of each index item of the commodities in the initially screened commodity set and the target commodity, so as to screen commodities that are closer to the target commodity in periodicity;

[0017] The periodicity evaluation indicators include: amplitude of seasonal components, variance of seasonal components, seasonal intensity index, and seasonal cycle peaks / troughs.

[0018] Furthermore, the product relevance of the commodities in the initially screened commodity set is evaluated, including:

[0019] For each product in the initially screened product set, the support, confidence and lift between the product and the target product are calculated to screen products that are more closely related to the target product.

[0020] Furthermore, the products in the initially screened product set are evaluated for product cannibalization, including:

[0021] For any two products in the potential product pool, the significance and regression coefficient of the two are calculated to exclude products with significant negative correlation.

[0022] Furthermore, quantizing the target product and the products in the selected product set into a coordinate system includes:

[0023] Calculating the mean value of each indicator item in the target product and the products in the selected product set within a preset time period, thereby forming a product-indicator item data matrix;

[0024] Based on the data matrix, PCA principal component analysis is used to select the principal component that meets the preset conditions as the reference indicator item;

[0025] Projecting the data in the data matrix onto the selected principal components to obtain a commodity matrix of commodity-reference indicator items;

[0026] A coordinate system is established according to the commodity matrix, so as to obtain the position of each commodity in the coordinate system.

[0027] Furthermore, selecting a preset number of commodities to form a final selection commodity set according to the Euclidean distance and vector angle between each commodity in the selected commodity set and the target commodity includes:

[0028] The commodities in the selected commodity set are sorted in descending order based on the calculated Euclidean distance and vector angle, and then the two sorting results are comprehensively sorted with each accounting for 50% of the weight.

[0029] The present invention also provides a device for screening potential products, the device comprising:

[0030] Processor; and

[0031] A memory arranged to store computer executable instructions which, when executed, cause the processor to perform the operations of the above-described method.

[0032] The present invention also provides a computer readable medium storing instructions, which, when executed, cause the system to perform the operations of the above method.

[0033] The method and device for screening potential products of the present invention utilize commodity data in combination with corresponding algorithms to construct triple screening (primary screening, fine screening, and final screening), and conduct multi-dimensional and comprehensive evaluations on the commodities in the potential product pool and the target commodities in terms of similarity, fit, and similarity in the commodity matrix, thereby being able to more efficiently, objectively, and accurately select substitutes for the target commodities (potential explosive products), greatly reducing the time for research and analysis of enterprises during potential explosive screening, avoiding the subjectivity of operational personnel, and improving the objectivity and accuracy of product selection. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0035] Figure 1 A schematic diagram showing a flow chart of a method for potential product screening according to an embodiment of the present invention;

[0036] Figure 2 The functional modules of an exemplary system that can be used in various embodiments of the present invention are shown.

[0037] The same or similar reference numerals in the drawings represent the same or similar components. DETAILED DESCRIPTION

[0038] The present application is described in further detail below in conjunction with the accompanying drawings.

[0039] In a typical configuration of the present invention, the terminal, the device of the service network and the trusted party each include one or more processors (eg, a central processing unit (CPU)), an input / output interface, a network interface and a memory.

[0040] Memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash memory. Memory is an example of a computer-readable medium.

[0041] Computer readable media include permanent and non-permanent, removable and non-removable media and can store information by any method or technology. The information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, Phase-Change Memory (PCM), Programmable Random Access Memory (PRAM), Static Random-Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read-Only Memory (ROM), Electrically-Erasable Programmable Read-Only Memory (EEPROM), Flash Memory or other memory technology, Compact Disc Read-Only Memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0042] The device referred to in the present invention includes but is not limited to user equipment, network equipment, or equipment formed by integrating user equipment and network equipment through a network. The user equipment includes but is not limited to any mobile electronic product that can interact with a user (for example, interact with a user through a touchpad), such as a smart phone, a tablet computer, etc. The mobile electronic product can use any operating system, such as an Android operating system, an iOS operating system, etc. Among them, the network device includes an electronic device that can automatically perform numerical calculations and information processing according to pre-set or stored instructions, and its hardware includes but is not limited to a microprocessor, an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a programmable logic device (Programmable Logic Device, PLD), a field programmable gate array (Field Programmable Gate Array, FPGA), a digital signal processor (Digital Signal Processor, DSP), an embedded device, etc. The network device includes but is not limited to a computer, a network host, a single network server, a plurality of network server sets or a cloud composed of a plurality of servers; here, the cloud is composed of a large number of computers or network servers based on cloud computing (Cloud Computing), wherein cloud computing is a kind of distributed computing, a virtual supercomputer composed of a group of loosely coupled computer sets. The network includes but is not limited to the Internet, a wide area network, a metropolitan area network, a local area network, a VPN network, a wireless ad hoc network, etc. Preferably, the device may also be a program running on the user device, the network device, or a device formed by integrating the user device and the network device, the network device, the touch terminal, or the network device and the touch terminal through a network.

[0043] Of course, those skilled in the art should understand that the above-mentioned devices are only examples, and other existing or future devices that are applicable to the present invention should also be included in the scope of protection of the present invention and are included here by reference.

[0044] In the description of the embodiments of the present invention, “plurality” means two or more, unless otherwise clearly and specifically defined.

[0045] For the common problem of potential explosive screening in the e-commerce field, for example, a brand has a hot product that has been on the market for many years, and the market area is currently saturated. At this time, it is necessary to screen suitable products from the potential product pool to be used as subsequent products for market promotion. If we only rely on the experience of the operators, as individual operators usually make subjective judgments based on their experience, this increases the uncertainty of the marketing strategy and often even has a negative impact.

[0046] The core idea of ​​the present invention is to select the required products from the potential product pool in a scientific way during the commodity operation process. The selection process should be scientific and reasonable to avoid subjective judgment, and it should also be able to achieve specific operational sales goals. Through three rounds of funnel screening, statistical indicators and algorithm indicators are used to screen out the potential products that best match the target products, thereby achieving the purpose of scientific product selection.

[0047] Figure 1 A schematic flow chart of a method for screening potential products according to an embodiment of the present invention is shown, comprising the following steps:

[0048] Step 1: Determine the indicators for product screening and standardize the indicators of the target products and products in the potential product pool.

[0049] The index items used for product screening can be selected from various data collected by the products, such as access data, sales data, etc. Usually, relevant data are collected daily. The index items that can be used in this embodiment include but are not limited to: exposure number (IM), page views (PV), number of users (UV), number of clicks (UV), collection and addition number (CP), sales volume (SV), sales amount (GMV), price (price), and click-through rate (CK).

[0050] The normalization method used in this embodiment is maximum and minimum normalization, and the formula for normalizing the index items is:

[0051]

[0052] Among them, x is any original data in the indicator item, X norm is the normalized data, x min is the minimum value of the original data in the indicator item, x max It is the maximum value of the original data in the indicator item.

[0053] Step 2: Calculate the total similarity between each product in the potential product pool and the target product based on each indicator item, and select a preset number of products with the highest total similarity to form a preliminary product set.

[0054] This step is the first level of screening for potential products, specifically the screening of potential products based on similarity, including:

[0055] The data of all the index items based on the target commodity are subjected to PCA principal component analysis, and the data are subjected to dimensionality reduction, such as factor analysis using SPSS, Matlab, Orgin, etc. In the present embodiment, the correlation matrix is ​​selected for analysis, so as to obtain the total variance explanation and the component matrix. The principal component (usually the principal component with an eigenvalue greater than 1) is selected from the total variance explanation, and the coefficient of the principal component corresponding to the index item is calculated in combination with the load coefficient of the principal component corresponding to the index item in the component matrix, and the formula is: the square root of the eigenvalue of the load coefficient / principal component of the index item. For each index item, the coefficient corresponding to each principal component is weighted averaged with the variance percentage of the eigenvalue of the corresponding principal component as the weight, and the weight coefficient of the index item is calculated. Finally, the weight coefficient of each index item is normalized, and the weight value of each index item is finally obtained.

[0056] Calculate the similarity between each product in the potential product pool and each indicator item of the target product by using the DTW (Dynamic Time Warping) algorithm;

[0057] For each product in the potential product pool, the similarity of each index item is multiplied by the weight value of the corresponding index item and the sum is calculated, so as to obtain the total similarity between the product and the target product.

[0058] Finally, the products in the potential product pool are sorted in descending order according to the total similarity, and a preset number of products with the highest total similarity are selected to form a preliminary product set, thereby completing the first level of similarity-based potential product screening. The size of the preset number can be determined according to the current size of the potential product pool, and can usually be preset to 20% of the number of products in the potential product pool.

[0059] Step 3: Evaluate the trends, periodicity, product relevance and / or product cannibalization of the products in the initially screened product set, and select products that meet preset conditions to form a selected product set.

[0060] This step is the second level of screening for potential products, specifically the screening of potential products based on compatibility, including:

[0061] For the evaluation of trend, trend is used to indicate the trend of the indicator items of the commodity during the sales process, whether the data is getting bigger or smaller, so it is necessary to use trend indicators to quantify the trend in the commodity sales process. The method for calculating trend in this embodiment is to calculate the slope of the trend component. First, use STL decomposition for each indicator item of the commodity in the initial screening commodity set, extract the trend component (Trend) from the decomposition result, and then calculate the slope of the trend component by linear regression or simple difference of the trend component. If the slope is positive, it means that the corresponding indicator item of the commodity tends to rise. If the slope is negative, it means that the corresponding indicator item of the commodity tends to decline. When screening potential products, it is usually necessary to select commodities with positive trends.

[0062] For the evaluation of periodicity, periodicity is also called seasonality. In potential product screening, the target product may be a product with strong periodicity. Therefore, when screening potential products, it is also necessary to select potential products with similar periodicity rules and periodicity strength. First, use STL decomposition for each indicator item of the products in the initial screening product set, and then calculate the following evaluation indicators:

[0063] 1. The amplitude of the seasonal component. The amplitude represents the maximum distance that the seasonal component deviates from the equilibrium position during its cycle, which reflects the intensity of the periodic change.

[0064] 2. Variance of seasonal components. Variance indicates the degree of dispersion of seasonal components within their cycles. It can also reflect the intensity of cyclical changes. The larger the variance, the more obvious the cyclical changes of seasonal components.

[0065] 3. Seasonal intensity index. The seasonal intensity index is usually defined as the ratio of the variance of the residual term to the variance of the data after removing the trend, that is, Var(R(t)) / Var(S(t)+R(t)), where R(t) represents the residual value at time t, and S(t) represents the seasonal term value at time t. The closer this ratio is to 1, the higher the proportion of seasonal components in the data and the stronger the periodicity; conversely, the closer the ratio is to 0, the lower the proportion of seasonal components in the data and the weaker the periodicity.

[0066] 4. Seasonal cycle peaks and troughs. The peaks represent the maximum value of the seasonal component in its cycle, while the troughs represent the minimum value. By calculating the distance between the peaks and troughs (i.e., amplitude) and the time points when they occur, we can further understand the law of periodic changes.

[0067] When screening potential products, try to select products with cyclical indicators similar to those of the target product, or select based on the ranking of indicator items.

[0068] Regarding the evaluation of product relevance, the analysis of product relevance is different from the aforementioned similarity between commodities. In the relevance analysis, the FP-Growth algorithm in the association rule algorithm is used to calculate the relevance between each commodity in the preliminary screening commodity set and the target commodity. The evaluation indicators of relevance include:

[0069] 1. Support:

[0070] Support indicates the probability that product A and product B are purchased at the same time. It shows how representative this rule is in all transactions. The greater the support, the more important the association rule is.

[0071] Calculation formula: Number of orders for purchasing both product A and product B / total number of purchase orders.

[0072] 2. Confidence:

[0073] Confidence indicates the conditional probability of purchasing product B after purchasing product A, that is, the probability of purchasing product B because of purchasing product A.

[0074] Calculation formula: Number of orders for both product A and product B / Number of orders for product A.

[0075] 3. Lift:

[0076] The lift indicates the effect of purchasing product A first on purchasing product B, and is used to determine whether a product combination has real value. If the number of times the combined product is purchased is higher than the number of times the individual products are purchased, it means that the combination is effective; otherwise, it is ineffective.

[0077] Calculation formula: Support / ((Number of times product A is purchased / Total number of purchase orders)×(Number of times product B is purchased / Total number of purchase orders)).

[0078] In the above calculation formula, product A represents the target product, and product B represents a product in the initial screening product set. The thresholds of the above three indicators need to be adjusted in actual calculations so that an appropriate amount of potential products can be screened out from the initial screening product set. If the above three indicators are set too high, it will not be possible to screen out enough products from the initial screening product set. If the indicators are too low, the purpose of screening may not be achieved. Alternatively, selection can be made based on the ranking of the indicator items.

[0079] For the evaluation of product cannibalization, mutual cannibalization of products refers to the correlation between commodities. In this embodiment, it specifically refers to the correlation between any two commodities in the initial screening commodity set. For example, if there are two commodities A and B that are highly negatively correlated, then when there is a commodity C that needs to be selected as a potential substitute, it is necessary to carefully consider commodity A, because the hot-selling of commodity A will lead to the sluggish sales of commodity B. When analyzing the correlation, it is necessary to perform pairwise correlation analysis on all commodities in the potential product pool. Specifically, data related to commodity sales, such as sales volume, can be used for analysis. Then the relationship between commodities is judged based on the indicators between them, which specifically include the following evaluation indicators:

[0080] 1. Significance: Significance is used to indicate whether two commodities are related. In this embodiment, the Pearson correlation coefficient is used to define the correlation between the data of the two commodities, and a value less than 0.05 indicates a strong correlation, and a value greater than 0.05 indicates a weak correlation.

[0081] 2. Regression coefficient. The regression coefficient indicates whether two commodities are positively correlated or negatively correlated. In this embodiment, a least squares formula is used to perform a linear regression equation for the data between the two commodities, and it is set that if the regression coefficient is greater than 0, it indicates that the two commodities are positively correlated, and if the regression coefficient is less than 0, it indicates that the two commodities are negatively correlated.

[0082] For the above four evaluations, some or all of them can be selected as needed to conduct the second level of potential product screening based on fit. For each evaluation, based on their respective preset product selection conditions, a group of selected products will be generated respectively. At this time, the intersection of each group is taken as the result of the second level of screening, thereby forming a selected product set. Similarly, in order to be able to screen out an appropriate amount of potential products from the initial screening product set, the preset product selection conditions for each of the above evaluations can be relaxed or tightened according to actual conditions.

[0083] Step 4: quantize the target product and the products in the selected product set into a coordinate system, and select a preset number of products to form a final selected product set based on the Euclidean distance and vector angle between each product in the selected product set and the target product.

[0084] This step is the third level of screening for potential products, specifically the screening of potential products based on the commodity matrix, including:

[0085] The mean value of each indicator item in the target product and the products in the selected product set within a preset time period is calculated to form a product-indicator item data matrix, wherein the preset time period can be selected from the hot-selling time period of the target product, such as the promotion period of each e-commerce platform, or a recent period of time, such as the last two weeks.

[0086] Based on the data matrix, PCA principal component analysis is used to reduce the dimension of the data, such as using SPSS, Matlab, Orgin, etc. for factor analysis. In this embodiment, the covariance matrix is ​​selected for analysis to obtain the total variance explanation and component matrix, including the eigenvalue and eigenvector of each principal component. The eigenvalue of the principal component represents its variance contribution rate, that is, its ability to explain the original data, and the eigenvector of the principal component represents its direction, that is, the projection of the original data on the principal component. According to the size of the eigenvalue, the principal components corresponding to the first few larger eigenvalues ​​are selected as reference indicators. The number of principal components can be determined according to the actual situation, and the principal components whose cumulative contribution rate reaches a preset level are usually selected, such as the cumulative contribution rate reaches more than 85%.

[0087] Quantify the target products and the products in the selected product set into a coordinate system, that is, construct a product matrix with each reference indicator item as a dimension, so that each product has its own corresponding position in the product matrix. Specifically, project the data in the data matrix onto the selected principal component (i.e., the reference indicator item) to obtain a new data matrix of the product-reference indicator item after dimensionality reduction. This matrix is ​​the product matrix, in which each row represents a product and each column represents a reference indicator item, i.e., a principal component. In the product matrix, two to three principal components are usually retained, that is, the matrix is ​​generally a two-dimensional plane matrix or a three-dimensional space matrix. Construct a coordinate system based on the product matrix, in which each reference indicator item is a dimension, and project the data of the reference indicator item of each product into the coordinate system, that is, determine the position of the product in the coordinate system.

[0088] The Euclidean distance between each product in the selected product set and the target product is calculated, and then the products in the selected product set are sorted in ascending order based on their corresponding Euclidean distances.

[0089] The vector angle of the Euclidean distance between each product in the selected product set and the target product is calculated. In this embodiment, the cosine similarity is used to calculate the above vector angle to measure the similarity between the products in the selected product set and the target product. The smaller the vector angle, that is, the greater the cosine similarity, the higher the similarity between the products, and vice versa. Then, the products in the selected product set are sorted in ascending order based on their corresponding vector angles, or in descending order based on cosine similarity.

[0090] The above-mentioned sorting results based on Euclidean distance and cosine similarity are comprehensively sorted with each accounting for 50% of the weight. In other words, the comprehensive sorting can be regarded as taking the average of the sequence numbers of the products in the selected product set in the above two sorting results as the value of the comprehensive sorting, and sorting the products in the selected product set in ascending order based on the value. Finally, the first preset number of products are selected to form the final selection product set, thereby completing the third level of potential product screening based on the product matrix.

[0091] This embodiment further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer code. When the computer code is executed, the method described in any of the preceding items is executed.

[0092] This embodiment further provides a computer program product. When the computer program product is executed by a computer device, the method described in any of the preceding items is executed.

[0093] This embodiment further provides a computer device, the computer device comprising:

[0094] one or more processors;

[0095] a memory for storing one or more computer programs;

[0096] When the one or more computer programs are executed by the one or more processors, the one or more processors are caused to implement the method as described in any of the preceding items.

[0097] Figure 2 An exemplary system is shown that can be used to implement the various embodiments described herein.

[0098] like Figure 2 As shown, in some embodiments, the system 1000 can be used as any user terminal device in each of the embodiments. In some embodiments, the system 1000 may include one or more computer-readable media (e.g., system memory or NVM / storage device 1020) having instructions and one or more processors (e.g., (one or more) processors 1005) coupled to the one or more computer-readable media and configured to execute instructions to implement modules to perform the actions described in the present invention.

[0099] For one embodiment, the system control module 1010 may include any suitable interface controller to provide any suitable interface to at least one of the processor(s) 1005 and / or any suitable device or component in communication with the system control module 1010 .

[0100] The system control module 1010 may include a memory controller module 1030 to provide an interface to the system memory 1015. The memory controller module 1030 may be a hardware module, a software module, and / or a firmware module.

[0101] The system memory 1015 may be used, for example, to load and store data and / or instructions for the system 1000. For one embodiment, the system memory 1015 may include any suitable volatile memory, such as a suitable DRAM. In some embodiments, the system memory 1015 may include double data rate type four synchronous dynamic random access memory (DDR4 SDRAM).

[0102] For one embodiment, system control module 1010 may include one or more input / output (I / O) controllers to provide interfaces to NVM / storage device 1020 and communication interface(s) 1025 .

[0103] For example, NVM / storage device 1020 may be used to store data and / or instructions. NVM / storage device 1020 may include any suitable non-volatile memory (e.g., flash memory) and / or may include any suitable non-volatile storage device(s) (e.g., one or more hard disk drives (HDDs), one or more compact disk (CD) drives, and / or one or more digital versatile disk (DVD) drives).

[0104] NVM / storage device 1020 may include storage resources that are physically part of the device on which system 1000 is installed, or it may be accessible to the device without being part of the device. For example, NVM / storage device 1020 may be accessed via communication interface(s) 1025 over a network.

[0105] Communication interface(s) 1025 may provide an interface for system 1000 to communicate over one or more networks and / or with any other suitable devices. System 1000 may wirelessly communicate with one or more components of a wireless network in accordance with any of one or more wireless network standards and / or protocols.

[0106] For one embodiment, at least one of the processor(s) 1005 may be packaged together with the logic of one or more controllers (e.g., memory controller module 1030) of the system control module 1010. For one embodiment, at least one of the processor(s) 1005 may be packaged together with the logic of one or more controllers of the system control module 1010 to form a system-in-package (SiP). For one embodiment, at least one of the processor(s) 1005 may be integrated on the same die with the logic of one or more controllers of the system control module 1010. For one embodiment, at least one of the processor(s) 1005 may be integrated on the same die with the logic of one or more controllers of the system control module 1010 to form a system on chip (SoC).

[0107] In various embodiments, the system 1000 may be, but is not limited to: a server, a workstation, a desktop computing device, or a mobile computing device (e.g., a laptop computing device, a handheld computing device, a tablet computer, a netbook, etc.). In various embodiments, the system 1000 may have more or fewer components and / or a different architecture. For example, in some embodiments, the system 1000 includes one or more cameras, a keyboard, a liquid crystal display (LCD) screen (including a touch screen display), a non-volatile memory port, multiple antennas, a graphics chip, an application specific integrated circuit (ASIC), and a speaker.

[0108] It should be noted that the present invention can be implemented in software and / or a combination of software and hardware, for example, can be implemented using an application specific integrated circuit (ASIC), a general purpose computer or any other similar hardware device. In one embodiment, the software program of the present invention can be executed by a processor to implement the steps or functions described above. Similarly, the software program of the present invention (including related data structures) can be stored in a computer readable recording medium, for example, a RAM memory, a magnetic or optical drive or a floppy disk and the like. In addition, some steps or functions of the present invention can be implemented using hardware, for example, as a circuit that cooperates with a processor to perform each step or function.

[0109] In addition, a part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of computer program instructions in computer-readable media includes, but is not limited to, source files, executable files, installation package files, etc., and accordingly, the way in which computer program instructions are executed by a computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0110] Communication media include media by which communication signals containing, for example, computer readable instructions, data structures, program modules, or other data are transmitted from one system to another. Communication media may include guided transmission media such as cables and wires (e.g., fiber optic, coaxial, etc.) and wireless (unguided transmission) media that can propagate energy waves, such as acoustic, electromagnetic, RF, microwave, and infrared. Computer readable instructions, data structures, program modules, or other data may be embodied as a modulated data signal in, for example, a wireless medium such as a carrier wave or similar mechanism such as embodied as part of spread spectrum technology. The term "modulated data signal" refers to a signal whose one or more characteristics are changed or set in such a manner as to encode information in the signal. Modulation may be analog, digital, or a hybrid modulation technique.

[0111] By way of example and not limitation, computer-readable storage media may include volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data. For example, computer-readable storage media include, but are not limited to, volatile memory, such as random access memory (RAM, DRAM, SRAM); and non-volatile memory, such as flash memory, various read-only memories (ROM, PROM, EPROM, EEPROM), magnetic and ferromagnetic / ferroelectric memories (MRAM, FeRAM); and magnetic and optical storage devices (hard disks, magnetic tapes, CDs, DVDs); or other media now known or later developed that can store computer-readable information / data for use by a computer system.

[0112] Here, according to one embodiment of the present invention, a device is included, which includes a memory for storing computer program instructions and a processor for executing the program instructions, wherein, when the computer program instructions are executed by the processor, the device is triggered to run the methods and / or technical solutions based on the aforementioned multiple embodiments of the present invention.

[0113] It is obvious to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential features of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the present invention is defined by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any figure mark in the claims should not be regarded as limiting the claims involved. In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the device claim can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

Claims

1. A method for screening potential products, characterized in that: include: Determine the indicators for product screening and standardize the indicators of target products and products in the potential product pool; Calculating the total similarity between each product in the potential product pool and the target product based on each indicator item, and selecting a preset number of products with the highest total similarity to form a preliminary product set; Evaluate the trends, periodicity, product relevance and / or product cannibalization of the commodities in the initially screened commodity set, and select commodities meeting the preset conditions to form a selected commodity set; The target product and the products in the selected product set are quantized into a coordinate system, and a preset number of products are selected to form a final selected product set according to the Euclidean distance and vector angle between each product in the selected product set and the target product.

2. The method according to claim 1, characterized in that: The calculating the total similarity between each product in the potential product pool and the target product based on each indicator item includes: Based on the data of all index items of the target product, PCA principal component analysis is used to calculate the weight of each index item; Calculate the similarity between each product in the potential product pool and each indicator item of the target product by using the DTW algorithm; For each product in the potential product pool, the similarity of each index item is multiplied by the weight of the corresponding index item and the sum is calculated, so as to obtain the total similarity between the product and the target product.

3. The method according to claim 1, characterized in that Conduct trend assessment on the commodities in the initial screening commodity set, including: Use STL decomposition for each index item of the commodities in the initial screening commodity set, extract the trend component from the decomposition result, and then calculate the slope of the trend component. If the slope is positive, it means that the corresponding index item of the commodity tends to increase, and if the slope is negative, it means that the corresponding index item of the commodity tends to decrease.

4. The method according to claim 1, characterized in that Conduct periodic evaluations on the products in the initial screening product set, including: Calculating the periodicity evaluation index of each index item of the commodities in the initially screened commodity set and the target commodity, so as to screen commodities that are closer to the target commodity in periodicity; The periodicity evaluation indicators include: amplitude of seasonal components, variance of seasonal components, seasonal intensity index, and seasonal cycle peaks / troughs.

5. The method according to claim 1, characterized in that Evaluate the product relevance of the products in the initial screening product set, including: For each product in the initially screened product set, the support, confidence and lift between the product and the target product are calculated to screen products that are more closely related to the target product.

6. The method according to claim 1, characterized in that Conduct product cannibalization assessment on the products in the initial screening product set, including: For any two products in the potential product pool, the significance and regression coefficient of the two are calculated to exclude products with significant negative correlation.

7. The method according to claim 1, characterized in that The step of quantizing the target product and the products in the selected product set into a coordinate system includes: Calculating the mean value of each indicator item in the target product and the products in the selected product set within a preset time period, thereby forming a product-indicator item data matrix; Based on the data matrix, PCA principal component analysis is used to select the principal component that meets the preset conditions as the reference indicator item; Projecting the data in the data matrix onto the selected principal components to obtain a commodity matrix of commodity-reference indicator items; A coordinate system is established according to the commodity matrix, so as to obtain the position of each commodity in the coordinate system.

8. The method according to claim 1, characterized in that: The step of selecting a preset number of commodities to form a final selection commodity set according to the Euclidean distance and vector angle between each commodity in the selected commodity set and the target commodity, comprises: The commodities in the selected commodity set are sorted in descending order based on the calculated Euclidean distance and vector angle, and then the two sorting results are comprehensively sorted with each accounting for 50% of the weight.

9. A device for screening potential products, wherein: The device comprises: Processor; and A memory arranged to store computer executable instructions which, when executed, cause the processor to perform the operations of the method according to any one of claims 1 to 8.

10. A computer readable medium storing instructions which, when executed, cause a system to perform the operations of the method according to any one of claims 1 to 8.

Images